Anam session limit per plan vs Sume's 4-60 second window
Anam caps one live session by plan, from 3 minutes on Free to 2 hours on Growth. Sume limits each avatar request to a 4-60 second estimated script.
The two limits count different things. Anam's conversation limit caps how long one live session can run on your plan. Sume's avatar limit applies to one request: the script or plan must estimate at 4-60 seconds, whatever your account.
Anam facts are from its pricing page; Sume facts from Generate avatar video and Jobs and results, read 2026-10-01.
What is Anam's conversation limit?
The pricing page says a conversation limit is the maximum length of a single session: 3 minutes on Free, 5 on Starter, 10 on Explorer, and up to 2 hours on Growth and Professional. Enterprise has no limit.
| Plan or route | Per-unit limit |
|---|---|
| Anam Free / Starter / Explorer | 3 / 5 / 10 min per session |
| Anam Growth / Professional | Up to 2 h per session |
| Sume avatar request | 4-60 s estimated script or plan |
| Sume inline captions | Rejected above 60 s |
What is Sume's limit per request?
Scripts and multi-scene plans are accepted when Sume estimates the video at 4-60 seconds inclusive. Shorten longer scripts or split them into multiple jobs. Inline captions are also rejected above 60 seconds. The limit is the same for every plan in the docs; it is not tiered. See avatar video longer than 60 seconds.
Is the 30-second sync wait the same limit?
No. wait_timeout_seconds is clamped to 0..30 and only bounds how long the HTTP request blocks, not job length. Avatar videos routinely outlast it, so submit async and poll or use a webhook.
Sources
Related posts
More in Pricing
- Arcads MCP out of credits vs Sume 402 insufficient_credits
Arcads says generation fails without credits. Sume answers 402 insufficient_credits before provider work, and an MCP agent can preview cost with dry_run first.
- Cartesia Sonic 3.6 heteronyms: read, bass, live, and Sume pricing
Sonic 3.6 improves English heteronyms like read, bass and live in context. When context is enough, when to use a dictionary id, and Sume's TTS rate.
- Cheapest AI video API model on Sume: 5-second clips ranked
Grok Imagine 1.5 is the cheapest 5-second clip on Sume at 480p, then Gemini Omni Flash at 360p and Wan 3.0. Ten models ranked by reserved amount.
- Managed Agents budget_reached vs Sume generation_spend_cap_usd
A Managed Agents session budget caps spend at list rates and pauses with budget_reached. Sume's generation_spend_cap_usd is a separate required cap.
Written by Sume