Open multimodal Llama model for long-context analysis and efficient agents
Llama 4 Scout 17B 16E Instruct by meta is offered by 5 providers on this page. Its reference price is $0.27 per 1M input tokens and $0.85 per 1M output tokens. The lowest paid channel is Deep Infra at $0.10 / $0.30 per 1M, about 2.7× below the reference price.
The context window is 131,000 tokens at the reference host, but hosts report different limits, from 128,000 to 327,680, so the usable window depends on the provider you pick. It supports tool use. Accepted input modalities are Text and Image. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2024-08.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Deep Infra meta-llama/Llama-4-Scout-17B-16E-Instruct | Cloud | $0.10 | $0.30 | — | — | 327,680 ⚠ | 16,384 | |
| NovitaAI | Gateway | $0.18 | $0.59 | — | — | 131,072 ⚠ | 131,072 | |
| Azure | Cloud | $0.20 | $0.78 | — | — | 128,000 ⚠ | 8,192 | |
| Azure Cognitive Services | Cloud | $0.20 | $0.78 | — | — | 128,000 ⚠ | 8,192 | |
| Cloudflare Workers AI | Cloud | $0.27 | $0.85 | — | — | 131,000 | 16,384 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.