Mistral AI SDK

Drop-in replacement for mistralai.Mistral with automatic telemetry on chat completions.

from weflayr.sdk.mistralai.client import Mistral

Client

Class	Replaces	Mode
`Mistral`	`mistralai.Mistral`	Sync + async

Constructor parameters

Parameter	Env var	Description
`api_key`	—	Your Mistral API key
`intake_url`	`WEFLAYR_INTAKE_URL`	Weflayr intake base URL
`client_id`	`WEFLAYR_CLIENT_ID`	Your Flare client ID
`bearer_token`	`WEFLAYR_CLIENT_SECRET`	Your Flare client secret

Coverage

2 covered

9 not covered

11 total endpoints

Endpoint	Accessor	Sync	Async	Stream	Billing metrics	Notes
`complete()` covered	client.chat	✓	—	—	prompt_tokens, completion_tokens	Synchronous chat completion
`complete_async()` covered	client.chat	—	✓	—	prompt_tokens, completion_tokens	Async chat completion via `await`
`stream()` not covered	client.chat	—	—	✓	—	Streaming chat not yet instrumented
`stream_async()` not covered	client.chat	—	✓	✓	—	Async streaming chat not yet instrumented
`create()` not covered	client.embeddings	—	—	—	—	Not yet instrumented
`create_async()` not covered	client.embeddings	—	—	—	—	Not yet instrumented
`complete()` not covered	client.fim	—	—	—	—	Code completion endpoint — not yet instrumented
`complete_async()` not covered	client.fim	—	—	—	—	Not yet instrumented
`complete()` not covered	client.agents	—	—	—	—	Agentic completion — not yet instrumented
`upload / list / delete` not covered	client.files	—	—	—	—	File management — not yet instrumented
`jobs.create()` not covered	client.fine_tuning	—	—	—	—	Not yet instrumented

Examples

Synchronous chat

from weflayr.sdk.mistralai.client import Mistral

client = Mistral(api_key="...")

response = client.chat.complete(
    model="mistral-small-latest",
    messages=[{"role": "user", "content": "Hello!"}],
    tags={"feature": "chat-widget"},
)
print(response.choices[0].message.content)

Async chat

import asyncio
from weflayr.sdk.mistralai.client import Mistral

client = Mistral(api_key="...")

async def main():
    response = await client.chat.complete_async(
        model="mistral-large-latest",
        messages=[{"role": "user", "content": "What is AI?"}],
        tags={"customer_tier": "enterprise"},
    )
    print(response.choices[0].message.content)

asyncio.run(main())