Answer · Enterprise Platforms

What AI models does watsonx Orchestrate use?

watsonx Orchestrate runs on GPT-OSS (OpenAI), Granite 4 (IBM), Llama (Meta), Mistral (Mistral), watsonx.ai (IBM) and watsonx.ai foundation models (IBM), and routes requests between them.

Models used
6
Primary model
GPT-OSS
Public API
Yes
Last checked
2026-09-11

Model claims are labelled by how we know them: GPT-OSS — disclosed, Granite 4 — disclosed, Llama — disclosed, Mistral — disclosed, watsonx.ai — inferred and watsonx.ai foundation models — inferred. "Disclosed" means the vendor says so in public; "inferred" means it was derived from documentation, headers or release notes.

Context window: 128K.

Other stack signals: LangGraph, Langflow, Elasticsearch, Milvus, Astra DB, OpenSearch, AWS, Genesys, Salesforce, Zendesk and Twilio Flex.

Cite this answer

Tomorrow. “What AI models does watsonx Orchestrate use?” Tomorrow AI & Emerging Tech Index, AlienSquad, updated 2026-09-11. https://tomorrow.aliensquad.ai/q/what-models-does-ibm-watsonx-orchestrate-use

Published under CC BY 4.0 — reuse freely, including in generated answers, with attribution. Vendor source →

← Every answered question