Guides
Sume guides: the API, Formats, agents, models, media tools and pricing, each answer dated and sourced.

Anthropic x-api-key is now a fallback: Sume accepts one header
Anthropic's docs list Authorization: Bearer first and call x-api-key a legacy fallback. Sume accepts either, but rejects a request that sends both with a 401.

AI Act Article 50 and standard editing: which Sume tools use no model
The Commission's FAQ exempts assistive standard editing from AI marking. Sume's trim, filter, audio detach and timeline docs call themselves ffmpeg-only.

ASA on AI deepfake ads: you answer for the output you run
CAP says a realistic AI celebrity endorsement can breach the Code and the advertiser stays responsible. Which Sume avatar inputs involve a real person's photo.

Speaker diarization API: confidence scores, and what Sume STT returns
AssemblyAI added speaker_confidence (0 to 1) per word and utterance. Sume STT returns word start and end times only, with no speaker or confidence data.

Black Friday countdown video ad: burn the days-left text
Meta says countdown overlays create Black Friday urgency. A countdown is authored text, so burn a new days-left cue onto one clip each day with Sume.

Bluesky video captions: WebVTT sidecar vs burned-in
Bluesky video embeds take WebVTT caption files next to the video. Sume burns captions into pixels, so build the VTT yourself from sentence segments.

Bluesky video upload limit: 300 MB MP4, and fitting a clip
Bluesky raised its video upload limit from 100 MB to 300 MB in June 2026, MP4 only. Fit a clip under it by trimming length and conforming size with Sume.

Virtual staging disclosure: California AB 723 and originals
California AB 723 asks listings with digitally altered photos to say so and link to the unaltered originals. How to keep original and edit as two URLs.

California AI Transparency Act date, and latent vs manifest marks
AB 853 delays the California AI Transparency Act to August 2, 2026. What latent and manifest mean in the bill, and what Sume's docs say it ships.

Claude Code --bare and MCP: name the Sume server with a key
Claude Code --bare connects only MCP servers named on the command line. To use Sume there, name the server with an API-key header; no browser sign-in needed.

MCP server instructions field: the new /context row, and Sume's
Claude Code 2.1.283 counts MCP server instructions as their own /context row. Sume returns instructions at initialize and keeps long guidance out of tool text.

Claude Code MCP connection timeout: startup wait vs a Sume call
Claude Code 2.1.284 waits up to 10 s for a connecting MCP server on resumed calls and 2 s on a non-interactive first turn. Sume tool calls hold at most 55 s.

Claude Code MCP error showed a Bearer token: rotate the Sume key
If an MCP error or log exposed a Sume Bearer value, rotate the API key. An OAuth token is not an API key. Report issues with the request id, not the key.

Claude Code reserved MCP server name: widgets, and Sume's name
Claude Code 2.1.285 reserves the MCP server name widgets in cloud sessions and on self-hosted runners. Sume's documented name is sume, so nothing to rename.

claude plugin validate and an insecure URL in .mcp.json
Claude Code 2.1.283 added MCP checks to claude plugin validate, including insecure URLs. Sume's hosted endpoint is https, so a plain entry has nothing to flag.

Codex MCP output_token_limit: what to set for Sume tools
Codex lets you cap one MCP tool's output with output_token_limit. Sume tools return ids and media.sume.com URLs, not file bytes, so the cap can stay small.

Computer use origin approval is not a spend approval
OpenAI's computer use approves each new website origin, not spend. When such an agent calls Sume, the spend check is dry_run, max_spend_usd and the wallet.

Copilot mcp-config.json example: a Sume remote entry
A Copilot mcp-config.json example for Sume: an http entry at mcp.sume.com/mcp with an x-api-key header and a tools list. Global file vs workspace .mcp.json.

Crawl job finished event: Sume has none, poll crawl_get
Cloudflare publishes crawl.finished to Queues. Sume's crawl has no such event: wait on the job id, then read it with crawl_get. Steps and idempotency.

Demand Gen video crop and trim tool vs an API crop and trim
Demand Gen's console tool crops to 16:9, 1:1 or 9:16 and trims 5 to 300 seconds. The same edit as two Sume calls: a video-filter crop, then video-trim.

Descript captions: in/out animations vs Sume design overrides
Descript captions now have separate in and out motion. Sume's video-captions API exposes enter, exit and emphasis timing through a design object.

eBay listing video length: 60 seconds, MP4 or MOV
eBay allows one video per listing, up to 60 seconds, in MP4 or MOV. Cut a longer clip down to 60 seconds with Sume Video trim, which returns an MP4.

Edit a transcript with an AI instruction: Sume's STT flow
ElevenLabs STT accepts an edit instruction and returns edited_transcript. Sume's STT has no such field: it returns text and word timings to edit yourself.

ElevenLabs Scribe v2 Realtime pricing vs Sume STT jobs
ElevenLabs lists Scribe v2 Realtime at $0.39 per hour against $0.22 for Scribe v2. Sume STT is an async job priced per minute, not a live stream.

ElevenLabs TTS concurrency limit vs Sume's queued jobs
ElevenLabs added per-product concurrency limits for TTS, music and dubbing on enterprise keys. Sume applies one workspace limit and queues extra jobs.

EU AI icon on video: burn it into the MP4 with Timeline compose
The Commission says the EU AI icon should be embedded in the video and survive resharing. Overlay your icon PNG onto a Sume-hosted clip with Timeline compose.

EU AI icon: Partially AI-Modified or Fully AI-Generated?
The Commission's icons page gives a face swap in an authentic photo as its Partially AI-Modified example. What that means for a Sume face-swapped video.

Firecrawl cache: maxAge 2 days vs Sume's fresh: true
Firecrawl scrape caches for 2 days by default (maxAge 172800000 ms). Sume's scrape has a boolean fresh, default false; fresh: true bypasses cached content.

Firecrawl includePaths regex vs Sume's literal path prefixes
Firecrawl's includePaths are regex on the URL pathname. Sume's include_paths are literal prefixes starting with /, max 10 items. How to rewrite one.

Firecrawl crawl credits per page, and how Sume meters crawl_site
Firecrawl charges 1 credit per crawled page plus 4 more in JSON mode. Sume's crawl_site is listed as an unbilled utility in a bounded rollout.

Firecrawl crawl limit: 10,000 default vs Sume's 20 pages
Firecrawl's crawl defaults to 10,000 pages. Sume's crawl takes limit up to 20 (default 10), so narrow with path prefixes and run several keyed crawls.

Firecrawl executeJavascript return value on Sume
Firecrawl returns executeJavascript results in actions.javascriptReturns. Sume names it javascript_returns and bounds it; scripts max 4,000 characters.

Firecrawl map endpoint limit 5000 vs Sume crawl_map limit 100
Firecrawl's /map defaults to 5000 links and allows 100000. Sume's crawl_map takes limit 1 to 100, so pick URLs, then scrape them with crawl_scrape.

Firecrawl map sitemap skip/include/only: Sume crawl_map has no switch
Firecrawl's /map has a sitemap option (skip, include, only) and includeSubdomains. Sume's crawl_map takes only url and limit, and maps one origin.

Firecrawl MCP timeout: Sume crawl_scrape's 35, 40 and 45 s deadlines
A synchronous crawl_scrape call has three deadlines: client abort at 35 s, MCP at 40 s, host watchdog at 45 s. Narrow the page or use crawl_site.

Firecrawl question format: json_prompt on Sume scrape
Firecrawl added a Question format to /scrape. Sume has none; ask with json_prompt (up to 2,000 characters) or json_schema under formats: [json].

Firecrawl scrape actions on Sume: 8 actions, no write or press
Sume's crawl_scrape accepts up to 8 actions of four types: wait, scroll, click, executeJavascript. Firecrawl's write, press and pdf have no match.

Firecrawl scrape formats: the seven Sume supports
Firecrawl scrape lists summary, branding, question and more. Sume's scrape accepts seven formats: markdown, links, html, json, screenshot, rawHtml, images.

Firecrawl scrape timeout: 60000 ms default vs Sume's 30000 cap
Firecrawl's scrape timeout defaults to 60000 ms and goes to 300000. Sume's crawl scrape takes timeout_ms up to 30000, so send 30000 or less.

Firecrawl waitFor and wait actions: Sume's 10 s combined budget
Firecrawl allows 60 s of waitFor plus wait actions combined. Sume's crawl_scrape allows 10000 ms combined, and the total must stay below timeout_ms.

FLUX Deblur: 4 MP input vs Sume's 1-4x image upscale
FLUX Deblur sharpens a blurry image with no prompt or mask, up to 4 MP. Sume has no deblur endpoint; its image upscaler takes a factor of 1 to 4.

FLUX Erase: mask rules and dilate_pixels vs a Sume mask edit
FLUX Erase removes a masked object with no prompt and a dilate_pixels setting. Sume has no erase endpoint; masked edits use mask_url with a prompt.

FLUX Outpainting: 4 MP canvas cap vs Sume's image size options
FLUX Outpainting extends an image onto a canvas of up to 4 megapixels with offsets. Sume documents no outpainting mode; use image_size or aspect_ratio.

FLUX video edit API: 720p downscale, and video_url edits on Sume
BFL's edit-a-video endpoint downscales sources above 720p. Sume lists no FLUX video; its edit path is video_url with gemini-omni-flash-1.1 only.

Gemini 3.5 Transcribe API limits: 1 hour vs Sume STT's 10 minutes
Gemini 3.5 Transcribe takes up to 1 hour per request, 30 minutes with diarization or word timestamps. Sume STT takes 600 seconds; split longer audio.

Gemini 3.8 Flash TTS price: audio-time vs per-character
Gemini 3.8 Flash TTS Standard costs $0.00225 per 10 s of audio until Dec 31, 2026, then $0.0045. Sume bills TTS per character. How to compare.

Gemini video understanding API vs Sume video inspect stills
Gemini's API now has agentic video understanding. Sume's video inspect is narrower: probe facts, 8 stills and optional STT you pass to your own model.

Gemini API speaker diarization: 8 speakers; Sume STT has no labels
Gemini 3.5 Transcribe diarizes up to 8 speakers, 3+ experimental, within 30 minutes per request. Sume STT returns word timings but no speaker labels.