modelgrep

Longest-Context Mistral Models

Match · Updated July 2026

Mistral Medium 3.5 has the largest context window of any Mistral model, at 262K tokens. Mistral Small 4 (262K) and Devstral 2 2512 (262K) round out the top three.

262KContext
29.9Intelligence
$1.50Input /M

AI models with the largest context windows, ranked by token capacity. The best large language models for long documents, codebases and extended conversations.

  1. 1mistralai logo
    mistral-medium-3-5
    ReasoningToolsJSON+129.9 intel · $1.50/M
    262K
    Context
  2. 2mistralai logo
    mistral-small-2603
    ReasoningToolsJSON+1$0.150/M
    262K
    Context
  3. 3mistralai logo
    devstral-2512
    ToolsJSON$0.400/M
    262K
    Context
  4. 4mistralai logo
    ministral-14b-2512
    ToolsJSONVision$0.200/M
    262K
    Context
  5. 5mistralai logo
    ministral-8b-2512
    ToolsJSONVision$0.150/M
    262K
    Context
  6. 6mistralai logo
    mistral-large-2512
    ToolsJSONVision$0.500/M
    262K
    Context
  7. 7mistralai logo
    codestral-2508
    ToolsJSON$0.300/M
    256K
    Context
  8. 8mistralai logo
    mistral-small-3.2-24b-instruct
    ToolsJSONVision$0.100/M
    256K
    Context

Frequently asked

Which Mistral model has the largest context window?

Mistral Medium 3.5 has the largest context window of any Mistral model, at 262K tokens. Mistral Small 4 (262K) and Devstral 2 2512 (262K) round out the top three.

What's a good alternative to Mistral Medium 3.5?

Mistral Small 4 (262K) is the closest alternative on this metric, followed by Devstral 2 2512 (262K). See the full ranking above for the tradeoffs.

How many Mistral models are there?

modelgrep tracks 19 Mistral models with live benchmarks, speed, latency and per-provider pricing, led on intelligence by Mistral Medium 3.5. 8 of them qualify for this ranking.

More Mistral rankings

All rankings