Setup guide - Documented by Goose
Use Kimi in Goose
goose ships a built-in declarative Moonshot provider, defined in the official block/goose repo. It reads MOONSHOT_API_KEY, takes an optional MOONSHOT_BASE_URL, and lists kimi-k3 (1,048,576 context), kimi-k2.7-code, kimi-k2.7-code-highspeed and kimi-k2.6. You set it up through the documented goose configure > Configure Providers flow.
Last verified 5 steps4 official sources
Steps
- Step 1.
Run goose configure.
Terminalgoose configure - Step 2.
Select Configure Providers from the menu and press Enter.
- Step 3.
Choose the Moonshot provider. Use the arrow keys to move through the options, or start typing to filter the list.
- Step 4.
Enter your MOONSHOT_API_KEY when prompted. For MOONSHOT_BASE_URL, the provider definition says: "Use https://api.moonshot.ai/v1 for international access outside China Mainland."
Snippethttps://api.moonshot.ai/v1 - Step 5.
Select kimi-k3 from the model list. The change takes effect the next time you start a session.
Caveats
- The Moonshot provider, its env vars and its model list come from crates/goose-providers/src/declarative/definitions/moonshot.json in the official block/goose repo (read 2026-10-17). The goose docs provider table does not list Moonshot; the configure flow is the documented generic one.
- MOONSHOT_BASE_URL defaults to https://api.moonshot.cn/v1/chat/completions (China endpoint). Kimi's docs say platform.kimi.ai keys only work with api.moonshot.ai, so international users must override it. The definition suggests https://api.moonshot.ai/v1; we did not test whether goose also needs the /chat/completions suffix there.
- The bundled list also includes discontinued ids (kimi-k2-0711-preview, kimi-k2-0905-preview, kimi-k2-thinking, kimi-k2-thinking-turbo, kimi-k2-turbo-preview, kimi-k2.5). Do not pick these.
- Per the goose docs, goose configure does not support entering custom model names; edit GOOSE_MODEL in config.yaml for models not in the list.
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 Goose?
goose ships a built-in declarative Moonshot provider, defined in the official block/goose repo. It reads MOONSHOT_API_KEY, takes an optional MOONSHOT_BASE_URL, and lists kimi-k3 (1,048,576 context), kimi-k2.7-code, kimi-k2.7-code-highspeed and kimi-k2.6. You set it up through the documented goose configure > Configure Providers flow.
Which Kimi model ids work in Goose?
The official docs read for this guide list kimi-k3, kimi-k2.7-code, kimi-k2.7-code-highspeed and kimi-k2.6. Requests go to https://api.moonshot.ai/v1.
Is this an official Kimi and Goose setup?
Goose 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.
- github.comhttps://github.com/block/goose/blob/main/crates/goose-providers/src/declarative/definitions/moonshot.json
- goose-docs.aihttps://goose-docs.ai/docs/getting-started/providers/
- platform.kimi.aihttps://platform.kimi.ai/docs/guide/codex-kimi.md
- 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.