MistralAI logo

MistralAI AI models

2 MistralAI models on FastRouter, all behind one OpenAI-compatible API. Compare pricing, context windows and benchmarks, then open any model for its providers and code samples.

Filter in catalog
Models
2
Largest context
131K
Mistral Nemo
Lowest input /1M
$0.02
Mistral Nemo
Top intelligence
5.5
Mistral Small 3

All MistralAI models

MistralAI logo

A 24B parameter model optimized for speed and efficiency while rivaling models 3x its size like Llama 3.3 70B. Achieves 81% accuracy on MMLU benchmarks with impressive 150 tokens/second throughput on consumer hardware. Released under Apache 2.0 license, it serves as an excellent base for developing advanced reasoning capabilities.

mistralai/Mistral-Small-24B-Instruct-2501Jan 30, 20253.2s latency
Context
28K
Price /1M
$0.05 in$0.08 out
Intel
5.5
MistralAI logo

A streamlined 12B parameter model developed in collaboration with NVIDIA featuring 128K context window support. Offers multilingual capabilities and integrated function calling, making it well-suited for deployment on NVIDIA hardware with optimized performance characteristics for real-time applications.

mistralai/Mistral-Nemo-Instruct-2407Jul 19, 20243.3s latency
Context
131K
Price /1M
$0.02 in$0.03 out
Intel
5.2

Frequently asked questions

Model scores sourced from ArtificialAnalysis

MistralAI AI Models & API Pricing | FastRouter.ai