Llama 4 Scout
Llama 4 Scout is Meta's language model with a 10.0M context window and up to 16K output tokens, available from 5 providers, starting at $0.080 / 1M input and $0.300 / 1M output. Meta's Llama 4 Scout MoE LLM with 17B active parameters and 16 experts, offering efficient multimodal inference with native image and text support.
Capabilities
Input2/5
Text✓
Image✓
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities3/13
Reasoning·
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling·
Structured Outputs✓
Native JSON Schema✓
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Pricing by Provider
| Provider | Standard | Batch | ||
|---|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Input $ / 1M | Output $ / 1M | |
 OpenRouter | $0.080 | $0.300 | — | — |
 Vercel AI Gateway | $0.170 | $0.660 | — | — |
 Snowflake | $0.204 | $0.792 | $0.102 | $0.396 |
 Google Gemini | $0.250 | $0.700 | $0.125 | $0.350 |
 Google Vertex AI | $0.250 | $0.700 | $0.125 | $0.350 |
Cost Calculator
Preset:
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| LlamaGuard 4 12B | 164K | $0.180 | $0.180 | Available | |
| Llama 4 Scout | 10.0M | $0.080 | $0.300 | Current | |
| Llama 4 Maverick | 1.0M | $0.120 | $0.485 | Available |