Add Router One models to Zed's Agent Panel
Zed is a fast, Rust-built code editor with a native Agent Panel, and it takes custom OpenAI-compatible providers straight from settings.json. Registering Router One once puts GPT, Claude, Gemini, and Grok family models in Zed's model picker behind a single key — and every agent turn gets a per-request cost trace on the gateway, so long agentic sessions stop being a billing black box.
Configure Zed to use the Router One base URL
Add an openai_compatible block under language_models in settings.json (run "zed: open settings"), listing each model you want in the picker — set max_tokens to the context window shown on /models. The API key never lives in settings.json: Zed asks for it in the Agent Panel's provider settings, or reads the ROUTER_ONE_API_KEY environment variable:
{
"language_models": {
"openai_compatible": {
"router-one": {
"api_url": "https://api.router.one/v1",
"available_models": [
{
"name": "<model-id-from-/models>",
"display_name": "<label shown in the picker>",
"max_tokens": 1000000
}
]
}
}
}
}Which model ID should Zed 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 Zed. 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 Zed 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 Zed call in your request trace
Send a simple text request from Zed, 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
Why is there no api_key field in Zed's settings.json?
By design — Zed keeps credentials out of settings.json. After adding the provider block, open the Agent Panel's settings and paste your key under the router-one provider, or export ROUTER_ONE_API_KEY (Zed derives the variable name from the provider id) before launching the editor.
Which models can Zed use through the gateway?
Choose a current catalog model that supports both the endpoint and the features Zed 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.