AI Rate CardHappyHorse-1.1 vs Wan 2.6: API price and specs
Wan 2.6 has a 9665.6% larger context than HappyHorse-1.1.
| Field | HappyHorse-1.1 | Wan 2.6 |
|---|---|---|
| Lowest input, per 1M | — | — |
| Median input, per 1M | — | — |
| Lowest output, per 1M | — | — |
| Median output, per 1M | — | — |
| Lowest unit price | $0.13 / second +30% | $0.10 / second |
| Cost of 1M in + 200k out | — | — |
| Context | 4K +99% | 400K |
| Max output | — | 4K |
| Providers | 3 | 3 |
| Regions | — | — |
| Accepts | image, text, video | audio, image, text, video |
| Returns | video | video |
| Type | Video | Video |
| Free option | no | no |
| Cheapest provider | — | — |
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 has the larger context, HappyHorse-1.1 or Wan 2.6?
HappyHorse-1.1: 4K tokens; Wan 2.6: 400K tokens.
Where can I use both HappyHorse-1.1 and Wan 2.6?
empiriolabs, fastrouter, ofox