Mistral Small 3.1 24B
Mistral· released 17 Mar 2025
mistralai/mistral-small-3.1-24b-instruct- Input / 1M tokens
- $0.351
- Output / 1M tokens
- $0.555
Longest answer: 102K tokens
About
Mistral Small 3.1 24B Instruct is Mistral’s upgraded Small 3 variant, released March 17, 2025. It is an open-weights model with 24 billion parameters and advanced multimodal capabilities. The model accepts text and image inputs, produces text, and supports tools and vision. Its context window is 128,000 tokens, with a maximum output of 102,400 tokens. Mistral lists it in the mistralai family under the identifier mistralai/mistral-small-3.1-24b-instruct. The Hugging Face identifier is mistralai/Mistral-Small-3.1-24B-Instruct-2503. Its supplied description highlights text-based reasoning and multimodal operation. Pricing is $0.351 per 1M input tokens and $0.555 per 1M output tokens. Builders can consider it when they need open weights, image-aware inputs, tool support, and a comparatively large context for an instruct model.
Who it is for
It suits builders who need open weights with text-and-image input, vision, tools, and reasoning-oriented text generation. The Hugging Face identifier supports teams tracking the model in that ecosystem.
What is good
- Open weights available
- Accepts text and image inputs
- Supports tools and vision
- 128,000-token context window
- 102,400-token maximum output
What to know first
- $0.351 per 1M input tokens
- $0.555 per 1M output tokens
- Released March 17, 2025
Verdict
Mistral Small 3.1 24B Instruct combines open weights with multimodal inputs, tools, and vision. Its context, output limits, and per-million-token prices define the practical envelope for applications.
Details
- Lab
- Mistralopenrouter.ai · 3 Oct 2026
- Context
- 128Kopenrouter.ai · 3 Oct 2026
- Input price
- $0.351 / 1Mopenrouter.ai · 3 Oct 2026
- Output price
- $0.555 / 1Mopenrouter.ai · 3 Oct 2026
- Max output
- 102,400 tokensopenrouter.ai · 3 Oct 2026
- Inputs
- text, imageopenrouter.ai · 3 Oct 2026
- Open weights
- Yesopenrouter.ai · 3 Oct 2026
More newest models
See the list
Listed on Inferse
- Newest Models in 2026466 listed
- Longest-Context Models in 2026466 listed
- Cheapest Language Models in 2026437 listed
- Models with Tool Calling in 2026395 listed
- Vision Language Models in 2026295 listed
- Open-Weight Models in 2026178 listed
- Mistral Models: Pricing per 1M Tokens and Context (2026)23 listed
Sources
- openrouter.ai/mistralai/mistral-small-3.1-24b-instruc· checked 3 Oct 2026