Mistral AI

Magistral Small 2506

DeprecatedOpen weights128K context

Summary

Magistral Small 2506 is an open-weight language model from Mistral AI, released on 10 Jun 2025. It accepts text and generates text, with a 128K-token context window and up to 4K output tokens per response. Mistral AI has deprecated this model.

Mistral reasoning model for transparent analysis, math, and complex decisions

Last verified 18 Nov 2026. Every figure on this page links to its source.

Specifications

DeveloperMistral AI
Release date10 Jun 2025 [models.dev]
StatusDeprecated [models.dev]
WeightsOpen weights [models.dev]
Context window128K (128,000 tokens) [models.dev]
Max output4K tokens [models.dev]
Knowledge cutoffJan 2025 [models.dev]
InputText [models.dev]
OutputText [models.dev]
Reasoning modeNo [models.dev]
Tool callingYes [models.dev]
Structured outputNo [models.dev]

Magistral Small 2506 API pricing by provider

USD per million tokens. Sorted by input price.

We do not currently track a paid API listing for this model.

Frequently asked questions

What is the context window of Magistral Small 2506?

Magistral Small 2506 has a context window of 128,000 tokens (128K) and can generate up to 4,096 tokens in a single response, according to models.dev.

Is Magistral Small 2506 open source?

Magistral Small 2506 is an open-weight model. Check the license terms before commercial use.

When was Magistral Small 2506 released?

Mistral AI released Magistral Small 2506 on 10 Jun 2025, according to models.dev.

Similar models from other labs

Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.

ModelLabReleasedContextInput $/1MOutput $/1MWeights
DeepSeek R1 0528 Qwen3 8BDeepSeek29 May 2025128K$0.06$0.09Open
ERNIE 4.5 300B A47BBaidu30 Jun 2025123K––Open
ERNIE 4.5 VL 424B A47BBaidu30 Jun 2025123K––Open
UncensoredCognitivecomputations9 Jul 2025128K$0.20$0.90Open
Hunyuan A13B InstructTencent (Hunyuan)8 Jul 2025131K––Open
Kimi K2 InstructMoonshot AI11 Jul 2025131K$0.57$2.30Open

Change history

  • Max output changed from 33K to 4K
  • Context window changed from 33K to 128K
  • Tool calling changed from no to yes
  • Tool calling changed from yes to no
  • Max output changed from 4K to 33K
  • Context window changed from 128K to 33K
  • Context window changed from 33K to 128K
  • Tool calling changed from no to yes
  • Max output changed from 33K to 4K
  • Max output changed from 4K to 33K
  • Tool calling changed from yes to no
  • Context window changed from 128K to 33K
  • Max output changed from 33K to 4K
  • Tool calling changed from no to yes
  • Context window changed from 33K to 128K
  • Max output changed from 4K to 33K
  • Tool calling changed from yes to no
  • Context window changed from 128K to 33K
  • Max output changed from 33K to 4K
  • Tool calling changed from no to yes
  • Context window changed from 33K to 128K
  • Context window changed from 128K to 33K
  • Max output changed from 4K to 33K
  • Tool calling changed from yes to no
  • Tool calling changed from no to yes

Sources