FeaturedBlog
Chat Completions and the Messages API look alike but differ in system prompts, max_tokens, tool calls, streaming events and usage fields. When it matters.
Relaykit Team8 min read
Tutorials
Pick an alert level from your real daily spend, choose email or a webhook, and run a small signed receiver in Node or Python that you can test with curl.
8 min read
Product Updates
Step-by-step setups for eight coding agents at /agents, and three free browser tools at /tools: a cost calculator, a config generator and a token estimator.
5 min read
Tutorials
Call Claude through a gateway with the Anthropic SDKs: base URL, headers, streaming, a tool-use loop and prompt caching, in Python, Node and curl.
7 min read
Guides
LLM API keys spend real money. How to keep them out of browsers and git, scope one key per app, rotate without downtime, rate-limit users and respond to a leak.
8 min read
AI News
Anthropic shipped Opus 5.5, Sonnet 5.5 and Haiku 5.5 between September 22 and October 7. Prices, limits and the breaking changes that affect your code.
6 min read
Guides
Plain-language definitions of the LLM API terms on pricing pages and in SDK docs, with a worked cost example and the mistake each term commonly causes.
7 min read
Newest first. Every post is dated; edits are marked as updates.
Product Updates
The console at /console now covers API keys with spend limits and expiry dates, a per-request usage log and your prepaid balance.
4 min read
Tutorials
One key per project and environment, each with a spend limit sized from real traffic, an expiry when it should end and an alert when it is blocked.
7 min read
Tutorials
Relay a streaming LLM response from your server to the browser over SSE, keep the API key server-side, stop billing when the tab closes. Node and Python code.
8 min read
Tutorials
Point a working OpenAI SDK app at another compatible endpoint with env vars or one line of code. Python, Node, curl, LangChain and the AI SDK, plus pitfalls.
6 min read
AI News
What OpenAI shipped to developers in September and early October 2026: four GPT-6 models, DevDay speed tiers, a Decisions API and simpler usage tiers.
5 min read3 sources
AI News
xAI shipped grok-4.7 in September 2026: 500k context, four reasoning levels, Grok 4.6 pricing and a 200k long-context price step. What to check.
5 min read3 sources