Models / Mistral AI
Mistral-Small-24B-Instruct-2501
by Mistral AI
Used for chat, agents, fast, multilingual and reasoning.
Best forChatAgents and toolsMany languages
Mistral-Small-24B-Instruct-2501 is made by Mistral AI. It takes text in and answers in text, with a context window of 32,768 tokens.
Price per 1M tokens
The live price, read from billing as this page loads. You pay only for the tokens you use, from prepaid credit.
catalog/mistral-small-24b-instruct-2501Tīrtha Bench review
What people use it for, in its maker's words:
Try it
Model id catalog/mistral-small-24b-instruct-2501 · base URL https://api.tirtha.ai/v1. Any OpenAI-compatible client works: change the base URL and keep your code.
Using a coding tool? Set up OpenCode, Cline, Cursor and more. PowerShell and the full reference: Quickstart.
Limits and support
- Text inYes
- StreamingYes
- Sampling settingsYou can set themThe maker suggests temperature 0.15.
What it is for
- Chat
Fast response conversational agents.
From the maker's card - Agents and tools
Offers best-in-class agentic capabilities with native function calling and JSON outputting.
From the maker's card - Many languages
Supports dozens of languages, including English, French, German, Spanish, Italian, Chinese, Japanese, Korean
From the maker's card
In the maker's own words, from its published model card. Claims and benchmarks on that card are the maker's own, not measured by Tīrtha.
What a job costs
1,000 calls of 2,000 tokens in and 500 out cost about -
Worked out from the live price above, without cached input. Your own calls will differ in size.
Similar models on Tīrtha
Licence
Weights: Apache-2.0. Read the licence.
From the maker: Model card: mistralai/Mistral-Small-24B-Instruct-2501 on Hugging Face · Built on: mistralai/Mistral-Small-24B-Base-2501 · Last updated by the maker: Jul 28, 2025Facts from the maker's card are the maker's own, not measured by Tīrtha.