Deploy any model — ours or yours — with inference speed that changes what's possible.
Your agent can sign up for you.
Hand this prompt to your autonomous coding agent and it'll walk through our signup flow on your behalf.
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.
See the difference.
Both running GPT OSS 120B — same model, same prompt. Only the infrastructure is different.
General ComputeUsReady to compare
Together AICompetitorReady to compare
Try preset prompts or enter your own to compare inference speed in real-time
How We're Faster & Cheaper
We rethought the entire stack from silicon to site selection — so you get better performance at a fraction of the cost.
How We're Faster
- Purpose-built AI accelerators — not general-purpose GPUs
- Optimized software stack tuned end-to-end for inference
- Disaggregated architecture that scales each resource independently
How We're Cheaper
- Cheap energy inputs — $0.035/kWh vs $0.13 US average
- 7x more energy-efficient accelerators (17 kW* vs 120 kW)
- Air cooled — no expensive liquid cooling infrastructure
General Compute vs NVIDIA GPU Cloud
MiniMax M2.5 model comparison
Throughput (tokens/sec)*
Higher is better
Energy Usage*
Lower is better
Energy Cost
Lower is better
*Projected on next-generation racks. NVIDIA throughput via Together AI benchmarks. Energy: US commercial avg vs. our rate.
Built for Every Workload
From prototyping to production, we have the infrastructure to match your needs.
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 MoreSpeed That Speaks for Itself
Real numbers, real infrastructure, real-time performance.
Faster Inference
Time to First Token
Uptime SLA
Tokens per Second
*Performance varies by model and geography.
Switch at warp speed
OpenAI-compatible API. Change your base URL and API key — that's it. Your existing code works instantly, just faster.
from 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,
)Start Building Today
Get your API key in seconds. OpenAI-compatible — just change your base URL and start shipping faster.