Mistral: Codestral 2508 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.
| Signal | Result | Reference |
|---|---|---|
| Tokenizer signature | Exact match with 12 other models | tk_0da8a999 |
| API surface | No other entry shares this exact contract | api_336f3ff0 |
| Context and output | 256,000 context · – max output | declared |
| Reasoning contract | None declared | declared |
| Serving providers observed | Mistral | measured 21 August 2026 |
Click a row to open the full comparison.
An x marks a row excluded as corrupt (caching or provider interference detected during measurement). Overhead subtracted: 3 prompt tokens.
Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. [Blog Post](https://mistral.ai/news/codestral-25-08)
Supported parameters
frequency_penaltymax_tokenspredictionpresence_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_p
defaults: {"temperature":0.3}
Cite this page as the evidence record for Mistral: Codestral 2508: the URL is stable, measurements are dated, and revisions append to the history above. Method: tokenizer fingerprinting, v1, 50 strings. The raw data behind every figure is on the data page.
