{"slug": "codex-gpt-5-5-plus-plan-rate-limit-cost-per-token-jumped-10x-since-june-16", "title": "Codex (GPT-5.5, Plus plan) – rate-limit cost per token jumped 10x+ since June 16", "summary": "OpenAI's Codex desktop app on the ChatGPT Plus plan has experienced a 10-20x increase in rate-limit cost per token since June 16, reducing usable prompts from 20+ to 2-3 per 5-hour budget. User logs show smaller prompts with near-zero reasoning tokens consuming 10-27% of the budget each, compared to 1% previously. The issue coincides with an active OpenAI status incident and may indicate an unannounced rate-limit change or bug.", "body_md": "-\n[Notifications](/login?return_to=%2Fopenai%2Fcodex)You must be signed in to change notification settings -\n[Fork 13.6k](/login?return_to=%2Fopenai%2Fcodex)\n\n# Codex (gpt-5.5, Plus plan) — rate-limit cost per token jumped ~10-20x since June 16, draining the 5h budget in 2-3 prompts #28879\n\n[appIssues related to the Codex desktop app](https://github.com/openai/codex/issues?q=state%3Aopen%20label%3A%22app%22)Issues related to the Codex desktop app\n\n[bugSomething isn't working](https://github.com/openai/codex/issues?q=state%3Aopen%20label%3A%22bug%22)Something isn't working\n\n[rate-limitsIssues related to rate limits, quotas, and token usage reporting](https://github.com/openai/codex/issues?q=state%3Aopen%20label%3A%22rate-limits%22)Issues related to rate limits, quotas, and token usage reporting\n\n## Description\n\n## Summary\n\nStarting ~June 16, my ChatGPT Plus Codex budget drains in 2–3 prompts on `gpt-5.5`\n\n, where the same model/plan/app previously gave 20+ prompts. My Codex session logs (`token_count`\n\n/ `rate_limits`\n\nevents) show the **limit-% consumed per token has increased roughly 10–20×**, with no change on my side — prompts are actually *smaller* now and reasoning tokens are near zero.\n\n## Environment\n\n- Codex desktop app, Windows 11\n- Model:\n`gpt-5.5`\n\n,`service_tier = \"default\"`\n\n- Plan:\n`plus`\n\n(confirmed in`rate_limits.plan_type`\n\n) - Config unchanged across the regression window\n\n## Evidence — same plan, same model, same app\n\n**June 12 (working — 20+ prompts/day):**\n\n| Prompt | Input tokens | Reasoning tokens | Primary limit % |\n|---|---|---|---|\n| 06:08 | 22,334 | 488 | 2% |\n| 06:09 | 52,161 | 1,130 | 3% |\n| 06:51 | 57,112 | 3,645 | 9% → 11% |\n| 06:54 | 79,961 | 5,125 | 15% → 16% |\n\n→ ~57K-token prompt with 3.6K reasoning ≈ **1% of the 5h budget**\n\n**June 18 (broken — 2–3 prompts):**\n\n| Prompt | Input tokens | Reasoning tokens | Primary limit % |\n|---|---|---|---|\n| 07:22:27 | 18,910 | 152 | 18% |\n| 07:22:30 | 20,480 | 0 | 45% |\n| 07:22:34 | 23,469 | 48 | 57% |\n| 07:22:43 | 23,631 | 0 | 68% |\n| 07:22:50 | 23,839 | 0 | 77% |\n\n→ ~20K-token prompt with **zero** reasoning ≈ **10–27% of the 5h budget**\n\n**Per-token limit cost changed ~10–20×.** Smaller prompts, near-zero reasoning, yet each consumes 10–20× more of the 5-hour budget than a 57K-token xhigh prompt did on June 12.\n\n## What I ruled out (verified from logs)\n\n**Not reasoning effort:** reasoning tokens are 0–152 today vs 3,645–5,125 on the good days.**Not prompt/context bloat:** input tokens dropped from 57K–80K to 18K–23K.**Not my config:**`model_reasoning_effort`\n\nwas already`high`\n\n/`xhigh`\n\non the working days (June 12–15). xhigh gave 30–40+ prompts on June 3, 12, 13, 15.**Not the weekly cap:** secondary window is only at 12%. The 5-hour window is the one draining.\n\n## Corroborating timing\n\nOpenAI status page shows an active incident ongoing ~2 days (since ~June 16), which matches exactly when my usable prompt count dropped from ~9 sessions/day to ~4.\n\n## Ask\n\nWas the Plus-tier `gpt-5.5`\n\nrate-limit budget reduced or the per-token weighting changed around June 16? If intentional, what's the new budget? If not, can it be investigated?\n\n## Session log references\n\n- Good day:\n`rollout-2026-06-12T09-07-36-019eba71-5c57-70d0-a8fa-aa999731e9ff.jsonl`\n\n- Bad day:\n`rollout-2026-06-18T10-22-14-019ed99b-ea9d-7fa1-a86b-dca4e55a8e3e.jsonl`\n\n- Rate-limit data is in\n`token_count`\n\nevents with`rate_limits`\n\npayload (fields:`primary.used_percent`\n\n,`secondary.used_percent`\n\n,`plan_type`\n\n,`resets_at`\n\n).\n\n## Metadata\n\n## Metadata\n\n### Assignees\n\n### Labels\n\n[appIssues related to the Codex desktop app](https://github.com/openai/codex/issues?q=state%3Aopen%20label%3A%22app%22)Issues related to the Codex desktop app\n\n[bugSomething isn't working](https://github.com/openai/codex/issues?q=state%3Aopen%20label%3A%22bug%22)Something isn't working\n\n[rate-limitsIssues related to rate limits, quotas, and token usage reporting](https://github.com/openai/codex/issues?q=state%3Aopen%20label%3A%22rate-limits%22)Issues related to rate limits, quotas, and token usage reporting\n\n### Type\n\n### Fields\n\n[Give feedback](https://github.com/orgs/community/discussions/189141)", "url": "https://wpnews.pro/news/codex-gpt-5-5-plus-plan-rate-limit-cost-per-token-jumped-10x-since-june-16", "canonical_source": "https://github.com/openai/codex/issues/28879", "published_at": "2026-06-20 21:43:37+00:00", "updated_at": "2026-06-20 22:07:45.480972+00:00", "lang": "en", "topics": ["ai-products", "ai-tools", "large-language-models"], "entities": ["OpenAI", "Codex", "ChatGPT Plus", "GPT-5.5"], "alternates": {"html": "https://wpnews.pro/news/codex-gpt-5-5-plus-plan-rate-limit-cost-per-token-jumped-10x-since-june-16", "markdown": "https://wpnews.pro/news/codex-gpt-5-5-plus-plan-rate-limit-cost-per-token-jumped-10x-since-june-16.md", "text": "https://wpnews.pro/news/codex-gpt-5-5-plus-plan-rate-limit-cost-per-token-jumped-10x-since-june-16.txt", "jsonld": "https://wpnews.pro/news/codex-gpt-5-5-plus-plan-rate-limit-cost-per-token-jumped-10x-since-june-16.jsonld"}}