Integration
Zed with an OpenAI-compatible API
Zed can talk to OpenAI-compatible providers through its language model settings. The values are the same as everywhere else: base URL, key, model ID.
Updated
Configuration
Add an OpenAI-compatible provider in Zed's settings with api_url https://llmcode.io/v1 and your LLMcode key.
Register the published profile as a model. Exact setting keys differ between Zed versions; keep the base URL and model slug identical to the catalog.
Workflow
Use the assistant panel for chat and inline edits. A dedicated key with a spend limit keeps editor usage separate from backend usage.
If a model is missing from the picker, re-open the assistant after changing settings.
Troubleshooting
A 401 points to the key; a 404 usually means the base URL is wrong (for example a missing or duplicated /v1).
Run GET /v1/models with the same key to confirm the model slug before editing settings.
Connect
Provider type: OpenAI Compatible
Base URL: https://llmcode.io/v1
API key: sk-llmcode-…
Model: flashPublished model prices
USD per 1M tokens. The numbers come from the public catalog on every page rebuild — this is the sale price, not an estimate.
| Model | Input | Output | Cache |
|---|---|---|---|
| Claude Opus 5.5 | $2.70 | $8.00 | $0.14 |
| DeepSeek Flash | $0.50 | $2.00 | $0.01 |
| Claude Sonnet 5.5 | $1.33 | $6.67 | $0.07 |
| DeepSeek V4 Pro | $2.20 | $6.60 | $0.07 |
Top-up from $10, balance in USD. 1 USD = 1,000,000 UT. No subscription and no auto-charge.
Questions
Is Zed's configuration stable?
The OpenAI-compatible settings have changed across versions. Verify field names against your Zed release.
Can I use streaming?
Chat streaming is supported by the API; whether Zed uses it depends on the client.
Can I share one key between Zed and my server?
You can, but separate keys with limits are safer and make the journal easier to read.