Magistral Small 2506: API Pricing, Context Window & Benchmarks
Magistral Small 2506 is a language model from Mistral, released in June 2025.
Building upon Mistral Small 3.1 (2503), with added reasoning capabilities, undergoing SFT from Magistral Medium traces and RL on top, it's a small, efficient reasoning model with 24B parameters. Magistral Small can be deployed locally,
Magistral Small 2506 benchmarks
Capability tiers
Standing within each category, adjusted for leaderboard depth.
Real tasks performance
How Magistral Small 2506 performs across real-world prompt categories.
Performance by conversation depth
How Magistral Small 2506 holds up as conversations get longer.
Quality Tracker
Magistral Small 2506 Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Mon Aug 24 2026Magistral Small 2506 model size
Magistral Small 2506 has 24 billion parameters. See how it compares to other models in the same parameter range.
Magistral Small 2506 API
Available from the model provider
Magistral Small 2506 has an official provider API. It is not currently routed through the LLM Stats gateway.
Read the official API documentationMagistral Small 2506 latency
Magistral Small 2506 time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.
Magistral Small 2506 examples
Recent arena outputs from Magistral Small 2506, picked from the highest-ranked matchups.
Magistral Small 2506 license
Magistral Small 2506 is released under the Apache 2.0 license, which permits commercial use, has 24.0B parameters, has a knowledge cutoff of June 2025.
- License
- Apache 2.0
- Commercial use allowed
- Parameters
- 24.0B
- Knowledge cutoff
- June 2025
Apache License 2.0 - allows commercial use
Magistral Small 2506 resources
Official sources for Magistral Small 2506: api documentation, official playground, paper or system card, official launch post, model weights.
Magistral Small 2506 vs other models
The most-compared alternatives to Magistral Small 2506 are Kimi K2 0905, Phi 4 Reasoning Plus, DeepSeek R1 Zero. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like Magistral Small 2506
Models ranked just above and below Magistral Small 2506 by LLM Stats score.
FAQ
Common questions about Magistral Small 2506.