Documentation
Build with the ChatInfer API
Explore the developer concepts, API patterns, and integration flow for building AI chat applications with reliable inference.
curl https://api.chatinfer.com/v1/chat/completions \
-H "Authorization: Bearer $CHATINFER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "chatinfer-auto",
"messages": [
{
"role": "user",
"content": "Explain vector search in simple terms."
}
]
}'Quick start
Quick start
A simple four-step flow for integrating ChatInfer into your application.
Integration flow
Join early access
Request access and tell us about your AI application or inference workflow.
Create an API key
Generate a project API key once your account is enabled.
Send a chat completion request
Use a familiar chat completions interface to send messages through ChatInfer.
Monitor and iterate
Track latency, cost, errors, usage, and user conversations as your application scales.
Example
Chat completions example
ChatInfer is designed around a familiar request pattern for developer-friendly integration.
Request
{
"model": "chatinfer-auto",
"messages": [
{
"role": "user",
"content": "Explain vector search in simple terms."
}
]
}Response
{
"id": "chatcmpl_demo",
"object": "chat.completion",
"model": "chatinfer-auto",
"choices": [
{
"message": {
"role": "assistant",
"content": "Vector search finds information by comparing meaning, not just keywords."
}
}
]
}Documentation
Explore the docs
The full documentation set is being prepared for early access users.
Getting Started
PreviewLearn the basics of integrating ChatInfer into your application.
Authentication
PreviewHow to authenticate your API requests securely.
Chat Completions
PreviewSend and receive chat completion requests.
Knowledge Base
Coming soonConnect your knowledge sources for grounded AI answers.
Model Routing
Coming soonRoute requests across models based on cost and latency.
Webhooks
Coming soonReceive real-time events from the ChatInfer platform.
SDKs
Coming soonOfficial client libraries for popular programming languages.
Rate Limits
Coming soonUnderstanding API rate limits and best practices.
Documentation is in early access
The ChatInfer API is currently available to selected early access users. Early access users will receive integration guidance, API examples, and onboarding support as features become available.
Need access to the API?
Join the waitlist and tell us what you're building. We'll prioritize early users based on use case, scale, and integration needs.