OverviewProductsCompareSend a fileFactsPricingExamplesBenchmarksStatusFAQChangelogTermsPrivacyLegal noticeSecuritySupportGalleryllms.txt日本語

3D file to MP4 over an API (and over MCP)

Updated 2026-10-07

JANCTION Render renders a 3D file into a video over HTTP in four calls: POST /v1/keys for a key (no sign-up), POST /v1/files/url with the file's https link (returns scene_id), POST /v1/jobs with kind 'final', output 'mp4' and either orbit true (a turntable) or a frame range (the file's own animation), then GET /v1/jobs/{id} until status is done and fetch output.mp4 from the artifact link. From an AI agent it is one tool call, render_final(scene_url=..., orbit=True, output='mp4'). Blender 5.0 with Cycles on a datacenter GPU does the import and the render; textures next to a glTF or OBJ are fetched automatically. Free beta: 10 GPU-minutes per key per day, up to 240 frames at 1080p per job.

HTTP: the four calls

# 1. a key (no sign-up; keep it)
KEY=$(curl -s -X POST https://render.janction.jp/v1/keys | python -c "import sys,json;print(json.load(sys.stdin)['api_key'])")

# 2. the file, by https link (.glb .gltf .fbx .usd .usdc .usdz .obj .stl .ply .abc or .blend / .py)
curl -s -X POST https://render.janction.jp/v1/files/url -H "X-API-Key: $KEY" -H "Content-Type: application/json" \
  -d '{"url": "https://example.com/model.glb"}'
# -> {"scene_id": "f_...", ...}

# 3a. a turntable video (one rotation, 48 frames, studio lighting)
curl -s -X POST https://render.janction.jp/v1/jobs -H "X-API-Key: $KEY" -H "Content-Type: application/json" \
  -d '{"scene_id": "f_...", "kind": "final", "orbit": true, "orbit_frames": 48, "width": 1280, "height": 720,
       "samples": 64, "environment": "studio", "output": "mp4", "fps": 24}'
# 3b. or the file's own animation (frames 1-120 of a glTF with animation clips)
#  -d '{"scene_id": "f_...", "kind": "final", "frame_start": 1, "frame_end": 120, "width": 1280, "height": 720,
#       "samples": 64, "environment": "studio", "output": "mp4", "fps": 24}'
# -> {"job_id": "j_...", "status": "queued", "estimate": {"seconds": ..., "human": "..."}, ...}

# 4. wait, then download
curl -s https://render.janction.jp/v1/jobs/j_... -H "X-API-Key: $KEY"        # status, progress, eta, artifacts[]
curl -s -o output.mp4 "https://render.janction.jp/v1/jobs/j_.../artifacts/output.mp4" -H "X-API-Key: $KEY"

Before step 3, POST /v1/estimate with the same body returns the GPU seconds and whether it fits today's quota. notify_url in the job body receives one JSON POST when the job finishes, so a pipeline does not have to poll. Every field is in the OpenAPI; a preview ("kind": "preview", 1 to 4 frames tiled in one image) costs a few GPU seconds and is the right first call.

MCP: one call

render_preview(scene_url="https://example.com/model.glb", orbit=True, environment="studio")   # four angles, seconds
render_final(scene_url="https://example.com/model.glb", orbit=True, orbit_frames=48, width=1280, height=720,
             environment="studio", output="mp4")                                                 # the video

The MCP URL is https://render.janction.jp/mcp; Claude.ai, ChatGPT, Claude Code, Codex and Cursor connect with OAuth and get a free key on the consent page.

What the service does with the file

The model is centred; with orbit the camera circles it at the elevation and distance you set (flat floors and walls are ignored when framing). Without orbit, a file with its own camera uses it; otherwise a default camera frames the bounds. Outputs: mp4 (H.264), webm (VP9, alpha with transparent), prores (.mov, for editing), gif / webp (up to 960 px), or png / exr frames.

Limits during the beta

240 frames and 1080p per job (split longer clips into several jobs or use notify_url to chain them), 10 GPU-minutes per key per day, inputs and results deleted 24 hours after last use. Measured: a 24-frame 720p turntable of a headphones model, 58 GPU-seconds; 48-frame EEVEE clips at 720p, 46 to 57 GPU-seconds (examples, costs).

FAQ

Do I need Blender installed?

No. The service runs Blender 5.0 on its GPU worker; you send a file link and get links back.

Can the file have its own animation?

Yes. glTF, FBX, USD and Alembic animation is imported; give frame_start / frame_end instead of orbit. The frame range of the file is reported by scene_info (MCP) or a job with kind 'info'.

How big can the file be?

Tens of megabytes are fine; the receptionist fetches it once and keeps it 24 hours after last use. Large texture sets: pass them in asset_urls or embed them (GLB, USDZ).

Is there a webhook?

Yes. notify_url in the job body receives a JSON POST (job.done or job.failed, with artifact links) when the job finishes.

Related

• Blender render farm for AI agents
• Blender cloud rendering without a GPU
• Blender MCP server for rendering
• Claude Code + Blender: render on a cloud GPU
• Codex + Blender: render on a cloud GPU
• Blender rendering API
• ChatGPT + Blender: render without a GPU
• Claude + Blender: render without a GPU
• How to render Blender without a GPU
• Free Blender cloud rendering: what is actually free
• Run a bpy script on a cloud GPU
• Blender render farm APIs compared (2026)
• Blender MCP servers compared: local (Blender Lab MCP, blender-mcp, Blender Agent Bridge) vs cloud (Sceneplane, JANCTION Render)
• Google Colab vs JANCTION Render for Blender rendering
• FAQ
• Render a .blend file online on a GPU (free beta): upload, preview, final
• Render a Blender animation online as an MP4 (free beta): frames, samples, time
• JANCTION Render vs SheepIt: free Blender rendering for AI agents vs a volunteer farm
• Blender add-on: render the open file on cloud GPUs (free beta)
• Render Maya, Houdini and Cinema 4D scenes on cloud GPUs with Cycles (free beta)
• Cursor + Blender: render on a cloud GPU
• VS Code + Blender: render on a cloud GPU
• Windsurf + Blender: render on a cloud GPU
• Gemini CLI / Antigravity + Blender: render on a cloud GPU
• JANCTION Render vs BlendSwap Render Farm
• Render a glTF / FBX / USD / OBJ file online (no Blender)
• Render 3D that an AI agent generated
• Headless Blender rendering in the cloud (CI, batch, scripts)
• Product turntable video from a 3D model, online
• 7-angle product shots from ChatGPT or Claude, rendered on a cloud GPU
• How much does cloud rendering a Blender video cost? Measured GPU seconds and prices
• Make a 360-degree product video with AI: glTF to turntable MP4 on a cloud GPU
• Headless Blender as an API: run your own GPU server or call a hosted one
• JANCTION Render vs RebusFarm, GarageFarm and Fox Renderfarm: what is different
• JANCTION Render for companies and teams: terms, data handling, invoices and plans

Overview · llms.txt

JANCTION Render v0.4.20 · JasmyLab Inc. · Updated 2026-10-07 · Tested with Blender 5.0, JANCTION Render 0.4.20 · 日本語

OverviewProductsCompareSend a fileFactsPricingExamplesBenchmarksStatusFAQChangelogTermsPrivacyLegal noticeSecuritySupportGalleryllms.txt日本語