AI Rate CardQwen 2.5 72B Instruct vs Qwen3-Coder 480B-A35B Instruct: API price and specs
Qwen3-Coder 480B-A35B Instruct is 4% cheaper than Qwen 2.5 72B Instruct on input price.
Qwen 2.5 72B Instruct is 50% cheaper than Qwen3-Coder 480B-A35B Instruct on output price.
Qwen 2.5 72B Instruct is 18% cheaper than Qwen3-Coder 480B-A35B Instruct on a 1M-in / 200k-out workload.
Qwen3-Coder 480B-A35B Instruct has a 100% larger context than Qwen 2.5 72B Instruct.
| Field | Qwen 2.5 72B Instruct | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Lowest input, per 1M | $0.23 +4.5% | $0.22 |
| Median input, per 1M | $0.36 | $0.36 +0.4% |
| Lowest output, per 1M | $0.40 | $0.80 +100% |
| Median output, per 1M | $0.40 | $1.58 +293.8% |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $0.31 | $0.38 +22.6% |
| Context | 131K +50% | 262K |
| Max output | 16K +93.8% | 262K |
| Providers | 11 +52.2% | 23 |
| Regions | US | EU, US |
| Accepts | text | audio, image, text, video |
| Returns | text | text |
| Type | Text models | Text models |
| Free option | no | no |
| Cheapest provider | requesty | google-vertex |
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, deepinfra, edenai, fastrouter, huggingface, jiekou, kilo, openrouter, requesty, siliconflow, trustedrouter
Frequently asked questions
Which is cheaper, Qwen 2.5 72B Instruct or Qwen3-Coder 480B-A35B Instruct?
Qwen3-Coder 480B-A35B Instruct is 4% cheaper than Qwen 2.5 72B Instruct on input price. Qwen 2.5 72B Instruct is 50% cheaper than Qwen3-Coder 480B-A35B Instruct on output price. Qwen 2.5 72B Instruct is 18% cheaper than Qwen3-Coder 480B-A35B Instruct on a 1M-in / 200k-out workload.
Which has the larger context, Qwen 2.5 72B Instruct or Qwen3-Coder 480B-A35B Instruct?
Qwen 2.5 72B Instruct: 131K tokens; Qwen3-Coder 480B-A35B Instruct: 262K tokens.
Where can I use both Qwen 2.5 72B Instruct and Qwen3-Coder 480B-A35B Instruct?
aihubmix, deepinfra, edenai, fastrouter, huggingface, jiekou, kilo, openrouter, requesty, siliconflow, trustedrouter