Nbility Blog - Nbility AI Gateway

Nbility Blog

Articles about AI Agents, model APIs, developer-tool integration, and Nbility workflows.

All posts

#Nbility

Jul 21, 2026429Retry

How One 429 Took Down an Agent Chain: Retry, Backoff, and Failover Postmortem

Replay a synthetic 429 retry storm with immediate retries, synchronized exponential backoff, and jitter plus a total budget, then build a safe gateway and agent state machine.

Jul 20, 2026Multi-Model RoutingLLM Router

Multi-Model Routing Is Not Random Switching: Balancing Quality, Cost, and Latency

Use three tasks and a runnable offline replay to design constraint-first LLM routing across quality thresholds, cost, TTFT, health, cache affinity, and fallback.

Jul 19, 2026LLM GatewayAPI Gateway

LLM Gateway vs API Gateway: Follow One Model Request End to End

Trace authentication, model mapping, protocol translation, SSE streaming, retries, token billing, and observability to see what an LLM gateway adds beyond a conventional API gateway.

Jul 19, 2026Prompt CachingOpenAI

Does Prompt Caching Save Money? Replaying Three Bills with the Same 12K Context

Replay OpenAI, Claude, and Gemini cache bills with a 12,000-token prefix and ten requests. Calculate writes, reads, TTL costs, misses, and break-even points from official pricing.

Jul 19, 2026Agent SkillsSKILL.md

Why Agent Skills Took Off: CLAUDE.md vs AGENTS.md vs SKILL.md

Agent Skills are more than prompts saved to files. Learn how CLAUDE.md, AGENTS.md, and SKILL.md differ, then inspect a two-call experiment measuring instruction compliance and token cost.

Jul 19, 2026MCPA2A

MCP vs A2A: One Connects Tools, the Other Connects Agents

MCP and A2A are both agent protocols, but they solve different problems. Compare tool invocation with agent delegation using the same refund workflow, Agent Cards, Tasks, Artifacts, transports, and security boundaries.

Jul 19, 2026MCPModel Context Protocol

What Is MCP? Host, Client, and Server Explained with a Real Tool Call

MCP is not a model API or merely a plugin system. Follow a real order lookup to understand MCP hosts, clients, servers, JSON-RPC, stdio, and Streamable HTTP.

Jul 18, 2026Structured OutputJSON Schema

Structured Outputs and JSON Schema: Reliable JSON from AI Models

Stop malformed or inconsistent AI JSON. Learn the difference between JSON mode and schema-constrained output, with OpenAI, Claude, and Gemini examples plus validation and retry patterns.

Jul 17, 2026ContinueVS Code

Connect Continue to an OpenAI-Compatible API in VS Code

Configure Continue 2.0 in VS Code with config.yaml, an OpenAI-compatible apiBase, API key, model roles, and fixes for Chat, Edit, Autocomplete, and Responses API issues.

Jul 17, 2026ClineOpenAI-Compatible API

Connect Cline to a Custom API: Models, Permissions, and Cost Control

Configure an OpenAI-compatible Base URL, API key, model, and capabilities in Cline, then control risk and spend with Auto Approve, Checkpoints, .clineignore, and model routing.

Jul 17, 2026Claude CodeCodex

Claude Code vs Codex vs Cursor vs OpenCode: Which Coding Agent Fits You?

Compare Claude Code, Codex, Cursor, and OpenCode across interfaces, models, custom APIs, automation, permissions, cost, and real developer workflows.

Jul 17, 2026Qwen CodeOpenAI-Compatible API

Connect Qwen Code to an OpenAI-Compatible API: Install to First Request

Install Qwen Code, configure an OpenAI-compatible Base URL, API key, and model in settings.json or environment variables, then validate and troubleshoot your first agent task.

Jul 16, 2026Codex CLIOpenAI-Compatible API

Connect Codex CLI to an OpenAI-Compatible API: Installation, Configuration, and Model Selection

Install Codex CLI, configure config.toml and auth.json for an OpenAI-compatible endpoint, choose a model, verify the connection, and fix common API errors.

Jul 16, 2026Claude CodeNbility

Connect Claude Code to a Third-Party API: Base URL, API Key, and Common Errors

Configure Claude Code with Nbility using ANTHROPIC_BASE_URL, ANTHROPIC_AUTH_TOKEN, settings.json, model selection, and practical fixes for 401, 404, 429, and timeout errors.

Jun 8, 2026Node.jsJavaScript

Calling Nbility from Node.js: From a CLI Tool to a Web App

A practical Node.js / JavaScript guide to using Nbility as an OpenAI-compatible API: environment variables, the openai npm SDK, CLI tools, Express endpoints, streaming output, error handling, logging, and launch checks.

Jun 8, 2026PythonNbility

Calling Nbility from Python: Chat, Streaming, and Error Handling

A practical Python developer guide for using Nbility as an OpenAI-compatible API: environment variables, openai-python setup, Chat Completions, streaming output, timeouts, retries, error classification, logging, and cost control.

Jun 7, 2026Image GenerationPrompting

Image Generation Failed? Safety Policies, Prompts, and Retries

A practical troubleshooting workflow for AI image generation failures: safety policy, prompt design, API parameters, async jobs, retries, cost control, and human review.

May 27, 2026XiaohongshuX

A Workflow for Generating Xiaohongshu and X Post Images

Turn a title, summary, and platform requirements into reusable Xiaohongshu covers, carousel cards, and X/Twitter post images with AI generation, safe zones, cropping, and human review.

May 27, 2026WeChat Official AccountCover Image

Automatically Generate Cover Images for WeChat Official Account Articles

A practical workflow for turning article titles and summaries into WeChat Official Account cover images: 900×383 headline covers, 383×383 sharing cards, and 1283×383 combined assets.

May 27, 2026GPT ImageImage Generation

GPT-image / Multimodal Image API Beginner Guide

A practical beginner guide to text-to-image generation, reference-image editing, Base URLs, b64_json outputs, cost control, and troubleshooting with an OpenAI-compatible image API.