Skip to navigation
ModelsMore providers

Provider: Mistral AI

Call Mistral AI models through Respan Gateway with unified logs, cost, and latency.
This page is for Respan LLM Gateway users.

Use Respan Gateway to call Mistral models (mistral/mistral-medium-3-5, mistral/mistral-small-2603, mistral/ministral-14b-2512, and the rest) while keeping unified observability (logs, cost, latency, reliability) in Respan.

Mistral AI requires bring your own key (BYOK). Provider usage cannot be paid with Respan credits.

Quick setup

1

Get a Respan API key

Sign up and create a key on the API keys page.

2

Add your Mistral AI credentials

Configure your Mistral AI credentials on the Providers page before using the examples below. See Use your own Mistral AI key.

Send your first request

After configuring your Mistral AI credentials in Respan, pick the integration that matches your stack. The base URL is https://api.respan.ai/api and your application authenticates with RESPAN_API_KEY.

Point the official Mistral SDK at the Respan gateway by overriding server_url (Python) / serverURL (TypeScript).

from mistralai import Mistral
client = Mistral(
    api_key="YOUR_RESPAN_API_KEY",
    server_url="https://api.respan.ai/api",
)
response = client.chat.complete(
    model="mistral/mistral-medium-3-5",
    messages=[{"role": "user", "content": "Hello, Mistral!"}],
)
print(response.choices[0].message.content)

More integrations

Mistral models work with every Respan gateway integration:

Switch models

Change the model parameter to call any supported model through the same client. Use the mistral/ prefix to disambiguate when routing across providers. Browse the full list on the Models page.

client.chat.completions.create(model="mistral/mistral-medium-3-5", messages=messages)
client.chat.completions.create(model="mistral/mistral-small-2603", messages=messages)
client.chat.completions.create(model="mistral/ministral-14b-2512", messages=messages)
client.chat.completions.create(model="openai/gpt-6-sol", messages=messages)
client.chat.completions.create(model="anthropic/claude-opus-5-5", messages=messages)

Use your own Mistral AI key (BYOK)

Mistral AI credentials are required. Configure them in Respan or pass them with each request using one of the options below.

1

Open Providers

Go to the Providers page.

2

Add Mistral

Select Mistral and paste your mistral.api_key.

3

Load balancing (Optional)

Add multiple credential sets and use Load balancing weight to distribute traffic across them.

Override credentials per model (Optional)

Use credential_override when one model on a request should use a different Mistral key than the default.

{
  "customer_credentials": {
    "mistral": { "api_key": "YOUR_MISTRAL_API_KEY" }
  },
  "credential_override": {
    "mistral/mistral-medium-3-5": { "api_key": "ANOTHER_MISTRAL_API_KEY" }
  }
}

Log without proxying (Optional)

Already calling Mistral directly? Send logs to Respan asynchronously to track cost, latency, and performance for those external calls.

import requests
requests.post(
    "https://api.respan.ai/api/request-logs/create/",
    headers={
        "Authorization": "Bearer YOUR_RESPAN_API_KEY",
        "Content-Type": "application/json",
    },
    json={
        "model": "mistral/mistral-medium-3-5",
        "prompt_messages": [{"role": "user", "content": "Hello, how are you?"}],
        "completion_message": {"role": "assistant", "content": "Hello from Mistral through Respan."},
        "cost": 0.001,
        "generation_time": 1.2,
        "customer_params": {"customer_identifier": "user_123"},
    },
)

See the logging guide for the full setup.