CoreWeave is a cloud platform that resells models with its own infrastructure, billing and regional hosting. Its prices tend to track the first-party rate, with the platform's own quotas and service-level terms attached.
It lists 29 models on this page. Coverage spans text and chat (29). The lowest-priced model hosted here is GPT OSS 20B.
CoreWeave is the lowest paid channel for 1 model that has at least two competing paid hosts, which is where its pricing genuinely leads rather than being the only option.
| Cheapest here? | |||||
|---|---|---|---|---|---|
| GPT OSS 20Bopenai/gpt-oss-20b | $0.03 | $0.13 | $0.03 | 131,072 | 1.5× pricier |
| Granite 4.1 8Bibm-granite/granite-4.1-8b | $0.05 | $0.10 | $0.05 | 131,072 | Only channel |
| Mellum2 12B A2.5BJetBrains/Mellum2-12B-A2.5B-Instruct | $0.05 | $0.10 | $0.05 | 131,072 | Only channel |
| GPT OSS 120Bopenai/gpt-oss-120b | $0.03 | $0.17 | $0.03 | 131,072 | 1.1× pricier |
| Qwen3 14B InstructOpenPipe/Qwen3-14B-Instruct | $0.05 | $0.22 | $0.05 | 32,768 | Only channel |
| Nemotron 3.5 Lightningnvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B | $0.07 | $0.20 | $0.04 | 262,144 | Only channel |
| Granite 4.2 8Bibm-granite/granite-4.2-8b | $0.10 | $0.15 | $0.05 | 131,072 | 1.0× pricier |
| Gemma 4 26B A4B ITgoogle/gemma-4-26B-A4B-it | $0.10 | $0.30 | $0.05 | 262,144 | 1.7× pricier |
| Qwen3 30B A3B Instruct 2507Qwen/Qwen3-30B-A3B-Instruct-2507 | $0.10 | $0.30 | $0.10 | 262,144 | 1.8× pricier |
| Gemma 4 31Bgoogle/gemma-4-31B-it | $0.10 | $0.34 | $0.10 | 262,144 | Lowest anywhere |
| DeepSeek V4 Flash 0731deepseek-ai/DeepSeek-V4-Flash-0731 | $0.13 | $0.28 | $0.07 | 262,144 | 3.8× pricier |
| DeepSeek V4 Flashdeepseek-ai/DeepSeek-V4-Flash | $0.14 | $0.28 | $0.07 | 1,048,576 | 4.0× pricier |
| Llama 3.1 8Bmeta-llama/Llama-3.1-8B-Instruct | $0.22 | $0.22 | $0.22 | 131,072 | 3.8× pricier |
| GLM-5.3-Flashzai-org/GLM-5.3-Flash | $0.15 | $0.50 | $0.05 | 1,048,576 | 5.0× pricier |
| DeepSeek V4.1 Flashdeepseek-ai/DeepSeek-V4.1-Flash | $0.20 | $0.65 | $0.03 | 1,048,576 | 6.3× pricier |
| MiniMax-M3MiniMaxAI/MiniMax-M3 | $0.23 | $0.96 | $0.05 | 262,144 | 1.1× pricier |
| Qwen3.6 35B-A3BQwen/Qwen3.6-35B-A3B | $0.25 | $1.25 | $0.25 | 262,144 | 4.6× pricier |
| Qwen3.5 35B-A3BQwen/Qwen3.5-35B-A3B | $0.25 | $1.25 | $0.25 | 262,144 | 3.2× pricier |
| Llama 3.3 70Bmeta-llama/Llama-3.3-70B-Instruct | $0.71 | $0.71 | $0.71 | 128,000 | 1.2× pricier |
| Llama-3.1-70B-Instructmeta-llama/Llama-3.1-70B-Instruct | $0.80 | $0.80 | $0.80 | 131,072 | 2.0× pricier |
| DeepSeek-V3.1deepseek-ai/DeepSeek-V3.1 | $0.55 | $1.65 | $0.55 | 161,000 | 2.6× pricier |
| Nemotron 3 Ultranvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B | $0.50 | $2.15 | $0.10 | 262,144 | 1.1× pricier |
| Qwen3.8 27BQwen/Qwen3.8-27B | $0.40 | $3.00 | $0.15 | 262,144 | 9.2× pricier |
| GLM-5.2zai-org/GLM-5.2 | $0.76 | $2.42 | $0.14 | 1,048,576 | 2.4× pricier |
| Kimi K2.6moonshotai/Kimi-K2.6 | $0.65 | $3.41 | $0.15 | 262,144 | 2.8× pricier |
| Qwen3.6 27BQwen/Qwen3.6-27B | $0.60 | $3.60 | $0.12 | 262,144 | 2.6× pricier |
| Kimi K2.7 Codemoonshotai/Kimi-K2.7-Code | $0.71 | $3.50 | $0.15 | 262,144 | 2.9× pricier |
| DeepSeek V4 Prodeepseek-ai/DeepSeek-V4-Pro | $1.15 | $2.55 | $0.20 | 1,048,576 | 5.7× pricier |
| DeepSeek V4 Pro 0813deepseek-ai/DeepSeek-V4-Pro-0813 | $1.31 | $3.96 | $0.044 | 1,048,576 | 4.3× pricier |