Provider: Cerebras

Use Respan Gateway to call Cerebras models (llama-3.3-70b, llama-3.1-8b, gpt-oss-120b, and the rest) while keeping unified observability (logs, cost, latency, reliability) in Respan.

Quick setup

Send your first request

Pick the integration that matches your stack. The base URL is https://api.respan.ai/api and the only key needed is your RESPAN_API_KEY.

1
from cerebras.cloud.sdk import Cerebras
2
3
client = Cerebras(
4
    api_key="YOUR_RESPAN_API_KEY",
5
    base_url="https://api.respan.ai/api",
6
)
7
8
response = client.chat.completions.create(
9
    model="llama-3.3-70b",
10
    messages=[{"role": "user", "content": "Hello, Cerebras!"}],
11
)
12
print(response.choices[0].message.content)

More integrations

Cerebras models work with every Respan gateway integration:

• OpenAI SDK
• OpenAI Agents SDK
• LangChain
• LlamaIndex
• Pydantic AI
• Respan native (OTel)

Switch models

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

1
client.chat.completions.create(model="cerebras/llama-3.3-70b", messages=messages)
2
client.chat.completions.create(model="cerebras/llama-3.1-8b", messages=messages)
3
client.chat.completions.create(model="cerebras/gpt-oss-120b", messages=messages)
4
client.chat.completions.create(model="openai/gpt-5.5", messages=messages)
5
client.chat.completions.create(model="anthropic/claude-sonnet-4-5", messages=messages)

Use your own Cerebras key (BYOK)

Credits are the default path. If you’d rather bill Cerebras directly, attach your own provider key.

Override credentials per model (Optional)

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

1
{
2
  "customer_credentials": {
3
    "cerebras": { "api_key": "YOUR_CEREBRAS_API_KEY" }
4
  },
5
  "credential_override": {
6
    "cerebras/gpt-oss-120b": { "api_key": "ANOTHER_CEREBRAS_API_KEY" }
7
  }
8
}

Log without proxying (Optional)

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

1
import requests
2
3
requests.post(
4
    "https://api.respan.ai/api/request-logs/create/",
5
    headers={
6
        "Authorization": "Bearer YOUR_RESPAN_API_KEY",
7
        "Content-Type": "application/json",
8
    },
9
    json={
10
        "model": "cerebras/llama-3.3-70b",
11
        "prompt_messages": [{"role": "user", "content": "Hello, how are you?"}],
12
        "completion_message": {"role": "assistant", "content": "Hello from Cerebras through Respan."},
13
        "cost": 0.001,
14
        "generation_time": 1.2,
15
        "customer_params": {"customer_identifier": "user_123"},
16
    },
17
)

See the logging guide for the full setup.