# HeyGen's Avatar V model now available via API

By Steven Van · 2026-05-20

Priced at $0.05 per second; HeyGen says it beat Veo 3.1, Kling O3 Pro, OmniHuman 1.5 and Seedance 2.0 on talking-head benchmarks.

HeyGen's [HeyGen](<https://creatorstoolbox.com/tools/heygen>) Avatar V model is now available through the API at $0.05 per second. The company says it benchmarked the model against Veo 3.1, Kling O3 Pro, OmniHuman 1.5 and Seedance 2.0 on cross-scene talking-head generation, and Avatar V won every category. Developers building on avatar video can now access what HeyGen calls its highest-quality model directly, priced per second of output. [See the announcement](<https://x.com/i/status/2056781720842899794>).

[View media](<https://video.twimg.com/amplify_video/2056770446486605824/vid/avc1/1280x720/Ap1BGuyBJ_M6pbhK.mp4>)

![HeyGen](<https://unavatar.io/heygen.com?fallback=false>)

HeyGen

Talking-head videos from AI avatars — pick from hundreds or build your own from a clip, script in 40+ languages, and translate with lip sync intact.

[View HeyGen →](<https://creatorstoolbox.com/tools/heygen>)

[Read HeyGen's Avatar V model now available via API on Creators Toolbox](<https://creatorstoolbox.com/blog/heygen-avatar-v-api-at-0-05-sec>)

---
Canonical source: https://creatorstoolbox.com/blog/heygen-avatar-v-api-at-0-05-sec