AI Rate CardQwen3 VL 235B A22B Thinking vs Qwen3.5 122B-A10B: API price and specs
Qwen3.5 122B-A10B is 59% cheaper than Qwen3 VL 235B A22B Thinking on input price.
Qwen3.5 122B-A10B is 67% cheaper than Qwen3 VL 235B A22B Thinking on output price.
Qwen3.5 122B-A10B is 64% cheaper than Qwen3 VL 235B A22B Thinking on a 1M-in / 200k-out workload.
| Field | Qwen3 VL 235B A22B Thinking | Qwen3.5 122B-A10B |
|---|---|---|
| Lowest input, per 1M | $0.27 +143.3% | $0.11 |
| Median input, per 1M | $0.42 +62.3% | $0.26 |
| Lowest output, per 1M | $2.74 +204.2% | $0.90 |
| Median output, per 1M | $3.95 +79.5% | $2.20 |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $0.82 +180.8% | $0.29 |
| Context | 262K | 262K |
| Max output | 41K +84.4% | 262K |
| Providers | 6 +68.4% | 19 |
| Regions | — | CH, EU, GLOBAL, US |
| Accepts | image, image/bmp, image/heic, image/jpeg, image/png, image/tiff, image/webp, text | 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 | aihubmix | 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
aihubmix, deepinfra, huggingface, kilo, orcarouter, trustedrouter
Frequently asked questions
Which is cheaper, Qwen3 VL 235B A22B Thinking or Qwen3.5 122B-A10B?
Qwen3.5 122B-A10B is 59% cheaper than Qwen3 VL 235B A22B Thinking on input price. Qwen3.5 122B-A10B is 67% cheaper than Qwen3 VL 235B A22B Thinking on output price. Qwen3.5 122B-A10B is 64% cheaper than Qwen3 VL 235B A22B Thinking on a 1M-in / 200k-out workload.
Which has the larger context, Qwen3 VL 235B A22B Thinking or Qwen3.5 122B-A10B?
Qwen3 VL 235B A22B Thinking: 262K tokens; Qwen3.5 122B-A10B: 262K tokens.
Where can I use both Qwen3 VL 235B A22B Thinking and Qwen3.5 122B-A10B?
aihubmix, deepinfra, huggingface, kilo, orcarouter, trustedrouter