AI Rate CardQwen2.5-VL 72B Instruct vs Pixtral 12B: API price and specs
Pixtral 12B is 70% cheaper than Qwen2.5-VL 72B Instruct on input price.
Pixtral 12B is 70% cheaper than Qwen2.5-VL 72B Instruct on output price.
Pixtral 12B is 70% cheaper than Qwen2.5-VL 72B Instruct on a 1M-in / 200k-out workload.
| Field | Qwen2.5-VL 72B Instruct | Pixtral 12B |
|---|---|---|
| Lowest input, per 1M | $0.50 +233.3% | $0.15 |
| Median input, per 1M | $1.01 +418.6% | $0.19 |
| Lowest output, per 1M | $0.50 +233.3% | $0.15 |
| Median output, per 1M | $1.01 +418.6% | $0.19 |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $0.60 +233.3% | $0.18 |
| Context | 128K | 128K |
| Max output | 115K | 4K +96.4% |
| Providers | 10 | 2 +80% |
| Regions | EU | EU, GLOBAL |
| Accepts | 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 |
| Returns | text | text |
| Type | Text models | Text models |
| Free option | no | no |
| Cheapest provider | aihubmix | edenai |
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, Qwen2.5-VL 72B Instruct or Pixtral 12B?
Pixtral 12B is 70% cheaper than Qwen2.5-VL 72B Instruct on input price. Pixtral 12B is 70% cheaper than Qwen2.5-VL 72B Instruct on output price. Pixtral 12B is 70% cheaper than Qwen2.5-VL 72B Instruct on a 1M-in / 200k-out workload.
Which has the larger context, Qwen2.5-VL 72B Instruct or Pixtral 12B?
Qwen2.5-VL 72B Instruct: 128K tokens; Pixtral 12B: 128K tokens.
Where can I use both Qwen2.5-VL 72B Instruct and Pixtral 12B?
cortecs, edenai