Mistral Medium
mistral-medium
About
Mistral Medium is a versatile large language model developed by Mistral AI, designed to handle a wide array of tasks with a robust 32k token context window, allowing it to process approximately 24,000 words. Built on a transformer architecture, it offers native fluency in multiple languages, including English, French, Spanish, German, and Italian, enhancing its multilingual reasoning capabilities. Available via API, Mistral Medium is proprietary and stronger than some of Mistral AI's open-source models like Mixtral 8x7B and Mistral-7B. While it is described as more cost-effective than models such as GPT-4, specific pricing details are not provided 11011.
Mistral Medium has a 32K-token context window.
Mistral Medium input tokens at $0.4/1M, output at $2/1M.
Capabilities
Providers(2)
Compare all →| Provider | Input (per 1M) | Output (per 1M) | Type | |
|---|---|---|---|---|
| Mistral AI Studio | $2.7 | $8.1 | Serverless | |
| OpenRouter | $0.4 | $2 | Serverless |
Benchmark Scores(4)
| Benchmark | Score | Version | Source |
|---|---|---|---|
| Google-Proof Q&A | 58.9 | diamond | research |
| HellaSwag | 93.9 | 10-shot | research |
| HumanEval | 84.3 | pass@1 | research |
| Massive Multitask Language Understanding | 82.9 | 5-shot | research |
