Guides
Sume guides: the API, Formats, agents, models, media tools and pricing, each answer dated and sourced.
Split an image into 2-4 editable layers by API: Qwen Image Layered
Send one picture to qwen-image-layered on Sume and get 2 to 4 transparent PNG layers, billed at $0.05 each. num_images is required; the call runs as a job.
Can Google Jules use Sume's MCP server? Not yet: use the REST API
Jules connects MCP servers through a short hand-picked list with API keys. Sume is not on the changelog list, so call the Sume REST API from the task instead.
Claude Code subagent autoCompactWindow: keep Sume job ids
Claude Code 2.1.296 lets a subagent auto-compact earlier than the main chat. Keep Sume job ids out of the summary and re-read state with jobs_status.
CLAUDE_CODE_WORKFLOW_SUBAGENT_MODEL: model choice vs Sume spend gates
Claude Code 2.1.296 can run every workflow agent on one model. Sume's idempotency_key, dry_run and max_spend_credits gates do not change with the model.
Qwen Image 2.1 rate limits: Pro 20 RPM, Turbo 120 RPM vs Sume's queue
Alibaba caps qwen-image-2.1-pro at 20 requests a minute and Turbo at 120. How long 1,000 images take at each cap, and how Sume's plan queue behaves instead.
GET /v1/balance returns available_credits: a TypeScript gate
Sume's balance read returns whole credits in available_credits, a funded or empty state, and expiring_soon_credits. Gate a job on it in TypeScript.
Best AI video model for lip-synced dialogue clips on Sume
For speech that matches the mouth, Sume offers Omni (native synced audio), H3 Max Lip Sync (audio 5-14.8 s, 10 MB max), or an avatar route. Read 2026-10-13.
Slow down for phone numbers: phrase pacing in a Sume TTS script
Decagon says Chord's pacing follows each sentence. On Sume, speed is one setting per job, so render a phone number as its own slower take and join the takes.
Eleven Multilingual v2 or Turbo v2.5 on Sume: 28 vs 31 languages
On Sume's TTS Router, Eleven Turbo v2.5 lists 31 languages, 20,000 characters and half the list price of Multilingual v2, which lists 28 languages.
Grok Imagine API pricing: xAI 8c and 2c a second, Sume 1.25c
xAI lists Grok Imagine Video 1.5 at $0.08 a second and 1.5 Lite at $0.02. Sume bills its one Grok row at 1.25 cents a second. Totals for 4 to 15 s.
HelixWorld license: Apache 2.0 code, weights and paper differ
HelixWorld's code is Apache 2.0, its weights have a separate license on Hugging Face, and the arXiv page lists CC BY-NC-SA 4.0. Read all three.
HelixWorld WASD camera moves as prompt words for Omni Flash
HelixWorld steers its camera with WASD and direction actions. Sume has no camera-key input, so write the move as a phrase and test it with a 3 s 360p draft.
Is Qwen Image 2.1 Turbo on Sume? No: use these three Qwen rows
Sume's image catalog has no Qwen-Image-2.1 Turbo row. It lists Qwen Image, Qwen Image Max and Qwen Image Layered, and one call shows which.
MAI-Transcribe-2 on OpenRouter: wav, base64, transcript JSON
OpenRouter exposes microsoft/mai-transcribe-2 at POST /api/v1/audio/transcriptions with base64 audio and returns JSON with transcript and usage.
Can Meta Muse Wonder generate images? It returns text; use /v1/images
Muse Wonder is listed on OpenRouter as a chat-completions model with text responses. It is not in Sume's image catalog; pick an image row instead.
Mistral Large 4 function calling: validate arguments against Sume
Mistral Large 4 (Public Preview) lists function calling and structured outputs. Validate its arguments with Sume's tools_schema before any paid call.
Nano Banana 2.1 8:1 and 1:8 images: banners and strips on Sume
Yes: google/nano-banana-2.1 lists 8:1, 4:1, 1:4 and 1:8, and Nano Banana Pro does not. List $0.08 per image at 1K, $0.10 billed on Sume.
Use MAI-Voice-2.1 audio in a Sume lip sync clip: import it first
MAI-Voice-2.1 is not in Sume's TTS Router, but its audio can drive a Sume talking clip if you import the file first: Sume-hosted, 10 MB, 5 to 14.8 s.
30-second AI video with sound: what it costs on Sume
Kling 3 with audio is $0.21 a second on Sume, so 30 s is $6.30 in two jobs. Compare Wan 3.0 and Seedance 2.5 for a 30-second clip with sound.
30-second video: one job, two 15 s jobs or three 10 s jobs?
Does splitting a 30-second video change the price on Sume? Compare one, two and three jobs on Seedance, Wan and Kling 3, read 2026-10-13.
Per-second vs per-token video pricing: why Seedance moves
Wan 3.0 and Omni Flash price per second; Seedance prices per video token, so frame size and aspect ratio change the bill. Worked on Sume, list x 1.25.
AI video with sound vs voiceover plus lip sync: which Sume route
Use a video model's native audio for ambient sound, and TTS plus lip sync for a talking face. Sume's docs say video models do not lip-sync a later voiceover.
Amazon Nova 2.5 Sonic: four regions, seven languages, 256K context
AWS announced Nova 2.5 Sonic on October 5, 2026: four regions, seven languages and a 256K context window for live voice agents, not rendered voiceovers.
avatar-image-to-video_create: choosing H3 Max lip sync over Fabric
On Sume MCP, avatar-image-to-video_create is the only talk tool. Its model field picks veed/fabric-1.0 (default) or minimax/h3-max/lip-sync.
Best AI video model for a consistent character: reference rows
For one character across clips, use a Sume row with reference images: Wan 3.0 (10), Omni (10), H3 and H3 Max (9). Kling 3 takes none. Read 2026-10-13.
Best AI video model for draft clips: lowest per-second rows
Cheapest drafts on Sume: Grok Imagine (image-to-video) $0.0125 a second, Omni 360p $0.0375, Wan 3.0 and H3 480p $0.0625. List x 1.25, read 2026-10-13.
Best AI video model for product videos: pick the row by input
For a product video, pick the Sume row by the photos you have: first frame, end frame or reference images. Limits for seven rows, read 2026-10-13.
Best AI video model for seamless loops: the end-frame rows
For a looping clip, use a Sume row that takes both a first and an end frame: Seedance, Wan 3.0, Kling 3, MiniMax H3 or Omni. Rows without one, read 2026-10-13.
Best AI video model for UGC-style ads: a model or an avatar?
For UGC-style ads, Sume offers two routes: a script-driven Avatar video of 4-60 s, or a video model with native speech such as Kling 3. Read 2026-10-13.
Best AI video model to edit an existing clip: four Sume rows
To edit or regenerate a clip you already have, Sume has four rows that take video_url: Omni edit, Genjutsu, H3 Max Recast and Hailuo H3 Regen. Read 2026-10-13.
Budget for 100 image ads on Sume: seven models, one image per job
100 single-image ad jobs on Sume cost $3 on Grok image or Qwen Image up to $10 on Nano Banana 2.1 at 1K. Each job rounds up to a cent.
Budget for 100 six-second video ads on Sume, by model and tier
100 six-second ads cost $23 to $853 on Sume, from Omni Flash at 360p to Seedance 2.5 at 1080p. Twelve model and tier rows, list x 1.25.
Extend a Grok Imagine video on Sume: chain by last frame
xAI's guide lists video extension from the final frame. Sume's Grok row has no extend, so pull a late frame with video-frames and start the next clip from it.
Claude Code 2.1.296: MCP tool names over 128 characters, and Sume's
Claude Code 2.1.296 leaves out an MCP tool whose name exceeds 128 characters. The longest tool name in Sume's hosted list is 28, so none are near it.
Claude MCP connector denylist: switch off Sume's paid tools
Enable all Sume tools in an mcp_toolset, then disable the paid ones by name. Anthropic recommends denylisting write tools for read-only assistants.
Claude MCP connector needs an https URL and a token: Sume's endpoint
The connector requires an MCP server URL starting with https and takes an authorization_token. Sume's hosted endpoint is https://mcp.sume.com/mcp.
Claude MCP connector supports tool calls only: how Sume results arrive
The Messages API connector supports only MCP tool calls, not resources or prompts. Fetch Sume job results with the jobs_result tool, not a resource read.
Clef takes 1 to 64 questions per request: check a brief in one call
Cloudflare's Clef page allows 1 to 64 typed questions on one state. Put the brief checks in one request, then submit to Sume once.
AI video cost per second at 1080p on Sume, six models ranked
One second of 1080p on Sume: Omni Flash $0.1875, Wan 3.0 $0.25, H3 Max $0.20, Kling 3 $0.14 silent. List x 1.25, read 2026-10-13.
Cheapest AI video per second at 480p on Sume, ranked
At 480p Sume Grok Imagine is $0.0125 a second, Omni Flash 360p $0.0375, then Wan 3.0 and H3 at $0.0625. Ranked, list x 1.25, read 2026-10-13.
AI video cost per second at 720p on Sume: the models table
What one second of 720p AI video costs on Sume by model, from the repo price tables at list x 1.25, read 2026-10-13. Seedance 2.5 is $0.5778.
Decagon Chord's 45.7% human test: what the number measures
In Decagon's test, 45.7% of listeners thought the real human voice was the AI. That is a customer-call result, not proof for ad voiceover.
Is Decagon Chord a public API? What Decagon has published
Decagon introduced Chord on October 1, 2026 as the speech model inside Voice 3. Its post does not state a public API, so a voiceover job needs another model.
Detect a new video model on Sume: a Python diff of /v1/videos/models
Grok Imagine 1.5 Lite is on xAI's price table, not Sume's. A short Python script diffs GET /v1/videos/models against a saved list to flag new ids.
Edit a video with a prompt API: Python script for Omni Flash 1.1
Send a clip and a sentence to POST /v1/video-router/generate with gemini-omni-flash-1.1 and video_url, poll the job, read the result. Stdlib Python.
Every Sume image model compared: edit, text-only, n and formats
Sume's repo catalog lists 20 image rows: 14 take edit references, 5 are text-only, 1 makes layers. Grok is capped at n 1; Recraft is webp only.
Gemini Omni edit returns 400: the five field mistakes on Sume
A video_url edit on gemini-omni-flash-1.1 fails with 400 when you add aspect_ratio, generate_audio false, bitrate_mode, reference audio, or other media. Fixes.
Omni Flash 1.1 vs Wan 3.0 per second: which is cheaper at each tier?
At 720p Omni Flash 1.1 and Wan 3.0 both cost $0.125 a second on Sume. At 1080p Omni is $0.1875 against $0.25. Tier-by-tier table, list x 1.25.