Calculator
Self-host or API?
For an open-weights model, compare renting GPUs to run it yourself with the cheapest API offer. The answer is an estimate, built from published prices and published throughput figures.
Hardware rental only: the hourly price the provider publishes for the machine. It does not count the engineering to deploy and run the model, monitoring, redundancy, start-up time, or storage and network costs billed separately.
How it is calculated
We decline to give a number
Rather than an unreliable figure, here is what is missing.
The weights (2,779.9 GB in fp8) do not fit within 70% of the memory of the requested configuration.
Memory of the requested configuration: 2,048 GB Memory needed: 3,971.3 GB
Weights: 2,779.9 GB Memory needed: 3,971.3 GB Memory available: 2,048 GB Aion-RP 1.0 (8B) Apertus-70B-Instruct-2509 Apertus-8B-Instruct-2509 Apertus-v1.5-70B AutoGLM-Phone-9B-Multilingual Beam 1.0 501B A23B Bielik-11B-v3.0-Instruct Command A Command R (08-2024) Command R+ (08-2024) Command R7B (12-2024) Cydonia 24B V4.1 DeepSeek V3 DeepSeek V3 0324 DeepSeek V3.1 DeepSeek V3.1 Terminus DeepSeek V3.2 DeepSeek V3.2 Exp DeepSeek V3.2 Exp Thinking DeepSeek V4 Flash 0731 DeepSeek V4 Pro 0813 DeepSeek V4.1 Flash DeepSeek V4.1 Flash 1017 DeepSeek-R1-Distill-Llama-8B DeepSeek-R1-Distill-Qwen-14B DeepSeek-R1-Distill-Qwen-7B Devstral 2 2512 Gemma 2 27B Gemma 3 12B Gemma 3 27B Gemma 3 4B Gemma 4 26B A4B Gemma 4 31B Gemma-SEA-LION-v4-27B-IT GLM 4.5 GLM 4.5 Air GLM 4.5V GLM 4.6 GLM 4.6V GLM 4.7 GLM 4.7 Flash GLM 5 GLM 5.1 GLM 5.2 GLM 5.3 GLM 5.3 Flash GLM-4-32B-0414 GLM-4.6V-Flash gpt-oss-120b gpt-oss-20b gpt-oss-safeguard-20b Granite 4.0 Micro Granite 4.2 8B granite-4.2-30b granite-4.2-3b Hermes 3 405B Instruct Hermes 3 70B Instruct Hermes 4 405B Hy3 Hy3 preview Hy4 preview Inkling Inkling Small Kimi K2 0711 Kimi K2 0905 Kimi K2 Thinking Kimi K2.5 Kimi K2.6 Kimi K2.7 Code Kimi K3 L3-8B-Stheno-v3.2 Laguna S 2.1 Laguna XS 2.1 LFM2.5-24B-A2B Ling 3.0 Flash Ling 3.0 Flash Fin Ling 3.0 Flash VL Ling 3.1 Flash Llama 3 8B Lunaris Llama 3.1 405B Instruct Llama 3.1 70B Instruct Llama 3.1 8B Instruct Llama 3.2 1B Instruct Llama 3.2 3B Instruct Llama 3.3 70B Instruct Llama 3.3 Euryale 70B Llama 4 Maverick Llama 4 Scout Llama Guard 4 12B LongCat 2.0 Magnum v4 72B MiMo-V2.5 MiMo-V2.5-Pro MiMo-V2.6-Flash MiMo-V2.6-Pro MiniMax M1 MiniMax M2 MiniMax M2.1 MiniMax M2.5 MiniMax M2.7 MiniMax M3 MiniMax M3.1 Flash MiniMax-01 MiniMax-M1-80k Ministral 3 14B 2512 Ministral 3 3B 2512 Ministral 3 8B 2512 Mistral Large 2407 Mistral Medium 3.5 Mistral Nemo Mistral Small 3 Mistral Small 3.1 24B Mistral Small 3.2 24B Mistral Small 4 Mixtral 8x22B Instruct Muse Glimmer 30B Nemotron 3 Nano 30B A3B Nemotron 3 Super Nemotron 3 Ultra Nemotron 3.5 Content Safety Nemotron 3.5 Lightning Nex-N2.5-Mini NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4 Phi 4 Qwen-SEA-LION-v4-32B-IT Qwen-SEA-LION-v4.5-27B-IT Qwen2.5 72B Instruct Qwen2.5 7B Instruct Qwen2.5 Coder 32B Instruct Qwen2.5 VL 72B Instruct Qwen2.5-Coder-3B-Instruct Qwen2.5-Coder-7B-Instruct Qwen3 14B Qwen3 235B A22B Qwen3 235B A22B Instruct 2507 Qwen3 235B A22B Thinking 2507 Qwen3 30B A3B Qwen3 30B A3B Instruct 2507 Qwen3 32B Qwen3 8B Qwen3 Coder 30B A3B Instruct Qwen3 Coder 480B A35B Qwen3 Coder Next Qwen3 Next 80B A3B Instruct Qwen3 Next 80B A3B Thinking Qwen3 VL 235B A22B Instruct Qwen3 VL 235B A22B Thinking Qwen3 VL 30B A3B Instruct Qwen3 VL 30B A3B Thinking Qwen3 VL 32B Instruct Qwen3 VL 8B Instruct Qwen3-4B-Instruct-2507 Qwen3-4B-Thinking-2507 Qwen3.5 397B A17B Qwen3.5-122B-A10B Qwen3.5-27B Qwen3.5-35B-A3B Qwen3.5-9B Qwen3.6 27B Qwen3.6 35B A3B Qwen3.8 2.4T A95B Qwen3.8 27B Qwen3.8 Flash R1 R1 0528 R1 Distill Llama 70B Reka Edge Step 3.5 Flash Step 3.7 Flash Step 5 Preview Tev1-4B-experimental Trinity Large Thinking UI-TARS 7B UnslopNemo 12B Voxtral Small 24B 2507
