Magistral Small 2506 vs Mistral Medium 3
Magistral Small 2506 (2025) and Mistral Medium 3 (2025) are frontier reasoning models from MistralAI. Both ship a 128K-token context window. This comparison covers specs, pricing, API access, capabilities, benchmarks, input and output token costs, and production fit for coding and agent workloads. It focuses on practical selection signals rather than broad model-family marketing. The goal is to make the tradeoff clear before deeper testing.
Magistral Small 2506 is safer overall; choose Mistral Medium 3 when coding workflow support matters.
Decision scorecard
Local evidence first| Signal | Magistral Small 2506 | Mistral Medium 3 |
|---|---|---|
| Best for | reasoning-heavy apps | multimodal apps, tool-calling agents, and provider-routed production |
| Decision fit | Long context | Coding, RAG, and Agents |
| Context window | 128K | 128K |
| Cheapest output | - | $2/1M tokens |
| Provider routes | 1 tracked | 5 tracked |
| Shared benchmarks | 0 shared | 0 shared |
Decision tradeoffs
- Magistral Small 2506 uniquely exposes Reasoning in local model data.
- Local decision data tags Magistral Small 2506 for Long context.
- Mistral Medium 3 has broader tracked provider coverage for fallback and route flexibility.
- Mistral Medium 3 uniquely exposes Vision, Multimodal, and JSON / Tool use in local model data.
- Local decision data tags Mistral Medium 3 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.
Magistral Small 2506
Unavailable
No complete token price in local provider data
Mistral Medium 3
$820
Cheapest tracked route/tier: Mistral AI Studio
Cost delta unavailable until both models have sourced input and output token prices.
Switch friction
- Provider overlap exists on NVIDIA NIM; start route-level A/B tests there.
- Check replacement coverage for Reasoning before moving production traffic.
- Mistral Medium 3 adds Vision, Multimodal, and JSON / Tool use in local capability data.
- Provider overlap exists on NVIDIA NIM; start route-level A/B tests there.
- Check replacement coverage for Vision, Multimodal, and JSON / Tool use before moving production traffic.
- Magistral Small 2506 adds Reasoning in local capability data.
Specs
| Specification | ||
|---|---|---|
| Released | 2025-06-10 | 2025-05-01 |
| Context window | 128K | 128K |
| Parameters | 24B | — |
| Architecture | Decoder Only | Decoder Only |
| License | Apache 2.0OSI-approved | Proprietary |
| Openness | Open source | Proprietary |
| Weights | Unknown | Not released |
| Code | Unknown | Unknown |
| Commercial use | Permitted | Restricted |
| Knowledge cutoff | 2025-06 | 2025-03 |
Pricing and availability
| Pricing attribute | Magistral Small 2506 | Mistral Medium 3 |
|---|---|---|
| Input price | - | $0.40/1M tokens |
| Output price | - | $2/1M tokens |
| Providers |
Capabilities
| Capability | Magistral Small 2506 | Mistral Medium 3 |
|---|---|---|
| Vision | No | Yes |
| Multimodal | No | Yes |
| Reasoning | Yes | No |
| JSON / Tool use | No | Yes |
| Structured outputs | No | Yes |
| Code execution | No | Yes |
| IDE integration | No | No |
| Computer use | No | No |
| Parallel agents | No | No |
Benchmarks
No shared benchmark scores are currently available for this pair.
Deep dive
The capability footprint differs most on vision: Mistral Medium 3, multimodal input: Mistral Medium 3, reasoning mode: Magistral Small 2506, JSON / Tool use: Mistral Medium 3, JSON / Tool use: Mistral Medium 3, structured outputs: Mistral Medium 3, and code execution: Mistral Medium 3. Both models share the core language-model surface, 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.
Pricing coverage is uneven: Magistral Small 2506 has no token price sourced yet and Mistral Medium 3 has $0.40/1M input tokens. Provider availability is 1 tracked routes versus 5. Treat unknown pricing as an integration gap, then verify the route you will actually call before estimating production spend.
Choose Magistral Small 2506 when reasoning depth are central to the workload. Choose Mistral Medium 3 when coding workflow support and broader provider choice 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, Magistral Small 2506 or Mistral Medium 3?
Magistral Small 2506 supports 128K 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.
Is Magistral Small 2506 or Mistral Medium 3 open source?
Magistral Small 2506 is listed under Apache 2.0. Mistral Medium 3 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, Magistral Small 2506 or Mistral Medium 3?
Mistral Medium 3 has the clearer documented vision signal in this comparison. If vision is mission-critical, validate it against the provider endpoint because model-level support and API-level exposure can differ.
Which is better for multimodal input, Magistral Small 2506 or Mistral Medium 3?
Mistral Medium 3 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.
Which is better for reasoning mode, Magistral Small 2506 or Mistral Medium 3?
Magistral Small 2506 has the clearer documented reasoning mode signal in this comparison. If reasoning mode is mission-critical, validate it against the provider endpoint because model-level support and API-level exposure can differ.
Where can I run Magistral Small 2506 and Mistral Medium 3?
Magistral Small 2506 is available on NVIDIA NIM. Mistral Medium 3 is available on NVIDIA NIM, Mistral AI Studio, Microsoft Foundry, OpenRouter, and GCP Vertex AI. Provider coverage can affect latency, region availability, compliance posture, and fallback options.
Continue comparing
- Magistral Small 2506 vs Qwen2-7B-Instruct
- Mistral Magistral Small 2509 vs Mistral Medium 3.5
- Codex 1 vs Mistral Medium 3
- Magistral Small 2506 vs Mistral Medium 3.5
- Mistral Large 3 675B Instruct vs Mistral Medium 3
- Mistral Magistral Small 2509 vs Mistral Medium 3
- Claude Mythos Preview vs Mistral Medium 3
- Llama 2 7B vs Mistral Medium 3
- Codex Mini Latest vs Mistral Medium 3
- Mistral Medium 3 vs Qwen2-7B-Instruct
Popular comparisons for Magistral Small 2506
Popular comparisons for Mistral Medium 3
Last reviewed: 2026-10-18. Data sourced from public model cards and provider documentation.