Skip to content
← Models
ClosedMistral AI/10 trustVerified
Codestral 25.08 logo

Codestral 25.08

Mistral's August 2025 code model refresh with 256K context and FIM completion.

Visit official page →

About

Codestral 25.08 is Mistral AI's updated code generation model, released August 1, 2025 as the successor to Codestral 25.01. It keeps the 256K-token context window and the fill-in-the-middle completion specialty that made the line popular with IDE copilots, with updated training data carrying a March 2025 knowledge cutoff. Mistral positions it for high-frequency, low-latency coding assistance: code completion, generation, and function calling across 80+ programming languages.

The honest picture: unlike Codestral 25.01, whose weights shipped under Mistral's research license, 25.08 is served API-only with no downloadable weights as of October 2026, so it is proprietary for catalog purposes. Mistral's API pricing sits at roughly $0.30 per million input tokens and $0.90 per million output tokens. It is a completion specialist rather than an agentic coder, so teams wanting autonomous multi-file refactoring should pair it with an agent harness rather than expecting it to plan work itself.

Specs

Context window

Pricing

Free quota

API access

Weights

Closed — API only

Released

August 1, 2025

Benchmarks

Provider-reported unless a source says otherwise. Benchmarks are marketing-adjacent by nature — treat them as directional.

Use cases

code-completioncode-generationide-assistantsfill-in-the-middle

Trust score — 8/10

/10 trustVerified

Scored 8/10 (verified tier, metrics-v1). Evidence: Verified via vendor site/docs/GitHub and reputable coverage, wave 117; Trending score 82/100 from researcher assessment.

Sources