CoreWeave
US · gpu cloud
Large-scale GPU cloud used to host frontier training and inference.
- Category
- gpu cloud
- Free tier
- No
- OpenAI API
- Custom
- Adds on top
- None - undercuts list price
Margin over the underlying model price
What CoreWeave charges
Live prices for widely-hosted open-weight models, sampled from the shared catalogue. Compare the same row against other hosts on each model page.
| Model | Input / 1M | Output / 1M | Context | Throughput |
|---|---|---|---|---|
| Nemotron 3.5 Lightning | $0.070 | $0.200 | 262K | - |
| Granite 4.2 8B | $0.100 | $0.150 | 131K | - |
| DeepSeek V4 Flash 0731 | $0.130 | $0.280 | 262K | - |
| GLM 5.3 Flash | $0.150 | $0.500 | 1.0M | - |
| Qwen3.8 27B | $0.400 | $3.00 | 262K | - |
| DeepSeek V4 Pro 0813 | $1.31 | $3.96 | 1.0M | - |
CoreWeave alternatives
Other services in the same category. These are genuine substitutes - services in a different category solve a different problem.
Crusoe
GPU cloud powered by otherwise-stranded and low-carbon energy.
Hyperbolic
Pivoted from serverless inference to GPU rental during 2026; the dedicated inference pricing page is gone.
Lambda
GPU cloud. Its serverless Inference API is being wound down, so treat it as GPU rental rather than a token-billed endpoint.
Modal
Serverless GPU platform where you deploy your own inference code.
RunPod
Rentable GPUs and serverless workers for self-managed model serving.
Frequently asked
Is CoreWeave OpenAI-compatible?
No. CoreWeave uses its own API shape, so you will need its SDK or a translation layer such as LiteLLM.
Does CoreWeave have a free tier?
Not currently. CoreWeave bills from the first request.
How does CoreWeave charge?
Per GPU-hour Margin over the underlying model price: none - undercuts list price.