MISTRAL MEDIUM 3.5

Mistral Medium 3.5: agentic & coding mid-tier

Released April 2026 (v26.04). Optimized for agentic and coding workloads. 128K context. Native vision. $0.40/$2.00 per million tokens.

Try Mistral Medium 3.5 on Council See it in a council

Mistral Medium 3.5 (released April 2026 as v26.04) is the mid-tier model in Mistral's 2026 lineup, deliberately tuned for agentic workflows and coding. It runs a 128K context window, accepts image input, and is priced at $0.40 per million input tokens and $2.00 per million output — about half the cost of Mistral Large 3 and roughly 1/12 of GPT-5.5 input. On benchmarks it lands close to Large 3 on coding while shedding the heaviest reasoning workloads. The case for: high-throughput agent loops where you want frontier-adjacent quality but cannot stomach GPT-5.5 economics, code-generation pipelines that don't need SWE-bench leadership, and multimodal classification at scale. The case against: extended reasoning chains (Large 3 or Opus 4.7 still win), and anything that needs more than 128K of context. Web search is disabled in Council AI for Mistral models.

Specs

ProviderMistral AI
Versionv26.04 (April 2026)
Context window128,000 tokens
MultimodalText + image input; text output
Optimized forAgentic workflows, coding
Web searchNot enabled in Council
Price (in / out per 1M)$0.40 / $2.00

Best at

Where it loses

Medium 3.5 vs Large 3

Pick Large 3 for the hardest reasoning, longest context (256K), and where the extra ~$0.40/M input is worth it. Pick Medium 3.5 for agent loops, code generation, and bulk multimodal — anywhere throughput and cost matter more than the last few benchmark points.

Frequently asked questions

What changed in v26.04?

April 2026 release; Mistral rebuilt the tuning specifically around agentic tool-use and code generation. The model card emphasizes function-calling reliability and lower hallucination on tool arguments.

How does Medium 3.5 compare to GPT-5.4 Mini?

Both are mid-tier 2026 models. Medium 3.5 is cheaper on input, has vision, and is tuned harder for agentic work. GPT-5.4 Mini has stronger tool-calling stability and native web search through the Responses API.

Is Mistral Medium 3.5 deprecated?

No — it is the active production Medium model in Council AI as of mid-2026. (Note: Mistral's prior Magistral Medium / Small via OpenRouter were deprecated separately.)

How much does Mistral Medium 3.5 cost?

$0.40 per million input tokens and $2.00 per million output. Council AI bundles it inside monthly plan budgets — no separate Mistral key required.

Can I use Medium 3.5 in a multi-model council?

Yes — pair it with GPT-5.5 for tool reliability and Claude Sonnet 4.6 for code quality. The cheap Medium 3.5 input price keeps total council cost low.