Llama 4 Scout API Pricing
Open-weight · 10000K context · Available from 7 hosts. Cheapest: Novita at $0.16 input / $0.48 output per 1M tokens.
Among Meta's 10 open-weight models tracked here, Llama 4 Scout ($0.2/$0.6 per 1M tokens) is above Llama Guard 3 8B ($0.2/$0.2) and priced the same as Llama 3.1 70B ($0.2/$0.6). Its 10000K context window is well above the open-weight category's typical range.
Llama 4 Scout price by host (7 providers)
| Host | Input /1M | Output /1M | In+Out |
|---|---|---|---|
| Novita | $0.16 | $0.48 | $0.64 |
| DeepInfra | $0.17 | $0.51 | $0.68 |
| Groq | $0.19 | $0.57 | $0.76 |
| Meta | $0.2 | $0.6 | $0.8 |
| Together | $0.2 | $0.6 | $0.8 |
| OpenRouter | $0.2 | $0.6 | $0.8 |
| Fireworks | $0.21 | $0.63 | $0.84 |
Prices per 1M tokens, USD. Snapshot 2026-07 — verify with the provider before relying on them.
Llama 4 Scout cost calculator
Frequently asked
Llama 4 Scout costs $0.16 per 1M input tokens and $0.48 per 1M output tokens at its cheapest host (Novita).
Llama 4 Scout supports a context window of about 10000K tokens. Remember every token in the context is billed on each call.
Across 7 hosts, Novita is currently cheapest at $0.16/$0.48 per 1M tokens, versus Fireworks at $0.21/$0.63. Prices change often — use the comparison table above.