Provider: Baseten

Call Baseten models through Respan Gateway with unified logs, cost, and latency.

This page is for Respan LLM Gateway users.

Use Respan Gateway to call Baseten-hosted models (DeepSeek V4.1 Flash, GLM 5.3, and other deployments) while keeping unified observability (logs, cost, latency, reliability) in Respan.

Paste this into your coding agent:


Help me set up the Respan gateway to call Baseten models.
Follow https://www.respan.ai/docs/integrations/gateway/model-providers/baseten.md

Quick setup

Get a Respan API key

Add credits (recommended)

Top up credits to pay through Respan. No Baseten key required, Respan handles provider auth and billing.

Prefer to route through your own Baseten account? See Use your own Baseten key.

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.

Baseten is OpenAI-compatible. Point the OpenAI SDK at the Respan gateway and call any Baseten model.


from openai import OpenAI

client = OpenAI(
    api_key="YOUR_RESPAN_API_KEY",
    base_url="https://api.respan.ai/api",
)

response = client.chat.completions.create(
    model="baseten/deepseek-ai/DeepSeek-V4.1-Flash",
    messages=[{"role": "user", "content": "Hello, Baseten!"}],
)
print(response.choices[0].message.content)

Call respan.chat(...) explicitly to use the Gateway Chat Completions endpoint.

Use @ai-sdk/openai and point createOpenAI at the Respan gateway.


import { createOpenAI } from "@ai-sdk/openai";
import { generateText } from "ai";

const respan = createOpenAI({
  apiKey: process.env.RESPAN_API_KEY!,
  baseURL: "https://api.respan.ai/api",
});

const result = await generateText({
  model: respan.chat("baseten/deepseek-ai/DeepSeek-V4.1-Flash"),
  prompt: "Hello, Baseten!",
});
console.log(result.text);

Call the Respan REST API directly from any language.


import requests

response = requests.post(
    "https://api.respan.ai/api/chat/completions",
    headers={
        "Authorization": "Bearer YOUR_RESPAN_API_KEY",
        "Content-Type": "application/json",
    },
    json={
        "model": "baseten/deepseek-ai/DeepSeek-V4.1-Flash",
        "messages": [{"role": "user", "content": "Hello, Baseten!"}],
    },
)
print(response.json()["choices"][0]["message"]["content"])

More integrations

Baseten models work with every Respan gateway integration:

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 .


client.chat.completions.create(model="baseten/deepseek-ai/DeepSeek-V4.1-Flash", messages=messages)
client.chat.completions.create(model="baseten/zai-org/GLM-5.3-Fast", messages=messages)
client.chat.completions.create(model="baseten/zai-org/GLM-5.3", 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 Baseten key (BYOK)

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

Open Providers

Go to the Providers page .

Add Baseten

Select Baseten and paste your baseten.api_key.

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 Baseten key than the default.


{
  "customer_credentials": {
    "baseten": { "api_key": "YOUR_BASETEN_API_KEY" }
  },
  "credential_override": {
    "baseten/deepseek-ai/DeepSeek-V4.1-Flash": { "api_key": "ANOTHER_BASETEN_API_KEY" }
  }
}

Log without proxying (Optional)

Already calling Baseten 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": "baseten/deepseek-ai/DeepSeek-V4.1-Flash",
        "prompt_messages": [{"role": "user", "content": "Hello, how are you?"}],
        "completion_message": {"role": "assistant", "content": "Hello from Baseten through Respan."},
        "cost": 0.001,
        "generation_time": 1.2,
        "customer_params": {"customer_identifier": "user_123"},
    },
)

See the logging guide for the full setup.