Meta Llama API
Access Meta's Llama models directly through the official Llama API.
Configuration
| Field | Required | Example |
|---|---|---|
| Application Name | Yes | my-llama-app |
| Model Name | Yes | Llama-4-Maverick-17B-128E-Instruct |
| API Key | Yes | Your Llama API key |
Getting Your API Key
- Go to Meta Llama Developer
- Sign up for API access
- Navigate to your dashboard
- Copy your API key
Popular Models
| Model | Description |
|---|---|
Llama-4-Maverick-17B-128E-Instruct | Flagship MoE (400B total, 17B active), 1M context, 128 experts |
Llama-4-Scout-17B-16E-Instruct | Best multimodal in its class, 10M context, fits single H100 |
Llama-4-Behemoth | 288B active params, 2T total (teacher model, still training) |
Llama-3.3-70B-Instruct | High-quality text-only model |
Note: Llama 4 models are natively multimodal with mixture-of-experts architecture, supporting 12 languages for image/text understanding.
For the complete list of available models, visit the Llama API Models Documentation.
Advanced Parameters
| Parameter | Type | Description |
|---|---|---|
max_completion_tokens | integer | Maximum tokens |
temperature | float | Randomness |
top_p | float | Nucleus sampling |
top_k | integer | Top-k sampling |
repetition_penalty | float | Penalize repetition |
Setup Steps
- Navigate to AI Applications → New Application
- Select Model Providers tab
- Click Meta Llama API
- Enter your Application Name and API Key
- Select your desired Model Name
- Configure Advanced Settings (optional)
- Click Test Response to verify (optional)
- Review and submit