Do I need Blender installed?
No. The service runs Blender 5.0 (5.2 or 5.3 with blender='5.2' or '5.3') on its GPU worker; you send a file link and get links back.
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 (5.2 or 5.3 with blender='5.2' or '5.3') with Cycles on a datacenter GPU does the import and the render; for a glTF or OBJ given by https link, the .bin and textures in the same folder are fetched automatically (a .gltf uploaded on its own needs them sent as assets). Each new key starts with a welcome credit of up to 500 JPY (100 JPY with no card, 400 JPY more after registering a card, which is not charged) (14 days); after that, previews stay free up to 2 GPU-minutes a day and finals cost 0.1 JPY per GPU-second. Up to 3,000 frames per instruction (automatic internal parts), 1080p on free time and 4K on prepaid credit. AI agents connect at https://render.janction.jp/mcp (remote MCP with OAuth; connecting creates a free key).
Updated 2026-11-17
See also: Render an AI-generated 3D model (Meshy, Tripo, Rodin, Hunyuan3D) into product shots and a turntable
What it does Your own .blend, bpy script or 3D file (glTF/GLB, FBX, USD, OBJ...) rendered to images or video on a cloud NVIDIA GPU, from an AI app, the terminal or the browser. The first preview needs no payment.
What it does not do It does not speed up the Blender viewport on your machine, does not take non-Blender video, simulations or general GPU jobs, and an AI that is not connected cannot render on its own.
Try a turntable of your modelBuild it with an AI and try
Browser only; no connector or CLI needed. A 100 JPY welcome credit for a new key (14 days, no card; one per network every 30 days, further keys on the same network share what is left), and 400 JPY more for saving a card that is not charged (once per card); after that, previews stay free up to 2 GPU-minutes a day and finals cost 0.1 JPY per GPU-second.
Real runs on the production GPU (NVIDIA RTX PRO 6000 Blackwell; the WaterBottle GLB is Khronos's public-domain sample):
| machine / route | settings | GPU seconds | cost | round trip |
|---|---|---|---|---|
| uvx janction-render turntable <link to WaterBottle.glb> (2026-10-10) | 24 frames, 1280x720, one full turn, MP4 | 85.2 GPU-s | about 8.5 JPY | — |
| HTTP API, orbit final (monkey + metal cube) | 48 frames, 960x540 / 24, MP4 | 75.7 GPU-s | about 7.6 JPY | 80 s |
| HTTP API, orbit preview (0/90/180/270 degrees in one image) | 4 angles, 320x180 tiles / 8 | 2.5 GPU-s | within the free previews | 7 s |
The turntable is a fixed-price outcome: the ceiling is shown before anything runs and only the GPU seconds used are charged.
Sources: /benchmarks (2026-09-30 to 2026-10-01), examples/one-command (2026-10-10), a laptop measured on 2026-10-11. Individual runs, not a guarantee; 0.1 JPY per GPU-second after the welcome credit.
render_final(scene_url="https://render.janction.jp/samples/ex21_product_clock.py", asset_urls=["polyhaven:alarm_clock_01"], preset="turntable", orbit_elevation=25, orbit_distance=0.85)The script, settings and GPU seconds are on each example's page. Prices at 0.1 JPY per GPU-second; 0 while the free credit covers it.
# 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 the free GPU time left (the welcome credit while it lasts, then up to 2 preview GPU-minutes a day). 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.
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.
| Format | Imported with | Companion files |
|---|---|---|
| .glb | Blender's glTF importer | everything is inside the file |
| .gltf | glTF importer | by https link (POST /v1/files/url, scene_url): .bin buffers and textures are fetched from the same folder as the .gltf. Uploaded on its own (POST /v1/files): send them with POST /v1/files/{id}/assets under the same relative names, or the job is refused before it runs (gltf_external_files, no charge). A .gltf with everything embedded (data: URIs) needs nothing else |
| .obj | OBJ importer | .mtl and the textures it names, from the same folder |
| .fbx, .usd / .usdc / .usdz, .stl, .ply, .abc | Blender's importers | embed textures, or pass them in asset_urls (they land next to the file) |
The model is centered; 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.
Up to 3,000 frames per instruction (automatic internal parts), 1080p on free time and 4K on prepaid credit (split longer clips into several instructions or use notify_url to chain them), a welcome credit of up to 500 JPY per new key, then 0.1 JPY per GPU-second (previews free up to 2 GPU-minutes a day), inputs and results deleted 24 hours after last use (7 days, normally, for keys that have paid 500 JPY or more in total). 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).
| from | how |
|---|---|
| A file on this computer (.blend, 3D file) | Drop it at /upload to get a 12-hour link (no sign-up), then tell the AI "Render this file: <link>". From inside Blender use the add-on; from a terminal the CLI uploads directly |
| Claude.ai (web / desktop / mobile) | Plugins (older menu: Customize → Connectors) → Add custom connector → https://render.janction.jp/mcp. "Connect" opens a page that creates a free key |
| Claude Team / Enterprise | An owner adds https://render.janction.jp/mcp under Organization settings → Connectors; each member then presses Connect with their own account. In organizations that turn Skills off, Claude Desktop also blocks plugins from November 30 (use the connector URL, or ask the admin to turn Skills on) |
| ChatGPT | Plugins (left sidebar) → Add → Create plugin → https://render.janction.jp/mcp (OAuth). Attach your .blend to the chat. On Business workspaces an admin adds it and shares it |
| Claude Code | claude mcp add --transport http janction-render https://render.janction.jp/mcp, then /mcp to authenticate |
| Claude Code on the web (claude.ai/code) | The same connector as Claude.ai: Plugins (older menu: Customize → Connectors) → Add custom connector → https://render.janction.jp/mcp. Works without changing the session's network settings (guide) |
| Codex | codex mcp add janction-render --url https://render.janction.jp/mcp (the sign-in page opens right away; if Codex later says the server needs login, run codex mcp login janction-render; with a key, add --bearer-token-env-var JANCTION_RENDER_API_KEY) |
| Cursor / VS Code | Add to Cursor Add to VS Code Add to LM Studio The button opens the editor; confirm and it is added. Manual: Streamable HTTP at https://render.janction.jp/mcp |
| Antigravity CLI / Gemini CLI | agy plugin install https://github.com/JasmyLab-JANCTION/janction-render or gemini extensions install https://github.com/JasmyLab-JANCTION/janction-render (the MCP server and the workflow skill) |
| Kimi Code (Kimi K3 and other models) | /plugins install https://github.com/JasmyLab-JANCTION/janction-render (the MCP server and the workflow skill), or add https://render.janction.jp/mcp as a url entry under mcpServers in ~/.kimi-code/mcp.json and run /mcp-config login janction-render (OAuth). Guide |
| OpenCode | Add https://render.janction.jp/mcp under mcp in ~/.config/opencode/opencode.json with "type": "remote", then opencode mcp auth janction-render (OAuth). Guide |
| Qwen Code | qwen extensions install https://github.com/JasmyLab-JANCTION/janction-render (the MCP server and the workflow skill), or qwen mcp add --transport http janction-render with https://render.janction.jp/mcp (stored as httpUrl). Guide |
| GitHub Copilot CLI | copilot mcp add --transport http janction-render with https://render.janction.jp/mcp, then /mcp auth janction-render in copilot (OAuth). With the skill: copilot plugin marketplace add JasmyLab-JANCTION/janction-render, then copilot plugin install janction-render@janction-render. Guide |
| DeepSeek Harness (dsh) | One @deepseek-ai/dsh-mcp-client entry: transport: streamable-http, url: https://render.janction.jp/mcp, headers Authorization: Bearer with a key from POST /v1/keys (no OAuth). DeepSeek guide (API function calling too) |
| Grok / Perplexity / Le Chat | Add a custom (remote MCP) connector with https://render.janction.jp/mcp in each app's Connectors settings (Grok: Plugins → New connector → Custom, guide; Perplexity: Settings → Connectors → Custom → Remote, Pro / Max / Enterprise, OAuth; Le Chat: workspace admin, OAuth or a Bearer key) |
| Gemini app (gemini.google.com) | On the web: Settings → Connected Apps → Custom apps, add the MCP URL https://render.janction.jp/mcp (web only, English interface, with activity saving on). Sign-in is the OAuth consent page |
| Manus | Connectors → Create → Add MCP by URL with https://render.janction.jp/mcp (remote MCP only; OAuth or a Bearer key) |
| MiniMax (MiniMax Code) | One streamable-http entry in the MCP settings: url https://render.janction.jp/mcp, and Authorization: Bearer jr_… in headers |
| Notion (Notion Agent) | Business / Enterprise: Settings → Connections → Discover → Add Custom MCP → https://render.janction.jp/mcp, then sign in (the button shows when a workspace admin allows custom MCP servers) |
| JetBrains (AI Assistant, Junie) | AI Assistant: Settings → Tools → AI Assistant → Model Context Protocol (MCP) → Add → connect over HTTP with {"mcpServers": {"janction-render": {"url": "https://render.janction.jp/mcp"}}}. Junie: the same url in ~/.junie/mcp/mcp.json (Authorize opens the browser), or "headers": {"Authorization": "Bearer jr_…"} |
| Kiro (IDE, CLI) / Amazon Q Developer CLI | Kiro: "url": "https://render.janction.jp/mcp" under mcpServers in ~/.kiro/settings/mcp.json (in the IDE, open a folder: MCP SERVERS appears in the Kiro panel and the authorization page opens; in the CLI, /mcp auth janction-render). With a key: "headers": {"Authorization": "Bearer ${JANCTION_RENDER_API_KEY}"} (add the variable to Mcp Approved Env Vars). Amazon Q Developer CLI: "type": "http" and the same url in the agent configuration, then /mcp to sign in |
| Microsoft Copilot Studio | Tools → Add a tool → New tool → Model Context Protocol → Server URL https://render.janction.jp/mcp. Authentication: OAuth 2.0 with Dynamic discovery, or API key (Header, name X-API-Key, value jr_…). Set the agent's Settings → Generative AI → Orchestration to Yes (generative orchestration), or it will not use the tool |
| LM Studio (0.3.17 or later) | Program tab → Install → Edit mcp.json: {"mcpServers": {"janction-render": {"url": "https://render.janction.jp/mcp", "headers": {"Authorization": "Bearer jr_…"}}}} |
| Cherry Studio | Settings → MCP Servers → Add → Import from JSON: {"mcpServers": {"janction-render": {"type": "streamableHttp", "baseUrl": "https://render.janction.jp/mcp"}}}. Turn it on and press "Sign-in required." to open the consent page in the default browser. If no tools show after signing in, turn the server off and on again (with a key: "headers": {"Authorization": "Bearer jr_…"}) |
| Windsurf, Cline, Goose, Amp, Auggie, Warp, Zed, Roo Code, Continue and other MCP clients | Streamable HTTP at https://render.janction.jp/mcp; OAuth or Authorization: Bearer <api key> |
| Claude Desktop and other stdio-only clients (npm) | npx -y janction-render (in the client's mcpServers: {"command": "npx", "args": ["-y", "janction-render"]}). The npm package janction-render bridges stdio to https://render.janction.jp/mcp with OAuth; --key jr_… for a key you have, --local for the Python stdio server through uv |
| Terminal (stdio, sends local files) | claude mcp add janction-render -e JANCTION_RENDER_SERVER=https://render.janction.jp -- uvx --from janction-render janction-render-mcp |
| Inside Blender (for people) | The add-on; extension repository https://render.janction.jp/extensions/index.json. Maya / Houdini / Cinema 4D: submit tools |
No. The service runs Blender 5.0 (5.2 or 5.3 with blender='5.2' or '5.3') on its GPU worker; you send a file link and get links back.
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'.
Up to 512 MB for a glTF, FBX, USD or OBJ file, from a link or through /upload. The service fetches it once and keeps it 24 hours after last use (7 days, normally, for keys that have paid 500 JPY or more in total). Large texture sets: pass them in asset_urls or embed them (GLB, USDZ). Every monthly plan includes JANCTION Storage (beta): renders and scenes are kept for as long as you are subscribed (Basic 200 GiB, Standard 1 TiB for 3 people, Pro 5 TiB for 5 people). .blend uploads go up to 10 GB.
Yes. notify_url in the job body receives a JSON POST (job.done or job.failed, with artifact links) when the job finishes.