Skip to main content
Watch: I Built an AI App Without Leaving Databricks

Setup guide - Documented by Zed

Use Kimi in Zed

Zed documents custom OpenAI-compatible providers under language_models.openai_compatible in settings.json, with an API key env var generated from the provider ID. A provider ID of moonshot pointed at Kimi's documented base URL runs kimi-k3, with interleaved reasoning_content and reasoning_effort support.

Last verified 3 steps5 official sources

Steps

  1. Step 1.

    Open Agent Settings (agent::OpenSettings), click Add Provider in the LLM Providers section, and fill in provider name, API URL (https://api.moonshot.ai/v1), model ID (kimi-k3) and context window. Or configure it in your settings file as below.

  2. Step 2.

    Add the provider to settings.json. This combines Zed's documented openai_compatible schema with Kimi's base URL, model id and 1M context window.

    JSON
    {
      "language_models": {
        "openai_compatible": {
          "moonshot": {
            "api_url": "https://api.moonshot.ai/v1",
            "available_models": [
              {
                "name": "kimi-k3",
                "display_name": "Kimi K3",
                "max_tokens": 1048576,
                "reasoning_effort": "max",
                "capabilities": {
                  "tools": true,
                  "images": false,
                  "parallel_tool_calls": false,
                  "prompt_cache_key": false,
                  "chat_completions": true,
                  "interleaved_reasoning": true,
                  "max_tokens_parameter": false
                }
              }
            ]
          }
        }
      }
    }
  3. Step 3.

    Enter the API key in the provider settings UI, or set the generated environment variable (provider ID in upper snake case plus _API_KEY). Do not put API keys in settings.json.

    Terminal
    export MOONSHOT_API_KEY=<your Kimi API key>

Caveats

  • This combines Zed's documented OpenAI-compatible provider config with Moonshot's documented base URL, model ids and 1,048,576-token K3 context window (from Kimi's Codex guide). No Zed page covers Kimi specifically.
  • interleaved_reasoning: true sends prior thinking back in reasoning_content, which Kimi's thinking-model guide asks for in multi-turn and tool-call conversations. reasoning_effort "max" matches Kimi K3's low/high/max values. We did not test this exact config.
  • images is left false, Zed's default. Kimi K3 supports image input, so set it to true if you need vision.
  • Zed also documents an Anthropic-compatible provider type, which could target https://api.moonshot.ai/anthropic instead.

FAQ

How do I use Kimi in Zed?

Zed documents custom OpenAI-compatible providers under language_models.openai_compatible in settings.json, with an API key env var generated from the provider ID. A provider ID of moonshot pointed at Kimi's documented base URL runs kimi-k3, with interleaved reasoning_content and reasoning_effort support.

Which Kimi model ids work in Zed?

The official docs read for this guide list kimi-k3, kimi-k2.7-code and kimi-k2.6. Requests go to https://api.moonshot.ai/v1.

Is this an official Kimi and Zed setup?

Zed documents this setup in its own docs. It was last checked against 5 official pages on October 17, 2026.

Sources

Last verified against 5 official pages.

Newsletter

New models, set up the day they ship

One email per week. New model releases, the coding tools that support them and how to wire them up.