Studio Inference
BillingGet API key
Studio Inference Platform

Vision LLMs, image, and video generation.
One API key. One bill.

OpenAI-compatible chat with multimodal models. Image and video generation with the same auth. Sub-second time-to-first-token from datacenter GPUs.

✦
Language
Chat completions, vision-grounded reasoning, structured extraction
4 models →
◆
Image
Text-to-image, photoreal and stylized, up to 1536px
6 models →
▶
Video
Image-to-video and speech-to-video, 5-10s clips
1 model →

Featured models

View all →
Cyber-XL / SDXL (local)
image
SDXL-based Cyber-XL on local RTX pool. ~25s/image.
FLUX 2 Klein 4B (local)
image
FLUX 2 Klein 4B on local RTX pool. ~18s/image.
Flux Krea
image
High-fidelity text-to-image. Photorealistic and stylized. Up to 1536px.
photorealstylized
Qwen Image Edit (2511 v1.1)
image
Prompt-guided image editing on 1, 2, or 3 input images. RunPod serverless on 24GB Pro.
image-editmulti-image
Z-Image Pro
image
Fast turbo text-to-image. Good for thumbnails, drafts, and high-volume use.
fastdraft
Z-Image Turbo (local)
image
Fast Z-Image Turbo on local RTX pool. ~12s/image.

Ready in 60 seconds

Sign up, grab a key, and curl your first completion.