Hosting plans
Every plan we track, with its provider, pricing model and the LLMs it can run.
| Plan | LLM host | Type | Pricing | Models |
|---|---|---|---|---|
| Fireworks AI On-Demand Deployments | Fireworks AI | Dedicated endpoint | Per GPU-hour, Per second of GPU time | Llama 3.3 70B Instruct, DeepSeek-V3, Qwen2.5 72B Instruct |
| Fireworks AI Serverless | Fireworks AI | Serverless API | Pay per token | Llama 3.3 70B Instruct, Llama 3.1 8B Instruct, DeepSeek-V3, gpt-oss-120b |
| GroqCloud Developer Tier | Groq | Serverless API | Pay per token | Llama 3.3 70B Instruct, Llama 3.1 8B Instruct, gpt-oss-120b |
| RunPod GPU Pods | RunPod | GPU cloud | Per GPU-hour | Llama 3.3 70B Instruct, Llama 3.1 8B Instruct, Qwen2.5 72B Instruct, DeepSeek-V3, gpt-oss-120b |
| RunPod Serverless | RunPod | Serverless GPU | Per second of GPU time | Llama 3.1 8B Instruct, Llama 3.3 70B Instruct, Qwen2.5 72B Instruct, gpt-oss-120b |
| Together AI Dedicated Endpoints | Together AI | Dedicated endpoint | Per GPU-hour | Llama 3.3 70B Instruct, Qwen2.5 72B Instruct, Llama 3.1 8B Instruct |
| Together AI Serverless Inference | Together AI | Serverless API | Pay per token | Llama 3.3 70B Instruct, Llama 3.1 8B Instruct, Qwen2.5 72B Instruct, DeepSeek-V3, gpt-oss-120b |