Zed

Code editor · OpenAI Chat, OpenAI Responses, Anthropic Messages

Full guide

Format	Where to set it up
OpenAI Chat, OpenAI Responses, Anthropic Messages	Agent Settings (agent::OpenSettings) → LLM Providers → Add Provider, or settings.json → language_models.openai_compatible / language_models.anthropic_compatible. Set the key in the settings window, where it is stored in the system keychain, or through <PROVIDER_ID_UPPERCASE>_API_KEY.

Setup

Copy the configuration and replace sk-... with your key from the Ailoot Dashboard. Prefer storing the key in the environment variable AILOOT_API_KEY, if the application supports it.

Before starting, request GET /v1/models with your Ailoot key. Choose an exact model ID whose methods include POST /v1/chat/completions, POST /v1/responses, POST /v1/messages, then use that ID in the configuration. For agents, also check tool support and the features required by your client version.

{
  "language_models": {
    "openai_compatible": {
      "ailoot": {
        "api_url": "https://api.ailoot.ai/v1",
        "available_models": [
          {
            "name": "gpt-6.1-sol",
            "display_name": "GPT-6.1 Sol (Ailoot)",
            "max_tokens": 272000,
            "capabilities": {
              "tools": true,
              "images": false,
              "chat_completions": true
            }
          },
          {
            "name": "deepseek-v4-pro",
            "display_name": "DeepSeek V4 Pro (Ailoot)",
            "max_tokens": 128000
          }
        ]
      }
    },
    "anthropic_compatible": {
      "ailoot-claude": {
        "api_url": "https://api.ailoot.ai",
        "available_models": [
          {
            "name": "claude-sonnet-5-5",
            "display_name": "Claude Sonnet 5.5 (Ailoot)",
            "max_tokens": 200000,
            "capabilities": {
              "tools": true,
              "images": false,
              "prompt_caching": false
            }
          }
        ]
      }
    }
  }
}

export AILOOT_API_KEY="sk-..."
export AILOOT_CLAUDE_API_KEY="$AILOOT_API_KEY"

Example model: gpt-6.1-sol. Choose any other model from the catalog — check that it supports the format you need.

Good to know

openai_compatible uses a URL with /v1 and calls /v1/chat/completions; capabilities.chat_completions = false switches the model to /v1/responses. anthropic_compatible uses a URL without /v1 and calls /v1/messages; Zed sends x-api-key, which Ailoot accepts. images = false and parallel_tool_calls = false by default. Zed can send images, but enable images only for a specific model whose current catalog card declares image input in the selected API format. The GPT and Claude examples use images = false: the 2026-09-30 snapshot lists text only for them. For example, gemini-3.6-flash declares image input for OpenAI Chat in that snapshot; actual support depends on the model card and format. Reasoning models have a reasoning_effort field. The example’s max_tokens values represent context size; check exact limits in the model catalog.

Test

For the OpenAI format, the URL is https://api.ailoot.ai/v1 (or the full path if the application asks for a full URL).
For the Anthropic format, the URL is https://api.ailoot.ai without /v1.
Ask a short question. If you get an error, check the code and Request ID, then consult Errors and limits.
404 immediately after setup almost always means the URL is wrong: an extra or missing /v1.
402 — insufficient balance for the reserve. Agents reserve more than chat: why.

Application documentation: https://zed.dev/docs/ai/use-api-access

Still have questions? Send your Request ID and a description — we'll help you troubleshoot.Contact support