Gemini Pro API Guide: Key, Endpoint, Model IDs, and OpenAI Compatibility
Set up the Gemini Pro API with a Google AI Studio key, current model ID, native REST endpoint, OpenAI-compatible client, and agent backend pattern.
Filter posts by category
Kimi K3 on Novita AI: Pricing, 1M Context, and When to Choose It Over K2
Kimi K3 is live on Novita AI with a 1M-token context window, multimodal input, and $3/$15 per-million-token pricing. See when K3 beats K2.
Kimi K3 Quick Start for Long-Context API Workflows
Connect to Kimi K3 with Novita AI's OpenAI-compatible API. Follow the model ID, endpoint, Python, cURL, pricing, and troubleshooting steps.
Claude Code Plugins: How MCP Tools Extend Claude Code with External Capabilities
Understand Claude Code plugins — what they are, how MCP servers work as plugins, how to install them, and how to run tool execution through Novita AI.
Claude Code Rules: How to Write CLAUDE.md and Manage Agentic Coding Context
Learn how Claude Code rules work — CLAUDE.md files, .claude/rules/ path scoping, settings.json permissions, and auto memory — with best practices for agentic coding.
Claude Opus 3 vs Opus 4 for Academic Writing: Which Model Should You Use?
Claude Opus 3 vs Opus 4 for academic writing: compare context windows, reasoning depth, pricing, and real workflow impact. Includes Opus 4 vs Sonnet 4 guidance.
OpenAI Python SDK: Installation, Setup, and Practical Integration
Install and use the OpenAI Python SDK for chat completions, streaming, function calling, and async requests. Includes JavaScript SDK and Novita AI integration.
Claude Code vs VS Code: What's the Difference and Do You Need Both?
Claude Code is an AI coding agent; VS Code is a code editor. They're not competitors — Claude Code runs inside VS Code as an extension. Here's exactly how they relate.
Claude Code Router: Use Any Model Backend with MCP Tools and Sandbox Execution
Set up a Claude Code router to use any Anthropic-compatible endpoint — ANTHROPIC_BASE_URL, MCP tool routing, and Novita Agent Sandbox execution.
Claude Code Price: Plans, Token Costs, and How to Spend Less
Claude Code pricing: Pro at $20/month, Max 5x at $100, Max 20x at $200. API billing runs $1–$10/MTok. Real monthly estimates and five ways to reduce your bill.
What Are Coding Agents? How They Work and How to Build One
Coding agents combine an LLM planner, tool execution, and a sandboxed runtime to autonomously write, run, and fix code. Learn how the full loop works and how to build one.
How to Build AI Agents: Planning, Tool Use, and Execution
Build AI agents from scratch: planning loop, tool calling, sandboxed code execution, and evaluation. Runnable Python examples using the Novita LLM API.
How to Use Claude Code in VS Code: LLM Backend, Model Selection, and Agent Sandbox
Install the Claude Code VS Code extension, configure its LLM API backend to use Novita AI, pick open-source models for coding tasks, and run heavy jobs in Agent Sandbox.
Claude Code Default Model: How to Change, Switch, and Choose the Right One
Claude Code's default model is Sonnet. Learn how to change it with /model, --model, or env vars, and when to use Opus, Haiku, or open-weight alternatives.