TraceCheck.dev

Verified only

Changes

Every public entry was checked by a human against the linked official source. Pending detections never appear here.

Clear

  1. Codex
    model
    Codex now recommends GPT-6.1 Sol and adds GPT-6 Sol and GPT-6 Luna. GPT-5.3-Codex-Spark retired on September 14, and GPT-5.5 retires from ChatGPT-signed-in Codex on October 14, 2026.
    Codex models on Plus: GPT-6 Astra, GPT-5.6 Sol, GPT-5.6 Terra, GPT-5.6 Luna; Pro also GPT-5.3-Codex-Spark→GPT-6.1 Sol (recommended), GPT-6 Astra, GPT-6 Sol and GPT-6 Luna, with GPT-5.6 Sol, Terra and Luna available during the rollout. Spark retired September 14, 2026; GPT-5.5 retires October 14, 2026

    Updated pages: Codex overview · Codex usage limits · Codex pricing

  2. Codex
    usage limit
    Codex Plus limits now list the GPT-6 models: GPT-6.1 Sol 15–160, GPT-6 Sol 15–150 and GPT-6 Luna 350–3,000 local messages per five hours. GPT-5.6 Terra has no row.
    Plus approximate local messages per five hours: GPT-6 Astra 5–45, GPT-5.6 Sol 10–100, GPT-5.6 Terra 25–200, GPT-5.6 Luna 250–2,000→Plus and Standard Business approximate local messages per five hours: GPT-6.1 Sol 15–160, GPT-6 Astra 5–45, GPT-6 Sol 15–150, GPT-6 Luna 350–3,000, GPT-5.6 Sol 10–100, GPT-5.6 Luna 250–2,000

    Updated pages: Codex overview · Codex usage limits · Codex vs Claude Code: Plans and Limits

  3. Codex
    usage limit
    Codex Pro is now three plans ($100, $200 and $500 per month), and Pro plans currently have no five-hour limit. The Pro 5x and 20x message columns are gone from the usage table.
    Pro was one plan from $100/month with official 5x and 20x capacity columns of approximate local messages per five hours (GPT-6 Astra 25–225 at 5x, 100–900 at 20x)→Pro plans at $100, $200 or $500 per month. Pro plans currently have no five-hour limit; weekly limits may apply. Ultrafast mode is on Pro $500

    Updated pages: Codex overview · Codex usage limits · Codex vs Claude Code: Plans and Limits

  4. Qwen Code
    model
    Alibaba Cloud's Coding Plan, usable from Qwen Code, dropped qwen3-max-2026-01-23, qwen3-coder-next, qwen3-coder-plus and glm-4.7 from its supported models.
    qwen3.7-plus, qwen3.6-plus, kimi-k2.5, glm-5, MiniMax-M2.5; more: qwen3.5-plus, qwen3-max-2026-01-23, qwen3-coder-next, qwen3-coder-plus, glm-4.7→qwen3.7-plus, qwen3.6-plus, kimi-k2.5, glm-5, MiniMax-M2.5; more: qwen3.5-plus

    Updated pages: Qwen Code overview · Qwen Code pricing · Qwen Code usage limits

  5. Claude Code
    usage limit
    Claude Max plans now list a separate weekly limit for Fable, and usage credits can continue work after any of the three limits.
    Previous value not verified→Max plans have a separate weekly limit for Fable; usage credits can continue after the five-hour, weekly, or Fable weekly limit. Monthly API credits included with Max do not pay for usage in Claude, Claude Code, or Claude Cowork

    Updated pages: Claude Code usage limits · Claude Code Extra Usage: Credits, Caps and API Billing

  6. Claude Code
    usage limit
    Claude Code weekly limits are now permanently 25% higher than before the May–September promotion, starting September 14, 2026; the temporary +50% ended September 13.
    Claude Code weekly usage limits 50% higher from May 13, 2026 through September 13, 2026 at 11:59 PM PT; after that, weekly limits return to standard levels→Promotion ended September 13, 2026. Starting September 14, 2026, Claude Code weekly limits are 25% higher than before the promotion for Pro, Max, Team, and seat-based Enterprise plans

    Updated pages: Claude Code overview · Claude Code usage limits · Claude Code Extra Usage: Credits, Caps and API Billing

  7. Kimi Code
    usage limit
    Kimi released new membership plans: new members no longer have a weekly Kimi Code quota, and the official overview no longer publishes the 300–1,200 requests per 5 hours range.
    Approximately 300–1,200 requests per rolling 5-hour window across tiers, plus a separate Kimi Code limit of 5 hours per week→New plans (pricing unchanged): no weekly quota for new members; rolling 5-hour rate window and monthly total quota remain. Go has no coding quota; Plus and above include Kimi Code. Legacy Andante–Allegro plans keep 5 hours per week. No 5-hour request count is published

    Updated pages: Kimi Code overview · Kimi Code vs Claude Code vs Codex · Kimi Code usage limits

  8. OpenCode
    pricing
    OpenCode Go now has two tiers, Go ($10/month) and Go Plus ($40/month), and measures limits per model as a monthly dollar amount.
    OpenCode Go $10/month with base limits of $12 per 5 hours, $30 per week and $60 per month in usage value→Go $10/month and Go Plus $40/month. Limits are per-model monthly dollar amounts ($15–$60 on Go, $60–$240 on Go Plus) with 5-hour and weekly limits at 20% and 50% of each

    Updated pages: OpenCode overview · OpenCode pricing · OpenCode usage limits

  9. GitHub Copilot
    usage limit
    Copilot Business and Enterprise current pooled AI Credit allowances recorded from official org billing docs; they are not copied into Pro or Pro+.
    Seat licensing plus pooled AI Credits and optional additional usage controls.→Copilot Business: 1,900 AI Credits per user per month, pooled at the billing entity. Copilot Enterprise: 3,900 AI Credits per user per month, pooled. Completions and next edit suggestions remain unlimited and are not AI Credits. A June 1–September 1, 2026 promotional 3,000/7,000 amount for existing org customers has ended.

    Updated pages: GitHub Copilot overview · GitHub Copilot pricing · GitHub Copilot usage limits

  10. GitHub Copilot
    usage limit
    Copilot current unit is AI Credits; premium requests are historical except for remaining annual legacy plans.
    Premium requests / earlier request-based billing for model interactions.→As of June 1, 2026, current Copilot metering is GitHub AI Credits (1 credit = $0.01). Premium request units remain only for remaining annual Pro/Pro+ plans still on legacy request-based billing.

    Updated pages: GitHub Copilot overview · GitHub Copilot usage limits

  11. Kiro
    usage limit
    Kiro current unit is monthly credits; historical vibe/spec request tables are not current pools.
    Separate vibe-request and spec-request monthly allocations on older Kiro pricing posts.→Current Kiro plans meter a single monthly credit pool (Free 50; Pro 1,000; Pro+ 2,000; Pro Max 5,000; Power 10,000). Vibe and spec remain action classes that consume credits, not current request quotas.

    Updated pages: Kiro overview · Kiro pricing

  12. Claude Code
    usage limit
    Claude Code weekly limits remain temporarily 50% higher through September 13, 2026; five-hour limits are unchanged.
    Previous value not verified→Claude Code weekly usage limits 50% higher from May 13, 2026 through September 13, 2026 at 11:59 PM PT; 5-hour session limits unchanged

    Updated pages: Claude Code overview · Claude Code usage limits

  13. Codex
    usage limit
    Codex Plus approximate five-hour local-message ranges re-verified from the official Plus column; they are not a single collapsed quota.
    Unknown — current model-specific message estimates require re-verification. A shared five-hour allowance applies, and additional weekly limits may apply.→Approximate official local-message estimates per five-hour period from the Plus column: GPT-6 Astra 5–45; GPT-5.6 Sol 10–100; GPT-5.6 Terra 25–200; GPT-5.6 Luna 250–2,000. Shared pool; weekly limits may apply; estimates are not fixed limits.

    Updated pages: Codex overview · Codex usage limits

  14. Cursor
    model
    Cursor Other Models listing updated to official Fable 5.1 and Gemini 3.8 Flash; dual monthly pools remain without published numeric budgets.
    Composer 2.5; Grok 4.6; Grok 4.5; Claude Fable 5; Claude Opus 5; Claude Sonnet 5; Gemini 3.1 Pro; Gemini 3.7 Flash; GPT-5.6 Luna; GPT-5.6 Sol; GPT-5.6 Terra→Composer 2.5; Grok 4.6; Grok 4.5; Claude Fable 5.1; Claude Opus 5; Claude Sonnet 5; Gemini 3.1 Pro; Gemini 3.8 Flash; GPT-5.6 Luna; GPT-5.6 Sol; GPT-5.6 Terra. Cursor Models pool vs Other Models pool confirmed; numeric included budgets remain Unknown.

    Updated pages: Cursor overview · Cursor pricing · Cursor usage limits

  15. Codex
    availability
    GPT-5.4 and GPT-5.4 mini retired from Codex for ChatGPT-signed-in users on August 31, 2026.
    GPT-5.4; GPT-5.4 mini→GPT-5.6 Terra replaces GPT-5.4; GPT-5.6 Luna replaces GPT-5.4 mini

    Updated pages: Codex overview · Codex usage limits · Codex vs Claude Code: Plans and Limits

  16. Codex
    other
    Initial verified Codex pricing baseline recorded from the official pricing page.
    Previous value not verified→Free $0; Go $8; Plus $20; Pro from $100; Business $20/user/month billed annually

    Updated pages: Codex overview · Codex usage limits · Codex vs Claude Code: Plans and Limits

Verified software issue history

Evidence-backed state transitions from the software inventory. Dates below are the recorded transition dates; verification timestamps stay separate.

  1. Windows black screen after KB5120998 on AVD / FSLogix — Mitigated

    Microsoft records mitigation with a future resolution still pending.

    Last verified Oct 12, 2026, 1:53 AM UTC

  2. USB Audio Class 1.0 Code 10 / no sound after KB5124008 — Mitigated

    The reviewed 24H2 entry is mitigated and describes a partial September 14 fix. Its opened date is later than that update, so no earlier confirmed state is invented.

    Last verified Oct 11, 2026, 2:43 PM UTC

  3. Claude Cowork / WSL host folders missing after KB5124008 — Resolved

    Microsoft records resolution with the September 14 updates and later.

    Last verified Oct 11, 2026, 2:36 PM UTC

  4. Claude Cowork / WSL host folders missing after KB5124008 — Confirmed

    Microsoft opened the Plan9 sharing record. This is an acknowledgement timestamp, not the first device occurrence.

    Last verified Oct 11, 2026, 2:36 PM UTC

  5. Teams / new Outlook fail to launch on ARM after KB5121003 — Resolved

    Microsoft records the September 8 Windows update resolution.

    Last verified Oct 11, 2026, 2:43 PM UTC

  6. Teams / new Outlook fail to launch on ARM after KB5121003 — Confirmed

    Microsoft opened the ARM application launch record.

    Last verified Oct 11, 2026, 2:43 PM UTC

  7. NDI streaming stutters after KB5063878 — Resolved

    Microsoft records the Windows 11 24H2 issue as resolved by KB5065426.

    Last verified Oct 11, 2026, 1:33 PM UTC

  8. NDI streaming stutters after KB5063878 — Confirmed

    Microsoft opened the issue in release health.

    Last verified Oct 11, 2026, 1:33 PM UTC