Llama-4-Maverick-17B-128E-Instruct-FP8 vs Llama-4-Scout-17B-16E-Instruct: API Pricing Compared
Side-by-side API pricing and capabilities for Llama-4-Maverick-17B-128E-Instruct-FP8 and Llama-4-Scout-17B-16E-Instruct. Both are available through Riven behind one OpenAI-compatible endpoint — at vendor list price with transparent per-token pricing, or a flat $3 per million tokens on pay-as-you-go.
| Llama-4-Maverick-17B-128E-Instruct-FP8 | Llama-4-Scout-17B-16E-Instruct | |
|---|---|---|
| Input price ($/1M tokens) | $0.25 | $0.20 |
| Output price ($/1M tokens) | $1.00 | $0.78 |
| Vendor | meta-llama | meta-llama |
| Capabilities | chat | chat |
Model pages: Llama-4-Maverick-17B-128E-Instruct-FP8 · Llama-4-Scout-17B-16E-Instruct
FAQ
Which is cheaper, Llama-4-Maverick-17B-128E-Instruct-FP8 or Llama-4-Scout-17B-16E-Instruct?
On Riven both are billed at vendor list price with transparent per-token pricing: Llama-4-Maverick-17B-128E-Instruct-FP8 is $0.25/1M input and $1.00/1M output; Llama-4-Scout-17B-16E-Instruct is $0.20/1M input and $0.78/1M output. On the pay-as-you-go plan, every model is a flat $3 per million tokens.
Can I use Llama-4-Maverick-17B-128E-Instruct-FP8 and Llama-4-Scout-17B-16E-Instruct with one API key?
Yes. One Riven key reaches both models through the same OpenAI-compatible endpoint, so you can A/B them by changing only the model id.
Is there a markup on these prices?
No. Riven lists these models at vendor list price with transparent per-token pricing. Pay-as-you-go users instead pay a flat $3 per million tokens across every model.