Use the OpenAI SDK with Router One Chat Completions
The official OpenAI SDK can send Chat Completions requests to Router One using a custom base URL and key. Keep client.chat.completions.create for this guide, choose a model supporting that endpoint, and verify any streaming or tool features you use. client.responses.create is a separate API with its own model and feature requirements. Each gateway request has a cost trace.
Configure OpenAI SDK to use the Router One base URL
Python and JS/TS both take the base URL in the client constructor:
from openai import OpenAI
client = OpenAI(
base_url="https://api.router.one/v1",
api_key="sk-your-router-one-key",
)
resp = client.chat.completions.create(
model="<model-id-from-/models>",
messages=[{"role": "user", "content": "Hello!"}],
)
# JS/TS: new OpenAI({ baseURL, apiKey }) — same two argumentsWhich model ID should OpenAI SDK send?
Copy the exact model ID from /models, preserving case, hyphens, and version suffixes; do not substitute a display name. Open its detail page and match the supported API endpoints, context window, and capabilities such as tool calling to the provider and features selected in OpenAI SDK. A catalog listing does not mean the client can use every feature of that model. Give each tool a dedicated API key with a maxSpend cap.
Which API protocol is OpenAI SDK using?
OpenAI-compatible describes an interface format; it does not make Chat Completions (/v1/chat/completions), Responses (/v1/responses), and Anthropic Messages (/v1/messages) interchangeable. Check the installed client version, provider configuration, and actual request path against the model detail page and API compatibility fact sheet. A successful plain-text chat does not establish support for hosted tools, conversation state, or file-editing features.
Verify the OpenAI SDK call in your request trace
Send a simple text request from OpenAI SDK, then match its trace in Dashboard → Logs by time, model, and request_id: tokens, cost, latency, and status. Next, test streaming, tool calls, and multi-turn history separately. For failures, retain the actual request path, full error message, and request_id. If there is no matching log, check client configuration and connectivity before attributing the error to the gateway or upstream.
FAQ
Do I need to change any request code?
For a supported Chat Completions request, configure the gateway base URL and key and copy the exact model ID. Check optional parameters, tools, and multimodal inputs against that model's support. Code using client.responses.create, hosted tools, or previous_response_id needs the separate Responses compatibility check; the shared SDK does not make the endpoints interchangeable.
Which models can OpenAI SDK use through the gateway?
Choose a current catalog model that supports both the endpoint and the features OpenAI SDK uses. Check /models and the model detail page for the exact ID, current rates, and capabilities; a family name such as GPT or Claude is not a compatibility guarantee. Seeing a model in the picker confirms discovery, so verify an actual request too.
Models are listed, but requests fail with 400 or 404. What should I check?
Record the actual request path and error message, then check the exact model ID. A 400 can indicate invalid parameters, unsupported tools, or a model/endpoint mismatch; a 404 can indicate an incorrect path or missing resource, so it does not by itself establish that a model was retired. If the error says must be called via, use the named endpoint or select a model supported on the current endpoint. Do not add or remove /v1 or /chat/completions across all clients indiscriminately.
Does this work from Mainland China?
Yes. The gateway is reachable from Mainland China without a VPN, and the configuration is identical to the global setup.
How do I debug a 401/402/403/429?
Match the request and error message in Dashboard → Logs. For 401, check whether the key was sent and is valid; for 402, check wallet balance and maxSpend; for 403, check key permissions and access restrictions. For 429, distinguish request/token limits from upstream throttling using the error details. Keep the request_id and follow the error-codes reference.