Compare
Add up to four models. The bill starts at 1M input tokens, 1M output tokens, and 1,000 units.
Monthly bill
Token models use the token counts. Other models use units times the flat rate.
Lowest bill: Intel: Qwen3 Coder 480B A35B Instruct INT4 Mixed AR · $1.58
Add another
Search by name, then add up to four.
| Intel: Qwen3 Coder 480B A35B Instruct INT4 Mixed AR | Qwen: Qwen3.6 Plus | |
|---|---|---|
| Provider | Io Net | Alibaba |
| Modality | text | text, image, video |
| Context | 106K | 1M |
| Input | $0.325/1M | $0.325/1M |
| Output | $1.25/1M | $1.95/1M |
| Cache read | $0.1625/1M | Not published— |
| Cache write | Not published— | $0.4063/1M |
Tiers and extras
- Intel: Qwen3 Coder 480B A35B Instruct INT4 Mixed AR
- —
- Qwen: Qwen3.6 Plus
- Above 256,000 prompt tokens: in $1.3 · out $3.9 · cache write $1.625