Meta (Llama)
Use Meta’s Llama models via the official Llama API. 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
- Install
- Environment
Factory
string
required
Model ID (e.g.,
"Llama-3.3-70B-Instruct", "Llama-4-Scout-17B-16E-Instruct", "Llama-4-Maverick-17B-128E-Instruct-FP8").MetaLlamaConfig
Optional
{ apiKey?, baseURL? }.Supported Models
See the full list at llama.developer.meta.com/docs/models.
Basic Example
Tool Calling
Llama 3.1+ and Llama 4 models support function calling:Multi-Modal (Llama 4)
Llama 4 models support image input:Full Example
Running Llama Locally
You can also run Llama models locally via Ollama:Environment Variables
Cross-References
- Ollama — Run Llama models locally
- AWS Bedrock — Llama models on AWS
- Azure AI Foundry — Llama models on Azure
- Tools — Tool calling guide