Signals
Community chatter from Hacker News, Bluesky, Mastodon, Lobsters, Lemmy & GitHub issues that mentions a tracked vendor — unverified early warnings, not confirmed changes. Catch a price, limit or deprecation move before it's official, then confirm it at the source. Verified changes live on the change feed →
Unverified · community-sourced · confirm before acting
-
@alvinashcraft@hachyderm.io on Mastodon
Use the Azure OpenAI Decisions API | Microsoft Learn https:// learn.microsoft.com/azure/foun dry/openai/how-to/decisions # ai # azureopenai # openai # decisionsapi # models # gpt6luna # apis # azure # foundry
-
@alvinashcraft@hachyderm.io on Mastodon
Build more responsive apps with the Decisions API | OpenAI blog https:// openai.com/index/decisions-api/ # ai # openai # decisionsapi # gpt6luna # models # apis # gpt
-
Provider usage: show and spend Codex and Claude usage-limit resets
get-bb/bb — ### The workflow Codex (ChatGPT) and Claude subscriptions now come with usage-limit resets, even on a single account. When I hit a limit I want to see that I have a reset and spend it from bb's Provider usage card, the same place that already shows the limit I just hit. Today I have to leave bb and redeem it in the provider's own client (Codex CLI /status → Redeem reset, Claude Code /limit-reset). bb never shows that a reset exists, so they can expire unused. What happens today Provi
-
Subscription slots blocked for a usage limit stay blocked after the limit resets (OpenAI and Claude)
code-yeongyu/senpi — ## Summary A beta user (desktop 1022.1) with several saved subscription accounts, on OpenAI (login-3..login-6, all "Connected") and on Claude, reports that once an account hits its usage limit it's marked blocked and never comes back: "when usage fills up it force-disconnects, and after that it never reconnects." The same happens across providers, so this looks like the shared credential-pool/slot logic rather than one provider's adapter. Related (prior art) #2081 (closed):
-
@oludai.bsky.social on Bluesky
DeepSeek V4 Flash 0731 output tokens dropped 80% in 30 days, from $0.64 to $0.13. Open weights at that price point changes the math on inference budgets. https://olud.ai/model/deepseek-v4-flash-0731.html #AI #LLM #Pricing
-
@limitdigest.bsky.social on Bluesky
Codex and ChatGPT limits reset (Oct 23, 12:46 AM EDT) Day 18 of the 28-day run: limit reset for Codex and ChatGPT Work. Source: @thsottiaux on X limitdigest.com/resets/codex
-
[AI] Gemini free tier chỉ 20 request/ngày, cần bật billing hoặc đổi key cho prod
quocta-uranus/FlexTrip — Hiện tượng: AI (gợi ý mô tả, tranh chấp, giá) trả 500/503/504 trên prod dù local chạy được. Nguyên nhân đã xác định: Free tier chỉ ~20 request/ngày cho mỗi model; gemini-3.6-flash đã 21/20, gemini-3.5-flash trả 429. gemini-3.8-flash mất ~70s mỗi request nên gây 504 qua proxy. Đã chuyển sang gemini-3.5-flash-lite (~1.4s) ở #72/#73. Còn lại: [ ] Bật billing cho project chứa key prod (AI Studio → Set up billing) hoặc đổi key [ ] Xác nhận key trên VPS thuộc đúng project [ ]
-
backend deprecated models check - 2026-10-23
HeyPuter/puter — Automated read-only check of the hardcoded backend model lists against https://ai-models.puter.work/. A model is listed only if none of its names (id + aliases) appear in the upstream ids, names or aliases. chat/mistral (3) mistral-large-4 mistral-large-2512 zai-glm-5-3 Notes: upstream mistral has no "large" model at all. mistral-large-4 is a recent public-preview entry (release_date 2026-10-06) and may just not be in the upstream feed yet, so confirm before removing. zai-glm-5-
-
[Bug] AI Coach (Gemini) returns 404: models/gemini-2.5-pro is deprecated for new users
DuarteSantos8/openGym — ### What did you do? Generated a new API Key in Google AI Studio. Configured the AI Coach in openGym using the Google Gemini provider and pasted the API Key. Opted in and triggered an AI Coach action (e.g., workout review / coach response). What did you expect to happen? The AI Coach should successfully connect to the Gemini API and return the workout review/response. Additionally, there should ideally be a field in the UI to specify or override the model name manually. W
-
🆕 New open-weight model just dropped: MiniMax M3.1 Flash (MiniMax) Context: 1M tokens · $0.15 in / $0.6 out per 1M · open weights All the latest models, tracked hourly: https:// olud.ai/latest.html # AI # LLM # OpenSource
-
@whichaicoder.bsky.social on Bluesky
I also refreshed pricing checks for Kiro, Amazon Q, Augment Code, and Amp. You can review all the details and our rubric at https://whichaicoder.com/github-copilot-pricing/
-
@whichaicoder.bsky.social on Bluesky
I updated the pricing and model details for GitHub Copilot on WhichAICoder following recent changes. The free tier now offers 2,000 completions and 50 chat requests. Paid tiers range from Pro at $10/mo to Max at $100/mo.
-
@ctxwindow.thecompound.tech on Bluesky
Context Window · 22 October 2026 Model releases, pricing and API changes from OpenAI, Anthropic and other AI labs. Five updates, with source links below. Jordine: not a model release, not intended for use. https://huggingface.co/Jordine/rlport-hkl_jord9v_anC_pl10_20261022_083811
-
xilistudios/lele — ## Problem The bundled catalogs catalog/providers/opencode_go.json (29 ids) and opencode.json (40 ids) are mirrors of models.dev, and they are what the WebUI model picker and offline onboarding validation read. A live probe of POST https://opencode.ai/zen/go/v1/chat/completions on 2026-10-22 (all lele headers present, streaming and non-streaming) shows the catalog offers ids the gateway refuses: | id | response | | --- | --- | | minimax-m3.1-flash-free | 400 ModelDeprecated —
-
@teckhustlers.bsky.social on Bluesky
DeepSeek Launches Web Search and Page-Fetch APIs for AI Agents at $0.75 per 1,000 Calls TL;DR: DeepSeek has launched its own web search and page-fetching APIs built specifically for AI agents, pricing them at $0.75 per 1,000 successful calls, putting it in direct competition with the search…
-
OpenAI: Build more responsive apps with the Decisions API https:// ai-news.ypetit.net/?a=19b3e42p fzt&utm_source=mastodon&utm_medium=social&utm_campaign=bot # AI # OpenAI
-
OpenAI has made its Decisions API model widely available to all customers. First announced on September 29, the model reconfigures technology previously used in ChatGPT Luna to accelerate inference and lower costs. Early trial customers like Speak reported significant performance improvements, cutting action times from 1.4 seconds to 0.13 seconds. https:// en.hacks.gr/i-openai-diathetei -se-oloys-ti-nea-ypiresia-tis-gia-grigores-apofaseis/ # OpenAI # API # ArtificialIntelligence # MachineLearnin
-
anthropics/claude-code — Summary. My usage page showed a reset offer labelled "expires on Oct 22". Late on Oct 21 (Toronto time), I asked a Claude Code side chat whether I'd still have it the next day. It said probably, and after midnight said it would most likely last until about 8 PM Toronto time on Oct 22. When I went to press the reset during Oct 22, it was gone. My weekly limit then froze a multi-session build mid-task, two days before a release deadline. The weekly limit resets Oct 25, 4 P
-
@zdrojak@zdrojak.cz on Mastodon
OpenAI zveřejnilo na GitHubu open source nástroj openai-cli, oficiální příkazovou řádku pro práci s OpenAI API. Je napsaný v Go a vychází pod licencí Apache 2.0. Z terminálu teď můžete volat OpenAI API bez vlastních skriptů nad HTTP požadavky. Nástroj openai se instaluje přes Homebrew (brew install openai/tools/openai) nebo přes go install, na což potřebujete Go ve […] https://zdrojak.cz/zpravicky/openai-vydalo-oficialni-cli-pro-svoje-api/
-
@whichaicoder.bsky.social on Bluesky
If you want the full breakdown of credits and Gemini 4 Argon availability on paid plans, take a look at the updated guide: https://whichaicoder.com/github-copilot-pricing/
-
@georgesl.bsky.social on Bluesky
ChatGPT weekly usage reset on Day 17 when I have a banked reset expiring in less than 2hrs! Definitely using my OpenAI Daybreak Blue access it can burn 43% of my weekly usage limit in 23 minute session ai.georgeliu.com/p/openai-tru...! Wonder what Daybreak Red access is like though 🤓
-
OpenAI API pricing changed OpenAI shifted pricing page focus from API token rates to ChatGPT Business/Enterprise subscription plans https://changeradar.ai/tools/openai
-
Google Gemini API pricing changed Veo 3.1 video models deprecated and removed from pricing; multiple Gemini models with future price increases scheduled for 2026-2027. https://changeradar.ai/tools/google-gemini
-
[BUG] claude -p exits 1 with empty stderr when the usage limit hits
anthropics/claude-code — ### Preflight Checklist [x] I have searched existing issues and this hasn't been reported yet [x] This is a single bug report (please file separate reports for different bugs) [x] I am using the latest version of Claude Code What's Wrong? claude -p exits 1 with empty stderr when the usage limit is reached; the reason is only in stdout JSON Using claude -p --output-format json as a judge in a prompt benchmark (28 scripts, a few calls each). When the login's usage limit hi
-
stablyai/orca — ### Operating system Other Orca version v1.4.232 Details Short summary When using two separate Claude accounts across two independent projects in Orca, hitting the usage limit on the first account incorrectly triggers a usage limit error for the second account as well. However, the second account still functions normally when run independently in a terminal. What happened? I am currently using Orca version 1.4.232 with two separate Claude accounts configured across two distinct p
-
@aibuildersuse.bsky.social on Bluesky
Is Google Antigravity free? Yes, for individuals: $0, weekly agent quota, unlimited Tab completions. Google AI Pro ($19.99/mo) adds 5-hour quotas, Gemini 4 Argon and Claude 5.5. Claude 4.6 leaves the free tier Nov 2. Checked Oct 20, 2026: aibuildersuse.com/best/is-goog...
-
Azure OpenAI tts, tts-hd and whisper retire Dec 15. List your audio deployments. Check each Azure OpenAI deployment of tts, tts-hd and whisper. Microsoft has not named a model to use next. https:// timetobail.com/e/azure-openai- audio-models-retirement-2026?utm_source=mastodon&utm_medium=social&utm_campaign=azure-openai-audio-models-retirement-2026 # OpenAI # AI
-
Insight generation fails on free-tier 503s: move off gemini-3.1-flash-lite, add retry, raise timeout
SatcherInstitute/health-equity-tracker — AI insights are live to the public on prod (the flag gate came out in #5065), but when a request actually reaches Gemini rather than a cache, it fails most of the time. Caching hides this almost completely: the only requests that go live are cold cache keys, which happen after a DAG rerun moves an insight's content-hash key. Evidence Cloud Logging, 14 days ending 2026-10-22, filtering on jsonPayload.insight.outcome: | Project | generated | error | |---|--
-
Deprecated Claude model ID: claude-sonnet-4-20250514
pid1/textmaxxing — main.py:76 hard-codes model="claude-sonnet-4-20250514" (Claude Sonnet 4). Anthropic lists it as deprecated (retirement date TBD). Suggested replacement: claude-sonnet-5-5 (current Sonnet, same price tier class, 1M context). Note the API differences on Sonnet 5.5: thinking: {type: "disabled"} returns 400, forced tool_choice any/tool returns 400, assistant prefill returns 400. This app does a plain messages call, so the switch should be small, but it changes reply behavior and n
-
star: worker-probe prints ok for a worker stopped at Claude's usage limit
jrsgacusan/juel-claude — ## What happened Three build workers stopped on Claude Code's "Usage limit reached · limit resets · Continuing automatically at " screen. For about 20 minutes worker-probe.sh --item --home --worktree --deadline 45 printed ok for each, so STAR saw healthy workers. It found the stop only by reading the worker terminal's last lines with orca terminal read --terminal. Expected The probe reports a usage-limit stop as its own line, for example stalled: usage-limit until. STAR
-
@ctxwindow.thecompound.tech on Bluesky
Context Window · 22 October 2026 Model releases, pricing and API changes from OpenAI, Anthropic and other AI labs. Five updates, with source links below. mradermacher: decision-model https://huggingface.co/mradermacher/elythros-decider-1.7b-GGUF
-
@bcherny-mir-rt3.selfhosted.social on Bluesky
RT @jackhenry0001: Yeah, today I used Claude Code for just 3–4 hours, and almost 50% of my weekly limit is already gone. Bruh, I only made a few basic changes, but the token consumption is crazy today. I've never experienced this before.
-
@porcellato.bsky.social on Bluesky
LLM API Pricing Climbs as Alibaba Lifts DeepSeek Rates https://ift.tt/hGm6PDk
-
DeepSeek V4.1 Flash 1017 gives you 1M tokens context and open weights for $0.15 in/$0.6 out per 1M — a practical price for running a long-context model yourself. https:// olud.ai/latest.html # AI # LLM # OpenSource
-
@tatecole.bsky.social on Bluesky
How does Claude Duet handle concurrent sessions when the shared usage limit is nearly exhausted?
-
Same quota, twice the work — the only thing I changed was the clock. All my scheduled LLM jobs now run between 22:00 and 00:15 UTC. DeepSeek bills off-peak at exactly half price, and the GLM coding plan deducts half credits at night too. Bonus finding: 06:00–10:00 UTC is peak on both providers at once. One evening, zero code — just cron strings. # DeepSeek # GLM # LLM # DevOps
-
OpenAI is partnering with Google Cloud to offer its frontier models and Codex workflows through the cloud provider's Model Garden and Marketplace. Source: BusinessLine https://www. thehindubusinessline.com/news/ openai-partners-with-google-cloud-to-offer-ai-models-codex-workflows/article71610243.ece # AI # OpenAI # Google
-
@limitdigest.bsky.social on Bluesky
Codex and ChatGPT limits reset (Oct 22, 2:55 AM EDT) Day 17 of the 28-day run: limit reset day for Codex and ChatGPT Work. Source: @thsottiaux on X limitdigest.com/resets/codex
-
First Claude rate limit in weeks, only from testing Fable and Opus side by side. With Opus alone I barely crossed 50-60% of my weekly limit. How does Fable compare for you?
-
@harunrrayhan.bsky.social on Bluesky
কয়েক সপ্তাহে প্রথমবার Claude-এর limit hit, Fable আর Opus পাশাপাশি test করতে গিয়ে। Opus দিয়ে weekly limit-এর ৫০-৬০% পার করাই কঠিন ছিল। আপনার কাছে Fable কেমন লাগছে?
-
I didn't know limit resets are a thing in Claude Code usage. #ai
-
🌘 OpenAI API 官方命令列工具（openai-cli）說明與使用指南 ➤ 掌握 OpenAI 官方 CLI：安裝配置、指令架構與實務應用解析 ✤ https:// github.com/openai/openai-cli 本文介紹 OpenAI REST API 的官方命令列工具（openai-cli）。該工具支援透過 Homebrew 或 Go 語言進行安裝，採用資源導向的指令結構，提供完整且可離線查詢的說明系統，並具備版本更新檢查、自動補全與結構化格式輸出等功能，方便開發者有效率地在終端機中管理與呼叫 OpenAI API。 + 終於推出官方的 CLI 工具了，用 Go 語言編譯在效能和跨平臺上都相當優秀，特別是支援 JSON 格式輸出非常方便整合到自動化腳本中！ + 版本更新檢查機制設計得很貼心，不僅不會強制自動更新，還能自動識別是 Homebrew 還是 Go 安裝並提示對應的升級指令。 # OpenAI # 命令列工具 # Go語言 # API整合 # 開發者工具
-
@spaisee.bsky.social on Bluesky
Google is selling Gemini 4 Argon at $2/$10 per million tokens until Nov. 30, then doubling both rates. The real test is who stays after the discount ends. #AI #Google https://spaisee.com/article/google-s-gemini-4-argon-launch-tests-whether-safety-can-scale
-
Anthropic rate limits changed Minor formatting change: 'Usage' page reference bolded for emphasis; no numeric limit changes. https://changeradar.ai/tools/claude-code
-
💸 DeepSeek V4 Flash 0423 output price dropped 15% — $0.165 → $0.140/MTok. Compare providers, speed & capability. #LLM #AI
-
💸 DeepSeek V4 Pro 0813 output price dropped 19% — $0.990 → $0.800/MTok. Compare providers, speed & capability. #LLM #AI
-
AI routers like OpenRouter will soon need OpenAI’s permission to sell GPT models From November 20, OpenAI’s Usage Policies require model routers and AI gateways like OpenRouter to get its approval before offering access to its models. # OpenAI # OpenRouter # AI https:// madrobot.blog/2026/10/22/opena i-usage-policies-model-routers-ai-gateways-approval-openrouter/
-
ClaudeDuet, a # proactiveagent built on # Claude Opus 5.5, launches via # waitlist for US Pro and Max subscribers. It provides daily briefs, handles tasks across connected apps and a virtual machine, and requires approval before sensitive actions. https:// claude.com/resources/articles/ claude-duet?AIagents.at # AIagent # AI # ML # NLP # LLM # GenAI
-
Update ladder and hard-tier pins to remove deprecated models
quadseven/loom — Difficulty: medium Why The current ladder, hard-tier pins, and equivalents still reference deprecated models gpt-6-sol and gemini-4-argon, even though the runner no longer uses them according to the 2026-10-21 operator rule. What Update the LADDER, HARD_MODELS, and EQUIVALENTS tables to remove gpt-6-sol and gemini-4-argon references, ensuring the codex rung uses gpt-6-luna. Update documentation in docs/MUSE.md, docs/LANES.md, and docs/BRAIN.md to reflect the current ladder struc
-
ai usage on the dashboard: claude code and opencode go limits
FindMalek/keep-dashboard — i hit the 5-hour and weekly limits without seeing them coming what in FindMalek/dotfiles: a claude code status line script that shows the 5-hour and weekly usage in the terminal and posts the numbers to the keep dashboard over tailscale same for opencode go, once i know where it exposes usage (check its cli / api) keep dashboard: an "ai usage" tile per tool and per machine, with time until reset, and an ntfy alert at 80% done when the terminal shows usage without runni
-
GitHub Copilot pricing changed Free plan now explicitly includes 50 chat requests per month alongside 2,000 completions https://changeradar.ai/tools/github-copilot
-
Anthropic rate limits changed Minor wording refinements to rate limits documentation; no numeric limit changes. https://changeradar.ai/tools/claude-code
-
@monkeyscode.bsky.social on Bluesky
Why pay a $30 base fee just to unlock API list prices? Cursor unbundled frontier models behind extra fees. MonkeysCode Pro stays $20/mo: unlimited Capuchin + $20/mo frontier… https://monkeyscode.com/pricing?utm_source=bluesky&utm_medium=company&utm_campaign=story-f3572e03 #AIcoding #devtools
-
ChatGPT Go también tendrá anuncios: ¿pagar por una IA con publicidad? OpenAI está ampliando su estrategia publicitaria en ChatGPT y hay un detalle que puede generar debate entre los usuarios: la publicidad no estará limitada al plan gratuito, sino que también podrá aparecer en ChatGPT Go, la suscripción de pago más económica. Así lo indica la documentación oficial de OpenAI. Consulta la información oficial. La compañía explica que mantener ChatGPT requiere una infraestructura considerable y una
-
@ctxwindow.thecompound.tech on Bluesky
Context Window · 21 October 2026 Model releases, pricing and API changes from OpenAI, Anthropic and other AI labs. Five updates, with source links below. mradermacher: For a convenient overview and download list, visit our model page for this model.
-
OpenAI will shut off GPT-4o and GPT-4.1 API access in January. Moving to GPT-6 Luna changes tool calls, pricing for long prompts and fine-tuned models.
-
1/ Raw Token Pricing per 1M Tokens: • DeepSeek R1 (671B Reasoning): $0.5 in / $2.15 out (Cache read: $0.14) • OpenAI o3-mini: $1.1 in / $4.4 out (Cache read: $0.55)
-
@anthropicai.xmirror.bot on Bluesky
API version 2026-10-21 is now available. The Claude API has evolved a lot, but this is our first official version release since 2023. We plan to release versions more often so you can handle breaking changes before a new model requires them. 2023-06-01 is not deprecated.
-
@claudedevs-mirr.selfhosted.social on Bluesky
API version 2026-10-21 is now available. The Claude API has evolved a lot, but this is our first official version release since 2023. We plan to release versions more often so you can handle breaking changes before a new model requires them. 2023-06-01 is not deprecated.
-
Resume Claude sessions stopped by a usage limit once the rotator has a login with capacity
rysweet/amplihack-rs — ## Problem amplihack profile rotate moves the login with the most capacity into ~/.claude. Running Claude Code sessions pick up the new login on their next request, but a session whose turn already ended with "You've hit your … limit" sits idle and never retries. Newer Claude Code also shows a "What do you want to do? 1. Stop and wait for limit to reset" menu over it. On one host this left several tmux sessions stuck for hours after a login with capacity had been rotated i
-
bizimind/loxel — ## Problem When the Claude Code Review job hits the reviewer's usage limit, it fails with only a red check on the PR. The reason and the reset time are buried in the step log ("api_error_status": 429, "api_error": "usage_limit_reached", "result": "You've hit your session limit · resets 12:30am (UTC)"). The author, or an agent babysitting the PR, has to download and grep the log to learn that a re-run is pointless until the reset, and the PR otherwise looks like it simply never g
-
pingdotgg/t3code — ## What happened On the Usage page (Limits view, All environments), the Claude card showed a "Monthly spend" row with a bar for each Claude account (99% and 74% left). After I clicked the refresh button, the row disappeared. Session, Weekly, and Weekly · Fable stayed. The server still had the data: both Claude provider status caches held a monthly_spend window after the refresh. Diagnosis The hub read never produces a monthly spend window, and the client lets a newer hub read
-
github/docs — ### Code of Conduct [x] I have read and agree to the GitHub Docs project's Code of Conduct What article on docs.github.com is affected? https://docs.github.com/en/enterprise-cloud@latest/copilot/reference/copilot-billing/request-based-billing-legacy/model-multipliers-for-annual-plans What part(s) of the article would you like to see updated? I would like to remove some models that were already deprecated from GitHub Copilot GPT-4o GPT-4o mini GPT-5.1 GPT-5.1-Codex GPT-5.1-Codex-Min
-
@gorozai.bsky.social on Bluesky
Claude "Reset for free": sites and users say it expires Oct 22. Your offer shows the exact date and time. It isn't in Claude Code's terminal or IDE: use web or desktop, Settings > Usage > Resets. You can't undo it. https://support.claude.com/en/articles/17007452-what-is-a-limit-reset
-
@priyansh7.bsky.social on Bluesky
Anthropic has removed the separate Fable limits and merged them into the weekly limit. Is this a sign that Fable 5.5 is coming? 👀
-
OpenAI retires early GPT-5 snapshots, o3 and old image models. List the models you call. Search for gpt-5-2025-08-07, gpt-5-mini, gpt-5-nano, gpt-5-pro, o3, o3-pro and older gpt-image names. The first GPT-5 snapshots, o3 and o3-pro stop Dec 11. https:// timetobail.com/e/openai-gpt-5- o3-image-models-shutdown-2026?utm_source=mastodon&utm_medium=social&utm_campaign=openai-gpt-5-o3-image-models-shutdown-2026 # OpenAI # AI
-
[P2] Pricing: cursor-admin pricing (models-and-pricing) — reviewed claims changed
futurastudio/ai-spend-agent — <!-- provider-contract-alert:v1 key=resource:9cf95110e2a8bf61 --> P2 · Pricing · reviewed claims changed Reviewed semantic fingerprint changed. This page states official rates that reviewed pricing claims and estimates depend on. | | | | --- | --- | | Contract | cursor-admin · Cursor Admin API spending and usage events | | Page | pricing · https://cursor.com/docs/models-and-pricing | | Alert class | pricing | | Required markers | Models & Pricing, Usage pools, Paid
-
SHIPPED: OpenAI models now available on Google Cloud, including GPT-4o and o1. Accessible via Vertex AI API; pricing aligned with OpenAI's direct endpoints. #AI #LLM
-
A Claude usage limit switches the session to Codex while other Claude accounts have quota
syncra-studio/brigadier-ai — Seen 10-21 ~18:19 in a brigadier-ai session (branch brigadier/6ed2fe57/session). The thread hit Claude's session limit and the app said "Claude Code hit its usage limit; continuing on Codex gpt-6-astra until 19:10, then back on Claude Code." Two other signed-in Claude accounts had fresh quota at the time. The session should have kept going on Claude.
-
@spaisee.bsky.social on Bluesky
Replit now preselects OpenAI for Agent, while Anthropic remains available. That quiet UI choice may redirect more coding-model spend than a benchmark win. Distribution is becoming the product. #AI #Coding…
-
@ahiruai.bsky.social on Bluesky
OpenAIのAPIにおいて、プロンプトキャッシュの有効期間が12時間に延長されました。 何時間もアイドル状態になるエージェントでも、次のターンでキャッシュ入力価格が受けられます。 ひと言でいうと、間隔を空けて動かす自動化でもキャッシュが効き、運用の支出を抑えやすくなります。 2026年10月20日公開の情報で、長時間の休止を挟む処理に適用可能です。
-
@juliangoldie.bsky.social on Bluesky
DeepSeek V4.1 Flash is a top-tier coding model you can run for free. It goes toe-to-toe with Claude Opus 5, with open MIT weights and a 1 million token context window. Grab a free API key, drop it into your agent, and start building. Just one catch — the free key has a weekly limit. #DeepSeek
-
Quawake auto-resumes Claude Code work across usage-limit resets. It's 3.5 months old now, so it's time for the first release. I thought it wouldn't be needed anymore after Anthropic released their auto-resume feature in Claude Code on 17th of August, but I was wrong. github.com/kvistgaard/q...
-
1/ Raw Token Pricing per 1M Tokens: • Claude 3.7 Sonnet: $3 in / $15 out (Cache read: $0.3) • DeepSeek V3 (0324): $0.24 in / $0.79 out (Cache read: $0.07)
-
Price check could not read https://developers.openai.com/api/docs/pricing.md
antharmaya/tokencost — The daily price check could not use https://developers.openai.com/api/docs/pricing.md: openai pricing page: column "Short context cache writes" not found; header is: Model | Short context input | Short context output | Short context cached input | Short context 30m write | Short context 12h write | Long context input | Long context output | Long context cached input | Long context 30m write | Long context 12h write Nothing was guessed. These rows could not be verified auto
-
stablyai/orca — ### Setup Orca 1.4.230 on macOS, running on an always-on remote host (SSH/Tailscale) that hosts dozens of long-lived Claude Code sessions in separate worktrees, including unattended overnight runs. Multiple managed Claude accounts. Problem When the active Claude account hits its usage limit, an external watcher switches the active account through the accounts.selectClaude RPC. Only newly launched sessions use the new account. Already-running sessions stay on the old profile and s
-
[delphi:rfp] gemini.free — Gemini API free tier
timerloggedout-spec/termux-monorepo — ### Surface id gemini.free Lane model Filed by (collaboration lane) delphi Gantt plan oracle facts | T0 | T0 | - panel rounds | T0 | T0 | oracle facts shadow lane (5% traffic) | T0+1d | T0+7d | panel rounds promote or park | T0+7d | T0+7d | shadow lane Free quota RPM/TPM/RPD per model: (no fetched page states a number) per-model — source https://ai.google.dev/gemini-api/docs/rate-limits Reset and zone midnight America/Los_Angeles (daily (RPD)) Auth from Acti
-
@CuratedHackerNews on Mastodon
Alibaba hikes DeepSeek V4 Flash 0731 output prices by 230% https://www. stork.ai/newsletter/2026-10-20 -alibaba-quietly-tripled-deepseek-prices#lead # ai # deepseek
-
@aiatlasresearch.bsky.social on Bluesky
OpenAI added 12-hour prompt caching to the Responses API. Cached input is billed at cached-input pricing. Cache writes cost 2.5 times the input token price.
-
robhunter/agentdeals — ## Defect /ai-coding-tools-pricing (about 40 readers a week and rising; Claude Code, claude.ai and ChatGPT) answers the FAQ "Is GitHub Copilot still the cheapest AI coding tool?" with: Yes — Copilot Pro at $10/month is the cheapest paid plan among the tools compared here. The same page lists two cheaper paid plans: Cursor Plus at $8/month (Cursor's entry plan for new subscribers since 2026-10-12) and ChatGPT Go at $8/month, which includes Codex. The text is hand-typed in s
-
LLM API prices on TANDIU, Oct 21 (per 1M tokens): · New: MiniMax M3.1 Flash $0.15/$0.60 (½ of M3), 1M ctx; LiveBench 2.0 73.1 · 70 models; no other official list-price changes · Cheapest: Hunyuan A13B ¥0.5/¥2 · Priciest: GPT-5.5 Pro $30/$180 https://www. tandiu.cn/en/token-market # LLM
-
@pricingdiff.bsky.social on Bluesky
Bolt.new is not showing everyone the same price. Loading their pricing page daily for 66 days returned $9 on some visits and $25 on others - 3 switches, back and forth. One page load cannot reveal this. The number looks fixed. https://pricing-diff.netlify.app/price-testing/
-
core: rateLimitOf carries the quota Gemini names (size, unit, free tier, model)
amenophis1er/byok — rateLimitOf reads Gemini's QuotaFailure only to tell a minute window from a day window. The same violation says more, and a caller needs it to word the failure: { "@type": "type.googleapis.com/google.rpc.QuotaFailure", "violations": [{ "quotaMetric": "generativelanguage.googleapis.com/generate_content_free_tier_requests", "quotaId": "GenerateRequestsPerDayPerProjectPerModel-FreeTier", "quotaDimensions": { "location": "global", "model": "gemini-2.5-pro" }, "quotaValue": "50" }
-
China's DeepSeek widens its open-source footprint: DeepInfer, a new repo under the deepseek-ai GitHub org, is described as a high-performance, large-scale inference framework for DeepSeek models — +12,017 stars already on GitHub trending. Inference efficiency turns a strong model into an affordable product: pricing, latency and scale all hinge on this layer. Opening it up is classic DeepSeek — compete on openness. # DeepSeek # AI # OpenSource # LLM https:// github.com/deepseek-ai/DeepInf er
-
@koltregaskes.bsky.social on Bluesky
I don't quite follow the Gemini 4 Argon weekly limit. It says 0% here, but when I select the model in Antigravity, it immediately says my quota will refresh on the 25th of October.
-
@remixtures@tldr.nettime.org on Mastodon
"The addition of locked chats adds a new layer of privacy to ChatGPT, as the app is increasingly used for personal conversations. Of course, while locking a chat can limit access, it doesn’t address concerns about how sensitive information is stored or handled. OpenAI notes that locking a chat doesn’t create end-to-end encryption or a separate encrypted vault, change how long it retains the chat, remove information that ChatGPT remembered before a chat was locked, or change the “Improve the mode
-
@ctxwindow.thecompound.tech on Bluesky
Context Window · 20 October 2026 Model releases, pricing and API changes from OpenAI, Anthropic and other AI labs. Five updates, with source links below. HYU-NLP-EVA2: Base model: Qwen/Qwen2.5-7B-Instruct, revision. https://huggingface.co/HYU-NLP-EVA2/qwen2.5-7b-ruscarl-baseline-261019-step-010
-
happier-dev/happier — ### Summary A Claude session stopped making progress after repeated provider usage-limit responses and an account change inside one Connected Services pool. The pool selected a connected replacement profile, while session metadata still recorded the previous member. No usable recovery attempt was exposed. Explicitly applying the already-selected member through the daemon switch coordinator, followed by one continuation, recovered the same native conversation without restart
-
@feed@igeek.gamer-geek-news.com on Mastodon
📰 ChatGPT now lets you lock sensitive chats behind a PIN OpenAI has introduced a new "locked chats" feature to protect users' more sensitive conversations with ChatGPT. 📰 Source: Engadget - Technology News & Expert Reviews 🔗 Link: https://www.engadget.com/2292365/chatgpt-now-lets-you-lock-sensitive-chats-behind-a-pin/ # ChatGPT
-
FYI: DeepSeek prices web search for AI agents at $0.75 per 1,000 calls #DeepSeek #AI #WebSearch #Pricing #ArtificialIntelligence
-
@marketingnews.bsky.social on Bluesky
FYI: DeepSeek prices web search for AI agents at $0.75 per 1,000 calls #DeepSeek #AI #WebSearch #Pricing #ArtificialIntelligence
-
Slow-Inc/MangaDock — ## Bug (EN) Where: Frontend/app/lib/translateDescription.ts (used by the home hero, BookRow, ContinueReadingRow, BookDetailModal). What happens: only successful translations are cached. When the backend answers translated: false (LLM unavailable, quota, nothing to translate) the function throws, cacheOrFetch stores nothing, and the next call fetches again. The home hero carousel calls it on every slide, so an open home page re-requests the same descriptions every ~5 s. Measu
-
OpenAI is rolling out a chat-locking feature across ChatGPT accounts to protect sensitive conversations on shared devices. Locked threads are removed from standard lists, search, and pinned chats, with access protected by a four-digit PIN or mobile biometrics like Face ID or fingerprint recognition. While the feature hides titles and contents from casual onlookers, OpenAI notes it retains access to locked chats and ma… https:// en.hacks.gr/to-chatgpt-apokta- dynatotita-kleidomatos-synomilies-me-
-
OpenAI Evals, reusable prompts and Agent Builder shut down Nov 30. Copy your evals before Oct 31. After Oct 31 they are read-only. https:// timetobail.com/e/openai-evals- prompts-agent-builder-shutdown-2026?utm_source=mastodon&utm_medium=social&utm_campaign=openai-evals-prompts-agent-builder-shutdown-2026 # OpenAI # AI
-
@mstimaj.bsky.social on Bluesky
A thing worth knowing about the effort setting in Claude Desktop: the top one is marked four times or more usage. Higher effort means a more thorough answer. It also takes longer and eats your limit faster. Medium is what it recommends, and it is the one to leave alone until you have a reason.
-
DeepSeek API pricing changed Clarification that deepseek-flash model is now served by DeepSeek-V4.1-Flash-1017 with unchanged calling method. https://changeradar.ai/tools/deepseek
-
Claude Sonnet 4.5 retires on the Claude API on Nov 30. Find calls to the old model. Search your code and settings for claude-sonnet-4-5-20250929. https:// timetobail.com/e/claude-sonnet -4-5-retirement-2026?utm_source=mastodon&utm_medium=social&utm_campaign=claude-sonnet-4-5-retirement-2026 # Anthropic # AI
-
Mistral AI wypuścił Voxtral 3 – model transkrypcji, model syntezy mowy i SDK na bazie LiveKit, które razem obsługują rozmowę głosową od słuchania po odpowiedź. Firma stawia na wdrożenia we własnej infrastrukturze i API hostowane w UE. # si # ai # sztucznainteligencja # wiadomości # informacje # technologia https:// aisight.pl/agenci-ai/mistral-v oxtral-3-agent-glosowy/
-
jimmycgz/challenge2-117 — ## Overview & Live Model Validation Per team decision, @jimmycgz is upgrading the ADK agent reasoning model from deprecated gemini-2.5-flash to gemini-3.8-flash. We validated gemini-3.8-flash directly against Vertex AI in our Qwiklabs project (qwiklabs-gcp-04-6c7101c1dba1) including function calling (lookup_shelf_life). Assignee: @jimmycgz (owner: jimmycgz) Status: 🔴 status: in-progress (needs-pickup — @jimmycgz to mark complete once deployed) --- Live Vertex AI Valida
-
@spicymilktea.bsky.social on Bluesky
work on a site long enough and eventually you get the "attie couldn't finish this turn" error. it's not a usage limit. unless attie allows 3rd party tools (claude code) or adds the ability to start a new chat in the same project, any site that goes on long enough can hit this and then it's all over.
-
GitHub Changelog:GitHub Copilot models deprecated on October 19, 2026
forks-felickz/github-changelog-reader — # GitHub Copilot models deprecated on October 19, 2026 <!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN" "http://www.w3.org/TR/REC-html40/loose.dtd"> As of today, October 19, 2026, we have deprecated the following models across most GitHub Copilot experiences (including Copilot Chat, inline edits, ask and agent modes, and code completions). These deprecations were announced on September 18, 2026. Model Deprecation date Suggested alternative Gem
-
@kimbodo.bsky.social on Bluesky
Copilot now mixes provider-priced and local model paths. Claude Haiku 5.5 uses provider list pricing; Copilot CLI finds local Ollama models but requires session opt-in. Sandboxing is GA, while context-aware detection can flag likely secrets without standard token formats. Read more on Kimbodo:
-
GitHub Changelog:GitHub Copilot models deprecated on October 19, 2026
renefritze/github-changelog-reader — # GitHub Copilot models deprecated on October 19, 2026 <!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN" "http://www.w3.org/TR/REC-html40/loose.dtd"> As of today, October 19, 2026, we have deprecated the following models across most GitHub Copilot experiences (including Copilot Chat, inline edits, ask and agent modes, and code completions). These deprecations were announced on September 18, 2026. Model Deprecation date Suggested alternative Gemini
-
Azure OpenAI o1, o3, o3-mini and o4-mini retire Nov 19. List your deployments. Check each Azure OpenAI deployment: model, version and deployment type. gpt-4o 2024-05-13 follows on Dec 9. https:// timetobail.com/e/azure-openai- o-series-retirement-2026?utm_source=mastodon&utm_medium=social&utm_campaign=azure-openai-o-series-retirement-2026 # OpenAI # AI
-
🔴 Breaking Change: GitHub Copilot models deprecated on October 19, 2026
sujithq/updates — ## GitHub Copilot models deprecated on October 19, 2026 Source: GitHub Changelog Severity: CRITICAL Published: 2026-10-19T21:27:10+00:00 Deadline: ⏰ 2026-10-19 Impact Specified Copilot models are deprecated across most Copilot experiences. Recommended Action Move workflows to supported Copilot models immediately. Full Summary As of today, October 19, 2026, we have deprecated the following models across most GitHub Copilot experiences (including Copilot Chat, inline edits, ask a
-
[product-watch] GitHub Copilot models deprecated on October 19, 2026
shariqh/github-enterprise-settings-configurator — <!-- product-watch:key:7165bd772b7538c8bf5c6113 --> <!-- product-watch:fingerprint:850da14a57c02c9645be72abebcbfa4dd6180baa740427ad361dbd20a4d744b2 --> <!-- product-watch:managed --> Product-change review This is a deterministic review candidate. The automation does not edit catalog, recommendation, persistence, scoring, or application code. Source evidence | Field | Value | | --- | --- | | Source | GitHub Changelog | | Entry | GitHub Copilot mod
-
DeepInfer: DeepSeek open sources their infra stack that makes their pricing so competitive DeepSeek is steadily open sourcing their entire stack, free for all github.com/deepseek-ai/...
-
[FEATURE] Hide deprecated models from /v1/models by default, list them with?include=deprecated
inference-gateway/inference-gateway — /v1/models relays each provider's catalog as-is, and operators filter it with ALLOWED_MODELS / DISALLOWED_MODELS. Several of our providers (OpenAI, Mistral, MiniMax, DeepSeek, Google) keep deprecated models in their listing, so clients discover models that are about to disappear. PR #792 proposed a MiniMax-only hardcoded list in providers/core plus a provider check in the handler. That does not scale and was closed. Proposal: sync models.dev's status field i
-
@deployedbyai.bsky.social on Bluesky
THE DEPLOY LOG: 31 AI DEPLOYS ON THE RECORD FOR OCT 19, 34 SO FAR THIS WEEK MOST READ: AZURE: BROWSER AUTOMATION TOOL IN MICROSOFT FOUNDRY NOW GA VERCEL: MERCURY 3 ON AI GATEWAY, 50% OFF LAUNCH PRICING, 1M CONTEXT OPENAI: OPENAI-NODE V7.39.0 ADDS OPT-IN BOUNDED CONNECTION RECOVERY FOR REALTIME
-
GitHub Changelog:GitHub Copilot models deprecated on October 19, 2026
abirismyname/github-changelog-reader — # GitHub Copilot models deprecated on October 19, 2026 <!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN" "http://www.w3.org/TR/REC-html40/loose.dtd"> As of today, October 19, 2026, we have deprecated the following models across most GitHub Copilot experiences (including Copilot Chat, inline edits, ask and agent modes, and code completions). These deprecations were announced on September 18, 2026. Model Deprecation date Suggested alternative Gemi
-
Codex is doing this for last whole week... every morning you wakeup with 100% weekly limit remaining no matter what it was last night 80, 50, 10 any even 0 and no matter how many days you have left for the week...
-
Is Claude Code support still needed now that Claude Code auto-continues at usage limits (2.1.234+)?
saaranshM/unsnooze — Claude Code now has a built-in "continue automatically at usage limit" feature. Is unsnooze's Claude Code support still needed, and if so for which cases? What Claude Code ships From the Claude Code CHANGELOG: 2.1.234 - "Claude Code now continues your session automatically when a claude.ai usage limit resets; turn it off in /config ("Continue automatically at usage limit")" 2.1.269 - "Fixed /goal runs silently stalling after API errors, network drops, or token limits: the go
-
OpenCode表示，黑客侵入了与其托管Console相连的一套旧系统，可能导致1.4%的Console用户的AI服务商密钥泄露并引发未授权扣费，相关退款工作目前正在进行中。 https:// harava.news/zh/articles/2026/1 0/20/opencode-console-breach # OpenCode # OpenCodeConsole # API密钥 # 未授权扣费 # AI服务商 # OpenAI [AI]
-
@limitdigest.bsky.social on Bluesky
Codex and ChatGPT limits reset (Oct 20, 2:33 AM EDT) Day 15 of the 28-day run: limit reset for Codex and ChatGPT Work. Source: @thsottiaux on X limitdigest.com/resets/codex
-
[source] GitHub Copilot models deprecated on October 19, 2026
steveash/hitchhikers-guide-to-ai-native-engineering — ### Source URL https://github.blog/changelog/2026-10-19-github-copilot-models-deprecated-on-october-19-2026 Source Type documentation What's interesting about this source? Auto-discovered from trusted feed github-copilot (GitHub Copilot changelog — Copilot-specific feature changes and updates). Feed: https://github.blog/changelog/feed/?label=copilot Entry title: GitHub Copilot models deprecated on October 19, 2026 Published: Mon, 19 Oct 2026
-
📰 Latent — OpenCode keys stolen; diffusion LLM hits 1,068 tok/s • OpenCode platform breached, users' API keys stolen • One hacker, 100+ sites, an army of mostly autonomous agents • Microsoft: treat employee-used AI agents like insider threats • Inception's Mercury 3 diffusion LLM claims 1,068 tokens/second • MiniMax M3.1 Flash: 428B MoE at $0.15/M input Today's AI briefing → https:// latent.steenbergen.ai/archive/ 2026-10-20/ # AI # MachineLearning # TechNews
-
💸 DeepSeek V4 Pro 0423 output price dropped 21% — $1.91 → $1.50/MTok. Compare providers, speed & capability. #LLM #AI
-
💸 DeepSeek V4 Flash 0731 input price dropped 25% — $0.0069 → $0.0052/MTok. Compare providers, speed & capability. #LLM #AI
-
@dunkybot.bsky.social on Bluesky
GitHub Copilot CLI: They Retired Six Ways to Disagree Six models were deprecated on schedule today — and the replacement map folds them into two. When both halves of a pair wake up as the same model, agreement s… https://theagentpost.co/posts/review-github-copilot-they-retired-six-ways-to-disagree
-
@DailyCyberSecurity@infosec.exchange on Mastodon
The OpenCode security breach may have exposed stored third-party API keys for 1.4% of Console users. Revoke and rotate keys now. # OpenCode # SecurityBreach # APIKeys # AIDistillation # OpenCodeConsole # Anthropic # OpenAI # Google https:// securityonline.info/opencode-s ecurity-breach/?utm_source=mastodon&utm_medium=jetpack_social
No signals match these filters.