# QCode.cc

> Multi-model AI API gateway. One API key for Claude, GPT, Gemini, GLM, Kimi, DeepSeek and Qwen, billed at official provider rates times a service multiplier.

QCode.cc resells frontier model APIs over Anthropic-compatible and OpenAI-compatible endpoints. It is not an IDE, not a subscription tool, and does not train its own models. Every page below is available in Chinese (default path), English (/en/), Japanese (/ja/) and Russian (/ru/).

Pages that describe a model do not imply that model is purchasable here; pages that make an availability claim are the ones categorised as model guides or comparisons.

## Model guides

- [Claude Fable 5.1 complete guide: cache reads 75% cheaper, $10/$50 unchanged, 1M context 2026](https://qcode.cc/en/claude-fable-5-1-guide): Cache reads 75% cheaper, input and output unchanged, 1M context, and how to decide whether to switch from Fable 5.
- [Is Claude Fable 5 Available? API Yes, Subscriptions Tiered by Plan (July 2026)](https://qcode.cc/en/claude-fable-5-availability): Fable 5 is available on the API throughout. On Anthropic's own subscriptions it has been tiered by plan since July 19, 2026: standard on Max and Team/Enterprise premium seats, pay-as-you-go usage cred
- [Claude Fable 5 Complete Guide — A New Flagship Tier Above Opus](https://qcode.cc/en/claude-fable-5-guide): Claude Fable 5 guide: Anthropic's most capable tier above Opus — 1M context, 128K output, $10/$50. Available on the API and live on QCode; tiered by plan on Anthropic subscriptions since 2026-07-19.
- [Claude Haiku 4.5: The Complete Guide to the Cheapest Tier That's #1 Platform-Wide](https://qcode.cc/en/claude-haiku-4-5-guide): Pricing, positioning, and evidence it's the #1 model by call volume
- [Claude Mythos / Capybara Leak Guide: Anthropic's Possible Tier Above Opus](https://qcode.cc/en/claude-mythos-capybara-guide): Claude Mythos (codename Capybara) leak guide: Anthropic may be testing a model tier above Opus. This page summarizes the public reporting around its coding, reasoning, cybersecurity claims, and possib
- [Claude Opus 4.6: The Complete Guide to Its SWE-bench Score, Pricing, and Use on QCode](https://qcode.cc/en/claude-opus-4-6-guide): SWE-bench score, pricing, and how to use it
- [Claude Opus 4.7 Complete Guide — Coding / Vision / Agentic Leap](https://qcode.cc/en/claude-opus-4-7-guide): Claude Opus 4.7 complete guide: 64.3% on SWE-bench Pro, 3x vision resolution, new xhigh effort tier, native 1M context. Same price as 4.6 ($5/$25). Covers coding breakthroughs, vision upgrades, migrat
- [Claude Opus 4.8 Complete Guide — Sharper Agentic Judgement, 4x Fewer Code Flaws](https://qcode.cc/en/claude-opus-4-8-guide): Claude Opus 4.8 complete guide: sharper agentic judgement, 4x fewer code flaws than 4.7, Online-Mind2Web 84%, native 1M context. Same price as 4.7 ($5/$25). Covers agentic coding gains, capability upg
- [Claude Opus 5 Complete Guide — Same Price and Window as Opus 4.8](https://qcode.cc/en/claude-opus-5-guide): Claude Opus 5 is live: $5/$25 per million tokens, 1M context, 128K output — identical pricing and window to Opus 4.8. The prompt cache threshold drops to 512 tokens (Opus 4.8 needs 2048), so short sys
- [Claude Sonnet 5: Model ID, Context Window, Pricing & Review (2026)](https://qcode.cc/en/claude-sonnet-5): Claude Sonnet 5 (claude-sonnet-5), released 2026-06-30: 1M context, 128K output, standard $2/$10 after the September increase was cancelled.
- [Claude Sonnet 5 API: Setup Guide, Model ID & Effort Parameter](https://qcode.cc/en/claude-sonnet-5-api): How to use the Claude Sonnet 5 API: model id claude-sonnet-5, curl and Python SDK examples, adaptive thinking, the effort parameter, re-tuning max_tokens for the new tokenizer, and stable access throu
- [Is Claude Sonnet 5 Available? Release Date, Plans & Providers (2026)](https://qcode.cc/en/claude-sonnet-5-availability): Claude Sonnet 5 released June 30, 2026 and is available now: the default model on Free and Pro, plus Max/Team/Enterprise and Claude Code. Full plan and provider availability matrix (Claude API, Amazon
- [DeepSeek V4 Flash 0731 Guide 2026: Benchmarks, Price, vs Sonnet 5](https://qcode.cc/en/deepseek-v4-flash-0731): 0731 re-post-train: agent scores, $0.14/$0.28, local weights
- [DeepSeek V4 Pro 0813 Guide 2026: GA Specs, Price, vs Fable 5](https://qcode.cc/en/deepseek-v4-pro-0813): 1.6T-class GA, agent benchmarks, peak/off-peak pricing, QCode catalog price
- [GLM-5.2: 2026's Strongest Open-Weight Coding Model — Benchmarks and Access](https://qcode.cc/en/glm-5-2-guide): GLM-5.2 is 2026's strongest open-weight coding model (MIT, 1M context). Verified benchmarks, pricing, supply and compliance caveats, and what you can use today.
- [GLM-5.3-Flash Guide: 320B-A18B, 1M Context, MIT Weights and the Real Benchmark](https://qcode.cc/en/glm-5-3-flash-guide): 320B-A18B, 1M context, MIT weights; promo ends 9/9; real DeepSWE 63.4%
- [GPT-5.6 Sol, Terra & Luna — Benchmarks, Pricing & Access (GA July 2026)](https://qcode.cc/en/gpt-5-6-guide): GPT-5.6 in use: Terra by default, Luna $0.20/$1.20 for volume, Sol $5/$30 when it is hard. As of 2026-08-30 prices unchanged. ChatGPT-login drops 5.4 starting 08-31.
- [GPT-5.6 Mini / Nano: The Complete Guide to the Smallest Tiers Beyond Sol/Terra/Luna](https://qcode.cc/en/gpt-5-6-mini-nano-guide): Positioning, use cases, and real usage data
- [Kimi K2.6: The Complete Guide — Still On Sale Alongside K3, 30-Day Usage Verified](https://qcode.cc/en/kimi-k2-6-guide): On sale alongside K3, real usage data verified
- [Kimi K3 guide 2026: kimi-k3, $3/$0.30/$15, thinking stays on](https://qcode.cc/en/kimi-k3-guide): kimi-k3: 2.8T, 1M, $3/$0.30/$15, thinking will not turn off
- [Qwen3.7-Max guide 2026: qwen3.7-max, 1M, $2.50/$7.50](https://qcode.cc/en/qwen3-7-max-guide): id qwen3.7-max, 1M, $2.50/$7.50; listed on QCode, 3.8-Max is not
- [Qwen3.7-Plus: The Complete Guide — On Sale Alongside Max, 30-Day Usage Verified](https://qcode.cc/en/qwen3-7-plus-guide): On sale alongside Max, real usage data verified

## Model comparisons

- [How to Choose an AI Coding Model in H2 2026: GPT-5.6, Claude Fable 5, Gemini 3.5](https://qcode.cc/en/ai-coding-model-lineup-2026h2): Decision framework + three-camp overview + navigation to this site's full lineup content.
- [AI Coding Tools Comparison 2026: Claude Code, Codex, Cursor, Copilot](https://qcode.cc/en/ai-coding-tools-comparison): In-depth analysis of mainstream AI coding tools: Claude Code, OpenAI Codex, Cursor 3, Google Antigravity 2.0, GitHub Copilot (2026-08 update: Cursor 3 Agents Window, Antigravity's five surfaces, Space
- [AI Coding Tools Review: Claude Code, Copilot and More](https://qcode.cc/en/ai-coding-tools-review)
- [Claude Code vs Cursor: 2026 In-Depth Comparison of AI Coding Tools](https://qcode.cc/en/claude-code-vs-cursor-comparison): Claude Code vs Cursor comprehensive comparison: AI models, context window, execution mode, pricing, agent capabilities — find the best AI coding tool for your workflow
- [Claude Fable 5 vs GPT-5.6 Sol: Price, Context & Benchmarks Compared](https://qcode.cc/en/claude-fable-5-vs-gpt-5-6-sol): Price, context window, and benchmark methodology compared, plus how to call both on QCode
- [Claude Opus 5 vs GPT-5.6 Sol (2026): 0.4 Apart on TB 2.1 — Price and Context Compared](https://qcode.cc/en/claude-opus-5-vs-gpt-5-6-sol): A half-point war: what to compare once benchmarks tie
- [Claude Sonnet 5 vs GPT-5.6 vs Gemini 3.1 Pro: an honest, no-hype comparison](https://qcode.cc/en/claude-sonnet-5-vs-gpt-5-6-vs-gemini-3): There is no shared benchmark across Anthropic, OpenAI and Google — so compare Claude Sonnet 5, GPT-5.6 and Gemini 3.1 Pro on price, value and availability, not one score. Honest specs, blank benchmark
- [Claude Sonnet 5 vs Opus 4.8: Price, Coding & Agent Comparison (2026)](https://qcode.cc/en/claude-sonnet-5-vs-opus-4-8): Claude Sonnet 5 vs Opus 4.8 compared: Sonnet 5 is ~40% cheaper and close to Opus 4.8, but Opus 4.8 still leads the hardest coding, judgment and cyber tasks. Specs, honest benchmarks, pricing and a rou
- [Claude Sonnet 5 vs Sonnet 4.6: API Migration & Upgrade Guide](https://qcode.cc/en/claude-sonnet-5-vs-sonnet-4-6): How to migrate from Claude Sonnet 4.6 to Sonnet 5: a drop-in model-id swap, plus the 3 breaking changes (adaptive thinking on by default, manual thinking and non-default temperature/top_p/top_k now re
- [DeepSeek V4 Flash 0731 vs Claude Sonnet 5 (2026)](https://qcode.cc/en/deepseek-v4-flash-vs-claude-sonnet-5): AA Intelligence 52 vs 55. Cost/task $0.06 vs $1.54. Speed 115 vs 69 tok/s. Both 1M context. Flash is open; Sonnet is the Claude default.
- [DeepSeek V4 Pro 0813 vs Claude Fable 5 (2026)](https://qcode.cc/en/deepseek-v4-pro-vs-claude-fable-5): Same HF table: TB2.1 87.9 vs 88.0, DeepSWE 62.7 vs 70.0, HLE w/tools 60.0 vs 63.0. Fable still leads most rows; Pro wins price and MIT weights.
- [DeepSeek V4 Pro 0813 vs GPT-5.6 Sol (2026)](https://qcode.cc/en/deepseek-v4-pro-vs-gpt-5-6-sol): Open 1.7T agent flagship vs the closed GPT-5.6 top tier: 53 vs 61 on intelligence, $0.435/$0.87 vs $5/$30.
- [GLM-5.2 vs DeepSeek V4 Pro (2026): Open-Flagship Value After the Price Hike](https://qcode.cc/en/glm-5-2-vs-deepseek-v4-pro): The post-hike open-flagship math: DeepSeek off-peak, GLM at peak
- [GLM-5.3-Flash vs DeepSeek V4 Flash: official $0.15/$0.50 vs $0.14/$0.28, both 1M and both sold](https://qcode.cc/en/glm-5-3-flash-vs-deepseek-v4-flash): Two sold Flash tiers: official price, 1M window, MIT; same-endpoint switch
- [GLM-5.3 vs Kimi K3 (2026): Tied at the Top of Open Source — Routes and Prices Compared](https://qcode.cc/en/glm-5-3-vs-kimi-k3): Two routes to the open-source lead: post-training vs giant base
- [GPT-5.5 vs Claude 4.7: 2026 Frontier AI Model Benchmark](https://qcode.cc/en/gpt-5-5-vs-claude-4-7): GPT-5.5 vs Claude 4.7 head-to-head — reasoning, coding, long context, multimodal, pricing. QCode proxies both with unified subscription.
- [GPT-5.5 vs Claude 4.8: 2026 Frontier AI Model Benchmark](https://qcode.cc/en/gpt-5-5-vs-claude-4-8): GPT-5.5 vs Claude 4.8 head-to-head — reasoning, coding, long context, multimodal, pricing. QCode proxies both with unified subscription.
- [GPT-5.6 Sol vs Terra vs Luna: Tier Comparison and Selection Guide](https://qcode.cc/en/gpt-5-6-sol-vs-terra-vs-luna): GPT-5.6 default: Terra daily, Luna $0.20/$1.20 for volume, Sol $5/$30 when hard. OpenAI’s @thsottiaux, 2026-07-29 (fetched 2026-08-30): has not reduced usage on any subscription plans; Sol faster than
- [GPT-5.6 vs Claude Opus 4.8 — Benchmarks, Pricing & Status (June 2026)](https://qcode.cc/en/gpt-5-6-vs-claude-opus-4-8): GPT-5.6 vs Claude Opus 4.8: both GA — Terminal-Bench 88.8% vs 78.9%, pricing $5/$30 vs $5/$25. A fact-checked comparison, with both available via QCode.
- [Kimi K3 vs Claude Opus 5 (2026): Open 2.8T vs Closed Flagship](https://qcode.cc/en/kimi-k3-vs-claude-opus-5): Opus 5 leads most independent aggregates (~83 vs ~80) with overlapping intervals. K3 is 2.8T, 1M, native vision, $3/$15, open weights. Official K3 blog says it still trails Fable 5 and Sol.
- [Kimi K3 vs GPT-5.6 Sol (2026): Open vs Closed Flagship, 1.2 Apart on TB 2.1](https://qcode.cc/en/kimi-k3-vs-gpt-5-6-sol): Open flagship vs closed flagship: a 1.2-point gap and an order-of-magnitude price gap

## Pricing and cost

- [2026 AI Model Radar: Release Status of Every Frontier Model](https://qcode.cc/en/ai-model-radar-2026): Live 2026 AI model tracker: GPT-5.6, Gemini 3.7 Flash, Fable 5 and GLM-5.2 — which models are available, which (such as Gemini 3.5 Pro) remain in preview or restricted, and how to access them.
- [Claude Code Cost Optimization: Token Savings & Smart Routing](https://qcode.cc/en/claude-code-cost-optimization): Master Claude Code cost optimization — token pricing, 5 money-saving tips, QCode.cc plan comparison, and model selection strategies. flexible subscription+ on AI coding costs.
- [How Much Does Claude Fable 5 Cost? Official Pricing vs Subscription](https://qcode.cc/en/claude-fable-5-pricing-guide): Official API rate breakdown, flagship price comparison, and estimated task costs
- [Claude Sonnet 5 Pricing: Cost Per Token, Intro vs Standard Rates](https://qcode.cc/en/claude-sonnet-5-pricing): Claude Sonnet 5 pricing: $2/$10 per MTok is now the standard rate — Anthropic cancelled the planned $3/$15 increase. Cache rates and the tokenizer caveat.
- [DeepSeek V4 Price Hike 2026 Explained: Peak/Off-Peak Pricing, the +350% Truth and Scheduling to Save](https://qcode.cc/en/deepseek-v4-price-increase-2026): Peak/off-peak pricing details, the real increase, and off-peak scheduling to save
- [Gemini 3.7 Flash pricing 2026: $0.75/$3.75 intro and the double](https://qcode.cc/en/gemini-3-7-flash-pricing): Intro $0.75/$3.75 through year-end, then doubles; Batch/Flex half
- [GLM-5.3-Flash Pricing: $0.075/$0.25 Until September 9, and Why Cache Reads Matter](https://qcode.cc/en/glm-5-3-flash-pricing): 50% off $0.075/$0.25 to 9/9; why cache reads are the real cost driver
- [GPT-5.6 Luna Price Tracker: $0.20/$1.20 After July 30 Cut](https://qcode.cc/en/gpt-5-6-luna-price-tracker): Luna $0.20/$1.20 after the July 30 cut, with Terra and Sol rates and Codex notes
- [GPT-5.6 Pricing Guide: Tier Prices, Cache Billing and Cost Estimates](https://qcode.cc/en/gpt-5-6-pricing): How GPT-5.6 bills work: as of 2026-08-30 the API list is still Sol $5/$30, Terra $2/$12, Luna $0.20/$1.20. Follow cache hits, not the launch sticker.
- [Kimi K3 Status Tracker: Launch Confirmed, Specs and Open Questions](https://qcode.cc/en/kimi-k3-status-tracker): Kimi K3 (Moonshot) status tracker: officially released 2026-07-16 with 1M context and K3·Max tiers, coding benchmark reports, and what is still unconfirmed.
- [OpenCode Go Free vs Paid (2026): Flash Free, Limits, When to Upgrade](https://qcode.cc/en/opencode-go-free): “OpenCode Go Free” mixes two things: free models on the OpenCode/Zen side, and Go’s paid $10 lane. New V4 Flash is advertised on Free too. Paid Go sells reliability and documented dollar caps.
- [OpenCode Go 2026: $5 then $10, Limits, vs Zen / Free](https://qcode.cc/en/opencode-go-guide): OpenCode Go is Anomaly’s $5 first month / $10 later subscription for curated open coding models. Limits are dollars ($12/5h, $30/week, $60/month), not fixed requests. Go ≠ Zen.
- [QCode.cc Complete Pricing Guide: Plan Details and Rate Explanation](https://qcode.cc/en/qcode-pricing-guide): Complete QCode.cc pricing guide: 7 plan tiers, 1:1 official rate, token estimates, no 4h window limits, booster packs, and plan selection guide.

## Errors, limits and account issues

- [When an AI API bill does not match: reset times, usage reconciliation and refund terms 2026](https://qcode.cc/en/ai-api-billing-refund-faq): Three reset times, four reasons a bill will not reconcile, and the refund and transfer terms.
- [Claude and Codex Subscription Bans Explained](https://qcode.cc/en/ai-coding-subscription-ban-guide): A neutral overview of Claude and Codex subscription bans and why pay-as-you-go API access is more stable for coding.
- [Claude's 5-Hour Rolling Window Explained: When It Starts and How It Stacks With the Weekly Limit](https://qcode.cc/en/claude-5-hour-window-explained): The window's starting point and how it stacks with the weekly limit
- [Claude API 529 Overloaded: what it means and how to handle it](https://qcode.cc/en/claude-529-overloaded): How 529 differs from 429/503, correct backoff, and multi-route availability.
- [Claude 529 vs 429 vs Weekly Limit: Three Causes and How to Respond to Each](https://qcode.cc/en/claude-529-vs-429-vs-weekly-limit): How to tell apart three error types and what to do about each
- [Claude Code Account Ban Guide - Why It Happens](https://qcode.cc/en/claude-code-account-ban-guide): Why Claude accounts get banned and the compliant, API-based path to keep using Claude models.
- [Auto-continue when limits reset: Claude Code Desktop resumes after refill, it does not cancel limits](https://qcode.cc/en/claude-code-auto-continue): Desktop resumes after official refill; does not cancel the 5-hour window or weekly limit
- [Claude usage limit reached: The Complete Guide for Russian-Speaking Developers When Quota Runs Out](https://qcode.cc/en/claude-code-limits-russia): How to diagnose the error and Russia payment methods explained
- [Claude Code Quota and Reset Mechanisms 2026](https://qcode.cc/en/claude-code-quota-reset-2026): Claude Code 2026 quota: @ClaudeDevs on 2026-08-29 said the +50% weekly boost stays through 2026-09-14, then standard weekly limits rise permanently by 25%. Help Center as of 2026-08-30 still says exte
- [Claude invisible watermark 2026: text mark, C2PA, Art. 50 limits](https://qcode.cc/en/claude-invisible-watermark-guide): Text watermark + C2PA: a mark ≠ author, no mark ≠ not AI
- [claude-sonnet-4-5-20250929: API not sooner than 2026-09-29, Copilot drops it 2026-09-01](https://qcode.cc/en/claude-sonnet-4-5-api-retirement): Same snapshot id, two removal dates — Copilot is not the Messages API
- [Claude usage limit reached: the 5-hour window vs the weekly cap](https://qcode.cc/en/claude-usage-limit-reached): 5-hour window vs weekly cap, official +50% boost through 2026-09-14, and what to do when quota is gone.
- [Claude weekly limit 2026: +50% through Sep 14, then standard +25%](https://qcode.cc/en/claude-weekly-limit-2026): Weekly-limit rules; +50% through 2026-09-14, then standard +25%
- [Claude Code weekly limits end 2026-09-13: the official wording, the 5-hour distinction and what to do](https://qcode.cc/en/claude-weekly-limit-september-2026): Official promotion dates, how the five-hour window differs, and a /usage self-check plus downgrade path.
- [Codex 5-Hour Rolling Limit Is Back (July 30, 2026): Mechanics, Reports, Workarounds](https://qcode.cc/en/codex-5-hour-limit-guide): The 5-hour rolling limit returned on 2026-07-30 — timeline, community reports and what to do when you hit it.
- [Codex & ChatGPT Pro Account Bans Explained](https://qcode.cc/en/codex-account-ban-guide): A calm, factual look at why Codex and ChatGPT accounts get suspended and why an API-based path is more stable.
- [Codex Quota Anomaly and Banked Reset 2026](https://qcode.cc/en/codex-quota-banked-reset): Codex mid-2026 quota anomaly, full reset and Banked Reset elastic mechanism. How users observed it and how to adapt with QCode.
- [Codex Usage Limit With /status Still Green: Why the Ghost Quota Happens and How to Tell](https://qcode.cc/en/codex-usage-limit-but-status-green): Why /status shows headroom but requests get rejected, and a 3-step way to tell why
- [Codex weekly limit burned in hours: what GPT-5.6 Sol actually costs](https://qcode.cc/en/codex-weekly-limit-burned): Reasoning-tier cost differences, the reality of extra credits, and alternatives.
- [Context Length Exceeded: The Complete Troubleshooting Guide to Its Three Disguises](https://qcode.cc/en/context-length-exceeded-guide): The three disguises of context overflow and how to tell them apart
- [Credit balance is too low: Anthropic Console prepaid credits are empty, not a weekly limit](https://qcode.cc/en/credit-balance-too-low): The literal means prepaid usage credits are 0, not weekly limit or the monthly cap
- [Cursor Usage Limit Reached: How the Two Usage Pools and Reset Date Actually Work](https://qcode.cc/en/cursor-two-usage-pools): Cursor Models pool vs Other Models pool and the reset rules
- [effort is not supported when thinking is disabled: xhigh/max cannot turn thinking off; 2.1.251 sends high](https://qcode.cc/en/effort-not-supported-thinking-disabled): xhigh/max plus thinking off is 400; 2.1.251 clients send high
- [Claude API 429 with no retry-after: enforced_spend_limit_reached is a monthly spend cap, not a rate limit](https://qcode.cc/en/enforced-spend-limit-reached): A 429 with no retry-after is the org monthly spend cap, not RPM throttling
- [Gemini CLI "Client No Longer Supported": How It Differs From a Zero Quota, and the Real Fix](https://qcode.cc/en/gemini-cli-client-no-longer-supported): Telling apart a retired sign-in path from a quota issue, and migration options
- [GPT-5.4 Retires from Codex Aug 31: Migration Guide](https://qcode.cc/en/gpt-5-4-codex-shutdown-migration): The 8/31 shutdown timeline, who's affected, and how to move to Terra/Luna
- [GPT-5.6 Sol is 272000 in Codex, not 1.05M: how originator splits one account into two catalogs](https://qcode.cc/en/gpt-5-6-sol-codex-272k-context): Under coding originators Sol is 272000, not the 1.05M model spec
- [How to judge whether an AI API relay is worth using: four self-tests and the pricing basis 2026](https://qcode.cc/en/how-to-choose-ai-api-relay): Four self-tests: multiplier conversion, cache hits, echoed model and usage reconciliation.
- [Stream Closed Before Completed: The Complete Guide to Its Four Causes and How to Triage Them](https://qcode.cc/en/stream-closed-before-completed): Four causes of stream cutoffs and a hop-by-hop triage method

## Coding tools and integrations

- [Aider Complete Guide: Git-Native AI Coding with Claude Models](https://qcode.cc/en/aider-ai-coding-guide): Aider is a Git-native AI coding assistant with 30K+ GitHub Stars, supporting Claude, GPT, and 260+ models. Learn to install and configure Aider with QCode.cc for low-cost Claude access.
- [Pointing Claude Code at a custom endpoint: the ANTHROPIC_BASE_URL and AUTH_TOKEN setup guide 2026](https://qcode.cc/en/anthropic-base-url-setup-guide): The two environment variables, the settings.json form, apiKeyHelper, and the documented web-session limitation.
- [API Key Usage Query API — Programmatically Check Usage & Expiry](https://qcode.cc/en/api-key-usage-query-guide): QCode Open API: generate a read-only token in your dashboard and query all your active API keys' expiry, daily usage and quota with one curl call — wire it into expiry alerts, usage dashboards and CI.
- [Claude Code Agent Teams Collaboration Guide](https://qcode.cc/en/claude-code-agent-teams-guide): Complete guide to Claude Code Agent Teams. Multi-agent collaboration architecture (Lead/Teammates/shared task list/mailbox), enabling configuration, Custom Subagents (@ mention), and QCode.cc setup.
- [Claude Code in China: Complete Guide 2026](https://qcode.cc/en/claude-code-china-guide): Complete guide to using Claude Code in China 2026: bypass network and payment barriers. Supports Alipay, direct developer platform without VPN. Compatible with Agent Teams, MCP, Managed Agents.
- [Claude Code Desktop Redesign 2026: Mission Control and Parallel Sessions](https://qcode.cc/en/claude-code-desktop-redesign-2026): Claude Code Desktop redesign 2026-04-14: Mission Control, parallel split panels, integrated terminal+editor, new diff viewer, SSH on Mac, plugin parity.
- [Claude Code Dynamic Workflows: Orchestrate Hundreds of Subagents](https://qcode.cc/en/claude-code-dynamic-workflows-guide): What dynamic workflows are in Claude Code, how to trigger them with the workflow keyword, ultracode, and /deep-research, and when to use them for audits, migrations, and research.
- [Claude Code FAQ: Usage, Pricing and Troubleshooting](https://qcode.cc/en/claude-code-faq): Answers to common questions about using Claude Code, covering getting started, pricing, quotas, and troubleshooting.
- [Claude Code User Guide: From Installation to Mastery](https://qcode.cc/en/claude-code-guide): Complete tutorial for Claude Code CLI tool, from installation to mastery. Supports latest features including Claude Opus 4.6/4.7/4.8, Background Agents, and Hooks.
- [Claude Code Hooks & Automation Guide: Custom Workflows](https://qcode.cc/en/claude-code-hooks-automation): Master Claude Code Hooks and automation — PreToolUse/PostToolUse configuration, CI/CD headless integration, sensitive file protection, and practical workflow recipes.
- [Claude Code MCP Complete Guide: Model Context Protocol Ecosystem](https://qcode.cc/en/claude-code-mcp-guide): Complete guide to Claude Code MCP (Model Context Protocol) — popular MCP Servers, configuration tutorials, and security best practices. Use MCP workflows at low cost via QCode.cc.
- [Claude Code Plugin Marketplace 2026: Transparent Context Cost and Dependency Management](https://qcode.cc/en/claude-code-plugin-marketplace-2026): Claude Code Plugin Marketplace May 2026 (v2.1.128-136): official Anthropic directory, projected context cost, dependency enforcement, project purge.
- [Claude Code Plugin Ecosystem Complete Guide](https://qcode.cc/en/claude-code-plugins-guide): Complete guide to the Claude Code plugin ecosystem. Official marketplace, community picks like Superpowers (42K★), plugin development basics, manifest format, and setup via QCode.cc.
- [Claude Code Routines: Schedule, API, and GitHub Trigger Automation](https://qcode.cc/en/claude-code-routines-guide): Claude Code Routines (2026-04-14 preview): cloud-scheduled automation via Schedule / API / GitHub triggers. Pro 5/day, Max 15, Team/Ent 25 routines per day.
- [Claude Code Slash Commands Complete Reference: Built-in and Custom](https://qcode.cc/en/claude-code-slash-commands-complete): Claude Code Slash Commands: 8 built-ins (/init /review /compact /cost /loop /schedule /plugin /help) + custom .claude/commands/ project & personal scopes.
- [ultracode & Effort Controls in Claude Code (Opus 4.8)](https://qcode.cc/en/claude-code-ultracode-guide): How Claude Code's reasoning effort levels work — high, xhigh, and max — what ultracode does, when to use each, and how the cheaper Fast Mode pricing fits in.
- [Claude Code Voice Mode: Complete Voice Coding Guide](https://qcode.cc/en/claude-code-voice-mode-guide): Claude Code Voice Mode complete guide: voice coding setup, 20 language support, workflow best practices for hands-free programming
- [Claude Code Worktree Parallel Workflow: Multi-Agent Git Isolation Done Right](https://qcode.cc/en/claude-code-worktree-parallel-guide): Claude Code worktree isolates each agent's files for parallel work. EnterWorktree tool, isolation: worktree config, agent teams, cleanup, pitfalls.
- [Claude Cowork Desktop Complete Guide](https://qcode.cc/en/claude-cowork-guide): Complete guide to Claude Cowork desktop app. Product positioning, core features (computer use, scheduled tasks, project management, plugin marketplace), installation, and setup via QCode.cc.
- [Claude Managed Agents: Complete Guide 2026](https://qcode.cc/en/claude-managed-agents-guide): Claude Managed Agents complete guide 2026: Anthropic's fully managed cloud AI agent platform, launched in public beta April 8, 2026. Sandboxed execution, checkpointing, credential management, scoped p
- [Claw Ecosystem Guide: From OpenClaw to ClawHub and ClawWork](https://qcode.cc/en/claw-ecosystem-guide): Deep dive into the 2026 Claw ecosystem: OpenClaw (302K+ Stars), ClawHub skills marketplace (800+ skills), ClawWork enterprise, PicoClaw lightweight, and security best practices.
- [Cline with OpenAI-Compatible APIs, 2026 Guide: BYOK Setup, Model Switching, vs Subscriptions](https://qcode.cc/en/cline-openai-compatible-guide): Three fields to QCode; choosing between BYOK pay-per-use and a $20 subscription
- [OpenAI Codex CLI Complete Guide: Setup, Features & Comparison](https://qcode.cc/en/codex-cli-complete-guide): OpenAI Codex CLI complete guide: installation, core features, multi-model support, MCP integration, and in-depth comparison with Claude Code
- [Codex Computer Use Guide: Background Cross-App Mac Control](https://qcode.cc/en/codex-computer-use-guide): OpenAI Codex Computer Use (2026-04-16): Codex sees/clicks/types across any Mac app in the background, multi-agent parallel, 90+ plugins. Mac-only, EU/UK soon.
- [Codex Desktop App & ChatGPT Super App Guide](https://qcode.cc/en/codex-desktop-super-app-guide): Complete guide to OpenAI Codex Desktop App and ChatGPT Super App. Evolution from CLI to desktop, ChatGPT Super App features (Chat+Codex+Atlas unified), new models GPT-5.5/5.4/5.3-Codex-Spark, and QCod
- [Enable GPT-5.5 in Codex CLI 0.124.0](https://qcode.cc/en/codex-enable-gpt-5-5): Codex CLI 0.124.0 doesn't ship GPT-5.5 by default. This 4-step tutorial shows how to enable it via model-catalog.json. Includes download, config.toml sample, and troubleshooting.
- [Use GPT-5.6 (Sol / Terra / Luna) in Codex CLI: 4-Step Setup](https://qcode.cc/en/codex-enable-gpt-5-6): GPT-5.6 in Codex: switch sol / terra / luna with /model; if the list is empty, tell ChatGPT login from an API key first. Official line: ChatGPT-login drops 5.4 starting 2026-08-31 (rechecked 2026-08-3
- [GPT-5.5 in Codex + Goal Mode: 2026 Guide](https://qcode.cc/en/codex-gpt-5-5-goal-mode-guide): GPT-5.5 is OpenAI's strongest agentic coding model — 82.7% on Terminal-Bench 2.0 and 58.6% on SWE-Bench Pro. Plus Codex Goal Mode, Appshots, and remote computer use.
- [Grok Build Open Source Guide 2026: What Shipped Under Apache 2.0, Self-Hosting, and the Privacy Backstory](https://qcode.cc/en/grok-build-open-source): Grok Build went fully open source on 2026-07-15 under Apache 2.0: ~840k lines of Rust, self-compile with your own inference endpoint, hybrid cloud patterns.
- [JetBrains AI Assistant OpenAI-compatible API 2026: Providers & API keys](https://qcode.cc/en/jetbrains-ai-guide): Official OpenAI-compatible: URL, API key, Test Connection
- [OpenClaw Open-Source AI Agent Complete Guide 2026](https://qcode.cc/en/openclaw-ai-agent-guide): Complete guide to OpenClaw open-source AI Agent: architecture, MCP plugin ecosystem, local deployment. Learn how to use AI coding tools efficiently with QCode.cc.
- [OpenClaw Skills Guide: 5,700+ AI Agent Skills Ecosystem](https://qcode.cc/en/openclaw-skills-guide): Explore the OpenClaw Skills ecosystem with 5,700+ AI agent skills covering coding, automation, DevOps, data analysis, and more. Learn how to install and create custom skills.
- [OpenCode Complete Guide: The 120K Stars Open Source AI Coding Assistant](https://qcode.cc/en/opencode-ai-coding-guide): OpenCode is an open-source AI coding assistant with 120K+ GitHub Stars, supporting 75+ model providers, multi-agent architecture, and native LSP integration. Use Claude models in OpenCode at low cost 
- [Warp custom OpenAI-compatible inference 2026: public URL, skip Auto, QCode](https://qcode.cc/en/warp-terminal-ai-guide): OpenAI Chat Completions, public URL, do not pick Auto
- [Tencent WorkBuddy Guide: Office AI Agent, Custom API & Coding Boundary](https://qcode.cc/en/workbuddy-guide): Office multi-agent overview, Custom API setup angle, and coding-tool boundary
- [Zed OpenAI-compatible API 2026: openai_compatible, api_url, QCode](https://qcode.cc/en/zed-ai-guide): Official openai_compatible: api_url, model id, key

## Engineering practices

- [Agentic Code Review Practical Guide: How Developers Review AI-Generated Code in 2026](https://qcode.cc/en/agentic-code-review-guide): AI agents now generate 10x more code. Review has become the highest-leverage human skill. Actionable checklists, common pitfalls, and team processes.
- [2026 Agentic Coding Trends: The AI Programming Revolution](https://qcode.cc/en/agentic-coding-trends-2026): 2026 Agentic coding trends analysis: 55% attention shift to autonomous programming, multi-agent collaboration, developer AI adoption, understand the future of AI coding
- [AGENTS.md Spec Complete Guide 2026: Cross-Vendor AI Agent Memory Standard](https://qcode.cc/en/agents-md-spec-complete-guide): AGENTS.md is the cross-vendor AI agent project memory standard launched Aug 2025 by OpenAI, Google, Cursor, Factory. Spec breakdown, CLAUDE.md interop, best practices, real examples.
- [AI Agent Evals & Readiness Harness 2026: Production Evaluation Playbook](https://qcode.cc/en/ai-agent-evals-readiness-harness): Going from demo to production for AI agents: build an evals suite and readiness harness. 7 evaluation dimensions, 4 harness patterns, CI integration, observability loop. A practical companion to harne
- [AI Coding Best Practices: Code Quality and Development Efficiency](https://qcode.cc/en/ai-coding-best-practices): Master professional AI-assisted coding techniques to improve code quality and development efficiency. Complete guide from prompt engineering to workflow optimization.
- [AI Coding Case Studies: Real-World Claude Code Applications](https://qcode.cc/en/ai-coding-case-studies): Explore AI coding applications in real-world projects. Learn from successful case studies and discover how Claude Code improves development efficiency and code quality.
- [Data compliance for AI coding tools: five questions to ask before buying 2026](https://qcode.cc/en/ai-coding-data-compliance-guide): Data classification, five contract questions, and the line between verifiable and contractual.
- [AI Multi-Agent Programming Guide: Claude Code + OpenCode + Codex](https://qcode.cc/en/ai-coding-multi-agent-guide): Complete guide to AI multi-agent programming with Claude Code Agent Teams, OpenCode multi-agent architecture, and Codex parallel execution. Learn how to orchestrate multiple AI agents for complex deve
- [Complete AI Coding Tutorial: Claude Code & Cursor, Beginner to Expert](https://qcode.cc/en/ai-coding-tutorial): From beginner to master in AI-assisted coding. Learn Claude Code, Cursor and other tools, master prompt engineering, and boost development efficiency by 10x.
- [Anthropic Agent Skills Open Standard: One Format for Claude / Codex / ChatGPT](https://qcode.cc/en/anthropic-agent-skills-standard-guide): Anthropic Agent Skills (Dec 2025 open standard, adopted by OpenAI Codex/ChatGPT): SKILL.md spec, 17 official skills, cross-vendor, enterprise admin.
- [Claude Agent SDK Developer Guide](https://qcode.cc/en/claude-agent-sdk-guide): Complete developer guide for Claude Agent SDK (formerly Claude Code SDK). Python and TypeScript quickstarts, core concepts, comparison with Managed Agents, and setup via QCode.cc proxy.
- [Claude Code /design: 2026-08-17 research preview, pick an artboard then implement](https://qcode.cc/en/claude-code-design-command): Artboards in CLI/Desktop before implementation; research preview, not GA
- [Claude Code PreModelSwitch: from 2.1.251, block / confirm / annotate before a model switch](https://qcode.cc/en/claude-code-premodelswitch-hooks): 2.1.251: official hooks before a model switch, block / confirm / annotate
- [CLAUDE.md Best Practices: Project Memory & Team AI Collaboration](https://qcode.cc/en/claude-md-best-practices): Learn how to write effective CLAUDE.md project memory files and master team AI collaboration best practices. Includes templates, advanced tips, and multi-person project standards.
- [Adding/Removing Tools Mid-Conversation in Claude: mid-conversation tool changes Beta (2026)](https://qcode.cc/en/claude-mid-conversation-tool-changes): The header, supported models, cache behavior and forwarding pitfalls
- [The Composable AI Coding Stack 2026: Orchestration / Execution / Review Layers and Multi-Tool Setups](https://qcode.cc/en/composable-ai-coding-stack): Orchestration/execution/review layering, per-task model routing, one key as the base
- [Context Engineering Complete Guide 2026](https://qcode.cc/en/context-engineering-guide): Complete Context Engineering guide 2026: AI agent information architecture design. Understand the fundamental difference between Context Engineering and Prompt Engineering, and master RAG, tool defini
- [DeepSeek Harness + Cordis (2026): Developer Preview Guide](https://qcode.cc/en/deepseek-harness-guide): Official DeepSeek agent harness (dsh). Everything is a plugin on the Cordis kernel. npx @deepseek-ai/dsh web. MIT, breaking changes. Minimal mode is how Flash 0731 / Pro 0813 official benches were run
- [Harness Engineering Complete Guide 2026](https://qcode.cc/en/harness-engineering-guide): Deep dive into Harness Engineering — the hottest AI concept of 2026. From Prompt Engineering to Context Engineering to Harness Engineering, master the Agent = Model + Harness paradigm for building rel
- [Kimi K3 Self-Host vs API (2026): The Cost Ledger for 2.8T Open Weights](https://qcode.cc/en/kimi-k3-self-host-vs-api): The real deployment cost and break-even point of 2.8T open weights
- [Long Context AI Coding Guide 2026: Practical Techniques for 1M+ Windows](https://qcode.cc/en/long-context-coding-guide): 1M+ context windows are common. How to use them effectively: repo maps, cache prefixes, selective loading and anti-patterns.
- [MCP Security & Sandboxing Guide: Production Practices for AI Agent MCP Servers](https://qcode.cc/en/mcp-security-sandboxing-guide): MCP boosts AI agents but increases risks. Guide to OWASP, sandboxing, least privilege, auditing and safe multi-MCP with one QCode key.
- [MCP Server Ecosystem 2026: 13,000+ Servers and the Context-Tax Reality](https://qcode.cc/en/mcp-servers-ecosystem-2026): MCP ecosystem 2026: 13,000+ servers, 97M monthly downloads. Must-have servers, context-tax pitfall, MCP Gateway, Claude Code/Codex/Cursor integration.
- [Multi-Model Routing Guide 2026: Best Practices for Task Allocation across Claude / GPT / Gemini](https://qcode.cc/en/multi-model-routing-guide): Claude, GPT-5.6, Gemini — which to use when? Decision matrix, implementation patterns and cost optimization. Route across models with one QCode key.
- [Multi-Tool Quota Rotation: The Complete Guide to Compliantly Orchestrating Claude Code, Codex, and Cursor](https://qcode.cc/en/multi-tool-quota-rotation): How to compliantly orchestrate quota across Claude Code, Codex, and Cursor
- [OpenCode Go + DeepSeek V4 Flash/Pro (2026)](https://qcode.cc/en/opencode-go-deepseek): Official X: new V4 Flash is in OpenCode Go and Free. Ids opencode-go/deepseek-v4-flash and deepseek-v4-pro. Flash is the volume lane; Pro burns the dollar cap faster. DeepSeek ZDR: as of 2026-08-30 fe
- [Why Sub-Agents Burn a Week's Quota in 30 Minutes: The Token-Resend Mechanism and How to Reduce It](https://qcode.cc/en/subagent-quota-drain): The token-resend mechanism, usage estimation, and reduction methods
- [Vibe Coding Complete Guide 2026](https://qcode.cc/en/vibe-coding-guide): Complete Vibe Coding guide for 2026: use natural language to describe what you want and let AI generate the code. Learn what Vibe Coding is, the best tools (Claude Code, Codex, Cursor), use cases, and

## Benchmarks and leaderboards

- [The Artificial Analysis Intelligence Index Explained: How the 9 Evaluations Are Weighted and Why Scores Shift](https://qcode.cc/en/artificial-analysis-index-explained): A full breakdown of the 9 weighted evaluations and common misreadings
- [How to evaluate Ornith-1.5: a method you can run yourself](https://qcode.cc/en/ornith-1-5-guide): Judge a new model against your own work instead of public leaderboards.
- [SWE-Bench Pro 2026 Coding Model Ranking: Opus 4.7 vs GPT-5.5 vs GPT-5.3-Codex](https://qcode.cc/en/swe-bench-pro-2026-ranking): SWE-Bench Pro 2026: GPT-5.3-Codex 56.8% SOTA, GPT-5.5 58.6%, GPT-5.2 80% Verified, Opus 4.8 Fast Mode default. Scenario-based model selection guide.
- [Claude Fable 5's 80.3% on SWE-Bench Pro: Where It Came From](https://qcode.cc/en/swe-bench-pro-fable-5): Where the 80.3% figure comes from, official methodology vs. independent reproduction, and how much it should weigh in your decision
- [SWE-bench Pro's Three 'First Places' Explained 2026: 80.3 vs 80.0 vs the Official Board](https://qcode.cc/en/swe-bench-pro-first-claims): 80.3 / 80.0 / the official board: the truth about data splits and scaffolds
- [From SWE-Bench to Production: How Benchmarks Do (Not) Translate to Delivery Speed in 2026](https://qcode.cc/en/swe-bench-production-reality): 88% on SWE-Bench sounds great, but often only 30% on your private repos. Understand the gap and build your own verification harness.
- [Terminal-Bench 2.1 Leaderboards, August 2026: Three Boards, Three Winners — Which to Read](https://qcode.cc/en/terminal-bench-2-1-leaderboard): Three boards, three winners: the official 83.8 / AA 89.5 / vals 85.77 gap fully explained
- [Terminal-Bench 3.0 Explained: How It Differs From 2.1, the Current Leader, and Why Scores Dropped](https://qcode.cc/en/terminal-bench-3-guide): TB 3.0 vs. 2.1, current rankings, and which leaders are sellable

## Business and reselling

- [Invoicing and corporate payment for an AI API: VAT invoices, fees and procurement 2026](https://qcode.cc/en/ai-api-invoice-corporate-payment): Two-band VAT invoice fee, bank transfer flow, channel limits and the refund terms.
- [How to Launch an AI API Subscription Business 2026: Complete Playbook](https://qcode.cc/en/ai-api-service-business-guide): Positioning, product mix, subscription pricing, compliance, customer ops — a complete playbook to launch your AI API subscription service. Based on QCode.cc partner field data, with a 5-tier pricing t
- [AI Subscription Platform vs Self-Host 2026: Enterprise Decision Framework + TCO](https://qcode.cc/en/ai-subscription-platform-vs-self-host): Two paths for enterprise AI: subscription platform vs self-host. 12-month TCO calculations, 5-dimension scorecard (cost, time-to-launch, compliance, control, scale), recommendations by company size.
- [Paying for an AI coding API with Alipay and WeChat: channel limits, fees and settlement 2026](https://qcode.cc/en/alipay-wechat-pay-ai-api): Per-transaction caps, who absorbs the fee and settlement time across four channels.
- [Become a Claude / Codex Channel Partner — QCode.cc Partner Program Guide 2026](https://qcode.cc/en/become-claude-channel-partner): QCode.cc Partner Program guide: five wholesale tiers locked by a one-time top-up (CNY 3,000–20,000 for a 0.95–0.75 multiplier), an 8% partnership fee per top-up, your own branded domain, one key acros
- [Buying an AI coding API for a team: pooled quota, concurrency and sub-key attribution 2026](https://qcode.cc/en/claude-code-team-deployment-guide): Pooled versus daily-cap quota, per-account concurrency and headcount, and sub-key attribution.
- [Cursor Auto pricing change: what to actually check](https://qcode.cc/en/cursor-auto-pricing-change): A billing-definition checklist and a predictable-cost alternative.
- [QCode team plans: pooled Max X20 account quota and volume tiers](https://qcode.cc/en/enterprise): For teams of 3+: each Max X20 account carries a pooled $4,000/month quota — monthly reset, no daily cap — from CNY 1,800 per account per month, CNY 1,680 at 11+ accounts. Invoicing supported.
- [QCode Partner Program: five wholesale tiers for white-label API resale](https://qcode.cc/en/partner-program): Resell Claude, Codex and Gemini under your own domain: one key across three protocols, pay-as-you-go, no concurrency cap. Five tiers lock a 0.95–0.75 multiplier; 8% fee per top-up; no KYC.
- [Stripe Acquires OpenRouter for $7B+: What Changes for the AI Gateway Business](https://qcode.cc/en/stripe-openrouter-acquisition): Facts, impact and practical developer options behind the $7B+ deal.
- [Will a 24/7 Agent Eat Through Your Subscription: A Break-Even Method Based on Real Token Volume](https://qcode.cc/en/subscription-vs-api-24x7-agent): How to calculate the break-even point
- [White-Label AI Coding API 2026: OEM Claude Code & Codex Solutions](https://qcode.cc/en/white-label-ai-coding-api): QCode.cc white-label AI coding API: resell Claude, Codex and Gemini under your own branded domain with one key across three protocols, per-customer second-level keys with their own caps and concurrenc

## Reference

- [How Russian Developers Pay for AI APIs: The Real Experience With СБП, Bank Cards, and Crypto](https://qcode.cc/en/ai-api-payment-russia): СБП, Russian cards, and crypto — the three payment paths explained
- [AI Coding Tools Guide for Russian Developers 2026](https://qcode.cc/en/ai-coding-russia-guide): Complete AI coding tools guide for Russian developers: Claude Code, OpenAI Codex, OpenClaw access. SBP (Faster Payments), Russian bank cards and cryptocurrency supported.
- [AI Coding Tool Pricing 2026: Cursor/Claude Code/Antigravity/Windsurf All at $20 — Pay-per-Use or Subscription](https://qcode.cc/en/ai-coding-tools-pricing-2026): Four at $20, three at $100: after convergence, how to choose between subscription and pay-per-use
- [2026 AI Coding Updates: GPT-5.6 GA, Claude Opus 4.8, Sonnet 5](https://qcode.cc/en/ai-coding-updates-2026): Latest AI coding tool developments in 2026. Covering the GPT-5.6 (Sol/Terra/Luna) GA release, Claude Opus 4.8, Sonnet 5, Codex Security, Agent Teams, and market trend analysis.
- [US AI Safety Executive Order Explained (2026-06): The 30-Day Review Window and Release Cadence](https://qcode.cc/en/ai-safety-executive-order-2026): The 30-day review window, the voluntary framework, the open-weights exemption, and the effect on release cadence
- [Pay for AI Coding APIs with Bitcoin and Ethereum: BTC Mainnet plus 10 ETH Networks](https://qcode.cc/en/bitcoin-pay-ai-coding-api): BTC mainnet plus four kBTC networks and ten ETH networks, zero platform fee, with kBTC explained.
- [Claude Code In-Depth Comparison vs Cursor and Gemini](https://qcode.cc/en/claude-code-vs-competitors): Detailed analysis of Claude Code's unique advantages over Cursor, Gemini CLI, and GitHub Copilot. Learn why more developers are choosing Claude Code.
- [Claude Mythos 5 vs Fable 5: What's the Relationship?](https://qcode.cc/en/claude-mythos-5-vs-fable-5): Same architecture, same benchmark score; the availability and safety-routing differences, plus evidence Mythos 5 has no public pricing
- [Claude Mythos Preview — When Anthropic's Next Flagship Reaches Everyone (June 2026 Tracker)](https://qcode.cc/en/claude-mythos-preview-guide): Claude Mythos Preview explained: Anthropic launched Mythos Preview on April 7, 2026 and confirmed on May 28 that Mythos-class models will reach all customers 'in the coming weeks'. This page separates
- [Buy Claude Opus 5, Sonnet 5 and GPT Credits with Crypto: One Balance Covers All](https://qcode.cc/en/crypto-pay-claude-opus-5): Crypto tops up an ordinary USD balance that reaches every model on offer, with no payment-method tiering.
- [Crypto Payment Guide: 9 Coins, 56 Networks for Claude Code & Codex API Credits](https://qcode.cc/en/crypto-payment-guide): Nine coins, 56 networks, zero platform fee for AI coding API credits.
- [Cursor 3 Agents Window Guide 2026: Parallel Agents, $20/$40 Pricing, the SpaceX Acquisition](https://qcode.cc/en/cursor-3-agents-window): A parallel multi-agent workspace, $4B ARR, and the SpaceX $60B acquisition timeline
- [Cursor Origin: paid-plan early beta code hosting from 2026-08-17, GitHub-free start on 08-27](https://qcode.cc/en/cursor-origin-code-hosting): Paid-plan early beta from 2026-08-17; GitHub-free cold start on 08-27
- [DeepSeek Code Plan (2026): No Official Subscription — What People Mean](https://qcode.cc/en/deepseek-code-plan): There is no official DeepSeek Coding Plan / Code Plan SKU. Consumer chat is free; money is prepaid API (peak/off-peak from 2026-08-16). The query maps to: 2026 coding roadmap, a Claude-Max-like wish, 
- [DeepSeek V5 Status Tracker 2026: September Release Is a Rumor; V4's Hike and Availability Are Facts](https://qcode.cc/en/deepseek-v5-status-tracker): The September rumor has no official source; V4's price hike and in-stock status are facts
- [Windsurf Renamed Devin Desktop: the Acquisition Saga, Pricing Changes and Migration Guide (2026)](https://qcode.cc/en/devin-desktop-windsurf-rebrand): The three-owner timeline, $20/mo pricing, and migration advice
- [Gemini 3.5 Flash guide 2026: id, 1,048,576, $1.50/$9.00](https://qcode.cc/en/gemini-3-5-flash-guide): Stable id, 1M context, Standard $1.50/$9.00
- [Gemini 3.5 Flash-Lite guide 2026: id, $0.30/$2.50, 1,048,576](https://qcode.cc/en/gemini-3-5-flash-lite-guide): Stable id, Standard $0.30/$2.50, 1M context
- [Gemini 3.5 Pro: Release Date, Status and How to Access Gemini Today](https://qcode.cc/en/gemini-3-5-pro-guide): Gemini 3.5 Pro is in enterprise preview, not yet GA (rumored July 2026). The real release timeline, confirmed benchmarks, and Gemini models you can use now.
- [Gemini 3.6 Flash Guide: Specs, $1.50/$7.50 Pricing & Coding Use](https://qcode.cc/en/gemini-3-6-flash-guide): July 21 release specs, $1.50/$7.50 pricing, and cost context for coding APIs
- [Gemini 3.7 Flash Guide 2026: GA specs, intro $0.75/$3.75](https://qcode.cc/en/gemini-3-7-flash-guide): 13 Aug 2026 GA: intro $0.75/$3.75, 1M context, coding benches
- [Gemini 3.7 vs 3.6 Flash 2026: same intro, capability gap](https://qcode.cc/en/gemini-3-7-flash-vs-3-6-flash): Same intro price, coding benchmark comparison; both ids in the catalog
- [Gemini 3.7 Flash vs Claude Sonnet 5: price, window, vendor table](https://qcode.cc/en/gemini-3-7-flash-vs-claude-sonnet-5): Intro rate vs $2/$10; both listed, same endpoint
- [Gemini 4 Pro Release Tracker 2026: Pre-training Only, No SKU](https://qcode.cc/en/gemini-4-pro-status-tracker): No Gemini 4 or Gemini 4 Pro SKU yet — pre-training confirmed, 3.5 Pro delayed
- [GitHub Copilot 2026-09-01 drops Claude Sonnet 4.5/4.6 and Opus 4.5/4.6 (annual individual keeps 4.6)](https://qcode.cc/en/github-copilot-claude-deprecation-sep-2026): Copilot-wide 09-01 drop of the listed models; not the same day as Anthropic API retirement
- [GLM-5.3 Guide 2026: 14 Aug launch, same-base post-training, staged API](https://qcode.cc/en/glm-5-3-guide): 14 Aug 2026 launch: same-base post-training, Coding Plan, staged weights
- [GLM-5.3 status tracker 2026: shipped, watching API and weights](https://qcode.cc/en/glm-5-3-status-tracker): Shipped 14 Aug 2026; tracking API and weights; not listed on QCode
- [GLM-5.3 vs GLM-5.2: same base, 5.2 listed, 5.3 not stocked](https://qcode.cc/en/glm-5-3-vs-glm-5-2): Same-base post-training; 5.2 listed, 5.3 not stocked
- [Google Antigravity 2.0 Guide 2026: Five Surfaces, Default Model, Pricing and Limits](https://qcode.cc/en/google-antigravity-2-guide): Five-surface architecture, model list, $19.99/$100 pricing, and the boundaries of a closed platform
- [GPT-5.3-Codex is retired: migrating to GPT-5.6 Sol / Terra / Luna](https://qcode.cc/en/gpt-5-3-codex-guide): GPT-5.3-Codex is retired: the API returns model_not_supported and points to gpt-5.6-sol/terra/luna. Impact, tier pricing ($5/$30, $2/$12, $0.20/$1.20) and migration steps.
- [GPT-5.4 & GPT-5.4 Pro Deep Dive 2026](https://qcode.cc/en/gpt-5-4-codex-guide): Deep analysis of OpenAI's latest GPT-5.4 and GPT-5.4 Pro (released March 2026): native Computer Use, Tool Search, SWE-bench benchmarks, pricing, and head-to-head comparison with Claude Opus 4.6/4.7/4.
- [GPT-5.6-Cyber Guide 2026: What Daybreak Red Is, Who Can Apply, Pricing](https://qcode.cc/en/gpt-5-6-cyber-guide): The vetted offensive model: who can apply, pricing, and how it differs from Sol
- [GPT-5.6 Sol Ultrafast 2026: 750 tok/s preview, not a QCode tier](https://qcode.cc/en/gpt-5-6-sol-ultrafast): 750 tok/s, vendor 14×; OpenAI limited preview, not a QCode tier
- [GPT-5.7 Rumors: Release Timing, Codenames, and the 1.5M Context Claim (July 2026)](https://qcode.cc/en/gpt-5-7-guide): Not released and no published date; confirmed facts and unverified rumors kept apart.
- [GPT-6 Release Tracker: Prediction Markets, Rumors and Dated Events (updated 2026-07-30)](https://qcode.cc/en/gpt-6-guide): Unreleased with no official date; dated events plus prediction-market odds, rumors labelled.
- [GPT Image 2 Complete Guide: OpenAI's Flagship Image Generation Model](https://qcode.cc/en/gpt-image-2-guide): Complete guide to OpenAI GPT Image 2 — capabilities, official pricing, QCode proxy pricing ($0.08/call floor), API examples, use cases. 2026 flagship image model.
- [Grok 4.5 API Coding Guide: Access, Comparisons and Practical Use](https://qcode.cc/en/grok-4-5-api-guide): Grok 4.5 API coding guide: released 2026-07-08, Opus-class, $2/$6 per million tokens, Claude and GPT comparisons, access and quota hedging via QCode.
- [Grok 4.6 Guide 2026: AA 61, $2/$6, vs Opus 5](https://qcode.cc/en/grok-4-6-guide): Grok 4.6 shipped 2026-08-12. AA 61 (tie with GPT-5.6 Sol), $2/$6, 500K context. Strong long agents; DeepSWE 65.9% still behind Sol/Fable.
- [Grok 4.6 vs Claude Opus 5 (2026): AA 61 vs 63, cost & turns](https://qcode.cc/en/grok-4-6-vs-claude-opus-5): Opus 5 still leads AA (63 vs 61) and DeepSWE. Grok 4.6 is ~1/4 the output price and ~half the Briefcase turns (53 vs 103).
- [Grok 4.7 Release Tracker 2026: Date, 2.1T Specs, vs Fable 5](https://qcode.cc/en/grok-4-7-status-tracker): Unreleased Grok 4.7: founder quotes, timeline, and today's alternatives
- [Grok 4.7 vs Claude Fable 5 (2026): What Is Known Before Launch](https://qcode.cc/en/grok-4-7-vs-claude-fable-5): Pre-layout comparison: live 4.6 vs Fable 5 numbers, no fake 4.7 benches
- [Grok Bot 16G 128G (2026): Community Cloud VM Specs](https://qcode.cc/en/grok-bot-16g-128g): Grok Bot cloud computer RAM and disk: unpublished officially; early users report Debian, 8 vCPU, 16GB RAM and ~128GB disk.
- [Grok Bot Guide 2026: Cloud Teammates, $200 / $120, Shared Computer](https://qcode.cc/en/grok-bot-guide): Grok Bot early beta 2026-08-11. SuperGrok Heavy, Cursor Ultra $200, Teams Premium $120/seat. One shared cloud PC per account — not a security boundary. 16G/128G is community-measured.
- [Kimi K4 Status Tracker 2026: Training Started, Release Date and Specs All Unknown](https://qcode.cc/en/kimi-k4-status-tracker): Training started (confirmed by multiple outlets); release date and specs all unknown
- [Kimi Work Guide 2026: Desktop Agent, WebBridge, Swarm, K3 3.1.0+](https://qcode.cc/en/kimi-work-guide): Kimi Work is Moonshot’s local desktop agent for knowledge work: folders, WebBridge browser automation, Cron, Agent Swarm, finance data. Windows + Apple silicon. K3 needs app ≥ 3.1.0.
- [OpenAI Files an S-1 (2026): What a Confidential IPO Means for API Users](https://qcode.cc/en/openai-ipo-s1-2026): What the confidential filing means, the impact on API users, and hedging strategies
- [Qwen3.8-27B guide 2026: 27B multimodal, 262K, Apache 2.0](https://qcode.cc/en/qwen3-8-27b-guide): 27B native multimodal, 262K, YaRN 1M, Apache 2.0; not on QCode
- [Qwen3.8-Flash status: announced 2026-08-26 at $0.16/$0.47, not in this catalog yet](https://qcode.cc/en/qwen3-8-flash-status-tracker): Announced 2026-08-26 with a public list price; qwen3.8-flash is not in this catalog yet
- [Qwen3.8-Max guide 2026: 2.4T, $2/$6, not on QCode](https://qcode.cc/en/qwen3-8-max-guide): 2.4T MoE, $2/$6, open weights; not on QCode — use qwen3.7-max
- [Pay for AI API Usage with USDC: Solana, Base, Arbitrum and 15 More Networks](https://qcode.cc/en/usdc-pay-ai-api): 18 USDC networks, zero platform fee, with the Canton memo and Stellar muxed address explained.
- [Buy Claude Code Credits with USDT: TRC20, Solana or Arbitrum](https://qcode.cc/en/usdt-buy-claude-code-credits): 18 USDT networks, zero platform fee, with per-chain cost notes and the USDT0 pitfall explained.

## Core

- [Pricing](https://qcode.cc/en/pricing): per-model rates and the service multiplier.
- [Model catalog](https://qcode.cc/en/models): the model ids currently listed.
- [Sitemap](https://qcode.cc/en/sitemap): human-readable index of every page.

## Guide categories

- [Model guides](https://qcode.cc/en/guides/model_guide): index of every model guides page, newest first.
- [Model comparisons](https://qcode.cc/en/guides/comparison): index of every model comparisons page, newest first.
- [Pricing and cost](https://qcode.cc/en/guides/pricing_tracker): index of every pricing and cost page, newest first.
- [Errors, limits and account issues](https://qcode.cc/en/guides/troubleshooting): index of every errors, limits and account issues page, newest first.
- [Coding tools and integrations](https://qcode.cc/en/guides/tooling): index of every coding tools and integrations page, newest first.
- [Engineering practices](https://qcode.cc/en/guides/engineering): index of every engineering practices page, newest first.
- [Benchmarks and leaderboards](https://qcode.cc/en/guides/benchmark): index of every benchmarks and leaderboards page, newest first.
- [Business and reselling](https://qcode.cc/en/guides/business): index of every business and reselling page, newest first.
- [Reference](https://qcode.cc/en/guides/default): index of every reference page, newest first.

## Notes

- Model availability changes; the catalog page is authoritative over any guide page.
- Prices on guide pages are snapshots with a stated date. The pricing page is generated from live upstream data.