mistralai

Codestral 2508 pricing & benchmarks

Released Aug 1, 2025 · served by 1 provider

Input / 1M tokens$0.300
Output / 1M tokens$0.900
Context window256K
Cached input$0.030
1M in + 300K out$0.57

What Codestral 2508 is

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.

Providers and prices for Codestral 2508

The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.

ProviderInputOutputContext QuantUptime 24hThroughput
Mistralcheapest $0.300 $0.900 256K 99.9%

Codestral 2508 benchmark results

Design Arena head-to-head results, as reported through the OpenRouter model API.

CategoryArenaRankEloWin rate
3d models #85 1078 45.5%
uicomponent models #86 1054 46.9%
dataviz models #92 1047 41.7%
codecategories models #98 1038 38.5%
gamedev models #98 1023 36.2%
website models #100 1038 37.8%

FAQ

How much does the Codestral 2508 API cost?

$0.300 per 1M input tokens and $0.900 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $0.57.

Is Codestral 2508 free?

No. It is a paid model starting at $0.300 per 1M input tokens, though some providers offer trial credits.

Which provider is cheapest for Codestral 2508?

Mistral at $0.300 input / $0.900 output per 1M tokens.

Can I self-host Codestral 2508?

No. Codestral 2508 is closed-weight and only available through hosted APIs.