The plan we recommend: 50,000 tokens every month — 2.5× what the one-time $20 pack gives you, refreshed automatically — plus full access to the Colab notebook library. One subscription, everything unlocked.
How the trial works: sign in with Google → use the Studio free for 7 days → keep everything by subscribing. Cancel anytime.
No subscription, no commitment — top up a shared balance whenever you need it. Works in the browser Studio and through the API. New here? Start the 7-day free trial first.
4K upsamples bill at 2 credits. Camera-mode renders bill at 1 credit per angle. Batch jobs bill per image. Millions of edits or dedicated capacity? Contact us for volume pricing.
| Provider | Standard instruction edit | Edits per $1 |
|---|---|---|
| MissingLink | $0.002 | 500 |
| fal.ai — qwen-image-edit-2511 | ~$0.03 | ~33 |
| fal.ai — Qwen Image 2.0 Edit | $0.035 | ~28 |
| xAI Grok Imagine Edit (via fal) | $0.022 | ~45 |
Competitor prices as publicly listed, July 2026; fal bills per megapixel rounded up. Verify current rates with each provider.
Prefer Colab? The Triton kernels and libraries powering Image Studio ship as prebuilt wheels — one pip install, zero collisions with the default Colab stack.
One-time purchase — yours forever
One-time payment via Stripe. Includes all current wheels for every supported GPU.
Stay current as Colab updates — includes hosted credits
Billed monthly by Stripe. We never see your card. Cancel or manage anytime.
Editing images? Start with the 7-day free trial — sign in with Google, works in the Studio and the API, and credit packs kick in when you need volume. Working in Colab notebooks? The Survival Pack is one payment for every wheel, forever. Want both worlds and automatic rebuilds every time Google changes the Colab runtime? Pro bundles the wheels with 2,500 hosted credits a month.
Buy individual packages if you only need a specific wheel.
More individual wheels coming soon. Need a specific one? Support
Both developer plans include every wheel below, prebuilt and guaranteed to work against CUDA 12.8, PyTorch 2.10, and Python 3.12 on Google Colab. Every wheel installs cleanly alongside the default Colab stack — no uninstalls, no version conflicts, no battling dependencies.
Flash Attention 2 — efficient transformer inference on A100/L4/T4.
Memory-efficient attention and transformer building blocks from Meta.
NVIDIA's differentiable rasterizer for 3D deep learning.
CUDA-accelerated mesh processing for 3D pipelines.
Flexible GEMM kernels for mixed-precision on Ampere GPUs.
CUDA voxel utilities for 3D pipeline work.
Neural rendering components for reconstruction pipelines.
3D math and geometry with CUDA acceleration.
Run GGUF-quantized Stable Diffusion models. Compiled for frictionless T4 compatibility.
| Spec | Details |
|---|---|
| GPU | NVIDIA A100 NVIDIA L4 NVIDIA T4 |
| Platform | Google Colab linux x86_64 |
| Python | 3.12 |
| CUDA | 12.8 |
| PyTorch | 2.10 |