CoreWeave API pricing
23 CoreWeave models. Source: https://www.coreweave.com/products/serverless-inference
- Provider type
- Cloud
- Server location (where inference runs)
- unknown
- Regions
- unknown
- Company HQ (secondary)
- US (outside EU)
- EU data residency
- unknown
- Residency notes
- The Serverless Inference page lists per-model prices but does not state serving regions. OpenRouter's provider list reports CoreWeave's datacenters as US.
- Residency source
- none found: unknown
Primary location is where inference servers run (server region, from the cited source; otherwise 'unknown'). Company HQ is secondary public company information. OpenRouter prices are volatile: refreshed twice daily and excluded from cheapest-price answers.
Blend input:output
| Provider | Model | Input | Output | Cached in | Blended 3:1* ▲ | Context | EU residency |
|---|---|---|---|---|---|---|---|
| CoreWeave Cloud | OpenAI GPT OSS 20B | $0.03 | $0.13 | — | $0.055 | — | unknown |
| CoreWeave Cloud | OpenAI GPT OSS 120B | $0.03 | $0.17 | — | $0.065 | — | unknown |
| CoreWeave Cloud | NVIDIA Nemotron 3.5 Lightning | $0.07 | $0.20 | $0.04 | $0.103 | — | unknown |
| CoreWeave Cloud | IBM Granite 4.2 8B | $0.10 | $0.15 | $0.05 | $0.113 | — | unknown |
| CoreWeave Cloud | Google Gemma 4 26B A4B Instruct | $0.10 | $0.30 | $0.05 | $0.15 | — | unknown |
| CoreWeave Cloud | Google Gemma 4 31B | $0.10 | $0.34 | — | $0.16 | — | unknown |
| CoreWeave Cloud | DeepSeek V4-Flash-0731 | $0.13 | $0.28 | $0.07 | $0.168 | — | unknown |
| CoreWeave Cloud | Meta Llama 3.1 8B | $0.22 | $0.22 | — | $0.22 | — | unknown |
| CoreWeave Cloud | Z.AI GLM 5.3 Flash | $0.15 | $0.50 | $0.05 | $0.237 | — | unknown |
| CoreWeave Cloud | DeepSeek V4.1-Flash | $0.20 | $0.65 | $0.03 | $0.313 | — | unknown |
| CoreWeave Cloud | MiniMax M3 | $0.23 | $0.96 | $0.05 | $0.412 | — | unknown |
| CoreWeave Cloud | Qwen3.6 35B A3B | $0.25 | $1.25 | — | $0.50 | — | unknown |
| CoreWeave Cloud | NVIDIA Nemotron 3.5 Super VL | $0.25 | $1.50 | $0.05 | $0.563 | — | unknown |
| CoreWeave Cloud | Meta Llama 3.3 70B | $0.71 | $0.71 | — | $0.71 | — | unknown |
| CoreWeave Cloud | Deepseek V3.1 | $0.55 | $1.65 | — | $0.825 | — | unknown |
| CoreWeave Cloud | NVIDIA Nemotron 3 Ultra | $0.50 | $2.15 | $0.10 | $0.912 | — | unknown |
| CoreWeave Cloud | Qwen3.8 27B | $0.40 | $3.00 | $0.15 | $1.05 | — | unknown |
| CoreWeave Cloud | Z.AI GLM 5.2 | $0.76 | $2.42 | $0.14 | $1.18 | — | unknown |
| CoreWeave Cloud | Moonshot AI Kimi K2.6 | $0.65 | $3.41 | $0.15 | $1.34 | — | unknown |
| CoreWeave Cloud | Moonshot AI Kimi K2.7 Code | $0.71 | $3.50 | $0.15 | $1.41 | — | unknown |
| CoreWeave Cloud | Reflection Beam 1.0 | $1.00 | $3.00 | $0.10 | $1.50 | — | unknown |
| CoreWeave Cloud | Z.AI GLM 5.3 | $1.20 | $4.00 | $0.19 | $1.90 | — | unknown |
| CoreWeave Cloud | DeepSeek V4-Pro-0813 | $1.31 | $3.96 | $0.044 | $1.97 | — | unknown |
Per 1M tokens, standard (non-promo) list prices; short-context / peak tier where tiered. USD unless shown with € or CHF: those are as published and not converted. Click a header to sort. 23 models.
* Blended assumes 3 input tokens for every output token: (3×input + output) / 4. Your real mix will differ, so use the cost calculator with your own token counts for a real estimate.