Models
| Provider | Types | |||||||
|---|---|---|---|---|---|---|---|---|
 Mistral | Ministral 3B | Text | $0.04 | $0.04 | 131.1K | Cheapest | ||
| Mistral | Ministral 8B | Text | $0.10 | $0.10 | 128K | Cheapest | ||
| Mistral | Mistral Tiny | Text | $0.25 | $0.25 | 32.8K | Mid | ||
| Mistral | Mistral Tiny Latest | Text | $0.25 | $0.25 | 32.8K | Mid | ||
| Mistral | Mistral Nemo | Text | $0.02 | $0.07 | 131.1K | Cheapest | ||
| Mistral | Mistral Small | Text | $0.20 | $0.60 | 32.8K | Cheapest | ||
| Mistral | Mistral Small 2409 | Text | $0.20 | $0.60 | 32.8K | Cheapest | ||
| Mistral | Mistral Small 2501 | Text | $0.20 | $0.60 | 32.8K | Mid | ||
| Mistral | Mistral Small 2503 | Text | $0.20 | $0.60 | 32.8K | Mid | ||
| Mistral | Mistral Small Latest | Text | $0.20 | $0.60 | 32.8K | Mid | ||
| Mistral | Mistral Medium | Text | $2.75 | $8.10 | 32K | Expensive | ||
| Mistral | Mistral Medium Latest | Text | $2.75 | $8.10 | 32K | Expensive | ||
| Mistral | Mistral Medium 2505 | Text | $2.75 | $8.10 | 32K | Expensive | ||
| Mistral | Mistral Large | Text | $2.00 | $6.00 | 128K | Expensive | ||
| Mistral | Mistral Large 2411 | Text | $2.00 | $6.00 | 131.1K | Expensive | ||
| Mistral | Mistral Large 2407 | Text | $2.00 | $6.00 | 128K | Expensive | ||
| Mistral | Pixtral Large Latest | Text | $2.00 | $6.00 | 128K | Expensive | ||
| Mistral | Pixtral Large 2411 | Text | $2.00 | $6.00 | 128K | Expensive | ||
| Mistral | Codestral 2501 | Text | $0.30 | $0.90 | 262.1K | Mid | ||
| Mistral | Codestral Latest | Text | $0.30 | $0.90 | 262.1K | Mid |
Ministral 3B
(ministral-3b-latest)
Cheapest
Ministral 3BBy Mistral
Ministral 3B is a 3B parameter model optimized for on-device and edge computing. It excels in knowledge, commonsense reasoning, and function-calling, outperforming larger models like Mistral 7B on most benchmarks. Supporting up to 128k context length, it's ideal for orchestrating agentic workflows and specialist tasks with efficient inference.$0.04Input(Per Million)
$0.04Output(Per Million)
131.1KContext Window
Ministral 8B
(ministral-8b-latest)
Cheapest
Ministral 8BBy Mistral
Ministral 8B is an 8B parameter model featuring a unique interleaved sliding-window attention pattern for faster, memory-efficient inference. Designed for edge use cases, it supports up to 128k context length and excels in knowledge and reasoning tasks. It outperforms peers in the sub-10B category, making it perfect for low-latency, privacy-first applications.$0.10Input(Per Million)
$0.10Output(Per Million)
128KContext Window
Mistral Tiny
(mistral-tiny)
Mid
Mistral TinyBy Mistral
Note: This model is being deprecated. Recommended replacement is the newer [Ministral 8B](/mistral/ministral-8b)
This model is currently powered by Mistral-7B-v0.2, and incorporates a "better" fine-tuning than [Mistral 7B](/models/mistralai/mistral-7b-instruct-v0.1), inspired by community work. It's best used for large batch processing tasks where cost is a significant factor but reasoning capabilities are not crucial.$0.25Input(Per Million)
$0.25Output(Per Million)
32.8KContext Window
Mistral Tiny Latest
(mistral-tiny-latest)
Mid
Mistral Tiny LatestBy Mistral
Note: This model is being deprecated. Recommended replacement is the newer [Ministral 8B](/mistral/ministral-8b)
This model is currently powered by Mistral-7B-v0.2, and incorporates a "better" fine-tuning than [Mistral 7B](/models/mistralai/mistral-7b-instruct-v0.1), inspired by community work. It's best used for large batch processing tasks where cost is a significant factor but reasoning capabilities are not crucial.$0.25Input(Per Million)
$0.25Output(Per Million)
32.8KContext Window
Mistral Nemo
(mistral-nemo)
Cheapest
Mistral NemoBy Mistral
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.$0.02Input(Per Million)
$0.07Output(Per Million)
131.1KContext Window
Mistral Small
(mistral-small)
Cheapest
Mistral SmallBy Mistral
With 22 billion parameters, Mistral Small v24.09 offers a convenient mid-point between Mistral NeMo 12B and Mistral Large 2, providing a cost-effective solution that can be deployed across various platforms and environments. It has better reasoning, exhibits more capabilities, can produce and reason about code, and is multiligual, supporting English, French, German, Italian, and Spanish.$0.20Input(Per Million)
$0.60Output(Per Million)
32.8KContext Window
Mistral Small 2409
(mistral-small-2409)
Cheapest
Mistral Small 2409By Mistral
With 22 billion parameters, Mistral Small v24.09 offers a convenient mid-point between Mistral NeMo 12B and Mistral Large 2, providing a cost-effective solution that can be deployed across various platforms and environments. It has better reasoning, exhibits more capabilities, can produce and reason about code, and is multiligual, supporting English, French, German, Italian, and Spanish.$0.20Input(Per Million)
$0.60Output(Per Million)
32.8KContext Window
Mistral Small 2501
(mistral-small-2501)
Mid
Mistral Small 2501By Mistral
With 22 billion parameters, Mistral Small v24.09 offers a convenient mid-point between Mistral NeMo 12B and Mistral Large 2, providing a cost-effective solution that can be deployed across various platforms and environments. It has better reasoning, exhibits more capabilities, can produce and reason about code, and is multiligual, supporting English, French, German, Italian, and Spanish.$0.20Input(Per Million)
$0.60Output(Per Million)
32.8KContext Window
Mistral Small 2503
(mistral-small-2503)
Mid
Mistral Small 2503By Mistral
With 22 billion parameters, Mistral Small v24.09 offers a convenient mid-point between Mistral NeMo 12B and Mistral Large 2, providing a cost-effective solution that can be deployed across various platforms and environments. It has better reasoning, exhibits more capabilities, can produce and reason about code, and is multiligual, supporting English, French, German, Italian, and Spanish.$0.20Input(Per Million)
$0.60Output(Per Million)
32.8KContext Window
Mistral Small Latest
(mistral-small-latest)
Mid
Mistral Small LatestBy Mistral
With 22 billion parameters, Mistral Small v24.09 offers a convenient mid-point between Mistral NeMo 12B and Mistral Large 2, providing a cost-effective solution that can be deployed across various platforms and environments. It has better reasoning, exhibits more capabilities, can produce and reason about code, and is multiligual, supporting English, French, German, Italian, and Spanish.$0.20Input(Per Million)
$0.60Output(Per Million)
32.8KContext Window
Mistral Medium
(mistral-medium)
Expensive
Mistral MediumBy Mistral
This is Mistral AI's closed-source, medium-sided model. It's powered by a closed-source prototype and excels at reasoning, code, JSON, chat, and more. In benchmarks, it compares with many of the flagship models of other companies.$2.75Input(Per Million)
$8.10Output(Per Million)
32KContext Window
Mistral Medium Latest
(mistral-medium-latest)
Expensive
Mistral Medium LatestBy Mistral
This is Mistral AI's closed-source, medium-sided model. It's powered by a closed-source prototype and excels at reasoning, code, JSON, chat, and more. In benchmarks, it compares with many of the flagship models of other companies.$2.75Input(Per Million)
$8.10Output(Per Million)
32KContext Window
Mistral Medium 2505
(mistral-medium-2505)
Expensive
Mistral Medium 2505By Mistral
This is Mistral AI's closed-source, medium-sided model. It's powered by a closed-source prototype and excels at reasoning, code, JSON, chat, and more. In benchmarks, it compares with many of the flagship models of other companies.$2.75Input(Per Million)
$8.10Output(Per Million)
32KContext Window
Mistral Large
(mistral-large-latest)
Expensive
Mistral LargeBy Mistral
This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/).
It supports dozens of languages including French, German, Spanish, Italian, Portuguese, Arabic, Hindi, Russian, Chinese, Japanese, and Korean, along with 80+ coding languages including Python, Java, C, C++, JavaScript, and Bash. Its long context window allows precise information recall from large documents.$2.00Input(Per Million)
$6.00Output(Per Million)
128KContext Window
Mistral Large 2411
(mistral-large-2411)
Expensive
Mistral Large 2411By Mistral
Mistral Large 2 2411 is an update of [Mistral Large 2](/mistralai/mistral-large) released together with [Pixtral Large 2411](/mistralai/pixtral-large-2411)
It provides a significant upgrade on the previous [Mistral Large 24.07](/mistralai/mistral-large-2407), with notable improvements in long context understanding, a new system prompt, and more accurate function calling.$2.00Input(Per Million)
$6.00Output(Per Million)
131.1KContext Window
Mistral Large 2407
(mistral-large-2407)
Expensive
Mistral Large 2407By Mistral
This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement here: https://mistral.ai/news/mistral-large-2407/.
It supports dozens of languages including French, German, Spanish, Italian, Portuguese, Arabic, Hindi, Russian, Chinese, Japanese, and Korean, along with 80+ coding languages including Python, Java, C, C++, JavaScript, and Bash. Its long context window allows precise information recall from large documents.$2.00Input(Per Million)
$6.00Output(Per Million)
128KContext Window
Pixtral Large Latest
(pixtral-large-latest)
Expensive
Pixtral Large LatestBy Mistral
Pixtral Large is a 124B parameter, open-weight, multimodal model built on top of Mistral Large 2. The model is able to understand documents, charts and natural images.
The model is available under the Mistral Research License (MRL) for research and educational use, and the Mistral Commercial License for experimentation, testing, and production for commercial purposes.$2.00Input(Per Million)
$6.00Output(Per Million)
128KContext Window
Pixtral Large 2411
(pixtral-large-2411)
Expensive
Pixtral Large 2411By Mistral
Pixtral Large is a 124B parameter, open-weight, multimodal model built on top of Mistral Large 2. The model is able to understand documents, charts and natural images.
The model is available under the Mistral Research License (MRL) for research and educational use, and the Mistral Commercial License for experimentation, testing, and production for commercial purposes.$2.00Input(Per Million)
$6.00Output(Per Million)
128KContext Window
Codestral 2501
(codestral-2501)
Mid
Codestral 2501By Mistral
[Mistral](/mistralai)'s cutting-edge language model for coding. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.
Learn more on their blog post: https://mistral.ai/news/codestral-2501/$0.30Input(Per Million)
$0.90Output(Per Million)
262.1KContext Window
Codestral Latest
(codestral-latest)
Mid
Codestral LatestBy Mistral
[Mistral](/mistralai)'s cutting-edge language model for coding. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.
Learn more on their blog post: https://mistral.ai/news/codestral-2501/$0.30Input(Per Million)
$0.90Output(Per Million)
262.1KContext Window
Showing 1-20 of 35 models