Model catalog
One endpoint, every model. Compare context windows, capabilities and real per-token pricing side by side, then swap the model string in your request — nothing else changes.
- 351
- Models
- 35
- Providers
- 11
- Free to try
- $0.0001
- Cheapest input / 1M
16 of 351 models
LanguageMistral Medium Latest
mistral/mistral-medium-3.5
Mistral's frontier-class multimodal model optimized for agentic and coding use cases.
- Context
- 256K
- In / 1M
- $1.50
- Out / 1M
- $7.50
- Reasoning
- Tool use
- Vision
- Language
Ministral 14B
mistral/ministral-14b
Ministral 3 14B is the largest model in the Ministral 3 family, offering state-of-the-art capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. Optimized for local deployment, it delivers high performance across diverse hardware, including local setups.
- Context
- 256K
- In / 1M
- $0.200
- Out / 1M
- $0.200
- Tool use
- Vision
- File input
- Language
Magistral Medium 2509
mistral/magistral-medium
Complex thinking, backed by deep understanding, with transparent reasoning you can follow and verify. The model excels in maintaining high-fidelity reasoning across numerous languages, even when switching between languages mid-task.
- Context
- 128K
- In / 1M
- $2.00
- Out / 1M
- $5.00
- Reasoning
- Tool use
- Vision
- Language
Magistral Small 2509
mistral/magistral-small
Complex thinking, backed by deep understanding, with transparent reasoning you can follow and verify. The model excels in maintaining high-fidelity reasoning across numerous languages, even when switching between languages mid-task.
- Context
- 128K
- In / 1M
- $0.500
- Out / 1M
- $1.50
- Reasoning
- Tool use
- Vision
- Language
Devstral Small 2
mistral/devstral-small-2
Our open source model that excels at using tools to explore codebases, editing multiple files, and powering software engineering agents.
- Context
- 256K
- In / 1M
- $0.100
- Out / 1M
- $0.300
- Tool use
- Vision
- Language
Mistral Large 3
mistral/mistral-large-3
Mistral Large 3 2512 is Mistral’s most capable model to date. It has a sparse mixture-of-experts architecture with 41B active parameters (675B total).
- Context
- 256K
- In / 1M
- $0.500
- Out / 1M
- $1.50
- Tool use
- Vision
- Language
Mistral Medium 3.1
mistral/mistral-medium
Mistral Medium 3 delivers frontier performance while being an order of magnitude less expensive. For instance, the model performs at or above 90% of Claude Sonnet 3.7 on benchmarks across the board at a significantly lower cost.
- Context
- 128K
- In / 1M
- $0.400
- Out / 1M
- $2.00
- Tool use
- Vision
- Language
Ministral 3B
mistral/ministral-3b
A compact, efficient model for on-device tasks like smart assistants and local analytics, offering low-latency performance.
- Context
- 128K
- In / 1M
- $0.100
- Out / 1M
- $0.100
- Tool use
- Vision
- Language
Ministral 8B
mistral/ministral-8b
A more powerful model with faster, memory-efficient inference, ideal for complex workflows and demanding edge applications.
- Context
- 128K
- In / 1M
- $0.150
- Out / 1M
- $0.150
- Tool use
- Vision
- Language
Mistral Small
mistral/mistral-small
Mistral Small is the ideal choice for simple tasks that one can do in bulk - like Classification, Customer Support, or Text Generation. It offers excellent performance at an affordable price point.
- Context
- 32K
- In / 1M
- $0.100
- Out / 1M
- $0.300
- Tool use
- Vision
- Language
Pixtral 12B 2409
mistral/pixtral-12b
A 12B model with image understanding capabilities in addition to text.
- Context
- 128K
- In / 1M
- $0.150
- Out / 1M
- $0.150
- Tool use
- Vision
- Language
Mistral Nemo 12B
mistral/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, Korean, Arabic, and Hindi. It supports function calling and is released under the Apache 2.0 license.
- Context
- 128K
- In / 1M
- $0.150
- Out / 1M
- $0.150
- Tool use
- Vision
- Language
Devstral 2
mistral/devstral-2
An enterprise-grade text model that excels at using tools to explore codebases, editing multiple files, and powering software engineering agents.
- Context
- 256K
- In / 1M
- $0.400
- Out / 1M
- $2.00
- Tool use
- Language
Mistral Codestral
mistral/codestral
Mistral's cutting-edge language model for coding released end of July 2025, Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.
- Context
- 128K
- In / 1M
- $0.300
- Out / 1M
- $0.900
- Tool use
- Embedding
Codestral Embed
mistral/codestral-embed
Code embedding model that can embed code databases and repositories to power coding assistants.
- Context
- —
- In / 1M
- $0.150
- Out / 1M
- —
- Embedding
Mistral Embed
mistral/mistral-embed
General-purpose text embedding model for semantic search, similarity, clustering, and RAG workflows.
- Context
- —
- In / 1M
- $0.100
- Out / 1M
- —