The Orchestrator › Models › Meta Llama
Meta Llama: 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...
Specifications
| Provider | Meta Llama |
| Model ID | meta-llama/llama-4-scout |
| Context window | 1.3M tokens (1,310,720) |
| Modalities | text + image → text |
| Tokenizer | Llama4 |
| Router sources | OpenRouter |
| Released | 2025-04-05 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | — |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | OpenRouter | meta-llama/llama-4-scout | $0.1 | $0.3 | 1.3M |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $0.1 | $0.3 | 1.3M |
Capabilities
Vision (image input)Agentic tool useStructured outputs1M+ context window
Supported parameters
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