AI Rate CardQwen3.5 35B-A3B vs Qwen3.5 4B: API price and specs
Qwen3.5 4B is 47% cheaper than Qwen3.5 35B-A3B on input price.
Qwen3.5 4B is 84% cheaper than Qwen3.5 35B-A3B on output price.
Qwen3.5 4B is 70% cheaper than Qwen3.5 35B-A3B on a 1M-in / 200k-out workload.
| Field | Qwen3.5 35B-A3B | Qwen3.5 4B |
|---|---|---|
| Lowest input, per 1M | $0.0564 +88% | $0.03 |
| Median input, per 1M | $0.14 +211.1% | $0.045 |
| Lowest output, per 1M | $0.45 +544.6% | $0.07 |
| Median output, per 1M | $1.00 +809.1% | $0.11 |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $0.15 +233.3% | $0.044 |
| Context | 262K | 262K |
| Max output | 262K | 262K |
| Providers | 19 | 5 +73.7% |
| Regions | GLOBAL, US | TH |
| Accepts | 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 | image, text, video |
| Returns | text | text |
| Type | Text models | Text models |
| Free option | no | yes |
| Cheapest provider | aihubmix | 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, empiriolabs, mixlayer, requesty, trustedrouter
Frequently asked questions
Which is cheaper, Qwen3.5 35B-A3B or Qwen3.5 4B?
Qwen3.5 4B is 47% cheaper than Qwen3.5 35B-A3B on input price. Qwen3.5 4B is 84% cheaper than Qwen3.5 35B-A3B on output price. Qwen3.5 4B is 70% cheaper than Qwen3.5 35B-A3B on a 1M-in / 200k-out workload.
Which has the larger context, Qwen3.5 35B-A3B or Qwen3.5 4B?
Qwen3.5 35B-A3B: 262K tokens; Qwen3.5 4B: 262K tokens.
Where can I use both Qwen3.5 35B-A3B and Qwen3.5 4B?
deepinfra, empiriolabs, mixlayer, requesty, trustedrouter