Setup guide - Documented by Kilo Code
Use Kimi in Kilo Code
Kilo Code documents a built-in Moonshot provider. In VS Code you add it from Settings > Providers; in the CLI you set MOONSHOT_API_KEY and configure the moonshotai provider in kilo.json. Kimi model ids get a Kimi-tuned system prompt automatically.
Last verified 4 steps4 official sources
Steps
- Step 1.
VS Code: open Settings (gear icon), go to the Providers tab, add Moonshot.ai and enter your API key. The extension stores this in your kilo.json config file.
- Step 2.
CLI: set the API key as an environment variable.
Terminalexport MOONSHOT_API_KEY="your-api-key" - Step 3.
Or configure it in ~/.config/kilo/kilo.json or ./kilo.json.
JSON{ "provider": { "moonshotai": { "env": ["MOONSHOT_API_KEY"], }, }, } - Step 4.
Then set your default model. Kilo's docs example uses moonshotai/moonshot-v1-auto, which is discontinued; use the current Kimi K3 id instead.
JSON{ "model": "moonshotai/kimi-k3", }
Caveats
- Kilo's docs example model moonshotai/moonshot-v1-auto was discontinued on August 31, 2026. moonshotai/kimi-k3 combines Kilo's documented provider/model format with the kimi-k3 entry in the moonshotai provider of the models.dev registry (sst/models.dev). Moonshot's model list confirms kimi-k3 as the current id.
- Kilo's page still describes K2-Thinking and 200K context and links platform.moonshot.cn. Moonshot's docs say platform.kimi.ai keys only work with https://api.moonshot.ai/v1; the base URL above comes from the models.dev moonshotai provider.
- Kilo automatically uses a Kimi-tuned system prompt for model IDs containing kimi.
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 Kilo Code?
Kilo Code documents a built-in Moonshot provider. In VS Code you add it from Settings > Providers; in the CLI you set MOONSHOT_API_KEY and configure the moonshotai provider in kilo.json. Kimi model ids get a Kimi-tuned system prompt automatically.
Which Kimi model ids work in Kilo Code?
The official docs read for this guide list moonshotai/kimi-k3, moonshotai/kimi-k2.7-code and moonshotai/kimi-k2.6. Requests go to https://api.moonshot.ai/v1.
Is this an official Kimi and Kilo Code setup?
Kilo Code documents this setup in its own docs. It was last checked against 4 official pages on October 17, 2026.
Sources
Last verified against 4 official pages.
- kilo.aihttps://kilo.ai/docs/ai-providers/moonshot
- raw.githubusercontent.comhttps://raw.githubusercontent.com/sst/models.dev/dev/providers/moonshotai/provider.toml
- raw.githubusercontent.comhttps://raw.githubusercontent.com/sst/models.dev/dev/providers/moonshotai/models/kimi-k3.toml
- platform.kimi.aihttps://platform.kimi.ai/docs/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.