Mistral AI

Mixtral 8x7B Instruct v0.1

Generally availableOpen weights32K contextReasoning

Summary

Mixtral 8x7B Instruct v0.1 is an open-weight language model from Mistral AI, released on 11 Dec 2023. It accepts text and PDFs and generates text, with a 32K-token context window and up to 4K output tokens per response.

Reasoning model for deliberate analysis, multi-step problem solving, and tool use

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

Specifications

DeveloperMistral AI
Release date11 Dec 2023 [models.dev]
StatusGenerally available [models.dev]
WeightsOpen weights [models.dev]
Context window32K (32,000 tokens) [models.dev]
Max output4K tokens [models.dev]
InputText and PDFs [models.dev]
OutputText [models.dev]
Reasoning modeYes [models.dev]
Tool callingNo [models.dev]
Structured outputYes [models.dev]

Mixtral 8x7B Instruct v0.1 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 Mixtral 8x7B Instruct v0.1?

Mixtral 8x7B Instruct v0.1 has a context window of 32,000 tokens (32K) and can generate up to 4,096 tokens in a single response, according to models.dev.

Is Mixtral 8x7B Instruct v0.1 open source?

Mixtral 8x7B Instruct v0.1 is an open-weight model. Check the license terms before commercial use.

When was Mixtral 8x7B Instruct v0.1 released?

Mistral AI released Mixtral 8x7B Instruct v0.1 on 11 Dec 2023, 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
GPT-3.5 Turbo 16kOpenAI28 Aug 202316K$3$4–
WizardLM 2 8x22BMicrosoft15 Apr 202466K$0.62$0.62Open
Qwen/Qwen2.5-7B-InstructAlibaba (Qwen)19 Sept 202433K$0.05$0.05Open
BGE M3Baai30 Jan 20248K$0.01–Open
Magnum v4 72BAnthracite ORG22 Oct 202433K$2.50$5Open
BGE Reranker V2 M3Baai15 Mar 20248K$0.01–Open

Change history

  • Max output changed from 33K to 4K
  • Context window changed from 33K to 32K
  • Reasoning mode changed from no to yes
  • Input modalities changed from text to text, pdf
  • Tool calling changed from yes to no
  • Structured output changed from no to yes
  • Name changed from Mixtral 8x7B Instruct v0.1 (Deep Infra) to Mixtral 8x7B Instruct v0.1
  • Context window changed from 32K to 33K
  • Name changed from Mixtral 8x7B Instruct v0.1 to Mixtral 8x7B Instruct v0.1 (Deep Infra)
  • Tool calling changed from no to yes
  • Max output changed from 4K to 33K
  • Input modalities changed from text, pdf to text
  • Structured output changed from yes to no
  • Reasoning mode changed from yes to no
  • Name changed from Mixtral 8x7B Instruct v0.1 (Deep Infra) to Mixtral 8x7B Instruct v0.1
  • Context window changed from 33K to 32K
  • Max output changed from 33K to 4K
  • Reasoning mode changed from no to yes
  • Tool calling changed from yes to no
  • Structured output changed from no to yes
  • Input modalities changed from text to text, pdf
  • Name changed from Mixtral 8x7B Instruct v0.1 to Mixtral 8x7B Instruct v0.1 (Deep Infra)
  • Context window changed from 32K to 33K
  • Tool calling changed from no to yes
  • Max output changed from 4K to 33K

Sources