Model library / Mistral AI / Mixtral 8x7B Instruct

Mixtral 8x7B Instruct

LLM TRT-LLM H100

An LLM with a mixture of experts architecture for efficient inference on general chat tasks.

Deploy Mixtral 8x7B Instruct behind an API endpoint in seconds.

Deploy model

Example usage

Mistral uses the standard llama-style multi-turn messaging framework with system and user prompts.

Input

1import requests
2
3# Replace the empty string with your model id below
4model_id = ""
5baseten_api_key = os.environ["BASETEN_API_KEY"]
6
7data = {
8    "messages": [
9        {"role": "system", "content": "You are a knowledgable, engaging, geology teacher."},
10        {"role": "user", "content": "What is the impact of the Mistral wind on the French climate?"},
11    ]
12    "stream": True,
13    "max_new_tokens": 512,
14    "temperature": 0.9
15}
16
17# Call model endpoint
18res = requests.post(
19    f"https://model-{model_id}.api.baseten.co/production/predict",
20    headers={"Authorization": f"Api-Key {baseten_api_key}"},
21    json=data,
22    stream=True
23)
24
25# Print the generated tokens as they get streamed
26for content in res.iter_content():
27    print(content.decode("utf-8"), end="", flush=True)

JSON output

1[
2    "streaming",
3    "output",
4    "text"
5]

Example usage

Deploy any model in just a few commands