AI Desk · AI FingerprintingNew arrival

DeepSeek: DeepSeek V4.1 Flash (batch)

deepseek/deepseek-v4.1-flash:batch · DeepSeekDeclared and measured agree

Tokenizer group (measured): DeepSeek
Declared tokenizer tag: DeepSeek
Entered catalogue: 10 September 2026
Measurement: Variant: inherits its base model’s measurement
Evidence confidence: High

Why high: inherited from deepseek/deepseek-v4.1-flash: a serving variant shares its base model's tokenizer.

Evidence

✓ inherited from deepseek/deepseek-v4.1-flash: a serving variant shares its base model's tokenizer

Compare with DeepSeek: DeepSeek V4.1 Flash

Report a correction

This entry is a serving variant of DeepSeek: DeepSeek V4.1 Flash. 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

DeepSeek: DeepSeek V4.1 Flash (batch) is DeepSeek's model, and its measured tokenizer sits in DeepSeek's own signature group alongside its sibling models. No other maker's measured model shares it so far.

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_f830600e
How much it can read and write	Reads up to 1,048,576 tokens at once, writes up to 131,072	its own listing
Whether it thinks before answering	Reasons when asked to, at max, high, low, high by default	its own listing

Declared record

What the catalogue claims about this model

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...

Modalities: text+image->text
Declared tokenizer: DeepSeek
Prompt price: $0.11 / M tokens
Completion price: $0.34 / M tokens

Supported parameters

frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p

defaults: {}

Catalogue entry Weights on Hugging Face

History

Every observation, kept as taken

10 September 2026Enters the OpenRouter catalogue declared as DeepSeek.