Comparisons

Sume vs fal: a generative media API or a video agent platform

fal runs 1,000+ image, video, and audio models behind one API. Sume adds a video agent, Formats, and avatars to a multi-model API. How the two surfaces differ.

6 min readSume
All posts

fal and Sume are both APIs for generating media, but they sit at different layers. fal is a generative media platform: a large model catalog, a queue API, SDKs, and serverless hosting, priced per output. Sume is a video agent platform: a smaller video catalog, plus an agent that plans whole videos, Formats your backend calls, Avatar 1.0, and timeline assembly, billed from one wallet.

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

What is fal?

fal's homepage says: “Generative media platform for developers. The world's best generative image, video, and audio models, all in one place.” It adds: “Choose from 1,000+ production ready image, video, audio and 3D models.”

  • API: “Asynchronous inference is the recommended way to call models on fal,” through a persistent queue you poll or take by webhook (queue, webhooks).
  • SDKs: client libraries for Python, JavaScript, Swift, Kotlin/Java, and Dart (client libraries).
  • Coding agents: a hosted MCP server at https://mcp.fal.ai/mcp (MCP) and the genmedia CLI, which “gives any terminal, script, or AI agent direct access to fal's 1,000+ models” (genmedia).
  • Pipelines: “Workflows let you chain multiple models together into a single endpoint” (workflows). fal Agent, in Early Access, “plans and runs generative media work across every top image, video, audio, and 3D model on fal.”

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 fal compare?

Sume column: Sume docs, Pricing, and the public catalog. fal column: fal's own pages, read 2026-09-24 (links under Sources). Rows we could not verify on both sides are left out.
ComparedSumefal
Catalogseedance-2.5, seedance-2-mini, seedance-2, seedance-2-fast, kling-3, wan-3.0, grok-imagine-video-1.5, minimax-h3, minimax-h3-max, gemini-omni-flash-1.1, or sume/auto to let Sume pick1,000+ image, video, audio, and 3D models
APIREST API at api.sume.com with a Bearer key; async jobs you poll or take by signed webhook; Idempotency-Key on createsQueue API you poll or take by webhook
SDKsTypeScript SDK (@sume-com/sdk)Python, JavaScript, Swift, Kotlin/Java, Dart
MCP and CLIHosted MCP at mcp.sume.com/mcp; OAuth (read-only unless you grant write) or an API key; Sume CLIHosted MCP at mcp.fal.ai/mcp; genmedia CLI
AgentAgents tab: the agent plans the video, asks before it spends, and can save the result as a reusable Formatfal Agent (Early Access) plans and runs work across fal's models
BillingOne prepaid wallet; each model's published USD rate plus a 5.5% agent fee; routed video models at the provider's list price × 1.25Per output (per second of video or per video); prepaid credits, invoicing for higher volume

What does video cost on fal?

fal says “Video generation models charge per second of generated video or a flat rate per video” and “fal uses a prepaid credit model” (pricing, FAQ). Three published examples:

  • On Sume, routed video models are billed at the provider's list price × 1.25 plus the agent fee, and the plan ladder is Free $0, Pro $40 / month, Startup $120 / month, Scale $400 / month. Exact per-model rates are in the catalog and on API pricing.
fal model prices in USD from each model page, read 2026-09-24. fal notes some prices are approximations of a token formula.
Model on falPublished price
Veo 3.1$0.20/s without audio, $0.40/s with audio (720p or 1080p)
Kling Video v3 Pro, text to video$0.112/s audio off, $0.168/s audio on
Seedance 2.0, text to video$0.3034/s at 720p, $0.682/s at 1080p

Which one fits which job?

  • fal fits when you want direct access to a very large model catalog, SDKs in several languages, or serverless hosting for your own apps, billed per second while runners are alive.
  • Sume fits when the deliverable is a finished video rather than one clip: its agent plans the shots, voice, avatar, and timeline, and a saved Format turns that into one API call with an idempotency key, a spend cap, and an optional webhook.
  • Both run a hosted MCP server that coding agents can connect to.

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.

Sources

Related posts

Written by Sume