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: Qwen: Qwen3 Coder Flash · $1.17
Add another
Search by name, then add up to four.
| MoonshotAI: Kimi K3 | Qwen: Qwen3 Coder Flash | |
|---|---|---|
| Provider | Moonshot AI | Alibaba |
| Modality | text, image, video | text |
| Context | 1.0M | 1M |
| Input | $0.192/1M | $0.195/1M |
| Output | $15/1M | $0.975/1M |
| Cache read | $0.182/1M | $0.039/1M |
| Cache write | Not published— | $0.2437/1M |
Tiers and extras
- MoonshotAI: Kimi K3
- —
- Qwen: Qwen3 Coder Flash
- Above 32,000 prompt tokens: in $0.325 · out $1.625 · cache read $0.065 · cache write $0.4063; Above 128,000 prompt tokens: in $0.52 · out $2.6 · cache read $0.104 · cache write $0.65