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
- 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.
- 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 } } ] } } } } - 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.
Terminalexport 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.
More setup guides
Same tool, other providers
Related reading
- Kimi K3 Is GA in GitHub Copilot: Pricing, Rollout, and What It Means for Model ChoiceKimi K3 is GA in GitHub Copilot at $3/$15 per million tokens, off by default for Business and Enterprise. Rollout details and what it means for model choice.
- Cloudflare Runs Kimi and GLM at Scale: FP8 KV Caches, INT4 Weights, and a Cache Safety NetCloudflare runs Kimi K2.6 and GLM 5.2 on Workers AI with FP8 KV caches, INT4 weights and a KV cache integrity check. What each technique buys on GPU fleets.
- AMD MI355X vs NVIDIA B200 vs B300 for Open-Weight ServingAMD MI355X vs NVIDIA B200 vs B300 for serving Kimi K3's about 1.5TB of open weights: verified specs, the Wafer benchmark, and cost per token for each.
- Kimi Linear: An Attention Architecture That Outperforms Full AttentionKimi Linear explained: Moonshot's KDA hybrid linear attention beat full attention with 75% less KV cache and up to 6x faster decoding at 1M context.
- Kimi K3 Weights Land on HuggingFace: 2.8T Open Frontier Model You Can Actually DownloadKimi K3 open weights are on HuggingFace: 2.8T parameters, 1M context, native MXFP4 and a ~1.63TB download. The specs, license terms and HN reaction.
- Kimi K3 in 10 Minutes: Moonshot AI's 2.8T Open Model, API Setup, Pricing, and BenchmarksKimi K3 from Moonshot AI is a 2.8T open model with a 1M-token context and an OpenAI-compatible API. How to call it, what it costs, and how it benchmarks.
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.
- zed.devhttps://zed.dev/docs/ai/use-api-access
- github.comhttps://github.com/zed-industries/zed/blob/main/docs/src/ai/use-api-access.md
- platform.kimi.aihttps://platform.kimi.ai/docs/api/overview.md
- platform.kimi.aihttps://platform.kimi.ai/docs/guide/codex-kimi.md
- platform.kimi.aihttps://platform.kimi.ai/docs/guide/use-thinking-models.md
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.