AI Rate CardQVQ-72B-Preview vs Deepseek Prover V2 671B: API price and specs
Deepseek Prover V2 671B is 60% cheaper than QVQ-72B-Preview on input price.
Deepseek Prover V2 671B is 80% cheaper than QVQ-72B-Preview on output price.
Deepseek Prover V2 671B is 66% cheaper than QVQ-72B-Preview on a 1M-in / 200k-out workload.
Deepseek Prover V2 671B has a 412% larger context than QVQ-72B-Preview.
| Field | QVQ-72B-Preview | Deepseek Prover V2 671B |
|---|---|---|
| Lowest input, per 1M | $0.25 +150% | $0.10 |
| Median input, per 1M | $0.72 +141.7% | $0.30 |
| Lowest output, per 1M | $0.50 +400% | $0.10 |
| Median output, per 1M | $0.85 | $1.14 +34.1% |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $0.35 +191.7% | $0.12 |
| Context | 32K +80.5% | 164K |
| Max output | — | — |
| Providers | 2 | 2 |
| Regions | — | — |
| Accepts | — | — |
| Returns | text | text |
| Type | Text models | Text models |
| Free option | no | no |
| Cheapest provider | deepinfra | aihubmix |
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 Deepseek Prover V2 671B?
Deepseek Prover V2 671B is 60% cheaper than QVQ-72B-Preview on input price. Deepseek Prover V2 671B is 80% cheaper than QVQ-72B-Preview on output price. Deepseek Prover V2 671B is 66% cheaper than QVQ-72B-Preview on a 1M-in / 200k-out workload.
Which has the larger context, QVQ-72B-Preview or Deepseek Prover V2 671B?
QVQ-72B-Preview: 32K tokens; Deepseek Prover V2 671B: 164K tokens.
Where can I use both QVQ-72B-Preview and Deepseek Prover V2 671B?
aihubmix, deepinfra