What is Codestral Mamba?

A 7.3B parameter Mamba-based model designed for code and reasoning tasks. - Linear time inference, allowing for theoretically infinite sequence lengths - 256k token context window - Optimized for quick responses, especially beneficial for code productivity - Performs comparably to state-of-the-art transformer models in code and reasoning tasks - Available under the Apache 2.0 license for free...

What is the context length of Codestral Mamba?

Codestral Mamba has a 256,000 token context window.

What other text models does Mistral have?

Mistral Large 4, Mistral Medium 3.5, Mistral Small 4 and 17 more are other text models from Mistral.

When was Codestral Mamba released?

Codestral Mamba was released on July 19, 2024. Its knowledge cutoff is March 31, 2024.

Mistral: Codestral Mamba

mistralai/codestral-mamba

Model weights

A 7.3B parameter Mamba-based model designed for code and reasoning tasks.

Linear time inference, allowing for theoretically infinite sequence lengths
256k token context window
Optimized for quick responses, especially beneficial for code productivity
Performs comparably to state-of-the-art transformer models in code and reasoning tasks
Available under the Apache 2.0 license for free use, modification, and distribution

Modalities

Context

256K

Released

Jul 19, 2024

Knowledge cutoff

Mar 2024

Not currently available through EU in-region routing. In-region routing docs

More models from Mistral

Voxtral TTS 3

Voxtral TTS 3 is Mistral's text-to-speech model. It converts text into natural-sounding speech, offers a library of preset voices, supports zero-shot voice cloning, and accepts emotion and pace tags in the input to control delivery. It streams audio with low time-to-first-audio and suits voice agents, narration, and multilingual assistants.

Speech$13/M characters

Voxtral Small Transcribe 3

Voxtral Small Transcribe 3 is Mistral's flagship speech-to-text model. It takes audio input and returns a transcript with timestamps and speaker diarization, and supports context biasing for domain-specific vocabulary. Suited for high-accuracy multilingual transcription of meetings, interviews, media, and support calls.

Transcription$0.000067/second

Voxtral Mini Transcribe 3

Voxtral Mini Transcribe 3 is Mistral's compact speech-to-text model. It takes audio input and returns a transcript with timestamps and speaker diarization. It also supports context biasing for domain terms. It is small enough to self-deploy in resource-constrained environments, and fits meeting notes, call analytics, and voice-agent pipelines where cost matters.

Transcription$0.000058/second

Mistral Large 4

Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 1M-token context window with up to 256K output tokens, and supports tool calling and structured outputs.

Text1.0M context$0.70 / $2.10

Voxtral Small 24B 2507 STT

Voxtral Small 24B 2507 STT is a speech transcription model from Mistral AI. It is suited for transcription, translation, and audio understanding workloads that benefit from its larger model capacity.

Transcription$0.00005/second

Voxtral Mini 3B 2507

Voxtral Mini 3B 2507 is a speech and audio understanding model from Mistral AI. It is suited for transcription, translation, and compact audio processing workloads.

Transcription$0.000017/second

Voxtral Mini Transcribe

Voxtral Mini Transcribe is Mistral's speech-to-text model, derived from the Voxtral Mini family. It accepts audio input and returns transcribed text via the standard transcription API. Suited for transcribing meetings, voice notes, podcasts, and other spoken content.

Transcription$0.00005/second

Mistral Medium 3.5

Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex multi-step reasoning. It is particularly strong at reliable multi-tool calling and long-horizon tasks, with a 256K context window, configurable reasoning effort per request, and a custom vision encoder that handles variable image sizes and aspect ratios. Self-hostable on as few as four GPUs and available under open weights.

Text262K context$1.50 / $7.50

Mistral Medium 3.5 (batch)

Text262K context$0.75 / $3.75

Voxtral Mini TTS

Voxtral Mini TTS is Mistral's text-to-speech model featuring zero-shot voice cloning and multilingual support. It converts text input into natural-sounding audio output.

Speech$16/M characters

Mistral Small 4

Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from Magistral, multimodal understanding from Pixtral, and agentic coding capabilities from Devstral, enabling one model to handle complex analysis, software development, and visual tasks within the same workflow.

Text262K context$0.15 / $0.60

Mistral Small Creative

Mistral Small Creative is an experimental small model designed for creative writing, narrative generation, roleplay and character-driven dialogue, general-purpose instruction following, and conversational agents.

Text33K context

Devstral 2 2512

Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window.

Devstral 2 supports exploring codebases and orchestrating changes across multiple files while maintaining architecture-level context. It tracks framework dependencies, detects failures, and retries with corrections—solving challenges like bug fixing and modernizing legacy systems. The model can be fine-tuned to prioritize specific languages or optimize for large enterprise codebases. It is available under a modified MIT license.

Text262K context$0.40 / $2

Ministral 3 14B 2512

The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language model with vision capabilities.

Text262K context$0.20 / $0.20

Ministral 3 8B 2512

A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.

Text262K context$0.15 / $0.15

Ministral 3 3B 2512

The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.

Text131K context$0.10 / $0.10

Mistral Large 3 2512

Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.

Text262K context$0.50 / $1.50

Mistral Embed 2312

Mistral Embed is a specialized embedding model for text data, optimized for semantic search and RAG applications. Developed by Mistral AI in late 2023, it produces 1024-dimensional vectors that effectively capture semantic relationships in text.

Embeddings$0.10/M tokens

Codestral Embed 2505

Mistral Codestral Embed is specially designed for code, perfect for embedding code databases, repositories, and powering coding assistants with state-of-the-art retrieval.

Embeddings$0.15/M tokens

Voxtral Small 24B 2507

Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding. Input audio is priced at $100 per million seconds.

Text33K context$0.10 / $0.30

Mistral: Codestral Mamba

Activity

Frequently asked questions

Explore more models

More models from Mistral

More models from Mistral