Skip to content
TA

Together AI

Inference and tuning

Official site consultedAI and speech (global tools)

Last verified: 1 October 2026

Together AI offers an OpenAI-compatible serverless inference API billed per token, dedicated instances, GPU clusters, fine-tuning and batch inference. The catalog includes chat, audio (Whisper), image and vision models.

Services
  • Serverless inference API
  • Dedicated instances and GPU clusters
  • Fine-tuning
  • Batch inference and Evals API
Access requirements

Usage-based pricing; the page states no free credits. A playground is mentioned.

Sources