5 models · video
HeyGen API
HeyGen is a family of AI video models. varg runs 5 of them on one API key: HeyGen Avatar IV, HeyGen Avatar, HeyGen Avatar V and 2 more. Between them they cover avatar, text to video, image to video and video to video; they return video.
- HeyGen Avatar IV
- $0.0667/s
- Flagship id
heygen_avatar_iv
Every HeyGen model runs on one varg API key and one credit balance, the same as every other model here. You pay the provider's price, with no markup.
curl -X POST https://api.varg.ai/v2/tools/video/call \
-H "Authorization: Bearer $VARG_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "heygen_avatar_iv"
}'HeyGen models and prices
Prices are in US dollars and are the provider's own, with no markup. A "from" price is the cheapest request the catalog states for that model; each model's page has every rate and input. The descriptions are the catalog's own, shortened.
| Model | Catalog description | Takes | Price | Typical time |
|---|---|---|---|---|
HeyGen Avatar IVheygen_ | HeyGen Interactive Avatar. Next-gen avatar with improved visual fidelity. | Avatar | $0.0667/s | ~3 min |
HeyGen Avatarheygen_ | HeyGen AI avatar video. Generate talking avatar videos from text scripts. | Avatar | $0.05/s | ~3 min |
HeyGen Avatar Vheygen_ | HeyGen Avatar V. Talking avatar video, billed per second. | — | $0.0667/s | ~3 min |
HeyGen Image to Videoheygen_ | HeyGen avatar video made from an image, billed per second. | Avatar | $0.05/s | ~3 min |
HeyGen Video 1heygen_ | HeyGen Video 1. Text, image and multi-reference video with generated sound, 5-15 seconds up to 2K. | Text to video, Image to video, Video to video | From $0.10 per runfrom $0.02/s | ~2 min |
Call the HeyGen API
The call below runs HeyGen Avatar IV. For another HeyGen model, put its id from the table in "model"; the rest of the request keeps its shape.
REST
POST https://api.varg.ai/v2/tools/video/call with Authorization: Bearer $VARG_API_KEY. It answers 202 with a job right away; poll GET /v2/jobs/{id} until its status is completed, then read output.outputs[0].url.
curl -X POST https://api.varg.ai/v2/tools/video/call \
-H "Authorization: Bearer $VARG_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "heygen_avatar_iv"
}'From Claude, ChatGPT or Cursor (MCP)
The varg MCP server, https://mcp.varg.ai/mcp, runs HeyGen Avatar IV with call_tool. Sign in with varg, no API key to paste. How to connect it
claude mcp add --transport http varg https://mcp.varg.ai/mcp{
"tool": "video",
"input": {
"model": "heygen_avatar_iv"
},
"wait": true
}From a terminal (CLI)
vargai is the varg command line: every tool of the MCP server is a command. Install and log in
curl -fsSL https://varg.ai/install | sh
vargai call_tool --tool video '{"model":"heygen_avatar_iv"}'How billing works
Every model is billed at its provider's price with no markup, from one credit balance: 1 credit is $0.01. varg's fee is on the top-up, not on the run: 5.5% of the credits you buy ($0.80 at the least), or 8% for a team workspace. Pricing
How to use HeyGen
Step-by-step pages on varg how to.
HeyGen API: questions
- How much does the HeyGen API cost on varg?
- Among the HeyGen models with a stated run price, the lowest is from $0.10 per run (from $0.02/s), on HeyGen Video 1. HeyGen Avatar IV ($0.0667/s), HeyGen Avatar ($0.05/s), HeyGen Avatar V ($0.0667/s) and HeyGen Image to Video ($0.05/s) are billed by rate with no stated minimum, so a short request can cost less. Every model is billed at its provider's price with no markup, from one credit balance: 1 credit is $0.01. For the exact price of a request before you run it, send the same body to POST https://api.varg.ai/v2/estimate.
- Which HeyGen models are on varg?
- 5: HeyGen Avatar IV ($0.0667/s), HeyGen Avatar ($0.05/s), HeyGen Avatar V ($0.0667/s), HeyGen Image to Video ($0.05/s) and HeyGen Video 1 (from $0.10 per run). Each has its own page with the parameters and a call to copy.
- Which HeyGen models take an image?
- 1 of the 5: HeyGen Video 1. The catalog lists image to video for it; pass the image as a URL in "files".
- What is the longest clip the HeyGen models make?
- 15 seconds, on HeyGen Video 1, by the models' input schemas.
- How long do HeyGen requests take?
- Typically from about 2 min (HeyGen Video 1) to about 3 min (HeyGen Avatar IV), by the catalog's estimates for each model's fastest route. The API answers at once with a job id, so nothing waits on an open connection while it runs.
- How do I call the HeyGen API?
- Send POST https://api.varg.ai/v2/tools/video/call with the header "Authorization: Bearer $VARG_API_KEY" and a JSON body that includes "model", for example "model": "heygen_avatar_iv". The call answers 202 with a job right away. Poll GET https://api.varg.ai/v2/jobs/{id} until "status" is "completed", then read output.outputs[0].url, or pass options.webhook_url to be called back.
- Can I use HeyGen from Claude, ChatGPT or Cursor?
- Yes. Add the varg MCP server (https://mcp.varg.ai/mcp) to Claude, ChatGPT, Cursor or any other MCP client and sign in with varg, with no API key to paste. The agent runs a model with call_tool, passing tool "video" and the model id, for example "model": "heygen_avatar_iv".
More model APIs
Same API key, same request shape: change the model string to switch.
For AI agents: each model above has its full spec as Markdown at varg.ai/models/heygen_avatar_iv.md (swap the id), and every model is listed in varg.ai/models/llms.txt.