Mistral AI — awesome-ai-stack

Overview

Mistral AI is a European foundation-model lab known for releasing strong open-weight models (Mistral, Mixtral, Codestral) alongside its hosted API, La Plateforme.
The API is OpenAI-shaped and has a free experimentation tier, while the open-weight models can be downloaded and self-hosted.

flowchart LR
  prompt[prompt] --> api[(La Plateforme)]
  api --> resp[completion]
  weights[open weights] --> self[self-host option]

The Code samples tab shows a LiteLLM-routed call.

When to use it

Choose Mistral when you want a cost-effective frontier alternative with EU data residency, or when the flexibility to self-host the same family of open-weight models matters.

Pricing

Free Experiment tier on La Plateforme. Paid is pay-as-you-go per token; rates vary by model (per million tokens).

Plan	Price	Notes
Experiment	$0	Free, rate-limited
Pay-as-you-go	~$0.04–$6 / M	Varies by model size

Source ↗ · as of 2026-06-27

Example

Python · via LiteLLM

When to use

Reach for Mistral when you want competitive quality at low cost, EU data residency, or the option to self-host its open-weight models.

from litellm import completion

# MISTRAL_API_KEY in the environment (La Plateforme has a free tier).
resp = completion(
    model="mistral/mistral-large-latest",
    messages=[{"role": "user", "content": "Say hello in one short sentence."}],
)
print(resp.choices[0].message.content)

Related tools

Overview

When to use it

Pricing

When to use