Model prices / Meta / Llama 4 Scout 17B Instruct
Llama 4 Scout 17B InstructOpen weights
Meta · released 2025-04-05
No price from the maker itself is on record for Llama 4 Scout 17B Instruct. The lowest of 13 providers is Kilo Gateway: $0.08 per 1M input tokens and $0.24 per 1M output tokens (as of 2026-11-12). Context window: 131K tokens, up to 16.4K output tokens per request.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
KKilo GatewayLowestmeta-llama/ | $0.08 | $0.24 | — | Lowest | Official docs |
HHeliconellama-4-scout | $0.08 | $0.3 | — | Official docs | |
 Deep Inframeta-llama/ | $0.1 | $0.3 | — | Official docs | |
 OpenRoutermeta-llama/ | $0.1 | $0.3 | — | Official docs | |
NNanoGPTmeta-llama/ | $0.085 | $0.46 | $0.0425 | Official docs | |
 DevPass (LLM Gateway)llama-4-scout-17b-instruct | $0.18 | $0.59 | — | Official docs | |
LLLM Gatewaynovita/ | $0.18 | $0.59 | — | Official docs | |
 Novita AImeta-llama/ | $0.18 | $0.59 | — | Official docs | |
 Vercel AI Gatewaymeta/ | $0.17 | $0.66 | — | Official docs | |
 Vertexmeta/ | $0.25 | $0.7 | — | Official docs | |
 Cloudflare Workers AI@cf/ | $0.27 | $0.85 | — | Official docs | |
OOCI Generative AImeta. | $0.72 | $0.72 | — | Official docs |
3 more listings
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
 Amazon BedrockDeprecatedmeta. | $0.17 | $0.66 | — | Deprecated | Official docs |
| Amazon BedrockDeprecatedus. | $0.17 | $0.66 | — | Deprecated | Official docs |
LLLM GatewayDeprecatedaws-bedrock/ | $0.17 | $0.66 | — | Deprecated | Official docs |
Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.
About
Open Llama with long-context vision for efficient multimodal agents
Description from models.dev.
Specs
- Type
- Text
- Context
- 131K
- Max output
- 16.4K
- Input
- Text, Image
- Output
- Text
- Reasoning
- No
- Tool calling
- Yes
- Structured output
- No
- Knowledge cutoff
- 2024-08
- Open weights
- Yes
- Released
- 2025-04-05
Source
Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.