CoreWeave API pricing
Live prices for every model CoreWeave serves: its own per-1M-token prices, or per image, second or character, next to the cheapest price elsewhere.
CoreWeave serves 19 models with live API prices on SF·SIX, 19 models priced per 1M tokens. The cheapest is gpt-oss-20b at $0.03 per 1M input and $0.13 per 1M output tokens. The most used on OpenRouter is GLM 5.3 Flash (1.73T tokens on 2026-10-16).
- Models with live prices
- 19
- Cheapest language model
- gpt-oss-20b$0.03 / $0.13 per 1M tokens
- Most used on OpenRouter (2026-10-16)
- GLM 5.3 Flash1.73T tokens
- Newest model
- Beam 1.0 501B A23B2026-10-16
- Cheapest standard host for
- 2 models of 19
CoreWeave token prices (USD per 1M tokens)
| Model | Input / 1M | Output / 1M | Terms | Cheapest standard price anywhere | Context (tokens) | OpenRouter tokens / day |
|---|---|---|---|---|---|---|
| GLM 5.3 Flash | $0.15 | $0.50 | Standard · nvfp4 | $0.075 / $0.25DeepInfra (fp4) | 1,048,576 | 1.73T |
| GLM 5.2 | $0.62 | $2.42 | Standard · fp4 | $0.189 / $0.594Baidu (fp8) | 1,048,576 | 140.87B |
| DeepSeek V4 Flash 0731 | $0.13 | $0.28 | Standard · fp8 | $0.0598 / $0.1795Baidu (fp8) | 1,048,576 | 620.6B |
| DeepSeek V4 Pro 0813 | $1.31 | $3.96 | Standard · fp8 | $0.1333 / $0.40Baidu (fp8) | 1,048,576 | 161.08B |
| gpt-oss-120b | $0.03 | $0.17 | Standard · fp4 | $0.03 / $0.15Near AI (fp4) | 131,072 | 86.23B |
| Kimi K2.6 | $0.65 | $3.41 | Standard · fp4 | $0.4323 / $1.82Baidu (fp4) | 262,144 | Not in named rows |
| MiniMax M3 | $0.23 | $0.96 | Standard · fp4 | CoreWeavecheapest standard host | 1,048,576 | 210.13B |
| Kimi K2.7 Code | $0.71 | $3.50 | Standard · int4 | $0.7125 / $3.00StreamLake | 262,144 | Not in named rows |
| Gemma 4 26B A4B | $0.10 | $0.30 | Standard · bf16 | $0.042 / $0.22Darkbloom | 262,144 | Not in named rows |
| Gemma 4 31B | $0.10 | $0.34 | Standard · fp4 | CoreWeavecheapest standard host | 262,144 | 73.13B |
| Qwen3.6 35B A3B | $0.25 | $1.25 | Standard · fp8 | $0.05 / $0.70Darkbloom (fp4) | 262,144 | 386.14B |
| gpt-oss-20b | $0.03 | $0.13 | Standard · fp4 | $0.018 / $0.09Darkbloom (fp8) | 131,072 | Not in named rows |
| Llama 3.3 70B Instruct | $0.71 | $0.71 | Standard · fp16 | $0.135 / $0.40Novita AI (bf16) | 131,072 | Not in named rows |
| Llama 3.1 8B Instruct | $0.22 | $0.22 | Standard · bf16 | $0.02 / $0.04DeepInfra (fp8) | 131,072 | Not in named rows |
| Beam 1.0 501B A23B | $1.00 | $3.00 | Standard · fp4 | $0.25 / $1.00Nebius AI Studio (fp8) | 1,048,576 | Not in named rows |
| Nemotron 3.5 Lightning | $0.07 | $0.20 | Standard · bf16 | $0.025 / $0.12Darkbloom (int4) | 262,144 | 90.07B |
| DeepSeek V3.1 | $0.55 | $1.65 | Standard · fp8 | $0.25 / $0.95DeepInfra (fp4) | 163,840 | Not in named rows |
| Nemotron 3.5 Super VL | $0.15 | $0.50 | Standard · nvfp4 | $0.10 / $0.40DeepInfra (fp4) | 1,048,576 | 287.58B |
| Granite 4.2 8B | $0.10 | $0.15 | Standard · bf16 | $0.06 / $0.25DeepInfra (bf16) | 131,072 | Not in named rows |
CoreWeave’s own endpoint for each model (standard tier and default region first), next to the cheapest standard price from any provider. Most widely served first.
Method
Prices are USD per 1M tokens at the standard service tier in the default region: the cheapest qualifying provider per model, with flex, batch, priority and fast endpoints and unusually low outliers never used as the headline. “Blended” weights input and output 3:1. Missing prices are unknown, not free. OpenRouter tokens per day are the latest full UTC day of OpenRouter’s public rankings (named rows only). Prices move: see AI API price changes for recent cuts and increases.