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 13, 2026

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

LatestAPI 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

Claude Opus 5.5, six ways in: the Claude app from $20 a month, Claude Code v2.1.280+, the API at $4 / $20 per million tokens, and no Opus on the Free plan

Claude & Anthropic

How to Access Claude Opus 5.5: 6 Ways In, Which Free Routes Work

No Claude Opus 5.5 route stays free. As of November 13, 2026, a 7-day guest pass or API test credit works; gifts are paused and 'free' chat sites are capped.

Nov 13, 202620 min

Cheapest AI API by token mix: GPT-6 Luna at $0.10 / $0.50, DeepSeek Flash cached input at $0.003 off-peak, and Grok 4.7 at $2 / $6 per 1M tokens

API Pricing & Plans

AI API Price Comparison: Cheapest Model by Input and Output Mix

As of September 26, 2026, GPT-6 Luna and DeepSeek Flash cost least per token. Among $2-input models, Grok 4.7 is cheapest; past 272K tokens, Sonnet 5 beats Sol.

Nov 12, 202618 min

One 10-second video clip costs $0.20 on xAI's 1.5-lite rate, $0.30 on Gemini Omni or Muse via LaoZhang API, and $1.20 on Runway Gen-4.5

AI Video Generation

Cheapest Video Generation API: What a 10-Second Clip Costs

As of November 12, 2026, a 10-second 720p clip costs $0.30 flat on Gemini Omni 1.2 Flash or Muse via LaoZhang API, and up to $1.20 on other video APIs.

Nov 12, 202611 min

Claude vs OpenAI API pricing: Sol matches Sonnet 5 and Astra matches Fable 5.1, Claude costs less past 272K input and on top-tier cache hits, OpenAI's Luna costs less at the budget tier

API Pricing & Plans

Claude API vs OpenAI API Pricing: When Each One Costs Less

As of September 26, 2026, GPT-6 Sol matches Sonnet 5 and Astra matches Fable 5.1 on list price. Prompts over 272K favor Claude; Luna costs a tenth of Haiku 4.5.

Nov 12, 202612 min

Claude Code's OAuth refresh lock: the empty .oauth_refresh.lock folder, the 60-second stale rule and rmdir when it never ages

Claude & Anthropic

Claude Code "Failed to Refresh OAuth Token": The 60-Second Lock

Claude Code's login isn't rejected: another process holds the refresh lock in ~/.claude. Retry in a minute; if nothing holds it, remove the empty lock folder.

Nov 12, 202614 min

Claude Code

Claude Code Fast Mode: 2x Price, How to Use It, Fix Its Errors

Claude Code fast mode runs the same Opus 5.5 or Fable 5.2 up to 2.5x faster at 2x the token price, paid from usage credits on plans. Enable it at session start.

Nov 12, 202618 min

Claude Fable 5.2 API key access: one Claude Console sk-ant- key, the model ID claude-fable-5-2 and API credit on the organization

API Guides

Claude Fable 5.2 API Key: How to Access It With a Regular Key

There's no separate Fable 5.2 key: any Claude Console key calls claude-fable-5-2 once its organization has API credit. A Pro or Max plan alone doesn't cover it.

Nov 12, 202615 min

Claude Haiku 5.5 vs Opus 5.5 cost comparison: 40x per token up to 100K-token prompts, 8x above, 23–29x per task at equal effort

Claude Code

Haiku 5.5 vs Opus 5.5: 40x Cheaper per Token, 23–29x per Task

Claude Haiku 5.5 costs 1/40 of Opus 5.5 per token on prompts up to 100K and 23–29x less per task at equal effort. Move checkable work; keep agents on Opus.

Nov 12, 202619 min

Claude Code

command 'claude-vscode.editor.openLast' not found: Claude Code Not Working in VS Code

Claude Code not working in VS Code with command 'claude-vscode.editor.openLast' not found? The extension failed to start: update it and fully restart VS Code.

Nov 12, 202621 min

Two separate paths for estimating Opus 5.5 API cost and checking a Claude subscription limit reset

API Pricing & Plans

Claude Opus 5.5 Pricing and Limit Reset: What Each One Changes

Claude Opus 5.5 costs $4/$20 per million tokens; Opus 5 through 4.6 stay at $5/$25. Limit resets are free, can't be bought and don't add API credits.

Nov 12, 202615 min

Claude Opus 5.5 at $4/$20 vs GPT-6 Astra at $10/$50 per 1M tokens, with per-task cost on small coding tasks and long agent runs

Model Comparisons

Claude Opus 5.5 vs GPT-6 Astra: 60% Less per Token, Not per Task

Claude Opus 5.5 lists 60% below GPT-6 Astra per token. On small coding tasks it cost 0.5–0.7x as much; on long agentic work at equal score, about the same.

Nov 12, 202620 min

Codex sidebar list showing no projects while the state_5.sqlite project database still holds every project, with start-up copying only from list to database

Developer Tools & Agents

Codex Local Projects Disappeared After Update: Don't Re-Add Yet

Codex projects missing after an update or account switch are usually still on disk. Update to 26.1106.51428, fully quit, and back up .codex before re-adding.

Nov 12, 202614 min

Google's API, Vercel AI Gateway, OpenRouter and LaoZhang for Gemini Omni 1.2 Flash, with clip length, resolution and price model

AI Video Generation

Gemini Omni 1.2 Flash API Gateway: 4 Routes, Cost by Clip Length

Vercel AI Gateway and OpenRouter carry Google's 3–15 s, up-to-4K model. A flat per-clip gateway costs less than per-second billing for 5–10 s clips to 1080p.

Nov 12, 202615 min

Gemini Omni 1.2 Flash at $0.70 vs Seedance 2.5 at $2.32 per 10-second 720p clip, with the job types each one wins

AI Video Generation

Gemini Omni vs Seedance 2.5: Pick by Job Type, 3.3× Cost Gap

Gemini Omni 1.2 Flash ties Seedance 2.5 on text-to-video and edges it on editing at $0.70 vs $2.32 per 10 s clip; Seedance leads image-to-video and 30 s takes.

Nov 12, 202614 min

Claude Code

How to Use GPT-6 Astra in Claude Code: Proxy or Codex Plugin

Run GPT-6 Astra as Claude Code's main model via a local LiteLLM proxy on API billing, or keep Claude in charge and hand tasks to Astra with the Codex plugin.

Nov 12, 202615 min

GPT Image 2.6 API guide cover with the two model IDs, gpt-image-2.6-flare for fast drafts and gpt-image-2.6-sunburst for steady edits, both on the Image API only

AI Image Generation

GPT Image 2.6 API: Model IDs, Python and curl Code, Error Fixes

Set model to gpt-image-2.6-flare or gpt-image-2.6-sunburst; bare gpt-image-2.6 doesn't exist. Both cost the same, and edits without model run on 2.5.

Nov 12, 202613 min

GPT Image 2.6 GIF in ComfyUI: needs v0.45.0 or later, link frames and fps to Save Animated WEBP, and 12 frames at 512x512 cost $0.0445 against $0.0503 for 9

AI Image Generation

GPT Image 2.6 GIF in ComfyUI: v0.45 Workflow, Save Nodes, Cost

Update to ComfyUI v0.45.0 or later, then link the GIF node's frames and fps outputs to Save Animated WEBP. At most square sizes, 12 frames cost less than 9.

Nov 12, 202616 min

GPT Image 2.6 prompt guide cover with a six-part prompt card: result, format, visible details, people, exact text and constraints, then a final check

AI Image Generation

GPT Image 2.6 Prompt Guide: Which Rules Held Up in Testing

Write GPT Image 2.6 prompts in plain words: result, details, quoted text, exclusions. Quoted text held 2 of 2 times; edits need a size that matches the photo.

Nov 12, 202615 min

GPT Image 2.6 SVG output in two stages: the image model draws a reference image, then gpt-6.1-terra writes the SVG code

AI Image Generation

GPT Image 2.6 SVG Generator: Python Script, Output Checks, Cost

Send output_format svg to gpt-image-2.6-flare with an svg.model writer on OpenAI, or to LaoZhang's gpt-image-2.6-web at $0.03 a call with an ordinary key.

Nov 12, 202621 min

What AI video really costs: creator plans at $5 to $35 a month, 720p API rates of $0.04 to $0.25 per second, and $1.20 to $9.60 for a usable 8-second clip

AI Video Generation

How Much Does an AI Video Generator Cost Per Month and Per Clip?

As of September 2026, creator plans run about $5–$35 a month and APIs charge $0.04–$0.25 per second at 720p. Sora is gone, and retries set the real cost.

Nov 12, 202618 min

MiniMax H3 API pricing: LaoZhang API at $0.05/s for 768P and $0.08/s for 2K against MiniMax's $0.08 and $0.13 list, a 5-second 768P clip at $0.25

AI Video Generation

MiniMax H3 (Hailuo) API Pricing: Cost Per Clip at 768P and 2K

As of November 12, 2026, MiniMax H3 lists at $0.08/s (768P) and $0.13/s (2K); LaoZhang API charges $0.05 and $0.08, so a 5-second 768P clip is $0.25.

Nov 12, 202611 min