llama-4-maverick-17b-128e-instruct-fp8 API price — 3 gateways compared
from $0.20 per
million input tokens · 1.4× spread between gateways
· updated hourly
| Gateway | $ in /MTok | $ out /MTok |
Context | Input price history | Model ID |
|---|
| Requesty | $0.20 | $0.85 | 1,048,576 | since 2026-08-20 | novita/meta-llama/llama-4-maverick-17b-128e-instruct-fp8 |
| DeepInfra | $0.20 | $0.80 | 1,048,576 | since 2026-08-20 | meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 |
| Novita | $0.27 | $0.85 | 1,048,576 | since 2026-08-20 | meta-llama/llama-4-maverick-17b-128e-instruct-fp8 |
Changelog for llama-4-maverick-17b-128e-instruct-fp8
- No changes recorded for this model yet — history starts the day we first saw it.
llama-4-maverick-17b-128e-instruct-fp8 pricing FAQ
How much does llama-4-maverick-17b-128e-instruct-fp8 cost per million tokens?
The cheapest tracked gateway charges $0.20 per million input tokens and $0.80 per million output tokens (DeepInfra). Prices refresh hourly.
Which gateway is cheapest for llama-4-maverick-17b-128e-instruct-fp8?
DeepInfra for input tokens and DeepInfra for output tokens, among the 3 gateways we track.
Do llama-4-maverick-17b-128e-instruct-fp8 prices differ between gateways?
Yes — the most expensive tracked gateway charges 1.4× the cheapest for input tokens. Identical model, identical tokens, different bill.
← All LLM prices · API