AI Rate CardQwen3 Omni 30B A3B Thinking vs Qwen3.5 122B-A10B: API price and specs
Qwen3.5 122B-A10B is 55% cheaper than Qwen3 Omni 30B A3B Thinking on input price.
Qwen3.5 122B-A10B is 7% cheaper than Qwen3 Omni 30B A3B Thinking on output price.
Qwen3.5 122B-A10B is 34% cheaper than Qwen3 Omni 30B A3B Thinking on a 1M-in / 200k-out workload.
Qwen3.5 122B-A10B has a 300% larger context than Qwen3 Omni 30B A3B Thinking.
| Field | Qwen3 Omni 30B A3B Thinking | Qwen3.5 122B-A10B |
|---|---|---|
| Lowest input, per 1M | $0.25 +122% | $0.11 |
| Median input, per 1M | $0.26 | $0.26 +1.2% |
| Lowest output, per 1M | $0.97 +7.7% | $0.90 |
| Median output, per 1M | $1.00 | $2.20 +120.7% |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $0.44 +51.7% | $0.29 |
| Context | 66K +75% | 262K |
| Max output | 16K +93.8% | 262K |
| Providers | 2 +89.5% | 19 |
| Regions | — | CH, EU, GLOBAL, US |
| Accepts | audio, image, text, video | audio, image, image/bmp, image/heic, image/jpeg, image/png, image/tiff, image/webp, text, video, video/mp4, video/quicktime, video/x-flv, video/x-matroska, video/x-ms-wmv, video/x-msvideo |
| Returns | text | text |
| Type | Text models | Text models |
| Free option | no | no |
| Cheapest provider | novita | 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, Qwen3 Omni 30B A3B Thinking or Qwen3.5 122B-A10B?
Qwen3.5 122B-A10B is 55% cheaper than Qwen3 Omni 30B A3B Thinking on input price. Qwen3.5 122B-A10B is 7% cheaper than Qwen3 Omni 30B A3B Thinking on output price. Qwen3.5 122B-A10B is 34% cheaper than Qwen3 Omni 30B A3B Thinking on a 1M-in / 200k-out workload.
Which has the larger context, Qwen3 Omni 30B A3B Thinking or Qwen3.5 122B-A10B?
Qwen3 Omni 30B A3B Thinking: 66K tokens; Qwen3.5 122B-A10B: 262K tokens.
Where can I use both Qwen3 Omni 30B A3B Thinking and Qwen3.5 122B-A10B?
novita, trustedrouter