As of: 2026-10-25 23:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/heygen-video-1/

# HeyGen Video 1

HeyGen, HeyGen Video family. Status: current. Type: video generation. Released: 2026-09-30.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| HeyGen API | `heygen-video-1` | https://api.heygen.com/v3/models/videos | https://developers.heygen.com/docs/models/heygen-video |
| OpenRouter | `heygen/heygen-video-1` |  |  |
| Web app |  |  | https://app.heygen.com/apps/creative-studio/video |

## Pricing

- T2v i2v per second 480p: $0.01
- T2v i2v per second 768p: $0.018
- T2v i2v per second 1080p 2k: $0.05
- Ref2v per second 480p: $0.035
- Ref2v per second 768p: $0.05
- Ref2v per second 1080p 2k: $0.09
- Unit as published: USD per second of output video, API launch promotion (50% off; HeyGen says list price is double these rates)
- Source: https://help.heygen.com/en/articles/10060327-heygen-api-pricing-explained
- Last checked: 2026-10-25

## Specs

- Input: text, image, video, audio
- Output: video, audio
- Context window: not published
- Max output: not published
- Open weights: no
- Licence: proprietary

## Where it stands

- Newer video generation models in the registry since its release: 3:
  - FLUX 3 Max (2026-10-19) https://postcutoff.com/m/flux-3-max/
  - Kling 4.0 (and 4.0 Flash) (2026-10-15) https://postcutoff.com/m/kling-4-0/
  - Tavus Griffin (Human Interaction Model) (2026-10-01) https://postcutoff.com/m/tavus-griffin/
- Closed weights; access is hosted only.

## What stands out

- Whole scene with sound in one pass: General-purpose (non-avatar) model: picture, dialogue, ambience and sound effects generated together; AAC 32 kHz stereo in MP4. Source: https://www.heygen.com/blog/introducing-heygen-video
- Text, image and reference modes: text_to_video, image_to_video and reference_to_video (default), with up to 9 images, 3 videos and 3 audio references (12 total). Source: https://developers.heygen.com/docs/models/heygen-video
- Up to 30 s and 2K (added after launch) (found after launch): October 2026 updates added auto duration (8-30 s from quoted dialogue), 5-30 s for t2v/i2v with turbo or quality enhancement, and 1080p and 2K outputs (billed at 3x 768p). Source: https://developers.heygen.com/changelog?page=4

## Notes

Artificial Analysis text-to-video leaderboard (read 2026-10-25): #3, Elo 1160; AA price 2.40 USD per minute of 1080p (AA lists release Oct 2026). Released 2026-09-30 per OpenRouter's model listing (created date) and HeyGen's changelog ('September 2026'); no dated HeyGen post seen. HeyGen's blog quotes the API launch price as 0.01 USD/s through October and other HeyGen blog posts give 0.03/s list at 768p, conflicting with the help-center table (list = 2x shown); post-promo prices from November 2026 not verified. Free playground: 2 five-second clips per day with a HeyGen account. Also on Civitai's generator from 2026-10-13 (reported by aipicks.jp, not verified). No timeline entry.

HeyGen's first general-purpose video model (not its avatar engine): text, image or reference to video with native dialogue and effects, 480p-2K. Async API: POST /v3/models/videos with an x-api-key header, then GET /v3/models/videos/{video_id} until completed.

Artificial Analysis text-to-video (with audio) leaderboard, read 2026-10-25: rank 3, Elo 1160 (https://artificialanalysis.ai/video/leaderboard/text-to-video).

Sources: https://www.heygen.com/blog/introducing-heygen-video · https://developers.heygen.com/docs/models/heygen-video · https://developers.heygen.com/changelog?page=4 · https://help.heygen.com/en/articles/10060327-heygen-api-pricing-explained · https://openrouter.ai/heygen/heygen-video-1

Model page: https://postcutoff.com/m/heygen-video-1/