Mistral Medium 3 vs Qwen3.5-397B-A17B
Mistral Medium 3 (2025) and Qwen3.5-397B-A17B (2026) are frontier reasoning models from MistralAI and Alibaba. Mistral Medium 3 ships a 128K-token context window, while Qwen3.5-397B-A17B ships a 256K-token context window. On LMArena Vision Arena, Qwen3.5-397B-A17B leads by 91 pts. On pricing, Mistral Medium 3 costs $0.40/1M input tokens versus $0.45/1M 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.
Pick Qwen3.5-397B-A17B for general evaluation; Mistral Medium 3 is better when coding workflow support matters more.
Decision scorecard
Local evidence first| Signal | Mistral Medium 3 | Qwen3.5-397B-A17B |
|---|---|---|
| Best for | multimodal apps, tool-calling agents, and provider-routed production | reasoning-heavy apps, multimodal apps, and tool-calling agents |
| Decision fit | Coding, RAG, and Agents | Coding, RAG, and Agents |
| Context window | 128K | 256K |
| Cheapest output | $2/1M tokens | $3/1M tokens |
| Provider routes | 5 tracked | 5 tracked |
| Shared benchmarks | 2 shared | LMArena Vision Arena leader |
Decision tradeoffs
- Mistral Medium 3 has the lower cheapest tracked output price at $2/1M tokens.
- Mistral Medium 3 uniquely exposes Code execution in local model data.
- Local decision data tags Mistral Medium 3 for Coding, RAG, and Agents.
- Qwen3.5-397B-A17B holds a shared-benchmark lead on LMArena Vision Arena, ahead by 91 points.
- Qwen3.5-397B-A17B has the larger context window for long prompts, retrieval packs, or transcript analysis.
- Qwen3.5-397B-A17B uniquely exposes Reasoning in local model data.
- Local decision data tags Qwen3.5-397B-A17B 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 Medium 3
$820
Cheapest tracked route/tier: Mistral AI Studio
Qwen3.5-397B-A17B
$1,110
Cheapest tracked route/tier: DeepInfra
Estimated monthly gap: $290. Batch, cache, alternate speed tiers, and negotiated pricing are excluded from this local estimate.
Switch friction
- Provider overlap exists on OpenRouter; start route-level A/B tests there.
- Qwen3.5-397B-A17B is $1/1M tokens higher on cheapest tracked output pricing, so quality gains need to justify the spend.
- Check replacement coverage for Code execution before moving production traffic.
- Qwen3.5-397B-A17B adds Reasoning in local capability data.
- Provider overlap exists on OpenRouter; start route-level A/B tests there.
- Mistral Medium 3 is $1/1M tokens lower on cheapest tracked output pricing before cache, batch, or negotiated discounts.
- Check replacement coverage for Reasoning before moving production traffic.
- Mistral Medium 3 adds Code execution in local capability data.
Specs
| Specification | ||
|---|---|---|
| Released | 2025-05-01 | 2026-02-16 |
| Context window | 128K | 256K |
| Parameters | — | 397B (17B active) |
| Architecture | Decoder Only | Mixture of Experts |
| License | Proprietary | Apache 2.0OSI-approved |
| Openness | Proprietary | Open source |
| Weights | Not released | Available |
| Code | Unknown | Unknown |
| Commercial use | Restricted | Permitted |
| Knowledge cutoff | 2025-03 | - |
Pricing and availability
| Pricing attribute | Mistral Medium 3 | Qwen3.5-397B-A17B |
|---|---|---|
| Input price | $0.40/1M tokens | $0.45/1M tokens |
| Output price | $2/1M tokens | $3/1M tokens |
| Providers |
Capabilities
| Capability | Mistral Medium 3 | Qwen3.5-397B-A17B |
|---|---|---|
| Vision | Yes | Yes |
| Multimodal | Yes | Yes |
| Reasoning | No | Yes |
| JSON / Tool use | Yes | Yes |
| Structured outputs | Yes | Yes |
| Code execution | Yes | No |
| IDE integration | No | No |
| Computer use | No | No |
| Parallel agents | No | No |
Benchmarks
| Benchmark | Mistral Medium 3 | Qwen3.5-397B-A17B |
|---|---|---|
| LMArena Vision Arena | 1155.0 | 1246.0 |
| LMArena Text Arena - Creative Writing | 1343.0 | 1402.0 |
Deep dive
On shared benchmark coverage, LMArena Vision Arena has Mistral Medium 3 at 1155 and Qwen3.5-397B-A17B at 1246, with Qwen3.5-397B-A17B ahead by 91 points; LMArena Text Arena - Creative Writing has Mistral Medium 3 at 1343 and Qwen3.5-397B-A17B at 1402, with Qwen3.5-397B-A17B ahead by 59 points. The largest visible gap is 91 points on LMArena Vision Arena, 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: Qwen3.5-397B-A17B and code execution: Mistral Medium 3. Both models share vision, multimodal input, JSON / Tool use, and JSON / 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 lists $0.40/1M input and $2/1M output tokens on the cheapest listed provider, while Qwen3.5-397B-A17B lists $0.45/1M input and $3/1M output tokens on the cheapest listed provider. A 70/30 input-output blend puts Mistral Medium 3 lower by about $0.33 per million blended tokens. Availability is 5 providers versus 5, so concentration risk also matters.
Choose Mistral Medium 3 when coding workflow support and lower input-token cost are central to the workload. Choose Qwen3.5-397B-A17B 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 Medium 3 or Qwen3.5-397B-A17B?
Qwen3.5-397B-A17B supports 256K tokens, while Mistral Medium 3 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 Medium 3 or Qwen3.5-397B-A17B?
Mistral Medium 3 is cheaper on listed token pricing. Mistral Medium 3 costs $0.40/1M input and $2/1M output tokens. Qwen3.5-397B-A17B costs $0.45/1M input and $3/1M output tokens. Provider discounts or batch pricing can still change the final bill.
Is Mistral Medium 3 or Qwen3.5-397B-A17B open source?
Mistral Medium 3 is listed under Proprietary. Qwen3.5-397B-A17B 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 or Qwen3.5-397B-A17B?
Both Mistral Medium 3 and Qwen3.5-397B-A17B 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 Medium 3 or Qwen3.5-397B-A17B?
Both Mistral Medium 3 and Qwen3.5-397B-A17B expose multimodal input. 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.
Where can I run Mistral Medium 3 and Qwen3.5-397B-A17B?
Mistral Medium 3 is available on NVIDIA NIM, Mistral AI Studio, Microsoft Foundry, OpenRouter, and GCP Vertex AI. Qwen3.5-397B-A17B is available on OpenRouter, Together AI, Alibaba Cloud PAI-EAS, Novita AI, and DeepInfra. Provider coverage can affect latency, region availability, compliance posture, and fallback options.
Continue comparing
Popular comparisons for Mistral Medium 3
Popular comparisons for Qwen3.5-397B-A17B
Last reviewed: 2026-10-27. Data sourced from public model cards and provider documentation.