AI Rate CardQwen 2.5 72B Instruct vs qwen3-4b: API price and specs
qwen3-4b is 96% cheaper than Qwen 2.5 72B Instruct on input price.
qwen3-4b is 92% cheaper than Qwen 2.5 72B Instruct on output price.
qwen3-4b is 95% cheaper than Qwen 2.5 72B Instruct on a 1M-in / 200k-out workload.
qwen3-4b has a 100% larger context than Qwen 2.5 72B Instruct.
| Field | Qwen 2.5 72B Instruct | qwen3-4b |
|---|---|---|
| Lowest input, per 1M | $0.23 +2200% | $0.01 |
| Median input, per 1M | $0.36 +682.6% | $0.046 |
| Lowest output, per 1M | $0.40 +1233.3% | $0.03 |
| Median output, per 1M | $0.40 | $0.46 +15% |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $0.31 +1837.5% | $0.016 |
| Context | 131K +50% | 262K |
| Max output | 16K | — |
| Providers | 11 | 3 +72.7% |
| Regions | US | — |
| Accepts | text | text |
| Returns | text | text |
| Type | Text models | Text models |
| Free option | no | no |
| Cheapest provider | requesty | huggingface |
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
aihubmix, huggingface, trustedrouter
Frequently asked questions
Which is cheaper, Qwen 2.5 72B Instruct or qwen3-4b?
qwen3-4b is 96% cheaper than Qwen 2.5 72B Instruct on input price. qwen3-4b is 92% cheaper than Qwen 2.5 72B Instruct on output price. qwen3-4b is 95% 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 qwen3-4b?
Qwen 2.5 72B Instruct: 131K tokens; qwen3-4b: 262K tokens.
Where can I use both Qwen 2.5 72B Instruct and qwen3-4b?
aihubmix, huggingface, trustedrouter