Model
Llama 4 Maverick 17B 128E Instruct FP8
1 providers
$0.371
best input /M · watsonx.ai
$1.48
best output /M
131K
context window
8K
max output
Compare providers (sorted by listed input price)
| Provider | Input /M | Output /M | Cache read /M | Cache write /M | Context | Capabilities | Status | Updated |
|---|---|---|---|---|---|---|---|---|
| watsonx.ai meta-llama/llama-4-maverick-17b-128e-instruct-fp8 | $0.371 | $1.48 | — | — | 131K | no reasoningtoolsno structuredvision | Apr 5, 2025 |
Price badge
https://models.sutraworks.ai/badge/watsonx/meta-llama/llama-4-maverick-17b-128e-instruct-fp8.svgLive SVG, regenerated on every hourly sync — paste it into a README to always show the current cheapest listed price. Updates when prices change; no build step needed on your side.
Prices are per million tokens (USD). “—” means the provider does not publicly list a price for this model. Data from models.dev; verify with the provider before purchasing.