Meta: Llama 4 Scout 17B
Open multimodal Llama model for long-context analysis and efficient agents
Sources
Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| LiteLLMcheapestlambda_ai/llama-4-scout-17b-16e-instruct | N/A | $0.05 | $0.1 | $0.005 | N/A |
| LiteLLMnscale/meta-llama/Llama-4-Scout-17B-16E-Instruct | N/A | $0.09 | $0.29 | $0.009 | N/A |
| models.devmeta-llama/Llama-4-Scout-17B-16E-Instruct | DeepInfra | $0.1 | $0.3 | $0.01 | 328K |
| LiteLLMmeta-llama/Llama-4-Scout-17B-16E-Instruct | N/A | $0.1 | $0.3 | $0.01 | N/A |
| models.devmeta-llama/llama-4-scout-17b-16e-instruct | Novita AI | $0.18 | $0.59 | $0 | 131K |
| LiteLLMmeta-llama/llama-4-scout-17b-16e-instruct | N/A | $0.18 | $0.59 | $0.018 | N/A |
| LiteLLMnovita/meta-llama/llama-4-scout-17b-16e-instruct | N/A | $0.18 | $0.59 | $0.018 | N/A |
| LiteLLMtogether_ai/meta-llama/Llama-4-Scout-17B-16E-Instruct | N/A | $0.18 | $0.59 | $0.018 | N/A |
| models.devllama-4-scout-17b-16e-instruct | Azure | $0.2 | $0.78 | $0 | 128K |
| models.devllama-4-scout-17b-16e-instruct | Azure | $0.2 | $0.78 | $0 | 128K |
| LiteLLMLlama-4-Scout-17B-16E-Instruct | N/A | $0.2 | $0.78 | $0.02 | N/A |
| LiteLLMazure_ai/Llama-4-Scout-17B-16E-Instruct | N/A | $0.2 | $0.78 | $0.02 | N/A |
| models.dev@cf/meta/llama-4-scout-17b-16e-instruct | Cloudflare | $0.27 | $0.85 | $0 | 131K |
| LiteLLMllama-4-scout-17b-16e-instruct | N/A | $0.27 | $0.85 | $0.027 | N/A |
| LiteLLM@cf/meta/llama-4-scout-17b-16e-instruct | N/A | $0.27 | $0.85 | $0.027 | N/A |
| LiteLLMcloudflare/@cf/meta/llama-4-scout-17b-16e-instruct | N/A | $0.27 | $0.85 | $0.027 | N/A |
| models.devmeta.llama-4-scout-17b-16e-instruct | OCI Generative AI | $0.72 | $0.72 | $0.072 | 192K |
| LiteLLMmeta.llama-4-scout-17b-16e-instruct | N/A | $0.72 | $0.72 | $0.072 | N/A |
Capabilities
- Tool calling
- Structured output
- Attachments
- Open weights
- In: text
- In: image
- Out: text
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Hover or tap the i next to any score for its source. Full boards on /benchmarks.
- AA intelligence8.1i
- AA coding8.2i
- AA agentic0.5i
Arena rows are community-vote Elo from Arena AI, Artificial Analysis indices arrive via OpenRouter, and launch-eval figures are collected from vendor announcements, analyst writeups, and community benchmarks. Full boards and credits on /benchmarks.
See what this model costs you
The app reads the sessions your tools already wrote and prices this model's tokens at the published API rate. Free on your computer.