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

# Meta (Llama)

> Use Meta Llama models with Agentium — powerful open models via the Llama API.

# Meta (Llama)

Use Meta's **Llama** models via the official [Llama API](https://llama.developer.meta.com). Access Llama 3.3, Llama 4 Scout, Llama 4 Maverick, and more through Meta's hosted inference endpoint.

The Llama API exposes an **OpenAI-compatible** interface.

***

## Setup

<Tabs>
  <Tab title="Install">
    ```bash theme={null}
    npm install openai
    ```
  </Tab>

  <Tab title="Environment">
    Get your API key from [llama.developer.meta.com](https://llama.developer.meta.com):

    ```bash theme={null}
    export LLAMA_API_KEY="..."
    ```
  </Tab>
</Tabs>

***

## Factory

```typescript theme={null}
import { meta } from "@agentium/core";

const model = meta("Llama-4-Scout-17B-16E-Instruct");
```

<ParamField path="modelId" type="string" required>
  Model ID (e.g., `"Llama-3.3-70B-Instruct"`, `"Llama-4-Scout-17B-16E-Instruct"`, `"Llama-4-Maverick-17B-128E-Instruct-FP8"`).
</ParamField>

<ParamField path="config" type="MetaLlamaConfig" required={false}>
  Optional `{ apiKey?, baseURL? }`.
</ParamField>

***

## Supported Models

| Model                                    | Description                      | Best For                           |
| ---------------------------------------- | -------------------------------- | ---------------------------------- |
| `Llama-4-Maverick-17B-128E-Instruct-FP8` | Latest flagship, 128 experts MoE | Maximum capability                 |
| `Llama-4-Scout-17B-16E-Instruct`         | Latest scout model, 16 experts   | Great balance of speed and quality |
| `Llama-3.3-70B-Instruct`                 | Proven large model               | Complex reasoning, tool calling    |
| `Llama-3.1-8B-Instruct`                  | Fast, efficient                  | Simple tasks, high throughput      |

See the full list at [llama.developer.meta.com/docs/models](https://llama.developer.meta.com/docs/models).

***

## Basic Example

```typescript theme={null}
import { Agent, meta } from "@agentium/core";

const agent = new Agent({
  name: "llama-agent",
  model: meta("Llama-4-Scout-17B-16E-Instruct"),
  instructions: "You are a helpful, harmless, and honest assistant.",
});

const result = await agent.run("Explain the difference between TCP and UDP.");
console.log(result.text);
```

***

## Tool Calling

Llama 3.1+ and Llama 4 models support function calling:

```typescript theme={null}
import { Agent, meta, defineTool } from "@agentium/core";
import { z } from "zod";

const agent = new Agent({
  name: "tool-agent",
  model: meta("Llama-3.3-70B-Instruct"),
  tools: [
    defineTool({
      name: "calculate",
      description: "Evaluate a math expression",
      parameters: z.object({ expression: z.string() }),
      execute: async ({ expression }) => {
        try { return String(Function(`return ${expression}`)()); }
        catch { return "Error evaluating expression"; }
      },
    }),
  ],
});

const result = await agent.run("What is 2^16 + 3^10?");
console.log(result.text);
```

***

## Multi-Modal (Llama 4)

Llama 4 models support image input:

```typescript theme={null}
import { Agent, meta, type ContentPart } from "@agentium/core";
import { readFileSync } from "node:fs";

const agent = new Agent({
  name: "vision-agent",
  model: meta("Llama-4-Scout-17B-16E-Instruct"),
  instructions: "Analyze images carefully.",
});

const imageData = readFileSync("photo.jpg").toString("base64");
const result = await agent.run([
  { type: "text", text: "Describe this image in detail." },
  { type: "image", data: imageData, mimeType: "image/jpeg" },
] as ContentPart[]);
console.log(result.text);
```

***

## Full Example

```typescript theme={null}
import { Agent, meta, CostTracker, defineTool } from "@agentium/core";
import { z } from "zod";

const costTracker = new CostTracker({
  pricing: {
    "Llama-3.3-70B-Instruct": { promptPer1k: 0.00099, completionPer1k: 0.00099 },
    "Llama-4-Scout-17B-16E-Instruct": { promptPer1k: 0.00015, completionPer1k: 0.0006 },
  },
});

const agent = new Agent({
  name: "coding-assistant",
  model: meta("Llama-3.3-70B-Instruct"),
  instructions: "You are a senior software engineer. Help with code reviews and architecture.",
  tools: [
    defineTool({
      name: "readFile",
      description: "Read a file's contents",
      parameters: z.object({ path: z.string() }),
      execute: async ({ path }) => `// ${path}\nexport function main() { console.log("hello"); }`,
    }),
  ],
  costTracker,
});

const result = await agent.run("Review the main function in index.ts");
console.log(result.text);
console.log(`Cost: $${costTracker.getSummary().totalCost.toFixed(6)}`);
```

***

## Running Llama Locally

You can also run Llama models locally via Ollama:

```typescript theme={null}
import { ollama } from "@agentium/core";

const model = ollama("llama3.1:70b");
```

See [Ollama](/models/ollama) for local setup instructions.

***

## Environment Variables

| Variable        | Description   |
| --------------- | ------------- |
| `LLAMA_API_KEY` | Llama API key |

***

## Cross-References

* [Ollama](/models/ollama) — Run Llama models locally
* [AWS Bedrock](/models/aws-bedrock) — Llama models on AWS
* [Azure AI Foundry](/models/azure-foundry) — Llama models on Azure
* [Tools](/agents/tools) — Tool calling guide