Models / Mistral
Codestral 2508
by Mistral ·
mistralai/codestral-2508Mistral'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)
tool-usereleased 2025-08-01
Legal score · raw
-
not yet benchmarked
Context
256K
max output 205K
Input
$0.38
per 1M tokens
Output
$1.13
per 1M tokens
Suite cost
-
no run recorded
Prompt caching
Grounded answers re-send the same retrieved authority every turn, so a cached read is what a long matter actually costs. Prices are per 1M tokens, from the provider’s own catalog.
Cache read
$0.04
10x cheaper than uncached
Uncached input
$0.38
per 1M tokens
Capabilities
Modalities
in textfile
out text
Request parameters it accepts
frequency_penaltymax_tokenspredictionpresence_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_p
Benchmark results
This model has not been run through the suite yet. See Humanity's Last Lawsuit for the benchmark models are ranked on.