In November 2026 an AI agent that needs Blender renders has five kinds of option. Hosted services with a public MCP server: JANCTION Render (no sign-up, a welcome credit of up to 500 JPY for a new key (100 JPY with no card, 400 JPY more after saving a card that is not charged) then 0.1 JPY per GPU-second with previews free up to 2 GPU-minutes a day, a preview with a critic verdict in seconds, takes .blend files, bpy scripts and 3D files; monthly plans from 1,500 JPY a month include JANCTION Storage (beta)), BlendSwap Render Farm (paid, about $4.30 per L40S GPU-hour, up to 10 GPUs per job, .blend or zip) and Sceneplane (a cloud Blender runtime with saved projects that an agent edits, 30 free compute-minutes a month, plans from $9). A worker you build on a GPU cloud such as Modal (L40S at $0.000542 per second, $30 of free credit a month) or RunPod gives full control if you write and maintain the Blender container. A local Blender MCP edits the scene open on your machine and renders on your own GPU. Studio farms (RebusFarm, GarageFarm.NET, Fox Renderfarm) render long sequences on many nodes, but we found no public agent API for them. AI agents connect at https://render.janction.jp/mcp (remote MCP with OAuth; connecting creates a free key).
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.
| JANCTION Render | BlendSwap Render Farm | Sceneplane | Your own worker on Modal or RunPod | Local Blender MCP | Studio farms |
| How the agent connects | remote MCP (OAuth or key), stdio MCP, HTTP API | remote MCP and REST API (key) | remote MCP (API key or OAuth) | your own code on their SDK or HTTP | MCP to the Blender running on your machine | desktop client or plugins; no public agent API found |
| Sign-up | none: the MCP consent page or POST /v1/keys issues a key | required | required (free, no card) | an account on the GPU cloud | none | required |
| Free tier | a welcome credit of up to 500 JPY for a new key (100 JPY with no card, 400 JPY more after saving a card that is not charged), valid 14 days, then previews free up to 2 GPU-minutes a day | none listed | 30 compute-minutes a month | Modal: $30 of credit a month (Starter) | your own hardware | $25 trial credit (GarageFarm.NET, Fox Renderfarm) |
| Price after that | 0.1 JPY per GPU-second (360 JPY, about $2.40 at 150 JPY per USD, per GPU-hour), prepaid credit; monthly plans from 1,500 JPY a month include JANCTION Storage (beta) | $4.30 per L40S GPU-hour with credit packs, about $3.78 on the Studio plan | $9 / $29 / $99 a month for 300 / 1,500 / 6,000 compute-minutes | Modal L40S $0.000542 per second (about $1.95 per hour); RunPod serverless L40 / L40S / 6000 Ada (48 GB) $1.89 per hour | electricity | per node-hour, GHz-hour or OctaneBench-hour |
| Minimum charge | 1 JPY (the paid part is rounded up to whole yen); top-ups from 100 JPY | each worker bills at least 4 minutes, in whole credits ($0.10 each) | the monthly plan | billed per second of use | none | per their price lists |
| Inputs | .blend, bpy script, glTF / GLB, FBX, USD, OBJ, STL, PLY, Alembic | .blend or .zip up to 500 MB | cloud projects shaped by scene operations (templates such as product_studio) | whatever your worker accepts | the scene open in your Blender | DCC projects packaged by the client |
| GPU and job limits | NVIDIA RTX PRO 6000 (96 GB), the live count below the table; 3,000 frames per instruction (automatic internal parts), 1080p on free time and 4K on prepaid credit | L40S 48 GB, up to 10 per job; 250 frames and 4K per job | hardware not stated; renders up to 1024 px (free), 2048 px (Hobby) and 4096 px (Studio, Scale) | your choice of GPU | your GPU | many CPU or GPU nodes |
| Preview loop for the agent | 1 to 4 frames tiled in one image in seconds, with a critic verdict (ok / check / fix) and fix code | a quote before launching | renders inside the project | build it yourself | renders in your Blender | test renders through the client |
| Outputs | PNG / EXR frames; MP4, WebM, ProRes, GIF, WebP | rendered frames | renders, MP4, GLB, STL, .blend | what you code | what Blender writes | frames and video |
| How long results stay | 24 hours after last use (normally 7 days for keys that have paid 500 JPY or more in total). Monthly plans keep them 30 days here and in JANCTION Storage (beta) with no expiry while subscribed (200 GiB to 5 TiB). | see their site | saved cloud projects | your own storage | your disk | RebusFarm 7 days, GarageFarm.NET 28 days (compared) |
GPUs available right now: 3 (from /v1/health). The number updates itself when GPUs are added.
The published prices use different units (GPU-second, GPU-hour, compute-minute, node-hour) on different hardware, so the only fair number is the cost of one of your own frames on each service. Measured on JANCTION Render: a 1080p Cycles still takes 6 to 10 GPU-seconds (0.6 to 1 JPY at 0.1 JPY per GPU-second) and a 24-frame 720p turntable takes 58 GPU-seconds (about 6 JPY); how we measured. We have not measured the other services, so this page gives no per-frame price for them.
JANCTION Render's prices, free credit and retention are the current ones (updated 2026-11-17). Sources for the other services, read on 2026-11-17: blendswap.com/render-farm, sceneplane.online, modal.com/pricing, modal.com/docs/examples/blender_video, runpod.io/pricing; studio farms as read on 2026-10-07 (details). Prices change. If a value here is out of date, tell us at support; this page is checked every month. Other comparisons: BlendSwap, Blender MCP, all.
| 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 |
Which render farms support MCP?
As of 2026-11-17: JANCTION Render, BlendSwap Render Farm and Sceneplane publish remote MCP servers. A local Blender MCP controls the Blender on your own machine. In what we read, the studio farms had no public agent API.
Is there a free render farm for AI agents?
JANCTION Render needs no sign-up, and each new key starts with a welcome credit of up to 500 JPY for a new key (100 JPY with no card, 400 JPY more after saving a card that 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. Sceneplane has 30 free compute-minutes a month after sign-up. Modal gives $30 of credit a month if you build your own worker.
Can an agent render a Blender scene without installing Blender?
Yes, with the hosted options: JANCTION Render (send a bpy script, a .blend or a 3D file), BlendSwap Render Farm (.blend or zip) and Sceneplane (cloud projects). A local Blender MCP needs Blender on the machine.
Can I keep my renders?
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. After cancelling, saved work can still be opened and downloaded for 90 days after the paid period ends.
Can I continue from an earlier render?
Yes, on a monthly plan. A final's reply carries a one-time link to open it in storage, where each version lists its results and source scene. Ask your AI to open the earlier render and render it again with the same settings, or open it from the browser workbench.
Can I upload a large .blend file?
Every monthly plan uploads .blend files up to 10 GB. Scenes with packed textures can be sent as they are and rendered to the final.
Which one is cheapest per frame?
It depends on the scene and the GPU, so render one of your scenes on each. JANCTION Render measured 6 to 10 GPU-seconds (0.6 to 1 JPY) for a 1080p Cycles still, and each new key starts with a welcome credit of up to 500 JPY for a new key (100 JPY with no card, 400 JPY more after saving a card that is not charged) (14 days).