Home / Meta / Llama 4 Maverick 17B 128E Instruct FP8
Llama 4 Maverick 17B 128E Instruct FP8 API price
Llama-4-Maverick-17B-128E-Instruct-FP8
Llama 4 Maverick 17B 128E Instruct FP8 API costs $0.27/M input at Together AI (inference host), per 1M tokens.
SmallMeta1.0M context1 seller
Input
$0.27
per 1M tokens · Together AI (inference host)
Output
$0.85
per 1M tokens · Together AI (inference host)
Where to buy it
The one source pricing Llama 4 Maverick 17B 128E Instruct FP8 today, per 1M tokens.
Cost calculator
| Provider | Input $/M | Output $/M | Your cost |
|---|---|---|---|
| Together AI (inference host) | 0.270cheapest | 0.850 |
Against its tier
- This model$1.12
- Cheapest · Nemotron 3.5 Lightning$0.145
- Tier median · GPT 5.4 Nano (latest)$0.9425
- Dearest · GPT 5.4 Mini (03-17 snapshot)$5.25
#12 of 20 small · cheaper than 42%
Details
- Context window
- 1.0M1,048,000 tokens
- Developer
- Meta
- Intelligence
- 10.0 est.
- Sellers
- 1
- Cheapest at
- Together AI (inference host)
- Combined
- $1.12in + out per 1M
- Last checked
- 2026-10-12