Guides
Sume guides: the API, Formats, agents, models, media tools and pricing, each answer dated and sourced.
Luma Ray3.2 modify: what is confirmed, and Sume's edit route
Luma's Ray3.2 notes list keyframes, 1080p, HDR and reframe but no quotable modify details. Sume's video edit route is gemini-omni-flash-1.1 with video_url.
Lyria 3 Pro or Lyria 3.5: which model id do I send?
Sume's Music Router accepts sume/music-auto, lyria-3.5 and lyria-3-pro. What each id does, how to pin one, and what Google lists for the models.
Lyria 3.5 API: model id, request and how to call it
Lyria 3.5 is in the Gemini API as lyria-3.5. Here is what Google's page says about it and how to call it from Sume with one music request.
AI music generator with vocals: Lyria 3.5 lyrics by API
Lyria 3.5 can sing. How to ask for vocals or an instrumental, steer lyrics with section tags, and read the lyrics back from a Sume music job.
Lyria 3.5 pricing: what a song costs on Google and on Sume
Google lists Lyria 3.5 at $0.08 per song on the paid tier. Sume lists its own per-generation music price. Both rate cards, side by side.
Lyria 3.5 release date: where it is available
Google announced Lyria 3.5 in the Gemini app on 2026-09-04. Where Google says you can use it, and where Sume lists it.
How long is a Lyria 3.5 song, and how do I set the length?
Lyria 3.5 makes songs of a couple of minutes, and length is set in the prompt. What Google says, what Sume rejects, and prompts that steer duration.
Can AI make a song from a voice memo or a video?
Suno v6 says it can start from a voice memo, image or video. Sume's music API takes a text prompt and one optional image, so audio and video stay outside it.
Mastodon video size limit: 99 MB, one video per post
Mastodon's docs allow a video of up to 99 MB (MP4, M4V, MOV or WebM), one per post, transcoded to H.264 at up to 1300 kbps. What that means for your export.
MCP config API key: use an environment variable, not the file
Cursor, Claude Code, Windsurf and Codex can read an MCP API key from an environment variable. Here is each client's syntax and what an unset variable does.
MCP server rate limit: per tool call or per request on Sume?
On Sume the MCP endpoint POST is a read, a tool call spends write budget once for the run it creates, and a jobs_status poll over MCP spends no write budget.
MCP-Method header: route and rate-limit MCP requests at a gateway
The 2026-07-28 MCP spec requires Mcp-Method and Mcp-Name headers on HTTP requests. How Sume counts MCP calls against its rate limits.
MCP input_required, inputResponses and multi round trip vs dry_run
MCP 2026-07-28 lets a server return input_required and the client retry with inputResponses. Sume's paid confirmation is two calls with dry_run instead.
MCP OAuth rejects a callback with no iss: what to do
Gemini CLI and Codex validate the RFC 9207 iss parameter on the OAuth callback. Which clients reject a missing iss, and what a server without iss can rely on.
MCP OAuth resource indicator: is a token bound to the server?
Sume's MCP OAuth resource audience is https://mcp.sume.com/mcp, its authorization server is the MCP origin, and the token is not an API key.
MCP roots, sampling and logging deprecated: Sume impact
The 2026-07-28 MCP spec deprecates Roots, Sampling and Logging. Sume's hosted server declares only tools, so a client calling it has nothing to migrate.
MCP Tasks extension: does Sume use it for long jobs?
No. Sume's hosted MCP server has no task handles. A paid create returns a job id, and you poll it with jobs_status or jobs_wait, then read jobs_result.
MCP tool search: how a long Sume tool list loads in Claude Code
Claude Code loads MCP tools on demand with tool search, which is on by default. What that means for Sume's long hosted tool list and how to prompt for it.
MCP tools/list ttlMs and cacheScope: what is safe to cache?
The 2026-07-28 MCP spec adds ttlMs and cacheScope to tools/list. Sume's tool list depends on the session's scopes, which is why caching it per session matters.
Unsupported MCP protocol version: the 400 from Sume's server
Sume's MCP endpoint answers an MCP-Protocol-Version it does not support with HTTP 400 and code -32600. Here is what the 2026-07-28 spec tells a client to do.
Maximum video length for Sume's media tools: 300, 900 or 1800 seconds
Each Sume media tool has its own length cap: video filter and frames 300 s, trim and audio detach 1800 s in and 900 s out, compose 300 s. The full table.
Meta Ads CLI dynamic creative: limits for videos and text
Meta's Ads CLI dynamic creative takes up to 10 videos, 10 images and 5 each of titles, bodies, descriptions and CTAs. How to size a batch of AI variants.
Meta Ads CLI video ad: upload an AI-generated MP4
Meta's Ads CLI makes a video ad from a local file with meta ads creative create --video. Download the Sume clip first, then upload; ads start paused.
Meta ads MCP server in Claude Code: the add command
Meta's docs add its ads MCP server to Claude Code with one claude mcp add line. The same session can also add Sume's hosted MCP to make the video.
Do I need a Meta developer app for the ads MCP server?
Not always: Meta says owning an app is not a prerequisite. With your own app you choose OAuth or a user access token with seven listed permissions.
Meta ads MCP server rules: cap what an AI agent can do
Meta's ads MCP rules deny an agent action on one ad account or catalog, such as budget increases above 20%. What the rule fields are and where Sume adds a cap.
Advantage+ creative: how to turn off Meta's AI enhancements
Meta says some Advantage+ creative enhancements may be on by default and can be turned off at any time. Check the previews before your video ad goes live.
Meta AI effects in Stories vs making your own AI video clip
Instagram's Meta AI Stories effects transform photos with one tap and are US-only. For an AI video clip instead, generate a 9:16 clip. Steps and limits.
Microdrama AI video: keep the same characters across episodes
Sume's video API has no cast-lock switch. To keep a character across episodes, start every shot from the same still with first_frame and reuse references.
Microdramas on YouTube: how Shorts series fit the format
YouTube says microdramas passed 6.5 billion views in early 2026 and Shorts series now supports episodes. What the format needs and how to render episodes.
2K AI video generator API: MiniMax H3 at 2K on Sume
MiniMax H3 makes video up to 2K. On Sume you ask for resolution 2K on minimax-h3, an upscale of native 768p. Request, price for 10 seconds, and limits.
MiniMax H3 4-second clips: MiniMax says 4, Sume says 5
MiniMax lists 4–15 seconds for H3, but Sume's docs and pricing code start at 5 seconds. Send 5 or more, and trim to 4 afterwards if you need it.
MiniMax H3 768p: why 720p is refused and what to send instead
MiniMax H3 renders natively at 768p, not 720p. Sume refuses resolution 720p on H3 and H3 Max and tells you to use 768p. The accepted values per id.
MiniMax H3 aspect ratios: 21:9 to 9:16, and when adaptive works
MiniMax H3 makes six aspect ratios, from 21:9 to 9:16. Which ones Sume accepts, where adaptive is allowed, and how frame images set the ratio.
MiniMax H3 in ComfyUI or through a hosted API: what differs
ComfyUI documents three MiniMax H3 workflows with local model files; a hosted API returns a job. The limits that change between the two, from the docs.
First and last frame to video with MiniMax H3: request and rules
MiniMax H3 fills the motion between an opening and a closing image. On Sume send frame_images with first_frame and last_frame; ratio, length and price rules.
MiniMax H3 languages: which spoken languages does it support?
MiniMax says H3 has stable support for 11 dialogue languages and partial support for others. Sume's docs list no language set, so test yours first.
MiniMax H3 Max 1080p: a latent refinement from native 768p
MiniMax H3 Max on Sume offers 480p, 768p and 1080p. The 1080p tier is a latent refinement from native 768p. What that means for price and output checks.
What is MiniMax H3 Max? The post-trained variant, explained
MiniMax H3 Max is a variant post-trained by fal.ai on MiniMax H3 for faster generation. Its resolutions, lengths and modes, and how Sume lists it.
Multi-shot AI video prompts: MiniMax H3 shot labels and timecodes
MiniMax H3 models multiple shots natively. Write [Shot 1] labels or timecoded blocks in the prompt; syntax from the vendor guides and a Sume request.
AI video with native stereo sound: MiniMax H3 audio through the API
MiniMax H3 generates native stereo sound in the same pass as the video. On Sume audio is always on, generate_audio false is refused, and audio steers.
MiniMax H3 open weights on Hugging Face: what is in the release
MiniMax H3 has a model card on Hugging Face: two checkpoints, a 33B-parameter Transformer, a community license and a 4-GPU serving example. What to check first.
MiniMax H3 pricing per second on Sume, by resolution
What a MiniMax H3 or H3 Max clip costs on Sume: a per-second rate by resolution, reserved on submit. Rates for 480p, 768p, 1080p and 2K, with 10-second totals.
MiniMax H3 prompt guide: reference jobs, negative direction, length
The MiniMax H3 prompting rules that change output: give each reference a job, write timecodes, say what to avoid, and stay under 7,000 characters.
MiniMax H3 reference images: what you pay past the fifth
MiniMax H3 reference-to-video on Sume includes the first five reference images; each one after that adds a charge. Worked totals for 6 to 9 images.
MiniMax H3 reference limits: 9 images, 3 videos, 3 audio, 12 total
The MiniMax H3 reference-to-video limits and the errors Sume returns when you cross them. Counts, clip lengths, the audio-only rule and image price.
MiniMax H3 cache and sparse attention: what the open release has
MiniMax's H3 open release ships full-attention inference only; sparse attention comes later. About 13B parameters can be cached, not loaded.
AI video editing with a text prompt: MiniMax H3 and Sume's edit path
MiniMax H3 is described as editing existing video from instructions. What the vendor says, what Sume's H3 ids accept, and the id with an edit field.