AI Rate CardQwen 2.5 72B Instruct vs granite-4.2-3b: API price and specs
granite-4.2-3b is 87% cheaper than Qwen 2.5 72B Instruct on input price.
granite-4.2-3b is 70% cheaper than Qwen 2.5 72B Instruct on output price.
granite-4.2-3b is 83% cheaper than Qwen 2.5 72B Instruct on a 1M-in / 200k-out workload.
| Field | Qwen 2.5 72B Instruct | granite-4.2-3b |
|---|---|---|
| Lowest input, per 1M | $0.23 +666.7% | $0.03 |
| Median input, per 1M | $0.36 +1100% | $0.03 |
| Lowest output, per 1M | $0.40 +233.3% | $0.12 |
| Median output, per 1M | $0.40 +233.3% | $0.12 |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $0.31 +474.1% | $0.054 |
| Context | 131K | 131K |
| Max output | 16K | — |
| Providers | 11 | 3 +72.7% |
| Regions | US | US |
| Accepts | text | text |
| Returns | text | text |
| Type | Text models | Text models |
| Free option | no | no |
| Cheapest provider | requesty | 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
deepinfra, edenai, huggingface
Frequently asked questions
Which is cheaper, Qwen 2.5 72B Instruct or granite-4.2-3b?
granite-4.2-3b is 87% cheaper than Qwen 2.5 72B Instruct on input price. granite-4.2-3b is 70% cheaper than Qwen 2.5 72B Instruct on output price. granite-4.2-3b is 83% cheaper than Qwen 2.5 72B Instruct on a 1M-in / 200k-out workload.
Which has the larger context, Qwen 2.5 72B Instruct or granite-4.2-3b?
Qwen 2.5 72B Instruct: 131K tokens; granite-4.2-3b: 131K tokens.
Where can I use both Qwen 2.5 72B Instruct and granite-4.2-3b?
deepinfra, edenai, huggingface