The Orchestrator › Models › Meta
Meta: Llama 4 Scout 17B Instruct
Llama 4 Scout is the best multimodal model in the world in its class and is more powerful than our Llama 3 models, while fitting in a single H100 GPU. Additionally, Llama 4 Scout supports an industry-leading context window of up to 10M tokens.
Specifications
| Provider | Meta |
| Model ID | meta/llama-4-scout |
| Context window | 128K tokens (128,000) |
| Modalities | text + image → text |
| Tokenizer | — |
| Router sources | Vercel AI Gateway |
| 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 | Vercel AI Gateway | meta/llama-4-scout | $0.17 | $0.66 | 128K |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $0.17 | $0.66 | 128K |
Capabilities
Vision (image input)Agentic tool useStructured outputsNo training on inputs (attested)
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
max_tokens, temperature, stop, tools, tool_choice, response_format, structured_outputs