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: Perplexity: Embed V1 4B · $0.03
Add another
Search by name, then add up to four.
| Qwen: Qwen3.7 Flash | Perplexity: Embed V1 4B | |
|---|---|---|
| Provider | Alibaba | Perplexity |
| Modality | text, image, video | text |
| Context | 1M | 32K |
| Input | $0.03/1M | $0.03/1M |
| Output | $0.13/1M | $0/1M |
| Cache read | $0.006/1M | Not published— |
| Cache write | $0.038/1M | Not published— |
Tiers and extras
- Qwen: Qwen3.7 Flash
- Above 32,000 prompt tokens: in $0.1 · out $0.4 · cache read $0.02 · cache write $0.125; Above 256,000 prompt tokens: in $0.2 · out $0.8 · cache read $0.04 · cache write $0.25
- Perplexity: Embed V1 4B
- —