SERVERLESS INFERENCE
GPU inference, zero infrastructure.
Stop managing GPU instances, CUDA versions, model loading, and autoscaling. Runcrate's serverless inference runs 200+ AI models on dedicated hardware with per-token billing. No cold starts, no idle costs, no infrastructure to maintain. Send requests, get results, pay for what you use.
AVAILABLE GPUS
GPUs you can deploy today.
| Model | Provider | Price | Detail |
|---|---|---|---|
| deepseek-ai/DeepSeek-V3 | DeepSeek | Per-token | 128K context, MoE architecture |
| meta-llama/Llama-4-Scout-17B-16E-Instruct | Meta | Per-token | 17B MoE, 128K context |
| black-forest-labs/FLUX.1-dev | Black Forest Labs | Per-image | 12B, photorealistic images |
| openai/whisper-large-v3 | OpenAI | Per-minute | Speech-to-text, 100+ languages |
WHY RUNCRATE
Built for production.
Zero Infrastructure
No GPU provisioning, no Docker containers, no autoscaling policies, no CUDA debugging. Send a request, get a result. Runcrate handles everything else.
No Cold Starts
Models are always warm and ready. First request is as fast as the thousandth. No waiting for model loading, container spin-up, or weight downloads.
Per-Usage Billing
Pay per token, per image, per second of audio, or per second of video. No idle GPU costs, no monthly minimums, no seat licenses. Credits never expire.
Multi-Modal
Chat, image generation, video generation, speech-to-text, text-to-speech, embeddings, and vision, all through one API and one billing account.
COMPARISON
Runcrate vs Self-Hosted GPU.
| Feature | Runcrate | Self-Hosted GPU |
|---|---|---|
| Setup time | < 60 seconds | Hours to days |
| Cold starts | None | Model loading time |
| Scaling | Automatic | Manual autoscaling |
| Idle cost | $0 | Full GPU cost 24/7 |
| Maintenance | Zero | CUDA, drivers, monitoring |
GET STARTED
Try it now.
from openai import OpenAI
client = OpenAI(
base_url="https://api.runcrate.ai/v1",
api_key="rc_live_YOUR_API_KEY",
)
# Chat completion
chat = client.chat.completions.create(
model="deepseek-ai/DeepSeek-V3",
messages=[{"role": "user", "content": "Hello, world!"}],
)
# Image generation
image = client.images.generate(
model="black-forest-labs/FLUX.1-dev",
prompt="A futuristic cityscape",
)
# Speech-to-text
transcript = client.audio.transcriptions.create(
model="openai/whisper-large-v3",
file=open("audio.mp3", "rb"),
)FAQ