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

604 articles
6 languages
12 topics
Updated Nov 10, 2026

Conceptual Claude API key ownership guide: create and revoke your own key, track billing, and match the endpoint; Max, Ultra, and Team offer claimed monthly API credits, while Pro includes none.

LatestAPI Guides

Claude API Key: How to Get One, Is It Free, and Safe Buying

Creating a Claude API key is free; calls spend prepaid credits. New users get a small test credit, Max, Ultra, and Team add monthly API credits, and Pro adds none.

Nov 10, 202616 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 Credit vs Usage Credits vs Limit Reset

Cloud session credit claims closed October 7, 2026; claimed balances still pay for cloud runs. Usage credits bill API rates; Max/Ultra/Team API credits fund the API.

Nov 10, 202617 min

Claude Code

Claude Code Discounts in 2026: What's Live and the Cheapest Route

As of October 10, 2026, no Claude Code coupon exists. Pro annual saves $40, bundles cut overflow credits up to 30%, and guest passes give 7 free days of Pro.

Nov 10, 202616 min

Claude Free and Pro usage compared through five-hour session windows, Pro's weekly limit and a three-task test

Claude & Anthropic

Claude Free vs Pro Usage Limits: Decide With Work, Not Counts

Claude Pro gives more usage per session than Free, but as of October 8, 2026, Anthropic states no multiple. Test three real tasks before paying $20.

Nov 10, 202610 min

Claude extra usage cost decision board comparing capped credits, Max, Claude Code route checks, and spend caps

Claude & Anthropic

Claude Extra Usage Cost: Credit Math and When Max Is Cheaper

Claude extra usage bills at API rates: a 200K-token Claude Code turn costs $0.60 on Sonnet 5.5 and $3 on Fable 5.1. Over $80 a month on Pro, Max 5x usually wins.

Nov 10, 202617 min

Claude Fable 5.1 API rate cards showing input at $10, cache reads at $0.25 and output at $50 per million tokens, with a Batch 50% off stamp

API Pricing & Plans

Claude Fable 5.1 API Pricing: What Changed and What You'll Pay

Claude Fable 5.1 costs $10 per million input and $50 per million output tokens. Only cache reads got cheaper, $1 to $0.25, so savings track your cache use.

Nov 10, 202612 min

Fable 5.1 vs 5.2: 20% lower token price, 32% lower cost per task at medium, 104% higher at max

Claude Code

Fable 5.1 vs 5.2: Cheaper at Medium, Costlier at High and Max

Claude Fable 5.2 outscores 5.1 at every effort level and costs about 32% less per task at medium, but at high and above it uses more tokens and costs more.

Nov 10, 202615 min

Opus 5.5 and Fable 5.1 beside a checklist for choosing a model by accepted work

Claude Code

Claude Fable 5.1 vs Opus 5.5: Which Should You Use?

Opus 5.5 is the sensible starting point for most work. Fable 5.1 earns its premium when it solves problems that Opus still misses at higher effort—not simply because the job is long.

Nov 10, 20268 min

Fable 5.2 vs GPT-6 Astra: $8/$40 list price, 39% less per task at medium vs Astra max, 1.74x cost on small tasks

Model Comparisons

Claude Fable 5.2 vs GPT-6 Astra: When Each Costs Less per Task

Fable 5.2 at medium nearly matches GPT-6 Astra at max for 39% less per task. On small tasks both passed, but Fable at high cost 1.74x what Astra did.

Nov 10, 202618 min

Fable 5.2 at high scores 62 for $9.08 per task against 59 for $10.04 for Opus 5.5 at max, and on SWE-bench Pro Opus at xhigh costs $0.75 per solved task against $1.39

Claude Code

Claude Fable 5.2 vs Opus 5.5: When Fable High Beats Opus Max

Keep Opus 5.5 as the default and switch a task to Fable 5.2 at high effort only when Opus at xhigh or max fails it. On routine coding, Fable costs about double.

Nov 10, 202618 min

A weekly allowance gauge and credit wallet illustrate Fable 5.1 plan limits and paid continuation

Claude & Anthropic

Claude Fable 5.1 Usage Limits: Pro, Max, and Paid Credits

Claude Max includes Fable 5.1 within its existing weekly allowance, with a shared 50% cap for Fable models. Pro pays with usage credits from the first request. Here's how to check your limit, reset time, and spending controls before continuing.

Nov 10, 20268 min

Claude usage limits by plan card dated October 8, 2026, showing Pro at $20, Max 5x at $100 and Max 20x at $200 per month

Claude & Anthropic

Claude Usage Limits by Plan: What 5x and 20x Actually Multiply

Since October 30, 2026, Max 20x is Ultra: 10x Pro's weekly usage and no five-hour limit once verified. Max, formerly 5x, is 5x Pro per session and per week.

Nov 10, 202615 min

Gemini 4 Argon scores 50.41 and Claude Fable 5.1 scores 50.02 on AA, while Fable's everyday-task bill falls from 8.6x to 4.3x Argon's

Model Comparisons

Gemini 4 Argon vs Claude Fable 5.1: A Tie on Score, Not on Cost

Gemini 4 Argon and Claude Fable 5.1 tie on Artificial Analysis, yet Fable cost 8.6x Argon on everyday tasks in an October–November test, 4.3x from December 1.

Nov 10, 202618 min

Access cards dated October 6, 2026: Fable 5.5 unannounced, Gemini 4 Argon then limited to Fairwind, GPT-6.1 Sol available, and GPT-6.1 Astra canceled.

Model Comparisons

Fable 5.5 vs Gemini 4 vs GPT-6.1: Fable 5.2 Is Out, 5.5 Isn't

Anthropic released Claude Fable 5.2 on November 9, 2026, at $8/$40 per million tokens. Fable 5.5 is still unannounced; Gemini 4 Argon and GPT-6.1 Sol are out.

Nov 10, 202619 min

Video advertising tools grouped by product assets, spokesperson scripts, and free-plan limits

AI Video Generation

Best Free AI Video Ad Generators in 2026: Free Exports and Limits

For a free ad you can finish from existing product photos, start with Canva and free or self-owned assets. Try Creatify for generated product ads with a watermark. HeyGen Free is limited to personal use and internal evaluation, so it is not a free commercial-ad option.

Nov 9, 202610 min

GPT Image 4K price per image as of November 9, 2026: about $0.40 for GPT Image 2 and about $0.10 for GPT Image 2.6 on OpenAI at high, $0.03 per call on LaoZhang API -vip

AI Image Generation

Real 4K GPT Image 2 / 2.5 / 2.6 API: $0.03 vs OpenAI, Tested

Native 4K GPT Image 2, 2.5 and 2.6 costs $0.03 per call on LaoZhang API -vip; on OpenAI a 4K high image is about $0.40 (GPT Image 2) or $0.10 (2.6, measured).

Nov 9, 202614 min

Claude Code

Claude Code Routines: Set Up Cloud Scheduled Tasks and Choose the Right Runtime

Claude Code routines are now called cloud scheduled tasks. Use them for recurring repo work that must run with your laptop closed; choose Desktop for local files, /loop for session polling, and GitHub Actions for CI. Start with a small scheduled task and inspect its actual run output.

Nov 9, 202612 min

Two Codex Browser disabled messages compared: the in-chat Work settings message fixed by a full quit and new chat, and the Settings → Browser message traced through the log reason

Troubleshooting

Codex Browser Disabled Even When Enabled: 2 Messages, 2 Fixes

Browser on but Codex says it is disabled? Fully quit and reopen the ChatGPT app, continue in a new chat, then check Work preferences → Local browser use.

Nov 8, 202614 min

Seedance 2 prompt planning board connecting a scene idea to references, camera direction, and repairs

AI Video Generation

Seedance 2 Prompt Guide: Shots, References, and Targeted Repairs

Turn a scene idea into a usable Seedance prompt: give each reference a job, write shots for your version, place the sound, and fix one problem at a time.

Nov 8, 202616 min

DeepSeek chat message at 6/6 versions with the pencil greyed out and an Edit limit reached notice, counted per message rather than per day

Troubleshooting

DeepSeek Edit Limit Reached: Counted per Message, Not per Day

Edit limit reached in DeepSeek means one message used up its 6 versions, not a daily quota. Waiting won't reopen it; branch from the message above.

Nov 7, 20269 min

Cover drawn before DeepSeek merged its modes: photos and scanned PDFs marked No text extracted, the old Instant and Expert drop zone reading Text extraction only, and the old image mode

Troubleshooting

DeepSeek "No Text Extracted": Photos and Scans Are Read Now

Since DeepSeek merged its chat modes in September 2026, one mode reads photos and scanned PDFs. If No text extracted still appears, re-save or OCR the file.

Nov 7, 20269 min

Cover drawn before DeepSeek merged its modes: a chat reply under an Expert label cut off by a server busy message, a Continue button, and the old choice between waiting out an outage and switching to Instant mode

Troubleshooting

DeepSeek "Server Is Busy" Fix: Outage or Unposted Overload?

DeepSeek's busy message is a refusal from its servers, not your device. Check status.deepseek.com; if nothing is posted, press Continue, then try a new chat.

Nov 7, 202611 min

DeepSeek Upload failed: retry once when the card has a retry icon, remove the file when it has none, and wait on Server busy

Troubleshooting

DeepSeek "Upload Failed": When Retry Works and When It Can't

DeepSeek's Upload failed means the file didn't get through or the check after it broke, not that its content is bad. Retry once; no retry icon means remove it.

Nov 7, 202611 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 Plus and Go Image Generation Limits: How Many per Day?

OpenAI gives no image count for ChatGPT Go or Plus. Plus users reported about 120 a day through September 2026; your limit banner shows the real reset time.

Nov 6, 202619 min