Skip to content

Capabilities

Fine-Tuning

Custom model training on user data

Read this when
  • Training a model on customer data

Compatibility

ProviderAPIpi-goNotes
Anthropic⚠️ Bedrock-only (Haiku, LoRA)
OpenAI Chat✅ SFT, vision FT, DPO, RFT
OpenAI Responsesuses base FT’d models
Google Gemini✅ supervised tuning (LoRA / full) on Gemini 2.5 Pro/Flash/Flash-lite via Vertex
Claude CLI

Provider Documentation

pi-go Gaps

  • No fine-tuning helpers anywhere — typically out of scope for an SDK focused on inference.
  • Fine-tuned model IDs do work today as plain Model.ID strings; no special handling required.