Skip to main content

    Mistral AI

    Codestral 25.08

    Mistral's July 30, 2025 model for low-latency code completion and fill-in-the-middle workflows. Current API documentation lists a 128K-token context and supports code generation, function calling and structured outputs. Enterprise deployment options include cloud, private cloud and on-premises infrastructure.

    128K tokens
    Text only
    Pro
    Provider
    Mistral AI
    Context
    128K
    Catalog · As of Sep 10, 2026Recent · 1d old
    yno subscription tier
    Pro
    Released
    Jul 30, 2025
    Speed
    Fast
    Reasoning
    Advanced
    Modality
    Text only

    Benchmarks

    Quality

    AA Intelligence Index
    22points
    Estimated · As of Aug 11, 2026Stale · 31d old
    GPQA Diamond
    73%
    Estimated · As of Aug 11, 2026Stale · 31d old

    Speed and latency

    Output speed
    168tokens/s
    Estimated · As of Aug 11, 2026Stale · 31d old

    API pricing

    Not available

    AA measurements unavailable

    Indexes use points; evaluations use accuracy percentages. API measurements do not measure yno application performance. Methodology

    Capabilities

    • Code
    • Multilingual Code
    • Fill-in-Middle
    • Refactoring

    Use cases

    • IDE completion
    • Repo-wide refactors
    • Code generation
    • FIM completion

    Strengths

    • 128K context
    • Fill-in-the-middle completion
    • Function calling
    • Structured outputs

    Best for

    Engineering teams that want a dedicated, fast coding model for completion-heavy workflows

    Use Codestral 25.08 in yno.ai

    No credit card required

    Related models

    Frequently asked

    What is Codestral 25.08?
    Mistral's July 30, 2025 model for low-latency code completion and fill-in-the-middle workflows. Current API documentation lists a 128K-token context and supports code generation, function calling and structured outputs. Enterprise deployment options include cloud, private cloud and on-premises infrastructure.
    How much does Codestral 25.08 cost in yno.ai?
    Codestral 25.08 is available on the Pro tier of yno.ai.
    What can Codestral 25.08 do?
    Codestral 25.08 is best for Engineering teams that want a dedicated, fast coding model for completion-heavy workflows. Its main capabilities include Code, Multilingual Code, Fill-in-Middle, Refactoring.
    How does Codestral 25.08 compare to other models?
    Codestral 25.08 excels at 128K context and is recommended for IDE completion, Repo-wide refactors, Code generation, FIM completion. See related models below.
    How do I use Codestral 25.08 in yno.ai?
    Sign up for yno.ai, select Codestral 25.08 from the model picker, and start chatting.