HASTATAgent stack guide llama
Meta Llama 4 Scout 17B 16E
Open multimodal Llama model for long-context analysis and efficient agents
Fresh · fetched 2026-08-17T02:11:57.739Z · Models.dev(opens in a new tab)
Minimum context1.31M
Output64K
Providers5
CapabilitiesTool calling, Image input
Provider offers
| Providers | Input / 1M | Output / 1M | Cache read / 1M | Context / output | Updated |
|---|---|---|---|---|---|
 NanoGPTmeta-llama/llama-4-scout | $0.085 | $0.46 | $0.043 | 328K | 2025-09-05 |
 OpenRoutermeta-llama/llama-4-scout | $0.10 | $0.30 | Unavailable | 1.31M | 2025-04-05 |
 Heliconellama-4-scout | $0.080 | $0.30 | Unavailable | 128K | 2025-01-01 |
 Vercel AI Gatewaymeta/llama-4-scout | $0.00 | $0.00 | Unavailable | 128K | 2025-04-05 |
 Kilo Gatewaymeta-llama/llama-4-scout | $0.10 | $0.30 | Unavailable | 320K | 2025-04-05 |
Lowest reported provider price in USD per 1M tokens; unavailable is not free. Provider documentation remains authoritative. Catalogue presence is not an uptime, security, or quality endorsement.
Source metadata and limitations
Capabilities are source-reported. Tool calling does not prove quality in a particular harness. Prices and limits can change.
Modalities: text, image → text