Compare model prices
Input, output, cached and batch prices, every route and a month of tokens, side by side.
A month of tokens
Qwen3 Next 80B A3B Instruct$25.35
Qwen3.8 Max Prime$640.00
100M input and 20M output tokens, list price. Use your own numbers.
Side by side
| Qwen3 Next 80B A3B Instruct | Qwen3.8 Max Prime | |
|---|---|---|
| Input per 1M | $0.098 | $4 |
| Output per 1M | $0.78 | $12 |
| Cached input | n/a | $0.5 |
| Batch in / out | n/a | n/a |
| Blended (3:1) | $0.268 | $6 |
| Context | 262K | 1M |
| Routes | 5 | 1 |
| Released | Sep 11, 2025 | Sep 23, 2026 |
| Leadersboard score | n/a | n/a |
On the price map
Size: context window, 8K to 2MEqual blended cost (3:1) 243 models, lower left is cheaper
Every route
Qwen3 Next 80B A3B Instruct
Qwen (Alibaba) (list)the lab's own API$0.098 / $0.78$0.268 blended
DeepInfrafp8, fp8+28%$0.09 / $1.1$0.343 blended
Parasailfp8, fp8+31%$0.1 / $1.1cached $0.07
Google Vertex AIglobal+54%$0.15 / $1.2$0.413 blended
Novita AIbf16, bf16+82%$0.15 / $1.5$0.488 blended
Qwen3.8 Max Prime
Qwen (Alibaba) (list)the lab's own API$4 / $12cached $0.5
List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.