Skip to main content
Verlon AI ships adapters for four providers and gives you access to 214 language models through a single API. Pick a provider below for its full model list, quickstart, and SDK compatibility notes — or hit the live registry endpoint for machine-readable data (pricing, capabilities, deprecation status).

OpenAI

Frontier chat and reasoning across the GPT-4o, GPT-5, and o-series lineups — plus image, audio, TTS, STT, moderation, and embeddings.

Anthropic

The full Claude family — Opus, Sonnet, and Haiku across the 3.5, 4, 4.5, 4.6, 4.7, and 4.8 generations.

Google

Gemini 1.5 through 3.5 (chat and reasoning), plus Gemma open-weights and the full multimodal lineup — image, video, TTS, audio, embeddings.

Mistral

Large, Medium, Small, Ministral, Codestral, Devstral, Magistral, and Pixtral — plus embeddings, moderation, OCR, STT, and TTS.

​
Live registry

For the machine-readable list with per-model pricing, capabilities, context windows, and deprecation status: 
GET https://api.verlon.ai/v1/registry
Public endpoint, no authentication required. Cached for one hour with an ETag; safe to poll from clients and agents. Every Verlon SDK validates model values against this registry, and the dashboard’s model picker renders directly from it.
Missing a model or provider? Ping us at micah@verlon.ai — most additions ship inside a week.