Mistral AI

Name: Mistral AI
Rating: 5.0 (70 reviews)

Mistral AI API provides access to frontier AI models including Mistral Large, Medium, Small, and Codestral for chat, code, and embeddings.

Categories

Mistral AI offers 11 LLM API models.

Speed benchmark average: 132 tok/s.

Avg Speed132.21 tok/s

Latency0.53 s

Total Tests70

Models11

Updated4/16/2026

Created At12/10/2025

Supported Models

Model	Speed	Latency	Tests
ministral-3b-2410	271.53 tok/s	0.45s	10
open-mistral-nemo	200.44 tok/s	0.40s	5
magistral-small-latest	189.91 tok/s	0.39s	5
mistral-tiny-latest	155.43 tok/s	0.38s	5
codestral-latest	151.00 tok/s	0.38s	5
ministral-14b-latest	129.12 tok/s	0.46s	5
mistral-medium	99.70 tok/s	0.35s	5
mistral-medium-latest	82.38 tok/s	0.41s	10
mistral-small-latest	74.79 tok/s	0.33s	5
mistral-large-latest	48.72 tok/s	1.19s	10
mistral-large-2411	45.26 tok/s	0.58s	5