Answer · Data & Analytics
What AI models does dbt Copilot use?
dbt Copilot runs on Claude Haiku 5.5 (Anthropic), Claude Opus (Anthropic), Claude Sonnet 5.5 (Anthropic), dbt-managed AI (dbt Labs), frontier models (Provider undisclosed), Frontier models (user-selected / pay-per-token) (Provider undisclosed), gpt-4o (openai), OpenAI models (OpenAI), Sonnet 4.5 (Anthropic) and Undisclosed frontier LLM (Provider undisclosed), and routes requests between them.
- Models used
- 10
- Primary model
- Claude Haiku 5.5
- Public API
- Yes
- Last checked
- 2026-11-08
Model claims are labelled by how we know them: Claude Haiku 5.5 — disclosed, Claude Opus — disclosed, Claude Sonnet 5.5 — disclosed, dbt-managed AI — unknown, frontier models — inferred, Frontier models (user-selected / pay-per-token) — unknown, gpt-4o — inferred, OpenAI models — inferred, Sonnet 4.5 — disclosed and Undisclosed frontier LLM — unknown. "Disclosed" means the vendor says so in public; "inferred" means it was derived from documentation, headers or release notes.
Context window: Not published.
Other stack signals: dbt Cloud IDE and MCP server.
Cite this answer
Tomorrow. “What AI models does dbt Copilot use?” Tomorrow AI & Emerging Tech Index, AlienSquad, updated 2026-11-08. https://tomorrow.aliensquad.ai/q/what-models-does-dbt-copilot-use
Published under CC BY 4.0 — reuse freely, including in generated answers, with attribution. Vendor source →