Requesty
Mistral AI SAS logo

Mistral AI SAS

French AI company focused on efficient and powerful language models. Requesty routes to 12 Mistral AI SAS models starting at $0.10 per 1M input tokens with context windows up to 256K tokens. One API key, OpenAI-compatible SDK, no markup.

MMLU Pro
60.1%
HumanEval
30.5%

All Mistral AI SAS models

ModelContextMax OutputInput/1MOutput/1MCapabilitiesSWE-Bench
mistral-small-latest
256K$0.15$0.60
👁🧠🔧
mistral-small-2603
256K$0.15$0.60
👁🧠🔧
devstral-latest
256K$0.40$2.00
🔧
devstral-small-latest
131K$0.10$0.30
🔧
devstral-small-2507
131K$0.10$0.30
🔧
mistral-medium-latest
131K$0.40$2.00
🔧
devstral-medium-2507
131K$0.40$2.00
🔧
codestral-latest
131K$0.30$0.90
🔧
pixtral-large-latest
131K$2.00$5.00
🔧
mistral-small-2503
33K$0.10$0.30
🔧
open-mistral-7b
33K$0.25$0.25
🔧
mistral-large-latest
131K$0.50$1.50
🔧

About Mistral AI SAS on Requesty

How many Mistral AI SAS models are available through Requesty?
Requesty routes to 12 Mistral AI SAS models including regional variants, with pricing synced in real time to the upstream provider.
What is the cheapest Mistral AI SAS model?
The cheapest Mistral AI SAS model starts at $0.10 per million input tokens. See the pricing column in the table below for full per-model rates.
Does Requesty add markup on Mistral AI SAS pricing?
No. Requesty passes through exactly what Mistral AI SAS charges. You pay the same per-token rates as going direct — plus you get smart routing, caching, analytics, and one unified API for 400+ models.
Is my data used to train Mistral AI SAS models?
Mistral AI SAS's terms state that API data is not used for training. See their privacy policy for the authoritative statement.
Where are Mistral AI SAS models hosted?
Mistral AI SAS models are hosted in 🇪🇺 EU. Some models are available in additional regions through AWS Bedrock, Azure, or Google Vertex AI — filter by region on the Mistral AI SAS rows in the models explorer.