DevTk.AI

Codestral 25.08

Mistral

Codestral 25.08 by Mistral: $0.3/M cache-miss input, $0.9/M output tokens. 128K context. Function Calling & JSON Mode. Price verified 2026-11-18.

Input Price

$0.3

cache miss / 1M tokens

Output Price

$0.9

per 1M tokens

Context Window

128K

tokens

Codestral 25.08 price history

No price changes recorded for Codestral 25.08 in our AI API price change log (earliest entry: 2026-05-27). Current rates last verified against the official Mistral pricing page on 2026-11-18. See all AI API price changes

Specifications

ProviderMistral
Model IDcodestral-2508
Input Price$0.3 / 1M cache-miss tokens
Output Price$0.9 / 1M tokens
Context Window128K tokens
Max OutputNot published by provider
Capabilities
textfunction_callingstructured_output
Release Date2025-07-30
Pricing SourceOfficial Mistral pricing
Price Verified2026-11-18
NotesMistral's low-latency code model for completion and fill-in-the-middle (FIM), with predicted outputs. Alias codestral-latest.

Monthly Cost Estimates

Estimated monthly costs based on different daily usage levels (assuming 50% input / 50% output split). Input estimates use cache-miss pricing, so cache-heavy workloads can be lower.

Daily TokensMonthly CostAnnual Cost
10K $0.18 $2.16
50K $0.9 $10.80
100K $1.80 $21.60
500K $9.00 $108.00
1.0M $18.00 $216.00

How Codestral 25.08 Pricing Compares

Standard cache-miss input / output prices per 1M tokens, compared with active, price-verified models priced in USD. Cached, batch and long-context rates are not included.

  • Within Mistral: 4 of 5 other active Mistral models have a lower input price, and 4 have a lower output price.
  • Similar context window: among the 15 active models with a 64K–256K token context window, Codestral 25.08 ranks #8 from cheapest at a 50/50 input/output mix. Cheapest: GLM-4.7-Flash ($0.00/$0.00). Most expensive: Jamba Large 1.7 ($2.00/$8.00).

Use our Token Counter to estimate how many tokens your prompts use, and our Pricing Calculator to compare costs across all models.

Codestral 25.08 Key Details

  • Pricing: $0.3/M cache-miss input tokens, $0.9/M output tokens
  • Context window: 128K tokens — 87 of 90 active models we track have a larger window
  • Max output: not separately published by the provider
  • Capabilities: text, function_calling, structured_output
  • Highlights: Mistral's low-latency code model for completion and fill-in-the-middle (FIM), with predicted outputs. Alias codestral-latest.
  • Released: 2025-07-30

Other Mistral Models

Similar Price Range

Related Tools

FAQ

How much does Codestral 25.08 cost?

Codestral 25.08 costs $0.3 per million cache-miss input tokens and $0.9 per million output tokens. For a typical workload of 100K input tokens/day and 50K output tokens/day, expect approximately $2.25/month before cache-hit savings.

What is Codestral 25.08's context window?

Codestral 25.08 supports a context window of 128K tokens. This means your combined input prompt and output response can be up to 128K tokens. Mistral does not publish a separate maximum-output limit for this model.

Is Codestral 25.08 good for my use case?

Codestral 25.08 supports text, function_calling, structured_output. We track pricing and limits, not output quality, so test it on your own prompts before committing. The price comparison above lists cheaper and pricier models with a similar context window, and the Pricing Calculator estimates your monthly cost across all of them.