Compare model prices
Input, output, cached and batch prices, every route and a month of tokens, side by side.
Qwen3 Next 80B A3B InstructA month of tokens
100M input and 20M output tokens, list price. Use your own numbers.
Side by side
| Qwen3 Next 80B A3B Instruct | |
|---|---|
| Input per 1M | $0.098 |
| Output per 1M | $0.78 |
| Cached input | n/a |
| Batch in / out | n/a |
| Blended (3:1) | $0.268 |
| Context | 262K |
| Routes | 5 |
| Released | Sep 11, 2025 |
| Leadersboard score | 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
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
| Qwen (Alibaba) API The lab's own API | $0.098 | $0.78 | $0.098 / $0.78List price | n/a | List price |
 DeepInfrafp8 | $0.09 | $1.1 | $0.09 / $1.1+28% vs list | n/a | +28% vs list |
 Parasailfp8 · cached $0.07 | $0.1 | $1.1 | $0.1 / $1.1+31% vs list | $0.07 | +31% vs list |
 Google Vertex AIglobal | $0.15 | $1.2 | $0.15 / $1.2+54% vs list | n/a | +54% vs list |
 Novita AIbf16 | $0.15 | $1.5 | $0.15 / $1.5+82% vs list | n/a | +82% vs list |
List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.