Posts tagged "API Gateway"
17 posts
Leaked API Key or Runaway Agent: What Actually Caps the Bill
Leaked API key or runaway agent: what stops the bill. 2026 spend limits at OpenAI, Google, Cloudflare and OpenRouter vs Router One, and a first-hour runbook.
How Companies in China Buy Claude and GPT API for Dev Teams
Five ways companies in China buy Claude and GPT API access for a dev team, compared on payment, invoices, traceability and per-developer spend caps.
Gemini 4 Argon API Guide: Model ID, OpenAI SDK, Plan Quota
Call Gemini 4 Argon on Router One: the google/gemini-4-argon catalog ID, OpenAI-compatible Chat Completions, plan quota, wallet billing and a first request.
Claude Haiku 5.5 API Guide: Model ID, Billing, Claude Code
Claude Haiku 5.5 on Router One: the claude-haiku-5-5 id, 1M context, two rate lines at 100K prompt tokens, wallet billing (no plan tier) and the haiku alias.
GPT-6 Astra API Guide: Model ID, Codex, Plan Quota
GPT-6 Astra on Router One: model ID, tool calls per OpenAI (Responses API only), Codex setup, and the Flagship quota on Max and Ultra (wallet billing on Pro).
GPT-6.1 Sol API Guide: Model ID, Codex, Tool Calls
GPT-6.1 Sol on Router One: model ID, tool calls on the Responses API, plan quota or wallet billing, Codex's new default model and what changes from GPT-6 Sol.
Claude Sonnet 5.5 API Guide: Model ID, Claude Code, Plans
Claude Sonnet 5.5 on Router One: the claude-sonnet-5-5 id, 1M context, wallet billing (no plan tier), Claude Code alias pins and what changes from Sonnet 5.
Claude Opus 5.5 API Guide: Model ID, Endpoints, First Call
Claude Opus 5.5 on Router One: the claude-opus-5-5 id, 1M context, always-on thinking, plan coverage, and first calls on /v1/messages and Chat Completions.
Migrating to Claude Opus 5.5: Breaking Changes and 400 Fixes
Move Opus 5 code to claude-opus-5-5: four breaking changes, the exact 400 errors, before/after JSON, what Router One normalizes, and which SDKs are ready.
GPT-6 Sol API Guide: Endpoints, 272K Price Tier, First Call
GPT-6 Sol on Router One: openai/gpt-6-sol, 1.05M context, the whole-request 272K tier, plan coverage, Chat Completions and Responses calls, Codex CLI setup.
Azure GPT, AWS & Vertex Claude on One Key: Channel Model IDs
What azure/, aws/ and vertex/ model ids change on Router One — isolated routing, own rates and quota, the channel in every trace — and how to call one.
LLM API Balance Monitoring: Alert Before Credit Runs Out
Monitor a prepaid LLM API balance from a server: GET /v1/balance fields, a burn-rate threshold, debounced alerts, and bash and Python monitors for resellers.
Claude Web Search and Code Execution via /v1/messages
Use Claude's web_search and code_execution server tools via Router One's /v1/messages: request shape, response blocks, rejections, billing.
LLM API 429 Errors: The Three Causes and How to Fix Each
HTTP 429 from an LLM API hides three failures: upstream rate limits, gateway key or account limits, and exhausted quota. How to tell them apart and fix each.
LLM Cost Attribution: One Key per App, Agent, Environment
LLM cost attribution on a gateway ledger: one API key per app or agent, weekly per-key review, and spend caps that stop runaway loops.
Reselling LLM API Access Safely with Spend-Capped Keys
Resell LLM API access on a managed upstream: one server-side key per customer, a cap on each key's wallet charges, and per-request usage data for billing.
What is an AI API Gateway and Why You Need One
An AI API gateway sits between your app and LLM providers: one endpoint and key for many models, with routing, fallback, spend caps and per-request cost logs.