LLM Reference

Mistral Large 2 (2407) vs Mistral Medium 3 Instruct

Mistral Large 2 (2407) (2024) and Mistral Medium 3 Instruct (2025) are compact production models from MistralAI. Mistral Large 2 (2407) ships a 128k-token context window, while Mistral Medium 3 Instruct ships a 128k-token context window. On pricing, Mistral Medium 3 Instruct costs $0.40/1M input tokens versus $0.50/1M for the alternative. This comparison covers specs, pricing, API access, capabilities, benchmarks, input and output token costs, and production fit for coding and agent workloads.

Mistral Medium 3 Instruct is safer overall; choose Mistral Large 2 (2407) when vision-heavy evaluation matters.

Decision scorecard

Local evidence first
SignalMistral Large 2 (2407)Mistral Medium 3 Instruct
Best formultimodal apps and provider-routed productionmultimodal apps and provider-routed production
Decision fitRAG, Long context, and VisionLong context and Vision
Context window128k128k
Cheapest output$1.50/1M tokens$2/1M tokens
Provider routes3 tracked2 tracked
Shared benchmarks0 rows0 rows

Decision tradeoffs

Choose Mistral Large 2 (2407) when...
  • Mistral Large 2 (2407) has the lower cheapest tracked output price at $1.50/1M tokens.
  • Mistral Large 2 (2407) has broader tracked provider coverage for fallback and procurement flexibility.
  • Mistral Large 2 (2407) uniquely exposes Structured outputs in local model data.
  • Local decision data tags Mistral Large 2 (2407) for RAG, Long context, and Vision.
Choose Mistral Medium 3 Instruct when...
  • Mistral Medium 3 Instruct uniquely exposes Multimodal in local model data.
  • Local decision data tags Mistral Medium 3 Instruct for Long context and Vision.

Monthly cost at traffic

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

Lower estimate Mistral Large 2 (2407)

Mistral Large 2 (2407)

$775

Cheapest tracked route/tier: Chutes AI

Mistral Medium 3 Instruct

$820

Cheapest tracked route/tier: Mistral AI Studio

Estimated monthly gap: $45.00. Batch, cache, alternate speed tiers, and negotiated pricing are excluded from this local estimate.

Switch friction

Mistral Large 2 (2407) -> Mistral Medium 3 Instruct
  • No overlapping tracked provider route is sourced for Mistral Large 2 (2407) and Mistral Medium 3 Instruct; plan for SDK, billing, or endpoint changes.
  • Mistral Medium 3 Instruct is $0.50/1M tokens higher on cheapest tracked output pricing, so quality gains need to justify the spend.
  • Check replacement coverage for Structured outputs before moving production traffic.
  • Mistral Medium 3 Instruct adds Multimodal in local capability data.
Mistral Medium 3 Instruct -> Mistral Large 2 (2407)
  • No overlapping tracked provider route is sourced for Mistral Medium 3 Instruct and Mistral Large 2 (2407); plan for SDK, billing, or endpoint changes.
  • Mistral Large 2 (2407) is $0.50/1M tokens lower on cheapest tracked output pricing before cache, batch, or negotiated discounts.
  • Check replacement coverage for Multimodal before moving production traffic.
  • Mistral Large 2 (2407) adds Structured outputs in local capability data.

Specs

Specification
Released2024-07-232025-10-01
Context window128k128k
Parameters123B
Architecturedecoder onlydecoder only
LicenseMistral LicenseProprietary
OpennessOpen weightsProprietary
Commercial useNon-commercial onlyCommercial use with conditions
Knowledge cutoff2024-032025-03

Pricing and availability

Pricing attributeMistral Large 2 (2407)Mistral Medium 3 Instruct
Input price$0.50/1M tokens$0.40/1M tokens
Output price$1.50/1M tokens$2/1M tokens
Providers

Capabilities

CapabilityMistral Large 2 (2407)Mistral Medium 3 Instruct
VisionYesYes
MultimodalNoYes
ReasoningNoNo
Function callingNoNo
Tool useNoNo
Structured outputsYesNo
Code executionNoNo
IDE integrationNoNo
Computer useNoNo
Parallel agentsNoNo

Benchmarks

No shared benchmark rows are currently sourced for this pair.

Deep dive

The capability footprint differs most on multimodal input: Mistral Medium 3 Instruct and structured outputs: Mistral Large 2 (2407). Both models share vision, 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 Large 2 (2407) lists $0.50/1M input and $1.50/1M output tokens on the cheapest tracked provider, while Mistral Medium 3 Instruct lists $0.40/1M input and $2/1M output tokens on the cheapest tracked provider. A 70/30 input-output blend puts Mistral Large 2 (2407) lower by about $0.08 per million blended tokens. Availability is 3 providers versus 2, so concentration risk also matters.

Choose Mistral Large 2 (2407) when vision-heavy evaluation and broader provider choice are central to the workload. Choose Mistral Medium 3 Instruct 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. This keeps the decision grounded in measurable tradeoffs instead of brand-level assumptions.

FAQ

Which has a larger context window, Mistral Large 2 (2407) or Mistral Medium 3 Instruct?

Mistral Large 2 (2407) supports 128k tokens, while Mistral Medium 3 Instruct supports 128k 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 Large 2 (2407) or Mistral Medium 3 Instruct?

Mistral Large 2 (2407) is cheaper on tracked token pricing. Mistral Large 2 (2407) costs $0.50/1M input and $1.50/1M output tokens. Mistral Medium 3 Instruct costs $0.40/1M input and $2/1M output tokens. Provider discounts or batch pricing can still change the final bill.

Is Mistral Large 2 (2407) or Mistral Medium 3 Instruct open source?

Mistral Large 2 (2407) is listed under Mistral License. Mistral Medium 3 Instruct is listed under Proprietary. 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 Large 2 (2407) or Mistral Medium 3 Instruct?

Both Mistral Large 2 (2407) and Mistral Medium 3 Instruct 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 Large 2 (2407) or Mistral Medium 3 Instruct?

Mistral Medium 3 Instruct has the clearer documented multimodal input signal in this comparison. If multimodal input is mission-critical, validate it against the provider endpoint because model-level support and API-level exposure can differ.

Where can I run Mistral Large 2 (2407) and Mistral Medium 3 Instruct?

Mistral Large 2 (2407) is available on Microsoft Foundry, Chutes AI, and SiliconFlow. Mistral Medium 3 Instruct is available on NVIDIA NIM and Mistral AI Studio. Provider coverage can affect latency, region availability, compliance posture, and fallback options.

Continue comparing

Last reviewed: 2026-06-04. Data sourced from public model cards and provider documentation.