render every frame_
Rendering, compositing, generative video, audio, storage and playback behind one API key. Metered per second, with every model at the provider's own price: 0% markup. Cheap enough to build a product on, simple enough for an agent to drive.
+-[ rendermate ]----------------------------------------+ | |/ | +--------------+ +--------------+ +-------------+ |/ +--------------+ | | model router |->| compositor |->| player + | |/ | your app |/ | | seedance img | | GPU, <= 4K | | CDN, HLS | |/ | or agent |/-- API-->| | tts sfx stt | | mp4, hls | | embed | |/ +--------------+/ 1 key | +------+-------+ +------+-------+ +------+------+ |/ /////////////// | | | | |/ | v v v |/ | +-------------------------------------------------+ |/ | | assets (object storage) | |/ | +-------------------------------------------------+ |/ | |/ | metered per second, GB, token --> one invoice |/ | |/ +-------------------------------------------------------+/ /////////////////////////////////////////////////////////
■ for agents
Paste this into Claude Code, Cursor or Codex. Everything it needs is in /llms.txt.
Use rendermate for anything video in this project. Read https://rendermate.tella.dev/llms.txt first, then call https://rendermate.tella.dev/v1 with "Authorization: Bearer $RENDERMATE_API_KEY". Generated clips and uploads become assets; compose them, render, and return the video's playbackUrl.
Or give it the tools directly over MCP.
{
"mcpServers": {
"rendermate": {
"url": "https://rendermate.tella.dev/mcp",
"headers": { "Authorization": "Bearer ${RENDERMATE_API_KEY}" }
}
}
}■ quickstart · three calls
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 } }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 }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…" }■ api
Upload or import any media. Stored, probed, transcoded for playback.
- POST/assets
- POST/assets/imports
- GET/assets/{id}
- GET/assets/{id}/transcript
- DELETE/assets/{id}
One endpoint, every model and every provider parameter. Results land as assets; you pay the provider's price for what was used.
- GET/models
- POST/generations
- GET/generations/{id}
Freeform timeline JSON: tracks, layers, keyframes, text, transitions.
- POST/compositions
- POST/compositions/{id}/commands
- GET/compositions/{id}
- GET/compositions/schema
GPU compositing to MP4 or HLS. Same engine for preview and export.
- POST/renders
- GET/renders/{id}
A hosted, playable URL for any asset or render. Embed it anywhere.
- POST/videos
- GET/videos/{id}
- GET/videos/{id}/analytics
Metered usage and webhooks.
- GET/account
- GET/usage
- POST/webhooks/endpoints
■ pricing · coming soon
Renders, playback, storage and model calls are each billed for what they use. The full price list and a calculator to estimate your bill are coming soon.
■ limits
| Max asset size | 50 GB |
| Max render length | 4 h |
| Max output resolution | 3840×2160 @ 60 fps |
| Concurrent renders (default) | 20 per organization, raise on request |
| Generated video length | 4–30 s (Seedance 2.5), 4–15 s (2.0) |
| Rate limit | 100 req/s per key |
| Minimum spend | none, pay per use |