tools

Grounded Language Model

Grounded Language Model genera risposte a partire dai documenti recuperati, aggiunge riferimenti alle fonti direttamente nel testo e riduce le affermazioni prive di riscontro nelle applicazioni RAG.

In inglese

Grounded Language Model is Contextual AI's model for retrieval-augmented generation and agentic applications. It prioritizes retrieved knowledge over pretrained knowledge, provides inline attributions, and can separate factual content from commentary.

Teams access it through the /generate API or Contextual AI agents. The service includes free credits for the first 1M input and 1M output tokens; additional usage is charged by token, and custom rate limits and pricing require contacting Contextual AI.

Features

Generates responses grounded in retrieved documents
Provides inline attributions to source documents
Prioritizes retrieved knowledge over pretrained knowledge
Supports an avoid_commentary control
Can refuse to answer when supplied documents are not relevant
Available through the standalone /generate API
Available as the default model for new agents

Use cases

Answer questions from enterprise knowledge bases
Build customer-support assistants grounded in current policies
Support engineering research over technical documentation
Create finance research tools that cite source material
Add grounded generation to an existing RAG pipeline

Pros

Cons

Latest updates

2025-09-11 Contextual AI Summer Product Updates
Sync data from Google Drive and SharePoint, add custom metadata, select third-party LLMs, use agent templates, and upload documents in chat.
2025-09-11 Securely scale document ingestion with connectors
Sync data directly from external systems such as Google Drive and Microsoft SharePoint, with autosyncing and inherited permissions.
2025-09-11 Custom metadata is now available
Developers can add up to 50 custom metadata fields at ingestion using our API.
2025-09-11 Improved agent development experience
Supports 3rd party LLMs, reusable agent templates, ad-hoc document uploads, and saved history of prior conversations.

Capabilities

Developer API — “use the /generate standalone API!” source

Get it

Documentation

Security

SOC 2 Type II — “Our commitment to security excellence is validated through successful completion of SOC 2 Type II audit.” source
SOC 2 — “Our commitment to security excellence is validated through successful completion of SOC 2 Type II audit.” source

Pricing

Prices checked: 2026-10-24

Generate

Input: $3 / 1M tokens
Output: $15 / 1M tokens

The most grounded large language model in the world
Engineered specifically to minimize hallucinations

Official website