Every model

Name: YFarmX Model Identity: the full model catalogue
Creator: YFarmX
License: https://yfarmx.com/ai/models/data/

Most models are exactly what the label says. The 126 where the measurement adds something the label leaves out, or leaves a question open, come first.

In the catalogue: 486
Measured so far: 280
Worth a look: 126

measurement had something to addwithdrawnconfirmed the labelvariant or aliasnot measured yet

Showing all 486 entries.

AionLabs: Aion-2.0aion-labs/aion-2.0its own Aion Labs tokenizer groupModerate

Maker: Aion Labs
Label on the catalogue: no family named
What the measurement says: its own Aion Labs tokenizer group
Why moderate: an exact fingerprint match with one sibling only, and no second signal of a different kind yet
Fingerprint: tk_d3c6ae80 · shared with 1 other model
Context: 131,072
Max output: 32,768
Modalities: text->text
Prompt price: $0.80 / M tokens
Entered the catalogue: 23 February 2026
Last tested: 3 September 2026

Full record JSON Shares with AionLabs: Aion-3.0-Mini

AionLabs: Aion-3.0aion-labs/aion-3.0builds on the Z.ai tokenizerModerate

Maker: Aion Labs
Label on the catalogue: no family named
What the measurement says: builds on the Z.ai tokenizer
Why moderate: one template-boundary shift from the group rather than an exact signature member
Fingerprint: tk_c018f9f2 · unique so far
Context: 131,072
Max output: 32,768
Modalities: text->text
Prompt price: $3.00 / M tokens
Entered the catalogue: 7 July 2026
Last tested: 3 September 2026

Full record JSON

AionLabs: Aion-3.0-Miniaion-labs/aion-3.0-miniits own Aion Labs tokenizer groupModerate

Maker: Aion Labs
Label on the catalogue: no family named
What the measurement says: its own Aion Labs tokenizer group
Why moderate: an exact fingerprint match with one sibling only, and no second signal of a different kind yet
Fingerprint: tk_d3c6ae80 · shared with 1 other model
Context: 131,072
Max output: 32,768
Modalities: text->text
Prompt price: $0.70 / M tokens
Entered the catalogue: 7 July 2026
Last tested: 3 September 2026

Full record JSON Shares with AionLabs: Aion-2.0

AionLabs: Aion-RP 1.0 (8B)aion-labs/aion-rp-llama-3.1-8bmeasured, matches nothing else yetMeasured

Maker: Aion Labs
Label on the catalogue: no family named
What the measurement says: measured, matches nothing else yet
Fingerprint: tk_559886c2 · unique so far
Context: 32,768
Max output: 29,491
Modalities: text->text
Prompt price: $0.80 / M tokens
Entered the catalogue: 4 February 2025
Last tested: 3 September 2026

Full record JSON

AllenAI: Olmo 3 32B Thinkallenai/olmo-3-32b-thinkwithdrawn from the catalogueNo reading

Maker: Ai2
Label on the catalogue: no family named
What the measurement says: withdrawn from the catalogue
Context: 65,536
Max output: 65,536
Modalities: text->text
Prompt price: $0.15 / M tokens
Entered the catalogue: 21 November 2025
Last tested: not yet

Full record JSON

Amazon: Nova 2 Liteamazon/nova-2-lite-v1measured, matches nothing else yetMeasured

Maker: Amazon
Label on the catalogue: Nova
What the measurement says: measured, matches nothing else yet
Fingerprint: tk_f04fd33e · unique so far
Context: 1,000,000
Max output: 65,535
Modalities: text+image+file+video->text
Prompt price: $0.30 / M tokens
Entered the catalogue: 2 December 2025
Last tested: 21 August 2026

Full record JSON

Amazon: Nova Premier 1.0amazon/nova-premier-v1measured, matches nothing else yetMeasured

Maker: Amazon
Label on the catalogue: Nova
What the measurement says: measured, matches nothing else yet
Fingerprint: tk_79cd40d1 · unique so far
Context: 1,000,000
Max output: 32,000
Modalities: text+image->text
Prompt price: $2.50 / M tokens
Entered the catalogue: 31 October 2025
Last tested: 3 September 2026

Full record JSON

Anthropic: Claude Opus 4.7anthropic/claude-opus-4.7measured, matches nothing else yetMeasured

Maker: Anthropic
Label on the catalogue: Claude
What the measurement says: measured, matches nothing else yet
Context: 1,000,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $5.00 / M tokens
Entered the catalogue: 16 April 2026
Last tested: 3 September 2026

Full record JSON

Anthropic: Claude Opus 4.7 (Fast)anthropic/claude-opus-4.7-fastwithdrawn from the catalogueNo reading

Maker: Anthropic
Label on the catalogue: Claude
What the measurement says: withdrawn from the catalogue
Context: 1,000,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $30.0 / M tokens
Entered the catalogue: 12 May 2026
Last tested: not yet

Full record JSON

Anthropic: Claude Opus 4.8 (Fast)anthropic/claude-opus-4.8-fastwithdrawn from the catalogueNo reading

Maker: Anthropic
Label on the catalogue: Claude
What the measurement says: withdrawn from the catalogue
Context: 1,000,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $10.0 / M tokens
Entered the catalogue: 27 May 2026
Last tested: not yet

Full record JSON

Arcee AI: Trinity Large Thinkingarcee-ai/trinity-large-thinkingmeasured, matches nothing else yetMeasured

Maker: Arcee AI
Label on the catalogue: no family named
What the measurement says: measured, matches nothing else yet
Fingerprint: tk_a8b24bf6 · unique so far
Context: 262,144
Max output: 80,000
Modalities: text->text
Prompt price: $0.25 / M tokens
Entered the catalogue: 1 April 2026
Last tested: 21 August 2026

Full record JSON

Arcee AI: Virtuoso Largearcee-ai/virtuoso-largewithdrawn from the catalogueNo reading

Maker: Arcee AI
Label on the catalogue: no family named
What the measurement says: withdrawn from the catalogue
Context: 131,072
Max output: 64,000
Modalities: text->text
Prompt price: $0.75 / M tokens
Entered the catalogue: 5 May 2025
Last tested: not yet

Full record JSON

Baidu: ERNIE 4.5 VL 424B A47B baidu/ernie-4.5-vl-424b-a47bmeasured, matches nothing else yetMeasured

Maker: Baidu
Label on the catalogue: no family named
What the measurement says: measured, matches nothing else yet
Fingerprint: tk_41571a13 · unique so far
Context: 123,000
Max output: 16,000
Modalities: text+image->text
Prompt price: $0.42 / M tokens
Entered the catalogue: 30 June 2025
Last tested: 22 August 2026

Full record JSON

ByteDance Seed: Seed 1.6bytedance-seed/seed-1.6its own ByteDance Seed tokenizer groupVery high

Maker: ByteDance Seed
Label on the catalogue: no family named
What the measurement says: its own ByteDance Seed tokenizer group
Why very high: an exact fingerprint shared with 5 models and an identical API contract inside the same group: two signals of different kinds agree
Fingerprint: tk_25bf52d0 · shared with 5 other models
Context: 262,144
Max output: 32,768
Modalities: text+image+video->text
Prompt price: $0.25 / M tokens
Entered the catalogue: 23 December 2025
Last tested: 21 August 2026

Full record JSON Shares with ByteDance Seed: Seed 2.1 Turbo

ByteDance Seed: Seed 1.6 Flashbytedance-seed/seed-1.6-flashits own ByteDance Seed tokenizer groupVery high

Maker: ByteDance Seed
Label on the catalogue: no family named
What the measurement says: its own ByteDance Seed tokenizer group
Why very high: an exact fingerprint shared with 5 models and an identical API contract inside the same group: two signals of different kinds agree
Fingerprint: tk_25bf52d0 · shared with 5 other models
Context: 262,144
Max output: 32,768
Modalities: text+image+video->text
Prompt price: $0.07 / M tokens
Entered the catalogue: 23 December 2025
Last tested: 21 August 2026

Full record JSON Shares with ByteDance Seed: Seed 2.1 Turbo

ByteDance Seed: Seed 2.1 Turbobytedance-seed/seed-2-1-turboits own ByteDance Seed tokenizer groupHigh

Maker: ByteDance Seed
Label on the catalogue: no family named
What the measurement says: its own ByteDance Seed tokenizer group
Why high: an exact fingerprint shared with 5 models
Fingerprint: tk_25bf52d0 · shared with 5 other models
Context: 262,144
Max output: 235,929
Modalities: text+image+video->text
Prompt price: $0.50 / M tokens
Entered the catalogue: 12 August 2026
Last tested: 22 August 2026

Full record JSON Shares with ByteDance Seed: Seed-2.0-Code

ByteDance Seed: Seed-2.0-Codebytedance-seed/seed-2.0-codeits own ByteDance Seed tokenizer groupHigh

Maker: ByteDance Seed
Label on the catalogue: no family named
What the measurement says: its own ByteDance Seed tokenizer group
Why high: an exact fingerprint shared with 5 models
Fingerprint: tk_25bf52d0 · shared with 5 other models
Context: 262,144
Max output: 131,072
Modalities: text+image+video->text
Prompt price: $0.50 / M tokens
Entered the catalogue: 12 August 2026
Last tested: 22 August 2026

Full record JSON Shares with ByteDance Seed: Seed 2.1 Turbo

ByteDance Seed: Seed-2.0-Litebytedance-seed/seed-2.0-liteits own ByteDance Seed tokenizer groupHigh

Maker: ByteDance Seed
Label on the catalogue: no family named
What the measurement says: its own ByteDance Seed tokenizer group
Why high: an exact fingerprint shared with 5 models
Fingerprint: tk_25bf52d0 · shared with 5 other models
Context: 262,144
Max output: 131,072
Modalities: text+image+video->text
Prompt price: $0.25 / M tokens
Entered the catalogue: 10 March 2026
Last tested: 21 August 2026

Full record JSON Shares with ByteDance Seed: Seed 2.1 Turbo

ByteDance Seed: Seed-2.0-Minibytedance-seed/seed-2.0-miniits own ByteDance Seed tokenizer groupHigh

Maker: ByteDance Seed
Label on the catalogue: no family named
What the measurement says: its own ByteDance Seed tokenizer group
Why high: an exact fingerprint shared with 5 models
Fingerprint: tk_25bf52d0 · shared with 5 other models
Context: 262,144
Max output: 131,072
Modalities: text+image+video->text
Prompt price: $0.10 / M tokens
Entered the catalogue: 26 February 2026
Last tested: 21 August 2026

Full record JSON Shares with ByteDance Seed: Seed 2.1 Turbo

ByteDance: UI-TARS 7B bytedance/ui-tars-1.5-7bbuilds on the Qwen tokenizerHigh

Maker: Bytedance
Label on the catalogue: no family named
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 36 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_5410b38e · shared with 36 other models
Context: 128,000
Max output: 2,048
Modalities: text+image->text
Prompt price: $0.10 / M tokens
Entered the catalogue: 22 July 2025
Last tested: 21 August 2026

Full record JSON Shares with Dots Studio: Dots3-Note Preview (free)

Claude Opus 5 (Fast)anthropic/claude-opus-5-fastwithdrawn from the catalogueNo reading

Maker: Anthropic
Label on the catalogue: Claude
What the measurement says: withdrawn from the catalogue
Context: 1,000,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $10.0 / M tokens
Entered the catalogue: 24 July 2026
Last tested: not yet

Full record JSON

Cohere: Command Acohere/command-aits own Cohere tokenizer groupHigh

Maker: Cohere
Label on the catalogue: no family named
What the measurement says: its own Cohere tokenizer group
Why high: an exact fingerprint shared with 1 model that declares the same family, without a second signal of a different kind yet
Fingerprint: tk_2729e470 · shared with 1 other model
Context: 256,000
Max output: 8,192
Modalities: text->text
Prompt price: $2.50 / M tokens
Entered the catalogue: 13 March 2025
Last tested: 3 September 2026

Full record JSON Shares with Cohere: Command R7B (12-2024)

Cohere: North Mini Code (free)cohere/north-mini-code:freemeasured, matches nothing else yetMeasured

Maker: Cohere
Label on the catalogue: Cohere
What the measurement says: measured, matches nothing else yet
Fingerprint: tk_caaaa531 · unique so far
Context: 256,000
Max output: 64,000
Modalities: text->text
Prompt price: $0 / M tokens
Entered the catalogue: 17 June 2026
Last tested: 21 August 2026

Full record JSON

Deep Cogito: Cogito v2.1 671Bdeepcogito/cogito-v2.1-671bwithdrawn from the catalogueNo reading

Maker: Deepcogito
Label on the catalogue: no family named
What the measurement says: withdrawn from the catalogue
Context: 128,000
Max output: –
Modalities: text->text
Prompt price: $1.25 / M tokens
Entered the catalogue: 13 November 2025
Last tested: not yet

Full record JSON

DeepSeek: R1deepseek/deepseek-r1token accounting unreliable at this endpointNo reading

Maker: DeepSeek
Label on the catalogue: DeepSeek
What the measurement says: token accounting unreliable at this endpoint
Context: 64,000
Max output: 16,000
Modalities: text->text
Prompt price: $0.70 / M tokens
Entered the catalogue: 20 January 2025
Last tested: not yet

Full record JSON

DeepSeek: R1 Distill Llama 70Bdeepseek/deepseek-r1-distill-llama-70bits own DeepSeek tokenizer groupHigh

Maker: DeepSeek
Label on the catalogue: Llama3
What the measurement says: its own DeepSeek tokenizer group
Why high: an exact fingerprint shared with 1 model that declares the same family, without a second signal of a different kind yet
Fingerprint: tk_869dc1cf · shared with 1 other model
Context: 8,192
Max output: 7,372
Modalities: text->text
Prompt price: $0.80 / M tokens
Entered the catalogue: 23 January 2025
Last tested: 21 August 2026
Verified finding: The mismatch was traced to the serving layer, not the label. The model's own repository tokenizer, run over the same 50 strings offline, is Llama 3's exactly (50 of 50, vocabulary 128,256), so the catalogue's Llama3 tag is right about the weights. The endpoint…

Full record JSON Shares with DeepSeek: DeepSeek V3.1

Dots Studio: Dots3-Note Preview (free)dots-studio/dots-3-note-preview:freebuilds on the Qwen tokenizerHigh

Maker: Dots Studio
Label on the catalogue: no family named
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 36 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_5410b38e · shared with 36 other models
Context: 512,000
Max output: 460,800
Modalities: text+image->text
Prompt price: $0 / M tokens
Entered the catalogue: 14 August 2026
Last tested: 21 August 2026

Full record JSON Shares with Xiaomi: MiMo-V2.5

Google: Gemini 2.5 Flashgoogle/gemini-2.5-flashtoken accounting unreliable at this endpointNo reading

Maker: Google
Label on the catalogue: Gemini
What the measurement says: token accounting unreliable at this endpoint
Context: 1,048,576
Max output: 65,535
Modalities: text+image+file+audio+video->text
Prompt price: $0.30 / M tokens
Entered the catalogue: 17 June 2025
Last tested: 21 August 2026

Full record JSON

Google: Gemini 2.5 Pro Preview 05-06google/gemini-2.5-pro-preview-05-06withdrawn from the catalogue · measured as built on the Gemini tokenizerHigh

Maker: Google
Label on the catalogue: Gemini
What the measurement says: withdrawn from the catalogue · measured as built on the Gemini tokenizer
Why high: an exact fingerprint shared with 19 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_59ca250f · shared with 19 other models
Context: 1,048,576
Max output: 65,535
Modalities: text+image+file+audio+video->text
Prompt price: $1.25 / M tokens
Entered the catalogue: 7 May 2025
Last tested: 3 September 2026

Full record JSON Shares with Google: Gemini 3.8 Flash

Google: Gemma 2 27Bgoogle/gemma-2-27b-itmeasured, matches nothing else yetMeasured

Maker: Google
Label on the catalogue: Gemini
What the measurement says: measured, matches nothing else yet
Fingerprint: tk_a73edaf2 · unique so far
Context: 8,192
Max output: 2,048
Modalities: text->text
Prompt price: $0.65 / M tokens
Entered the catalogue: 13 July 2024
Last tested: 3 September 2026

Full record JSON

Google: Gemma 3n 4Bgoogle/gemma-3n-e4b-itwithdrawn from the catalogue · measured as built on the Gemini tokenizerHigh

Maker: Google
Label on the catalogue: no family named
What the measurement says: withdrawn from the catalogue · measured as built on the Gemini tokenizer
Why high: one template-boundary shift from a group whose members all declare the same family
Fingerprint: tk_a15512c7 · unique so far
Context: 32,768
Max output: –
Modalities: text->text
Prompt price: $0.06 / M tokens
Entered the catalogue: 20 May 2025
Last tested: 21 August 2026

Full record JSON

Google: Gemma 4 31B (batch)google/gemma-4-31b-it:batchwithdrawn from the catalogue · measured as built on the Gemma tokenizerHigh

Maker: Google
Label on the catalogue: Gemma
What the measurement says: withdrawn from the catalogue · measured as built on the Gemma tokenizer
Why high: inherited from google/gemma-4-31b-it: a serving variant shares its base model's tokenizer
Variant of: Google: Gemma 4 31B
Context: 262,144
Max output: 235,929
Modalities: text+image+video->text
Prompt price: $0.39 / M tokens
Entered the catalogue: 2 April 2026
Last tested: not yet

Full record JSON

Google: Lyria 3 Clip Previewgoogle/lyria-3-clip-previewmeasured, matches nothing else yetMeasured

Maker: Google
Label on the catalogue: no family named
What the measurement says: measured, matches nothing else yet
Context: 1,048,576
Max output: 65,536
Modalities: text+image->text+audio
Prompt price: $0 / M tokens
Entered the catalogue: 30 March 2026
Last tested: 3 September 2026

Full record JSON

Google: Lyria 3 Pro Previewgoogle/lyria-3-pro-previewtoken accounting unreliable at this endpointNo reading

Maker: Google
Label on the catalogue: no family named
What the measurement says: token accounting unreliable at this endpoint
Context: 1,048,576
Max output: 65,536
Modalities: text+image->text+audio
Prompt price: $0 / M tokens
Entered the catalogue: 30 March 2026
Last tested: 3 September 2026

Full record JSON

IBM: Granite 4.0 Microibm-granite/granite-4.0-h-microbuilds on the OpenAI cl100k tokenizerHigh

Maker: IBM
Label on the catalogue: no family named
What the measurement says: builds on the OpenAI cl100k tokenizer
Why high: an exact fingerprint shared with 3 models
Fingerprint: tk_ba918336 · shared with 3 other models
Context: 131,000
Max output: 117,900
Modalities: text->text
Prompt price: $0.02 / M tokens
Entered the catalogue: 20 October 2025
Last tested: 21 August 2026
Verified finding: Granite 4.0's endpoint counts match OpenAI's open cl100k_base encoding on all 50 strings, and its repository declares the matching 100,352-entry vocabulary. Microsoft's Phi-4 measures identically, which is why two rival labs share one signature group: both ado…

Full record JSON Shares with Microsoft: Phi 4

IBM: Granite 4.1 8Bibm-granite/granite-4.1-8bwithdrawn from the catalogue · measured as built on the OpenAI cl100k tokenizerHigh

Maker: IBM
Label on the catalogue: no family named
What the measurement says: withdrawn from the catalogue · measured as built on the OpenAI cl100k tokenizer
Why high: an exact fingerprint shared with 3 models
Fingerprint: tk_ba918336 · shared with 3 other models
Context: 131,072
Max output: 117,964
Modalities: text->text
Prompt price: $0.05 / M tokens
Entered the catalogue: 30 April 2026
Last tested: 21 August 2026
Verified finding: Granite 4.1's endpoint counts match OpenAI's open cl100k_base encoding on all 50 strings, the same result as Granite 4.0 and Microsoft's Phi-4. The three share one signature group because both labs adopted the tokenizer OpenAI released as open source with tikt…

Full record JSON Shares with IBM: Granite 4.0 Micro

IBM: Granite 4.2 8Bibm-granite/granite-4.2-8bmeasured, matches nothing else yetMeasured

Maker: IBM
Label on the catalogue: no family named
What the measurement says: measured, matches nothing else yet
Fingerprint: tk_b6cc7610 · unique so far
Context: 131,072
Max output: 117,964
Modalities: text->text
Prompt price: $0.06 / M tokens
Entered the catalogue: 31 August 2026
Last tested: 3 September 2026

Full record JSON

Inception: Mercury 2inception/mercury-2token accounting unreliable at this endpointNo reading

Maker: Inception
Label on the catalogue: no family named
What the measurement says: token accounting unreliable at this endpoint
Context: 128,000
Max output: 50,000
Modalities: text->text
Prompt price: $0.25 / M tokens
Entered the catalogue: 4 March 2026
Last tested: not yet

Full record JSON

Inception: Mercury 2.5 Previewinception/mercury-2.5-previewwithdrawn from the catalogueNo reading

Maker: Inception
Label on the catalogue: no family named
What the measurement says: withdrawn from the catalogue
Context: 260,000
Max output: 65,536
Modalities: text->text
Prompt price: $0.04 / M tokens
Entered the catalogue: 31 August 2026
Last tested: 3 September 2026

Full record JSON

inclusionAI: Ling 3.0 Flashinclusionai/ling-3.0-flashits own InclusionAI tokenizer groupHigh

Maker: InclusionAI
Label on the catalogue: no family named
What the measurement says: its own InclusionAI tokenizer group
Why high: an exact fingerprint shared with 4 models
Fingerprint: tk_fc5a4585 · shared with 4 other models
Context: 262,144
Max output: 32,768
Modalities: text->text
Prompt price: $0.02 / M tokens
Entered the catalogue: 23 July 2026
Last tested: 21 August 2026

Full record JSON Shares with inclusionAI: Ling 3.0 Flash Fin

inclusionAI: Ling 3.0 Flash Fininclusionai/ling-3.0-flash-finits own InclusionAI tokenizer groupHigh

Maker: InclusionAI
Label on the catalogue: no family named
What the measurement says: its own InclusionAI tokenizer group
Why high: an exact fingerprint shared with 4 models
Fingerprint: tk_fc5a4585 · shared with 4 other models
Context: 262,144
Max output: 235,929
Modalities: text->text
Prompt price: $0.06 / M tokens
Entered the catalogue: 27 August 2026
Last tested: 3 September 2026

Full record JSON Shares with inclusionAI: Ling 3.0 Flash

inclusionAI: Ling 3.0 Flash Fin (free)inclusionai/ling-3.0-flash-fin:freeits own InclusionAI tokenizer groupHigh

Maker: InclusionAI
Label on the catalogue: no family named
What the measurement says: its own InclusionAI tokenizer group
Why high: inherited from inclusionai/ling-3.0-flash-fin: a serving variant shares its base model's tokenizer
Variant of: inclusionAI: Ling 3.0 Flash Fin
Context: 262,144
Max output: 32,768
Modalities: text->text
Prompt price: $0 / M tokens
Entered the catalogue: 27 August 2026
Last tested: not yet

Full record JSON

inclusionAI: Ling-2.6-1Tinclusionai/ling-2.6-1twithdrawn from the catalogue · measured as its own InclusionAI tokenizer groupVery high

Maker: InclusionAI
Label on the catalogue: no family named
What the measurement says: withdrawn from the catalogue · measured as its own InclusionAI tokenizer group
Why very high: an exact fingerprint shared with 4 models and an identical API contract inside the same group: two signals of different kinds agree
Fingerprint: tk_fc5a4585 · shared with 4 other models
Context: 262,144
Max output: 32,768
Modalities: text->text
Prompt price: $0.07 / M tokens
Entered the catalogue: 23 April 2026
Last tested: 21 August 2026

Full record JSON Shares with inclusionAI: Ling 3.0 Flash Fin

inclusionAI: Ling-2.6-flashinclusionai/ling-2.6-flashwithdrawn from the catalogue · measured as its own InclusionAI tokenizer groupVery high

Maker: InclusionAI
Label on the catalogue: no family named
What the measurement says: withdrawn from the catalogue · measured as its own InclusionAI tokenizer group
Why very high: an exact fingerprint shared with 4 models and an identical API contract inside the same group: two signals of different kinds agree
Fingerprint: tk_fc5a4585 · shared with 4 other models
Context: 262,144
Max output: 32,768
Modalities: text->text
Prompt price: $0.01 / M tokens
Entered the catalogue: 21 April 2026
Last tested: 21 August 2026

Full record JSON Shares with inclusionAI: Ling 3.0 Flash Fin

inclusionAI: Ring-2.6-1Tinclusionai/ring-2.6-1twithdrawn from the catalogue · measured as its own InclusionAI tokenizer groupHigh

Maker: InclusionAI
Label on the catalogue: no family named
What the measurement says: withdrawn from the catalogue · measured as its own InclusionAI tokenizer group
Why high: an exact fingerprint shared with 4 models
Fingerprint: tk_fc5a4585 · shared with 4 other models
Context: 262,144
Max output: 65,536
Modalities: text->text
Prompt price: $0.07 / M tokens
Entered the catalogue: 8 May 2026
Last tested: 21 August 2026

Full record JSON Shares with inclusionAI: Ling 3.0 Flash Fin

Kwaipilot: KAT-Coder-Air V2.5kwaipilot/kat-coder-air-v2.5withdrawn from the catalogue · measured as built on the Qwen tokenizerHigh

Maker: Kwaipilot
Label on the catalogue: no family named
What the measurement says: withdrawn from the catalogue · measured as built on the Qwen tokenizer
Why high: an exact fingerprint shared with 2 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_06ffa14a · shared with 2 other models
Context: 256,000
Max output: 80,000
Modalities: text->text
Prompt price: $0.15 / M tokens
Entered the catalogue: 10 July 2026
Last tested: 21 August 2026

Full record JSON Shares with Qwen: Qwen3.6 35B A3B

Kwaipilot: KAT-Coder-Pro V2kwaipilot/kat-coder-pro-v2builds on the Qwen tokenizerHigh

Maker: Kwaipilot
Label on the catalogue: no family named
What the measurement says: builds on the Qwen tokenizer
Why high: one template-boundary shift from a group whose members all declare the same family
Fingerprint: tk_e60ca14a · unique so far
Context: 262,144
Max output: 144,000
Modalities: text->text
Prompt price: $0.30 / M tokens
Entered the catalogue: 27 March 2026
Last tested: 21 August 2026

Full record JSON

LiquidAI: LFM2.5-2.6B (free)liquid/lfm-2.5-2.6b:freemeasured, matches nothing else yetMeasured

Maker: Liquid AI
Label on the catalogue: no family named
What the measurement says: measured, matches nothing else yet
Fingerprint: tk_2c236574 · unique so far
Context: 65,536
Max output: 8,192
Modalities: text->text
Prompt price: $0 / M tokens
Entered the catalogue: 11 August 2026
Last tested: 21 August 2026

Full record JSON

Meituan: LongCat 2.0meituan/longcat-2.0measured, matches nothing else yetMeasured

Maker: Meituan
Label on the catalogue: no family named
What the measurement says: measured, matches nothing else yet
Fingerprint: tk_c670dac9 · unique so far
Context: 1,048,756
Max output: 262,144
Modalities: text->text
Prompt price: $0.30 / M tokens
Entered the catalogue: 20 July 2026
Last tested: 21 August 2026

Full record JSON

Meta: Llama Guard 4 12Bmeta-llama/llama-guard-4-12bmeasured, matches nothing else yetMeasured

Maker: Meta
Label on the catalogue: no family named
What the measurement says: measured, matches nothing else yet
Fingerprint: tk_985608d3 · unique so far
Context: 163,840
Max output: 16,384
Modalities: text+image->text
Prompt price: $0.18 / M tokens
Entered the catalogue: 30 April 2025
Last tested: 21 August 2026

Full record JSON

Meta: Muse Glimmer 30Bmeta/muse-glimmer-30bbuilds on the Llama4 tokenizerHigh

Maker: Meta
Label on the catalogue: no family named
What the measurement says: builds on the Llama4 tokenizer
Why high: one template-boundary shift from a group whose members all declare the same family
Fingerprint: tk_20b9d005 · unique so far
Context: 131,072
Max output: 117,964
Modalities: text+image->text
Prompt price: $0.35 / M tokens
Entered the catalogue: 9 August 2026
Last tested: 21 August 2026

Full record JSON

Meta: Muse Glimmer 30B (batch)meta/muse-glimmer-30b:batchbuilds on the Llama4 tokenizerHigh

Maker: Meta
Label on the catalogue: no family named
What the measurement says: builds on the Llama4 tokenizer
Why high: inherited from meta/muse-glimmer-30b: a serving variant shares its base model's tokenizer
Variant of: Meta: Muse Glimmer 30B
Context: 131,072
Max output: 117,964
Modalities: text+image->text
Prompt price: $0.17 / M tokens
Entered the catalogue: 9 August 2026
Last tested: not yet

Full record JSON

Microsoft: Phi 4microsoft/phi-4builds on the OpenAI cl100k tokenizerHigh

Maker: Microsoft
Label on the catalogue: no family named
What the measurement says: builds on the OpenAI cl100k tokenizer
Why high: an exact fingerprint shared with 3 models
Fingerprint: tk_ba918336 · shared with 3 other models
Context: 16,384
Max output: 14,745
Modalities: text->text
Prompt price: $0.07 / M tokens
Entered the catalogue: 10 January 2025
Last tested: 21 August 2026
Verified finding: Phi-4's repository tokenizer, run over the 50 strings offline, matches OpenAI's open cl100k_base encoding on every string (vocabulary 100,352, the padded cl100k table). IBM's Granite 4.0 and 4.1 declare the same vocabulary size and their endpoints return ident…

Full record JSON Shares with IBM: Granite 4.0 Micro

MiniMax: MiniMax M1minimax/minimax-m1its own MiniMax tokenizer groupHigh

Maker: MiniMax
Label on the catalogue: no family named
What the measurement says: its own MiniMax tokenizer group
Why high: an exact fingerprint shared with 7 models
Fingerprint: tk_9f84b5fb · shared with 7 other models
Context: 1,000,000
Max output: 40,000
Modalities: text->text
Prompt price: $0.40 / M tokens
Entered the catalogue: 17 June 2025
Last tested: 22 August 2026

Full record JSON Shares with MiniMax: MiniMax M3

MiniMax: MiniMax M2minimax/minimax-m2its own MiniMax tokenizer groupHigh

Maker: MiniMax
Label on the catalogue: no family named
What the measurement says: its own MiniMax tokenizer group
Why high: an exact fingerprint shared with 7 models
Fingerprint: tk_9f84b5fb · shared with 7 other models
Context: 204,800
Max output: 131,072
Modalities: text->text
Prompt price: $0.26 / M tokens
Entered the catalogue: 23 October 2025
Last tested: 21 August 2026

Full record JSON Shares with MiniMax: MiniMax M3

MiniMax: MiniMax M2-herminimax/minimax-m2-herits own MiniMax tokenizer groupHigh

Maker: MiniMax
Label on the catalogue: no family named
What the measurement says: its own MiniMax tokenizer group
Why high: an exact fingerprint shared with 7 models
Fingerprint: tk_9f84b5fb · shared with 7 other models
Context: 65,536
Max output: 2,048
Modalities: text->text
Prompt price: $0.30 / M tokens
Entered the catalogue: 23 January 2026
Last tested: 21 August 2026

Full record JSON Shares with MiniMax: MiniMax M3

MiniMax: MiniMax M2.1minimax/minimax-m2.1its own MiniMax tokenizer groupHigh

Maker: MiniMax
Label on the catalogue: no family named
What the measurement says: its own MiniMax tokenizer group
Why high: an exact fingerprint shared with 7 models
Fingerprint: tk_9f84b5fb · shared with 7 other models
Context: 204,800
Max output: 131,072
Modalities: text->text
Prompt price: $0.30 / M tokens
Entered the catalogue: 23 December 2025
Last tested: 21 August 2026

Full record JSON Shares with MiniMax: MiniMax M3

MiniMax: MiniMax M2.5minimax/minimax-m2.5its own MiniMax tokenizer groupHigh

Maker: MiniMax
Label on the catalogue: no family named
What the measurement says: its own MiniMax tokenizer group
Why high: an exact fingerprint shared with 7 models
Fingerprint: tk_9f84b5fb · shared with 7 other models
Context: 204,800
Max output: 128,000
Modalities: text->text
Prompt price: $0.27 / M tokens
Entered the catalogue: 12 February 2026
Last tested: 21 August 2026

Full record JSON Shares with MiniMax: MiniMax M3

MiniMax: MiniMax M2.7minimax/minimax-m2.7its own MiniMax tokenizer groupHigh

Maker: MiniMax
Label on the catalogue: no family named
What the measurement says: its own MiniMax tokenizer group
Why high: an exact fingerprint shared with 7 models
Fingerprint: tk_9f84b5fb · shared with 7 other models
Context: 204,800
Max output: 131,072
Modalities: text->text
Prompt price: $0.30 / M tokens
Entered the catalogue: 18 March 2026
Last tested: 21 August 2026

Full record JSON Shares with MiniMax: MiniMax M3

MiniMax: MiniMax M2.7 (free)minimax/minimax-m2.7:freewithdrawn from the catalogue · measured as its own MiniMax tokenizer groupHigh

Maker: MiniMax
Label on the catalogue: no family named
What the measurement says: withdrawn from the catalogue · measured as its own MiniMax tokenizer group
Why high: inherited from minimax/minimax-m2.7: a serving variant shares its base model's tokenizer
Variant of: MiniMax: MiniMax M2.7
Context: 196,608
Max output: 176,947
Modalities: text->text
Prompt price: $0 / M tokens
Entered the catalogue: 18 March 2026
Last tested: not yet

Full record JSON

MiniMax: MiniMax M3minimax/minimax-m3its own MiniMax tokenizer groupHigh

Maker: MiniMax
Label on the catalogue: no family named
What the measurement says: its own MiniMax tokenizer group
Why high: an exact fingerprint shared with 7 models
Fingerprint: tk_9f84b5fb · shared with 7 other models
Context: 1,048,576
Max output: 512,000
Modalities: text+image+video->text
Prompt price: $0.30 / M tokens
Entered the catalogue: 31 May 2026
Last tested: 21 August 2026

Full record JSON Shares with MiniMax: MiniMax M2.7

MiniMax: MiniMax M3 (batch)minimax/minimax-m3:batchits own MiniMax tokenizer groupHigh

Maker: MiniMax
Label on the catalogue: no family named
What the measurement says: its own MiniMax tokenizer group
Why high: inherited from minimax/minimax-m3: a serving variant shares its base model's tokenizer
Variant of: MiniMax: MiniMax M3
Context: 524,288
Max output: 471,859
Modalities: text+image+video->text
Prompt price: $0.30 / M tokens
Entered the catalogue: 31 May 2026
Last tested: not yet

Full record JSON

MiniMax: MiniMax M3 (free)minimax/minimax-m3:freewithdrawn from the catalogue · measured as its own MiniMax tokenizer groupHigh

Maker: MiniMax
Label on the catalogue: no family named
What the measurement says: withdrawn from the catalogue · measured as its own MiniMax tokenizer group
Why high: inherited from minimax/minimax-m3: a serving variant shares its base model's tokenizer
Variant of: MiniMax: MiniMax M3
Context: 1,048,576
Max output: 943,718
Modalities: text+image+video->text
Prompt price: $0 / M tokens
Entered the catalogue: 31 May 2026
Last tested: not yet

Full record JSON

MiniMax: MiniMax-01minimax/minimax-01its own MiniMax tokenizer groupHigh

Maker: MiniMax
Label on the catalogue: no family named
What the measurement says: its own MiniMax tokenizer group
Why high: an exact fingerprint shared with 7 models
Fingerprint: tk_9f84b5fb · shared with 7 other models
Context: 1,000,192
Max output: 900,172
Modalities: text+image->text
Prompt price: $0.20 / M tokens
Entered the catalogue: 15 January 2025
Last tested: 21 August 2026

Full record JSON Shares with MiniMax: MiniMax M3

Mistral: Ministral 8Bmistralai/ministral-8bwithdrawn from the catalogueNo reading

Maker: Mistral AI
Label on the catalogue: Mistral
What the measurement says: withdrawn from the catalogue
Context: 128,000
Max output: –
Modalities: text->text
Prompt price: $0.11 / M tokens
Entered the catalogue: 17 October 2024
Last tested: not yet

Full record JSON

Mistral: Mistral Small 3mistralai/mistral-small-24b-instruct-2501measured, matches nothing else yetMeasured

Maker: Mistral AI
Label on the catalogue: Mistral
What the measurement says: measured, matches nothing else yet
Fingerprint: tk_ddc193e9 · shared with 2 other models
Context: 32,768
Max output: 16,384
Modalities: text->text
Prompt price: $0.05 / M tokens
Entered the catalogue: 30 January 2025
Last tested: 21 August 2026

Full record JSON Shares with Venice: Uncensored

MoonshotAI: Kimi K2 0711moonshotai/kimi-k2measured, matches nothing else yetMeasured

Maker: Moonshot AI
Label on the catalogue: no family named
What the measurement says: measured, matches nothing else yet
Fingerprint: tk_2e353ea4 · unique so far
Context: 131,072
Max output: 98,304
Modalities: text->text
Prompt price: $0.57 / M tokens
Entered the catalogue: 11 July 2025
Last tested: 22 August 2026

Full record JSON

MoonshotAI: Kimi K2 0905moonshotai/kimi-k2-0905its own Moonshot AI tokenizer groupModerate

Maker: Moonshot AI
Label on the catalogue: no family named
What the measurement says: its own Moonshot AI tokenizer group
Why moderate: near-exact agreement (49 of 50 strings) with moonshotai/kimi-k2.6, short of a full exact signature
Fingerprint: tk_f14a0fdd · unique so far
Context: 262,144
Max output: 98,304
Modalities: text->text
Prompt price: $0.60 / M tokens
Entered the catalogue: 4 September 2025
Last tested: 3 September 2026

Full record JSON

MoonshotAI: Kimi K2 Thinkingmoonshotai/kimi-k2-thinkingits own Moonshot AI tokenizer groupHigh

Maker: Moonshot AI
Label on the catalogue: no family named
What the measurement says: its own Moonshot AI tokenizer group
Why high: an exact fingerprint shared with 2 models
Fingerprint: tk_ea6068bf · shared with 2 other models
Context: 262,144
Max output: 98,304
Modalities: text->text
Prompt price: $0.60 / M tokens
Entered the catalogue: 6 November 2025
Last tested: 3 September 2026

Full record JSON Shares with MoonshotAI: Kimi K2.7 Code

MoonshotAI: Kimi K2.5moonshotai/kimi-k2.5its own Moonshot AI tokenizer groupModerate

Maker: Moonshot AI
Label on the catalogue: no family named
What the measurement says: its own Moonshot AI tokenizer group
Why moderate: near-exact agreement (48 of 48 strings) with moonshotai/kimi-k2.6, short of a full exact signature
Context: 262,144
Max output: 235,929
Modalities: text+image->text
Prompt price: $0.45 / M tokens
Entered the catalogue: 27 January 2026
Last tested: 3 September 2026

Full record JSON

MoonshotAI: Kimi K2.6moonshotai/kimi-k2.6its own Moonshot AI tokenizer groupHigh

Maker: Moonshot AI
Label on the catalogue: no family named
What the measurement says: its own Moonshot AI tokenizer group
Why high: an exact fingerprint shared with 2 models
Fingerprint: tk_ea6068bf · shared with 2 other models
Context: 262,144
Max output: 235,929
Modalities: text+image->text
Prompt price: $0.95 / M tokens
Entered the catalogue: 20 April 2026
Last tested: 22 August 2026

Full record JSON Shares with MoonshotAI: Kimi K2.7 Code

MoonshotAI: Kimi K2.7 Codemoonshotai/kimi-k2.7-codeits own Moonshot AI tokenizer groupHigh

Maker: Moonshot AI
Label on the catalogue: no family named
What the measurement says: its own Moonshot AI tokenizer group
Why high: an exact fingerprint shared with 2 models
Fingerprint: tk_ea6068bf · shared with 2 other models
Context: 262,144
Max output: 235,929
Modalities: text+image->text
Prompt price: $0.71 / M tokens
Entered the catalogue: 12 June 2026
Last tested: 3 September 2026

Full record JSON Shares with MoonshotAI: Kimi K2.6

MoonshotAI: Kimi K2.7 Code (batch)moonshotai/kimi-k2.7-code:batchwithdrawn from the catalogue · measured as its own Moonshot AI tokenizer groupHigh

Maker: Moonshot AI
Label on the catalogue: no family named
What the measurement says: withdrawn from the catalogue · measured as its own Moonshot AI tokenizer group
Why high: inherited from moonshotai/kimi-k2.7-code: a serving variant shares its base model's tokenizer
Variant of: MoonshotAI: Kimi K2.7 Code
Context: 262,144
Max output: –
Modalities: text+image->text
Prompt price: $0.95 / M tokens
Entered the catalogue: 12 June 2026
Last tested: not yet

Full record JSON

MoonshotAI: Kimi K3moonshotai/kimi-k3measured, matches nothing else yetMeasured

Maker: Moonshot AI
Label on the catalogue: no family named
What the measurement says: measured, matches nothing else yet
Context: 1,048,576
Max output: 943,718
Modalities: text+image+video->text
Prompt price: $2.65 / M tokens
Entered the catalogue: 16 July 2026
Last tested: 21 August 2026

Full record JSON

Morph: Morph V3 Fastmorph/morph-v3-fastbuilds on the Qwen tokenizerHigh

Maker: Morph
Label on the catalogue: no family named
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 36 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_5410b38e · shared with 36 other models
Context: 81,920
Max output: 38,000
Modalities: text->text
Prompt price: $0.80 / M tokens
Entered the catalogue: 7 July 2025
Last tested: 3 September 2026

Full record JSON Shares with Dots Studio: Dots3-Note Preview (free)

Morph: Morph V3 Largemorph/morph-v3-largebuilds on the Qwen tokenizerHigh

Maker: Morph
Label on the catalogue: no family named
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 1 model that declares the same family, without a second signal of a different kind yet
Fingerprint: tk_c5c0a8ed · shared with 1 other model
Context: 262,144
Max output: 131,072
Modalities: text->text
Prompt price: $0.90 / M tokens
Entered the catalogue: 7 July 2025
Last tested: 3 September 2026

Full record JSON Shares with Perceptron: Perceptron Mk1

Nex AGI: Nex-N2-Mininex-agi/nex-n2-miniwithdrawn from the catalogue · measured as built on the Qwen tokenizerHigh

Maker: Nex Agi
Label on the catalogue: Qwen3
What the measurement says: withdrawn from the catalogue · measured as built on the Qwen tokenizer
Why high: an exact fingerprint shared with 14 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_181907f2 · shared with 14 other models
Context: 262,144
Max output: 235,929
Modalities: text+image->text
Prompt price: $0.02 / M tokens
Entered the catalogue: 24 June 2026
Last tested: 21 August 2026

Full record JSON Shares with Qwen: Qwen3.8 Flash

Nex AGI: Nex-N2-Pronex-agi/nex-n2-prowithdrawn from the catalogue · measured as built on the Qwen tokenizerHigh

Maker: Nex Agi
Label on the catalogue: Qwen3
What the measurement says: withdrawn from the catalogue · measured as built on the Qwen tokenizer
Why high: an exact fingerprint shared with 14 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_181907f2 · shared with 14 other models
Context: 262,144
Max output: 235,929
Modalities: text+image->text
Prompt price: $0.25 / M tokens
Entered the catalogue: 8 June 2026
Last tested: 21 August 2026

Full record JSON Shares with Qwen: Qwen3.8 Flash

Nous: Hermes 4 405Bnousresearch/hermes-4-405bbuilds on the Llama3 tokenizerVery high

Maker: Nous Research
Label on the catalogue: no family named
What the measurement says: builds on the Llama3 tokenizer
Why very high: an exact fingerprint shared with 4 models and an identical API contract inside the same group: two signals of different kinds agree
Fingerprint: tk_47615f2d · shared with 4 other models
Context: 131,072
Max output: 117,964
Modalities: text->text
Prompt price: $1.00 / M tokens
Entered the catalogue: 26 August 2025
Last tested: 3 September 2026

Full record JSON Shares with Meta: Llama 3.2 1B Instruct

Nous: Hermes 4 70Bnousresearch/hermes-4-70bwithdrawn from the catalogue · measured as built on the Llama3 tokenizerVery high

Maker: Nous Research
Label on the catalogue: Llama3
What the measurement says: withdrawn from the catalogue · measured as built on the Llama3 tokenizer
Why very high: an exact fingerprint shared with 4 models and an identical API contract inside the same group: two signals of different kinds agree
Fingerprint: tk_47615f2d · shared with 4 other models
Context: 131,072
Max output: 117,964
Modalities: text->text
Prompt price: $0.13 / M tokens
Entered the catalogue: 26 August 2025
Last tested: 21 August 2026

Full record JSON Shares with Nous: Hermes 4 405B

NVIDIA: Nemotron 3 Nano 30B A3Bnvidia/nemotron-3-nano-30b-a3bbuilds on the Mistral tokenizerHigh

Maker: NVIDIA
Label on the catalogue: no family named
What the measurement says: builds on the Mistral tokenizer
Why high: an exact fingerprint shared with 21 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_0da8a999 · shared with 21 other models
Context: 262,144
Max output: 235,929
Modalities: text->text
Prompt price: $0.05 / M tokens
Entered the catalogue: 14 December 2025
Last tested: 21 August 2026

Full record JSON Shares with NVIDIA: Nemotron 3.5 Lightning

NVIDIA: Nemotron 3 Nano 30B A3B (free)nvidia/nemotron-3-nano-30b-a3b:freewithdrawn from the catalogue · measured as built on the Mistral tokenizerHigh

Maker: NVIDIA
Label on the catalogue: no family named
What the measurement says: withdrawn from the catalogue · measured as built on the Mistral tokenizer
Why high: inherited from nvidia/nemotron-3-nano-30b-a3b: a serving variant shares its base model's tokenizer
Variant of: NVIDIA: Nemotron 3 Nano 30B A3B
Context: 256,000
Max output: –
Modalities: text->text
Prompt price: $0 / M tokens
Entered the catalogue: 14 December 2025
Last tested: not yet

Full record JSON

NVIDIA: Nemotron 3 Nano Omni (free)nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:freebuilds on the Mistral tokenizerHigh

Maker: NVIDIA
Label on the catalogue: no family named
What the measurement says: builds on the Mistral tokenizer
Why high: one template-boundary shift from a group whose members all declare the same family
Fingerprint: tk_e0b4c23e · unique so far
Context: 256,000
Max output: 65,536
Modalities: text+image+audio+video->text
Prompt price: $0 / M tokens
Entered the catalogue: 28 April 2026
Last tested: 21 August 2026

Full record JSON

NVIDIA: Nemotron 3 Supernvidia/nemotron-3-super-120b-a12bbuilds on the Mistral tokenizerHigh

Maker: NVIDIA
Label on the catalogue: no family named
What the measurement says: builds on the Mistral tokenizer
Why high: an exact fingerprint shared with 21 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_0da8a999 · shared with 21 other models
Context: 262,144
Max output: 235,929
Modalities: text->text
Prompt price: $0.08 / M tokens
Entered the catalogue: 11 March 2026
Last tested: 21 August 2026

Full record JSON Shares with NVIDIA: Nemotron 3.5 Lightning

NVIDIA: Nemotron 3 Super (free)nvidia/nemotron-3-super-120b-a12b:freebuilds on the Mistral tokenizerHigh

Maker: NVIDIA
Label on the catalogue: no family named
What the measurement says: builds on the Mistral tokenizer
Why high: inherited from nvidia/nemotron-3-super-120b-a12b: a serving variant shares its base model's tokenizer
Variant of: NVIDIA: Nemotron 3 Super
Context: 262,144
Max output: 235,929
Modalities: text->text
Prompt price: $0 / M tokens
Entered the catalogue: 11 March 2026
Last tested: not yet

Full record JSON

NVIDIA: Nemotron 3 Ultranvidia/nemotron-3-ultra-550b-a55bbuilds on the Mistral tokenizerHigh

Maker: NVIDIA
Label on the catalogue: no family named
What the measurement says: builds on the Mistral tokenizer
Why high: an exact fingerprint shared with 21 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_0da8a999 · shared with 21 other models
Context: 262,144
Max output: 182,520
Modalities: text->text
Prompt price: $0.60 / M tokens
Entered the catalogue: 4 June 2026
Last tested: 3 September 2026

Full record JSON Shares with NVIDIA: Nemotron 3.5 Lightning

NVIDIA: Nemotron 3 Ultra (batch)nvidia/nemotron-3-ultra-550b-a55b:batchwithdrawn from the catalogue · measured as built on the Mistral tokenizerHigh

Maker: NVIDIA
Label on the catalogue: no family named
What the measurement says: withdrawn from the catalogue · measured as built on the Mistral tokenizer
Why high: inherited from nvidia/nemotron-3-ultra-550b-a55b: a serving variant shares its base model's tokenizer
Variant of: NVIDIA: Nemotron 3 Ultra
Context: 512,288
Max output: –
Modalities: text->text
Prompt price: $0.60 / M tokens
Entered the catalogue: 4 June 2026
Last tested: not yet

Full record JSON

NVIDIA: Nemotron 3 Ultra (free)nvidia/nemotron-3-ultra-550b-a55b:freebuilds on the Mistral tokenizerHigh

Maker: NVIDIA
Label on the catalogue: no family named
What the measurement says: builds on the Mistral tokenizer
Why high: inherited from nvidia/nemotron-3-ultra-550b-a55b: a serving variant shares its base model's tokenizer
Variant of: NVIDIA: Nemotron 3 Ultra
Context: 1,000,000
Max output: 65,536
Modalities: text->text
Prompt price: $0 / M tokens
Entered the catalogue: 4 June 2026
Last tested: not yet

Full record JSON

NVIDIA: Nemotron 3.5 Content Safety (free)nvidia/nemotron-3.5-content-safety:freemeasured, matches nothing else yetMeasured

Maker: NVIDIA
Label on the catalogue: no family named
What the measurement says: measured, matches nothing else yet
Fingerprint: tk_9a840805 · unique so far
Variant of: NVIDIA: Nemotron 3.5 Content Safety
Context: 128,000
Max output: 8,192
Modalities: text+image->text
Prompt price: $0 / M tokens
Entered the catalogue: 4 June 2026
Last tested: 21 August 2026

Full record JSON

NVIDIA: Nemotron 3.5 Lightningnvidia/nemotron-3.5-lightningbuilds on the Mistral tokenizerHigh

Maker: NVIDIA
Label on the catalogue: no family named
What the measurement says: builds on the Mistral tokenizer
Why high: an exact fingerprint shared with 21 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_0da8a999 · shared with 21 other models
Context: 262,144
Max output: 131,072
Modalities: text->text
Prompt price: $0.08 / M tokens
Entered the catalogue: 11 August 2026
Last tested: 21 August 2026

Full record JSON Shares with NVIDIA: Nemotron 3 Ultra

NVIDIA: Nemotron 3.5 Lightning (free)nvidia/nemotron-3.5-lightning:freebuilds on the Mistral tokenizerHigh

Maker: NVIDIA
Label on the catalogue: no family named
What the measurement says: builds on the Mistral tokenizer
Why high: inherited from nvidia/nemotron-3.5-lightning: a serving variant shares its base model's tokenizer
Variant of: NVIDIA: Nemotron 3.5 Lightning
Context: 1,000,000
Max output: 65,536
Modalities: text->text
Prompt price: $0 / M tokens
Entered the catalogue: 11 August 2026
Last tested: not yet

Full record JSON

NVIDIA: Nemotron Nano 12B 2 VL (free)nvidia/nemotron-nano-12b-v2-vl:freewithdrawn from the catalogue · measured as built on the Mistral tokenizerLow

Maker: NVIDIA
Label on the catalogue: no family named
What the measurement says: withdrawn from the catalogue · measured as built on the Mistral tokenizer
Why low: partial agreement (40 of 47 strings) with nvidia/nemotron-nano-9b-v2:free only
Context: 128,000
Max output: 128,000
Modalities: text+image+video->text
Prompt price: $0 / M tokens
Entered the catalogue: 28 October 2025
Last tested: 21 August 2026

Full record JSON

NVIDIA: Nemotron Nano 9B V2 (free)nvidia/nemotron-nano-9b-v2:freewithdrawn from the catalogue · measured as built on the Mistral tokenizerHigh

Maker: NVIDIA
Label on the catalogue: no family named
What the measurement says: withdrawn from the catalogue · measured as built on the Mistral tokenizer
Why high: one template-boundary shift from a group whose members all declare the same family
Fingerprint: tk_b0a747db · unique so far
Context: 128,000
Max output: –
Modalities: text->text
Prompt price: $0 / M tokens
Entered the catalogue: 5 September 2025
Last tested: 21 August 2026

Full record JSON

OpenAI: GPT-3.5 Turboopenai/gpt-3.5-turbobuilds on the OpenAI cl100k tokenizerHigh

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the OpenAI cl100k tokenizer
Why high: an exact fingerprint shared with 3 models
Fingerprint: tk_ba918336 · shared with 3 other models
Context: 16,385
Max output: 4,096
Modalities: text->text
Prompt price: $0.50 / M tokens
Entered the catalogue: 28 May 2023
Last tested: 22 August 2026

Full record JSON Shares with IBM: Granite 4.0 Micro

OpenAI: GPT-3.5 Turbo (batch)openai/gpt-3.5-turbo:batchbuilds on the OpenAI cl100k tokenizerHigh

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the OpenAI cl100k tokenizer
Why high: inherited from openai/gpt-3.5-turbo: a serving variant shares its base model's tokenizer
Variant of: OpenAI: GPT-3.5 Turbo
Context: 16,385
Max output: 4,096
Modalities: text->text
Prompt price: $0.25 / M tokens
Entered the catalogue: 28 May 2023
Last tested: not yet

Full record JSON

OpenAI: GPT-3.5 Turbo Instructopenai/gpt-3.5-turbo-instructbuilds on the OpenAI cl100k tokenizerModerate

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the OpenAI cl100k tokenizer
Why moderate: near-exact agreement (41 of 41 strings) with ibm-granite/granite-4.0-h-micro, short of a full exact signature
Context: 4,095
Max output: 3,685
Modalities: text->text
Prompt price: $1.50 / M tokens
Entered the catalogue: 28 September 2023
Last tested: 3 September 2026

Full record JSON

OpenAI: GPT-4 Turbo Previewopenai/gpt-4-turbo-previewwithdrawn from the catalogueNo reading

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: withdrawn from the catalogue
Context: 128,000
Max output: 4,096
Modalities: text->text
Prompt price: $10.0 / M tokens
Entered the catalogue: 25 January 2024
Last tested: not yet

Full record JSON

OpenAI: GPT-5 Codex (batch)openai/gpt-5-codex:batchwithdrawn from the catalogueNo reading

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: withdrawn from the catalogue
Context: 400,000
Max output: 128,000
Modalities: text+image->text
Prompt price: $0.63 / M tokens
Entered the catalogue: 23 September 2025
Last tested: not yet

Full record JSON

OpenAI: GPT-5 Miniopenai/gpt-5-minitoken accounting unreliable at this endpointNo reading

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: token accounting unreliable at this endpoint
Context: 400,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $0.25 / M tokens
Entered the catalogue: 7 August 2025
Last tested: 21 August 2026

Full record JSON

OpenAI: GPT-5.6 Luna Proopenai/gpt-5.6-luna-protoken accounting unreliable at this endpointNo reading

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: token accounting unreliable at this endpoint
Context: 1,050,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $0.20 / M tokens
Entered the catalogue: 9 July 2026
Last tested: not yet

Full record JSON

OpenAI: GPT-5.6 Sol Proopenai/gpt-5.6-sol-protoken accounting unreliable at this endpointNo reading

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: token accounting unreliable at this endpoint
Context: 1,050,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $2.00 / M tokens
Entered the catalogue: 9 July 2026
Last tested: not yet

Full record JSON

OpenAI: GPT-5.6 Terra Proopenai/gpt-5.6-terra-protoken accounting unreliable at this endpointNo reading

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: token accounting unreliable at this endpoint
Context: 1,050,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $2.00 / M tokens
Entered the catalogue: 9 July 2026
Last tested: not yet

Full record JSON

OpenAI: gpt-oss-20b (batch)openai/gpt-oss-20b:batchwithdrawn from the catalogue · measured as built on the GPT tokenizerHigh

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: withdrawn from the catalogue · measured as built on the GPT tokenizer
Why high: inherited from openai/gpt-oss-20b: a serving variant shares its base model's tokenizer
Variant of: OpenAI: gpt-oss-20b
Context: 131,072
Max output: 117,964
Modalities: text->text
Prompt price: $0.05 / M tokens
Entered the catalogue: 5 August 2025
Last tested: not yet

Full record JSON

OpenAI: gpt-oss-20b (free)openai/gpt-oss-20b:freewithdrawn from the catalogue · measured as built on the GPT tokenizerHigh

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: withdrawn from the catalogue · measured as built on the GPT tokenizer
Why high: inherited from openai/gpt-oss-20b: a serving variant shares its base model's tokenizer
Variant of: OpenAI: gpt-oss-20b
Context: 131,072
Max output: 32,768
Modalities: text->text
Prompt price: $0 / M tokens
Entered the catalogue: 5 August 2025
Last tested: not yet

Full record JSON

OpenAI: o1 (batch)openai/o1:batchwithdrawn from the catalogueNo reading

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: withdrawn from the catalogue
Variant of: OpenAI: o1
Context: 200,000
Max output: 100,000
Modalities: text+image+file->text
Prompt price: $7.50 / M tokens
Entered the catalogue: 17 December 2024
Last tested: not yet

Full record JSON

OpenAI: o1-pro (batch)openai/o1-pro:batchwithdrawn from the catalogueNo reading

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: withdrawn from the catalogue
Variant of: OpenAI: o1-pro
Context: 200,000
Max output: 100,000
Modalities: text+image+file->text
Prompt price: $75.0 / M tokens
Entered the catalogue: 19 March 2025
Last tested: not yet

Full record JSON

OpenAI: o3 Mini High (batch)openai/o3-mini-high:batchwithdrawn from the catalogue · measured as built on the GPT tokenizerVery high

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: withdrawn from the catalogue · measured as built on the GPT tokenizer
Why very high: inherited from openai/o3-mini-high: a serving variant shares its base model's tokenizer
Variant of: OpenAI: o3 Mini High
Context: 200,000
Max output: 100,000
Modalities: text+file->text
Prompt price: $0.55 / M tokens
Entered the catalogue: 12 February 2025
Last tested: not yet

Full record JSON

OpenAI: o3 Pro (batch)openai/o3-pro:batchwithdrawn from the catalogueNo reading

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: withdrawn from the catalogue
Variant of: OpenAI: o3 Pro
Context: 200,000
Max output: 100,000
Modalities: text+image+file->text
Prompt price: $10.0 / M tokens
Entered the catalogue: 10 June 2025
Last tested: not yet

Full record JSON

OpenAI: o4 Mini High (batch)openai/o4-mini-high:batchwithdrawn from the catalogue · measured as built on the GPT tokenizerVery high

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: withdrawn from the catalogue · measured as built on the GPT tokenizer
Why very high: inherited from openai/o4-mini-high: a serving variant shares its base model's tokenizer
Variant of: OpenAI: o4 Mini High
Context: 200,000
Max output: 100,000
Modalities: text+image+file->text
Prompt price: $0.55 / M tokens
Entered the catalogue: 16 April 2025
Last tested: not yet

Full record JSON

Ox Alphastealth/ox-alphawithdrawn from the catalogueMeasured

Maker: Undisclosed (stealth)
Label on the catalogue: no family named
What the measurement says: withdrawn from the catalogue
Fingerprint: tk_133b086c · shared with 6 other models
Context: 1,048,576
Max output: 131,072
Modalities: text+image+video->text
Prompt price: $0 / M tokens
Entered the catalogue: 20 August 2026
Last tested: 21 August 2026

Full record JSON Shares with Z.ai: GLM 5.3 Flash

Perceptron: Perceptron Mk1perceptron/perceptron-mk1builds on the Qwen tokenizerHigh

Maker: Perceptron
Label on the catalogue: no family named
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 1 model that declares the same family, without a second signal of a different kind yet
Fingerprint: tk_c5c0a8ed · shared with 1 other model
Context: 32,768
Max output: 8,192
Modalities: text+image+video->text
Prompt price: $0.15 / M tokens
Entered the catalogue: 12 May 2026
Last tested: 21 August 2026

Full record JSON Shares with Morph: Morph V3 Large

Perplexity: Sonarperplexity/sonarbuilds on the Llama3 tokenizerHigh

Maker: Perplexity
Label on the catalogue: no family named
What the measurement says: builds on the Llama3 tokenizer
Why high: an exact fingerprint shared with 7 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_6588ed5b · shared with 7 other models
Context: 127,072
Max output: 114,364
Modalities: text+image->text
Prompt price: $1.00 / M tokens
Entered the catalogue: 27 January 2025
Last tested: 3 September 2026

Full record JSON Shares with Perplexity: Sonar Pro

Perplexity: Sonar Properplexity/sonar-probuilds on the Llama3 tokenizerHigh

Maker: Perplexity
Label on the catalogue: no family named
What the measurement says: builds on the Llama3 tokenizer
Why high: an exact fingerprint shared with 7 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_6588ed5b · shared with 7 other models
Context: 200,000
Max output: 8,000
Modalities: text+image->text
Prompt price: $3.00 / M tokens
Entered the catalogue: 7 March 2025
Last tested: 3 September 2026

Full record JSON Shares with Perplexity: Sonar

Poolside: Laguna S 2.1poolside/laguna-s-2.1measured, matches nothing else yetMeasured

Maker: Poolside
Label on the catalogue: no family named
What the measurement says: measured, matches nothing else yet
Fingerprint: tk_cd5bb5f6 · unique so far
Context: 1,048,576
Max output: 131,072
Modalities: text->text
Prompt price: $0.09 / M tokens
Entered the catalogue: 21 July 2026
Last tested: 21 August 2026

Full record JSON

Poolside: Laguna XS 2.1poolside/laguna-xs-2.1measured, matches nothing else yetMeasured

Maker: Poolside
Label on the catalogue: no family named
What the measurement says: measured, matches nothing else yet
Fingerprint: tk_08973fc0 · unique so far
Context: 262,144
Max output: 32,768
Modalities: text->text
Prompt price: $0.06 / M tokens
Entered the catalogue: 2 July 2026
Last tested: 21 August 2026

Full record JSON

Qwen: Qwen Plus 0728 (thinking)qwen/qwen-plus-2025-07-28:thinkingwithdrawn from the catalogue · measured as built on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen3
What the measurement says: withdrawn from the catalogue · measured as built on the Qwen tokenizer
Why high: inherited from qwen/qwen-plus-2025-07-28: a serving variant shares its base model's tokenizer
Variant of: Qwen: Qwen Plus 0728
Context: 1,000,000
Max output: 32,768
Modalities: text->text
Prompt price: $0.26 / M tokens
Entered the catalogue: 8 September 2025
Last tested: not yet

Full record JSON

Qwen: Qwen3.5 Plus 2026-04-20qwen/qwen3.5-plus-20260420token accounting unreliable at this endpointNo reading

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen3
What the measurement says: token accounting unreliable at this endpoint
Context: 1,000,000
Max output: 65,536
Modalities: text+image+video->text
Prompt price: $0.30 / M tokens
Entered the catalogue: 27 April 2026
Last tested: 21 August 2026

Full record JSON

Qwen: Qwen3.6 Max Previewqwen/qwen3.6-max-previewtoken accounting unreliable at this endpointNo reading

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen
What the measurement says: token accounting unreliable at this endpoint
Context: 262,144
Max output: 65,536
Modalities: text->text
Prompt price: $1.03 / M tokens
Entered the catalogue: 27 April 2026
Last tested: 21 August 2026

Full record JSON

Qwen: Qwen3.6 Plusqwen/qwen3.6-plustoken accounting unreliable at this endpointNo reading

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen3
What the measurement says: token accounting unreliable at this endpoint
Context: 1,000,000
Max output: 65,536
Modalities: text+image+video->text
Prompt price: $0.33 / M tokens
Entered the catalogue: 2 April 2026
Last tested: 21 August 2026

Full record JSON

Qwen: Qwen3.8 27Bqwen/qwen3.8-27bmeasured, matches nothing else yetMeasured

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen
What the measurement says: measured, matches nothing else yet
Fingerprint: tk_7a0c4565 · unique so far
Context: 1,000,000
Max output: 131,072
Modalities: text+image+video->text
Prompt price: $0.21 / M tokens
Entered the catalogue: 14 August 2026
Last tested: 21 August 2026

Full record JSON

Qwen: Qwen3.8 Maxqwen/qwen3.8-maxwithdrawn from the catalogue · measured as built on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen
What the measurement says: withdrawn from the catalogue · measured as built on the Qwen tokenizer
Why high: an exact fingerprint shared with 14 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_181907f2 · shared with 14 other models
Context: 1,000,000
Max output: 131,072
Modalities: text+image+video->text
Prompt price: $2.00 / M tokens
Entered the catalogue: 3 August 2026
Last tested: 3 September 2026

Full record JSON Shares with Qwen: Qwen3.8 Flash

Reka Edgerekaai/reka-edgemeasured, matches nothing else yetMeasured

Maker: Rekaai
Label on the catalogue: no family named
What the measurement says: measured, matches nothing else yet
Fingerprint: tk_9f6f8410 · unique so far
Context: 16,384
Max output: 14,745
Modalities: text+image+video->text
Prompt price: $0.10 / M tokens
Entered the catalogue: 20 March 2026
Last tested: 21 August 2026

Full record JSON

Reka Flash 3rekaai/reka-flash-3measured, matches nothing else yetMeasured

Maker: Rekaai
Label on the catalogue: no family named
What the measurement says: measured, matches nothing else yet
Context: 65,536
Max output: 58,982
Modalities: text->text
Prompt price: $0.10 / M tokens
Entered the catalogue: 12 March 2025
Last tested: 21 August 2026

Full record JSON

Relace: Relace Searchrelace/relace-searchbuilds on the Qwen tokenizerHigh

Maker: Relace
Label on the catalogue: no family named
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 36 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_5410b38e · shared with 36 other models
Context: 256,000
Max output: 128,000
Modalities: text->text
Prompt price: $1.00 / M tokens
Entered the catalogue: 8 December 2025
Last tested: 3 September 2026

Full record JSON Shares with Dots Studio: Dots3-Note Preview (free)

StepFun: Step 3.5 Flashstepfun/step-3.5-flashbuilds on the DeepSeek tokenizerHigh

Maker: StepFun
Label on the catalogue: no family named
What the measurement says: builds on the DeepSeek tokenizer
Why high: an exact fingerprint shared with 12 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_73c4f0dc · shared with 12 other models
Context: 262,144
Max output: 65,536
Modalities: text->text
Prompt price: $0.10 / M tokens
Entered the catalogue: 29 January 2026
Last tested: 21 August 2026
Verified finding: StepFun's own Step-3 repository ships a tokenizer behaviourally identical to DeepSeek-V3's: run over the 50 strings offline the two agree on every one, and both declare a 128,815-entry vocabulary. The endpoint's counts match as well, so this model sitting in t…

Full record JSON Shares with DeepSeek: DeepSeek V4 Flash Vision Exp

StepFun: Step 3.7 Flashstepfun/step-3.7-flashbuilds on the DeepSeek tokenizerHigh

Maker: StepFun
Label on the catalogue: no family named
What the measurement says: builds on the DeepSeek tokenizer
Why high: an exact fingerprint shared with 12 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_73c4f0dc · shared with 12 other models
Context: 262,144
Max output: 230,400
Modalities: text+image+video->text
Prompt price: $0.20 / M tokens
Entered the catalogue: 28 May 2026
Last tested: 21 August 2026
Verified finding: As with Step 3.5 Flash: StepFun's own Step-3 repository ships a tokenizer behaviourally identical to DeepSeek-V3's over all 50 strings, and this endpoint counts the same way. Its place in the DeepSeek signature group is genuine lineage reuse by StepFun.…

Full record JSON Shares with DeepSeek: DeepSeek V4 Flash Vision Exp

Tencent: Hunyuan A13B Instructtencent/hunyuan-a13b-instructits own Tencent tokenizer groupModerate

Maker: Tencent
Label on the catalogue: no family named
What the measurement says: its own Tencent tokenizer group
Why moderate: near-exact agreement (49 of 50 strings) with tencent/hy-mt2-7b, short of a full exact signature
Fingerprint: tk_856fd527 · unique so far
Context: 131,072
Max output: 117,964
Modalities: text->text
Prompt price: $0.14 / M tokens
Entered the catalogue: 8 July 2025
Last tested: 21 August 2026

Full record JSON

Tencent: Hy-MT2-1.8Btencent/hy-mt2-1.8bits own Tencent tokenizer groupHigh

Maker: Tencent
Label on the catalogue: no family named
What the measurement says: its own Tencent tokenizer group
Why high: an exact fingerprint shared with 3 models
Fingerprint: tk_2b541395 · shared with 3 other models
Context: 8,192
Max output: 4,096
Modalities: text->text
Prompt price: $0.04 / M tokens
Entered the catalogue: 20 August 2026
Last tested: 21 August 2026

Full record JSON Shares with Tencent: Hy-MT2-30B-A3B

Tencent: Hy-MT2-30B-A3Btencent/hy-mt2-30b-a3bits own Tencent tokenizer groupHigh

Maker: Tencent
Label on the catalogue: no family named
What the measurement says: its own Tencent tokenizer group
Why high: an exact fingerprint shared with 3 models
Fingerprint: tk_2b541395 · shared with 3 other models
Context: 8,192
Max output: 4,096
Modalities: text->text
Prompt price: $0.07 / M tokens
Entered the catalogue: 20 August 2026
Last tested: 21 August 2026

Full record JSON Shares with Tencent: Hy-MT2-1.8B

Tencent: Hy-MT2-7Btencent/hy-mt2-7bits own Tencent tokenizer groupModerate

Maker: Tencent
Label on the catalogue: no family named
What the measurement says: its own Tencent tokenizer group
Why moderate: near-exact agreement (49 of 50 strings) with tencent/hunyuan-a13b-instruct, short of a full exact signature
Fingerprint: tk_70a22c4f · unique so far
Context: 8,192
Max output: 4,096
Modalities: text->text
Prompt price: $0.07 / M tokens
Entered the catalogue: 19 August 2026
Last tested: 3 September 2026

Full record JSON

Tencent: Hy3tencent/hy3its own Tencent tokenizer groupHigh

Maker: Tencent
Label on the catalogue: no family named
What the measurement says: its own Tencent tokenizer group
Why high: an exact fingerprint shared with 3 models
Fingerprint: tk_2b541395 · shared with 3 other models
Context: 262,144
Max output: 128,000
Modalities: text->text
Prompt price: $0.13 / M tokens
Entered the catalogue: 6 July 2026
Last tested: 21 August 2026

Full record JSON Shares with Tencent: Hy-MT2-1.8B

Tencent: Hy3 previewtencent/hy3-previewits own Tencent tokenizer groupHigh

Maker: Tencent
Label on the catalogue: no family named
What the measurement says: its own Tencent tokenizer group
Why high: an exact fingerprint shared with 3 models
Fingerprint: tk_2b541395 · shared with 3 other models
Context: 262,144
Max output: 235,929
Modalities: text->text
Prompt price: $0.18 / M tokens
Entered the catalogue: 22 April 2026
Last tested: 21 August 2026

Full record JSON Shares with Tencent: Hy-MT2-1.8B

Tencent: Hy4 previewtencent/hy4-previewmeasured, matches nothing else yetMeasured

Maker: Tencent
Label on the catalogue: no family named
What the measurement says: measured, matches nothing else yet
Fingerprint: tk_5e7942ae · unique so far
Context: 1,048,576
Max output: 64,000
Modalities: text->text
Prompt price: $0.83 / M tokens
Entered the catalogue: 28 August 2026
Last tested: 3 September 2026

Full record JSON

TheDrummer: Cydonia 24B V4.1thedrummer/cydonia-24b-v4.1builds on the Mistral tokenizerModerate

Maker: Thedrummer
Label on the catalogue: no family named
What the measurement says: builds on the Mistral tokenizer
Why moderate: near-exact agreement (49 of 49 strings) with mistralai/mistral-small-24b-instruct-2501, short of a full exact signature
Context: 131,072
Max output: 117,964
Modalities: text->text
Prompt price: $0.30 / M tokens
Entered the catalogue: 27 September 2025
Last tested: 21 August 2026

Full record JSON

TheDrummer: Rocinante 12Bthedrummer/rocinante-12bwithdrawn from the catalogueNo reading

Maker: Thedrummer
Label on the catalogue: Qwen
What the measurement says: withdrawn from the catalogue
Context: 65,536
Max output: 65,536
Modalities: text->text
Prompt price: $0.25 / M tokens
Entered the catalogue: 30 September 2024
Last tested: not yet

Full record JSON

TheDrummer: Skyfall 36B V2thedrummer/skyfall-36b-v2builds on the Mistral tokenizerHigh

Maker: Thedrummer
Label on the catalogue: no family named
What the measurement says: builds on the Mistral tokenizer
Why high: an exact fingerprint shared with 2 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_ddc193e9 · shared with 2 other models
Context: 32,768
Max output: 29,491
Modalities: text->text
Prompt price: $0.55 / M tokens
Entered the catalogue: 10 March 2025
Last tested: 22 August 2026

Full record JSON Shares with Venice: Uncensored

TheDrummer: UnslopNemo 12Bthedrummer/unslopnemo-12bmeasured, matches nothing else yetMeasured

Maker: Thedrummer
Label on the catalogue: Mistral
What the measurement says: measured, matches nothing else yet
Fingerprint: tk_f573b76b · unique so far
Context: 1,024,000
Max output: 819,200
Modalities: text->text
Prompt price: $0.40 / M tokens
Entered the catalogue: 8 November 2024
Last tested: 22 August 2026

Full record JSON

Thinking Machines: Inklingthinkingmachines/inklingbuilds on the GPT tokenizerHigh

Maker: Thinking Machines
Label on the catalogue: no family named
What the measurement says: builds on the GPT tokenizer
Why high: an exact fingerprint shared with 31 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_d1411c9d · shared with 31 other models
Context: 1,048,576
Max output: 471,859
Modalities: text+image+audio->text
Prompt price: $1.00 / M tokens
Entered the catalogue: 17 July 2026
Last tested: 3 September 2026

Full record JSON Shares with Thinking Machines: Inkling Small

Thinking Machines: Inkling (batch)thinkingmachines/inkling:batchbuilds on the GPT tokenizerHigh

Maker: Thinking Machines
Label on the catalogue: no family named
What the measurement says: builds on the GPT tokenizer
Why high: inherited from thinkingmachines/inkling: a serving variant shares its base model's tokenizer
Variant of: Thinking Machines: Inkling
Context: 524,288
Max output: 471,859
Modalities: text+image+audio->text
Prompt price: $1.00 / M tokens
Entered the catalogue: 17 July 2026
Last tested: not yet

Full record JSON

Thinking Machines: Inkling (free)thinkingmachines/inkling:freebuilds on the GPT tokenizerHigh

Maker: Thinking Machines
Label on the catalogue: no family named
What the measurement says: builds on the GPT tokenizer
Why high: inherited from thinkingmachines/inkling: a serving variant shares its base model's tokenizer
Variant of: Thinking Machines: Inkling
Context: 1,048,576
Max output: 262,144
Modalities: text+image+audio->text
Prompt price: $0 / M tokens
Entered the catalogue: 17 July 2026
Last tested: not yet

Full record JSON

Thinking Machines: Inkling Smallthinkingmachines/inkling-smallbuilds on the GPT tokenizerHigh

Maker: Thinking Machines
Label on the catalogue: no family named
What the measurement says: builds on the GPT tokenizer
Why high: an exact fingerprint shared with 31 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_d1411c9d · shared with 31 other models
Context: 1,048,576
Max output: 262,144
Modalities: text+image+audio->text
Prompt price: $0.45 / M tokens
Entered the catalogue: 30 July 2026
Last tested: 22 August 2026

Full record JSON Shares with Thinking Machines: Inkling

Thinking Machines: Inkling Small (batch)thinkingmachines/inkling-small:batchwithdrawn from the catalogue · measured as built on the GPT tokenizerHigh

Maker: Thinking Machines
Label on the catalogue: no family named
What the measurement says: withdrawn from the catalogue · measured as built on the GPT tokenizer
Why high: inherited from thinkingmachines/inkling-small: a serving variant shares its base model's tokenizer
Variant of: Thinking Machines: Inkling Small
Context: 524,288
Max output: 471,859
Modalities: text+image+audio->text
Prompt price: $0.50 / M tokens
Entered the catalogue: 30 July 2026
Last tested: not yet

Full record JSON

Thinking Machines: Inkling Small (free)thinkingmachines/inkling-small:freebuilds on the GPT tokenizerHigh

Maker: Thinking Machines
Label on the catalogue: no family named
What the measurement says: builds on the GPT tokenizer
Why high: inherited from thinkingmachines/inkling-small: a serving variant shares its base model's tokenizer
Variant of: Thinking Machines: Inkling Small
Context: 1,048,576
Max output: 262,144
Modalities: text+image+audio->text
Prompt price: $0 / M tokens
Entered the catalogue: 30 July 2026
Last tested: not yet

Full record JSON

TypeSafe: Jev 1.13typesafe/jev-1.13measured, matches nothing else yetMeasured

Maker: TypeSafe
Label on the catalogue: no family named
What the measurement says: measured, matches nothing else yet
Fingerprint: tk_5e398719 · unique so far
Context: 32,000
Max output: 28,800
Modalities: text->decisions
Prompt price: $0.04 / M tokens
Entered the catalogue: 18 September 2026
Last tested: 18 September 2026

Full record JSON

Union Alphastealth/union-alphalikely Llama3 familyModerate

Maker: Undisclosed (stealth)
Label on the catalogue: no family named
What the measurement says: likely Llama3 family
Why moderate: near-exact agreement (46 of 47 strings) with meta-llama/llama-3.2-3b-instruct, short of a full exact signature
Context: 262,144
Max output: 131,072
Modalities: text+image->text
Prompt price: $0 / M tokens
Entered the catalogue: 16 September 2026
Last tested: 17 September 2026
Verified finding: Listed anonymously on 16 September 2026 and measured the same day. This endpoint returns TWO different token counts for a byte-identical request, and they describe different tokenizers, which is why early readings of it disagreed. A differential test settles w…

Full record JSON

Upstage: Solar Pro 3upstage/solar-pro-3its own Upstage tokenizer groupModerate

Maker: Upstage
Label on the catalogue: no family named
What the measurement says: its own Upstage tokenizer group
Why moderate: an exact fingerprint match with one sibling only, and no second signal of a different kind yet
Fingerprint: tk_865d84ce · shared with 1 other model
Context: 131,072
Max output: 117,964
Modalities: text->text
Prompt price: $0.15 / M tokens
Entered the catalogue: 27 January 2026
Last tested: 21 August 2026

Full record JSON Shares with Upstage: Solar Pro 4

Upstage: Solar Pro 4upstage/solar-pro4its own Upstage tokenizer groupModerate

Maker: Upstage
Label on the catalogue: no family named
What the measurement says: its own Upstage tokenizer group
Why moderate: an exact fingerprint match with one sibling only, and no second signal of a different kind yet
Fingerprint: tk_865d84ce · shared with 1 other model
Context: 524,288
Max output: 131,072
Modalities: text->text
Prompt price: $0.09 / M tokens
Entered the catalogue: 10 August 2026
Last tested: 21 August 2026

Full record JSON Shares with Upstage: Solar Pro 3

Venice: Uncensoredcognitivecomputations/dolphin-mistral-24b-venice-editionbuilds on the Mistral tokenizerHigh

Maker: Cognitivecomputations
Label on the catalogue: no family named
What the measurement says: builds on the Mistral tokenizer
Why high: an exact fingerprint shared with 2 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_ddc193e9 · shared with 2 other models
Context: 128,000
Max output: 8,192
Modalities: text->text
Prompt price: $0.20 / M tokens
Entered the catalogue: 9 July 2025
Last tested: 21 August 2026

Full record JSON Shares with TheDrummer: Skyfall 36B V2

WizardLM-2 8x22Bmicrosoft/wizardlm-2-8x22bmeasured, matches nothing else yetMeasured

Maker: Microsoft
Label on the catalogue: Mistral
What the measurement says: measured, matches nothing else yet
Fingerprint: tk_a49eb75d · unique so far
Context: 65,535
Max output: 8,000
Modalities: text->text
Prompt price: $0.62 / M tokens
Entered the catalogue: 16 April 2024
Last tested: 22 August 2026

Full record JSON

Writer: Palmyra X5writer/palmyra-x5builds on the Qwen tokenizerHigh

Maker: Writer
Label on the catalogue: no family named
What the measurement says: builds on the Qwen tokenizer
Why high: one template-boundary shift from a group whose members all declare the same family
Fingerprint: tk_920d45ce · unique so far
Context: 1,040,000
Max output: 8,192
Modalities: text->text
Prompt price: $0.60 / M tokens
Entered the catalogue: 21 January 2026
Last tested: 3 September 2026

Full record JSON

Xiaomi: MiMo-V2.5xiaomi/mimo-v2.5builds on the Qwen tokenizerHigh

Maker: Xiaomi
Label on the catalogue: no family named
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 36 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_5410b38e · shared with 36 other models
Context: 1,050,000
Max output: 131,072
Modalities: text+image+audio+video->text
Prompt price: $0.14 / M tokens
Entered the catalogue: 22 April 2026
Last tested: 21 August 2026

Full record JSON Shares with Dots Studio: Dots3-Note Preview (free)

Xiaomi: MiMo-V2.5-Proxiaomi/mimo-v2.5-probuilds on the Qwen tokenizerHigh

Maker: Xiaomi
Label on the catalogue: no family named
What the measurement says: builds on the Qwen tokenizer
Why high: one template-boundary shift from a group whose members all declare the same family
Fingerprint: tk_9c4e2396 · unique so far
Context: 1,050,000
Max output: 131,072
Modalities: text->text
Prompt price: $0.43 / M tokens
Entered the catalogue: 22 April 2026
Last tested: 22 August 2026

Full record JSON

Z.ai: GLM 4.5z-ai/glm-4.5its own Z.ai tokenizer groupHigh

Maker: Z.ai
Label on the catalogue: no family named
What the measurement says: its own Z.ai tokenizer group
Why high: an exact fingerprint shared with 6 models
Fingerprint: tk_3eaaf3e0 · shared with 6 other models
Context: 131,072
Max output: 98,304
Modalities: text->text
Prompt price: $0.60 / M tokens
Entered the catalogue: 25 July 2025
Last tested: 3 September 2026

Full record JSON Shares with Z.ai: GLM 5V Turbo

Z.ai: GLM 4.5 Airz-ai/glm-4.5-airits own Z.ai tokenizer groupHigh

Maker: Z.ai
Label on the catalogue: no family named
What the measurement says: its own Z.ai tokenizer group
Why high: an exact fingerprint shared with 6 models
Fingerprint: tk_3eaaf3e0 · shared with 6 other models
Context: 131,072
Max output: 98,304
Modalities: text->text
Prompt price: $0.13 / M tokens
Entered the catalogue: 25 July 2025
Last tested: 21 August 2026

Full record JSON Shares with Z.ai: GLM 5V Turbo

Z.ai: GLM 4.5Vz-ai/glm-4.5vits own Z.ai tokenizer groupHigh

Maker: Z.ai
Label on the catalogue: no family named
What the measurement says: its own Z.ai tokenizer group
Why high: an exact fingerprint shared with 6 models
Fingerprint: tk_3eaaf3e0 · shared with 6 other models
Context: 65,536
Max output: 16,384
Modalities: text+image->text
Prompt price: $0.60 / M tokens
Entered the catalogue: 11 August 2025
Last tested: 22 August 2026

Full record JSON Shares with Z.ai: GLM 5V Turbo

Z.ai: GLM 4.6z-ai/glm-4.6its own Z.ai tokenizer groupHigh

Maker: Z.ai
Label on the catalogue: no family named
What the measurement says: its own Z.ai tokenizer group
Why high: an exact fingerprint shared with 6 models
Fingerprint: tk_3eaaf3e0 · shared with 6 other models
Context: 204,800
Max output: 16,384
Modalities: text->text
Prompt price: $0.43 / M tokens
Entered the catalogue: 30 September 2025
Last tested: 22 August 2026

Full record JSON Shares with Z.ai: GLM 5V Turbo

Z.ai: GLM 4.6Vz-ai/glm-4.6vits own Z.ai tokenizer groupHigh

Maker: Z.ai
Label on the catalogue: no family named
What the measurement says: its own Z.ai tokenizer group
Why high: an exact fingerprint shared with 6 models
Fingerprint: tk_3eaaf3e0 · shared with 6 other models
Context: 131,072
Max output: 32,768
Modalities: text+image+video->text
Prompt price: $0.30 / M tokens
Entered the catalogue: 8 December 2025
Last tested: 21 August 2026

Full record JSON Shares with Z.ai: GLM 5V Turbo

Z.ai: GLM 4.7z-ai/glm-4.7its own Z.ai tokenizer groupHigh

Maker: Z.ai
Label on the catalogue: no family named
What the measurement says: its own Z.ai tokenizer group
Why high: an exact fingerprint shared with 6 models
Fingerprint: tk_3eaaf3e0 · shared with 6 other models
Context: 204,800
Max output: 131,072
Modalities: text->text
Prompt price: $0.40 / M tokens
Entered the catalogue: 22 December 2025
Last tested: 22 August 2026

Full record JSON Shares with Z.ai: GLM 5V Turbo

Z.ai: GLM 4.7 Flashz-ai/glm-4.7-flashmeasured, matches nothing else yetMeasured

Maker: Z.ai
Label on the catalogue: no family named
What the measurement says: measured, matches nothing else yet
Fingerprint: tk_133b086c · shared with 6 other models
Context: 200,000
Max output: 117,964
Modalities: text->text
Prompt price: $0.06 / M tokens
Entered the catalogue: 19 January 2026
Last tested: 21 August 2026

Full record JSON Shares with Z.ai: GLM 5.3 Flash

Z.ai: GLM 5z-ai/glm-5measured, matches nothing else yetMeasured

Maker: Z.ai
Label on the catalogue: no family named
What the measurement says: measured, matches nothing else yet
Fingerprint: tk_133b086c · shared with 6 other models
Context: 204,800
Max output: 128,000
Modalities: text->text
Prompt price: $0.60 / M tokens
Entered the catalogue: 11 February 2026
Last tested: 3 September 2026

Full record JSON Shares with Z.ai: GLM 5.3 Flash

Z.ai: GLM 5 Turboz-ai/glm-5-turbomeasured, matches nothing else yetMeasured

Maker: Z.ai
Label on the catalogue: no family named
What the measurement says: measured, matches nothing else yet
Fingerprint: tk_133b086c · shared with 6 other models
Context: 202,752
Max output: 131,072
Modalities: text->text
Prompt price: $1.20 / M tokens
Entered the catalogue: 15 March 2026
Last tested: 3 September 2026

Full record JSON Shares with Z.ai: GLM 5.3 Flash

Z.ai: GLM 5.1z-ai/glm-5.1measured, matches nothing else yetMeasured

Maker: Z.ai
Label on the catalogue: no family named
What the measurement says: measured, matches nothing else yet
Fingerprint: tk_133b086c · shared with 6 other models
Context: 204,800
Max output: 128,000
Modalities: text->text
Prompt price: $0.97 / M tokens
Entered the catalogue: 7 April 2026
Last tested: 3 September 2026

Full record JSON Shares with Z.ai: GLM 5.3 Flash

Z.ai: GLM 5.2z-ai/glm-5.2measured, matches nothing else yetMeasured

Maker: Z.ai
Label on the catalogue: no family named
What the measurement says: measured, matches nothing else yet
Fingerprint: tk_1d05586d · unique so far
Context: 1,048,576
Max output: 128,000
Modalities: text->text
Prompt price: $1.40 / M tokens
Entered the catalogue: 16 June 2026
Last tested: 21 August 2026

Full record JSON

Z.ai: GLM 5.3z-ai/glm-5.3measured, matches nothing else yetMeasured

Maker: Z.ai
Label on the catalogue: no family named
What the measurement says: measured, matches nothing else yet
Fingerprint: tk_133b086c · shared with 6 other models
Context: 1,310,720
Max output: 943,717
Modalities: text->text
Prompt price: $1.40 / M tokens
Entered the catalogue: 18 August 2026
Last tested: 21 August 2026

Full record JSON Shares with Z.ai: GLM 5.3 Flash

Z.ai: GLM 5.3 Flashz-ai/glm-5.3-flashmeasured, matches nothing else yetMeasured

Maker: Z.ai
Label on the catalogue: no family named
What the measurement says: measured, matches nothing else yet
Fingerprint: tk_133b086c · shared with 6 other models
Context: 1,310,720
Max output: 131,072
Modalities: text+image+video->text
Prompt price: $0.09 / M tokens
Entered the catalogue: 26 August 2026
Last tested: 3 September 2026

Full record JSON Shares with Z.ai: GLM 5.3

Z.ai: GLM 5V Turboz-ai/glm-5v-turboits own Z.ai tokenizer groupHigh

Maker: Z.ai
Label on the catalogue: no family named
What the measurement says: its own Z.ai tokenizer group
Why high: an exact fingerprint shared with 6 models
Fingerprint: tk_3eaaf3e0 · shared with 6 other models
Context: 202,752
Max output: 131,072
Modalities: text+image+video->text
Prompt price: $1.20 / M tokens
Entered the catalogue: 1 April 2026
Last tested: 3 September 2026

Full record JSON Shares with Z.ai: GLM 4.7

Amazon: Nova Lite 1.0amazon/nova-lite-v1builds on the Nova tokenizerVery high

Maker: Amazon
Label on the catalogue: Nova
What the measurement says: builds on the Nova tokenizer
Why very high: an exact fingerprint shared with 2 models and an identical API contract inside the same group: two signals of different kinds agree
Fingerprint: tk_76e424dd · shared with 2 other models
Context: 300,000
Max output: 5,120
Modalities: text+image->text
Prompt price: $0.06 / M tokens
Entered the catalogue: 5 December 2024
Last tested: 21 August 2026

Full record JSON Shares with Amazon: Nova Micro 1.0

Amazon: Nova Micro 1.0amazon/nova-micro-v1builds on the Nova tokenizerHigh

Maker: Amazon
Label on the catalogue: Nova
What the measurement says: builds on the Nova tokenizer
Why high: an exact fingerprint shared with 2 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_76e424dd · shared with 2 other models
Context: 128,000
Max output: 5,120
Modalities: text->text
Prompt price: $0.04 / M tokens
Entered the catalogue: 5 December 2024
Last tested: 21 August 2026

Full record JSON Shares with Amazon: Nova Lite 1.0

Amazon: Nova Pro 1.0amazon/nova-pro-v1builds on the Nova tokenizerVery high

Maker: Amazon
Label on the catalogue: Nova
What the measurement says: builds on the Nova tokenizer
Why very high: an exact fingerprint shared with 2 models and an identical API contract inside the same group: two signals of different kinds agree
Fingerprint: tk_76e424dd · shared with 2 other models
Context: 300,000
Max output: 5,120
Modalities: text+image->text
Prompt price: $0.80 / M tokens
Entered the catalogue: 5 December 2024
Last tested: 3 September 2026

Full record JSON Shares with Amazon: Nova Lite 1.0

Anthropic: Claude 3 Haikuanthropic/claude-3-haikubuilds on the Claude tokenizerHigh

Maker: Anthropic
Label on the catalogue: Claude
What the measurement says: builds on the Claude tokenizer
Why high: an exact fingerprint shared with 1 model that declares the same family, without a second signal of a different kind yet
Fingerprint: tk_2d06485c · shared with 1 other model
Context: 200,000
Max output: 4,096
Modalities: text+image->text
Prompt price: $0.25 / M tokens
Entered the catalogue: 13 March 2024
Last tested: 21 August 2026

Full record JSON Shares with Anthropic: Claude Haiku 4.5

Anthropic: Claude Fable 5anthropic/claude-fable-5builds on the Claude tokenizerModerate

Maker: Anthropic
Label on the catalogue: Claude
What the measurement says: builds on the Claude tokenizer
Why moderate: near-exact agreement (44 of 44 strings) with anthropic/claude-sonnet-5, short of a full exact signature
Context: 1,000,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $10.0 / M tokens
Entered the catalogue: 9 June 2026
Last tested: 3 September 2026

Full record JSON

Anthropic: Claude Fable 5 (batch)anthropic/claude-fable-5:batchbuilds on the Claude tokenizerModerate

Maker: Anthropic
Label on the catalogue: Claude
What the measurement says: builds on the Claude tokenizer
Why moderate: inherited from anthropic/claude-fable-5: a serving variant shares its base model's tokenizer
Variant of: Anthropic: Claude Fable 5
Context: 1,000,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $5.00 / M tokens
Entered the catalogue: 9 June 2026
Last tested: not yet

Full record JSON

Anthropic: Claude Fable 5.1anthropic/claude-fable-5.1builds on the Claude tokenizerModerate

Maker: Anthropic
Label on the catalogue: Claude
What the measurement says: builds on the Claude tokenizer
Why moderate: near-exact agreement (49 of 49 strings) with anthropic/claude-opus-5, short of a full exact signature
Context: 1,000,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $10.0 / M tokens
Entered the catalogue: 1 September 2026
Last tested: 3 September 2026

Full record JSON

Anthropic: Claude Fable 5.1 (batch)anthropic/claude-fable-5.1:batchbuilds on the Claude tokenizerModerate

Maker: Anthropic
Label on the catalogue: Claude
What the measurement says: builds on the Claude tokenizer
Why moderate: inherited from anthropic/claude-fable-5.1: a serving variant shares its base model's tokenizer
Variant of: Anthropic: Claude Fable 5.1
Context: 1,000,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $5.00 / M tokens
Entered the catalogue: 1 September 2026
Last tested: not yet

Full record JSON

Anthropic: Claude Haiku 4.5anthropic/claude-haiku-4.5builds on the Claude tokenizerHigh

Maker: Anthropic
Label on the catalogue: Claude
What the measurement says: builds on the Claude tokenizer
Why high: an exact fingerprint shared with 1 model that declares the same family, without a second signal of a different kind yet
Fingerprint: tk_2d06485c · shared with 1 other model
Context: 200,000
Max output: 64,000
Modalities: text+image+file->text
Prompt price: $1.00 / M tokens
Entered the catalogue: 15 October 2025
Last tested: 3 September 2026

Full record JSON Shares with Anthropic: Claude 3 Haiku

Anthropic: Claude Haiku 4.5 (batch)anthropic/claude-haiku-4.5:batchbuilds on the Claude tokenizerHigh

Maker: Anthropic
Label on the catalogue: Claude
What the measurement says: builds on the Claude tokenizer
Why high: inherited from anthropic/claude-haiku-4.5: a serving variant shares its base model's tokenizer
Variant of: Anthropic: Claude Haiku 4.5
Context: 200,000
Max output: 64,000
Modalities: text+image+file->text
Prompt price: $0.50 / M tokens
Entered the catalogue: 15 October 2025
Last tested: not yet

Full record JSON

Anthropic: Claude Opus 4anthropic/claude-opus-4not measuredNo reading

Maker: Anthropic
Label on the catalogue: Claude
What the measurement says: not measured
Context: 200,000
Max output: 32,000
Modalities: text+image+file->text
Prompt price: $15.0 / M tokens
Entered the catalogue: 22 May 2025
Last tested: not yet

Full record JSON

Anthropic: Claude Opus 4.1anthropic/claude-opus-4.1not measuredNo reading

Maker: Anthropic
Label on the catalogue: Claude
What the measurement says: not measured
Context: 200,000
Max output: 32,000
Modalities: text+image+file->text
Prompt price: $15.0 / M tokens
Entered the catalogue: 5 August 2025
Last tested: not yet

Full record JSON

Anthropic: Claude Opus 4.1 (batch)anthropic/claude-opus-4.1:batcha serving variant of another entryNo reading

Maker: Anthropic
Label on the catalogue: Claude
What the measurement says: a serving variant of another entry
Variant of: Anthropic: Claude Opus 4.1
Context: 200,000
Max output: 32,000
Modalities: text+image+file->text
Prompt price: $7.50 / M tokens
Entered the catalogue: 5 August 2025
Last tested: not yet

Full record JSON

Anthropic: Claude Opus 4.5anthropic/claude-opus-4.5not measuredNo reading

Maker: Anthropic
Label on the catalogue: Claude
What the measurement says: not measured
Context: 200,000
Max output: 64,000
Modalities: text+image+file->text
Prompt price: $5.00 / M tokens
Entered the catalogue: 24 November 2025
Last tested: not yet

Full record JSON

Anthropic: Claude Opus 4.5 (batch)anthropic/claude-opus-4.5:batcha serving variant of another entryNo reading

Maker: Anthropic
Label on the catalogue: Claude
What the measurement says: a serving variant of another entry
Variant of: Anthropic: Claude Opus 4.5
Context: 200,000
Max output: 64,000
Modalities: text+image+file->text
Prompt price: $2.50 / M tokens
Entered the catalogue: 24 November 2025
Last tested: not yet

Full record JSON

Anthropic: Claude Opus 4.6anthropic/claude-opus-4.6not measuredNo reading

Maker: Anthropic
Label on the catalogue: Claude
What the measurement says: not measured
Context: 1,000,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $5.00 / M tokens
Entered the catalogue: 4 February 2026
Last tested: not yet

Full record JSON

Anthropic: Claude Opus 4.6 (batch)anthropic/claude-opus-4.6:batcha serving variant of another entryNo reading

Maker: Anthropic
Label on the catalogue: Claude
What the measurement says: a serving variant of another entry
Variant of: Anthropic: Claude Opus 4.6
Context: 1,000,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $2.50 / M tokens
Entered the catalogue: 4 February 2026
Last tested: not yet

Full record JSON

Anthropic: Claude Opus 4.7 (batch)anthropic/claude-opus-4.7:batcha serving variant of another entryNo reading

Maker: Anthropic
Label on the catalogue: Claude
What the measurement says: a serving variant of another entry
Variant of: Anthropic: Claude Opus 4.7
Context: 1,000,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $2.50 / M tokens
Entered the catalogue: 16 April 2026
Last tested: not yet

Full record JSON

Anthropic: Claude Opus 4.8anthropic/claude-opus-4.8builds on the Claude tokenizerModerate

Maker: Anthropic
Label on the catalogue: Claude
What the measurement says: builds on the Claude tokenizer
Why moderate: near-exact agreement (49 of 49 strings) with anthropic/claude-sonnet-5, short of a full exact signature
Context: 1,000,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $5.00 / M tokens
Entered the catalogue: 27 May 2026
Last tested: 3 September 2026

Full record JSON

Anthropic: Claude Opus 4.8 (batch)anthropic/claude-opus-4.8:batchbuilds on the Claude tokenizerModerate

Maker: Anthropic
Label on the catalogue: Claude
What the measurement says: builds on the Claude tokenizer
Why moderate: inherited from anthropic/claude-opus-4.8: a serving variant shares its base model's tokenizer
Variant of: Anthropic: Claude Opus 4.8
Context: 1,000,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $2.50 / M tokens
Entered the catalogue: 27 May 2026
Last tested: not yet

Full record JSON

Anthropic: Claude Opus 5anthropic/claude-opus-5builds on the Claude tokenizerModerate

Maker: Anthropic
Label on the catalogue: Claude
What the measurement says: builds on the Claude tokenizer
Why moderate: near-exact agreement (49 of 49 strings) with anthropic/claude-fable-5.1, short of a full exact signature
Context: 1,000,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $5.00 / M tokens
Entered the catalogue: 24 July 2026
Last tested: 3 September 2026

Full record JSON

Anthropic: Claude Opus 5 (batch)anthropic/claude-opus-5:batchbuilds on the Claude tokenizerModerate

Maker: Anthropic
Label on the catalogue: Claude
What the measurement says: builds on the Claude tokenizer
Why moderate: inherited from anthropic/claude-opus-5: a serving variant shares its base model's tokenizer
Variant of: Anthropic: Claude Opus 5
Context: 1,000,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $2.50 / M tokens
Entered the catalogue: 24 July 2026
Last tested: not yet

Full record JSON

Anthropic: Claude Sonnet 4anthropic/claude-sonnet-4not measuredNo reading

Maker: Anthropic
Label on the catalogue: Claude
What the measurement says: not measured
Context: 1,000,000
Max output: 64,000
Modalities: text+image+file->text
Prompt price: $3.00 / M tokens
Entered the catalogue: 22 May 2025
Last tested: not yet

Full record JSON

Anthropic: Claude Sonnet 4.5anthropic/claude-sonnet-4.5not measuredNo reading

Maker: Anthropic
Label on the catalogue: Claude
What the measurement says: not measured
Context: 1,000,000
Max output: 64,000
Modalities: text+image+file->text
Prompt price: $3.00 / M tokens
Entered the catalogue: 29 September 2025
Last tested: not yet

Full record JSON

Anthropic: Claude Sonnet 4.5 (batch)anthropic/claude-sonnet-4.5:batcha serving variant of another entryNo reading

Maker: Anthropic
Label on the catalogue: Claude
What the measurement says: a serving variant of another entry
Variant of: Anthropic: Claude Sonnet 4.5
Context: 1,000,000
Max output: 64,000
Modalities: text+image+file->text
Prompt price: $1.50 / M tokens
Entered the catalogue: 29 September 2025
Last tested: not yet

Full record JSON

Anthropic: Claude Sonnet 4.6anthropic/claude-sonnet-4.6builds on the Claude tokenizerModerate

Maker: Anthropic
Label on the catalogue: Claude
What the measurement says: builds on the Claude tokenizer
Why moderate: near-exact agreement (49 of 49 strings) with anthropic/claude-3-haiku, short of a full exact signature
Context: 1,000,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $3.00 / M tokens
Entered the catalogue: 17 February 2026
Last tested: 3 September 2026

Full record JSON

Anthropic: Claude Sonnet 4.6 (batch)anthropic/claude-sonnet-4.6:batchbuilds on the Claude tokenizerModerate

Maker: Anthropic
Label on the catalogue: Claude
What the measurement says: builds on the Claude tokenizer
Why moderate: inherited from anthropic/claude-sonnet-4.6: a serving variant shares its base model's tokenizer
Variant of: Anthropic: Claude Sonnet 4.6
Context: 1,000,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $1.50 / M tokens
Entered the catalogue: 17 February 2026
Last tested: not yet

Full record JSON

Anthropic: Claude Sonnet 5anthropic/claude-sonnet-5builds on the Claude tokenizerModerate

Maker: Anthropic
Label on the catalogue: Claude
What the measurement says: builds on the Claude tokenizer
Why moderate: near-exact agreement (49 of 49 strings) with anthropic/claude-opus-4.8, short of a full exact signature
Context: 1,000,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $2.00 / M tokens
Entered the catalogue: 30 June 2026
Last tested: 3 September 2026

Full record JSON

Anthropic: Claude Sonnet 5 (batch)anthropic/claude-sonnet-5:batchbuilds on the Claude tokenizerModerate

Maker: Anthropic
Label on the catalogue: Claude
What the measurement says: builds on the Claude tokenizer
Why moderate: inherited from anthropic/claude-sonnet-5: a serving variant shares its base model's tokenizer
Variant of: Anthropic: Claude Sonnet 5
Context: 1,000,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $1.00 / M tokens
Entered the catalogue: 30 June 2026
Last tested: not yet

Full record JSON

Auto Routeropenrouter/autoa router, not one stable modelNo reading

Maker: OpenRouter
Label on the catalogue: Router
What the measurement says: a router, not one stable model
Context: 2,000,000
Max output: –
Modalities: text+image+file+audio+video->text+image
Prompt price: $-1000000.00 / M tokens
Entered the catalogue: 8 November 2023
Last tested: not yet

Full record JSON

Auto Router (Beta)openrouter/auto-betaa router, not one stable modelNo reading

Maker: OpenRouter
Label on the catalogue: Router
What the measurement says: a router, not one stable model
Context: 2,000,000
Max output: –
Modalities: text+image+file+audio+video->text+image
Prompt price: $-1000000.00 / M tokens
Entered the catalogue: 17 July 2026
Last tested: not yet

Full record JSON

Body Builder (beta)openrouter/bodybuildera router, not one stable modelNo reading

Maker: OpenRouter
Label on the catalogue: Router
What the measurement says: a router, not one stable model
Context: 128,000
Max output: –
Modalities: text->text
Prompt price: $-1000000.00 / M tokens
Entered the catalogue: 5 December 2025
Last tested: not yet

Full record JSON

Cohere: Command R (08-2024)cohere/command-r-08-2024its own Cohere tokenizer groupModerate

Maker: Cohere
Label on the catalogue: Cohere
What the measurement says: its own Cohere tokenizer group
Why moderate: near-exact agreement (49 of 49 strings) with cohere/command-r7b-12-2024, short of a full exact signature
Context: 128,000
Max output: 4,000
Modalities: text->text
Prompt price: $0.15 / M tokens
Entered the catalogue: 30 August 2024
Last tested: 21 August 2026

Full record JSON

Cohere: Command R+ (08-2024)cohere/command-r-plus-08-2024not measuredNo reading

Maker: Cohere
Label on the catalogue: Cohere
What the measurement says: not measured
Context: 128,000
Max output: 4,000
Modalities: text->text
Prompt price: $2.50 / M tokens
Entered the catalogue: 30 August 2024
Last tested: not yet

Full record JSON

Cohere: Command R7B (12-2024)cohere/command-r7b-12-2024its own Cohere tokenizer groupModerate

Maker: Cohere
Label on the catalogue: Cohere
What the measurement says: its own Cohere tokenizer group
Why moderate: an exact fingerprint match with one sibling only, and no second signal of a different kind yet
Fingerprint: tk_2729e470 · shared with 1 other model
Context: 128,000
Max output: 4,000
Modalities: text->text
Prompt price: $0.04 / M tokens
Entered the catalogue: 14 December 2024
Last tested: 21 August 2026

Full record JSON Shares with Cohere: Command A

DeepSeek: DeepSeek V3deepseek/deepseek-chatits own DeepSeek tokenizer groupHigh

Maker: DeepSeek
Label on the catalogue: DeepSeek
What the measurement says: its own DeepSeek tokenizer group
Why high: an exact fingerprint shared with 12 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_73c4f0dc · shared with 12 other models
Context: 163,840
Max output: 16,000
Modalities: text->text
Prompt price: $0.26 / M tokens
Entered the catalogue: 26 December 2024
Last tested: 21 August 2026

Full record JSON Shares with DeepSeek: DeepSeek V4 Flash Vision Exp

DeepSeek: DeepSeek V3 0324deepseek/deepseek-chat-v3-0324its own DeepSeek tokenizer groupHigh

Maker: DeepSeek
Label on the catalogue: DeepSeek
What the measurement says: its own DeepSeek tokenizer group
Why high: an exact fingerprint shared with 12 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_73c4f0dc · shared with 12 other models
Context: 163,840
Max output: 147,456
Modalities: text->text
Prompt price: $0.25 / M tokens
Entered the catalogue: 24 March 2025
Last tested: 21 August 2026

Full record JSON Shares with DeepSeek: DeepSeek V4 Flash Vision Exp

DeepSeek: DeepSeek V3.1deepseek/deepseek-chat-v3.1its own DeepSeek tokenizer groupHigh

Maker: DeepSeek
Label on the catalogue: DeepSeek
What the measurement says: its own DeepSeek tokenizer group
Why high: an exact fingerprint shared with 1 model that declares the same family, without a second signal of a different kind yet
Fingerprint: tk_869dc1cf · shared with 1 other model
Context: 163,840
Max output: 32,768
Modalities: text->text
Prompt price: $0.25 / M tokens
Entered the catalogue: 21 August 2025
Last tested: 21 August 2026

Full record JSON Shares with DeepSeek: R1 Distill Llama 70B

DeepSeek: DeepSeek V3.1 Terminusdeepseek/deepseek-v3.1-terminusits own DeepSeek tokenizer groupHigh

Maker: DeepSeek
Label on the catalogue: DeepSeek
What the measurement says: its own DeepSeek tokenizer group
Why high: an exact fingerprint shared with 12 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_73c4f0dc · shared with 12 other models
Context: 163,840
Max output: 32,768
Modalities: text->text
Prompt price: $0.27 / M tokens
Entered the catalogue: 22 September 2025
Last tested: 21 August 2026

Full record JSON Shares with DeepSeek: DeepSeek V4 Flash Vision Exp

DeepSeek: DeepSeek V3.2deepseek/deepseek-v3.2its own DeepSeek tokenizer groupHigh

Maker: DeepSeek
Label on the catalogue: DeepSeek
What the measurement says: its own DeepSeek tokenizer group
Why high: an exact fingerprint shared with 12 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_73c4f0dc · shared with 12 other models
Context: 163,840
Max output: 65,536
Modalities: text->text
Prompt price: $0.27 / M tokens
Entered the catalogue: 1 December 2025
Last tested: 21 August 2026

Full record JSON Shares with DeepSeek: DeepSeek V4 Flash Vision Exp

DeepSeek: DeepSeek V3.2 Expdeepseek/deepseek-v3.2-expits own DeepSeek tokenizer groupHigh

Maker: DeepSeek
Label on the catalogue: DeepSeek
What the measurement says: its own DeepSeek tokenizer group
Why high: an exact fingerprint shared with 12 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_73c4f0dc · shared with 12 other models
Context: 163,840
Max output: 65,536
Modalities: text->text
Prompt price: $0.27 / M tokens
Entered the catalogue: 29 September 2025
Last tested: 21 August 2026

Full record JSON Shares with DeepSeek: DeepSeek V4 Flash Vision Exp

DeepSeek: DeepSeek V4 Flash 0423deepseek/deepseek-v4-flashits own DeepSeek tokenizer groupHigh

Maker: DeepSeek
Label on the catalogue: DeepSeek
What the measurement says: its own DeepSeek tokenizer group
Why high: an exact fingerprint shared with 12 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_73c4f0dc · shared with 12 other models
Context: 1,048,576
Max output: 384,000
Modalities: text->text
Prompt price: $0.09 / M tokens
Entered the catalogue: 24 April 2026
Last tested: 21 August 2026

Full record JSON Shares with DeepSeek: DeepSeek V4 Flash Vision Exp

DeepSeek: DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-0731its own DeepSeek tokenizer groupHigh

Maker: DeepSeek
Label on the catalogue: DeepSeek
What the measurement says: its own DeepSeek tokenizer group
Why high: an exact fingerprint shared with 12 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_73c4f0dc · shared with 12 other models
Context: 1,310,720
Max output: 943,718
Modalities: text->text
Prompt price: $0.06 / M tokens
Entered the catalogue: 31 July 2026
Last tested: 21 August 2026

Full record JSON Shares with DeepSeek: DeepSeek V4 Flash Vision Exp

DeepSeek: DeepSeek V4 Flash 0731 (batch)deepseek/deepseek-v4-flash-0731:batchits own DeepSeek tokenizer groupHigh

Maker: DeepSeek
Label on the catalogue: DeepSeek
What the measurement says: its own DeepSeek tokenizer group
Why high: inherited from deepseek/deepseek-v4-flash-0731: a serving variant shares its base model's tokenizer
Variant of: DeepSeek: DeepSeek V4 Flash 0731
Context: 1,048,576
Max output: 943,718
Modalities: text->text
Prompt price: $0.11 / M tokens
Entered the catalogue: 31 July 2026
Last tested: not yet

Full record JSON

DeepSeek: DeepSeek V4 Flash Vision Expdeepseek/deepseek-v4-flash-vision-expits own DeepSeek tokenizer groupHigh

Maker: DeepSeek
Label on the catalogue: DeepSeek
What the measurement says: its own DeepSeek tokenizer group
Why high: an exact fingerprint shared with 12 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_73c4f0dc · shared with 12 other models
Context: 1,048,576
Max output: 943,718
Modalities: text+image->text
Prompt price: $0.22 / M tokens
Entered the catalogue: 21 August 2026
Last tested: 3 September 2026

Full record JSON Shares with DeepSeek: DeepSeek V4 Pro 0813

DeepSeek: DeepSeek V4 Flash Vision Exp (batch)deepseek/deepseek-v4-flash-vision-exp:batchits own DeepSeek tokenizer groupHigh

Maker: DeepSeek
Label on the catalogue: DeepSeek
What the measurement says: its own DeepSeek tokenizer group
Why high: inherited from deepseek/deepseek-v4-flash-vision-exp: a serving variant shares its base model's tokenizer
Variant of: DeepSeek: DeepSeek V4 Flash Vision Exp
Context: 1,048,576
Max output: 943,718
Modalities: text+image->text
Prompt price: $0.11 / M tokens
Entered the catalogue: 21 August 2026
Last tested: not yet

Full record JSON

DeepSeek: DeepSeek V4 Pro 0423deepseek/deepseek-v4-proits own DeepSeek tokenizer groupHigh

Maker: DeepSeek
Label on the catalogue: DeepSeek
What the measurement says: its own DeepSeek tokenizer group
Why high: an exact fingerprint shared with 12 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_73c4f0dc · shared with 12 other models
Context: 1,048,576
Max output: 393,216
Modalities: text->text
Prompt price: $1.60 / M tokens
Entered the catalogue: 24 April 2026
Last tested: 22 August 2026

Full record JSON Shares with DeepSeek: DeepSeek V4 Flash Vision Exp

DeepSeek: DeepSeek V4 Pro 0813deepseek/deepseek-v4-pro-0813its own DeepSeek tokenizer groupHigh

Maker: DeepSeek
Label on the catalogue: DeepSeek
What the measurement says: its own DeepSeek tokenizer group
Why high: an exact fingerprint shared with 12 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_73c4f0dc · shared with 12 other models
Context: 1,048,576
Max output: 393,216
Modalities: text->text
Prompt price: $0.58 / M tokens
Entered the catalogue: 12 August 2026
Last tested: 21 August 2026

Full record JSON Shares with DeepSeek: DeepSeek V4 Flash Vision Exp

DeepSeek: DeepSeek V4 Pro 0813 (batch)deepseek/deepseek-v4-pro-0813:batchits own DeepSeek tokenizer groupHigh

Maker: DeepSeek
Label on the catalogue: DeepSeek
What the measurement says: its own DeepSeek tokenizer group
Why high: inherited from deepseek/deepseek-v4-pro-0813: a serving variant shares its base model's tokenizer
Variant of: DeepSeek: DeepSeek V4 Pro 0813
Context: 1,048,576
Max output: 943,718
Modalities: text->text
Prompt price: $0.66 / M tokens
Entered the catalogue: 12 August 2026
Last tested: not yet

Full record JSON

DeepSeek: DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flashqueued for measurementNo reading

Maker: DeepSeek
Label on the catalogue: DeepSeek
What the measurement says: queued for measurement
Context: 1,048,576
Max output: 384,000
Modalities: text+image->text
Prompt price: $0.15 / M tokens
Entered the catalogue: 10 September 2026
Last tested: not yet

Full record JSON

DeepSeek: R1 0528deepseek/deepseek-r1-0528its own DeepSeek tokenizer groupHigh

Maker: DeepSeek
Label on the catalogue: DeepSeek
What the measurement says: its own DeepSeek tokenizer group
Why high: an exact fingerprint shared with 12 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_73c4f0dc · shared with 12 other models
Context: 163,840
Max output: 32,768
Modalities: text->text
Prompt price: $0.50 / M tokens
Entered the catalogue: 28 May 2025
Last tested: 3 September 2026

Full record JSON Shares with DeepSeek: DeepSeek V4 Flash Vision Exp

Free Models Routeropenrouter/freea router, not one stable modelNo reading

Maker: OpenRouter
Label on the catalogue: Router
What the measurement says: a router, not one stable model
Context: 200,000
Max output: –
Modalities: text+image->text
Prompt price: $0 / M tokens
Entered the catalogue: 1 February 2026
Last tested: not yet

Full record JSON

Google: Gemini 2.5 Flash (batch)google/gemini-2.5-flash:batcha serving variant of another entryNo reading

Maker: Google
Label on the catalogue: Gemini
What the measurement says: a serving variant of another entry
Variant of: Google: Gemini 2.5 Flash
Context: 1,048,576
Max output: 65,535
Modalities: text+image+file+audio+video->text
Prompt price: $0.15 / M tokens
Entered the catalogue: 17 June 2025
Last tested: not yet

Full record JSON

Google: Gemini 2.5 Flash Litegoogle/gemini-2.5-flash-litebuilds on the Gemini tokenizerHigh

Maker: Google
Label on the catalogue: Gemini
What the measurement says: builds on the Gemini tokenizer
Why high: an exact fingerprint shared with 19 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_59ca250f · shared with 19 other models
Context: 1,048,576
Max output: 65,535
Modalities: text+image+file+audio+video->text
Prompt price: $0.10 / M tokens
Entered the catalogue: 22 July 2025
Last tested: 21 August 2026

Full record JSON Shares with Google: Gemini 3.8 Flash

Google: Gemini 2.5 Flash Lite (batch)google/gemini-2.5-flash-lite:batchbuilds on the Gemini tokenizerHigh

Maker: Google
Label on the catalogue: Gemini
What the measurement says: builds on the Gemini tokenizer
Why high: inherited from google/gemini-2.5-flash-lite: a serving variant shares its base model's tokenizer
Variant of: Google: Gemini 2.5 Flash Lite
Context: 1,048,576
Max output: 65,535
Modalities: text+image+file+audio+video->text
Prompt price: $0.05 / M tokens
Entered the catalogue: 22 July 2025
Last tested: not yet

Full record JSON

Google: Gemini 2.5 Progoogle/gemini-2.5-probuilds on the Gemini tokenizerHigh

Maker: Google
Label on the catalogue: Gemini
What the measurement says: builds on the Gemini tokenizer
Why high: an exact fingerprint shared with 19 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_59ca250f · shared with 19 other models
Context: 1,048,576
Max output: 65,536
Modalities: text+image+file+audio+video->text
Prompt price: $1.25 / M tokens
Entered the catalogue: 17 June 2025
Last tested: 3 September 2026

Full record JSON Shares with Google: Gemini 3.8 Flash

Google: Gemini 2.5 Pro (batch)google/gemini-2.5-pro:batchbuilds on the Gemini tokenizerHigh

Maker: Google
Label on the catalogue: Gemini
What the measurement says: builds on the Gemini tokenizer
Why high: inherited from google/gemini-2.5-pro: a serving variant shares its base model's tokenizer
Variant of: Google: Gemini 2.5 Pro
Context: 1,048,576
Max output: 65,536
Modalities: text+image+file+audio+video->text
Prompt price: $0.63 / M tokens
Entered the catalogue: 17 June 2025
Last tested: not yet

Full record JSON

Google: Gemini 2.5 Pro Preview 06-05google/gemini-2.5-pro-previewbuilds on the Gemini tokenizerHigh

Maker: Google
Label on the catalogue: Gemini
What the measurement says: builds on the Gemini tokenizer
Why high: an exact fingerprint shared with 19 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_59ca250f · shared with 19 other models
Context: 1,048,576
Max output: 65,536
Modalities: text+image+file+audio->text
Prompt price: $1.25 / M tokens
Entered the catalogue: 5 June 2025
Last tested: 3 September 2026

Full record JSON Shares with Google: Gemini 3.8 Flash

Google: Gemini 3 Flash Previewgoogle/gemini-3-flash-previewbuilds on the Gemini tokenizerHigh

Maker: Google
Label on the catalogue: Gemini
What the measurement says: builds on the Gemini tokenizer
Why high: an exact fingerprint shared with 19 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_59ca250f · shared with 19 other models
Context: 1,048,576
Max output: 65,536
Modalities: text+image+file+audio+video->text
Prompt price: $0.50 / M tokens
Entered the catalogue: 17 December 2025
Last tested: 22 August 2026

Full record JSON Shares with Google: Gemini 3.8 Flash

Google: Gemini 3 Flash Preview (batch)google/gemini-3-flash-preview:batchbuilds on the Gemini tokenizerHigh

Maker: Google
Label on the catalogue: Gemini
What the measurement says: builds on the Gemini tokenizer
Why high: inherited from google/gemini-3-flash-preview: a serving variant shares its base model's tokenizer
Variant of: Google: Gemini 3 Flash Preview
Context: 1,048,576
Max output: 65,536
Modalities: text+image+file+audio+video->text
Prompt price: $0.25 / M tokens
Entered the catalogue: 17 December 2025
Last tested: not yet

Full record JSON

Google: Gemini 3.1 Flash Litegoogle/gemini-3.1-flash-litebuilds on the Gemini tokenizerHigh

Maker: Google
Label on the catalogue: Gemini
What the measurement says: builds on the Gemini tokenizer
Why high: an exact fingerprint shared with 19 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_59ca250f · shared with 19 other models
Context: 1,048,576
Max output: 65,536
Modalities: text+image+file+audio+video->text
Prompt price: $0.25 / M tokens
Entered the catalogue: 7 May 2026
Last tested: 21 August 2026

Full record JSON Shares with Google: Gemini 3.8 Flash

Google: Gemini 3.1 Flash Lite (batch)google/gemini-3.1-flash-lite:batchbuilds on the Gemini tokenizerHigh

Maker: Google
Label on the catalogue: Gemini
What the measurement says: builds on the Gemini tokenizer
Why high: inherited from google/gemini-3.1-flash-lite: a serving variant shares its base model's tokenizer
Variant of: Google: Gemini 3.1 Flash Lite
Context: 1,048,576
Max output: 65,536
Modalities: text+image+file+audio+video->text
Prompt price: $0.13 / M tokens
Entered the catalogue: 7 May 2026
Last tested: not yet

Full record JSON

Google: Gemini 3.1 Flash Lite Previewgoogle/gemini-3.1-flash-lite-previewbuilds on the Gemini tokenizerHigh

Maker: Google
Label on the catalogue: Gemini
What the measurement says: builds on the Gemini tokenizer
Why high: an exact fingerprint shared with 19 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_59ca250f · shared with 19 other models
Context: 1,048,576
Max output: 65,536
Modalities: text+image+file+audio+video->text
Prompt price: $0.25 / M tokens
Entered the catalogue: 3 March 2026
Last tested: 21 August 2026

Full record JSON Shares with Google: Gemini 3.8 Flash

Google: Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-previewbuilds on the Gemini tokenizerHigh

Maker: Google
Label on the catalogue: Gemini
What the measurement says: builds on the Gemini tokenizer
Why high: an exact fingerprint shared with 19 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_59ca250f · shared with 19 other models
Context: 1,048,576
Max output: 65,536
Modalities: text+image+file+audio+video->text
Prompt price: $2.00 / M tokens
Entered the catalogue: 19 February 2026
Last tested: 3 September 2026

Full record JSON Shares with Google: Gemini 3.8 Flash

Google: Gemini 3.1 Pro Preview (batch)google/gemini-3.1-pro-preview:batchbuilds on the Gemini tokenizerHigh

Maker: Google
Label on the catalogue: Gemini
What the measurement says: builds on the Gemini tokenizer
Why high: inherited from google/gemini-3.1-pro-preview: a serving variant shares its base model's tokenizer
Variant of: Google: Gemini 3.1 Pro Preview
Context: 1,048,576
Max output: 65,536
Modalities: text+image+file+audio+video->text
Prompt price: $1.00 / M tokens
Entered the catalogue: 19 February 2026
Last tested: not yet

Full record JSON

Google: Gemini 3.1 Pro Preview Custom Toolsgoogle/gemini-3.1-pro-preview-customtoolsbuilds on the Gemini tokenizerHigh

Maker: Google
Label on the catalogue: Gemini
What the measurement says: builds on the Gemini tokenizer
Why high: an exact fingerprint shared with 19 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_59ca250f · shared with 19 other models
Context: 1,048,576
Max output: 65,536
Modalities: text+image+file+audio+video->text
Prompt price: $2.00 / M tokens
Entered the catalogue: 25 February 2026
Last tested: 3 September 2026

Full record JSON Shares with Google: Gemini 3.8 Flash

Google: Gemini 3.5 Flashgoogle/gemini-3.5-flashbuilds on the Gemini tokenizerVery high

Maker: Google
Label on the catalogue: Gemini
What the measurement says: builds on the Gemini tokenizer
Why very high: an exact fingerprint shared with 19 models and an identical API contract inside the same group: two signals of different kinds agree
Fingerprint: tk_59ca250f · shared with 19 other models
Context: 1,048,576
Max output: 65,536
Modalities: text+image+file+audio+video->text
Prompt price: $1.50 / M tokens
Entered the catalogue: 19 May 2026
Last tested: 3 September 2026

Full record JSON Shares with Google: Gemini 3.8 Flash

Google: Gemini 3.5 Flash (batch)google/gemini-3.5-flash:batchbuilds on the Gemini tokenizerVery high

Maker: Google
Label on the catalogue: Gemini
What the measurement says: builds on the Gemini tokenizer
Why very high: inherited from google/gemini-3.5-flash: a serving variant shares its base model's tokenizer
Variant of: Google: Gemini 3.5 Flash
Context: 1,048,576
Max output: 65,536
Modalities: text+image+file+audio+video->text
Prompt price: $0.75 / M tokens
Entered the catalogue: 19 May 2026
Last tested: not yet

Full record JSON

Google: Gemini 3.5 Flash Litegoogle/gemini-3.5-flash-litebuilds on the Gemini tokenizerHigh

Maker: Google
Label on the catalogue: Gemini
What the measurement says: builds on the Gemini tokenizer
Why high: an exact fingerprint shared with 19 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_59ca250f · shared with 19 other models
Context: 1,048,576
Max output: 65,536
Modalities: text+image+file+audio+video->text
Prompt price: $0.30 / M tokens
Entered the catalogue: 21 July 2026
Last tested: 21 August 2026

Full record JSON Shares with Google: Gemini 3.8 Flash

Google: Gemini 3.5 Flash Lite (batch)google/gemini-3.5-flash-lite:batchbuilds on the Gemini tokenizerHigh

Maker: Google
Label on the catalogue: Gemini
What the measurement says: builds on the Gemini tokenizer
Why high: inherited from google/gemini-3.5-flash-lite: a serving variant shares its base model's tokenizer
Variant of: Google: Gemini 3.5 Flash Lite
Context: 1,048,576
Max output: 65,536
Modalities: text+image+file+audio+video->text
Prompt price: $0.15 / M tokens
Entered the catalogue: 21 July 2026
Last tested: not yet

Full record JSON

Google: Gemini 3.6 Flashgoogle/gemini-3.6-flashbuilds on the Gemini tokenizerVery high

Maker: Google
Label on the catalogue: Gemini
What the measurement says: builds on the Gemini tokenizer
Why very high: an exact fingerprint shared with 19 models and an identical API contract inside the same group: two signals of different kinds agree
Fingerprint: tk_59ca250f · shared with 19 other models
Context: 1,048,576
Max output: 65,536
Modalities: text+image+file+audio+video->text
Prompt price: $0.75 / M tokens
Entered the catalogue: 21 July 2026
Last tested: 3 September 2026

Full record JSON Shares with Google: Gemini 3.8 Flash

Google: Gemini 3.6 Flash (batch)google/gemini-3.6-flash:batchbuilds on the Gemini tokenizerVery high

Maker: Google
Label on the catalogue: Gemini
What the measurement says: builds on the Gemini tokenizer
Why very high: inherited from google/gemini-3.6-flash: a serving variant shares its base model's tokenizer
Variant of: Google: Gemini 3.6 Flash
Context: 1,048,576
Max output: 65,536
Modalities: text+image+file+audio+video->text
Prompt price: $0.38 / M tokens
Entered the catalogue: 21 July 2026
Last tested: not yet

Full record JSON

Google: Gemini 3.7 Flashgoogle/gemini-3.7-flashbuilds on the Gemini tokenizerVery high

Maker: Google
Label on the catalogue: Gemini
What the measurement says: builds on the Gemini tokenizer
Why very high: an exact fingerprint shared with 19 models and an identical API contract inside the same group: two signals of different kinds agree
Fingerprint: tk_59ca250f · shared with 19 other models
Context: 1,048,576
Max output: 65,536
Modalities: text+image+file+audio+video->text
Prompt price: $0.75 / M tokens
Entered the catalogue: 13 August 2026
Last tested: 21 August 2026

Full record JSON Shares with Google: Gemini 3.8 Flash

Google: Gemini 3.7 Flash (batch)google/gemini-3.7-flash:batchbuilds on the Gemini tokenizerVery high

Maker: Google
Label on the catalogue: Gemini
What the measurement says: builds on the Gemini tokenizer
Why very high: inherited from google/gemini-3.7-flash: a serving variant shares its base model's tokenizer
Variant of: Google: Gemini 3.7 Flash
Context: 1,048,576
Max output: 65,536
Modalities: text+image+file+audio+video->text
Prompt price: $0.38 / M tokens
Entered the catalogue: 13 August 2026
Last tested: not yet

Full record JSON

Google: Gemini 3.8 Flashgoogle/gemini-3.8-flashbuilds on the Gemini tokenizerVery high

Maker: Google
Label on the catalogue: Gemini
What the measurement says: builds on the Gemini tokenizer
Why very high: an exact fingerprint shared with 19 models and an identical API contract inside the same group: two signals of different kinds agree
Fingerprint: tk_59ca250f · shared with 19 other models
Context: 1,048,576
Max output: 65,536
Modalities: text+image+file+audio+video->text
Prompt price: $0.75 / M tokens
Entered the catalogue: 2 September 2026
Last tested: 3 September 2026

Full record JSON Shares with Google: Gemini 3.7 Flash

Google: Gemini 3.8 Flash (batch)google/gemini-3.8-flash:batchbuilds on the Gemini tokenizerVery high

Maker: Google
Label on the catalogue: Gemini
What the measurement says: builds on the Gemini tokenizer
Why very high: inherited from google/gemini-3.8-flash: a serving variant shares its base model's tokenizer
Variant of: Google: Gemini 3.8 Flash
Context: 1,048,576
Max output: 65,536
Modalities: text+image+file+audio+video->text
Prompt price: $0.38 / M tokens
Entered the catalogue: 2 September 2026
Last tested: not yet

Full record JSON

Google: Gemma 3 12Bgoogle/gemma-3-12b-itbuilds on the Gemini tokenizerHigh

Maker: Google
Label on the catalogue: Gemini
What the measurement says: builds on the Gemini tokenizer
Why high: an exact fingerprint shared with 19 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_59ca250f · shared with 19 other models
Context: 131,072
Max output: 16,384
Modalities: text+image->text
Prompt price: $0.05 / M tokens
Entered the catalogue: 13 March 2025
Last tested: 21 August 2026

Full record JSON Shares with Google: Gemini 3.8 Flash

Google: Gemma 3 27Bgoogle/gemma-3-27b-itbuilds on the Gemini tokenizerHigh

Maker: Google
Label on the catalogue: Gemini
What the measurement says: builds on the Gemini tokenizer
Why high: an exact fingerprint shared with 19 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_59ca250f · shared with 19 other models
Context: 131,072
Max output: 117,964
Modalities: text+image->text
Prompt price: $0.08 / M tokens
Entered the catalogue: 12 March 2025
Last tested: 21 August 2026

Full record JSON Shares with Google: Gemini 3.8 Flash

Google: Gemma 3 4Bgoogle/gemma-3-4b-itbuilds on the Gemini tokenizerHigh

Maker: Google
Label on the catalogue: Gemini
What the measurement says: builds on the Gemini tokenizer
Why high: an exact fingerprint shared with 19 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_59ca250f · shared with 19 other models
Context: 131,072
Max output: 16,384
Modalities: text+image->text
Prompt price: $0.05 / M tokens
Entered the catalogue: 13 March 2025
Last tested: 22 August 2026

Full record JSON Shares with Google: Gemini 3.8 Flash

Google: Gemma 4 26B A4B google/gemma-4-26b-a4b-itbuilds on the Gemma tokenizerHigh

Maker: Google
Label on the catalogue: Gemma
What the measurement says: builds on the Gemma tokenizer
Why high: an exact fingerprint shared with 1 model that declares the same family, without a second signal of a different kind yet
Fingerprint: tk_ba03436b · shared with 1 other model
Context: 262,144
Max output: 235,929
Modalities: text+image+video->text
Prompt price: $0.09 / M tokens
Entered the catalogue: 3 April 2026
Last tested: 21 August 2026

Full record JSON Shares with Google: Gemma 4 31B

Google: Gemma 4 26B A4B (free)google/gemma-4-26b-a4b-it:freebuilds on the Gemma tokenizerHigh

Maker: Google
Label on the catalogue: Gemma
What the measurement says: builds on the Gemma tokenizer
Why high: inherited from google/gemma-4-26b-a4b-it: a serving variant shares its base model's tokenizer
Variant of: Google: Gemma 4 26B A4B
Context: 262,144
Max output: 32,768
Modalities: text+image+video->text
Prompt price: $0 / M tokens
Entered the catalogue: 3 April 2026
Last tested: not yet

Full record JSON

Google: Gemma 4 31Bgoogle/gemma-4-31b-itbuilds on the Gemma tokenizerHigh

Maker: Google
Label on the catalogue: Gemma
What the measurement says: builds on the Gemma tokenizer
Why high: an exact fingerprint shared with 1 model that declares the same family, without a second signal of a different kind yet
Fingerprint: tk_ba03436b · shared with 1 other model
Context: 262,144
Max output: 16,384
Modalities: text+image+video->text
Prompt price: $0.09 / M tokens
Entered the catalogue: 2 April 2026
Last tested: 21 August 2026

Full record JSON Shares with Google: Gemma 4 26B A4B

Google: Gemma 4 31B (free)google/gemma-4-31b-it:freebuilds on the Gemma tokenizerHigh

Maker: Google
Label on the catalogue: Gemma
What the measurement says: builds on the Gemma tokenizer
Why high: inherited from google/gemma-4-31b-it: a serving variant shares its base model's tokenizer
Variant of: Google: Gemma 4 31B
Context: 262,144
Max output: 32,768
Modalities: text+image+video->text
Prompt price: $0 / M tokens
Entered the catalogue: 2 April 2026
Last tested: not yet

Full record JSON

Google: Nano Banana (Gemini 2.5 Flash Image)google/gemini-2.5-flash-imagebuilds on the Gemini tokenizerHigh

Maker: Google
Label on the catalogue: Gemini
What the measurement says: builds on the Gemini tokenizer
Why high: an exact fingerprint shared with 19 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_59ca250f · shared with 19 other models
Context: 32,768
Max output: 8,192
Modalities: text+image->text+image
Prompt price: $0.30 / M tokens
Entered the catalogue: 7 October 2025
Last tested: 3 September 2026

Full record JSON Shares with Google: Gemini 3.8 Flash

Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)google/gemini-3.1-flash-image-previewbuilds on the Gemini tokenizerHigh

Maker: Google
Label on the catalogue: Gemini
What the measurement says: builds on the Gemini tokenizer
Why high: an exact fingerprint shared with 19 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_59ca250f · shared with 19 other models
Context: 65,536
Max output: 58,982
Modalities: text+image->text+image
Prompt price: $0.50 / M tokens
Entered the catalogue: 26 February 2026
Last tested: 22 August 2026

Full record JSON Shares with Google: Gemini 3.8 Flash

Google: Nano Banana 2 (Gemini 3.1 Flash Image)google/gemini-3.1-flash-imagebuilds on the Gemini tokenizerModerate

Maker: Google
Label on the catalogue: Gemini
What the measurement says: builds on the Gemini tokenizer
Why moderate: near-exact agreement (44 of 44 strings) with google/gemini-3.7-flash, short of a full exact signature
Context: 131,072
Max output: 32,768
Modalities: text+image->text+image
Prompt price: $0.50 / M tokens
Entered the catalogue: 18 June 2026
Last tested: 22 August 2026

Full record JSON

Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)google/gemini-3.1-flash-lite-imagebuilds on the Gemini tokenizerHigh

Maker: Google
Label on the catalogue: Gemini
What the measurement says: builds on the Gemini tokenizer
Why high: an exact fingerprint shared with 19 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_59ca250f · shared with 19 other models
Context: 65,536
Max output: 58,982
Modalities: text+image->text+image
Prompt price: $0.25 / M tokens
Entered the catalogue: 30 June 2026
Last tested: 3 September 2026

Full record JSON Shares with Google: Gemini 3.8 Flash

Google: Nano Banana Pro (Gemini 3 Pro Image Preview)google/gemini-3-pro-image-previewnot measuredNo reading

Maker: Google
Label on the catalogue: Gemini
What the measurement says: not measured
Context: 65,536
Max output: 32,768
Modalities: text+image->text+image
Prompt price: $2.00 / M tokens
Entered the catalogue: 20 November 2025
Last tested: not yet

Full record JSON

Google: Nano Banana Pro (Gemini 3 Pro Image)google/gemini-3-pro-imagenot measuredNo reading

Maker: Google
Label on the catalogue: Gemini
What the measurement says: not measured
Context: 131,072
Max output: 32,768
Modalities: text+image->text+image
Prompt price: $2.00 / M tokens
Entered the catalogue: 18 June 2026
Last tested: not yet

Full record JSON

Inception: Mercury 2.5inception/mercury-2.5queued for measurementNo reading

Maker: Inception
Label on the catalogue: no family named
What the measurement says: queued for measurement
Context: 260,000
Max output: 65,536
Modalities: text->text
Prompt price: $0.04 / M tokens
Entered the catalogue: 8 September 2026
Last tested: not yet

Full record JSON

inclusionAI: Ling 3.0 Flash Sante (free)inclusionai/ling-3.0-flash-sante:freequeued for measurementNo reading

Maker: InclusionAI
Label on the catalogue: no family named
What the measurement says: queued for measurement
Context: 262,144
Max output: 32,768
Modalities: text->text
Prompt price: $0 / M tokens
Entered the catalogue: 4 September 2026
Last tested: not yet

Full record JSON

inclusionAI: Ling 3.0 Flash VLinclusionai/ling-3.0-flash-vlqueued for measurementNo reading

Maker: InclusionAI
Label on the catalogue: no family named
What the measurement says: queued for measurement
Context: 131,072
Max output: 32,768
Modalities: text+image+video->text
Prompt price: $0.06 / M tokens
Entered the catalogue: 10 September 2026
Last tested: not yet

Full record JSON

inclusionAI: Ling 3.0 Flash VL (free)inclusionai/ling-3.0-flash-vl:freequeued for measurementNo reading

Maker: InclusionAI
Label on the catalogue: no family named
What the measurement says: queued for measurement
Variant of: inclusionAI: Ling 3.0 Flash VL
Context: 262,144
Max output: 32,768
Modalities: text+image+video->text
Prompt price: $0 / M tokens
Entered the catalogue: 10 September 2026
Last tested: not yet

Full record JSON

Inference.net: Schematron V2 Smallinference-net/schematron-v2-smallqueued for measurementNo reading

Maker: Inference Net
Label on the catalogue: no family named
What the measurement says: queued for measurement
Context: 128,000
Max output: 4,096
Modalities: text->text
Prompt price: $0.05 / M tokens
Entered the catalogue: 12 September 2026
Last tested: not yet

Full record JSON

Inference.net: Schematron V2 Turboinference-net/schematron-v2-turboqueued for measurementNo reading

Maker: Inference Net
Label on the catalogue: no family named
What the measurement says: queued for measurement
Context: 128,000
Max output: 8,192
Modalities: text->text
Prompt price: $0.03 / M tokens
Entered the catalogue: 12 September 2026
Last tested: not yet

Full record JSON

Kwaipilot: KAT-Coder-Pro V2.5kwaipilot/kat-coder-pro-v2.5not measuredNo reading

Maker: Kwaipilot
Label on the catalogue: no family named
What the measurement says: not measured
Context: 262,144
Max output: 235,929
Modalities: text->text
Prompt price: $0.74 / M tokens
Entered the catalogue: 10 July 2026
Last tested: not yet

Full record JSON

Magnum v4 72Banthracite-org/magnum-v4-72bbuilds on the Qwen tokenizerHigh

Maker: Anthracite Org
Label on the catalogue: Qwen
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 36 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_5410b38e · shared with 36 other models
Context: 32,768
Max output: 4,096
Modalities: text->text
Prompt price: $2.50 / M tokens
Entered the catalogue: 22 October 2024
Last tested: 3 September 2026

Full record JSON Shares with Dots Studio: Dots3-Note Preview (free)

Mancer: Weaver (alpha)mancer/weaverbuilds on the Llama2 tokenizerHigh

Maker: Mancer
Label on the catalogue: Llama2
What the measurement says: builds on the Llama2 tokenizer
Why high: one template-boundary shift from a group whose members all declare the same family
Fingerprint: tk_03ecdf53 · unique so far
Context: 8,000
Max output: 6,000
Modalities: text->text
Prompt price: $0.40 / M tokens
Entered the catalogue: 2 August 2023
Last tested: 21 August 2026

Full record JSON

Meta: Llama 3.1 70B Instructmeta-llama/llama-3.1-70b-instructbuilds on the Llama3 tokenizerHigh

Maker: Meta
Label on the catalogue: Llama3
What the measurement says: builds on the Llama3 tokenizer
Why high: an exact fingerprint shared with 7 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_6588ed5b · shared with 7 other models
Context: 131,072
Max output: 16,384
Modalities: text->text
Prompt price: $0.40 / M tokens
Entered the catalogue: 23 July 2024
Last tested: 21 August 2026

Full record JSON Shares with Perplexity: Sonar Pro

Meta: Llama 3.1 8B Instructmeta-llama/llama-3.1-8b-instructbuilds on the Llama3 tokenizerHigh

Maker: Meta
Label on the catalogue: Llama3
What the measurement says: builds on the Llama3 tokenizer
Why high: an exact fingerprint shared with 7 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_6588ed5b · shared with 7 other models
Context: 131,072
Max output: 117,964
Modalities: text->text
Prompt price: $0.05 / M tokens
Entered the catalogue: 23 July 2024
Last tested: 21 August 2026

Full record JSON Shares with Perplexity: Sonar Pro

Meta: Llama 3.2 1B Instructmeta-llama/llama-3.2-1b-instructbuilds on the Llama3 tokenizerHigh

Maker: Meta
Label on the catalogue: Llama3
What the measurement says: builds on the Llama3 tokenizer
Why high: an exact fingerprint shared with 4 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_47615f2d · shared with 4 other models
Context: 60,000
Max output: 54,000
Modalities: text->text
Prompt price: $0.03 / M tokens
Entered the catalogue: 25 September 2024
Last tested: 21 August 2026

Full record JSON Shares with Nous: Hermes 4 405B

Meta: Llama 3.2 3B Instructmeta-llama/llama-3.2-3b-instructbuilds on the Llama3 tokenizerHigh

Maker: Meta
Label on the catalogue: Llama3
What the measurement says: builds on the Llama3 tokenizer
Why high: an exact fingerprint shared with 7 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_6588ed5b · shared with 7 other models
Context: 131,072
Max output: 117,964
Modalities: text->text
Prompt price: $0.05 / M tokens
Entered the catalogue: 25 September 2024
Last tested: 21 August 2026

Full record JSON Shares with Perplexity: Sonar Pro

Meta: Llama 3.3 70B Instructmeta-llama/llama-3.3-70b-instructbuilds on the Llama3 tokenizerHigh

Maker: Meta
Label on the catalogue: Llama3
What the measurement says: builds on the Llama3 tokenizer
Why high: an exact fingerprint shared with 7 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_6588ed5b · shared with 7 other models
Context: 131,072
Max output: 16,384
Modalities: text->text
Prompt price: $0.10 / M tokens
Entered the catalogue: 6 December 2024
Last tested: 21 August 2026

Full record JSON Shares with Perplexity: Sonar Pro

Meta: Llama 4 Maverickmeta-llama/llama-4-maverickbuilds on the Llama4 tokenizerHigh

Maker: Meta
Label on the catalogue: Llama4
What the measurement says: builds on the Llama4 tokenizer
Why high: an exact fingerprint shared with 1 model that declares the same family, without a second signal of a different kind yet
Fingerprint: tk_59e2520c · shared with 1 other model
Context: 1,048,576
Max output: 16,384
Modalities: text+image->text
Prompt price: $0.19 / M tokens
Entered the catalogue: 5 April 2025
Last tested: 21 August 2026

Full record JSON Shares with Meta: Llama 4 Scout

Meta: Llama 4 Scoutmeta-llama/llama-4-scoutbuilds on the Llama4 tokenizerHigh

Maker: Meta
Label on the catalogue: Llama4
What the measurement says: builds on the Llama4 tokenizer
Why high: an exact fingerprint shared with 1 model that declares the same family, without a second signal of a different kind yet
Fingerprint: tk_59e2520c · shared with 1 other model
Context: 1,310,720
Max output: 16,384
Modalities: text+image->text
Prompt price: $0.10 / M tokens
Entered the catalogue: 5 April 2025
Last tested: 21 August 2026

Full record JSON Shares with Meta: Llama 4 Maverick

Meta: Muse Spark 1.1meta/muse-spark-1.1not measuredNo reading

Maker: Meta
Label on the catalogue: no family named
What the measurement says: not measured
Context: 1,048,576
Max output: 943,718
Modalities: text+image+file+audio+video->text
Prompt price: $1.25 / M tokens
Entered the catalogue: 16 July 2026
Last tested: not yet

Full record JSON

Meta: Muse Spark 1.2meta/muse-spark-1.2not measuredNo reading

Maker: Meta
Label on the catalogue: no family named
What the measurement says: not measured
Context: 1,048,576
Max output: 943,718
Modalities: text+image+file+audio+video->text
Prompt price: $1.25 / M tokens
Entered the catalogue: 5 August 2026
Last tested: not yet

Full record JSON

Meta: Muse Spark 1.2 Contributormeta/muse-spark-1.2-contributornot measuredNo reading

Maker: Meta
Label on the catalogue: no family named
What the measurement says: not measured
Context: 1,048,576
Max output: 943,718
Modalities: text+image+file+audio+video->text
Prompt price: $0.10 / M tokens
Entered the catalogue: 21 August 2026
Last tested: not yet

Full record JSON

Meta: Muse Spark 1.3meta/muse-spark-1.3not measuredNo reading

Maker: Meta
Label on the catalogue: no family named
What the measurement says: not measured
Context: 1,048,576
Max output: 943,718
Modalities: text+image+file+audio+video->text
Prompt price: $1.25 / M tokens
Entered the catalogue: 2 September 2026
Last tested: not yet

Full record JSON

Meta: Muse Spark 1.3 Contributormeta/muse-spark-1.3-contributornot measuredNo reading

Maker: Meta
Label on the catalogue: no family named
What the measurement says: not measured
Context: 1,048,576
Max output: 943,718
Modalities: text+image+file+audio+video->text
Prompt price: $0.10 / M tokens
Entered the catalogue: 2 September 2026
Last tested: not yet

Full record JSON

Mistral Largemistralai/mistral-largebuilds on the Mistral tokenizerHigh

Maker: Mistral AI
Label on the catalogue: Mistral
What the measurement says: builds on the Mistral tokenizer
Why high: an exact fingerprint shared with 21 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_0da8a999 · shared with 21 other models
Context: 128,000
Max output: 102,400
Modalities: text+file->text
Prompt price: $2.00 / M tokens
Entered the catalogue: 26 February 2024
Last tested: 3 September 2026

Full record JSON Shares with NVIDIA: Nemotron 3.5 Lightning

Mistral Large 2407mistralai/mistral-large-2407builds on the Mistral tokenizerVery high

Maker: Mistral AI
Label on the catalogue: Mistral
What the measurement says: builds on the Mistral tokenizer
Why very high: an exact fingerprint shared with 21 models and an identical API contract inside the same group: two signals of different kinds agree
Fingerprint: tk_0da8a999 · shared with 21 other models
Context: 131,072
Max output: 104,857
Modalities: text+file->text
Prompt price: $2.00 / M tokens
Entered the catalogue: 19 November 2024
Last tested: 3 September 2026

Full record JSON Shares with NVIDIA: Nemotron 3.5 Lightning

Mistral: Codestral 2508mistralai/codestral-2508builds on the Mistral tokenizerHigh

Maker: Mistral AI
Label on the catalogue: Mistral
What the measurement says: builds on the Mistral tokenizer
Why high: an exact fingerprint shared with 21 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_0da8a999 · shared with 21 other models
Context: 256,000
Max output: 204,800
Modalities: text+file->text
Prompt price: $0.30 / M tokens
Entered the catalogue: 1 August 2025
Last tested: 21 August 2026

Full record JSON Shares with NVIDIA: Nemotron 3.5 Lightning

Mistral: Codestral 2508 (batch)mistralai/codestral-2508:batchbuilds on the Mistral tokenizerHigh

Maker: Mistral AI
Label on the catalogue: Mistral
What the measurement says: builds on the Mistral tokenizer
Why high: inherited from mistralai/codestral-2508: a serving variant shares its base model's tokenizer
Variant of: Mistral: Codestral 2508
Context: 256,000
Max output: 204,800
Modalities: text+file->text
Prompt price: $0.15 / M tokens
Entered the catalogue: 1 August 2025
Last tested: not yet

Full record JSON

Mistral: Devstral 2 2512mistralai/devstral-2512builds on the Mistral tokenizerVery high

Maker: Mistral AI
Label on the catalogue: Mistral
What the measurement says: builds on the Mistral tokenizer
Why very high: an exact fingerprint shared with 21 models and an identical API contract inside the same group: two signals of different kinds agree
Fingerprint: tk_0da8a999 · shared with 21 other models
Context: 262,144
Max output: 209,715
Modalities: text+file->text
Prompt price: $0.40 / M tokens
Entered the catalogue: 9 December 2025
Last tested: 3 September 2026

Full record JSON Shares with NVIDIA: Nemotron 3.5 Lightning

Mistral: Ministral 3 14B 2512mistralai/ministral-14b-2512builds on the Mistral tokenizerVery high

Maker: Mistral AI
Label on the catalogue: Mistral
What the measurement says: builds on the Mistral tokenizer
Why very high: an exact fingerprint shared with 21 models and an identical API contract inside the same group: two signals of different kinds agree
Fingerprint: tk_0da8a999 · shared with 21 other models
Context: 262,144
Max output: 209,715
Modalities: text+image->text
Prompt price: $0.20 / M tokens
Entered the catalogue: 2 December 2025
Last tested: 21 August 2026

Full record JSON Shares with NVIDIA: Nemotron 3.5 Lightning

Mistral: Ministral 3 3B 2512mistralai/ministral-3b-2512builds on the Mistral tokenizerHigh

Maker: Mistral AI
Label on the catalogue: Mistral
What the measurement says: builds on the Mistral tokenizer
Why high: an exact fingerprint shared with 21 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_0da8a999 · shared with 21 other models
Context: 131,072
Max output: 104,857
Modalities: text+image->text
Prompt price: $0.10 / M tokens
Entered the catalogue: 2 December 2025
Last tested: 21 August 2026

Full record JSON Shares with NVIDIA: Nemotron 3.5 Lightning

Mistral: Ministral 3 8B 2512mistralai/ministral-8b-2512builds on the Mistral tokenizerVery high

Maker: Mistral AI
Label on the catalogue: Mistral
What the measurement says: builds on the Mistral tokenizer
Why very high: an exact fingerprint shared with 21 models and an identical API contract inside the same group: two signals of different kinds agree
Fingerprint: tk_0da8a999 · shared with 21 other models
Context: 262,144
Max output: 209,715
Modalities: text+image->text
Prompt price: $0.15 / M tokens
Entered the catalogue: 2 December 2025
Last tested: 21 August 2026

Full record JSON Shares with NVIDIA: Nemotron 3.5 Lightning

Mistral: Ministral 3 8B 2512 (batch)mistralai/ministral-8b-2512:batchbuilds on the Mistral tokenizerVery high

Maker: Mistral AI
Label on the catalogue: Mistral
What the measurement says: builds on the Mistral tokenizer
Why very high: inherited from mistralai/ministral-8b-2512: a serving variant shares its base model's tokenizer
Variant of: Mistral: Ministral 3 8B 2512
Context: 262,144
Max output: 209,715
Modalities: text+image->text
Prompt price: $0.07 / M tokens
Entered the catalogue: 2 December 2025
Last tested: not yet

Full record JSON

Mistral: Mistral Large 3 2512mistralai/mistral-large-2512builds on the Mistral tokenizerHigh

Maker: Mistral AI
Label on the catalogue: Mistral
What the measurement says: builds on the Mistral tokenizer
Why high: an exact fingerprint shared with 21 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_0da8a999 · shared with 21 other models
Context: 262,144
Max output: 209,715
Modalities: text+image+file->text
Prompt price: $0.50 / M tokens
Entered the catalogue: 1 December 2025
Last tested: 22 August 2026

Full record JSON Shares with NVIDIA: Nemotron 3.5 Lightning

Mistral: Mistral Large 3 2512 (batch)mistralai/mistral-large-2512:batchbuilds on the Mistral tokenizerHigh

Maker: Mistral AI
Label on the catalogue: Mistral
What the measurement says: builds on the Mistral tokenizer
Why high: inherited from mistralai/mistral-large-2512: a serving variant shares its base model's tokenizer
Variant of: Mistral: Mistral Large 3 2512
Context: 262,144
Max output: 209,715
Modalities: text+image+file->text
Prompt price: $0.25 / M tokens
Entered the catalogue: 1 December 2025
Last tested: not yet

Full record JSON

Mistral: Mistral Medium 3mistralai/mistral-medium-3builds on the Mistral tokenizerVery high

Maker: Mistral AI
Label on the catalogue: Mistral
What the measurement says: builds on the Mistral tokenizer
Why very high: an exact fingerprint shared with 21 models and an identical API contract inside the same group: two signals of different kinds agree
Fingerprint: tk_0da8a999 · shared with 21 other models
Context: 131,072
Max output: 104,857
Modalities: text+image+file->text
Prompt price: $0.40 / M tokens
Entered the catalogue: 7 May 2025
Last tested: 22 August 2026

Full record JSON Shares with NVIDIA: Nemotron 3.5 Lightning

Mistral: Mistral Medium 3.1mistralai/mistral-medium-3.1builds on the Mistral tokenizerVery high

Maker: Mistral AI
Label on the catalogue: Mistral
What the measurement says: builds on the Mistral tokenizer
Why very high: an exact fingerprint shared with 21 models and an identical API contract inside the same group: two signals of different kinds agree
Fingerprint: tk_0da8a999 · shared with 21 other models
Context: 131,072
Max output: 104,857
Modalities: text+image+file->text
Prompt price: $0.40 / M tokens
Entered the catalogue: 13 August 2025
Last tested: 22 August 2026

Full record JSON Shares with NVIDIA: Nemotron 3.5 Lightning

Mistral: Mistral Medium 3.1 (batch)mistralai/mistral-medium-3.1:batchbuilds on the Mistral tokenizerVery high

Maker: Mistral AI
Label on the catalogue: Mistral
What the measurement says: builds on the Mistral tokenizer
Why very high: inherited from mistralai/mistral-medium-3.1: a serving variant shares its base model's tokenizer
Variant of: Mistral: Mistral Medium 3.1
Context: 131,072
Max output: 104,857
Modalities: text+image+file->text
Prompt price: $0.20 / M tokens
Entered the catalogue: 13 August 2025
Last tested: not yet

Full record JSON

Mistral: Mistral Medium 3.5mistralai/mistral-medium-3-5builds on the Mistral tokenizerHigh

Maker: Mistral AI
Label on the catalogue: Mistral
What the measurement says: builds on the Mistral tokenizer
Why high: an exact fingerprint shared with 21 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_0da8a999 · shared with 21 other models
Context: 262,144
Max output: 209,715
Modalities: text+image+file->text
Prompt price: $1.50 / M tokens
Entered the catalogue: 30 April 2026
Last tested: 3 September 2026

Full record JSON Shares with NVIDIA: Nemotron 3.5 Lightning

Mistral: Mistral Medium 3.5 (batch)mistralai/mistral-medium-3-5:batchbuilds on the Mistral tokenizerHigh

Maker: Mistral AI
Label on the catalogue: Mistral
What the measurement says: builds on the Mistral tokenizer
Why high: inherited from mistralai/mistral-medium-3-5: a serving variant shares its base model's tokenizer
Variant of: Mistral: Mistral Medium 3.5
Context: 262,144
Max output: 209,715
Modalities: text+image+file->text
Prompt price: $0.75 / M tokens
Entered the catalogue: 30 April 2026
Last tested: not yet

Full record JSON

Mistral: Mistral Nemomistralai/mistral-nemobuilds on the Mistral tokenizerHigh

Maker: Mistral AI
Label on the catalogue: Mistral
What the measurement says: builds on the Mistral tokenizer
Why high: an exact fingerprint shared with 21 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_0da8a999 · shared with 21 other models
Context: 131,072
Max output: 16,384
Modalities: text->text
Prompt price: $0.02 / M tokens
Entered the catalogue: 19 July 2024
Last tested: 21 August 2026

Full record JSON Shares with NVIDIA: Nemotron 3.5 Lightning

Mistral: Mistral Small 3.1 24Bmistralai/mistral-small-3.1-24b-instructbuilds on the Mistral tokenizerHigh

Maker: Mistral AI
Label on the catalogue: Mistral
What the measurement says: builds on the Mistral tokenizer
Why high: an exact fingerprint shared with 21 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_0da8a999 · shared with 21 other models
Context: 128,000
Max output: 102,400
Modalities: text+image->text
Prompt price: $0.35 / M tokens
Entered the catalogue: 17 March 2025
Last tested: 21 August 2026

Full record JSON Shares with NVIDIA: Nemotron 3.5 Lightning

Mistral: Mistral Small 3.2 24Bmistralai/mistral-small-3.2-24b-instructbuilds on the Mistral tokenizerHigh

Maker: Mistral AI
Label on the catalogue: Mistral
What the measurement says: builds on the Mistral tokenizer
Why high: an exact fingerprint shared with 21 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_0da8a999 · shared with 21 other models
Context: 256,000
Max output: 16,384
Modalities: text+image->text
Prompt price: $0.09 / M tokens
Entered the catalogue: 20 June 2025
Last tested: 21 August 2026

Full record JSON Shares with NVIDIA: Nemotron 3.5 Lightning

Mistral: Mistral Small 4mistralai/mistral-small-2603builds on the Mistral tokenizerHigh

Maker: Mistral AI
Label on the catalogue: Mistral
What the measurement says: builds on the Mistral tokenizer
Why high: an exact fingerprint shared with 21 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_0da8a999 · shared with 21 other models
Context: 262,144
Max output: 209,715
Modalities: text+image->text
Prompt price: $0.15 / M tokens
Entered the catalogue: 16 March 2026
Last tested: 21 August 2026

Full record JSON Shares with NVIDIA: Nemotron 3.5 Lightning

Mistral: Mistral Small 4 (batch)mistralai/mistral-small-2603:batchbuilds on the Mistral tokenizerHigh

Maker: Mistral AI
Label on the catalogue: Mistral
What the measurement says: builds on the Mistral tokenizer
Why high: inherited from mistralai/mistral-small-2603: a serving variant shares its base model's tokenizer
Variant of: Mistral: Mistral Small 4
Context: 262,144
Max output: 209,715
Modalities: text+image->text
Prompt price: $0.07 / M tokens
Entered the catalogue: 16 March 2026
Last tested: not yet

Full record JSON

Mistral: Mixtral 8x22B Instructmistralai/mixtral-8x22b-instructbuilds on the Mistral tokenizerHigh

Maker: Mistral AI
Label on the catalogue: Mistral
What the measurement says: builds on the Mistral tokenizer
Why high: an exact fingerprint shared with 21 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_0da8a999 · shared with 21 other models
Context: 65,536
Max output: 52,428
Modalities: text+file->text
Prompt price: $2.00 / M tokens
Entered the catalogue: 17 April 2024
Last tested: 3 September 2026

Full record JSON Shares with NVIDIA: Nemotron 3.5 Lightning

Mistral: Sabamistralai/mistral-sababuilds on the Mistral tokenizerHigh

Maker: Mistral AI
Label on the catalogue: Mistral
What the measurement says: builds on the Mistral tokenizer
Why high: an exact fingerprint shared with 21 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_0da8a999 · shared with 21 other models
Context: 32,768
Max output: 26,214
Modalities: text+file->text
Prompt price: $0.20 / M tokens
Entered the catalogue: 17 February 2025
Last tested: 21 August 2026

Full record JSON Shares with NVIDIA: Nemotron 3.5 Lightning

Mistral: Voxtral Small 24B 2507mistralai/voxtral-small-24b-2507builds on the Mistral tokenizerHigh

Maker: Mistral AI
Label on the catalogue: Mistral
What the measurement says: builds on the Mistral tokenizer
Why high: an exact fingerprint shared with 21 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_0da8a999 · shared with 21 other models
Context: 32,768
Max output: 26,214
Modalities: text+file+audio->text
Prompt price: $0.10 / M tokens
Entered the catalogue: 30 October 2025
Last tested: 21 August 2026

Full record JSON Shares with NVIDIA: Nemotron 3.5 Lightning

MoonshotAI: Kimi K3 (batch)moonshotai/kimi-k3:batcha serving variant of another entryNo reading

Maker: Moonshot AI
Label on the catalogue: no family named
What the measurement says: a serving variant of another entry
Variant of: MoonshotAI: Kimi K3
Context: 1,048,576
Max output: 943,718
Modalities: text+image+video->text
Prompt price: $3.00 / M tokens
Entered the catalogue: 16 July 2026
Last tested: not yet

Full record JSON

MythoMax 13Bgryphe/mythomax-l2-13bbuilds on the Llama2 tokenizerHigh

Maker: Gryphe
Label on the catalogue: Llama2
What the measurement says: builds on the Llama2 tokenizer
Why high: an exact fingerprint shared with 1 model that declares the same family, without a second signal of a different kind yet
Fingerprint: tk_5348f9f6 · shared with 1 other model
Context: 8,192
Max output: 3,686
Modalities: text->text
Prompt price: $0.08 / M tokens
Entered the catalogue: 2 July 2023
Last tested: 21 August 2026

Full record JSON Shares with ReMM SLERP 13B

Nex AGI: Nex-N2.5-Mini (free)nex-agi/nex-n2.5-mini:freequeued for measurementNo reading

Maker: Nex Agi
Label on the catalogue: Qwen3
What the measurement says: queued for measurement
Context: 262,144
Max output: 235,929
Modalities: text+image->text
Prompt price: $0 / M tokens
Entered the catalogue: 8 September 2026
Last tested: not yet

Full record JSON

Nex AGI: Nex-N2.5-Pro (free)nex-agi/nex-n2.5-pro:freequeued for measurementNo reading

Maker: Nex Agi
Label on the catalogue: Qwen3
What the measurement says: queued for measurement
Context: 262,144
Max output: 235,929
Modalities: text+image->text
Prompt price: $0 / M tokens
Entered the catalogue: 8 September 2026
Last tested: not yet

Full record JSON

Nous: Hermes 3 405B Instructnousresearch/hermes-3-llama-3.1-405bbuilds on the Llama3 tokenizerHigh

Maker: Nous Research
Label on the catalogue: Llama3
What the measurement says: builds on the Llama3 tokenizer
Why high: an exact fingerprint shared with 4 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_47615f2d · shared with 4 other models
Context: 131,072
Max output: 16,384
Modalities: text->text
Prompt price: $1.00 / M tokens
Entered the catalogue: 16 August 2024
Last tested: 21 August 2026

Full record JSON Shares with Nous: Hermes 4 405B

Nous: Hermes 3 70B Instructnousresearch/hermes-3-llama-3.1-70bbuilds on the Llama3 tokenizerHigh

Maker: Nous Research
Label on the catalogue: Llama3
What the measurement says: builds on the Llama3 tokenizer
Why high: an exact fingerprint shared with 4 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_47615f2d · shared with 4 other models
Context: 131,072
Max output: 16,384
Modalities: text->text
Prompt price: $0.70 / M tokens
Entered the catalogue: 18 August 2024
Last tested: 21 August 2026

Full record JSON Shares with Nous: Hermes 4 405B

NVIDIA: Nemotron 3.5 Content Safetynvidia/nemotron-3.5-content-safetyqueued for measurementNo reading

Maker: NVIDIA
Label on the catalogue: no family named
What the measurement says: queued for measurement
Context: 131,072
Max output: 117,964
Modalities: text+image->text
Prompt price: $0.20 / M tokens
Entered the catalogue: 4 June 2026
Last tested: not yet

Full record JSON

OpenAI: GPT Audioopenai/gpt-audionot measuredNo reading

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: not measured
Context: 128,000
Max output: 16,384
Modalities: text+audio->text+audio
Prompt price: $2.50 / M tokens
Entered the catalogue: 19 January 2026
Last tested: not yet

Full record JSON

OpenAI: GPT Audio Miniopenai/gpt-audio-mininot measuredNo reading

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: not measured
Context: 128,000
Max output: 16,384
Modalities: text+audio->text+audio
Prompt price: $0.60 / M tokens
Entered the catalogue: 19 January 2026
Last tested: not yet

Full record JSON

OpenAI: GPT Chat Latestopenai/gpt-chat-latestbuilds on the GPT tokenizerHigh

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why high: an exact fingerprint shared with 31 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_d1411c9d · shared with 31 other models
Context: 400,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $5.00 / M tokens
Entered the catalogue: 5 May 2026
Last tested: 3 September 2026

Full record JSON Shares with Thinking Machines: Inkling Small

OpenAI: GPT-3.5 Turbo (older v0613)openai/gpt-3.5-turbo-0613builds on the GPT tokenizerHigh

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why high: an exact fingerprint shared with 31 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_d1411c9d · shared with 31 other models
Context: 4,095
Max output: 3,685
Modalities: text->text
Prompt price: $1.00 / M tokens
Entered the catalogue: 25 January 2024
Last tested: 3 September 2026

Full record JSON Shares with Thinking Machines: Inkling Small

OpenAI: GPT-3.5 Turbo 16kopenai/gpt-3.5-turbo-16knot measuredNo reading

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: not measured
Context: 16,385
Max output: 4,096
Modalities: text->text
Prompt price: $3.00 / M tokens
Entered the catalogue: 28 August 2023
Last tested: not yet

Full record JSON

OpenAI: GPT-4openai/gpt-4not measuredNo reading

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: not measured
Context: 8,191
Max output: 4,096
Modalities: text->text
Prompt price: $30.0 / M tokens
Entered the catalogue: 28 May 2023
Last tested: not yet

Full record JSON

OpenAI: GPT-4 Turboopenai/gpt-4-turbonot measuredNo reading

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: not measured
Context: 128,000
Max output: 4,096
Modalities: text+image->text
Prompt price: $10.0 / M tokens
Entered the catalogue: 9 April 2024
Last tested: not yet

Full record JSON

OpenAI: GPT-4 Turbo (batch)openai/gpt-4-turbo:batcha serving variant of another entryNo reading

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: a serving variant of another entry
Variant of: OpenAI: GPT-4 Turbo
Context: 128,000
Max output: 4,096
Modalities: text+image->text
Prompt price: $5.00 / M tokens
Entered the catalogue: 9 April 2024
Last tested: not yet

Full record JSON

OpenAI: GPT-4.1openai/gpt-4.1builds on the GPT tokenizerVery high

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why very high: an exact fingerprint shared with 31 models and an identical API contract inside the same group: two signals of different kinds agree
Fingerprint: tk_d1411c9d · shared with 31 other models
Context: 1,047,576
Max output: 32,768
Modalities: text+image+file->text
Prompt price: $2.00 / M tokens
Entered the catalogue: 14 April 2025
Last tested: 3 September 2026

Full record JSON Shares with Thinking Machines: Inkling Small

OpenAI: GPT-4.1 (batch)openai/gpt-4.1:batchbuilds on the GPT tokenizerVery high

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why very high: inherited from openai/gpt-4.1: a serving variant shares its base model's tokenizer
Variant of: OpenAI: GPT-4.1
Context: 1,047,576
Max output: 32,768
Modalities: text+image+file->text
Prompt price: $1.00 / M tokens
Entered the catalogue: 14 April 2025
Last tested: not yet

Full record JSON

OpenAI: GPT-4.1 Miniopenai/gpt-4.1-minibuilds on the GPT tokenizerVery high

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why very high: an exact fingerprint shared with 31 models and an identical API contract inside the same group: two signals of different kinds agree
Fingerprint: tk_d1411c9d · shared with 31 other models
Context: 1,047,576
Max output: 32,768
Modalities: text+image+file->text
Prompt price: $0.40 / M tokens
Entered the catalogue: 14 April 2025
Last tested: 22 August 2026

Full record JSON Shares with Thinking Machines: Inkling Small

OpenAI: GPT-4.1 Mini (batch)openai/gpt-4.1-mini:batchbuilds on the GPT tokenizerVery high

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why very high: inherited from openai/gpt-4.1-mini: a serving variant shares its base model's tokenizer
Variant of: OpenAI: GPT-4.1 Mini
Context: 1,047,576
Max output: 32,768
Modalities: text+image+file->text
Prompt price: $0.20 / M tokens
Entered the catalogue: 14 April 2025
Last tested: not yet

Full record JSON

OpenAI: GPT-4.1 Nanoopenai/gpt-4.1-nanobuilds on the GPT tokenizerVery high

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why very high: an exact fingerprint shared with 31 models and an identical API contract inside the same group: two signals of different kinds agree
Fingerprint: tk_d1411c9d · shared with 31 other models
Context: 1,047,576
Max output: 32,768
Modalities: text+image+file->text
Prompt price: $0.10 / M tokens
Entered the catalogue: 14 April 2025
Last tested: 21 August 2026

Full record JSON Shares with Thinking Machines: Inkling Small

OpenAI: GPT-4.1 Nano (batch)openai/gpt-4.1-nano:batchbuilds on the GPT tokenizerVery high

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why very high: inherited from openai/gpt-4.1-nano: a serving variant shares its base model's tokenizer
Variant of: OpenAI: GPT-4.1 Nano
Context: 1,047,576
Max output: 32,768
Modalities: text+image+file->text
Prompt price: $0.05 / M tokens
Entered the catalogue: 14 April 2025
Last tested: not yet

Full record JSON

OpenAI: GPT-4oopenai/gpt-4onot measuredNo reading

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: not measured
Context: 128,000
Max output: 16,384
Modalities: text+image+file->text
Prompt price: $2.50 / M tokens
Entered the catalogue: 13 May 2024
Last tested: not yet

Full record JSON

OpenAI: GPT-4o (2024-05-13)openai/gpt-4o-2024-05-13not measuredNo reading

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: not measured
Context: 128,000
Max output: 4,096
Modalities: text+image+file->text
Prompt price: $5.00 / M tokens
Entered the catalogue: 13 May 2024
Last tested: not yet

Full record JSON

OpenAI: GPT-4o (2024-08-06)openai/gpt-4o-2024-08-06not measuredNo reading

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: not measured
Context: 128,000
Max output: 16,384
Modalities: text+image+file->text
Prompt price: $2.50 / M tokens
Entered the catalogue: 6 August 2024
Last tested: not yet

Full record JSON

OpenAI: GPT-4o (2024-11-20)openai/gpt-4o-2024-11-20not measuredNo reading

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: not measured
Context: 128,000
Max output: 16,384
Modalities: text+image+file->text
Prompt price: $2.50 / M tokens
Entered the catalogue: 20 November 2024
Last tested: not yet

Full record JSON

OpenAI: GPT-4o (batch)openai/gpt-4o:batcha serving variant of another entryNo reading

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: a serving variant of another entry
Variant of: OpenAI: GPT-4o
Context: 128,000
Max output: 16,384
Modalities: text+image+file->text
Prompt price: $1.25 / M tokens
Entered the catalogue: 13 May 2024
Last tested: not yet

Full record JSON

OpenAI: GPT-4o-miniopenai/gpt-4o-minibuilds on the GPT tokenizerHigh

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why high: an exact fingerprint shared with 31 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_d1411c9d · shared with 31 other models
Context: 128,000
Max output: 16,384
Modalities: text+image+file->text
Prompt price: $0.15 / M tokens
Entered the catalogue: 18 July 2024
Last tested: 21 August 2026

Full record JSON Shares with Thinking Machines: Inkling Small

OpenAI: GPT-4o-mini (2024-07-18)openai/gpt-4o-mini-2024-07-18builds on the GPT tokenizerHigh

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why high: an exact fingerprint shared with 31 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_d1411c9d · shared with 31 other models
Context: 128,000
Max output: 16,384
Modalities: text+image+file->text
Prompt price: $0.15 / M tokens
Entered the catalogue: 18 July 2024
Last tested: 21 August 2026

Full record JSON Shares with Thinking Machines: Inkling Small

OpenAI: GPT-4o-mini (batch)openai/gpt-4o-mini:batchbuilds on the GPT tokenizerHigh

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why high: inherited from openai/gpt-4o-mini: a serving variant shares its base model's tokenizer
Variant of: OpenAI: GPT-4o-mini
Context: 128,000
Max output: 16,384
Modalities: text+image+file->text
Prompt price: $0.07 / M tokens
Entered the catalogue: 18 July 2024
Last tested: not yet

Full record JSON

OpenAI: GPT-5openai/gpt-5builds on the GPT tokenizerVery high

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why very high: an exact fingerprint shared with 31 models and an identical API contract inside the same group: two signals of different kinds agree
Fingerprint: tk_d1411c9d · shared with 31 other models
Context: 400,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $1.25 / M tokens
Entered the catalogue: 7 August 2025
Last tested: 3 September 2026

Full record JSON Shares with Thinking Machines: Inkling Small

OpenAI: GPT-5 (batch)openai/gpt-5:batchbuilds on the GPT tokenizerVery high

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why very high: inherited from openai/gpt-5: a serving variant shares its base model's tokenizer
Variant of: OpenAI: GPT-5
Context: 400,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $0.63 / M tokens
Entered the catalogue: 7 August 2025
Last tested: not yet

Full record JSON

OpenAI: GPT-5 Imageopenai/gpt-5-imagenot measuredNo reading

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: not measured
Context: 400,000
Max output: 128,000
Modalities: text+image+file->text+image
Prompt price: $10.0 / M tokens
Entered the catalogue: 14 October 2025
Last tested: not yet

Full record JSON

OpenAI: GPT-5 Image Miniopenai/gpt-5-image-mininot measuredNo reading

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: not measured
Context: 400,000
Max output: 128,000
Modalities: text+image+file->text+image
Prompt price: $2.50 / M tokens
Entered the catalogue: 16 October 2025
Last tested: not yet

Full record JSON

OpenAI: GPT-5 Mini (batch)openai/gpt-5-mini:batcha serving variant of another entryNo reading

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: a serving variant of another entry
Variant of: OpenAI: GPT-5 Mini
Context: 400,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $0.13 / M tokens
Entered the catalogue: 7 August 2025
Last tested: not yet

Full record JSON

OpenAI: GPT-5 Nanoopenai/gpt-5-nanobuilds on the GPT tokenizerVery high

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why very high: an exact fingerprint shared with 31 models and an identical API contract inside the same group: two signals of different kinds agree
Fingerprint: tk_d1411c9d · shared with 31 other models
Context: 400,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $0.05 / M tokens
Entered the catalogue: 7 August 2025
Last tested: 21 August 2026

Full record JSON Shares with Thinking Machines: Inkling Small

OpenAI: GPT-5 Nano (batch)openai/gpt-5-nano:batchbuilds on the GPT tokenizerVery high

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why very high: inherited from openai/gpt-5-nano: a serving variant shares its base model's tokenizer
Variant of: OpenAI: GPT-5 Nano
Context: 400,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $0.02 / M tokens
Entered the catalogue: 7 August 2025
Last tested: not yet

Full record JSON

OpenAI: GPT-5 Proopenai/gpt-5-pronot measuredNo reading

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: not measured
Context: 400,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $15.0 / M tokens
Entered the catalogue: 6 October 2025
Last tested: not yet

Full record JSON

OpenAI: GPT-5 Pro (batch)openai/gpt-5-pro:batcha serving variant of another entryNo reading

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: a serving variant of another entry
Variant of: OpenAI: GPT-5 Pro
Context: 400,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $7.50 / M tokens
Entered the catalogue: 6 October 2025
Last tested: not yet

Full record JSON

OpenAI: GPT-5.1openai/gpt-5.1builds on the GPT tokenizerHigh

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why high: an exact fingerprint shared with 31 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_d1411c9d · shared with 31 other models
Context: 400,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $1.25 / M tokens
Entered the catalogue: 13 November 2025
Last tested: 3 September 2026

Full record JSON Shares with Thinking Machines: Inkling Small

OpenAI: GPT-5.1 (batch)openai/gpt-5.1:batchbuilds on the GPT tokenizerHigh

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why high: inherited from openai/gpt-5.1: a serving variant shares its base model's tokenizer
Variant of: OpenAI: GPT-5.1
Context: 400,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $0.63 / M tokens
Entered the catalogue: 13 November 2025
Last tested: not yet

Full record JSON

OpenAI: GPT-5.1-Codexopenai/gpt-5.1-codexbuilds on the GPT tokenizerHigh

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why high: an exact fingerprint shared with 31 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_d1411c9d · shared with 31 other models
Context: 400,000
Max output: 128,000
Modalities: text+image->text
Prompt price: $1.25 / M tokens
Entered the catalogue: 13 November 2025
Last tested: 3 September 2026

Full record JSON Shares with Thinking Machines: Inkling Small

OpenAI: GPT-5.1-Codex-Maxopenai/gpt-5.1-codex-maxbuilds on the GPT tokenizerHigh

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why high: an exact fingerprint shared with 31 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_d1411c9d · shared with 31 other models
Context: 400,000
Max output: 128,000
Modalities: text+image->text
Prompt price: $1.25 / M tokens
Entered the catalogue: 4 December 2025
Last tested: 3 September 2026

Full record JSON Shares with Thinking Machines: Inkling Small

OpenAI: GPT-5.1-Codex-Miniopenai/gpt-5.1-codex-minibuilds on the GPT tokenizerHigh

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why high: an exact fingerprint shared with 31 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_d1411c9d · shared with 31 other models
Context: 400,000
Max output: 128,000
Modalities: text+image->text
Prompt price: $0.25 / M tokens
Entered the catalogue: 13 November 2025
Last tested: 21 August 2026

Full record JSON Shares with Thinking Machines: Inkling Small

OpenAI: GPT-5.2openai/gpt-5.2builds on the GPT tokenizerVery high

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why very high: an exact fingerprint shared with 31 models and an identical API contract inside the same group: two signals of different kinds agree
Fingerprint: tk_d1411c9d · shared with 31 other models
Context: 400,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $1.75 / M tokens
Entered the catalogue: 10 December 2025
Last tested: 3 September 2026

Full record JSON Shares with Thinking Machines: Inkling Small

OpenAI: GPT-5.2 (batch)openai/gpt-5.2:batchbuilds on the GPT tokenizerVery high

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why very high: inherited from openai/gpt-5.2: a serving variant shares its base model's tokenizer
Variant of: OpenAI: GPT-5.2
Context: 400,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $0.88 / M tokens
Entered the catalogue: 10 December 2025
Last tested: not yet

Full record JSON

OpenAI: GPT-5.2 Chatopenai/gpt-5.2-chatnot measuredNo reading

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: not measured
Context: 128,000
Max output: 32,000
Modalities: text+image+file->text
Prompt price: $1.75 / M tokens
Entered the catalogue: 10 December 2025
Last tested: not yet

Full record JSON

OpenAI: GPT-5.2 Proopenai/gpt-5.2-pronot measuredNo reading

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: not measured
Context: 400,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $21.0 / M tokens
Entered the catalogue: 10 December 2025
Last tested: not yet

Full record JSON

OpenAI: GPT-5.2 Pro (batch)openai/gpt-5.2-pro:batcha serving variant of another entryNo reading

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: a serving variant of another entry
Variant of: OpenAI: GPT-5.2 Pro
Context: 400,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $10.5 / M tokens
Entered the catalogue: 10 December 2025
Last tested: not yet

Full record JSON

OpenAI: GPT-5.2-Codexopenai/gpt-5.2-codexbuilds on the GPT tokenizerHigh

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why high: an exact fingerprint shared with 31 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_d1411c9d · shared with 31 other models
Context: 400,000
Max output: 128,000
Modalities: text+image->text
Prompt price: $1.75 / M tokens
Entered the catalogue: 14 January 2026
Last tested: 3 September 2026

Full record JSON Shares with Thinking Machines: Inkling Small

OpenAI: GPT-5.3-Codexopenai/gpt-5.3-codexbuilds on the GPT tokenizerVery high

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why very high: an exact fingerprint shared with 31 models and an identical API contract inside the same group: two signals of different kinds agree
Fingerprint: tk_d1411c9d · shared with 31 other models
Context: 400,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $1.75 / M tokens
Entered the catalogue: 24 February 2026
Last tested: 3 September 2026

Full record JSON Shares with Thinking Machines: Inkling Small

OpenAI: GPT-5.4openai/gpt-5.4builds on the GPT tokenizerVery high

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why very high: an exact fingerprint shared with 31 models and an identical API contract inside the same group: two signals of different kinds agree
Fingerprint: tk_d1411c9d · shared with 31 other models
Context: 1,050,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $2.50 / M tokens
Entered the catalogue: 5 March 2026
Last tested: 3 September 2026

Full record JSON Shares with Thinking Machines: Inkling Small

OpenAI: GPT-5.4 (batch)openai/gpt-5.4:batchbuilds on the GPT tokenizerVery high

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why very high: inherited from openai/gpt-5.4: a serving variant shares its base model's tokenizer
Variant of: OpenAI: GPT-5.4
Context: 1,050,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $1.25 / M tokens
Entered the catalogue: 5 March 2026
Last tested: not yet

Full record JSON

OpenAI: GPT-5.4 Image 2openai/gpt-5.4-image-2not measuredNo reading

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: not measured
Context: 272,000
Max output: 128,000
Modalities: text+image+file->text+image
Prompt price: $8.00 / M tokens
Entered the catalogue: 21 April 2026
Last tested: not yet

Full record JSON

OpenAI: GPT-5.4 Miniopenai/gpt-5.4-minibuilds on the GPT tokenizerVery high

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why very high: an exact fingerprint shared with 31 models and an identical API contract inside the same group: two signals of different kinds agree
Fingerprint: tk_d1411c9d · shared with 31 other models
Context: 400,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $0.75 / M tokens
Entered the catalogue: 17 March 2026
Last tested: 3 September 2026

Full record JSON Shares with Thinking Machines: Inkling Small

OpenAI: GPT-5.4 Mini (batch)openai/gpt-5.4-mini:batchbuilds on the GPT tokenizerVery high

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why very high: inherited from openai/gpt-5.4-mini: a serving variant shares its base model's tokenizer
Variant of: OpenAI: GPT-5.4 Mini
Context: 400,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $0.38 / M tokens
Entered the catalogue: 17 March 2026
Last tested: not yet

Full record JSON

OpenAI: GPT-5.4 Nanoopenai/gpt-5.4-nanobuilds on the GPT tokenizerVery high

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why very high: an exact fingerprint shared with 31 models and an identical API contract inside the same group: two signals of different kinds agree
Fingerprint: tk_d1411c9d · shared with 31 other models
Context: 400,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $0.20 / M tokens
Entered the catalogue: 17 March 2026
Last tested: 21 August 2026

Full record JSON Shares with Thinking Machines: Inkling Small

OpenAI: GPT-5.4 Nano (batch)openai/gpt-5.4-nano:batchbuilds on the GPT tokenizerVery high

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why very high: inherited from openai/gpt-5.4-nano: a serving variant shares its base model's tokenizer
Variant of: OpenAI: GPT-5.4 Nano
Context: 400,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $0.10 / M tokens
Entered the catalogue: 17 March 2026
Last tested: not yet

Full record JSON

OpenAI: GPT-5.4 Proopenai/gpt-5.4-pronot measuredNo reading

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: not measured
Context: 1,050,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $30.0 / M tokens
Entered the catalogue: 5 March 2026
Last tested: not yet

Full record JSON

OpenAI: GPT-5.4 Pro (batch)openai/gpt-5.4-pro:batcha serving variant of another entryNo reading

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: a serving variant of another entry
Variant of: OpenAI: GPT-5.4 Pro
Context: 1,050,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $15.0 / M tokens
Entered the catalogue: 5 March 2026
Last tested: not yet

Full record JSON

OpenAI: GPT-5.5openai/gpt-5.5builds on the GPT tokenizerVery high

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why very high: an exact fingerprint shared with 31 models and an identical API contract inside the same group: two signals of different kinds agree
Fingerprint: tk_d1411c9d · shared with 31 other models
Context: 1,050,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $5.00 / M tokens
Entered the catalogue: 24 April 2026
Last tested: 3 September 2026

Full record JSON Shares with Thinking Machines: Inkling Small

OpenAI: GPT-5.5 (batch)openai/gpt-5.5:batchbuilds on the GPT tokenizerVery high

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why very high: inherited from openai/gpt-5.5: a serving variant shares its base model's tokenizer
Variant of: OpenAI: GPT-5.5
Context: 1,050,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $2.50 / M tokens
Entered the catalogue: 24 April 2026
Last tested: not yet

Full record JSON

OpenAI: GPT-5.5 Proopenai/gpt-5.5-pronot measuredNo reading

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: not measured
Context: 1,050,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $30.0 / M tokens
Entered the catalogue: 24 April 2026
Last tested: not yet

Full record JSON

OpenAI: GPT-5.5 Pro (batch)openai/gpt-5.5-pro:batcha serving variant of another entryNo reading

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: a serving variant of another entry
Variant of: OpenAI: GPT-5.5 Pro
Context: 1,050,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $15.0 / M tokens
Entered the catalogue: 24 April 2026
Last tested: not yet

Full record JSON

OpenAI: GPT-5.6 Lunaopenai/gpt-5.6-lunabuilds on the GPT tokenizerVery high

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why very high: an exact fingerprint shared with 31 models and an identical API contract inside the same group: two signals of different kinds agree
Fingerprint: tk_d1411c9d · shared with 31 other models
Context: 1,050,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $0.20 / M tokens
Entered the catalogue: 9 July 2026
Last tested: 21 August 2026

Full record JSON Shares with Thinking Machines: Inkling Small

OpenAI: GPT-5.6 Luna (batch)openai/gpt-5.6-luna:batchbuilds on the GPT tokenizerVery high

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why very high: inherited from openai/gpt-5.6-luna: a serving variant shares its base model's tokenizer
Variant of: OpenAI: GPT-5.6 Luna
Context: 1,050,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $0.10 / M tokens
Entered the catalogue: 9 July 2026
Last tested: not yet

Full record JSON

OpenAI: GPT-5.6 Luna Pro (batch)openai/gpt-5.6-luna-pro:batcha serving variant of another entryNo reading

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: a serving variant of another entry
Variant of: OpenAI: GPT-5.6 Luna Pro
Context: 1,050,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $0.10 / M tokens
Entered the catalogue: 9 July 2026
Last tested: not yet

Full record JSON

OpenAI: GPT-5.6 Solopenai/gpt-5.6-solbuilds on the GPT tokenizerVery high

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why very high: an exact fingerprint shared with 31 models and an identical API contract inside the same group: two signals of different kinds agree
Fingerprint: tk_d1411c9d · shared with 31 other models
Context: 1,050,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $2.00 / M tokens
Entered the catalogue: 9 July 2026
Last tested: 3 September 2026

Full record JSON Shares with Thinking Machines: Inkling Small

OpenAI: GPT-5.6 Sol (batch)openai/gpt-5.6-sol:batchbuilds on the GPT tokenizerVery high

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why very high: inherited from openai/gpt-5.6-sol: a serving variant shares its base model's tokenizer
Variant of: OpenAI: GPT-5.6 Sol
Context: 1,050,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $1.00 / M tokens
Entered the catalogue: 9 July 2026
Last tested: not yet

Full record JSON

OpenAI: GPT-5.6 Sol Pro (batch)openai/gpt-5.6-sol-pro:batcha serving variant of another entryNo reading

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: a serving variant of another entry
Variant of: OpenAI: GPT-5.6 Sol Pro
Context: 1,050,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $1.00 / M tokens
Entered the catalogue: 9 July 2026
Last tested: not yet

Full record JSON

OpenAI: GPT-5.6 Terraopenai/gpt-5.6-terrabuilds on the GPT tokenizerVery high

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why very high: an exact fingerprint shared with 31 models and an identical API contract inside the same group: two signals of different kinds agree
Fingerprint: tk_d1411c9d · shared with 31 other models
Context: 1,050,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $2.00 / M tokens
Entered the catalogue: 9 July 2026
Last tested: 3 September 2026

Full record JSON Shares with Thinking Machines: Inkling Small

OpenAI: GPT-5.6 Terra (batch)openai/gpt-5.6-terra:batchbuilds on the GPT tokenizerVery high

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why very high: inherited from openai/gpt-5.6-terra: a serving variant shares its base model's tokenizer
Variant of: OpenAI: GPT-5.6 Terra
Context: 1,050,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $1.00 / M tokens
Entered the catalogue: 9 July 2026
Last tested: not yet

Full record JSON

OpenAI: GPT-5.6 Terra Pro (batch)openai/gpt-5.6-terra-pro:batcha serving variant of another entryNo reading

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: a serving variant of another entry
Variant of: OpenAI: GPT-5.6 Terra Pro
Context: 1,050,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $1.00 / M tokens
Entered the catalogue: 9 July 2026
Last tested: not yet

Full record JSON

OpenAI: GPT-6 Astraopenai/gpt-6-astraqueued for measurementNo reading

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: queued for measurement
Context: 1,050,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $10.0 / M tokens
Entered the catalogue: 4 September 2026
Last tested: not yet

Full record JSON

OpenAI: GPT-6 Astra (batch)openai/gpt-6-astra:batchqueued for measurementNo reading

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: queued for measurement
Variant of: OpenAI: GPT-6 Astra
Context: 1,050,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $5.00 / M tokens
Entered the catalogue: 4 September 2026
Last tested: not yet

Full record JSON

OpenAI: GPT-6 Astra Proopenai/gpt-6-astra-proqueued for measurementNo reading

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: queued for measurement
Context: 1,050,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $10.0 / M tokens
Entered the catalogue: 4 September 2026
Last tested: not yet

Full record JSON

OpenAI: GPT-6 Astra Pro (batch)openai/gpt-6-astra-pro:batchqueued for measurementNo reading

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: queued for measurement
Variant of: OpenAI: GPT-6 Astra Pro
Context: 1,050,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $5.00 / M tokens
Entered the catalogue: 4 September 2026
Last tested: not yet

Full record JSON

OpenAI: gpt-oss-120bopenai/gpt-oss-120bbuilds on the GPT tokenizerHigh

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why high: an exact fingerprint shared with 31 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_d1411c9d · shared with 31 other models
Context: 131,072
Max output: 117,964
Modalities: text->text
Prompt price: $0.04 / M tokens
Entered the catalogue: 5 August 2025
Last tested: 21 August 2026

Full record JSON Shares with Thinking Machines: Inkling Small

OpenAI: gpt-oss-120b (batch)openai/gpt-oss-120b:batchbuilds on the GPT tokenizerHigh

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why high: inherited from openai/gpt-oss-120b: a serving variant shares its base model's tokenizer
Variant of: OpenAI: gpt-oss-120b
Context: 131,072
Max output: 117,964
Modalities: text->text
Prompt price: $0.15 / M tokens
Entered the catalogue: 5 August 2025
Last tested: not yet

Full record JSON

OpenAI: gpt-oss-20bopenai/gpt-oss-20bbuilds on the GPT tokenizerHigh

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why high: an exact fingerprint shared with 31 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_d1411c9d · shared with 31 other models
Context: 131,072
Max output: 117,964
Modalities: text->text
Prompt price: $0.03 / M tokens
Entered the catalogue: 5 August 2025
Last tested: 21 August 2026

Full record JSON Shares with Thinking Machines: Inkling Small

OpenAI: gpt-oss-safeguard-20bopenai/gpt-oss-safeguard-20bbuilds on the GPT tokenizerHigh

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why high: an exact fingerprint shared with 31 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_d1411c9d · shared with 31 other models
Context: 131,072
Max output: 65,536
Modalities: text->text
Prompt price: $0.07 / M tokens
Entered the catalogue: 29 October 2025
Last tested: 21 August 2026

Full record JSON Shares with Thinking Machines: Inkling Small

OpenAI: o1openai/o1not measuredNo reading

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: not measured
Context: 200,000
Max output: 100,000
Modalities: text+image+file->text
Prompt price: $15.0 / M tokens
Entered the catalogue: 17 December 2024
Last tested: not yet

Full record JSON

OpenAI: o1-proopenai/o1-pronot measuredNo reading

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: not measured
Context: 200,000
Max output: 100,000
Modalities: text+image+file->text
Prompt price: $150 / M tokens
Entered the catalogue: 19 March 2025
Last tested: not yet

Full record JSON

OpenAI: o3openai/o3not measuredNo reading

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: not measured
Context: 200,000
Max output: 100,000
Modalities: text+image+file->text
Prompt price: $2.00 / M tokens
Entered the catalogue: 16 April 2025
Last tested: not yet

Full record JSON

OpenAI: o3 (batch)openai/o3:batcha serving variant of another entryNo reading

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: a serving variant of another entry
Variant of: OpenAI: o3
Context: 200,000
Max output: 100,000
Modalities: text+image+file->text
Prompt price: $1.00 / M tokens
Entered the catalogue: 16 April 2025
Last tested: not yet

Full record JSON

OpenAI: o3 Miniopenai/o3-minibuilds on the GPT tokenizerHigh

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why high: an exact fingerprint shared with 31 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_d1411c9d · shared with 31 other models
Context: 200,000
Max output: 100,000
Modalities: text+file->text
Prompt price: $1.10 / M tokens
Entered the catalogue: 31 January 2025
Last tested: 3 September 2026

Full record JSON Shares with Thinking Machines: Inkling Small

OpenAI: o3 Mini (batch)openai/o3-mini:batchbuilds on the GPT tokenizerHigh

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why high: inherited from openai/o3-mini: a serving variant shares its base model's tokenizer
Variant of: OpenAI: o3 Mini
Context: 200,000
Max output: 100,000
Modalities: text+file->text
Prompt price: $0.55 / M tokens
Entered the catalogue: 31 January 2025
Last tested: not yet

Full record JSON

OpenAI: o3 Mini Highopenai/o3-mini-highbuilds on the GPT tokenizerVery high

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why very high: an exact fingerprint shared with 31 models and an identical API contract inside the same group: two signals of different kinds agree
Fingerprint: tk_d1411c9d · shared with 31 other models
Context: 200,000
Max output: 100,000
Modalities: text+file->text
Prompt price: $1.10 / M tokens
Entered the catalogue: 12 February 2025
Last tested: 3 September 2026

Full record JSON Shares with Thinking Machines: Inkling Small

OpenAI: o3 Proopenai/o3-pronot measuredNo reading

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: not measured
Context: 200,000
Max output: 100,000
Modalities: text+image+file->text
Prompt price: $20.0 / M tokens
Entered the catalogue: 10 June 2025
Last tested: not yet

Full record JSON

OpenAI: o4 Miniopenai/o4-minibuilds on the GPT tokenizerHigh

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why high: an exact fingerprint shared with 31 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_d1411c9d · shared with 31 other models
Context: 200,000
Max output: 100,000
Modalities: text+image+file->text
Prompt price: $1.10 / M tokens
Entered the catalogue: 16 April 2025
Last tested: 3 September 2026

Full record JSON Shares with Thinking Machines: Inkling Small

OpenAI: o4 Mini (batch)openai/o4-mini:batchbuilds on the GPT tokenizerHigh

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why high: inherited from openai/o4-mini: a serving variant shares its base model's tokenizer
Variant of: OpenAI: o4 Mini
Context: 200,000
Max output: 100,000
Modalities: text+image+file->text
Prompt price: $0.55 / M tokens
Entered the catalogue: 16 April 2025
Last tested: not yet

Full record JSON

OpenAI: o4 Mini Highopenai/o4-mini-highbuilds on the GPT tokenizerVery high

Maker: OpenAI
Label on the catalogue: GPT
What the measurement says: builds on the GPT tokenizer
Why very high: an exact fingerprint shared with 31 models and an identical API contract inside the same group: two signals of different kinds agree
Fingerprint: tk_d1411c9d · shared with 31 other models
Context: 200,000
Max output: 100,000
Modalities: text+image+file->text
Prompt price: $1.10 / M tokens
Entered the catalogue: 16 April 2025
Last tested: 3 September 2026

Full record JSON Shares with Thinking Machines: Inkling Small

OpenRouter: Fusionopenrouter/fusiona router, not one stable modelNo reading

Maker: OpenRouter
Label on the catalogue: Router
What the measurement says: a router, not one stable model
Context: 1,000,000
Max output: –
Modalities: text->text
Prompt price: $-1000000.00 / M tokens
Entered the catalogue: 13 June 2026
Last tested: not yet

Full record JSON

Pareto Code Routeropenrouter/pareto-codea router, not one stable modelNo reading

Maker: OpenRouter
Label on the catalogue: Router
What the measurement says: a router, not one stable model
Context: 2,000,000
Max output: –
Modalities: text->text
Prompt price: $-1000000.00 / M tokens
Entered the catalogue: 21 April 2026
Last tested: not yet

Full record JSON

Perplexity: Sonar Deep Researchperplexity/sonar-deep-researchnot measuredNo reading

Maker: Perplexity
Label on the catalogue: no family named
What the measurement says: not measured
Context: 128,000
Max output: 115,200
Modalities: text->text
Prompt price: $2.00 / M tokens
Entered the catalogue: 7 March 2025
Last tested: not yet

Full record JSON

Perplexity: Sonar Pro Searchperplexity/sonar-pro-searchnot measuredNo reading

Maker: Perplexity
Label on the catalogue: no family named
What the measurement says: not measured
Context: 200,000
Max output: 8,000
Modalities: text+image->text
Prompt price: $3.00 / M tokens
Entered the catalogue: 30 October 2025
Last tested: not yet

Full record JSON

Perplexity: Sonar Reasoning Properplexity/sonar-reasoning-pronot measuredNo reading

Maker: Perplexity
Label on the catalogue: no family named
What the measurement says: not measured
Context: 128,000
Max output: 115,200
Modalities: text+image->text
Prompt price: $2.00 / M tokens
Entered the catalogue: 7 March 2025
Last tested: not yet

Full record JSON

Poolside: Laguna S 2.1 (free)poolside/laguna-s-2.1:freea serving variant of another entryNo reading

Maker: Poolside
Label on the catalogue: no family named
What the measurement says: a serving variant of another entry
Variant of: Poolside: Laguna S 2.1
Context: 262,144
Max output: 32,768
Modalities: text->text
Prompt price: $0 / M tokens
Entered the catalogue: 21 July 2026
Last tested: not yet

Full record JSON

Poolside: Laguna XS 2.1 (free)poolside/laguna-xs-2.1:freea serving variant of another entryNo reading

Maker: Poolside
Label on the catalogue: no family named
What the measurement says: a serving variant of another entry
Variant of: Poolside: Laguna XS 2.1
Context: 262,144
Max output: 32,768
Modalities: text->text
Prompt price: $0 / M tokens
Entered the catalogue: 2 July 2026
Last tested: not yet

Full record JSON

Qwen: Qwen Plus 0728qwen/qwen-plus-2025-07-28builds on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen3
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 36 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_5410b38e · shared with 36 other models
Context: 1,000,000
Max output: 32,768
Modalities: text->text
Prompt price: $0.26 / M tokens
Entered the catalogue: 8 September 2025
Last tested: 21 August 2026

Full record JSON Shares with Dots Studio: Dots3-Note Preview (free)

Qwen: Qwen-Plusqwen/qwen-plusbuilds on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 36 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_5410b38e · shared with 36 other models
Context: 1,000,000
Max output: 32,768
Modalities: text->text
Prompt price: $0.26 / M tokens
Entered the catalogue: 1 February 2025
Last tested: 21 August 2026

Full record JSON Shares with Dots Studio: Dots3-Note Preview (free)

Qwen: Qwen2.5 7B Instructqwen/qwen-2.5-7b-instructbuilds on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 36 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_5410b38e · shared with 36 other models
Context: 32,768
Max output: 29,491
Modalities: text->text
Prompt price: $0.10 / M tokens
Entered the catalogue: 16 October 2024
Last tested: 21 August 2026

Full record JSON Shares with Dots Studio: Dots3-Note Preview (free)

Qwen: Qwen2.5 VL 72B Instructqwen/qwen2.5-vl-72b-instructbuilds on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 36 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_5410b38e · shared with 36 other models
Context: 128,000
Max output: 115,200
Modalities: text+image->text
Prompt price: $0.80 / M tokens
Entered the catalogue: 1 February 2025
Last tested: 3 September 2026

Full record JSON Shares with Dots Studio: Dots3-Note Preview (free)

Qwen: Qwen3 14Bqwen/qwen3-14bbuilds on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen3
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 36 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_5410b38e · shared with 36 other models
Context: 131,072
Max output: 16,384
Modalities: text->text
Prompt price: $0.12 / M tokens
Entered the catalogue: 28 April 2025
Last tested: 21 August 2026

Full record JSON Shares with Dots Studio: Dots3-Note Preview (free)

Qwen: Qwen3 235B A22Bqwen/qwen3-235b-a22bbuilds on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen3
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 36 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_5410b38e · shared with 36 other models
Context: 131,072
Max output: 8,192
Modalities: text->text
Prompt price: $0.45 / M tokens
Entered the catalogue: 28 April 2025
Last tested: 3 September 2026

Full record JSON Shares with Dots Studio: Dots3-Note Preview (free)

Qwen: Qwen3 235B A22B Instruct 2507qwen/qwen3-235b-a22b-2507builds on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen3
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 36 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_5410b38e · shared with 36 other models
Context: 262,144
Max output: 235,929
Modalities: text->text
Prompt price: $0.09 / M tokens
Entered the catalogue: 21 July 2025
Last tested: 21 August 2026

Full record JSON Shares with Dots Studio: Dots3-Note Preview (free)

Qwen: Qwen3 235B A22B Thinking 2507qwen/qwen3-235b-a22b-thinking-2507builds on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen3
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 36 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_5410b38e · shared with 36 other models
Context: 131,072
Max output: 117,964
Modalities: text->text
Prompt price: $0.23 / M tokens
Entered the catalogue: 25 July 2025
Last tested: 21 August 2026

Full record JSON Shares with Dots Studio: Dots3-Note Preview (free)

Qwen: Qwen3 30B A3Bqwen/qwen3-30b-a3bbuilds on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen3
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 36 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_5410b38e · shared with 36 other models
Context: 131,072
Max output: 16,384
Modalities: text->text
Prompt price: $0.12 / M tokens
Entered the catalogue: 28 April 2025
Last tested: 21 August 2026

Full record JSON Shares with Dots Studio: Dots3-Note Preview (free)

Qwen: Qwen3 30B A3B Instruct 2507qwen/qwen3-30b-a3b-instruct-2507builds on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen3
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 36 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_5410b38e · shared with 36 other models
Context: 262,144
Max output: 32,000
Modalities: text->text
Prompt price: $0.05 / M tokens
Entered the catalogue: 29 July 2025
Last tested: 21 August 2026

Full record JSON Shares with Dots Studio: Dots3-Note Preview (free)

Qwen: Qwen3 30B A3B Thinking 2507qwen/qwen3-30b-a3b-thinking-2507builds on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen3
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 36 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_5410b38e · shared with 36 other models
Context: 81,920
Max output: 32,768
Modalities: text->text
Prompt price: $0.20 / M tokens
Entered the catalogue: 28 August 2025
Last tested: 21 August 2026

Full record JSON Shares with Dots Studio: Dots3-Note Preview (free)

Qwen: Qwen3 32Bqwen/qwen3-32bbuilds on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen3
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 36 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_5410b38e · shared with 36 other models
Context: 131,072
Max output: 16,384
Modalities: text->text
Prompt price: $0.08 / M tokens
Entered the catalogue: 28 April 2025
Last tested: 21 August 2026

Full record JSON Shares with Dots Studio: Dots3-Note Preview (free)

Qwen: Qwen3 8Bqwen/qwen3-8bbuilds on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen3
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 36 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_5410b38e · shared with 36 other models
Context: 131,072
Max output: 8,192
Modalities: text->text
Prompt price: $0.12 / M tokens
Entered the catalogue: 28 April 2025
Last tested: 21 August 2026

Full record JSON Shares with Dots Studio: Dots3-Note Preview (free)

Qwen: Qwen3 Coder 30B A3B Instructqwen/qwen3-coder-30b-a3b-instructbuilds on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen3
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 36 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_5410b38e · shared with 36 other models
Context: 262,144
Max output: 235,929
Modalities: text->text
Prompt price: $0.07 / M tokens
Entered the catalogue: 31 July 2025
Last tested: 21 August 2026

Full record JSON Shares with Dots Studio: Dots3-Note Preview (free)

Qwen: Qwen3 Coder 480B A35Bqwen/qwen3-coderbuilds on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen3
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 36 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_5410b38e · shared with 36 other models
Context: 262,144
Max output: 65,536
Modalities: text->text
Prompt price: $0.30 / M tokens
Entered the catalogue: 23 July 2025
Last tested: 21 August 2026

Full record JSON Shares with Dots Studio: Dots3-Note Preview (free)

Qwen: Qwen3 Coder Flashqwen/qwen3-coder-flashbuilds on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen3
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 36 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_5410b38e · shared with 36 other models
Context: 1,000,000
Max output: 65,536
Modalities: text->text
Prompt price: $0.20 / M tokens
Entered the catalogue: 17 September 2025
Last tested: 21 August 2026

Full record JSON Shares with Dots Studio: Dots3-Note Preview (free)

Qwen: Qwen3 Coder Nextqwen/qwen3-coder-nextbuilds on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 36 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_5410b38e · shared with 36 other models
Context: 262,144
Max output: 235,929
Modalities: text->text
Prompt price: $0.12 / M tokens
Entered the catalogue: 4 February 2026
Last tested: 21 August 2026

Full record JSON Shares with Dots Studio: Dots3-Note Preview (free)

Qwen: Qwen3 Coder Plusqwen/qwen3-coder-plusbuilds on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen3
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 36 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_5410b38e · shared with 36 other models
Context: 1,000,000
Max output: 65,536
Modalities: text->text
Prompt price: $0.65 / M tokens
Entered the catalogue: 23 September 2025
Last tested: 3 September 2026

Full record JSON Shares with Dots Studio: Dots3-Note Preview (free)

Qwen: Qwen3 Maxqwen/qwen3-maxbuilds on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen3
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 36 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_5410b38e · shared with 36 other models
Context: 262,144
Max output: 65,536
Modalities: text->text
Prompt price: $0.78 / M tokens
Entered the catalogue: 23 September 2025
Last tested: 3 September 2026

Full record JSON Shares with Dots Studio: Dots3-Note Preview (free)

Qwen: Qwen3 Max Thinkingqwen/qwen3-max-thinkingbuilds on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 36 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_5410b38e · shared with 36 other models
Context: 262,144
Max output: 65,536
Modalities: text->text
Prompt price: $0.78 / M tokens
Entered the catalogue: 9 February 2026
Last tested: 3 September 2026

Full record JSON Shares with Dots Studio: Dots3-Note Preview (free)

Qwen: Qwen3 Next 80B A3B Instructqwen/qwen3-next-80b-a3b-instructbuilds on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen3
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 36 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_5410b38e · shared with 36 other models
Context: 262,144
Max output: 16,384
Modalities: text->text
Prompt price: $0.09 / M tokens
Entered the catalogue: 11 September 2025
Last tested: 21 August 2026

Full record JSON Shares with Dots Studio: Dots3-Note Preview (free)

Qwen: Qwen3 Next 80B A3B Thinkingqwen/qwen3-next-80b-a3b-thinkingbuilds on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen3
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 36 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_5410b38e · shared with 36 other models
Context: 262,144
Max output: 32,768
Modalities: text->text
Prompt price: $0.15 / M tokens
Entered the catalogue: 11 September 2025
Last tested: 21 August 2026

Full record JSON Shares with Dots Studio: Dots3-Note Preview (free)

Qwen: Qwen3 VL 235B A22B Instructqwen/qwen3-vl-235b-a22b-instructbuilds on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen3
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 36 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_5410b38e · shared with 36 other models
Context: 262,144
Max output: 32,768
Modalities: text+image->text
Prompt price: $0.21 / M tokens
Entered the catalogue: 23 September 2025
Last tested: 21 August 2026

Full record JSON Shares with Dots Studio: Dots3-Note Preview (free)

Qwen: Qwen3 VL 235B A22B Thinkingqwen/qwen3-vl-235b-a22b-thinkingbuilds on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen3
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 36 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_5410b38e · shared with 36 other models
Context: 131,072
Max output: 32,768
Modalities: text+image->text
Prompt price: $0.40 / M tokens
Entered the catalogue: 23 September 2025
Last tested: 3 September 2026

Full record JSON Shares with Dots Studio: Dots3-Note Preview (free)

Qwen: Qwen3 VL 30B A3B Instructqwen/qwen3-vl-30b-a3b-instructbuilds on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen3
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 36 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_5410b38e · shared with 36 other models
Context: 262,144
Max output: 32,768
Modalities: text+image->text
Prompt price: $0.13 / M tokens
Entered the catalogue: 6 October 2025
Last tested: 21 August 2026

Full record JSON Shares with Dots Studio: Dots3-Note Preview (free)

Qwen: Qwen3 VL 30B A3B Thinkingqwen/qwen3-vl-30b-a3b-thinkingbuilds on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen3
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 36 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_5410b38e · shared with 36 other models
Context: 262,144
Max output: 32,768
Modalities: text+image->text
Prompt price: $0.20 / M tokens
Entered the catalogue: 6 October 2025
Last tested: 21 August 2026

Full record JSON Shares with Dots Studio: Dots3-Note Preview (free)

Qwen: Qwen3 VL 32B Instructqwen/qwen3-vl-32b-instructbuilds on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 36 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_5410b38e · shared with 36 other models
Context: 131,072
Max output: 32,768
Modalities: text+image->text
Prompt price: $0.10 / M tokens
Entered the catalogue: 23 October 2025
Last tested: 21 August 2026

Full record JSON Shares with Dots Studio: Dots3-Note Preview (free)

Qwen: Qwen3 VL 8B Instructqwen/qwen3-vl-8b-instructbuilds on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen3
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 36 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_5410b38e · shared with 36 other models
Context: 262,144
Max output: 32,768
Modalities: text+image->text
Prompt price: $0.12 / M tokens
Entered the catalogue: 14 October 2025
Last tested: 21 August 2026

Full record JSON Shares with Dots Studio: Dots3-Note Preview (free)

Qwen: Qwen3 VL 8B Thinkingqwen/qwen3-vl-8b-thinkingbuilds on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen3
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 36 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_5410b38e · shared with 36 other models
Context: 131,072
Max output: 32,768
Modalities: text+image->text
Prompt price: $0.18 / M tokens
Entered the catalogue: 14 October 2025
Last tested: 21 August 2026

Full record JSON Shares with Dots Studio: Dots3-Note Preview (free)

Qwen: Qwen3.5 397B A17Bqwen/qwen3.5-397b-a17bbuilds on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen3
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 14 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_181907f2 · shared with 14 other models
Context: 262,144
Max output: 235,929
Modalities: text+image+video->text
Prompt price: $0.55 / M tokens
Entered the catalogue: 16 February 2026
Last tested: 22 August 2026

Full record JSON Shares with Qwen: Qwen3.8 Flash

Qwen: Qwen3.5 Plus 2026-02-15qwen/qwen3.5-plus-02-15builds on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen3
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 14 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_181907f2 · shared with 14 other models
Context: 1,000,000
Max output: 65,536
Modalities: text+image+video->text
Prompt price: $0.26 / M tokens
Entered the catalogue: 16 February 2026
Last tested: 21 August 2026

Full record JSON Shares with Qwen: Qwen3.8 Flash

Qwen: Qwen3.5-122B-A10Bqwen/qwen3.5-122b-a10bbuilds on the Qwen tokenizerModerate

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen3
What the measurement says: builds on the Qwen tokenizer
Why moderate: near-exact agreement (48 of 48 strings) with nex-agi/nex-n2-mini, short of a full exact signature
Context: 262,144
Max output: 65,536
Modalities: text+image+video->text
Prompt price: $0.26 / M tokens
Entered the catalogue: 25 February 2026
Last tested: 21 August 2026

Full record JSON

Qwen: Qwen3.5-27Bqwen/qwen3.5-27bbuilds on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen3
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 14 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_181907f2 · shared with 14 other models
Context: 262,144
Max output: 65,536
Modalities: text+image+video->text
Prompt price: $0.20 / M tokens
Entered the catalogue: 25 February 2026
Last tested: 21 August 2026

Full record JSON Shares with Qwen: Qwen3.8 Flash

Qwen: Qwen3.5-35B-A3Bqwen/qwen3.5-35b-a3bbuilds on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen3
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 14 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_181907f2 · shared with 14 other models
Context: 262,144
Max output: 65,536
Modalities: text+image+video->text
Prompt price: $0.16 / M tokens
Entered the catalogue: 25 February 2026
Last tested: 21 August 2026

Full record JSON Shares with Qwen: Qwen3.8 Flash

Qwen: Qwen3.5-9Bqwen/qwen3.5-9bbuilds on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen3
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 14 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_181907f2 · shared with 14 other models
Context: 262,144
Max output: 235,929
Modalities: text+image+video->text
Prompt price: $0.10 / M tokens
Entered the catalogue: 10 March 2026
Last tested: 21 August 2026

Full record JSON Shares with Qwen: Qwen3.8 Flash

Qwen: Qwen3.5-9B (batch)qwen/qwen3.5-9b:batchbuilds on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen3
What the measurement says: builds on the Qwen tokenizer
Why high: inherited from qwen/qwen3.5-9b: a serving variant shares its base model's tokenizer
Variant of: Qwen: Qwen3.5-9B
Context: 262,144
Max output: 235,929
Modalities: text+image+video->text
Prompt price: $0.17 / M tokens
Entered the catalogue: 10 March 2026
Last tested: not yet

Full record JSON

Qwen: Qwen3.5-Flashqwen/qwen3.5-flash-02-23builds on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen3
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 14 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_181907f2 · shared with 14 other models
Context: 1,000,000
Max output: 65,536
Modalities: text+image+video->text
Prompt price: $0.07 / M tokens
Entered the catalogue: 25 February 2026
Last tested: 21 August 2026

Full record JSON Shares with Qwen: Qwen3.8 Flash

Qwen: Qwen3.6 27Bqwen/qwen3.6-27bbuilds on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen3
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 2 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_06ffa14a · shared with 2 other models
Context: 262,144
Max output: 65,536
Modalities: text+image+video->text
Prompt price: $0.30 / M tokens
Entered the catalogue: 27 April 2026
Last tested: 3 September 2026

Full record JSON Shares with Qwen: Qwen3.6 35B A3B

Qwen: Qwen3.6 35B A3Bqwen/qwen3.6-35b-a3bbuilds on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 2 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_06ffa14a · shared with 2 other models
Context: 262,144
Max output: 235,929
Modalities: text+image+video->text
Prompt price: $0.10 / M tokens
Entered the catalogue: 27 April 2026
Last tested: 21 August 2026

Full record JSON Shares with Qwen: Qwen3.6 27B

Qwen: Qwen3.6 Flashqwen/qwen3.6-flashbuilds on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen3
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 14 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_181907f2 · shared with 14 other models
Context: 1,000,000
Max output: 65,536
Modalities: text+image+video->text
Prompt price: $0.19 / M tokens
Entered the catalogue: 27 April 2026
Last tested: 21 August 2026

Full record JSON Shares with Qwen: Qwen3.8 Flash

Qwen: Qwen3.7 Flashqwen/qwen3.7-flashbuilds on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 14 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_181907f2 · shared with 14 other models
Context: 1,000,000
Max output: 65,536
Modalities: text+image+video->text
Prompt price: $0.03 / M tokens
Entered the catalogue: 27 July 2026
Last tested: 21 August 2026

Full record JSON Shares with Qwen: Qwen3.8 Flash

Qwen: Qwen3.7 Maxqwen/qwen3.7-maxbuilds on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 14 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_181907f2 · shared with 14 other models
Context: 1,000,000
Max output: 131,072
Modalities: text->text
Prompt price: $1.48 / M tokens
Entered the catalogue: 21 May 2026
Last tested: 3 September 2026

Full record JSON Shares with Qwen: Qwen3.8 Flash

Qwen: Qwen3.7 Plusqwen/qwen3.7-plusbuilds on the Qwen tokenizerVery high

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen
What the measurement says: builds on the Qwen tokenizer
Why very high: an exact fingerprint shared with 14 models and an identical API contract inside the same group: two signals of different kinds agree
Fingerprint: tk_181907f2 · shared with 14 other models
Context: 1,000,000
Max output: 131,072
Modalities: text+image->text
Prompt price: $0.32 / M tokens
Entered the catalogue: 3 June 2026
Last tested: 21 August 2026

Full record JSON Shares with Qwen: Qwen3.8 Flash

Qwen: Qwen3.8 2.4T A95Bqwen/qwen3.8-2.4t-a95bbuilds on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 14 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_181907f2 · shared with 14 other models
Context: 1,048,576
Max output: 131,072
Modalities: text->text
Prompt price: $2.00 / M tokens
Entered the catalogue: 12 August 2026
Last tested: 3 September 2026

Full record JSON Shares with Qwen: Qwen3.8 Flash

Qwen: Qwen3.8 2.4T A95B (batch)qwen/qwen3.8-2.4t-a95b:batchbuilds on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen
What the measurement says: builds on the Qwen tokenizer
Why high: inherited from qwen/qwen3.8-2.4t-a95b: a serving variant shares its base model's tokenizer
Variant of: Qwen: Qwen3.8 2.4T A95B
Context: 1,010,000
Max output: 909,000
Modalities: text->text
Prompt price: $2.00 / M tokens
Entered the catalogue: 12 August 2026
Last tested: not yet

Full record JSON

Qwen: Qwen3.8 Flashqwen/qwen3.8-flashbuilds on the Qwen tokenizerVery high

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen
What the measurement says: builds on the Qwen tokenizer
Why very high: an exact fingerprint shared with 14 models and an identical API contract inside the same group: two signals of different kinds agree
Fingerprint: tk_181907f2 · shared with 14 other models
Context: 1,000,000
Max output: 131,072
Modalities: text+image+video->text
Prompt price: $0.15 / M tokens
Entered the catalogue: 26 August 2026
Last tested: 3 September 2026

Full record JSON Shares with Qwen: Qwen3.8 2.4T A95B

Qwen: Qwen3.8 Max (0902)qwen/qwen3.8-max-0902queued for measurementNo reading

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen
What the measurement says: queued for measurement
Context: 1,000,000
Max output: 131,072
Modalities: text+image+video->text
Prompt price: $2.00 / M tokens
Entered the catalogue: 3 September 2026
Last tested: not yet

Full record JSON

Qwen2.5 72B Instructqwen/qwen-2.5-72b-instructbuilds on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 36 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_5410b38e · shared with 36 other models
Context: 32,768
Max output: 16,384
Modalities: text->text
Prompt price: $0.36 / M tokens
Entered the catalogue: 19 September 2024
Last tested: 21 August 2026

Full record JSON Shares with Dots Studio: Dots3-Note Preview (free)

Qwen2.5 Coder 32B Instructqwen/qwen-2.5-coder-32b-instructbuilds on the Qwen tokenizerHigh

Maker: Alibaba (Qwen)
Label on the catalogue: Qwen
What the measurement says: builds on the Qwen tokenizer
Why high: an exact fingerprint shared with 36 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_5410b38e · shared with 36 other models
Context: 32,768
Max output: 29,491
Modalities: text->text
Prompt price: $0.66 / M tokens
Entered the catalogue: 11 November 2024
Last tested: 3 September 2026

Full record JSON Shares with Dots Studio: Dots3-Note Preview (free)

Relace: Relace Apply 3relace/relace-apply-3not measuredNo reading

Maker: Relace
Label on the catalogue: no family named
What the measurement says: not measured
Context: 256,000
Max output: 128,000
Modalities: text->text
Prompt price: $0.85 / M tokens
Entered the catalogue: 26 September 2025
Last tested: not yet

Full record JSON

ReMM SLERP 13Bundi95/remm-slerp-l2-13bbuilds on the Llama2 tokenizerHigh

Maker: Undi95
Label on the catalogue: Llama2
What the measurement says: builds on the Llama2 tokenizer
Why high: an exact fingerprint shared with 1 model that declares the same family, without a second signal of a different kind yet
Fingerprint: tk_5348f9f6 · shared with 1 other model
Context: 6,144
Max output: 5,529
Modalities: text->text
Prompt price: $0.35 / M tokens
Entered the catalogue: 22 July 2023
Last tested: 22 August 2026

Full record JSON Shares with MythoMax 13B

Sakana: Fugu Maxsakana/fugu-maxqueued for measurementNo reading

Maker: Sakana
Label on the catalogue: no family named
What the measurement says: queued for measurement
Context: 1,000,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $2.00 / M tokens
Entered the catalogue: 11 September 2026
Last tested: not yet

Full record JSON

Sakana: Fugu Ultrasakana/fugu-ultranot measuredNo reading

Maker: Sakana
Label on the catalogue: no family named
What the measurement says: not measured
Context: 1,000,000
Max output: 128,000
Modalities: text+image->text
Prompt price: $5.00 / M tokens
Entered the catalogue: 24 June 2026
Last tested: 3 September 2026

Full record JSON

Sakana: Fugu Ultra v2sakana/fugu-ultra-v2queued for measurementNo reading

Maker: Sakana
Label on the catalogue: no family named
What the measurement says: queued for measurement
Context: 1,000,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $5.00 / M tokens
Entered the catalogue: 11 September 2026
Last tested: not yet

Full record JSON

Sakana: Sakana Namazusakana/sakana-namazunot measuredNo reading

Maker: Sakana
Label on the catalogue: no family named
What the measurement says: not measured
Context: 262,144
Max output: 65,536
Modalities: text+image+file->text
Prompt price: $0.95 / M tokens
Entered the catalogue: 11 August 2026
Last tested: not yet

Full record JSON

Sao10K: Llama 3 8B Lunarissao10k/l3-lunaris-8bbuilds on the Llama3 tokenizerHigh

Maker: Sao10k
Label on the catalogue: Llama3
What the measurement says: builds on the Llama3 tokenizer
Why high: one template-boundary shift from a group whose members all declare the same family
Fingerprint: tk_066351de · unique so far
Context: 8,192
Max output: 7,372
Modalities: text->text
Prompt price: $0.04 / M tokens
Entered the catalogue: 13 August 2024
Last tested: 21 August 2026

Full record JSON

Sao10K: Llama 3.1 Euryale 70B v2.2sao10k/l3.1-euryale-70bbuilds on the Llama3 tokenizerHigh

Maker: Sao10k
Label on the catalogue: Llama3
What the measurement says: builds on the Llama3 tokenizer
Why high: an exact fingerprint shared with 7 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_6588ed5b · shared with 7 other models
Context: 131,072
Max output: 16,384
Modalities: text->text
Prompt price: $0.85 / M tokens
Entered the catalogue: 28 August 2024
Last tested: 21 August 2026

Full record JSON Shares with Perplexity: Sonar Pro

Sao10K: Llama 3.3 Euryale 70Bsao10k/l3.3-euryale-70bbuilds on the Llama3 tokenizerHigh

Maker: Sao10k
Label on the catalogue: Llama3
What the measurement says: builds on the Llama3 tokenizer
Why high: an exact fingerprint shared with 7 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_6588ed5b · shared with 7 other models
Context: 131,072
Max output: 16,384
Modalities: text->text
Prompt price: $0.65 / M tokens
Entered the catalogue: 18 December 2024
Last tested: 21 August 2026

Full record JSON Shares with Perplexity: Sonar Pro

SpaceXAI: Grok 4.20x-ai/grok-4.20builds on the Grok tokenizerHigh

Maker: xAI
Label on the catalogue: Grok
What the measurement says: builds on the Grok tokenizer
Why high: an exact fingerprint shared with 2 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_a17bbc1d · shared with 2 other models
Context: 2,000,000
Max output: 1,800,000
Modalities: text+image+file->text
Prompt price: $1.25 / M tokens
Entered the catalogue: 31 March 2026
Last tested: 3 September 2026

Full record JSON Shares with SpaceXAI: Grok Build 0.1

SpaceXAI: Grok 4.20 Multi-Agentx-ai/grok-4.20-multi-agentnot measuredNo reading

Maker: xAI
Label on the catalogue: Grok
What the measurement says: not measured
Context: 2,000,000
Max output: 1,800,000
Modalities: text+image+file->text
Prompt price: $1.25 / M tokens
Entered the catalogue: 31 March 2026
Last tested: 3 September 2026

Full record JSON

SpaceXAI: Grok 4.3x-ai/grok-4.3builds on the Grok tokenizerHigh

Maker: xAI
Label on the catalogue: Grok
What the measurement says: builds on the Grok tokenizer
Why high: an exact fingerprint shared with 2 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_a17bbc1d · shared with 2 other models
Context: 1,000,000
Max output: 900,000
Modalities: text+image+file->text
Prompt price: $1.25 / M tokens
Entered the catalogue: 30 April 2026
Last tested: 3 September 2026

Full record JSON Shares with SpaceXAI: Grok Build 0.1

SpaceXAI: Grok 4.3 (batch)x-ai/grok-4.3:batchbuilds on the Grok tokenizerHigh

Maker: xAI
Label on the catalogue: Grok
What the measurement says: builds on the Grok tokenizer
Why high: inherited from x-ai/grok-4.3: a serving variant shares its base model's tokenizer
Variant of: SpaceXAI: Grok 4.3
Context: 1,000,000
Max output: 900,000
Modalities: text+image+file->text
Prompt price: $1.00 / M tokens
Entered the catalogue: 30 April 2026
Last tested: not yet

Full record JSON

SpaceXAI: Grok 4.5x-ai/grok-4.5builds on the Grok tokenizerModerate

Maker: xAI
Label on the catalogue: Grok
What the measurement says: builds on the Grok tokenizer
Why moderate: near-exact agreement (49 of 49 strings) with x-ai/grok-4.6, short of a full exact signature
Fingerprint: tk_cb7f8e86 · unique so far
Context: 500,000
Max output: 450,000
Modalities: text+image+file->text
Prompt price: $2.00 / M tokens
Entered the catalogue: 8 July 2026
Last tested: 3 September 2026

Full record JSON

SpaceXAI: Grok 4.6x-ai/grok-4.6builds on the Grok tokenizerModerate

Maker: xAI
Label on the catalogue: Grok
What the measurement says: builds on the Grok tokenizer
Why moderate: near-exact agreement (49 of 49 strings) with x-ai/grok-4.5, short of a full exact signature
Context: 500,000
Max output: 450,000
Modalities: text+image+file->text
Prompt price: $2.00 / M tokens
Entered the catalogue: 12 August 2026
Last tested: 3 September 2026

Full record JSON

SpaceXAI: Grok Build 0.1x-ai/grok-build-0.1builds on the Grok tokenizerHigh

Maker: xAI
Label on the catalogue: Grok
What the measurement says: builds on the Grok tokenizer
Why high: an exact fingerprint shared with 2 models that declare the same family, without a second signal of a different kind yet
Fingerprint: tk_a17bbc1d · shared with 2 other models
Context: 256,000
Max output: 230,400
Modalities: text+image+file->text
Prompt price: $1.00 / M tokens
Entered the catalogue: 20 May 2026
Last tested: 3 September 2026

Full record JSON Shares with SpaceXAI: Grok 4.3

Z.ai: GLM 5.2 (batch)z-ai/glm-5.2:batcha serving variant of another entryNo reading

Maker: Z.ai
Label on the catalogue: no family named
What the measurement says: a serving variant of another entry
Variant of: Z.ai: GLM 5.2
Context: 1,048,576
Max output: 943,718
Modalities: text->text
Prompt price: $0.70 / M tokens
Entered the catalogue: 16 June 2026
Last tested: not yet

Full record JSON

Z.ai: GLM 5.2 (free)z-ai/glm-5.2:freea serving variant of another entryNo reading

Maker: Z.ai
Label on the catalogue: no family named
What the measurement says: a serving variant of another entry
Variant of: Z.ai: GLM 5.2
Context: 32,768
Max output: 29,491
Modalities: text->text
Prompt price: $0 / M tokens
Entered the catalogue: 16 June 2026
Last tested: not yet

Full record JSON

Z.ai: GLM 5.3 (batch)z-ai/glm-5.3:batchqueued for measurementNo reading

Maker: Z.ai
Label on the catalogue: no family named
What the measurement says: queued for measurement
Variant of: Z.ai: GLM 5.3
Context: 1,048,576
Max output: 943,718
Modalities: text->text
Prompt price: $0.70 / M tokens
Entered the catalogue: 18 August 2026
Last tested: not yet

Full record JSON

Z.ai: GLM 5.3 Flash (batch)z-ai/glm-5.3-flash:batcha serving variant of another entryNo reading

Maker: Z.ai
Label on the catalogue: no family named
What the measurement says: a serving variant of another entry
Variant of: Z.ai: GLM 5.3 Flash
Context: 1,048,576
Max output: 943,718
Modalities: text+image+video->text
Prompt price: $0.07 / M tokens
Entered the catalogue: 26 August 2026
Last tested: not yet

Full record JSON

Anthropic: Claude Fable Latest~anthropic/claude-fable-latesta router, not one stable modelNo reading

Maker: Anthropic
Label on the catalogue: Router
What the measurement says: a router, not one stable model
Context: 1,000,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $10.0 / M tokens
Entered the catalogue: 9 June 2026
Last tested: not yet

Full record JSON

Anthropic: Claude Haiku Latest~anthropic/claude-haiku-latesta router, not one stable modelNo reading

Maker: Anthropic
Label on the catalogue: Router
What the measurement says: a router, not one stable model
Context: 200,000
Max output: 64,000
Modalities: text+image+file->text
Prompt price: $1.00 / M tokens
Entered the catalogue: 27 April 2026
Last tested: not yet

Full record JSON

Anthropic: Claude Opus Latest~anthropic/claude-opus-latesta router, not one stable modelNo reading

Maker: Anthropic
Label on the catalogue: Router
What the measurement says: a router, not one stable model
Context: 1,000,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $5.00 / M tokens
Entered the catalogue: 21 April 2026
Last tested: not yet

Full record JSON

Anthropic: Claude Sonnet Latest~anthropic/claude-sonnet-latesta router, not one stable modelNo reading

Maker: Anthropic
Label on the catalogue: Router
What the measurement says: a router, not one stable model
Context: 1,000,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $2.00 / M tokens
Entered the catalogue: 27 April 2026
Last tested: not yet

Full record JSON

DeepSeek: DeepSeek Flash Latest~deepseek/deepseek-flash-latestqueued for measurementNo reading

Maker: DeepSeek
Label on the catalogue: Router
What the measurement says: queued for measurement
Context: 1,048,576
Max output: 393,216
Modalities: text+image->text
Prompt price: $0.15 / M tokens
Entered the catalogue: 14 September 2026
Last tested: not yet

Full record JSON

DeepSeek: DeepSeek Pro Latest~deepseek/deepseek-pro-latestqueued for measurementNo reading

Maker: DeepSeek
Label on the catalogue: Router
What the measurement says: queued for measurement
Context: 1,048,576
Max output: 393,216
Modalities: text->text
Prompt price: $0.58 / M tokens
Entered the catalogue: 14 September 2026
Last tested: not yet

Full record JSON

DeepSeek: DeepSeek V4 Flash Latest~deepseek/deepseek-v4-flash-latesta router, not one stable modelNo reading

Maker: DeepSeek
Label on the catalogue: Router
What the measurement says: a router, not one stable model
Context: 1,310,720
Max output: 393,216
Modalities: text->text
Prompt price: $0.04 / M tokens
Entered the catalogue: 1 August 2026
Last tested: not yet

Full record JSON

Google: Gemini Flash Latest~google/gemini-flash-latesta router, not one stable modelNo reading

Maker: Google
Label on the catalogue: Router
What the measurement says: a router, not one stable model
Context: 1,048,576
Max output: 65,536
Modalities: text+image+file+audio+video->text
Prompt price: $0.75 / M tokens
Entered the catalogue: 27 April 2026
Last tested: not yet

Full record JSON

Google: Gemini Pro Latest~google/gemini-pro-latesta router, not one stable modelNo reading

Maker: Google
Label on the catalogue: Router
What the measurement says: a router, not one stable model
Context: 1,048,576
Max output: 65,536
Modalities: text+image+file+audio+video->text
Prompt price: $2.00 / M tokens
Entered the catalogue: 27 April 2026
Last tested: not yet

Full record JSON

MoonshotAI: Kimi Latest~moonshotai/kimi-latesta router, not one stable modelNo reading

Maker: Moonshot AI
Label on the catalogue: Router
What the measurement says: a router, not one stable model
Context: 1,048,576
Max output: 943,718
Modalities: text+image+video->text
Prompt price: $2.10 / M tokens
Entered the catalogue: 27 April 2026
Last tested: not yet

Full record JSON

OpenAI GPT Latest~openai/gpt-latestwithdrawn from the catalogueNo reading

Maker: OpenAI
Label on the catalogue: Router
What the measurement says: withdrawn from the catalogue
Context: 1,050,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $2.00 / M tokens
Entered the catalogue: 27 April 2026
Last tested: not yet

Full record JSON

OpenAI: GPT Astra Latest~openai/gpt-astra-latestqueued for measurementNo reading

Maker: OpenAI
Label on the catalogue: Router
What the measurement says: queued for measurement
Context: 1,050,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $10.0 / M tokens
Entered the catalogue: 11 September 2026
Last tested: not yet

Full record JSON

OpenAI: GPT Luna Latest~openai/gpt-luna-latestqueued for measurementNo reading

Maker: OpenAI
Label on the catalogue: Router
What the measurement says: queued for measurement
Context: 1,050,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $0.20 / M tokens
Entered the catalogue: 11 September 2026
Last tested: not yet

Full record JSON

OpenAI: GPT Mini Latest~openai/gpt-mini-latesta router, not one stable modelNo reading

Maker: OpenAI
Label on the catalogue: Router
What the measurement says: a router, not one stable model
Context: 400,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $0.75 / M tokens
Entered the catalogue: 27 April 2026
Last tested: not yet

Full record JSON

OpenAI: GPT Sol Latest~openai/gpt-sol-latestqueued for measurementNo reading

Maker: OpenAI
Label on the catalogue: Router
What the measurement says: queued for measurement
Context: 1,050,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $2.00 / M tokens
Entered the catalogue: 11 September 2026
Last tested: not yet

Full record JSON

OpenAI: GPT Terra Latest~openai/gpt-terra-latestqueued for measurementNo reading

Maker: OpenAI
Label on the catalogue: Router
What the measurement says: queued for measurement
Context: 1,050,000
Max output: 128,000
Modalities: text+image+file->text
Prompt price: $2.00 / M tokens
Entered the catalogue: 11 September 2026
Last tested: not yet

Full record JSON

xAI: Grok Latest~x-ai/grok-latesta router, not one stable modelNo reading

Maker: xAI
Label on the catalogue: Router
What the measurement says: a router, not one stable model
Context: 500,000
Max output: 450,000
Modalities: text+image+file->text
Prompt price: $2.00 / M tokens
Entered the catalogue: 8 July 2026
Last tested: not yet

Full record JSON

Z.ai: GLM Flash Latest~z-ai/glm-flash-latesta router, not one stable modelNo reading

Maker: Z.ai
Label on the catalogue: Router
What the measurement says: a router, not one stable model
Context: 1,310,720
Max output: 131,072
Modalities: text+image+video->text
Prompt price: $0.07 / M tokens
Entered the catalogue: 27 August 2026
Last tested: not yet

Full record JSON

Z.ai: GLM Latest~z-ai/glm-latesta router, not one stable modelNo reading

Maker: Z.ai
Label on the catalogue: Router
What the measurement says: a router, not one stable model
Context: 1,310,720
Max output: 235,929
Modalities: text->text
Prompt price: $0.88 / M tokens
Entered the catalogue: 19 August 2026
Last tested: not yet

Full record JSON

Why the dull ones are here too

Plenty of these rows say the obvious: a maker's model reads with that maker's own vocabulary, exactly as its label claims. Those are published because a measurement we took is a measurement we show, and because they are the reference library that makes the interesting ones possible. Ox Alpha could only be placed with the Z.ai family because GLM had already been measured. The method and the controls cover both halves.

Using these figures

Quote any figure here with attribution to YFarmX and a link to the row it came from. Every row has its own address, so a cited number stays checkable, and measurements are dated and append-only. We are not handing out the raw files at the moment; for bulk or commercial use, ask first.