Inference at the speed of light
Up to 1,000 tokens/second by ditching the real bottleneck: GPUs
Up to 16.1x faster
OpenCode running the identical task on both sides. A real coding session at measured operating points.
GPU cloud today
For Startups and Enterprises
The same hardware sits behind all three. Begin on the public API, graduate to dedicated capacity, or bring your own model — the speed comes along for the ride.
API Access
Get an API keyOpenAI-compatible REST endpoints. Swap your base URL, keep your code.
Custom Deployments
Talk to usDedicated capacity with SLAs and guaranteed throughput, sized to your traffic.
Bring Your Own Model
See how it worksShip your own weights on the same optimized stack. Your model, our hardware.
Your agent can sign up for you.
Hand this prompt to any autonomous coding agent. It handles the whole signup flow and comes back with a key — no dashboard, no forms.
Codex
Claude CodeOpenCode
CursorSign me up for a General Compute API account and get an API key. Fetch instructions from https://docs.generalcompute.com/agent-signup and follow them.
Verified benchmarks
GPT-OSS-120B on General Compute against the GPU cloud baseline — same model, same prompts, measured head to head.
See the full methodology and every model →Faster time to first token
Higher output throughput
Lower end-to-end latency
Output on GPT-OSS-120B
Switch in 30 seconds. No GPU required.
OpenAI-compatible API. Change your base URL, swap your key, and you're running on ASIC infrastructure. Your existing code doesn't change.
View Docsfrom openai import OpenAI
client = OpenAI(
base_url="https://api.generalcompute.com",
api_key="your-api-key",
)
response = client.chat.completions.create(
model="gpt-oss-120b",
messages=[{"role": "user", "content": "Hello!"}],
stream=True,
)Stop paying the GPU tax.
Get your API key in seconds. OpenAI-compatible — just change your base URL. $10 free credit to see the difference yourself.