Skip to main content

    Mistral AI

    Mistral Medium 3.5

    Mistral's April 28, 2026 model (v26.04), combining instruction-following, reasoning, and coding in 128B dense parameters. It supports vision, function calling, configurable reasoning, and a 256K-token context. Published weights use a Modified MIT license. Mistral lists standard provider API pricing of $1.50/$7.50 per MTok for input/output. Its May 22 product announcement made the model the default in Vibe CLI and Le Chat.

    256K tokens
    Multimodal
    Pro
    Provider
    Mistral AI
    Context
    256K
    Catalog · As of Aug 11, 2026Stale · 31d old
    yno subscription tier
    Pro
    Released
    Apr 28, 2026
    Speed
    Medium
    Reasoning
    Advanced
    Modality
    Multimodal

    Benchmarks

    Quality

    AA Intelligence Index
    14.9points
    Artificial Analysis · Date unknownAge unknown
    AA Coding Index
    46.9points
    Artificial Analysis · Date unknownAge unknown
    GPQA Diamond
    74.8%
    Artificial Analysis · Date unknownAge unknown

    Speed and latency

    Output speed
    134.09tokens/s
    Configuration: Prompt length: 1,000 · Parallel queries: 1
    Artificial Analysis · Date unknownAge unknown
    Time to first token
    0.74s
    Configuration: Prompt length: 1,000 · Parallel queries: 1
    Artificial Analysis · Date unknownAge unknown
    Time to first answer token
    15.66s
    Configuration: Prompt length: 1,000 · Parallel queries: 1
    Artificial Analysis · Date unknownAge unknown

    API pricing

    API input cost
    $1.50/ 1M tokens
    Artificial Analysis · Date unknownAge unknown
    API output cost
    $7.50/ 1M tokens
    Artificial Analysis · Date unknownAge unknown

    Benchmark variant: Mistral Medium 3.5

    AA data retrieved Sep 11, 2026 · Artificial Analysis

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

    Capabilities

    • Code
    • Agentic
    • Reasoning
    • Vision
    • Open Weights
    • Function Calling

    Use cases

    • Agentic coding
    • European sovereignty
    • Self-hosted deployments
    • Document and image QnA

    Strengths

    • 128B dense model
    • Vision and 256K context
    • Configurable reasoning effort
    • Modified MIT open weights

    Best for

    Teams building coding and image-analysis agents with hosted or self-hosted deployment

    Use Mistral Medium 3.5 in yno.ai

    No credit card required

    Related models

    Frequently asked

    What is Mistral Medium 3.5?
    Mistral's April 28, 2026 model (v26.04), combining instruction-following, reasoning, and coding in 128B dense parameters. It supports vision, function calling, configurable reasoning, and a 256K-token context. Published weights use a Modified MIT license. Mistral lists standard provider API pricing of $1.50/$7.50 per MTok for input/output. Its May 22 product announcement made the model the default in Vibe CLI and Le Chat.
    How much does Mistral Medium 3.5 cost in yno.ai?
    Mistral Medium 3.5 is available on the Pro tier of yno.ai.
    What can Mistral Medium 3.5 do?
    Mistral Medium 3.5 is best for Teams building coding and image-analysis agents with hosted or self-hosted deployment. Its main capabilities include Code, Agentic, Reasoning, Vision, Open Weights, Function Calling.
    How does Mistral Medium 3.5 compare to other models?
    Mistral Medium 3.5 excels at 128B dense model and is recommended for Agentic coding, European sovereignty, Self-hosted deployments, Document and image QnA. See related models below.
    How do I use Mistral Medium 3.5 in yno.ai?
    Sign up for yno.ai, select Mistral Medium 3.5 from the model picker, and start chatting.