Feature

Fine-Tuning & Custom Models

Adapt hosted models to your own data.

10 providers 73 APIs 9 declared variants

Customers can fine-tune, adapt, or train custom models on their data within the platform. Matters when prompt engineering alone cannot hit the required accuracy.

10 API providers on the APIs.io network offer fine-tuning & custom models. The highest-rated are ChatGPT, Replicate, Mistral AI, Deepgram, Leonardo.AI.

Providers

Ranked by API Evangelist rating — Exemplar and Strong are expanded by default.

Exemplar 1 Complete, well-documented, and agent-ready
ChatGPT OpenAI's ChatGPT API for conversational AI and language model interactions. 13 APIs 70.6
Strong 3 Solid coverage with minor gaps
Replicate Replicate lets you run machine learning models in the cloud with a simple API. Thousands of open-source mod... 1 API 64.8 Mistral AI Mistral AI provides state-of-the-art large language models and AI APIs for developers and enterprises. 11 APIs 60.6 Deepgram Deepgram is an enterprise voice AI platform that provides speech-to-text, text-to-speech, and voice agent A... 5 APIs 60.4
Developing 3 Usable, with meaningful gaps to close
Leonardo.AI Leonardo.AI is an Australian generative-AI company (acquired by Canva in July 2024) offering a Production A... 14 APIs 56.7 Apache OpenNLP Apache OpenNLP is a machine learning based toolkit for the processing of natural language text. It supports... 1 API 50.9 Amazon Nova Amazon Nova is a new generation of state-of-the-art foundation models from Amazon that deliver a compelling... 1 API 46.8
Thin 2 Limited public surface area
Docling Docling is an open-source toolkit for parsing diverse document formats — PDF, DOCX, PPTX, XLSX, HTML, image... 16 APIs 44.2 cohere Generates a text response to a user message and streams it down, token by token. 9 APIs 42.8
Emerging 1 Early or largely undocumented
Refact.ai Refact.ai is an open-source, local-first AI coding assistant and autonomous software-engineering agent buil... 2 APIs 19.5

What Providers Actually Declared

This feature is a canonical term. These are the free-text strings providers wrote in their own apis.yml that map onto it.

Custom Model TrainingCustom Models and Custom Elements — LoRA-style fine-tuning on user-uploaded datasetsCustom model training (Enterprise)Fine-TuningFine-tuning for Command and AyaFine-tuning service for select modelsLLM fine-tuning on company codebase (Refact, StarCoder, DeepSeek-Coder, CodeLlama variants)Synthetic data generation via docling-sdg for fine-tuningTraining service for fine-tuning

Scroll for all 9