Llama 4 Scout
As of Nov 22, 2026, the cheapest Llama 4 Scout API price is $0.085 per 1M input tokens (NanoGPT) and $0.3 per 1M output tokens (Kilo Gateway). Llama 4 Scout is offered by 3 providers in the llama family, open weights.
API pricing by provider
Metered per-token prices. Cheapest input and output are highlighted; † marks a context-tier surcharge. How prices are ranked.
| Kilo Gatewayopenmeta-llama/llama-4-scout | $0.1 | Cheapest$0.3 | — | — | 328k | 4d agoout +25% |
| OpenRouteropenmeta-llama/llama-4-scout | $0.1 | $0.3 | — | — | 328k | 36d ago |
| NanoGPTopenmeta-llama/llama-4-scout | Cheapest$0.085 | $0.46 | $0.0425 | — | 328k | — |
Llama 4 Scout price history
Output price per 1M tokens since tracking began on Sep 10, 2026, for the 2 providers whose rate moved. Each step is a recorded change. All recent price changes.
| Date | Provider | 1M input | 1M output | Change |
|---|---|---|---|---|
| Kilo Gateway | $0.08 → $0.1 | $0.24 → $0.3 | +25% | |
| OpenRouter | $0.18 → $0.1 | $0.59 → $0.3 | −49.2% | |
| Kilo Gateway | $0.1 → $0.08 | $0.3 → $0.24 | −20% | |
| OpenRouter | $0.1 → $0.18 | $0.3 → $0.59 | +96.7% |
Llama 4 Scout pricing FAQ
What is the cheapest Llama 4 Scout API?
As of Nov 22, 2026, Kilo Gateway has the lowest Llama 4 Scout output price at $0.3 per 1M tokens, and NanoGPT has the lowest input price at $0.085 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.
How many providers offer Llama 4 Scout?
3 providers list Llama 4 Scout on Sovyron; 3 of them sell it at a metered per-token price.
Is Llama 4 Scout free?
No provider in the Sovyron catalog lists a free tier for Llama 4 Scout.
What is the context window of Llama 4 Scout?
Llama 4 Scout supports a 328k-token context window and up to 66k output tokens.
Token cost calculator
What a month costs at one provider's published rates. Enter the tokens you expect to send and receive; cached tokens use the cached-input price where the provider lists one, and count as ordinary input where it does not. See how much prompt caching saves and why output tokens cost more than input tokens.
Estimated
—