Llama 4 Scout
The cheapest provider for Llama 4 Scout is DeepInfra at $0.15 per 1M tokens (blended), charging $0.10 per 1M input and $0.30 per 1M output tokens. 3 providers serve it; the most expensive charges 2.4× as much. Context window: 1.3M tokens. Prices tracked since Oct 3, 2026.
Best price
$0.15
at DeepInfra
Input / output
$0.10 / $0.30
per 1M tokens
Providers
3
2.4× spread
7 days
—
best price
30 days
—
best price
Context
1.3M
tokens
Providers
Active offers ranked by blended price. Bars are relative to the most expensive.
| Provider | Input | Output | Blended | vs cheapest | Context | Uptime 1d | Price since |
|---|---|---|---|---|---|---|---|
DeepInfraCheapest fp8 | $0.10 | $0.30 | $0.15 | best | |||
| bf16 | $0.18 | $0.59 | $0.283 | +88% | |||
Googleus-east5 | $0.25 | $0.70 | $0.363 | +142% |
- DeepInfraCheapest$0.15$0.10 in · $0.30 outbest320K ctx99.9% uptimefp8
- $0.283$0.18 in · $0.59 out+88%128K ctx100% uptimebf16
- us-east5$0.363$0.25 in · $0.70 out+142%1.3M ctx
Blended = (3 × input + output) / 4.
Price history
Hover to compare providers at any point in time. Click a legend item to hide it.
USD per 1M tokens · each step is a price change
Not enough history yet
Tracking since Oct 3, 2026. The chart fills in as new crawls arrive every 6 hours.
Change log
Every recorded change for this model since Oct 3, 2026.
No changes yet
Tracking since Oct 3, 2026. Price changes, new providers and delistings will show up here.
About this model
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