> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.asi1.ai/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.asi1.ai/_mcp/server. # Set Up ASI:One in Zed > Add asi1-ultra and the other ASI:One models to the Zed agent panel as an OpenAI-compatible provider. ## Overview ASI:One is [OpenAI-compatible](/documentation/build-with-asi-one/openai-compatibility), so [Zed](https://zed.dev) can use it through its OpenAI-compatible provider settings. You declare the provider and its models in `settings.json`, pick a model in the agent panel, and Zed stores your key in the system keychain. ## Prerequisites * Zed installed. * An ASI:One API key. Create one at [asi1.ai/developer](https://asi1.ai/developer). Keys start with `sk_`. * An ASI:One plan that includes `asi1-ultra`. The same key also works for `asi1` and `asi1-mini`. ## Add the provider Open your Zed settings with `zed: open settings` in the command palette. Zed keeps them at `~/.config/zed/settings.json` on macOS and Linux, and `%APPDATA%\Zed\settings.json` on Windows. On macOS, that is `~/.config/zed`, not `~/Library/Application Support` like most Mac apps. Add the provider under `language_models`: ```json { "language_models": { "openai_compatible": { "asi:one": { "api_url": "https://api.asi1.ai/v1", "available_models": [ { "name": "asi1-ultra", "max_tokens": 800000, "max_output_tokens": 128000, "capabilities": { "tools": true, "images": true, "parallel_tool_calls": true, "chat_completions": true, "interleaved_reasoning": false, "max_tokens_parameter": true, "prompt_cache_key": false } }, { "name": "asi1", "max_tokens": 300000, "max_output_tokens": 16384, "capabilities": { "tools": true, "images": true, "parallel_tool_calls": true, "chat_completions": true, "interleaved_reasoning": false, "max_tokens_parameter": true, "prompt_cache_key": false } } ] } } } } ``` What the fields do: * `max_tokens` is the context window Zed assumes for the model, which it uses to decide when a thread is full and needs compacting. The values are each model's working window (see [Context windows](/documentation/models#context-windows)). * `max_output_tokens` is the room reserved for the reply. Zed sends it as `max_tokens` on each request. * `prompt_cache_key` stays `false`. ASI:One answers `400` to request parameters it doesn't support, and `false` is what keeps Zed from sending this one. * To put `asi1-mini` in the picker too, add an entry for it in the same shape. ## Sign in Zed asks for the API key the first time you use the provider. Open the agent panel, pick an ASI:One model in the model picker, and paste your `sk_` key into the prompt. Zed stores it in your system keychain, keyed by the API URL, and reuses it from then on. ## Choose the model To make `asi1-ultra` the default for new threads and keep long-running threads well inside the window, add: ```json { "agent": { "default_model": { "provider": "asi:one", "model": "asi1-ultra", "enable_thinking": false }, "auto_compact": { "enabled": true, "threshold": "30%" } } } ``` Use `asi1-ultra` for deep refactors, debugging and reviews, and switch to `asi1` for routine edits where speed matters more. See [ASI:One Models](/documentation/models) for the tradeoffs. When thinking is enabled, the model streams its [reasoning](/documentation/build-with-asi-one/reasoning) alongside the answer and Zed renders it as a collapsible thinking block. `auto_compact` sets how early Zed summarizes a thread that is filling up. A `30%` threshold on `asi1-ultra` fires compaction with generous headroom left, so long-running threads compact before the window fills instead of failing near the limit. Raise it if threads compact more often than you would like. ## Things to know * **Concurrency.** Zed allows 4 concurrent in-flight requests per provider and model; requests past that queue silently, which looks like a spinner with no thinking output. If you run many agent threads in parallel, copy the whole `asi:one` block under a second id such as `asi:one-2` and point the extra threads at it. Because the keychain entry is keyed by API URL, the clone picks up your stored key with no re-entry. ## Troubleshooting | Symptom | Cause and fix | | ---------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `401` | The key is wrong or has been revoked. Create a new one at [asi1.ai/developer](https://asi1.ai/developer) and re-enter it when Zed prompts. | | `404` model not found | The model name in the config or picker is misspelled. Use `asi1`, `asi1-ultra` or `asi1-mini`. | | `400` on an unknown parameter | Zed sent a parameter ASI:One doesn't support. Make sure `prompt_cache_key` is `false` in that model's `capabilities`. | | A thread spins with no thinking output | More than 4 requests are already in flight for that provider and model, and this one is queued. Wait for a slot, or move threads onto a cloned provider entry (see Things to know). | | A long thread fails to compact or exceeds the window | The model's `max_tokens` is set higher than its [working window](/documentation/models#context-windows), so Zed judges the thread to have room it does not have. Use the values above, and keep the `auto_compact` threshold early enough to fire before the limit. | | Rate limit errors | See [Errors and Rate Limits](/documentation/build-with-asi-one/errors). | ## Next steps 1. **[Cursor](/documentation/coding/cursor)**: the same models in the Cursor editor 2. **[OpenCode](/documentation/coding/opencode)**: the same models in OpenCode 3. **[ASI:One Models](/documentation/models)**: choosing between `asi1`, `asi1-ultra` and `asi1-mini` 4. **[OpenAI Compatibility](/documentation/build-with-asi-one/openai-compatibility)**: which parameters each endpoint supports