Mistral Small 3
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% accuracy on the MMLU benchmark and performs competitively with larger models like Llama 3.3 70B and Qwen 32B, while operating at three times the speed on equivalent hardware. [Read the blog post about the model here.](https://mistral.ai/news/mistral-small-3/)
mistralai/mistral-small-24b-instruct-2501
- Context
- 33k tokens
- Completion cap
- 16,384
- Tools
- No
- JSON
- Yes
- Released
- 2025-01-30
Call it from Geek Hub
Same OpenAI SDK. Change the base URL and the model id.
curl https://api.geekhub.mx/v1/chat/completions \
-H "Authorization: Bearer $GEEKHUB_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "mistralai/mistral-small-24b-instruct-2501",
"messages": [{"role": "user", "content": "Hola"}]
}'Frequently asked questions
- What is Mistral Small 3?
- 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% accuracy on the MMLU benchmark and performs competitively with larger models like Llama 3.3 70B and Qwen 32B, while operating at three times the speed on equivalent hardware. [Read the blog post about the model here.](https://mistral.ai/news/mistral-small-3/) Mistral Small 3 runs on the Geek Hub API (OpenAI-compatible). Model id: mistralai/mistral-small-24b-instruct-2501.
- Is Mistral Small 3 free?
- No. Input is $0.0545 per 1M tokens and output is $0.0872 per 1M tokens on Geek Hub (markup included).
- What is the context length of Mistral Small 3?
- Mistral Small 3 has a 33k tokens context window. It supports up to 16,384 completion tokens.
- Does Mistral Small 3 support tool calling and structured outputs?
- Mistral Small 3 does not advertise tool calling on this endpoint. It also supports structured outputs via a JSON schema in response_format.
- When was Mistral Small 3 released?
- Mistral Small 3 was released on 2025-01-30.
More models from Mistral
- Codestral 2508Mistral'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 correc
- Ministral 3 14B 2512The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and
- Ministral 3 3B 2512The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.
- Ministral 3 8B 2512A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.
- Ministral 8BMinistral 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 suppor
- Mistral LargeThis 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.