Changelog
Fairness fix: balance and usage now count correctly (and what we reset)
A billing bug let heavy users drain free-tier volume without paying. Fixed, with a 1,000-request / 5M-token daily cap and affected accounts reset.
5 min read
One AI API Key Team
27 articles · latest Nov 13, 2026
Every article written by the One AI API Key Team: guides, tutorials and sourced AI news on running models through one API.
Changelog
Qwen3.8 27B now on a faster free lane
The same Qwen3.8 27B weights are now served from Groq under a new id, qwen3.8-27b-1:free, with 1,000 requests a day. The original qwen3.8-27b:free stays.
2 min read
Changelog
New free model: StepAudio 3 Chat Preview
StepFun audio-chat preview joins the model catalog at $0. A reasoning chat model on the OpenAI endpoint, added to the free lane.
2 min read
Blog
Qwen4 Max Preview:free — API Pricing, Providers & Specs
Qwen4 Max Preview from $3/month on Alibaba’s Token Plan: verified specs, a factual comparison vs Gemini 4 Carbon, Argon and Claude, free routes and code.
21 min read
Blog
Use Qwen4 Max Preview in Claude Code, Cursor, Codex and Cline
Qwen4 Max Preview speaks OpenAI and Anthropic protocols, so Claude Code, Cursor, Codex, Cline and Qwen Code can all point at it. Base URL, key and model id.
7 min read
Blog
Qwen4 Max Preview Context Window: the 1M-Token Window and 390K Output, and How to Use It
Alibaba docs list a 1M token context with about 390K output on Qwen4 Max Preview. What that means for long docs, codebases and agents, plus chunking patterns.
8 min read
Blog
The Qwen4 Family: Max, Plus, Flash and the 27B You Can Run Yourself
Qwen4 Max Preview is the only size shipped, but the slide showed four: Max, Plus, Flash and a 27B you can run yourself. Cloud vs local, and which to pick.
8 min read
Blog
Qwen4 Max Preview Has No Benchmarks Yet — Here Is What Is Real and What Is a Leak
Qwen4 Max Preview shipped with zero official scores. We traced the viral numbers to their sources; most are not what they claim.
8 min read
Blog
Is Qoduck Qwen4 Max? The Stealth Model Clues, the Koduck Claim and What Alibaba Has Actually Confirmed
Qoder ran a free stealth model called Qoduck during Qwen4 launch week, and a Chinese site claims Koduck was an early checkpoint. Every clue, confirmed and not.
8 min read
Blog
Qwen4 Max Preview Speed Test: the 20-Minute Pelican and What Early Numbers Really Say
Qwen4 Max Preview is hours old, so early speed reports are thin: a 20-minute pelican at roughly 20 tokens a second. What the numbers do and do not tell you.
9 min read
Tutorials
Get Warned Before Your LLM Balance Runs Out: Alert Levels, Email and Signed Webhooks
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
Changelog
Agent Kits and Free Tools Are Live
Step-by-step setups for eight coding agents in the docs, and free browser tools at /tools: a cost calculator and a config generator.
5 min read
Tutorials
Use the Anthropic Messages Format Through a Compatible Gateway
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
API Key Security for AI Apps: Rotation, Scoping, Rate Limits and Keeping Keys Server-Side
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 handle a leak.
8 min read
AI News
Claude 5.5 Is Complete: Opus 5.5, Sonnet 5.5 and Haiku 5.5 in Two Weeks
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
Glossary: Tokens, Context Windows, Cached Input, Streaming and Base URLs
Plain-language definitions of the LLM API terms you meet on pricing pages and in SDK docs, with a worked cost example and the mistakes each term tends to cause.
8 min read
Changelog
New Customer Console: Keys, Usage and Billing in One Place
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
Give Every Project Its Own API Key and Spend Limit
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
Stream Tokens to a Browser with Server-Sent Events (Node and Python)
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
Switch an Existing OpenAI SDK App to a Different Base URL
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
OpenAI's GPT-6 Family Reaches the API: Astra, Sol, Luna and GPT-6.1 Sol
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 read
AI News
Grok 4.7 Reaches the xAI API: Same Price as 4.6, New Base Model
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 developers should check.
5 min read
Guides
Choosing a Model for Coding Agents: Flagship vs Balanced vs Fast
A practical way to pick models for Claude Code, Codex CLI, Cline and other coding agents: what each tier is good at, cost per agent turn, and mixing tiers.
6 min read
Guides
Streaming vs Non-Streaming LLM Responses: Timeouts, UX and SSE in Python and Node
Why long non-streaming LLM requests time out, how streaming improves perceived speed, and working SSE code for Python and Node in both API formats.
8 min read
Tutorials
How to Estimate Your Monthly LLM API Cost (With Worked Examples)
A practical method to forecast LLM API spend: counting tokens, the hidden tokens people miss, how prompt caching changes the maths, and three worked examples.
7 min read
Guides
OpenAI-Compatible vs Anthropic-Compatible APIs: What Differs and When It Matters
Chat Completions and the Messages API look alike but differ in system prompts, max_tokens, tool calls, streaming events and usage fields. How to choose.
8 min read
Guides
What Changes When Claude Code Uses a Custom API Base URL
How ANTHROPIC_BASE_URL and the credential variables work, what you gain and lose behind a gateway, where the money goes, and how to tell which layer failed.
6 min read