Llama 4 Scout
- Input / output
- $0.08 / $0.24
- Providers
- 1
- Spread
- 1.88×
- 7 days
- 0%
- 30 days
- 0%
- Context
- 1.3M
Providers
| Provider | Input | Output | Blended | vs ref | Context | Uptime 1d | Price since |
|---|---|---|---|---|---|---|---|
| fp8 | $0.08 | $0.24 | $0.12 | ref | |||
| fp8 | $0.10 | $0.30 | $0.15 | +25% | |||
DeepInfrafp8/priority fp8 | $0.15 | $0.45 | $0.225 | +88% |
- DeepInfraCheapestfp8/flex$0.12$0.08 in · $0.24 outref vs ref320K ctx98.6% uptimefp8
- $0.15$0.10 in · $0.30 out+25% vs ref320K ctx100% uptimefp8
- fp8/priority$0.225$0.15 in · $0.45 out+88% vs ref320K ctx100% uptimefp8
Blended = (3 × input + output) / 4. Ref $0.12 = median of cheapest 20%.
Price history
USD per 1M tokens · each step is a price change
Prices in USD / 1M tokens.
No provider has changed its price since tracking began on Oct 3, 2026.
Changes
About
The cheapest provider for Llama 4 Scout is DeepInfra at $0.12 per 1M tokens (blended), charging $0.08 per 1M input and $0.24 per 1M output tokens. It is served by a single provider. Context window: 1.3M tokens. Prices tracked since Oct 3, 2026.
Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...
- Released
- Apr 5, 2025
- First tracked
- Oct 3, 2026
- Canonical slug
- meta-llama/llama-4-scout-17b-16e-instruct
- Weights
- meta-llama/Llama-4-Scout-17B-16E-Instruct