Magistral Small 2506
magistral-small-2506
Last refreshed 2026-05-14. Next refresh: weekly.
Long context
Magistral Small 2506 is worth evaluating for long context when its provider route and context window match the workload.
Decision context: Long context task fit, 1 tracked provider route, and research from 2026-05-14.
Use it for
- Teams evaluating long context
- Workloads that can use a 128K context window
- Buyers comparing 1 tracked provider route
Do not use it for
- Vision or document-understanding workloads
- Strict JSON or tool-calling flows
Cheapest output
-
NVIDIA NIM per 1M tokens
Provider routes
1
Tracked API hosts
Quality / dollar
Unknown
No task benchmark coverage yet
Freshness
2026-05-14
Researched 4d ago
fresh
Top use-case fit
Long context
Included by capability and metadata signals in the decision map.
Provider price ladder
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| NVIDIA NIM | - | - | ServerlessPartial |
Benchmark peer barsfor Long context
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.
About
Mistral Magistral Small reasoning model released January 2026.
Magistral Small 2506 has a 128K-token context window.
Capabilities
Reasoning
Rankings
Compare
All comparisons →Magistral Small 2506 vs Mistral Medium 3.5Magistral Small 2506 vs Mistral Medium 3 InstructMagistral Small 2506 vs Llama 3.3 Nemotron Super 49B v1Magistral Small 2506 vs Tencent Hy3 PreviewMagistral Small 2506 vs Mistral Small 3Magistral Small 2506 vs Mistral Magistral Small 2509Magistral Small 2506 vs Gemini Deep Research PreviewMagistral Small 2506 vs Grok 4.3Magistral Small 2506 vs Nemotron Mini 4B InstructMagistral Small 2506 vs Xiaomi MiMo-V2.5-ProMagistral Small 2506 vs GPT-5Magistral Small 2506 vs Dracarys Llama 3.1 70B InstructMagistral Small 2506 vs Mistral Large 3 675B InstructMagistral Small 2506 vs Llama 3.2 NV RerankQA 1B v2Magistral Small 2506 vs Claude Opus 4.7Magistral Small 2506 vs Claude Instant
