Models and regions

Labs

This feature is in Labs.

Otto and the AI features in the Astro IDE access models from OpenAI, Anthropic, and Google through the Astronomer Gateway. Astronomer hosts these models on Azure OpenAI Service and Google Cloud Vertex AI rather than calling the model providers directly.

This document is the source of truth for the specific models and hosting regions currently in use. Astronomer updates it as the available models change.

Azure OpenAI Service

These models run in the East US 2 region.

Model provider	Model
OpenAI	`gpt-5.5`
OpenAI	`gpt-5.4`
OpenAI	`gpt-5.4-mini`
OpenAI	`gpt-5.4-nano`
OpenAI	`gpt-5.3-codex`
Anthropic	`claude-opus-4-8`
Anthropic	`claude-opus-4-7`
Anthropic	`claude-opus-4-6`
Anthropic	`claude-sonnet-4-6`
Anthropic	`claude-haiku-4-5`

Google Cloud Vertex AI

These models run with the location set to global, which routes each request to whichever regional resource is available.

Model provider	Model
Anthropic	`claude-opus-4-7`
Anthropic	`claude-opus-4-6`
Anthropic	`claude-sonnet-4-6`
Anthropic	`claude-haiku-4-5`
Google	`google/gemini-3.1-pro-preview`
Google	`google/gemini-3.5-flash`
Google	`google/gemini-3-flash-preview`
Google	`google/gemini-2.5-pro`

Choose a model

To select a model for an Otto session, run /model in an interactive session to browse what’s available to you, or pass --model <id> to pin a model at launch. See Customize Otto and astro otto model selection.