RAG as a Service With Cited Answers and One API Call
CustomModel is RAG as a service: you add your content, we handle indexing and retrieval, and one API call returns the answer with its citations. A website widget comes with the same model.
Skip the pipeline work
Chunking, indexing, retrieval, and answer writing are handled for you. You manage content and call one endpoint.
- Content split into passages
- Passages found per question
- Answer written from those passages
curl \
https://custommodel.ai/api/v1/answer \
-H "Authorization: Bearer $CUSTOMMODEL_KEY" \
-d '{"model": "support", "question": "What time is late checkout?"}'200 OK
A response you can use in code
The response contains the answer, a list of citations with the exact passage, and a grounded flag that tells your app when to hand off.
- answer
- citations
- grounded
API from Growth
Growth includes API access, 5 models, and 8,000 answers a month. Enterprise gives 25 models and 25,000 answers.
-
Growth at $99 a month billed yearly
-
Enterprise at $299 a month billed yearly
-
Monthly billing available
What it costs
Plans start at $24 a month billed yearly ($49 monthly) with 1,000 answers, and Growth at $99 a month billed yearly ($199 monthly) adds the API and five seats. See chatbot pricing for every limit.
Starter: Starter is $24 a month billed yearly ($49 monthly).
Growth: Growth is $99 a month billed yearly ($199 monthly).
Enterprise: Enterprise is $299 a month billed yearly ($599 monthly).
Related pages
Keep exploring: custom LLM, chatbot features, chatbot security.
FAQ
What does the API return?
JSON with the answer, the citations, and a grounded flag.
Which plans include it?
Growth and Enterprise.
Can I store my content privately?
Each account has its own separate index.