API essentials
Developer documentation
Learn the API one step at a time: client setup, model features, production guides, and worked projects.
Start with one request
Create a key, choose a client, then add the features your project needs. Each guide covers one task, its request format, and what to do with the result. The endpoint reference remains available when you need exact route details.
API essentials
Start with a key, choose a client, and make your first API call.
API quickstart
Create a scoped key, send your first request, and read the response.
HTTP, cURL and PowerShell
Make requests without an SDK and inspect response bodies and status codes.
OpenAI Python SDK
Install the Python client, call Chat Completions and Responses, and pass Kendr-specific options.
OpenAI JavaScript SDK
Call Kendr from Node.js or TypeScript with Responses, custom fields, and explicit error handling.
Other clients and migration
Configure Anthropic clients, agent harnesses, Vercel AI SDK, and source-included helpers.
Authentication and SDKs
API keys, sessions, OAuth, and the JavaScript and Python client kits.
Model features
Add routing, streaming, structured output, tools, and images.
Models and routing
Discover aliases and capabilities, choose a route, and inspect optimization receipts.
Realtime Voice API
Connect a scoped API key, stream speech in both directions, receive transcripts, and renew bounded sessions.
Streaming responses
Display partial text, distinguish stream formats, and recover interrupted requests.
Structured JSON output
Constrain output to a schema and validate it before using it in application logic.
Tools and connected apps
Choose web search, connected apps, or custom MCP and understand who executes tools.
Web search and grounding
Request current information and require grounded answers when sources are essential.
Attach MCP servers
Register a trusted server, restrict its tools, and attach it to a model request.
Image generation and editing
Generate images, send reference pictures, track progress, and retrieve private output.
Knowledge and production
Integrate knowledge, recover failures, and look up endpoint contracts.
Query API
Call Kendr surfaces with cURL, JavaScript, Python, C#, Java, and Go.
Cloud knowledge bases
Hosted KB creation, staged indexing, sharing, retrieval testing, artifacts, and evaluations.
Hosted vector DB
Managed vector storage: dimensions, retrieval scores, sharing, billing, and rebuild boundaries.
Errors, retries and usage
Handle failures, recover interrupted requests, and reconcile usage and credits.
API reference
Endpoints, authentication modes, request fields, response contracts, and error behavior.
Case-study projects
Build and evaluate three practical integrations from complete Python examples.
Case-study projects
Three worked Python projects with setup, source files, expected behavior, and evaluation steps.
Project: documentation assistant
Answer support questions using a registered read-only MCP documentation server.
Project: support-ticket triage
Classify tickets with structured JSON and validate fields before routing them.
Project: product image studio
Generate and edit product artwork, retrieve its private bytes, and retain usage receipts.