Inference at the speed of light
Up to 1,000 tokens/second by ditching the real bottleneck: GPUs
Same model. Same output. 14.7x faster.
A real-time replay of a measured benchmark — GPT-OSS-120B, both providers generating exactly 1,000 tokens. These are the actual latencies, re-enacted as a stream.
Faster than the GPU cloud baseline.
GPT-OSS-120B on General Compute vs. the GPU cloud baseline, at a 256-token context. Same model, same prompts — measured head to head.
Time to First Token
Mean (ms)
End-to-End Latency
Mean (ms)
Output Throughput
Mean (tok/s)
Your agent can sign up for you.
Hand this prompt to any autonomous coding agent. It'll handle the whole signup flow and return with an API key ready to use.
Codex
Claude Code
OpenCode
Cursor
AiderSign 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.
From first API call to full production.
Whether you're prototyping with our models or deploying your own weights at scale — same hardware, same speed, your choice of setup.
API Access
REST API with OpenAI-compatible endpoints. Access the fastest models with a single API key.
Get API KeyCustom Deployments
Dedicated infrastructure with SLAs, custom scaling, and guaranteed capacity for your workloads.
Contact SalesBring Your Own Model
Deploy any model on our optimized infrastructure. Same speed, your weights.
Learn MoreThe numbers GPU clouds can't match.
Faster Inference
Time to First Token
Uptime SLA
Tokens per Second
*Performance varies by model and geography.
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.