Mistral Large vs Mistral Medium 3.5
Mistral Large (2024) and Mistral Medium 3.5 (2026) are frontier reasoning models from MistralAI. Mistral Large ships a 32k-token context window, while Mistral Medium 3.5 ships a 262k-token context window. On MMLU PRO, Mistral Medium 3.5 leads by 28.3 pts. On pricing, Mistral Large costs $0.32/1M input tokens versus $1.50/1M 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 Large is ~369% cheaper at $0.32/1M; pay for Mistral Medium 3.5 only for reasoning depth.
Decision scorecard
Local evidence first| Signal | Mistral Large | Mistral Medium 3.5 |
|---|---|---|
| Best for | multimodal apps, tool-calling agents, and provider-routed production | reasoning-heavy apps, multimodal apps, and tool-calling agents |
| Decision fit | Agents, Vision, and Classification | Coding, RAG, and Agents |
| Context window | 32k | 262k |
| Cheapest output | $0.96/1M tokens | $7.50/1M tokens |
| Provider routes | 8 tracked | 3 tracked |
| Shared benchmarks | 1 shared | MMLU PRO leader |
Decision tradeoffs
- Mistral Large has the lower cheapest tracked output price at $0.96/1M tokens.
- Mistral Large has broader tracked provider coverage for fallback and procurement flexibility.
- Local decision data tags Mistral Large for Agents, Vision, and Classification.
- Mistral Medium 3.5 holds a shared-benchmark lead on MMLU PRO, ahead by 28.3 points.
- Mistral Medium 3.5 has the larger context window for long prompts, retrieval packs, or transcript analysis.
- Mistral Medium 3.5 uniquely exposes Multimodal and Reasoning in local model data.
- Local decision data tags Mistral Medium 3.5 for Coding, RAG, and Agents.
Monthly cost at traffic
Estimate token spend from the cheapest tracked input and output route or tier on this page.
Mistral Large
$496
Cheapest tracked route/tier: GCP Vertex AI
Mistral Medium 3.5
$3,075
Cheapest tracked route/tier: Mistral AI Studio
Estimated monthly gap: $2,579. Batch, cache, alternate speed tiers, and negotiated pricing are excluded from this local estimate.
Switch friction
- Provider overlap exists on Mistral AI Studio and OpenRouter; start route-level A/B tests there.
- Mistral Medium 3.5 is $6.54/1M tokens higher on cheapest tracked output pricing, so quality gains need to justify the spend.
- Mistral Medium 3.5 adds Multimodal and Reasoning in local capability data.
- Provider overlap exists on Mistral AI Studio and OpenRouter; start route-level A/B tests there.
- Mistral Large is $6.54/1M tokens lower on cheapest tracked output pricing before cache, batch, or negotiated discounts.
- Check replacement coverage for Multimodal and Reasoning before moving production traffic.
Specs
| Specification | ||
|---|---|---|
| Released | 2024-02-08 | 2026-04-29 |
| Context window | 32k | 262k |
| Parameters | 123B | 128B |
| Architecture | - | Decoder Only |
| License | Mistral License | Mistral License |
| Openness | Open weights | Open weights |
| Commercial use | Commercial use: non-commercial | Commercial use: non-commercial |
| Knowledge cutoff | 2024-03 | - |
Pricing and availability
| Pricing attribute | Mistral Large | Mistral Medium 3.5 |
|---|---|---|
| Input price | $0.32/1M tokens | $1.50/1M tokens |
| Output price | $0.96/1M tokens | $7.50/1M tokens |
| Providers |
Capabilities
| Capability | Mistral Large | Mistral Medium 3.5 |
|---|---|---|
| Vision | Yes | Yes |
| Multimodal | No | Yes |
| Reasoning | No | Yes |
| Function calling | Yes | Yes |
| Tool use | Yes | Yes |
| Structured outputs | Yes | Yes |
| Code execution | No | No |
| IDE integration | No | No |
| Computer use | No | No |
| Parallel agents | No | No |
Benchmarks
| Benchmark | Mistral Large | Mistral Medium 3.5 |
|---|---|---|
| MMLU PRO | 51.5 | 79.8 |
Deep dive
On shared benchmark coverage, MMLU PRO has Mistral Large at 51.5 and Mistral Medium 3.5 at 79.8, with Mistral Medium 3.5 ahead by 28.3 points. The largest visible gap is 28.3 points on MMLU PRO, 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 multimodal input: Mistral Medium 3.5 and reasoning mode: Mistral Medium 3.5. Both models share vision, function calling, tool use, and structured outputs, 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 lists $0.32/1M input and $0.96/1M output tokens on the cheapest tracked provider, while Mistral Medium 3.5 lists $1.50/1M input and $7.50/1M output tokens on the cheapest tracked provider. A 70/30 input-output blend puts Mistral Large lower by about $2.79 per million blended tokens. Availability is 8 providers versus 3, so concentration risk also matters.
Choose Mistral Large when vision-heavy evaluation, lower input-token cost, and broader provider choice are central to the workload. Choose Mistral Medium 3.5 when reasoning depth and larger context windows 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 Large or Mistral Medium 3.5?
Mistral Medium 3.5 supports 262k tokens, while Mistral Large supports 32k 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 or Mistral Medium 3.5?
Mistral Large is cheaper on tracked token pricing. Mistral Large costs $0.32/1M input and $0.96/1M output tokens. Mistral Medium 3.5 costs $1.50/1M input and $7.50/1M output tokens. Provider discounts or batch pricing can still change the final bill.
Is Mistral Large or Mistral Medium 3.5 open source?
Mistral Large is listed under Mistral License. Mistral Medium 3.5 is listed under Mistral License. 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 or Mistral Medium 3.5?
Both Mistral Large and Mistral Medium 3.5 expose vision. The better choice depends on benchmark fit, context budget, pricing, and whether your provider route exposes the same capability surface. Use this as a quick comparison signal, then confirm the provider-specific limits before committing to production.
Which is better for multimodal input, Mistral Large or Mistral Medium 3.5?
Mistral Medium 3.5 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 and Mistral Medium 3.5?
Mistral Large is available on NVIDIA NIM, Microsoft Foundry, AWS Bedrock, Mistral AI Studio, and IBM watsonx. Mistral Medium 3.5 is available on Mistral AI Studio, OpenRouter, and Vercel AI Gateway. Provider coverage can affect latency, region availability, compliance posture, and fallback options.
Continue comparing
Last reviewed: 2026-06-17. Data sourced from public model cards and provider documentation.