rendermate

docs

Base URL https://rendermate.tella.dev/v1. Authenticate with Authorization: Bearer sk_…, a key from the dashboard. Agents: the same content as Markdown is at /llms.txt.

■ quickstart

1 · generate a clip
curl https://rendermate.tella.dev/v1/generations \
  -H "Authorization: Bearer $RENDERMATE_API_KEY" \
  --json '{
    "model": "bytedance/seedance-2.5",
    "prompt": "a paper boat drifting down a rainy street, macro lens",
    "resolution": "1080p",
    "ratio": "9:16",
    "duration": 5,
    "generateAudio": true
  }'
# → { "id": "gen_8f2k…", "status": "queued" }
#   poll GET /generations/gen_8f2k… →
#   { "status": "done", "assetId": "as_q7…",
#     "usage": { "completionTokens": 243000 } }
2 · compose it
curl https://rendermate.tella.dev/v1/compositions \
  -H "Authorization: Bearer $RENDERMATE_API_KEY" \
  --json '{
    "canvas": { "width": 1080, "height": 1920, "fps": 30, "durationMs": 5000 },
    "layers": [
      { "type": "media", "assetId": "as_q7…", "fit": "cover" },
      { "type": "text", "text": "Rainy day sale", "y": 0.8,
        "animate": { "in": "rise", "durationMs": 400 } }
    ]
  }'
# → { "id": "cmp_31x…", "revision": 1 }
3 · render and play
curl https://rendermate.tella.dev/v1/renders \
  -H "Authorization: Bearer $RENDERMATE_API_KEY" \
  --json '{ "compositionId": "cmp_31x…", "format": "mp4", "publish": true }'
# → { "id": "rnd_m2…", "status": "done",
#     "url": "https://rendermate.tella.dev/files/rnd_m2….mp4",
#     "playbackUrl": "https://rendermate.tella.dev/v/vid_a9…" }

■ mcp

mcp.json · coming soon
{
  "mcpServers": {
    "rendermate": {
      "url": "https://rendermate.tella.dev/mcp",
      "headers": { "Authorization": "Bearer ${RENDERMATE_API_KEY}" }
    }
  }
}

■ /assets

Upload or import any media. Stored, probed, transcoded for playback.

POST/assetsCreate an upload; returns a presigned PUT URL
POST/assets/importsImport from a URL (mp4, mov, YouTube, image, audio)
GET/assets/{id}Status, duration, dimensions, playbackUrl
GET/assets/{id}/transcriptWords with start/end ms
DELETE/assets/{id}Delete an asset and its renditions

■ /generations

One endpoint, every model and every provider parameter. Results land as assets; you pay the provider's price for what was used.

GET/modelsEvery routable model with its price
POST/generations{model, prompt, …model params} → generation
GET/generations/{id}Status, assetId, and usage: tokens and USD billed

■ /compositions

Freeform timeline JSON: tracks, layers, keyframes, text, transitions.

POST/compositionsCreate from a document or an empty canvas
POST/compositions/{id}/commandsApply edits (add layer, trim, animate…)
GET/compositions/{id}The current document
GET/compositions/schemaJSON schema for documents and commands

■ /renders

GPU compositing to MP4 or HLS. Same engine for preview and export.

POST/renders{compositionId, format, resolution} → render
GET/renders/{id}Progress, then url + playbackUrl

■ /videos

A hosted, playable URL for any asset or render. Embed it anywhere.

POST/videosPublish an asset or render → playbackUrl, embedUrl
GET/videos/{id}Playback URLs, thumbnail, captions
GET/videos/{id}/analyticsViews and watch time

■ /account

Metered usage and webhooks.

GET/accountWhich organization a key belongs to
GET/usageUsage per meter for a date range
POST/webhooks/endpointsGet called when renders and generations finish

■ bytedance/seedance · parameters + billing

Every BytePlus parameter is supported on POST /generations. You pay what BytePlus charges for the task, with 0% markup: the tokens it reports (usage.completionTokens on the generation) times the model's price per million. Tokens are about width × height × 24 × seconds / 1024 of the output, so size and length set the price.

promptstringWhat to generate. Put dialogue in double quotes for spoken audio. (content text)
resolution"480p" | "720p" | "1080p" | "4k"Output resolution; default 720p. 1080p on 2.5 and 2.0, 4k on 2.0 only. (resolution)
ratio"16:9" | "4:3" | "1:1" | "3:4" | "9:16" | "21:9" | "adaptive"Aspect ratio; default adaptive (picked from the prompt or inputs). First-frame, edit and extend tasks on 2.5 accept only adaptive. (ratio)
durationintegerSeconds: 4–30 on 2.5, 4–15 on 2.0 models, or -1 to let the model choose. (duration)
generateAudiobooleanSynchronised voice, effects and music; default true. Mono. (generate_audio)
inputsArray<{role, assetId}>Media to condition on, by asset id. role: first_frame, last_frame (image-to-video), or reference_image (2.5: up to 30, 2.0: up to 9), reference_video, reference_audio (omni reference). Frame roles and reference roles cannot be mixed. 2.0 needs an image or video beside reference_audio. (content image_url / video_url / audio_url + role)
draftboolean2.5 only: a cheap 480p draft to check shots and motion before the final. (draft)
draftIdstring2.5 only: render the final video from a draft generation's id. (content draft_task)
returnLastFramebooleanAlso save the last frame as an image asset, to chain clips with first_frame. (return_last_frame)
outputFormat"mp4" | "mov"mov keeps more colour precision for grading and keying; default mp4. (output_format)
watermarkbooleanBurn in an "AI Generated" mark; default false. (watermark)
expiresAfterSecondsintegerGive up if not finished in time: 3600–259200, default 172800. (execution_expires_after)
providerOptionsobjectAny other BytePlus task field, sent as-is, so new parameters work on day one.
modelresolutionssecondsper 1M tokens
bytedance/seedance-2.5480p, 720p, 1080p4–30$11.70
bytedance/seedance-2.0480p, 720p, 1080p, 4k4–15$7.70
bytedance/seedance-2.0-fast480p, 720p4–15$5.60
bytedance/seedance-2.0-mini480p, 720p4–15$3.50
output size (2.0 series)16:94:31:13:49:1621:9
480p864×496752×560640×640560×752496×864992×432
720p1280×7201112×834960×960834×1112720×12801470×630
1080p1920×10801664×12481440×14401248×16641080×19202206×946
4k3840×21603326×24942880×28802494×33262160×38404398×1886

2.5 is the same except 480p 16:9 and 9:16, which are 854×480 and 480×854. Tasks with a reference video bill at BytePlus' video-input token price.

■ models

bytedance/seedance-2.5videobest quality, video edit + extend, up to 30 s; ≈ $0.569/s at 1080p 16:9
bytedance/seedance-2.0videoup to 4K; ≈ $1.497/s at 4k 16:9
bytedance/seedance-2.0-fastvideoquicker, up to 720p; ≈ $0.121/s at 720p 16:9
bytedance/seedance-2.0-minivideocheapest, up to 720p; ≈ $0.076/s at 720p 16:9
openai/gpt-imageimagereference-image aware
elevenlabs/sound-effectsaudioprompt → SFX
elevenlabs/ttsspeechvoices + cloning
assemblyai/universaltranscriptionword-level timings