You might

@jackroberts____

68.7K followers · usually 3.2K views a post

Views

20.3K

Likes

1.5K

Comments

472

229

SoundTikTok sound · original sound - jackroberts____

View velocity

+3.9K views over 18.0d · ~214/day · 4 observations

Promoted product

AI Automations by Jack

If you're serious about AI Automation, this community will give you an unfair advantage. Join and build the world's most VALUABLE skill set 💎

2 videos

Why it worked

The video taps into the common pain point of high API costs for AI models and offers a readily available solution (a curated GitHub repo) that saves users time and money. The 'one-click' access and the promise of free resources are highly appealing to developers and AI enthusiasts.

Summary

This video highlights a GitHub repository that aggregates over 130 free API tiers from 40 different AI providers, including Gemini, Grok, and NVIDIA. It contrasts this with the common practice of paying for API access and suggests that finding these free tiers is the main challenge, offering a one-click solution for accessing various AI models and agents.

Structure

1Introduction to free API tiers
2Highlighting a GitHub repo with 130+ free APIs
3Listing providers like Gemini, Grok, NVIDIA

Original caption

Free API tiers aren't charity. They're providers bidding for you. Every one of them wants developer lock-in. So they hand out free inference. Gemini, Groq, NVIDIA all do it. Permanent free tiers, not trials. The cost was never the real barrier. Finding them was. Forty providers, forty signup pages. So most people give up and pay. This repo lists over 130. One place, every free tier. One click into Claude Code. Same for Codex and Cursor. Your agents run on someone else's budget. Like forty stores handing out samples. Most people never walk in. The models are the same either way. Only the invoice changes. Go collect the free tiers. #github #gemini #groq #claudecode #cursor

More from @jackroberts____

On-screen text

You might Google Cloud Unlock the potential of AI with the Gemini API to pay Gemini 1.5 Flash MODEL API again of this that knows the deal. README Please don't abuse these services, else we might lose the Warning This list explicitly excludes any services that are not legit Free Providers OpenRouter Google AI Studio NVIDIA NIM Mistral (La Plateforme) Mistral (Codestral) HuggingFace Inference Providers Vercel AI Gateway OpenCode Zen Cerebras Groq Cohere GitHub Models Cloudflare Workers AI Providers with trial credits Fireworks Baseten Nebius Novita AI21 Upstage NLP Cloud Alibaba Cloud (International) Model Studio AI21 Upstage NLP Cloud Alibaba Cloud (International) Model Studio Modal Inference.net Hyperbolic SambaNova Cloud Scaleway Generative APIs Free Providers OpenRouter Limits: 20 requests/minute 50 requests/day Up to 1000 requests/day with $10 lifetime topup Models share a common quota Hermes 3 Llama 3.1 8B Llama 3.2 8B Instruct Llama 3.3 70B Instruct cognitivecomputations/dolphin-mistral-24b-venice-ed cohere/north-mini-code:free google/gemma-4-26b-a4b-it:free google/gemma-4-31b-it:free nvidia/nemotron-3-nano-30b-a3b:free nvidia/nemotron-3-nano-30b-a3b-reasoning:free nvidia/nemotron-3-super-120b-a12b:free nvidia/nemotron-3-ultra-550b-a55b:free nvidia/nemotron-3.5-content-safety:free nvidia/nemotron-nano-12b-v2-vl:free nvidia/nemotron-nano-9b-v2:free openai/gpt-oss-20b:free poolside/laguna-m.1:free poolside/laguna-xs-2.1:free qwcn/qwcn3-coder:free qwcn/qwcn3-next-80b-a3b-instruct:free tencent/hy3:free Google AI Studio Data is used for training when used outside of the UK/CH/E Model Name Model Limits Gemini 3.5 Flash 250,000 tokens/minute 20 requests/day 5 requests/minute Gemini 3 Flash 250,000 tokens/minute 20 requests/day 5 requests/minute Gemini 3.1 Flash-Lite 250,000 tokens/minute 500 requests/day 15 requests/minute over 130 README Free LLM API resources This lists various services that provide free access Note Please don't abuse these services, else we might lose the Warning This list explicitly excludes any services that are not legit Free Providers OpenRouter Google AI Studio NVIDIA NIM Mistral (La Plateforme) Mistral (Codestral) HuggingFace Inference Providers over 130 free APIs from 40 different Gemini Grok AI Agents Complete AI Agents Complete README MIT license How to Build AI Agents in 2026 the ultimate beginner's guide $0 no credit card no prior exp permanent and here's the thing most "build a a paid API key around step 3. this — one that reasons, calls tools, and loops until a task is done works. and here's the thing most "build a a paid API key around step 3. this — one that reasons, calls tools, and loops until a task is done works. 6h 0% 4d12h src/components/app.tsx const theme = 'light' const fontSize = 14 // const theme = 'dark' 'light' // const fontSize = settings.fontSize ? settings.fontSize : 14 Allow Once Deny Show all 293 questions 6h 0% 4d12h agent-runtime Trace the agent event pipeline and remove duplicate... Yo, Polish the multi-agent session panel for release Claude Codex GPT-4o Ghostly 6h 0% 4d12h agent-runtime Trace the agent event pipeline and remove duplicate... Yo, Polish the multi-agent session panel for release Claude Codex GPT-4o Ghostly 6h 0% 4d12h vibe-island - Make terminal routing deterministic across... Yo, Make terminal routing deterministic across... Shipped the session routing update. setup inside Install for All Agents Claude Code Codex agent codex View on GitHub Claude 200 skills Refine skills codex. build.nvidia.com Search JK Login deepstream-dev NVIDIA DeepStream SDK 9.0 development with Python Pythonservice maker Use when building video analytics pipelines, GStreamer-based video processing... developer +4 Copy deepstream-import-vision-model Use this skill to bring any vision model from HuggingFace or NVIDIA NGC into an NVIDIA DeepStream pipeline with end-to-end automation ONNX download... developer +5 Copy everybody cuopt-user-rules Base rules for end users calling NVIDIA cuOpt (routing/MLP/DP/install/server). Not for cuOpt internals - use cuopt-... developer +3 Copy cuopt-server-api-python cuopt REST server - start server, endpoints, Python/curl client examples. Use when the user is deploying or calling a REST API. developer +4 Copy nemoclaw-user-manage-sandboxes Explains operational tasks after the quickstart listing sandboxes, status and health checks, logs, diagnostics, post-mortem, multiple sandboxes, credential... build.nvidia.com Search JK Login Get API Key you can Start Now NVIDIA Deploy Models Now with NVIDIA NIM Optimized Free serverless APIs for development Self-Host on your GPU infrastructure Continuous vulnerability fixes Discover for $0. Want the comment below "Key" over