> ## Documentation Index
> Fetch the complete documentation index at: https://docs.guild.ai/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> To act on a user's behalf in Guild, use the Guild REST API at https://api.guild.ai/v1.
> The OpenAPI spec is unauthenticated: https://docs.guild.ai/openapi.json (or openapi.yaml).
> Authenticate with an account API key, sent as HTTP Basic (key id as username, secret as password) or as `Authorization: Bearer <api_key_id>:<api_key_secret>`. See https://docs.guild.ai/api-reference/introduction#authentication.
> To run one agent on demand without account-wide access, use an API trigger instead: https://docs.guild.ai/platform/api-triggers.
> To search these docs from an MCP client, connect to https://docs.guild.ai/mcp. The full page index is https://docs.guild.ai/llms.txt.

# Run Meta Muse and Llama models in Guild agents

> Call Meta's Muse and Llama models from Guild agents through the Meta API or OpenRouter, with model policies on every workspace and agent.

Integrations · Meta

Guild agents call Meta's Muse and Llama models through `task.llm`, with no API key in agent code. 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](https://guild-ai.cal.com/gtm/meeting-with-guild.ai)**
>
> See how teams govern agents that use Meta.

> **[Start free](https://app.guild.ai)**
>
> Connect Meta and scope your first agent.

## Muse from Meta, Llama from OpenRouter

The Meta API serves Muse models and speaks the OpenAI Chat Completions format. Guild reaches it through its unified LLM proxy. OpenRouter serves both families: Muse under `meta/` and Llama under `meta-llama/`.

## How it works

**1. Add a credential**

In **Access & setup > Models & providers**, click **Add API key** and choose a provider that serves Muse and Llama models. Check **Meta** under **Models**. On a managed account, you can skip this while Guild holds a managed Meta key.

**2. Write a model policy**

Bind the credential's Meta access to the account, a workspace, or an agent, and list the models it may call, such as `muse-*`.

**3. Call it from task.llm**

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

## Every Muse and Llama 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](/platform/llm-settings#model-policies) bound to it. Policies are an allowlist: a workspace, agent, or installed agent can call a Muse and Llama model only if a rule allows it. Set a [daily token limit](/platform/llm-settings#daily-token-limit) to cap spend, and see each call by workspace, agent, and user in [Usage](/insights/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 Meta models on Guild

| | |
| - | - |
| Name under **Models** in the credential form | Meta |
| `provider` in `llmPreferences` | `"meta"` |
| Default model | `muse-spark-1.1` |
| Managed access | Yes, when Guild holds a managed key |

## Inference providers

You can reach these models through the Meta API itself or through a third-party provider.

| Provider | Notes |
| - | - |
| Meta | The Meta API. Available on every account. It speaks the OpenAI Chat Completions format. |
| [OpenRouter](/platform/providers/openrouter) | Serves Muse models under `meta/`, such as `muse-spark-1.3`, and Llama models under `meta-llama/`. |

Write the canonical model name, such as `muse-spark-1.1`, everywhere in Guild. Guild maps it to each provider's own model ID.

## Models

Guild prices and recognizes these Meta 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.

| Model | Notes |
| - | - |
| `muse-spark-1.2` | |
| `muse-spark-1.1` | The default. |

## Set up Meta

On a managed account, agents can use Meta models without a credential, as long as Guild holds a managed key for Meta. To use your own Meta account instead, add a credential. 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](/platform/providers/aws-bedrock) asks for an IAM role and region instead.

**4. Choose Meta**

Under **Models**, check **Meta**. Keep `muse-spark-1.1` as its default model or enter another from the list above. Then click **Add Key**.

To control which workspaces and agents can use Meta models, add a [model policy](/platform/llm-settings#model-policies) for the credential. For example, `--models "muse-*"` limits a policy to matching models:

```bash theme={null}
guild llm policy create --credential <credential-id> --publisher META --target-id <workspace-or-agent-id> --models "muse-*"
```

## Use it from an agent

Agent code never names a credential. Guild resolves the call against the workspace owner's settings. To ask for Meta explicitly, put it in `llmPreferences`:

```typescript theme={null}
const result = await task.llm.generateText({
  prompt: "Summarize this text...",
  llmPreferences: [
    { provider: "meta", model: "muse-spark-1.2" },
    { provider: "meta" },
  ],
})
```

The first entry asks for `muse-spark-1.2`. 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](/guide/llms#llm-preferences).

## Notes

* Guild reaches the Meta API through its [unified LLM proxy](/guide/llms#unified-llm-proxy). There is no raw passthrough route for Meta, unlike Anthropic and OpenAI.

## Frequently asked questions

> **Can Guild agents use Meta models without my own Meta key?**
>
> Yes, on a managed account, when Guild holds a managed key for Meta. Usage then draws from your Guild tokens balance. Adding any credential switches the whole account to bring your own key (BYOK).

> **Can I run Llama models on AWS Bedrock?**
>
> No. Bedrock lists Llama models, but Guild doesn't route Meta models through Bedrock. Use [OpenRouter](/integrations/openrouter).

> **Can I run Meta models on Fireworks AI?**
>
> Not today. Meta is a publisher you can check in the Fireworks AI form, but no Meta models are on its list.

> **Is there a raw passthrough route for the Meta API?**
>
> No. Meta calls go through the unified LLM proxy, unlike Anthropic and OpenAI, which also have passthrough routes.

## Put a governed agent on Meta this week

> **[Book a demo](https://guild-ai.cal.com/gtm/meeting-with-guild.ai)**
>
> See how teams govern agents that use Meta.

> **[Start free](https://app.guild.ai)**
>
> Connect Meta and scope your first agent.

## Related

**Also runs on Guild:** [OpenAI](/integrations/openai) · [Anthropic](/integrations/anthropic) · [OpenRouter](/integrations/openrouter)

**Read:** Docs: [Models & providers](/platform/llm-settings) · [LLMs](/guide/llms) · [Usage](/insights/usage)