AI Rate Cardqwen2-72b-instruct vs qwen2-7b-instruct: API price and specs
qwen2-7b-instruct is 84% cheaper than qwen2-72b-instruct on input price.
qwen2-7b-instruct is 86% cheaper than qwen2-72b-instruct on output price.
qwen2-7b-instruct is 85% cheaper than qwen2-72b-instruct on a 1M-in / 200k-out workload.
| Field | qwen2-72b-instruct | qwen2-7b-instruct |
|---|---|---|
| Lowest input, per 1M | $0.35 +536.4% | $0.055 |
| Median input, per 1M | $0.57 +618.7% | $0.08 |
| Lowest output, per 1M | $0.40 +627.3% | $0.055 |
| Median output, per 1M | $0.60 +650% | $0.08 |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $0.43 +551.5% | $0.066 |
| Context | 33K | 33K |
| Max output | — | — |
| Providers | 2 +33.3% | 3 |
| 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, qwen2-72b-instruct or qwen2-7b-instruct?
qwen2-7b-instruct is 84% cheaper than qwen2-72b-instruct on input price. qwen2-7b-instruct is 86% cheaper than qwen2-72b-instruct on output price. qwen2-7b-instruct is 85% cheaper than qwen2-72b-instruct on a 1M-in / 200k-out workload.
Which has the larger context, qwen2-72b-instruct or qwen2-7b-instruct?
qwen2-72b-instruct: 33K tokens; qwen2-7b-instruct: 33K tokens.
Where can I use both qwen2-72b-instruct and qwen2-7b-instruct?
aihubmix, deepinfra