ChatGPT & OpenAI
Codex Headless Login: Device Code, SSH Tunnel, or auth.json
On a server with no browser, run codex login --device-auth and enter the code on any device. If that is blocked, tunnel port 1455 over SSH or copy auth.json.
17 min
AI Model & API Guides · Page 16 of 26
Source-linked guidance for AI models, API integration, and developer workflows—turning fast-changing prices, quotas, capabilities, and limits into decisions you can verify.
AI Image Generation
Gemini Image to 3D Model: No GLB Export, 3 Tested Routes
Gemini makes the image, not the mesh. Asked for a GLB or STL on October 2, 2026, it declined. A converter, a code-written STL and a 3D viewer each got partway.
15 min
AI Image Generation
Gemini Image vs Canvas: Same Prompt Tested, Which to Use
Gemini's image tool returns a picture with the text baked in; Canvas returns a page with live text. Choose by what you hand over and what you'll edit later.
12 min
AI Image Generation
GPT Image Transparent Background: Fix a Baked-In Checkerboard
If the gray-and-white squares stay when the image sits on a colored background, they are painted pixels. Check the saved file, then fix it where it was made.
14 min
AI Image Generation
Seedream 5.0 Pro Layer Decomposition API Tutorial: PNGs to PSD
One POST with layer_decomposition: true returns a base image plus up to 16 PNG layers. Each image is billed, and the restack is not a pixel copy.
15 min
AI Video Generation
Veo Video Download 403: The URI Needs Your API Key
The video.uri that Veo returns through the Gemini API is not a public link. Request it with the same API key that generated the video, within 2 days.
11 min
API Pricing & Plans
ChatGPT Pro 500: $500 Plan Limits and Ultrafast's 8x Usage Cost
ChatGPT Pro 500 costs $500 a month and adds Astra Ultrafast in Work and Codex. Ultrafast draws usage at 8x, so it pays off only when speed is the bottleneck.
13 min
Troubleshooting
Codex 401 Incorrect API Key: Outage, Stale Token, or Your Key?
Signed in with ChatGPT and never set a key? That 401 came from OpenAI's September 25, 2026 outage. The URL and key text in the error tell you if yours differs.
10 min
Claude Code
Connect Claude Code to a Note Taker: MCP Commands by Tool
Granola, Circleback, Fathom and Notion publish a claude mcp add command. Other note takers need a claude.ai connector, the generic HTTP form, or plain files.
14 min
AI Video Generation
Seedance 2.5 vs Veo 3.1 vs Gemini Omni: Which Fits Your Job
Seedance 2.5 fits 30-second takes and reference-heavy shots, Veo 3.1 fits native 4k and 720p extension, and Omni Flash is Google's default. Sora 2 is retired.
13 min
AI Video Generation
Sora 2 API Shut Down: What Still Works and What to Switch To
The Sora 2 API no longer works. OpenAI shut it down on September 24, 2026, with no replacement; only Azure Foundry's preview remains, until October 15.
11 min
ChatGPT & OpenAI
How Many Files Can You Upload to ChatGPT? Free, Go, Plus, Pro
ChatGPT Free allows 3 file uploads a day; paid plans get up to 80 files every 3 hours. Projects, custom GPTs, file size and storage each have their own cap.
12 min
AI Image Generation
Does ChatGPT Save Your Photos? Where Uploads Go and How to Delete
Yes. ChatGPT keeps an uploaded photo in the chat, and often in Library, until you delete it. Training depends on one setting; deletion finishes within 30 days.
10 min
Developer Tools & Agents
Codex Computer Use: Setup on Mac and Windows, and When to Use It
Computer Use now runs in the ChatGPT desktop app on macOS and Windows, in Work or Codex. Install the plugin, grant OS access, then mention @Computer or an app.
13 min
API Guides
Gemini 3.8 Flash TTS API: Model Choice, Cost, and Migration
Both Gemini 3.8 TTS models are GA with a free tier. Flash-Lite replaces 3.1 preview at about $0.54 per audio hour; Flash is $0.81 for studio-grade acting.
16 min
Troubleshooting
Grok Authentication Failure: What Each Login Error Means
"Authentication failure: user is blocked" most likely means an account block only xAI can lift. Most other Grok sign-in errors you can fix yourself.
14 min
Developer Tools & Agents
Codex Mobile App: Control a Mac or Windows PC From Your Phone
There is no separate Codex app. Open Codex in the ChatGPT app on iPhone or Android, then pair it by QR code with a Mac or Windows PC running ChatGPT.
12 min
Claude Code
Claude Code API Overloaded (529): Switch Models or Add a Fallback
Claude Code shows a 529 overload only after retrying up to 10 times, and it never counts against your quota. Switch models with /model or set a fallback chain.
10 min
API Guides
Free Gemini API Key for Students: What Is Free and What Isn't
No student-only Gemini API key exists; students get the same free tier as everyone. The Google AI Pro student year helps API work only after you enable billing.
15 min
API Guides
OpenRouter Alternatives: Free Models, Fees, and When to Switch
OpenRouter's free models cap at 50 requests a day until a one-time $10 top-up; Vercel, Requesty, Cloudflare, LiteLLM, or direct free tiers each fix one problem.
16 min
Developer Tools & Agents
Google AI Studio Free Access: What's Still Free and What Isn't
AI Studio is still free for adults in supported countries, but since April 20, 2026, Gemini Pro and Nano Banana need Google AI Pro/Ultra or a paid API key.
12 min
API Pricing & Plans
DeepSeek API Peak Hours: Current Prices and When to Wait
DeepSeek doubles API rates from 01:00–04:00 and 06:00–10:00 UTC on weekdays. Flash was cut on September 10, 2026, so waiting saves less per batch.
8 min
API Guides
OpenAI Base URL Override: Which Setting Wins and What to Paste
In the official Python and Node SDKs, base_url beats OPENAI_BASE_URL and endpoint paths are appended to it, so paste the base ending in /v1, not an endpoint.
10 min
Troubleshooting
AWS Bedrock Claude 400 Error: Match the Exact Message to the Fix
A Claude 400 on Amazon Bedrock can be a stripped beta header, old Claude Code, full context, a bad model ID or an account setting. Fix it by the exact message.
15 min