AI Rate CardQVQ-72B-Preview vs qwq-32b-preview: API price and specs
qwq-32b-preview is 52% cheaper than QVQ-72B-Preview on input price.
qwq-32b-preview is 68% cheaper than QVQ-72B-Preview on output price.
qwq-32b-preview is 57% cheaper than QVQ-72B-Preview on a 1M-in / 200k-out workload.
qwq-32b-preview has a 2.4% larger context than QVQ-72B-Preview.
| Field | QVQ-72B-Preview | qwq-32b-preview |
|---|---|---|
| Lowest input, per 1M | $0.25 +108.3% | $0.12 |
| Median input, per 1M | $0.72 +417.9% | $0.14 |
| Lowest output, per 1M | $0.50 +212.5% | $0.16 |
| Median output, per 1M | $0.85 +400% | $0.17 |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $0.35 +130.3% | $0.15 |
| Context | 32K +2.3% | 33K |
| Max output | — | — |
| Providers | 2 | 2 |
| Regions | — | — |
| Accepts | — | — |
| Returns | text | text |
| Type | Text models | Text models |
| Free option | no | no |
| Cheapest provider | deepinfra | deepinfra |
Your own workload: how many tokens the model gets (input) and gives back (output) - for example, in a month. The "Cost" row of the table above is recalculated for these numbers, for each model.
Computed from current offers each time the page opens; the best value of a row is bold, the percent is how far behind the best.
Providers selling both
Frequently asked questions
Which is cheaper, QVQ-72B-Preview or qwq-32b-preview?
qwq-32b-preview is 52% cheaper than QVQ-72B-Preview on input price. qwq-32b-preview is 68% cheaper than QVQ-72B-Preview on output price. qwq-32b-preview is 57% cheaper than QVQ-72B-Preview on a 1M-in / 200k-out workload.
Which has the larger context, QVQ-72B-Preview or qwq-32b-preview?
QVQ-72B-Preview: 32K tokens; qwq-32b-preview: 33K tokens.
Where can I use both QVQ-72B-Preview and qwq-32b-preview?
aihubmix, deepinfra