Enter opens the highlighted result. Esc closes.

Codestral 2508 API pricing

As of October 22, 2026, Mistral Codestral 2508 costs $0.30 per million input tokens and $0.90 per million output tokens on Mistral AI's own API, with cached input at $0.03 per million.

Codestral 2508 benchmarks and specs · Every Mistral AI model's price

  • Input, per million tokens$0.30
  • Output, per million tokens$0.90
  • Cached input, per million$0.03
  • Context window256K tokens
  • Max output205K tokens
  • Output speedNot measured

What a request costs

Three fixed token mixes at the list price, without cache or batch discounts. For a whole month, use the calculator.

Cost of three workloads on Codestral 2508
WorkloadTokensOne request1,000 requestsFits the context window
Chat turn 1K input + 500 output tokens $0.0008 $0.750 Yes
Repository review 50K input + 3K output tokens $0.018 $17.70 Yes
Agent loop 200K input + 10K output tokens $0.069 $69.00 Yes
Solved coding task One SWE-bench Verified attempt, divided by the share that succeed Not computable Not computable

Price history

We have read Mistral AI's own price every day since October 21, 2026. It has not changed yet; any change will be listed here with its date.

  1. October 21, 2026 First recorded: $0.30 input, $0.90 output

Cheaper models as good as Codestral 2508

Codestral 2508 has no overall or coding score, so we make no quality claim against it.

Codestral 2508 pricing questions

How much does Codestral 2508 cost per million tokens?
$0.30 per million input tokens and $0.90 per million output tokens, as listed on OpenRouter on October 22, 2026.
Does Codestral 2508 support prompt caching?
Yes. OpenRouter lists cached input at $0.03 per million tokens, against $0.30 for uncached input.
Has the price of Codestral 2508 changed?
Not since we started recording it daily on October 21, 2026.