Baseten

Listed at https://www.baseten.co

Overall Rank #18 ⭐ Consider
⚠️ Partially available (stable proxy recommended in China) | 🌍 International

💰 Token Pricing

TypePriceNote
Input Per-second GPU billing (H100: $1.89/hr, A100: $0.83/hr, L40S: $0.54/hr) per million tokens
Output Model-dependent (inference time × GPU rate) per million tokens
Cache ReadN/A (no caching layer on hosted inference)Discounted
💡 Free Credits: $30 in inference credits on signup (valid 30 days); custom model hosting free tier: 1 deployed model

🤖 Supported Models (35)

Llama 3.3 70BLlama 3.1 405BMixtral 8x22BQwen 2.5 72BQwen 2.5 Coder 32BDeepSeek V3DeepSeek R1Mistral Large 2Phi-3.5 MediumFLUX.1 [schnell]SDXLStable Diffusion 3.5 LargeWhisper Large V3XTTS v2BGE Large v1.5GTE-Qwen2 7BAny custom model (Truss)

✨ Pros

  • Per-second GPU billing, the most transparent pay-as-you-go among Replicate-style competitors
  • Custom model hosting (Truss framework) — deploy any Hugging Face model in one command
  • Cold start < 1 second (proprietary warm pool + autoscaling)
  • Dedicated Deployments with reserved GPU capacity and SLA commitment
  • Supports PyTorch / TensorRT / vLLM inference engines, auto-selects the optimal backend
  • MCP server support for Claude/Cursor integration
  • No GPU idle fees on self-deployed models since 2025 (advantage over RunPod / Lambda Labs)

⚠️ Cons

  • ×No pretrained model marketplace (vs Replicate 200+ ready-to-use models; Baseten is more self-deploy focused)
  • ×China access requires stable proxy
  • ×Per-second billing advantage diminishes for sub-5s inference calls
  • ×Truss framework learning curve (vs direct HuggingFace Inference API)
  • ×Dedicated Deployment starting price is higher than bare AWS/GPU instances

🎯 Best For

Self-deploy open-source models (Llama / Qwen / DeepSeek) on production GPUs; mid-to-large teams needing Dedicated SLAs; MCP integration into Claude / Cursor