Available now
Meta
llama-4-scout
Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...
TextToolsVision131.1K
InputFree
OutputFree
Context131.1K
Endpointsopenai
Capabilities
ToolsVisionStructured
Modalities
Input
textimage
Output
text
Quick stats
Context window131.1K
Max output131K
Modechat
TokenizerLlama4
Knowledge cutoff2024
Quantizationbf16
Hugging Facemeta-llama/Llama-4-Scout-17B-16E-Instruct
Performance
Loading performance data...
Supported parameters
| Parameter | Always | Default |
|---|---|---|
| frequency_penalty | - | - |
| logit_bias | - | - |
| max_tokens | - | |
| min_p | - | - |
| presence_penalty | - | - |
| repetition_penalty | - | - |
| response_format | - | - |
| seed | - | |
| stop | - | |
| structured_outputs | - | - |
| temperature | - | |
| tool_choice | - | - |
| tools | - | - |
| top_k | - | - |
| top_p | - |
§ 01
Pricing
| Input price | $0.00 · 1M tokens |
| Output price | $0.00 · 1M tokens |
| Context window | 131.1K tokens |
| Compatible endpoints | openai |
| Vendor | Meta |
§ 02
Call llama-4-scout from your code
Point any OpenAI-compatible SDK at UnoRouter and request the model by name. Replace YOUR_API_KEY with a real key from your dashboard.
bash
curl https://api.unorouter.ai/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "llama-4-scout",
"messages": [{"role": "user", "content": "Hello!"}]
}'§ 03
Frequently asked questions
How much does llama-4-scout cost per 1M tokens?
Input is priced at $0.00 per 1M tokens, output at $0.00 per 1M tokens. Billing is per token, no rounding to batch sizes.
How do I access llama-4-scout via API?
Send requests to the UnoRouter /v1/chat/completions endpoint with model=llama-4-scout. Any OpenAI-compatible client library works. Authentication uses a standard Bearer token.
What is the context window of llama-4-scout?
llama-4-scout supports a context window of 131.1K tokens, shared between your prompt and the model's response.
§ 04