Provider: Baseten

Use Respan Gateway to call Baseten-hosted models (DeepSeek, Llama, Qwen, and other open-source deployments) 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 openai import OpenAI
2
3
client = OpenAI(
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="baseten/deepseek-ai/DeepSeek-V3",
10
    messages=[{"role": "user", "content": "Hello, Baseten!"}],
11
)
12
print(response.choices[0].message.content)

More integrations

Baseten models work with every Respan gateway integration:

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

Switch models

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

1
client.chat.completions.create(model="baseten/deepseek-ai/DeepSeek-V3", messages=messages)
2
client.chat.completions.create(model="baseten/meta-llama/Llama-3.3-70B-Instruct", messages=messages)
3
client.chat.completions.create(model="baseten/Qwen/Qwen3-235B-A22B", 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 Baseten key (BYOK)

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

Override credentials per model (Optional)

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

1
{
2
  "customer_credentials": {
3
    "baseten": { "api_key": "YOUR_BASETEN_API_KEY" }
4
  },
5
  "credential_override": {
6
    "baseten/deepseek-ai/DeepSeek-V3": { "api_key": "ANOTHER_BASETEN_API_KEY" }
7
  }
8
}

Log without proxying (Optional)

Already calling Baseten 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": "baseten/deepseek-ai/DeepSeek-V3",
11
        "prompt_messages": [{"role": "user", "content": "Hello, how are you?"}],
12
        "completion_message": {"role": "assistant", "content": "Hello from Baseten 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.