About Mistral
Our mission is to make frontier AI open to all, and together solve the world's hardest problems.
We partner with organizations in high-stakes industries like finance, manufacturing, defense, energy, and the public sector to co-create tailored AI systems to solve their hardest, most high-value problems. Because we believe that this critical stake for companies requires deep control, ownership, and production reliability, we have built full-stack AI solutions, including frontier models, developer tools, applications, and compute.
Website ↗Documentation ↗
Source ↗ · 2026-11-12T02:17:02.963004760Zmistralai/mistral-nemo
A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,...
- Context window
- 131,072
- Input modalities
- text
- Output modalities
- text
- Capabilities
- structuredOutputs, toolCalling
Benchmarks
- Open LLM Leaderboard v2: 24.666%
Inference prices
- Published price : $0.03 / input_tokens_per_million · openRouter ↗
- Published price : $0.03 / output_tokens_per_million · openRouter ↗
mistralai/mistral-small-24b-instruct-2501
Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed for efficient local deployment. The model achieves 81% accu
- Context window
- 32,768
- Input modalities
- text
- Output modalities
- text
- Capabilities
- structuredOutputs
Benchmarks
Inference prices
- Published price : $0.05 / input_tokens_per_million · deepInfra ↗
- Published price : $0.08 / output_tokens_per_million · deepInfra ↗
mistralai/mistral-small-3.1-24b-instruct-2503
Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and vision tasks, including image analysis, programming, mathem
- Context window
- 128,000
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, structuredOutputs, toolCalling, visionInput
Benchmarks
- LLM Stats · GitHub archive: 0.593
Inference prices
- Published price : $0.05 / input_tokens_per_million · deepInfra ↗
- Published price : $0.10 / output_tokens_per_million · deepInfra ↗
mistralai/mistral-small-3.2-24b-instruct-2506
Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on WildBench and Arena Hard, reduc
- Context window
- 256,000
- Input modalities
- image, text
- Output modalities
- text
- Capabilities
- multimodal, promptCaching, structuredOutputs, toolCalling, visionInput
Inference prices
- Published price : $0.08 / input_tokens_per_million · deepInfra ↗
- Published price : $0.20 / output_tokens_per_million · deepInfra ↗
mistralai/mixtral-8x22b-instruct
Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding,...
- Context window
- 65,536
- Input modalities
- text, file
- Output modalities
- text
- Capabilities
- fileInput, multimodal, promptCaching, structuredOutputs, toolCalling
Benchmarks
- Artificial Analysis: 5.7
- HELM Capabilities: 46%
- LiveBench: 32.781%
- Open LLM Leaderboard v1: 79.147%
- Open LLM Leaderboard v2: 33.886%
Inference prices
- Published price : $0.20 / cache_read_tokens_per_million · openRouter ↗
- Published price : $2.00 / input_tokens_per_million · openRouter ↗
- Published price : $6.00 / output_tokens_per_million · openRouter ↗
mistral/mistral-moderation-2603
Our latest moderation model with 128k context window and jailbreaking detection. Strong performance on complex multilingual data including long multi-turn conversations.
- Context window
- 128,000
- Input modalities
- text
- Output modalities
- scores
- Capabilities
- batch, moderation
Inference prices
- input / 1M tokens : $0.00 / input_tokens_per_million · mistral ↗
cheaperInference/mistral-nemo
- Context window
- 131,072
- Maximum output
- 131,072
- Input modalities
- text
- Output modalities
- text
- Capabilities
- structuredOutputs, toolCalling
Inference prices
vercelAIGatewayCatalog/mistral/mistral-nemo
12B model trained jointly by Mistral AI and NVIDIA, it significantly outperforms existing models smaller or similar in size.
- Context window
- 131,072
- Maximum output
- 131,072
- Input modalities
- text
- Output modalities
- text
- Capabilities
- structuredOutputs, toolCalling
Inference prices
vertexAI/publishers/mistral-ai/models/mistral@mistral-nemo-base-2407
- Input modalities
- text
- Output modalities
- text
Benchmarks
- Open LLM Leaderboard v2: 15.239%
vertexAI/publishers/mistralai/models/mistral-ocr-2505@001
Mistral OCR (25.05) is an Optical Character Recognition API for document understanding. Mistral OCR (25.05) excels in understanding complex document elements, including interleaved imagery, mathematical expressions, tables, and advanced layouts such as LaTeX formatting. The model
- Input modalities
- file
- Output modalities
- text
- Capabilities
- fileInput, ocr
azureFoundry/azureml-mistral/mistral-ocr-4-0@1
Document conversion to markdown with interleaved images and text
- Context window
- 128,000
- Maximum output
- 4,096
- Input modalities
- pdf, image
- Output modalities
- text
- Capabilities
- multimodal, visionInput
mistralai/mistral-saba-2502
Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional datasets, it supports multiple Indian-origin langu
- Context window
- 32,768
- Input modalities
- text, file
- Output modalities
- text
- Capabilities
- fileInput, multimodal, promptCaching, structuredOutputs, toolCalling
Benchmarks
Inference prices
- Published price : $0.02 / cache_read_tokens_per_million · openRouter ↗
- Published price : $0.20 / input_tokens_per_million · openRouter ↗
- Published price : $0.60 / output_tokens_per_million · openRouter ↗
cheaperInference/mistral-small
- Context window
- 262,144
- Maximum output
- 4,000
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, structuredOutputs, toolCalling, visionInput
Inference prices
vercelAIGatewayCatalog/mistral/mistral-small
Mistral Small currently runs Mistral Small 4, a multimodal model combining instruction following, reasoning, and coding with a 262,144-token context window.
- Context window
- 262,144
- Maximum output
- 4,000
- Input modalities
- text, image
- Output modalities
- text
awsBedrock/mistral.mistral-small-2402-v1:0
- Input modalities
- text
- Output modalities
- text
Benchmarks
vertexAI/publishers/mistralai/models/mistral-small-2503@001
Mistral Small 3.1 (25.03) features multimodal capabilities and a context of up to 128,000. The model can process and understand visual inputs and long documents, further expanding its range of applications compared to the previous Mistral AI Small model. Mistral Small 3.1 (25.03)
- Input modalities
- file, text
- Output modalities
- text
- Capabilities
- fileInput, multimodal
azureFoundry/azureml-mistral/mistral-small-2503@1
Enhanced Mistral Small 3 with multimodal capabilities and a 128k context length.
- Context window
- 128,000
- Maximum input
- 32,768
- Maximum output
- 4,096
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, toolCalling, visionInput
mistralai/voxtral-mini-3b-2507-20260813
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.
- Context window
- 0
- Input modalities
- audio
- Output modalities
- transcription
- Capabilities
- audioInput
Benchmarks
- Open ASR Leaderboard: 4.33%