Side by side

See the difference.

Scores, capabilities and costs for the models you’re considering.

Scroll to compare models →

Comparison of Alibaba: Wan 3.0, Together: Tev1 4B Experimental, MiniMax H3 Max Text to Video
3 modelsalibabaAlibaba: Wan 3.0Remove ×togethercomputerTogether: Tev1 4B ExperimentalRemove ×minimaxMiniMax H3 Max Text to VideoRemove ×
What’s differentCan choose clip duration from the prompt; toggle generated audio, prompt expansion and extra thinking before rendering.Tev1 4B Experimental is an experimental decision model from Together AI, a supervised fine-tune of Qwen3.5-4B trained to choose one option from a structured state, question, and list of 2-24...Uses native 480P/768P generation or 1080P latent refinement; supports supplied soundtracks and selectable prompt expansion.
DateAug 19, 2026ReleasedSep 30, 2026ListedAug 26, 2026Released
Listed rate$0.05/ secondDeepInfra · all routes ↗480P · $ cost per second · output second$0.042 in / $0.00 out/ 1M tokensOpenRouter · all routes ↗See provider quotes
Provider endpoints2 endpoints →1 endpoint →0 endpoints →
AA Video + Audio ↗2.11,173.29 ↗Text-to-video · audio evaluated · all categoriesIndependent result95% CI 1,157.29–1,189.29 · n=5,682Not reported1,155.56 ↗Text-to-video · audio evaluated · all categoriesIndependent result95% CI 1,139.56–1,171.56 · n=5,440
AA Video Silent ↗2.11,135.19 ↗Text-to-video · silent evaluation · all categoriesIndependent result95% CI 1,116.19–1,154.19 · n=3,890Not reported1,118.75 ↗Text-to-video · silent evaluation · all categoriesIndependent result95% CI 1,101.75–1,135.75 · n=5,734
Context window—32.8K—
Max output—8—
Parameters—4B—
Structured outputSupportedNot reportedNot reported
Image inputSupportedNot reportedNot reported
Audio inputSupportedNot reportedNot reported
Video inputSupportedNot reportedNot reported
Open weightsNot reportedSupportedNot reported

Add another model

Search all models →