AI Rate CardQwen2.5-VL 72B Instruct vs voxtral-small-2507: API price and specs
voxtral-small-2507 is 80% cheaper than Qwen2.5-VL 72B Instruct on input price.
voxtral-small-2507 is 26% cheaper than Qwen2.5-VL 72B Instruct on output price.
voxtral-small-2507 is 71% cheaper than Qwen2.5-VL 72B Instruct on a 1M-in / 200k-out workload.
Qwen2.5-VL 72B Instruct has a 290.6% larger context than voxtral-small-2507.
| Field | Qwen2.5-VL 72B Instruct | voxtral-small-2507 |
|---|---|---|
| Lowest input, per 1M | $0.50 +400% | $0.10 |
| Median input, per 1M | $1.01 +818.2% | $0.11 |
| Lowest output, per 1M | $0.50 +35.5% | $0.37 |
| Median output, per 1M | $1.01 +152.5% | $0.40 |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $0.60 +245.3% | $0.17 |
| Context | 128K | 33K +74.4% |
| Max output | 115K | 32K +72.2% |
| 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 | audio, 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 voxtral-small-2507?
voxtral-small-2507 is 80% cheaper than Qwen2.5-VL 72B Instruct on input price. voxtral-small-2507 is 26% cheaper than Qwen2.5-VL 72B Instruct on output price. voxtral-small-2507 is 71% 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 voxtral-small-2507?
Qwen2.5-VL 72B Instruct: 128K tokens; voxtral-small-2507: 33K tokens.
Where can I use both Qwen2.5-VL 72B Instruct and voxtral-small-2507?
cortecs, edenai