Heygen · Avatar model

HeyGen Avatar / Video Agent

HeyGen turns a text prompt or script into a fully rendered avatar video

Generate on Coinis Read the docs

One API key. Every model.

per second
Example
AI avatar
Commercial use included Verified May 26, 2026 Outputs are yours No training on your data
Endpoints

Start building with HeyGen Avatar / Video Agent.

One model. Three ways to call it. Same key, same bill.

HeyGen Avatar IV (Photo Avatar)

Avatar

One call. Same key. Same bill.

$0.09 / second

HeyGen Video Agent (Prompt to Video)

Avatar

One call. Same key. Same bill.

$0.51 / call

Capabilities

What it does best.

HeyGen capabilities

Avatars

  • Photo Avatar IV/V generation at 720p and 1080p, billed at $0.085/sec on Coinis[^1]
  • Photo Avatar IV/V also available at 4K resolution, billed at a higher per-second rate direct from HeyGen[^2]
  • Digital Twin and Studio Avatar (Avatar IV/V) at 720p/1080p and 4K. Enterprise plan required to create Digital Twins via API[^3]

Video Agent modes

  • Generate mode: fire-and-forget single API call. One prompt produces avatar selection, scripting, scene composition, and rendering[^4]
  • Chat mode: multi-turn session. The agent can pause, accept revisions, and continue. suited for iterative production workflows[^4]

Inputs

  • Text prompt: 1 to 10,000 characters[^5]
  • File attachments: images, video, audio, and PDFs passed as URL, asset ID, or base64. used as visual references or content sources[^5]

Controls

  • Curated Styles: visual templates controlling scene composition, pacing, and aesthetics[^6]
  • Avatar and voice overrides on top of any text prompt[^6]

Processing

  • Fully asynchronous generation. Standard tier processes at 5x to 10x the final video length (a 1-minute video takes roughly 5 to 10 minutes)[^7]
  • Enterprise plans receive priority queue access for faster throughput[^7]
  • HTTP 429 rate-limit responses include a Retry-After header. higher concurrency limits are available with API key authentication[^8]

Adjacent capabilities

  • Video Translation: three modes. Speed Audio Only, Speed Lip Sync, and Precision Lip Sync. translate and dub existing videos while preserving lip-sync[^9]
  • Lipsync API for syncing audio to existing video[^9]
  • Text-to-Speech via the Starfish model, billed per second of generated speech[^9]
API

Call HeyGen Avatar / Video Agent in three lines.

One key. One base URL. Same SDK shape you already use. 

# 1. set your key
export COINIS_API_KEY="sk_live_..."

# 2. call the model
curl https://api.app.coinis.com/v1/video/generate \
  -H "Authorization: Bearer $COINIS_API_KEY" \
  -d '{"prompt":"neon city, rain, tracking shot"}'
import { Coinis } from "@coinis/sdk";
const coinis = new Coinis(process.env.COINIS_API_KEY);

const job = await coinis.avatar.generate({
  model: "models/heygen/heygen",
  prompt: "neon city, rain, tracking shot",
});
from coinis import Coinis
coinis = Coinis(os.environ["COINIS_API_KEY"])

job = coinis.avatar.generate(
    model="models/heygen/heygen",
    prompt="neon city, rain, tracking shot",
)
Response 
{
  "id": "gen_8fa2c1",
  "status": "succeeded",
  "model": "models/heygen/heygen",
  "output": {
    "video_url": 
                "https://cdn.coinis.com/gen_8fa2c1.mp4"
              
              ,
    "format": "mp4"
  },
  "tokens_used": 10
}

Already on another provider's SDK? Change the host. Keep the call.

Pricing

Token pricing. No surprises.

One wallet across every model. No API accounts to juggle.

HeyGen Avatar / Video Agent · HeyGen Avatar IV (Photo Avatar)
0.9 tokens
per second · $0.09
Avatar model
$0.09 / second
One key. Every model. One invoice. 1 token = $0.10
8s clip ≈ 7 tokens ($0.72)
Start free. 15 tokens a week.

No credit card.

Why pay through Coinis
  • One wallet for every model. No API keys. No separate bills.
  • Generate ads. Launch to Meta. Track in one place.
  • On-brand output from your Brand Profile.

1 token = $0.10 pay-as-you-go. Less on a plan.

Standard vs Fast

Pick the run for the job.

HeyGen Avatar IV (Photo Avatar)

Final renders, studios
Resolution —
Price $0.09 / second

HeyGen Video Agent (Prompt to Video)

Rapid tests, high volume
Resolution —
Price $0.51 / call
Use cases

Two buyers. One model.

For builders

Resell every model. One key. One bill.

Unified API across video, image, audio, and LLM.

Generate 500 variants overnight.

Async queue plus webhooks. Batch at scale.

White-label the output.

Ship it under your brand. Outputs are yours.

For creatives

Ship a Reel before lunch.

Prompt to platform-native clip in minutes.

Same product. Ten formats.

One generation, every aspect ratio.

Commercial UGC without a creator.

Authentic selfie-style ads, on brand.

Talking-head sales and demo videos for high-volume pipelines Feed a script into Avatar IV and get a branded presenter video without a camera crew. At $0.085/sec on Coinis, a 30-second clip runs 30 × $0.085/sec. Teams producing hundreds of personalized sales videos per day use this path for cost-predictable output.

Single-prompt product walkthroughs Pass Video Agent one prompt. "Create a 30-second product walkthrough for a new project management app". and it handles avatar selection, scripting, and scene layout automatically.[^4] No manual scene configuration needed.

Multilingual video localization with lip-sync The Video Translation API rebuilds lip movement to match a dubbed audio track. Enterprise customers including Google, HubSpot, and Coursera use this to localize video libraries into multiple languages without re-shooting.[^10]

AI-agent-driven video pipelines HeyGen integrates with Claude, Manus, OpenAI, and custom agents via MCP for on-demand, conversational video creation.[^11] Connect your orchestration layer and trigger video generation programmatically inside existing agent workflows.

Branded content at volume for enterprise teams Enterprise plans add custom branding, Digital Twin creation via API, priority queue access, and discounted rates.[^3] Teams that need consistent presenter identity across hundreds of output videos use Digital Twin avatars to maintain brand coherence.

Renders in seconds. Set a seed. Get the same frame back.

Outputs are yours. Sell them.

Safe for paid ads.

Your prompts are never used for training.

FAQ

HeyGen Avatar / Video Agent FAQs

How much does HeyGen cost on Coinis vs. going direct to HeyGen?

On Coinis, HeyGen Avatar IV (Photo Avatar) is billed at $0.085/sec and HeyGen Video Agent is billed at $0.51/call. HeyGen's own API self-serve tier lists Photo Avatar IV at $0.05/sec and Video Agent at $0.0333/sec of output. The difference funds Coinis unified billing, a single wallet shared across all video models, and no requirement to manage a separate HeyGen API key. See the full rate card at the official docs for direct comparison.

What is the difference between HeyGen Avatar IV and HeyGen Video Agent?

Avatar IV is a talking-head endpoint. You supply a script and a photo avatar. the model renders a presenter video at 720p, 1080p, or 4K. Video Agent is a full production endpoint. You supply one text prompt and it handles avatar selection, scripting, scene composition, and rendering automatically. Avatar IV gives you granular control. Video Agent gives you speed and simplicity for prompt-driven output.

Is there a HeyGen API I can call through Coinis, and how does authentication work?

Yes. Send a POST request to https://api.app.coinis.com/v1/video/generate with model set to heygen-avatar-iv or heygen-video-agent. Authentication uses your Coinis API key. no separate HeyGen credentials required. Full schema, polling instructions, and file attachment payload details are on the /models/heygen/api sub-page.

How long does HeyGen take to generate a video, and is generation synchronous or async?

Generation is fully asynchronous. On the standard tier, expect processing time of 5x to 10x the final video length. a 1-minute video typically takes 5 to 10 minutes. Enterprise plans receive priority queue access for faster processing. Poll for job status and retrieve the video URL once the job completes. Jobs still running after 24 hours indicate an error requiring support contact.

What is the best alternative to HeyGen for talking-head video, and how does HeyGen compare to Veo or Kling?

HeyGen Avatar IV is the model built for talking-head and avatar-driven video. Google Veo 3 and Kling v2 are cinematic prompt-to-video models optimized for scene generation, not presenter-style output. For a video where a human avatar delivers a script directly to camera, Avatar IV is the right fit. For cinematic B-roll, product environments, or creative scenes without a talking presenter, Veo or Kling are the available options on Coinis.

Can I create a custom avatar (Digital Twin or Photo Avatar) through Coinis?

Photo Avatar creation is available as a per-call operation on the Pay-As-You-Go tier. Digital Twin creation via API requires an Enterprise plan. Pay-As-You-Go users cannot create Digital Twins through the API. Once a Digital Twin or Photo Avatar is created, it can be used with Avatar IV generation calls on Coinis. Contact the HeyGen team directly for Enterprise plan access.

What resolutions does HeyGen support, and is 4K worth the price premium?

Avatar IV and Avatar V support 720p, 1080p, and 4K for both Photo Avatars and Digital Twin / Studio Avatars. The 4K tier carries a higher per-second rate direct from HeyGen. see the official docs at developers.heygen.com/docs/pricing for current 4K rates. For most sales and marketing videos distributed via web or social, 1080p is sufficient and more cost-efficient. 4K is worth considering for broadcast output or large-format display.

Related

Pair it with.

ChatGPT API / GPT-5.4

Model

Claude (Sonnet 4.6 / Opus 4.7 / Haiku 4.5)

Model

Deepgram Nova-3 / Aura-2

Model

All avatar models

Catalog
Upscale this Edit a frame Add a voiceover

Start free

Your wallet. Every model. One call away.

Start free. 15 tokens a week. No card.

Generate on Coinis

No credit card.

Pricing and capabilities verified 2026-05-26. Read the docs .