Mistral Small 24.02
Mistral Small 24.02 is a text generation model from Mistral with a 128,000-token context window, available via Amazon Bedrock.
Mistral
Amazon BedrockEfficient text generation with large context support
Mistral Small 24.02 is a large language model developed by Mistral and released in February 2024. It is hosted on Amazon Bedrock under the identifier mistral.mistral-small-2402-v1:0 and supports a 128,000-token context window with a maximum response size of 16,000 tokens. The model is designed for text generation tasks including summarization, question answering, and instruction following.
Mistral Small 24.02 occupies the smaller end of Mistral's model lineup, making it suited for workloads where efficiency and lower latency matter alongside a large context capacity. It is currently marked as deprecated, meaning Mistral and Amazon Bedrock have moved toward newer model versions. Developers working with existing integrations on Bedrock may still reference this model, but new projects are generally directed to more recent releases.
What Mistral Small 24.02 supports
Long Context Window
Processes up to 128,000 tokens in a single request, enabling analysis of long documents or extended conversation histories.
Text Generation
Generates coherent text responses for tasks such as summarization, Q&A, and instruction following, with a maximum response size of 16,000 tokens.
Instruction Following
Responds to structured prompts and multi-turn chat interactions using a chat-optimized model architecture (llm_chat).
Multilingual Support
Handles text in multiple European languages including English, French, German, Spanish, and Italian, reflecting Mistral's training priorities.
Amazon Bedrock Integration
Deployed via Amazon Bedrock, allowing access through AWS APIs without managing model infrastructure directly.
Ready to build with Mistral Small 24.02?
Get Started FreeBenchmark scores
Scores represent accuracy — the percentage of questions answered correctly on each test.
| Benchmark | What it tests | Score |
|---|---|---|
| MMLU-Pro | Expert knowledge across 14 academic disciplines | 52.9% |
| GPQA Diamond | PhD-level science questions (biology, physics, chemistry) | 38.1% |
| MATH-500 | Undergraduate and competition-level math problems | 56.3% |
| AIME 2024 | American math olympiad problems | 6.3% |
| LiveCodeBench | Real-world coding tasks from recent competitions | 14.1% |
| HLE | Questions that challenge frontier models across many domains | 4.3% |
| SciCode | Scientific research coding and numerical methods | 15.6% |
Common questions about Mistral Small 24.02
What is the context window size for Mistral Small 24.02?
Mistral Small 24.02 supports a context window of 128,000 tokens, with a maximum response size of 16,000 tokens.
Is Mistral Small 24.02 still available to use?
The model is currently marked as deprecated. It was available through Amazon Bedrock under the identifier mistral.mistral-small-2402-v1:0, but users are generally encouraged to migrate to newer Mistral model versions.
Who publishes Mistral Small 24.02 and where is it hosted?
The model is published by Mistral and was made available through Amazon Bedrock as the cloud provider.
What types of tasks is Mistral Small 24.02 suited for?
It is a text generation model suited for tasks such as summarization, question answering, instruction following, and multi-turn chat, particularly where a large context window is needed alongside moderate model size.
What is the release date and knowledge cutoff for Mistral Small 24.02?
The model was released in February 2024. A specific training data knowledge cutoff date is not provided in the available metadata.
Parameters & options
Explore similar models
MistralMinistral 3 3B
Ministral 3 3B is a 3-billion-parameter open-source text generation model from Mistral with a 256,000-token context window.
MistralMinistral 3 8B
Ministral 3 8B is an open-source text generation model from Mistral with a 256,000-token context window.
MistralMinistral 3 14B
Ministral 3 14B is an open-source text generation model from Mistral with a 256,000-token context window.
OpenAIGPT-6 Astra
AnthropicClaude 5.1 Fable
DeepSeekDeepSeek V4.1 Flash
Start building with Mistral Small 24.02
No API keys required. Create AI-powered workflows with Mistral Small 24.02 in minutes — free.