Skip to main content
Integrations · Moonshot AI
Guild agents call Moonshot AI’s Kimi models through task.llm, using a credential for AWS Bedrock, OpenRouter, or Fireworks AI. Guild holds the credential server-side, checks your model policies on every call, and attributes spend to the workspace, agent, and user that made it.

Book a demo

See how teams govern agents that use Moonshot AI.

Start free

Connect Moonshot AI and scope your first agent.

​
Kimi through the provider you already run

Kimi models reach Guild only through third-party inference providers. kimi-k3 is on Bedrock in all four supported US regions and on Fireworks AI. The default, kimi-k2.5, and the reasoning model kimi-k2-thinking are on Bedrock outside us-west-1. OpenRouter serves its moonshotai/ namespace.

​
How it works

1

Add a credential

In Access & setup > Models & providers, click Add API key and choose AWS Bedrock, OpenRouter, or Fireworks AI. Check Moonshot AI under Models.
2

Write a model policy

Bind the credential’s Moonshot AI access to the account, a workspace, or an agent, and list the models it may call, such as kimi-*.
3

Call it from task.llm

Name "moonshot" in llmPreferences, or leave preferences out and let your policies choose. Guild resolves the credential at runtime.

​
Every Kimi call goes through your policies

Agents never hold the key. Guild stores the credential server-side and shows only a masked value, so you can rotate it without touching agent code or the model policies bound to it. Policies are an allowlist: a workspace, agent, or installed agent can call a Kimi model only if a rule allows it. Set a daily token limit to cap spend, and see each call by workspace, agent, and user in Usage. A raw API key in an agent’s environment reaches every model the key can. A policy reaches only the models you name.

​
About Moonshot AI models on Guild

​
Inference providers

Moonshot AI models are served only through third-party inference providers, not a Moonshot AI API. Write the canonical model name, such as kimi-k2.5, everywhere in Guild. Guild maps it to each provider’s own model ID.

​
Models

Guild prices and recognizes these Moonshot AI model IDs. A policy or preference can also name any other model your credential can reach. Third-party providers route more models than this list, and their catalogs change; see each provider’s page for what it serves.

​
Set up Moonshot AI

Guild has no managed key for Moonshot AI. To use Moonshot AI models, add a credential for a provider that serves them. Adding your first credential switches the whole account to bring your own key (BYOK).
1

Open Models & providers

Click Access & setup in the left nav, then Models & providers. In an organization, only admins can open it.
2

Add a credential

Click Add API key and choose an inference provider from the table above.
3

Enter the provider's secret

Give the credential a Name and paste your provider’s API key. AWS Bedrock asks for an IAM role and region instead.
4

Choose Moonshot AI

Under Models, check Moonshot AI. Keep kimi-k2.5 as its default model or enter another from the list above. Then click Add Key. On Fireworks AI, pick a model from its list, because the pre-filled default isn’t available there.
To control which workspaces and agents can use Moonshot AI models, add a model policy for the credential. For example, --models "kimi-*" limits a policy to matching models:

​
Use it from an agent

Agent code never names a credential. Guild resolves the call against the workspace owner’s settings. To ask for Moonshot AI explicitly, put it in llmPreferences:
The first entry asks for kimi-k2-thinking. The second falls back to the default model of the matching policy. Preferences are strict: if no credential or policy allows any of them, the call fails rather than using another publisher. See LLM preferences.
The "moonshot" provider value needs @guildai/agents-sdk 0.7.6 or later.

​
Frequently asked questions

No. Guild has no managed key for Moonshot AI. Add a credential for a provider that serves it, which switches the account to bring your own key (BYOK).
No. Guild serves Kimi models only through AWS Bedrock, OpenRouter, and Fireworks AI.
No. kimi-k3 is in all four supported US regions. kimi-k2.5 and kimi-k2-thinking aren’t in us-west-1.
@guildai/agents-sdk 0.7.6 or later, for the "moonshot" provider value in llmPreferences.

​
Put a governed agent on Moonshot AI this week

Book a demo

See how teams govern agents that use Moonshot AI.

Start free

Connect Moonshot AI and scope your first agent.
Also runs on Guild: DeepSeek · Z.ai · AWS Bedrock · Fireworks AI Read: Docs: Models & providers · LLMs · Usage
Last modified on October 20, 2026