Sume vs HeyGen: avatar video, agents, and API pricing compared

HeyGen and Sume both generate talking-avatar video, both have an agent that turns a prompt into a finished video, and both sell API access with a hosted MCP server. HeyGen is built around avatar video, with long videos, translation, and 4K export on higher plans. Sume is a video agent platform where avatars are one tool next to a multi-model video catalog, and where a finished workflow becomes a Format your backend calls.

HeyGen facts come from HeyGen's own pages, read on 2026-09-24. Sume facts come from Sume's docs, pricing page, and public catalog.

What is HeyGen?

HeyGen's homepage says: “Create AI videos from your ideas using HeyGen. Input text, image, or audio to create complete videos with narration, captions, visuals, and animations.” Its Video Agent is pitched as “a creative agent doing the work for you.”

• Avatars: stock video avatars, photo avatars, and custom digital twins, with 175+ languages and dialects on paid plans (pricing).
• Translation: “Voice cloning preserves your unique tone and delivery in 175+ languages and dialects, while precise lip-sync aligns translated speech with facial movements” (home).
• API: base URL https://api.heygen.com with an X-Api-Key header (quick start); jobs are asynchronous, with webhooks as an alternative to polling (webhooks); batch endpoints take up to 100 requests per call (developers).
• Coding agents: a CLI that wraps the v3 API, and a hosted MCP server that needs “no API key and nothing to install. Usage draws on your existing HeyGen plan's credits.”

What is Sume?

Sume is a video agent platform: people brief an agent in the Agents tab, save the result as a reusable Format, and call that Format, the agent, or individual models from their own backend over one API, a hosted MCP server, a CLI, and a TypeScript SDK, all billed from one wallet.

• Agents: a chat workspace at sume.com/agents where the agent plans a video, asks before it spends, and generates stills, avatars, voice, lip-sync, and a finished timeline.
• Formats: a saved recipe your backend calls with POST /v1/formats/{handle}/{slug}/runs, plus 27 ready-made Formats at the sume handle. See What is a Sume Format?.
• Models: an OpenRouter-compatible POST /v1/videos endpoint over a catalog of video models, with sume/auto routing, plus image, music, speech, and Avatar 1.0.
• Avatar 1.0: create a reusable avatar ($0.95 per avatar) and generate 4–60 second talking videos at $0.184/s standard, $0.245/s plus, $0.55/s max (no product image).
• Developer surfaces: the Developer API, a hosted MCP server for Claude Code, Cursor, and Codex, a CLI, and a TypeScript SDK.
• Plans are Free $0, Pro $40 / month, Startup $120 / month, Scale $400 / month. Usage draws from one prepaid wallet at each model's published USD rate plus a 5.5% agent fee by default; routed video models are priced at the provider's list price × 1.25. The public catalog states both.

How do Sume and HeyGen compare?

How does HeyGen's pricing compare with Sume's?

HeyGen splits billing in two. Subscription plans cover the web app, and the API is pay-as-you-go: “any user—including free users—can unlock powerful avatar and video features by purchasing any amount of API credits (in USD)” (API pricing).

• HeyGen plans: Free $0 (3 videos a month, up to 1 minute), Creator $29 a month or $24 billed annually, Pro from $49 a month for 1,000 credits, Business $149 a month plus $20 per extra seat, and Enterprise through sales (pricing).
• Sume Avatar 1.0: $0.184/s standard, $0.245/s plus, $0.55/s max (no product image); creating an avatar is $0.95 per avatar. Each video is 4–60 seconds.
• Sume plans: Free $0, Pro $40 / month, Startup $120 / month, Scale $400 / month. One prepaid wallet; each model's published USD rate plus a 5.5% agent fee; routed video models at the provider's list price × 1.25. API, CLI, and MCP access from the Pro plan up.

Which one fits which job?

• HeyGen publishes longer avatar videos per plan, 4K export on Pro and up, translation with lip-sync in 175+ languages, and mobile apps. For long presenter videos and localization, those are the documented strengths.
• Sume's avatar videos are 4–60 seconds at 720p, and they sit next to a catalog of other video models, image, music, and speech in the same API and wallet. For short product and UGC-style clips that mix an avatar with other generated shots, Sume's agent assembles the whole timeline.
• For repeatable backend jobs, a Sume Format is one HTTP call per run with an idempotency key, a spend cap, and an optional webhook.

How do I try Sume?

Start a thread in the Agents tab, or create an API key and follow the quick start. Plans and per-model rates are on Pricing and API pricing; How Sume pricing works explains the wallet.

Vendor details change often. Everything we say about other products here comes from their own pages as of 2026-09-24; check those pages before you decide.