Compare model prices
Input, output, cached and batch prices, every route and a month of tokens, side by side.
Qwen3 Coder 480B A35BQwen3.8 Max PrimeA month of tokens
100M input and 20M output tokens, list price. Use your own numbers.
Side by side
| Qwen3 Coder 480B A35B | Qwen3.8 Max Prime | |
|---|---|---|
| Input per 1M | $0.3 | $4 |
| Output per 1M | $1 | $12 |
| Cached input | $0.1 | $0.5 |
| Batch in / out | n/a | n/a |
| Blended (3:1) | $0.475 | $6 |
| Context | 262K | 1M |
| Routes | 5 | 1 |
| Released | Jul 23, 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 Coder 480B A35B
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
 DeepInfraturbo, fp4 · cached $0.1 | $0.3 | $1 | $0.3 / $1Same as list | $0.1 | Same as list |
 Google Vertex AIus-south1 | $0.22 | $1.8 | $0.22 / $1.8+29% vs list | n/a | +29% vs list |
 Venicefp8 · cached $0.04 | $0.35 | $1.5 | $0.35 / $1.5+34% vs list | $0.04 | +34% vs list |
 Novita AIfp8 | $0.38 | $1.55 | $0.38 / $1.55+42% vs list | n/a | +42% vs list |
| Qwen (Alibaba) opensource | $0.975 | $4.88 | $0.975 / $4.88+311% vs list | n/a | +311% vs list |
Qwen3.8 Max Prime
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
| Qwen (Alibaba) API The lab's own API · cached $0.5 | $4 | $12 | $4 / $12List price | $0.5 | List price |
List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.