Mistral Large 24.02
Mistral Large 24.02 is a text generation model from Mistral with a 128,000-token context window, available via Amazon Bedrock.
Mistral
Amazon BedrockLarge-scale text generation from Mistral AI
Mistral Large 24.02 is a large language model developed by Mistral AI and released in February 2024. It is hosted through Amazon Bedrock under the model ID mistral.mistral-large-2402-v1:0, and supports a 128,000-token context window with a maximum response size of 16,000 tokens. The model handles text-based chat and generation tasks across a wide range of domains, including reasoning, summarization, and code.
This model is suited for tasks that require processing long documents or maintaining extended conversational context, given its large context window. It is a text-only model and does not support image or video inputs. Note that this model has been marked as deprecated, meaning Mistral has released newer versions and this variant may no longer receive updates or active support on the platform.
What Mistral Large 24.02 supports
Long Context Window
Supports up to 128,000 tokens of input context, enabling processing of long documents, codebases, or extended conversations in a single request.
Text Generation
Generates coherent, multi-turn text responses across tasks like summarization, drafting, and question answering, with a maximum response size of 16,000 tokens.
Code Assistance
Handles code-related tasks such as generation, explanation, and debugging across common programming languages.
Multilingual Support
Mistral Large 24.02 was trained with strong multilingual capabilities, supporting several European languages including French, German, Spanish, and Italian alongside English.
Instruction Following
Designed to follow detailed system-level and user-level instructions, making it suitable for structured workflows and agent-style applications.
Ready to build with Mistral Large 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 | 69.7% |
| GPQA Diamond | PhD-level science questions (biology, physics, chemistry) | 48.6% |
| MATH-500 | Undergraduate and competition-level math problems | 73.6% |
| AIME 2024 | American math olympiad problems | 11.0% |
| LiveCodeBench | Real-world coding tasks from recent competitions | 29.3% |
| HLE | Questions that challenge frontier models across many domains | 4.0% |
| SciCode | Scientific research coding and numerical methods | 29.2% |
Common questions about Mistral Large 24.02
What is the context window size for Mistral Large 24.02?
Mistral Large 24.02 supports a context window of 128,000 tokens, allowing it to process long documents or extended conversations in a single request.
What is the maximum response length this model can produce?
The model has a maximum response size of 16,000 tokens per generation.
Is Mistral Large 24.02 still actively supported?
No. This model has a deprecated status, which means it is no longer the current recommended version from Mistral. Users may want to consider newer Mistral models for production use.
Does Mistral Large 24.02 support image or video inputs?
No. This model is text-only and does not support image or video analysis inputs.
Where is Mistral Large 24.02 hosted?
This model is provided through Amazon Bedrock, identified by the full model ID mistral.mistral-large-2402-v1:0.
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 Large 24.02
No API keys required. Create AI-powered workflows with Mistral Large 24.02 in minutes — free.