Meta
Llama 4 Scout
meta-llama/llama-4-scout
Input
$0.10
per 1M tokens
Output
$0.30
per 1M tokens
Cached input
—
per 1M tokens
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...
- Released
- Context window
- 1.3M tokens
- Max output
- 16K tokens
- Input
- text, image
- Output
- text
- Reasoning
- No
Price history
No price changes since we started tracking on .
Providers on OpenRouter
4 endpoints serve this model. Uptime is OpenRouter's share of successful requests; prices per 1M tokens.
| Provider | Input | Output | Context window | Uptime 30 min | Uptime 24 h |
|---|---|---|---|---|---|
| DeepInfrafp8 · flexdiscount/priority tier | $0.08 | $0.24 | 328K | — | 6.5% |
| DeepInfrafp8 | $0.10 | $0.30 | 328K | — | 99.66% |
| DeepInfrafp8 · prioritydiscount/priority tier | $0.15 | $0.45 | 328K | 46.7% | 96.2% |
| Googleus-east5 | $0.25 | $0.70 | 1.3M | — | — |