LLM Reference

Mistral Medium 3.5 vs Mistral Small 4

Mistral Medium 3.5 (2026) and Mistral Small 4 (2026) are frontier reasoning models from MistralAI. Mistral Medium 3.5 ships a 256K-token context window, while Mistral Small 4 ships a 256K-token context window. On Google-Proof Q&A, Mistral Small 4 leads by 5.6 pts. On pricing, Mistral Small 4 costs $0.15/1M input tokens versus $1.50/1M for the alternative. This comparison covers specs, pricing, capabilities, benchmarks, provider availability, and production fit.

Mistral Small 4 is ~900% cheaper at $0.15/1M; pay for Mistral Medium 3.5 only for reasoning depth.

Decision scorecard

Local evidence first
SignalMistral Medium 3.5Mistral Small 4
Best forreasoning-heavy apps, multimodal apps, and tool-calling agentsmultimodal apps, tool-calling agents, and provider-routed production
Decision fitCoding, RAG, and AgentsRAG, Agents, and Long context
Context window256K256K
Cheapest output$7.50/1M tokens$0.60/1M tokens
Provider routes3 tracked3 tracked
Shared benchmarks1 rowsGoogle-Proof Q&A leader

Decision tradeoffs

Choose Mistral Medium 3.5 when...
  • Mistral Medium 3.5 uniquely exposes Reasoning and Structured outputs in local model data.
  • Local decision data tags Mistral Medium 3.5 for Coding, RAG, and Agents.
Choose Mistral Small 4 when...
  • Mistral Small 4 leads the largest shared benchmark signal on Google-Proof Q&A by 5.6 points.
  • Mistral Small 4 has the lower cheapest tracked output price at $0.60/1M tokens.
  • Local decision data tags Mistral Small 4 for RAG, Agents, and Long context.

Monthly cost at traffic

Estimate token spend from the cheapest tracked input and output route or tier on this page.

Lower estimate Mistral Small 4

Mistral Medium 3.5

$3,075

Cheapest tracked route/tier: Mistral AI Studio

Mistral Small 4

$270

Cheapest tracked route/tier: OpenRouter

Estimated monthly gap: $2,805. Batch, cache, alternate speed tiers, and negotiated pricing are excluded from this local estimate.

Switch friction

Mistral Medium 3.5 -> Mistral Small 4
  • Provider overlap exists on OpenRouter and Mistral AI Studio; start route-level A/B tests there.
  • Mistral Small 4 is $6.90/1M tokens lower on cheapest tracked output pricing before cache, batch, or negotiated discounts.
  • Check replacement coverage for Reasoning and Structured outputs before moving production traffic.
Mistral Small 4 -> Mistral Medium 3.5
  • Provider overlap exists on Mistral AI Studio and OpenRouter; start route-level A/B tests there.
  • Mistral Medium 3.5 is $6.90/1M tokens higher on cheapest tracked output pricing, so quality gains need to justify the spend.
  • Mistral Medium 3.5 adds Reasoning and Structured outputs in local capability data.

Specs

Specification
Released2026-04-292026-03-16
Context window256K256K
Parameters128B119B (6.5B active)
Architecturedecoder onlymoe
LicenseMistral LicenseApache 2.0
Knowledge cutoff-2025-06

Pricing and availability

Pricing attributeMistral Medium 3.5Mistral Small 4
Input price$1.50/1M tokens$0.15/1M tokens
Output price$7.50/1M tokens$0.60/1M tokens
Providers

Capabilities

CapabilityMistral Medium 3.5Mistral Small 4
VisionYesYes
MultimodalYesYes
ReasoningYesNo
Function callingYesYes
Tool useYesYes
Structured outputsYesNo
Code executionNoNo
IDE integrationNoNo
Computer useNoNo
Parallel agentsNoNo

Benchmarks

BenchmarkMistral Medium 3.5Mistral Small 4
Google-Proof Q&A71.376.9

Deep dive

On shared benchmark coverage, Google-Proof Q&A has Mistral Medium 3.5 at 71.3 and Mistral Small 4 at 76.9, with Mistral Small 4 ahead by 5.6 points. The largest visible gap is 5.6 points on Google-Proof Q&A, which matters most when that benchmark mirrors your workload. Treat isolated benchmark wins as directional, because provider routing, prompt style, and tool access can move real application results.

The capability footprint differs most on reasoning mode: Mistral Medium 3.5 and structured outputs: Mistral Medium 3.5. Both models share vision, multimodal input, function calling, and tool use, so the practical split is not just feature count. Use those differences to decide whether the page is about raw model quality, agentic coding support, multimodal ingestion, or predictable structured API behavior.

For cost, Mistral Medium 3.5 lists $1.50/1M input and $7.50/1M output tokens on the cheapest tracked provider, while Mistral Small 4 lists $0.15/1M input and $0.60/1M output tokens on the cheapest tracked provider. A 70/30 input-output blend puts Mistral Small 4 lower by about $3.01 per million blended tokens. Availability is 3 providers versus 3, so concentration risk also matters.

Choose Mistral Medium 3.5 when reasoning depth are central to the workload. Choose Mistral Small 4 when vision-heavy evaluation and lower input-token cost are more important. For production, rerun your own prompts through the exact provider, region, and tool stack you plan to ship.

FAQ

Which has a larger context window, Mistral Medium 3.5 or Mistral Small 4?

Mistral Medium 3.5 supports 256K tokens, while Mistral Small 4 supports 256K tokens. That gap matters most for long documents, large codebases, retrieval-heavy agents, and conversations where earlier context must remain visible.

Which is cheaper, Mistral Medium 3.5 or Mistral Small 4?

Mistral Small 4 is cheaper on tracked token pricing. Mistral Medium 3.5 costs $1.50/1M input and $7.50/1M output tokens. Mistral Small 4 costs $0.15/1M input and $0.60/1M output tokens. Provider discounts or batch pricing can still change the final bill.

Is Mistral Medium 3.5 or Mistral Small 4 open source?

Mistral Medium 3.5 is listed under Mistral License. Mistral Small 4 is listed under Apache 2.0. License labels affect whether you can self-host, redistribute weights, or rely only on hosted APIs, so confirm the upstream license before deployment.

Which is better for vision, Mistral Medium 3.5 or Mistral Small 4?

Both Mistral Medium 3.5 and Mistral Small 4 expose vision. The better choice depends on benchmark fit, context budget, pricing, and whether your provider route exposes the same capability surface.

Which is better for multimodal input, Mistral Medium 3.5 or Mistral Small 4?

Both Mistral Medium 3.5 and Mistral Small 4 expose multimodal input. The better choice depends on benchmark fit, context budget, pricing, and whether your provider route exposes the same capability surface.

Where can I run Mistral Medium 3.5 and Mistral Small 4?

Mistral Medium 3.5 is available on Mistral AI Studio, OpenRouter, and Vercel AI Gateway. Mistral Small 4 is available on OpenRouter, NVIDIA NIM, and Mistral AI Studio. Provider coverage can affect latency, region availability, compliance posture, and fallback options.

Continue comparing

Last reviewed: 2026-05-22. Data sourced from public model cards and provider documentation.