Updated 2026-10-05
BlendSwap Render Farm is a paid farm (about $4.30 per GPU hour on L40S, up to 10 GPUs per job, .blend or zip only) with a REST API and a remote MCP server. JANCTION Render is a free beta on one RTX PRO 6000 that also takes bpy scripts and 3D files, and is built around a cheap preview the agent looks at before the final render. Pick BlendSwap for long paid jobs on many GPUs today; pick JANCTION Render for agent-written scenes, scripts, 3D files and a free start.
| JANCTION Render | BlendSwap Render Farm | |
|---|---|---|
| How an agent calls it | Remote MCP (Streamable HTTP, OAuth or Bearer key), stdio MCP, HTTP API, CLI | REST API (sources → quotes → generations) and a remote MCP server (Streamable HTTP, Bearer key) |
| Inputs | .blend, bpy Python script, glTF/GLB, FBX, USD, OBJ, STL, PLY, Alembic | .blend or zip only (no scripts) |
| Preview before the final | Yes: 1-4 frames in one image in a few GPU seconds, returned inline so the agent can look and fix | Quotes before launching; the output is the render itself |
| Price | Free beta (10 GPU-minutes per key per day); planned 0.1 JPY per GPU-second, prepaid | 43 credits per GPU hour, about $4.30; no free API tier |
| GPUs | One NVIDIA RTX PRO 6000 (96 GB) during the beta; frames are split into chunks on it | L40S 48 GB, up to 10 per job |
| Job limits | 240 frames and 1080p per job during the beta (split longer work) | 250 frames, 10 GPU hours, up to 4K per job; one job at a time |
| Blender versions | 5.0 (5.2 when the worker has it) | 2.79b to 5.2.1 bundled |
| Results | Inline preview image; files (stdio) or links valid 24 hours (remote); MP4 / WebM / ProRes / GIF / WebP or PNG / EXR frames | Download URLs that expire after 1 hour |
| Extras for agents | Environment presets (HDRI), orbit turntable, CC0 asset search (Poly Haven), MCP Apps panel, share pages | Many bundled Blender versions, more GPUs per job |
| Status | Free beta, no availability guarantee | Commercial |
Both services appeared in 2026 and change quickly. If a value above is out of date, tell us (support) and we will fix it.
| 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) | Settings → Connectors → Add custom connector → https://render.janction.jp/mcp. "Connect" opens a page that creates a free key |
| ChatGPT | Settings → Connectors → Advanced → Developer mode → Create → https://render.janction.jp/mcp (OAuth) |
| Claude Code | claude mcp add --transport http janction-render https://render.janction.jp/mcp, then /mcp to authenticate |
| Codex | codex mcp add janction-render --url https://render.janction.jp/mcp |
| Cursor / VS Code | Add to Cursor Add to VS Code The button opens the editor; confirm and it is added. Manual: Streamable HTTP at https://render.janction.jp/mcp |
| Gemini CLI / Antigravity CLI | gemini extensions install https://github.com/JasmyLab-JANCTION/janction-render |
| Grok / Perplexity / Le Chat | Add a custom (remote MCP) connector with https://render.janction.jp/mcp in each app's Connectors settings (Grok: New Connector → Custom; Perplexity: Pro / Max / Enterprise; Le Chat: workspace admin) |
| Windsurf, Cline, Goose, other MCP clients | Streamable HTTP at https://render.janction.jp/mcp; OAuth or Authorization: Bearer <api key> |
| 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 |
| 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.
Free beta (as of 2026-10-01): 10 GPU-minutes per key per day (20 per network), final renders up to 240 frames at 1080p. Quotas reset at 00:00 UTC (09:00 JST). New jobs exceeding the quota are rejected with HTTP 429 quota_exceeded and resets_at; they are not queued for the next day. Resubmit after the quota resets. No sign-up: connecting creates a key. Inputs and results are deleted 24 hours after last use and never used for training. Paid plans will be announced on this site and in llms.txt before they start.
No. As of 2026-09-30 it charges 43 credits (about $4.30) per GPU hour and has no free API tier. JANCTION Render is free during its beta with a daily quota.
Yes. Both expose remote MCP servers; an agent can preview on JANCTION Render and send a packed .blend to BlendSwap for a long paid job, or the other way round.
Per job BlendSwap can use up to 10 L40S GPUs, so long animations finish sooner there. JANCTION Render runs on one RTX PRO 6000 during the beta; its measured numbers are on the benchmarks page.
JANCTION Render v0.4.17 · JasmyLab Inc. · Updated 2026-10-05 · Tested with Blender 5.0, JANCTION Render 0.4.17 · 日本語