AI Desk · AI FingerprintingWithdrawn *

Qwen: Qwen3.8 2.4T A95B (batch)

qwen/qwen3.8-2.4t-a95b:batch · Alibaba (Qwen)Declared and measured agree

Tokenizer lineage (measured): Qwen
Declared tokenizer tag: Qwen
Entered catalogue: 12 August 2026
Measurement: Variant: inherits its base model’s measurement
Evidence confidence: High

Why high: inherited from qwen/qwen3.8-2.4t-a95b: a serving variant shares its base model's tokenizer.

Evidence

✓ inherited from qwen/qwen3.8-2.4t-a95b: a serving variant shares its base model's tokenizer

Compare with Qwen: Qwen3.8 2.4T A95B

Report a correction

This entry is a serving variant of Qwen: Qwen3.8 2.4T A95B. A variant shares its base model's tokenizer by construction, so the measurement lives on the base record and this page inherits it.

Identity statement

Qwen: Qwen3.8 2.4T A95B (batch) is Alibaba (Qwen)'s model. Its measured tokenizer sits with the Qwen group, which is evidence that it builds on the Qwen tokenizer. Tokenizer reuse is normal engineering, open vocabularies travel between labs, and this says nothing against Alibaba (Qwen)'s authorship of the model itself.

What we checked

Four different kinds of evidence, and what each one showed

We checked	What we found	Where it came from
How it counts tokens	Not measured yet	we measured it
How its API is set up	A combination of settings no other listing in the catalogue uses	api_ad9bd23f
How much it can read and write	Reads up to 1,010,000 tokens at onceOpenRouter's listing shows 909,000 output tokens, which is 90% of the context window, the figure it carries where the provider declares no maximum.	its own listing
Whether it thinks before answering	Always reasons, and cannot be turned off, at xhigh, medium, low, xhigh by default	its own listing

Declared record

What the catalogue claims about this model

Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...

Modalities: text->text
Declared tokenizer: Qwen
Prompt price: $2.00 / M tokens
Completion price: $6.00 / M tokens

Supported parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

defaults: {"temperature":1,"top_p":0.95,"top_k":20}

Catalogue entry Weights on Hugging Face

History

Every observation, kept as taken

12 August 2026Enters the OpenRouter catalogue declared as Qwen.

* Qwen: Qwen3.8 2.4T A95B (batch) no longer appears in the OpenRouter catalogue, first absent from the snapshot of 5 October 2026. The record stays because the measurements above were real when they were taken and this address has been published.