Built for real engineering decisions

AI Model & API Guides

Source-linked guidance for AI models, API integration, and developer workflows—turning fast-changing prices, quotas, capabilities, and limits into decisions you can verify.

Primary sources first
Reproducible steps and failure boundaries
Volatile facts carry review dates

621 articles
6 languages
12 topics
Updated Nov 15, 2026

Codex token-exchange 403: read the full error, preserve response details, distinguish an unexplained refusal from a country, account or workspace restriction, and check the actual Codex host

LatestDeveloper Tools & Agents

Codex Token Exchange Failed 403 and Error Sending Request Fixes

token_exchange_failed alone doesn’t say who is at fault. A 403 in the details is a server refusal; error sending request means Codex got no reply.

Nov 15, 202622 min

ChatGPT image not working: wait for a status incident, stop retrying on limits or refusals, fix your side when image generation failed

AI Image Generation

ChatGPT Image Generation Not Working? Match the Error to the Fix

"Image creation is temporarily unavailable" is a chat reply: check status.openai.com, then the line under the message box for a limit and its reset time.

Nov 14, 202616 min

ChatGPT Plus and Go image limits as of October 1, 2026: OpenAI publishes no count, next to unconfirmed reports of about 120 a day on Plus and 20–30 a day on Go

AI Image Generation

ChatGPT Go and Plus Image Generation Limits: How Many per Day?

OpenAI publishes no image count for ChatGPT Go, only more than Free. Plus users reported about 120 a day before Images 2.6; none of it is official.

Nov 14, 202623 min

Decision map for checking the billing provider, payment stage, eligibility, charge status, and one safe next action

ChatGPT & OpenAI

ChatGPT Payment Declined: Payment Was Not Approved, Card Declined

“Payment was not approved.” is ChatGPT checkout's banner for a blocked payment; card refusals show “Your card has been declined.” Check your bank first.

Nov 14, 202625 min

ChatGPT Plus Codex weekly limits board showing five-hour windows, weekly allowances, credits, and separate API-key billing

Developer Tools & Agents

ChatGPT Plus Codex Usage Limits and Credits: Is Codex Included?

Yes, Codex is included in ChatGPT Plus. OpenAI estimates 15–150 GPT-6 Sol messages per five hours, weekly limits may apply, and credits extend usage.

Nov 14, 202619 min

ChatGPT Plus image upload limit board showing 20 MB per image, a rolling file cap, and six counters to diagnose

Troubleshooting

ChatGPT Image Upload Limit, Free/Go/Plus: How Many Photos, Files?

ChatGPT Free allows 3 uploads a day; a photo, PDF or document is one each. Go has no upload count but has 25-file Projects and 4 GB. Cap: 80 files per 3 hours.

Nov 14, 202634 min

Guide to reading a ChatGPT Plus message-limit notice, reset, and safe recovery

ChatGPT & OpenAI

ChatGPT Plus Message Limit and Credits: What Is Still Capped

As of October 8, 2026, ChatGPT Plus text chat is unlimited under abuse guardrails. Thinking, uploads, images and Codex are capped; credits cover Codex and Work.

Nov 14, 202610 min

ChatGPT usage limits by plan as of October 8, 2026: everyday text chat unlimited on every plan, Thinking and Pro model counts not published, and file uploads at 80 every 3 hours or 3 a day on Free

ChatGPT & OpenAI

ChatGPT Usage Limits by Plan: Free, Go, Plus, Pro and Resets

As of October 8, 2026, everyday ChatGPT text chat is unlimited on every plan. Thinking, tools, Work and Codex have separate caps; few have published numbers.

Nov 14, 202615 min

Claude cloud session credit ($100 on Pro, $250 on Max, cloud sessions only), usage credits billed at API rates, and a free limit reset that refills one limit

Claude Code

Claude Cloud Session Credits: Expired Nov 4, vs Usage Credits

Claude cloud session credit claims closed October 7, 2026; all balances expired November 4. Cloud sessions now use plan limits; usage credits bill at API rates.

Nov 14, 202625 min

Claude Code

Claude Code API Billing vs Subscription: Key, Credits, or Pro/Max

Once you approve ANTHROPIC_API_KEY, Claude Code bills that key instead of your Pro or Max plan, and claude -p always uses it. /status shows which one pays.

Nov 14, 202621 min

Claude Code

Claude Fable 5.2 Error or Not Working: Fix by the Exact Message

Fable 5.2 errors trace to Claude Code older than 2.1.321, the dotted ID claude-fable-5.2, a /model picker bug, Fable limits, safeguards or API 400s.

Nov 14, 202620 min

Claude Sonnet 5.5 vs Gemini 3.8 Flash: Flash is 2.67x cheaper per token but cost 2.42x as much over 11 identical test calls

Model Comparisons

Claude Sonnet 5.5 vs Gemini 3.8 Flash, 4 Hydrogen: Cost per Task

Gemini 4 Hydrogen lists 25% below Claude Sonnet 5.5 per token, yet on the same 11 calls at high it cost 1.96x as much. 3.8 Flash cost 2.42x.

Nov 14, 202623 min

Claude verification guide showing phone, ID, payment, and enforcement as separate branches

Claude & Anthropic

Claude KYC Verification: ID, Verification Portal, Phone, Age

Claude KYC is a phone code for every new account and, for some, a Persona ID-and-selfie check. Do it only from the prompt in Claude or at portal.anthropic.com.

Nov 14, 202628 min

Codex could not start in VS Code, with a fix per window type: VS Code 1.141.2 for Remote-WSL on 1.141.1, proxy off for proxy or VPN setups, and the Codex CLI for Dev Containers and SSH

Developer Tools & Agents

Codex Could Not Start Its User Interface in VS Code: Fixes

“Codex could not start — The extension could not start its user interface” on build 26.1021.22027: fixed in 26.1106.51428 (Nov 11, 2026). Update and reload.

Nov 14, 202624 min

Codex request passing through authentication, limit, provider, and response-stream checkpoints

ChatGPT & OpenAI

Codex Exceeded Retry Limit, Last Status: 429 Too Many Requests

“exceeded retry limit, last status: 429 Too Many Requests” is a 429 Codex couldn't classify, not your usage limit. First stop parallel chats and sub-agents.

Nov 14, 202618 min

DeepSeek Search API pricing: $0.00075 per successful request, about $0.002 per Claude Code search on deepseek-flash, and agent search billing from October 31, 16:00 UTC

API Pricing & Plans

DeepSeek Search API Pricing: $0.75/1K and Web Search Tool Cost

DeepSeek search costs $0.75 per 1,000: the Search API bills each request with results, the deepseek_web_search tool each query. Agents pay since Oct 31.

Nov 14, 202626 min

Gemini free image limits as of September 26, 2026: the Gemini app has no image count and refreshes every 5 hours, AI Mode allows 25 images per 24 hours, and Google Flow shows 50 daily credits

AI Image Generation

Gemini Free Image Limit: How Many Images You Can Make and Upload

As of November 14, 2026, Google Flow allows 400 free images a day and AI Mode 25; the Gemini app publishes no number. Uploads stop at 10 files a prompt.

Nov 14, 202622 min

Illustration of a Gemini people-image request with policy, account-access and usage-limit checks

Gemini & Google AI

Why Can't Gemini Generate Images of People? Public Figure Error

Gemini says "I can't depict some public figures" when it reads a request as a real, identifiable person. Invented people and your own photos still work.

Nov 14, 202619 min

Three-stage Gemini image quality check connecting the prompt brief, API resolution request, and saved pixel dimensions

AI Image Generation

Gemini High-Resolution Images: Prompts, 4K Settings, and Pixel Checks

Writing HD or 4K in a Gemini prompt does not set the output pixels. Use a specific creative brief for visual quality, set image_size and aspect_ratio on a supported API model for delivery size, then inspect the saved file before changing prompts, plans, or providers.

Nov 14, 20267 min

Grok auth failure guide: user is blocked likely means an account block for xAI support, a sign-in mismatch needs the same login, and session errors need a clean browser

Troubleshooting

Grok Authentication Failure: User Is Blocked, Sign-In Unavailable

"User is blocked" on Grok means an account block. Appeal by emailing support@x.ai, as the Terms of October 27, 2026 allow. Linking errors are fixable too.

Nov 14, 202624 min

Delete ChatGPT Images cover: delete in Library on the web, delete the chat in the phone apps, and permanent removal follows within 30 days

ChatGPT & OpenAI

How to Delete ChatGPT Images: Fix Some Files Couldn't Be Deleted

On the web, delete a ChatGPT image from Library; on a phone, delete its chat. If it says "Some files couldn't be deleted", retry on chatgpt.com.

Nov 14, 202616 min

Gemini 4 Hydrogen API pricing: $1.50 input and $7.50 output including thinking per 1M tokens, one call from $0.0016 at low to $0.0495 at xhigh

API Guides

Gemini 4 Hydrogen Pricing: API Cost per Call by Thinking Level

Gemini 4 Hydrogen API: $1.50 input and $7.50 output per 1M tokens, thinking billed as output. Test calls cost $0.0016 at low to $0.0495 at xhigh.

Nov 13, 202613 min

Several Gemini API keys share one project's RPM, TPM, and RPD limits.

API Guides

Gemini API Free Tier 2026: Limits, Free Models, and Free API Keys

Gemini API keys are free, but free inference requires an eligible project, model and feature. Check live limits, grounding exceptions, 403s and data-use rules.

Nov 13, 202621 min

Gemini API access map connecting an official project key to billing, usage, and a separate provider contract

API Guides

Gemini API Pricing 2026: Token Rates, Free Tier, and Key Cost

A Gemini API key is free, but usage is free only within per-project limits. Gemini 3.8 Flash costs $0.75/$3.75 per 1M tokens; Gemini 4 Argon is paid-only at $2/$10 until Dec 1.

Nov 13, 202619 min