LLM Reference

Magistral Small 2506 vs Mistral Medium 3 Instruct

Magistral Small 2506 (2025) and Mistral Medium 3 Instruct (2025) are frontier reasoning models from MistralAI. Magistral Small 2506 ships a 128k-token context window, while Mistral Medium 3 Instruct ships 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.

Mistral Medium 3 Instruct is safer overall; choose Magistral Small 2506 when reasoning depth matters.

Decision scorecard

Local evidence first
SignalMagistral Small 2506Mistral Medium 3 Instruct
Best forreasoning-heavy appsmultimodal apps and provider-routed production
Decision fitLong contextLong context and Vision
Context window128k128k
Cheapest output-$2/1M tokens
Provider routes1 tracked2 tracked
Shared benchmarks0 shared0 shared

Decision tradeoffs

Choose Magistral Small 2506 when...
  • Magistral Small 2506 uniquely exposes Reasoning in local model data.
  • Local decision data tags Magistral Small 2506 for Long context.
Choose Mistral Medium 3 Instruct when...
  • Mistral Medium 3 Instruct has broader tracked provider coverage for fallback and route flexibility.
  • Mistral Medium 3 Instruct uniquely exposes Vision and Multimodal in local model data.
  • Local decision data tags Mistral Medium 3 Instruct for Long context and Vision.

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 Instruct

$820

Cheapest tracked route/tier: Mistral AI Studio

Cost delta unavailable until both models have sourced input and output token prices.

Switch friction

Magistral Small 2506 -> Mistral Medium 3 Instruct
  • 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 Instruct adds Vision and Multimodal in local capability data.
Mistral Medium 3 Instruct -> Magistral Small 2506
  • Provider overlap exists on NVIDIA NIM; start route-level A/B tests there.
  • Check replacement coverage for Vision and Multimodal before moving production traffic.
  • Magistral Small 2506 adds Reasoning in local capability data.

Specs

Specification
Released2025-06-102025-10-01
Context window128k128k
Parameters24B—
ArchitectureDecoder OnlyDecoder Only
LicenseApache 2.0OSI-approvedProprietary
OpennessOpen sourceProprietary
WeightsUnknownNot released
CodeUnknownUnknown
Commercial useCommercial use: permittedCommercial use: conditional
Knowledge cutoff2025-062025-03

Pricing and availability

Pricing attributeMagistral Small 2506Mistral Medium 3 Instruct
Input price-$0.40/1M tokens
Output price-$2/1M tokens
Providers

Capabilities

CapabilityMagistral Small 2506Mistral Medium 3 Instruct
VisionNoYes
MultimodalNoYes
ReasoningYesNo
JSON / Tool useNoNo
Structured outputsNoNo
Code executionNoNo
IDE integrationNoNo
Computer useNoNo
Parallel agentsNoNo

Benchmarks

No shared benchmark scores are currently available for this pair.

Continue comparing

Last reviewed: 2026-06-15. Data sourced from public model cards and provider documentation.