Mistral AI

Codestral-22B-v0.1

DeprecatedOpen weights128K context

Summary

Codestral-22B-v0.1 is an open-weight language model from Mistral AI, released on 29 May 2024. 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.

Open Mistral code model for fill-in-the-middle and 80+ programming languages

Last verified 22 Oct 2026. Every figure on this page links to its source.

Specifications

DeveloperMistral AI
Release date29 May 2024 [models.dev]
StatusDeprecated [models.dev]
WeightsOpen weights [models.dev]
Context window128K (128,000 tokens) [models.dev]
Max output4K tokens [models.dev]
InputText [models.dev]
OutputText [models.dev]
Reasoning modeNo [models.dev]
Tool callingNo [models.dev]

Codestral-22B-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 Codestral-22B-v0.1?

Codestral-22B-v0.1 has a context window of 128,000 tokens (128K) and can generate up to 4,000 tokens in a single response, according to models.dev.

Is Codestral-22B-v0.1 open source?

Codestral-22B-v0.1 is an open-weight model. Check the license terms before commercial use.

When was Codestral-22B-v0.1 released?

Mistral AI released Codestral-22B-v0.1 on 29 May 2024, 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
Llama 3.1 70B InstructMeta23 Jul 2024128K$0.72$0.72Open
Llama 3.1 8B InstructMeta23 Jul 2024128K$0.02$0.04Open
Hermes 3 405B InstructNousresearch16 Aug 2024131K––Open
Hermes 3 405B Instruct (Deep Infra)Nousresearch16 Aug 2024131K––Open
Command RCohere30 Aug 2024128K$0.15$0.60Open
Command R+Cohere30 Aug 2024128K$2.50$10Open

Change history

  • Status changed from active to deprecated

Sources