Ibot "🐉 $MON" Tabi 🟧

n0thing 'Reddio' ꧁IP꧂ $MYTH

[roman @Nozelcode]

CLAUDE PUEDE ENCONTRAR TRABAJO POR TI

Un científico danés programó a claude para que busque trabajo por él y lo acaba de hacer público.

Mandar CVs es uno de los trabajos más absurdos del mundo: copiar, pegar, adaptar, personalizar, repetir.

Todo manual, todo lento, todo para que lo lea un algoritmo antes que un humano.

Este sistema:

→ Analiza la oferta de trabajo automáticamente
→ Genera un CV personalizado para cada puesto
→ Redacta la carta de presentación adaptada al contexto
→ Todo lo hace Claude por debajo, sin que toques nada
→ Open source, ya en +32K stars en GitHub

El tío que debería estar buscando trabajo ha construido la herramienta que lo busca por él.

Aquí te explico cómo usarlo 👇
(repo al final del hilo)

[Atenov int. @Atenov_D]

FREE GPT-5.6 SOL AND CLAUDE OPUS 4.8. NO CARD REQUIRED. UNLIMITED USAGE PLUS 800 CREDITS ON TOP.

It's hiding inside Postman's Enterprise trial - the API testing tool most people already have installed, not some sketchy new site.

A proper professional IDE underneath it too, not a stripped-down web chat. Fat limits across the board.

Setup:

→ Go to postman(.)com
→ Sign up, temp email works fine
→ Top right corner, hit Upgrade
→ Pick Enterprise, click Start Trial
→ Fill in random values to start the trial
→ Download the official IDE from
→ Log in with your new account

That's it. GPT-5.6 Sol and Opus 4.8 running inside a real desktop IDE, unlimited, zero payment info anywhere in the flow.

Bookmark this before they patch the Enterprise trial loophole.

[鸟哥 | 蓝鸟会🕊️ @NFTCPS]

开盒工具又更新啦，不要轻易使用！

一条命令，就能把某人网上的马甲全给你扒出来，想想都后背发凉😅

Sherlock，100%免费开源，你丢一个用户名进去，它就去400多个社交平台和网站挨个找，看看这名字都注册过哪。

它能干这些：
1️⃣ 一次搜一个或者好几个用户名
2️⃣ 只给你留真实存在的号，不整虚的
3️⃣ 结果能导成TXT、CSV、Excel
4️⃣ 只想查某些平台，也能自己挑
5️⃣ 搜完自动帮你存好

搞OSINT、网络安全、威胁调查的基本都在用它，GitHub都88,200多星了。

https://t.co/PRtHQ0xLUh

[roman @Nozelcode]

ACABO DE ENCONTRAR UNA API QUE REGALA 10 MILLONES DE TOKENS AL MES

Claude Opus 4.8, GPT 5.5, DeepSeek V4, Kimi K2.6 y más de 340 modelos.

Sin tarjeta de crédito.
Solo iniciar sesión con Google y configurarlo en 2 minutos.

Esto es lo que ofrece What Runtime de Bad Theory Labs:

• 10 millones de tokens gratis al mes con su router inteligente btl-2, que elige automáticamente el mejor modelo para cada tarea.

• Acceso a Claude Opus 4.8, GPT 5.5, DeepSeek V4 Pro/Flash, GLM 5.2, Kimi K2.6, Gemini, Llama, Qwen y más de 340 modelos.

• DeepSeek V4 Pro y Flash gratis durante la promoción de lanzamiento.

• API compatible con OpenAI. Solo cambias la URL base y funciona con prácticamente cualquier herramienta.

Esto puede sustituir varias suscripciones:

ChatGPT Plus → 20 €/mes
Claude Pro → 20 €/mes
Cursor Pro → 20 €/mes
Perplexity Pro → 20 €/mes

Todo por 0 €.

Cómo conseguirlo (2 minutos):

1. Entra en https://t.co/I0TADcAyuk
2. Regístrate con Google (sin tarjeta)
3. Completa el onboarding
4. Recibirás los créditos gratis automáticamente
5. Copia tu API Key (empieza por BTL_)
6. Configura la Base URL: https://t.co/tfi4BlaxRF
7. Selecciona el modelo btl-2 para que el router elija automáticamente el mejor modelo en cada petición.

Es compatible con Cursor, Aider, Hermes Agent, OpenCode, OpenClaw, LangChain y cualquier herramienta compatible con la API de OpenAI.

Importante: el plan gratuito es una promoción de lanzamiento y puede cambiar cuando aumente el número de usuarios.

Además, tiene límites de uso, por lo que no está pensado para cargas de producción muy intensivas.

Mientras otros siguen pagando 20€ al mes por usar un único modelo, aquí tienes acceso a Claude + GPT + DeepSeek + GLM y cientos de modelos más sin pagar nada.

Guárdate este post antes de que cambien el plan gratuito.

[Yash Agrawal @YashAg946]

7 FREE Gemini models are now available on Airouter!

✅ Gemini 3.6 Flash
✅ Gemini 3.5 Flash
✅ Gemini 3.1 Flash Lite
✅ Gemini 3.1 Pro Preview
✅ Gemini 2.5 Flash Lite
✅ Gemini 2.5 Flash
✅ Gemini 2.5 Pro

👀 Coming soon: a single free endpoint.

If one free model is rate-limited, Airouter automatically routes your request to another available model.

One endpoint. Zero switching.

🌐 https://t.co/zcajR9Lhvl

#AI #Gemini #LLM #Developers #BuildInPublic

[Atenov int. @Atenov_D]

FREE Fable 5, Opus 4.8, Sonnet 5, and GPT-5.6 in one IDE. Alibaba built it, 520 credits at signup - one Sonnet 5 message eats 4.

It's called Accio. Web or Windows desktop, both free. Registration takes 30 seconds via Google or email.

Inside:

→ Fable 5 for creative and long-context work.
→ Opus 4.6 through 4.8 - the full Anthropic frontier lineup.
→ Sonnet 5 for speed and reasoning at pennies per message.
→ GPT-5.5 for OpenAI native tasks.
→ Gemini 3.1 Pro and 3.5 Flash for multimodal.

Real math: 520 credits divided by 4 = 130 Sonnet 5 messages in your first week. Cheaper models drop that even further.
Anthropic charges $20/month for the same access with weekly limits.

Custom MCP support built in. Profile > Settings > MCP. Every agent workflow you've built for Claude Desktop ports over instantly.

Setup:

→ Go to accio(.)com
→ Sign up with Google
→ 520 credits land automatically
→ Pick your model and start firing prompts

Bookmark this before Alibaba puts it behind a paywall.

[Atenov int. @Atenov_D]

FREE access to Opus 4.8, GPT-5.5, Sonnet 4.6, plus the best models for image, video, 3D, music, and code - all under one login. 500 credits free.

It's called GabAi.

Your buddy pays $20 for ChatGPT, $20 for Claude, $30 for Midjourney, $20 for Runway. You get every top model in one chat. No card. No sub.

Setup, 4 steps:

→ Go to gab(.)ai and sign up with a real Google account (no aliases, they get blocked)
→ Get 150 credits at signup
→ Complete the on-screen tasks - unlocks another 300-400 credits
→ Pick your model. 1 credit per message. Different models cost different rates

Inside:

- Fable 5, Opus 4.6 through 4.8, GPT-5.5, Sonnet 4.6, GLM 5.2, Kimi K2.6, and more.
- Best-in-class image, video, 3D animation, and music generation models.
- Import memory from ChatGPT or Claude - your context follows you.
- Ready-made templates: chat with a PDF, transcribe meetings, analyze CSVs, review code, compare contract diffs, translate documents, build custom agents.

Bookmark this before they add a waitlist.

[Student Offers @StudentOffersHQ]

$100 in free Microsoft Azure credits. No card.

What most people don't know: you get a fresh $100 every year until you graduate.

Re-verify with your school email each year — that's ~$400 across a 4-year degree.

What students actually build with it:
• A portfolio or personal site that stays live 24/7
• Discord bots, APIs and side projects that never sleep
• Real AI apps with Vision, Speech, Translator & Document Intelligence
• Databases and backends for full-stack apps, all free

One catch: you can't deploy Azure OpenAI/Foundry models on the student plan — but the classic AI services above all work.

And 65+ services stay free forever, even after the $100 runs out.

(Not a student? Public free account gives $200 credit, but for 30 days only + needs a card.)

[kaize @0x_kaize]

Free AI API credits & $4,000 right now

This is a limited-time offer, so you should create your accounts before it ends

1/ https://t.co/4uQXiHGjwU - claims $4,000 credit

Models: DeepSeek v4 flash, GLM-4.7

2/ https://t.co/W1e4juhslF - 100k credits (3-day window)

2,000+ open models, OpenAI-compatible

3/ https://t.co/beshLhjQEP - 3M credits on signup

Models: Sonnet 4.6, DeepSeek v4 pro

Also, If you want to use GPT-5.6 Sol, Terra, and Luna at the highest quality:

1. Go to: https://t.co/3p3Q5k7GUn
2. Sign up and select 'Agents' from the left-hand menu
3. Click: Create your first agent

Really like how they work on this service.

[Student Offers @StudentOffersHQ]

$500+ worth of paid AI models. Free. No card.

Access GLM 5.2, Kimi K2.7 Code, DeepSeek V4 Pro & flash, Qwen3.7 Max and more.

Qwen Cloud has the most generous AI free tier going:
→ 246 models: LLM, vision, voice, video
→ 1M tokens on each of 120+ LLMs
→ Free for 90 days

How to claim:
1. Sign up at Qwen Cloud
2. Free tier activates automatically, no card
3. Grab your API key, start building

1M per model runs out fast, so put LiteLLM in front. One endpoint that tracks every quota and auto-switches models when one runs dry.

Plugs into any coding agent — Claude Code, Codex, Cursor, Hermes, OpenClaw & more.

[Student Offers @StudentOffersHQ]

GLM-5.2. Claude Opus 4.8. GPT-5.5. & more. All free.

$26 in free credits to start — $25 on signup, $1 bonus on top.

Inference․net puts every frontier model behind one key. Claude, GPT and Gemini included.

Big models burn the $26 fast. Cheap tiers stretch it.

Works with Codex, Cursor, OpenCode, OpenClaw, Hermes, and any OpenAI-compatible client.

One thing to know: card's needed to open the dashboard + make keys. Pay-as-you-go, but the $26 covers you first — use it up, swap keys, done.

[Chuks @savemeChuks]

nvidia just added GLM-5.2 FREE API endpoint to their builders dashboard

frontier model by z-ai with 1M context window.

where you can apply this:
— cline
— continue
— cursor
— any openai compatible client.

use cases:
— agentic coding (write & debug codes)
— research & brainstorm tasks
— agentic workflow

how to setup:

1 —
visit: build(.)nvidia(.)com/z-ai/glm-5.2
create an account or sign in

2 —
generate api key

3 —
setup in your client

> base url: https://integrate(.)api(.)nvidia(.)com/v1
> api provider: openai compatible
> api key: nvidia glm key

4 —
done

this should be a good addition to free llm users.

[Meliasih @meliasiih]

Ayok bang claim API key GLM-5.2 gratis.

=> https://t.co/ilBnCT1HqW

Base URL: https://t.co/hmeIBBZvAC

Spam spam aja nanti juga dapet

[K2S @k2sbhai]

found an API provider giving away 10M free tokens every month across 340+ models 😳

no credit card
no subscriptions
just a Google login and 2 minutes to get started

what you get for $0:

- 10M free tokens/month on the btl-2 smart router
- Claude Opus 4.8, GPT-5.5, DeepSeek V4, GLM 5.2, Kimi K2.6, Gemini, Qwen, Llama, and 340+ models
- DeepSeek V4 Pro and Flash completely free during the launch promo
- OpenAI-compatible APIs that work with your existing tools

why this is huge:

> no paying $20/month for a single AI subscription
> no juggling multiple API providers and keys
> no changing your workflow beyond a base URL swap

getting started takes less than 2 minutes:

1. go to https://t.co/PaHlEL3qOi
2. sign in with your Google account
3. complete the onboarding steps
4. claim your free credits
5. copy your BTL API key
6. set your base URL to https://t.co/NmshbIh64o
7. use btl-2 for automatic model routing

pro tip:

use the btl-2 router instead of picking models manually it automatically selects the best model for each task and stretches your free credits further

the best part?

one free account gives you access to hundreds of models that would normally require multiple paid subscriptions

works with Cursor, Aider, Hermes Agent, OpenCode, OpenClaw, LangChain, and anything that supports the OpenAI API format

free credits are part of the launch promo, so enjoy them while they last

bookmark this and claim your free API key before the free tier changes 👀

[Student Offers @StudentOffersHQ]

Students get Figma Pro free. The $20/mo plan at $0.

Yeah it's the design tool everyone uses for UI and prototypes, but in 2026 it's basically an AI workstation:

→ 3,000 AI credits/mo worth ~$90 if you bought them, running Claude Opus, Gemini 3.1 Pro, GPT-5.5
→ Figma Make: prompt a full UI, wire a working web app, ship it to a live figma .site link
→ Dev Mode MCP: pipe designs into Claude Code, Cursor and Copilot, agents write back to canvas too

All of that is paid-tier stuff you get for $0 with a student email.

[Student Offers @StudentOffersHQ]

GLM-5.2. Kimi K2.7 Code. DeepSeek V4 Pro. MiniMax M3. & more.

10 coding models, one tool, $1.99 for the first month.

It's called ClinePass, runs inside @cline. Tried it today and it's smooth, didn't hit a single error.

For basically $2 the first month you get to run the best open-source models out right now, all in one place. Kind of insane value honestly.

No API keys, no provider accounts to manage. You get way higher rate limits than going to the providers one by one.

Oh, and DeepSeek V4 Flash & Step 3.5 Flash are free inside Cline CLI anyway.

$9.99/mo after the first month.

[Atenov int. @Atenov_D]

FREE Claude 4.5 through 4.8, GPT-5.5, Gemini 3.1 Pro and every top Chinese model in one API. No card. Temp email works. Unlimited accounts.

> The platform is g0iAI. Full API access to the entire stack of frontier models - Claude family, GPT family, Gemini, and top Chinese models including GLM 5.2.

Vision models included. Skills included. No card required anywhere in the flow.

Here's the exact setup:
→ Go to g0i(.)ai/register
→ Register with temp email or alias - both work
→ Confirm via email
→ Done. Start using immediately.

Plug into OpenCode, OpenClaw, Hermes, Claude Code - any tool that takes an OpenAI-compatible endpoint.

One note: trial gives 100K context window for 2 hours. When limits hit - just register a new account.

Registration takes 30 seconds with a fresh temp email. All other models work normally in the meantime - if one lags, switch model and keep going.

>> Models inside: Claude 4.5, 4.6, 4.7, 4.8, GPT-4o Mini through GPT-5.5, Gemini 3.1 Pro, Gemini 3.5 Flash, GLM 5.2 and the full Chinese model stack.

Bookmark this before the free tier gets locked down.

[painn @painn_x]

Found a way to run GLM-5.2 for FREE with no daily limits through Cloudflare Workers AI 😳

No credit card. No monthly bills. Just one API token and you get solid usage.

What GLM-5.2 on Cloudflare unlocks:
-Strong agentic coding performance
-262k context window
-Tool use and function calling
-OpenAI-compatible endpoint
-Works with OpenCode, Cursor, Aider, Hermes, and more

What this replaces:
-Paid frontier model usage for daily coding agents
-Expensive API costs just to test workflows

How to grab it (5 min):

1. Create a free Cloudflare account

2. Go to Workers AI and copy your Account ID

3. Create an API Token

4. Add the provider in OpenCode with this base URL:
https://t.co/I06wzl3TnF

5. Select model: @cf/zai-org/glm-5.2

6. Start running agents

Works in OpenCode, Cursor, Aider, Claude Code, Hermes Agent, and any OpenAI-compatible tool.

Your buddy pays $20–200/mo for coding agents. You get strong performance for $0.

Bookmark this before Cloudflare changes the free tier.