In Kimi Code CLI run /plugins install https://github.com/JasmyLab-JANCTION/janction-render, then /reload: it adds the MCP server https://render.janction.jp/mcp and the workflow skill. Or add the server to ~/.kimi-code/mcp.json and run /mcp-config login janction-render; the browser opens the OAuth consent page, which creates a free key. Each new key starts with a welcome credit of up to 500 JPY (14 days); after that, previews stay free up to 2 GPU-minutes a day and finals cost 0.1 JPY per GPU-second.
Updated 2026-10-27
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.
Paste your AI's script and tryTry your own file for free
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.
/plugins install https://github.com/JasmyLab-JANCTION/janction-render /reload
The plugin declares the MCP server and a skill that tells the agent the order: preview, fix, estimate, ask you, then render. Run /mcp to see the server; the first tool call (or /mcp-config login janction-render) opens the OAuth consent page in the browser, which creates a free key (no account, no card).
// ~/.kimi-code/mcp.json
{
"mcpServers": {
"janction-render": { "url": "https://render.janction.jp/mcp" }
}
}
An entry with url is a Streamable HTTP server. Then run /mcp-config login janction-render and approve the consent page. New sessions pick up the server; an open session does not. With a key you already have, use "headers": {"Authorization": "Bearer jr_..."} instead of OAuth. From a terminal, uvx janction-render connect kimi writes the same entry (without uv: pip install janction-render, then janction-render connect kimi). Kimi Code for VS Code: gear icon → MCP Servers → add an http server with the same URL.
Kimi Code asks before each MCP tool call that no permission rule covers; "Approve for this session" allows the same tool again. The tools are named mcp__janction-render__render_preview and so on. A final render that does not fit the free time or your credit stops and returns the top-up link instead of rendering.
Kimi Code runs commands on your computer, so a local file does not need a link: let it run uvx janction-render upload scene.blend and pass the link it prints as scene_url, or uvx janction-render render scene.blend --frames 1-48 --output mp4 --wait.
Using JANCTION Render, build a glossy red cube rotating on a grey floor and show me a 4-frame preview. If it looks right, render 24 frames at 1280x720 as an MP4.
To render a .blend or 3D file that is on your computer, drop it at /upload to get a 12-hour link (no sign-up) and tell the AI "Render this file: <link>". To test the connection first: "Render a preview of https://render.janction.jp/samples/cube_scene.py".
scene_info reads the scene without rendering: cameras, frame range, objects, missing files.render_preview renders 1-4 frames at 720p in a few GPU seconds and returns the image, so the agent can look, fix the script and try again.render_estimate says how long the final render takes ("about 3 minutes") and whether it fits the free GPU time left (the welcome credit while it lasts, then up to 2 preview GPU-minutes a day).render_final renders the frames on GPUs and joins them into an MP4; render_status reports the remaining time; render_download returns the files or links.| job | GPU time | note |
|---|---|---|
| preview, 4 frames (720p split in 4 tiles, 16 samples, denoised) | about 4 s | round trip about 8 s; the image comes back inline |
| final, 24 frames at 1280x720, 64 samples → MP4 | about 60 s | measured 2026-09-30 / 10-01 (59 s and 58 s) |
| final, one 1920x1080 frame at 128 samples | about 11 s | the estimator's baseline; heavy scenes take longer |
These are individual observations of simple scenes (2026-09-30 to 10-01 UTC, NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition, 96 GB). The 4-GPU-second example used a rotating cube, four 640x360 tiles and 16 samples. GPU time includes Blender startup and scene loading; it is distinct from completion time including queue and transfers. See conditions, round trips and reproduction files. These are not speed guarantees.
render_estimate gives the number before rendering; once a scene has been rendered once, the estimate uses that scene's own measurement.
/plugins remove janction-render, or delete the entry from mcp.json. Revoke the key with POST https://render.janction.jp/v1/keys/revoke if needed.
Pricing (since 2026-10-08): Each new key gets 100 JPY of GPU time free with no card (1,000 GPU-seconds, 14 days) for previews and finals, and 400 JPY more once a card is saved on a Stripe page that charges nothing (once per card): up to 500 JPY in all. After it is used up or expires, previews are free up to 2 GPU-minutes per key per day and final renders are paid from prepaid credit at 0.1 JPY per GPU-second. Top-ups (paid) start at 100 JPY. The first top-up during the 14-day welcome period counts 1.5x, with the bonus capped at 500 JPY (100 JPY buys 150 JPY of credit). Top-ups of 2,000 JPY or more get 10 to 20% extra (not combined with the first-top-up bonus; the larger one applies). Top-up bonuses are separate from the welcome credit and the card-saving credit. Payment is on a Stripe Checkout page. One full welcome credit per network every 30 days; further keys from the same network use what is left of that network's credit. A job without enough credit gets HTTP 402 payment_required with a checkout_url. Final renders go up to 3,000 frames per instruction (automatically split internally under one job id), 1080p (1920x1080) on free time and up to 4K (3840x2160) on prepaid credit. The free preview time resets at 00:00 UTC (09:00 JST). No sign-up: connecting creates a key. Inputs and results are deleted 24 hours after last use (normally 7 days for keys that have paid 500 JPY or more in total) and never used for training.
If you cannot add a connector to your AI (plan or administrator settings), the same result is one step away: send the prompt below to the AI and paste the code it returns into the paste-and-render page. The preview needs no payment.
Write a Blender 5.0 bpy script that builds <describe your scene here>. Add a camera and set scene.camera, and add one light. Do not call render and do not change render settings. Reply with the code only.
To fix something, give the AI the preview's notes (too dark, cut off, no light) and paste the rewritten script again.
Yes. JANCTION Render is a standard MCP server, so it works with whichever model Kimi Code runs (Kimi K3 or another). Outside MCP servers are added in Kimi Code (CLI or VS Code), not in the kimi.com chat.
The plugin adds the skill as well, so the agent previews before it renders and asks you before spending credit. mcp.json adds only the tools.
Each new key starts with 100 JPY of free GPU time (no card) and 400 JPY more after saving a card that is not charged, up to 500 JPY (14 days); after that, previews stay free up to 2 GPU-minutes a day and finals cost 0.1 JPY per GPU-second. A 24-frame 720p MP4 takes about 60 GPU seconds, about 6 JPY.
Overview · All guides · llms.txt
JANCTION Render v0.4.209 · JasmyLab Inc. · Updated 2026-10-27 · Tested with Blender 3.6 / 4.2 / 4.5 / 5.0 / 5.2, JANCTION Render 0.4.209 · 日本語