Mistral: Mistral Medium 3.5 (batch)

mistralai/mistral-medium-3-5:batch · Mistral AIDeclared and measured agree

Tokenizer lineage (measured): Mistral
Declared tokenizer tag: Mistral
Entered catalogue: 30 April 2026
Measurement: Variant: inherits its base model’s measurement
Evidence confidence: Very high

Why very high: inherited from mistralai/mistral-medium-3-5: a serving variant shares its base model's tokenizer.

Evidence

✓ inherited from mistralai/mistral-medium-3-5: a serving variant shares its base model's tokenizer

Compare with Mistral: Mistral Medium 3.5

Report a correction

This entry is a serving variant of Mistral: Mistral Medium 3.5. 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

Mistral: Mistral Medium 3.5 (batch) is Mistral AI's model. Its measured tokenizer sits with the Mistral group, which is evidence that it builds on the Mistral tokenizer. Tokenizer reuse is normal engineering, open vocabularies travel between labs, and this says nothing against Mistral AI'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	Set up identically to 3 other listings, field for field	api_e77b232e
How much it can read and write	Reads up to 262,144 tokens at once, writes up to 209,715	its own listing
Whether it thinks before answering	Reasons when asked to, at high, none, high by default	its own listing

Declared record

What the catalogue claims about this model

Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...

Modalities: text+image+file->text
Declared tokenizer: Mistral
Prompt price: $0.75 / M tokens
Completion price: $3.75 / M tokens

Supported parameters

frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningreasoning_effortresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_p

defaults: {"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null}

Catalogue entry

History

Every observation, kept as taken

30 April 2026Enters the OpenRouter catalogue declared as Mistral.