Specialized generative coding and fill-in-the-middle model fluent in 80+ programming languages Need a token count first? Use the Mistral token counter.
codestral-latest and are billed at current Codestral (Current Generation) rates.codestral-latest| Scenario | Input Tokens | Output Tokens | Uncached Cost | With Prompt Caching |
|---|---|---|---|---|
| Short Chat Query | 1,000 | 500 | $0.00075 | $0.00048 |
| Document Summarization | 10,000 | 2,000 | $0.00480 | $0.00210 |
| Codebase & Context Analysis | 100,000 | 20,000 | $0.0480 | $0.0210 |
| Batch Corpus Processing | 1,000,000 | 100,000 | $0.3900 | $0.1200 |
Tier 1 (free tier) reference limits — your account's actual quota may be higher.
Ideal for production workloads demanding flagship capabilities, deep context depth (256k tokens), and reliability from Mistral AI. Excellent when predictable tokenomics and prompt caching support are paramount.
If your use-case requires sub-second streaming latency or ultra-high frequency classification at micro-cent pricing, consider lighter budget options such as Gemini Flash-Lite or Claude Haiku. For deep formal logic, consider dedicated reasoning models like o3.
For Codestral (Current Generation), 1 million input tokens costs $0.30, while 1 million output tokens costs $0.90. If using prompt caching, repetitive input prefixes are discounted to $0.03 per million.
Codestral (Current Generation) features a maximum context window of 256,000 tokens (~192,000 words), with a maximum output limit of 8,192 tokens per completion.
Codestral (Current Generation) utilizes the Mistral Tekken BPE (~131k vocabulary). Token counting on TokenMath runs client-side to ensure maximum privacy.
Yes. Codestral (Current Generation) supports prompt caching with a cached input rate of $0.03/1M (saving up to 90% on repeated input context).