[{"data":1,"prerenderedAt":4},["ShallowReactive",2],{"readme:freellmapi":3},"\u003Cdiv align=\"center\">\u003Ch1>FreeLLMAPI\u003C\u002Fh1>\n\u003Cp>\u003Cstrong>One OpenAI-compatible endpoint. 18 free LLM providers. 161 free models. ~1.7B tokens per month.\u003C\u002Fstrong>\u003C\u002Fp>\n\u003Cp>Aggregate the free tiers from Google, Groq, Cerebras, NVIDIA, Mistral, OpenRouter, GitHub Models, Cohere, Cloudflare, HuggingFace, Z.ai (Zhipu), Ollama, Kilo, Pollinations, LLM7, OVH AI Endpoints, OpenCode Zen, and AI Horde, plus custom OpenAI-compatible chat, embedding, image, and audio endpoints, behind a single \u003Ccode>\u002Fv1\u003C\u002Fcode> API. Keys are stored encrypted. A router picks the best available model for each request, falls over to the next provider when one is rate-limited, and tracks per-key usage so you stay under every free-tier cap.\u003C\u002Fp>\n\u003Cp>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Ftashfeenahmed\u002Ffreellmapi\u002Factions\u002Fworkflows\u002Fci.yml\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Ftashfeenahmed\u002Ffreellmapi\u002Factions\u002Fworkflows\u002Fci.yml\u002Fbadge.svg\" alt=\"CI\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Ftashfeenahmed\u002Ffreellmapi\u002Fstargazers\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Ftashfeenahmed\u002Ffreellmapi?style=flat&logo=github&color=yellow\" alt=\"GitHub stars\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Ftashfeenahmed\u002Ffreellmapi\u002Fblob\u002FHEAD\u002FLICENSE\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-MIT-green.svg\" alt=\"License: MIT\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"#contributing\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPRs-welcome-brightgreen.svg\" alt=\"PRs Welcome\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Ftashfeenahmed\u002Ffreellmapi\u002Fpkgs\u002Fcontainer\u002Ffreellmapi\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fghcr.io-freellmapi-2496ED?logo=docker&logoColor=white\" alt=\"Docker image\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fdeepwiki.com\u002Ftashfeenahmed\u002Ffreellmapi\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fdeepwiki.com\u002Fbadge.svg\" alt=\"Ask DeepWiki\" \u002F>\u003C\u002Fa>\u003C\u002Fp>\n\u003Cp>\u003Cstrong>\u003Ca href=\"https:\u002F\u002Ffreellmapi.co\" rel=\"nofollow ugc noopener\">freellmapi.co\u003C\u002Fa>\u003C\u002Fstrong> · browse all 161 free models on the live catalog\u003C\u002Fp>\n\u003Cp>Your router updates its own model catalog. Free installs get each new model 30 days after it ships;\n\u003Cstrong>\u003Ca href=\"https:\u002F\u002Ffreellmapi.co\u002F?utm_source=github&utm_medium=readme#pricing\" rel=\"nofollow ugc noopener\">Premium gets it the day it lands, and is 79 models ahead right now\u003C\u002Fa>\u003C\u002Fstrong> ($19\u002Fyr, cancel anytime).\u003C\u002Fp>\n\u003Cp>\u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Ftashfeenahmed\u002Ffreellmapi\u002FHEAD\u002Frepo-assets\u002Ffallback-chain.png\" alt=\"Fallback chain with per-provider token budget\" \u002F>\u003C\u002Fp>\n\u003C\u002Fdiv>\u003Chr \u002F>\n\u003Ch2>Contents\u003C\u002Fh2>\n\u003Cul>\n\u003Cli>\u003Ca href=\"#why-this-exists\" rel=\"nofollow ugc noopener\">Why this exists\u003C\u002Fa>\u003C\u002Fli>\n\u003Cli>\u003Ca href=\"#supported-providers\" rel=\"nofollow ugc noopener\">Supported providers\u003C\u002Fa>\u003C\u002Fli>\n\u003Cli>\u003Ca href=\"#features\" rel=\"nofollow ugc noopener\">Features\u003C\u002Fa>\u003C\u002Fli>\n\u003Cli>\u003Ca href=\"#not-yet-supported\" rel=\"nofollow ugc noopener\">Not yet supported\u003C\u002Fa>\u003C\u002Fli>\n\u003Cli>\u003Ca href=\"#quick-start\" rel=\"nofollow ugc noopener\">Quick start\u003C\u002Fa>\u003C\u002Fli>\n\u003Cli>\u003Ca href=\"#works-with-ob-1-and-other-clients\" rel=\"nofollow ugc noopener\">Works with OB-1 and other clients\u003C\u002Fa>\u003C\u002Fli>\n\u003Cli>\u003Ca href=\"#docker\" rel=\"nofollow ugc noopener\">Docker\u003C\u002Fa>\u003C\u002Fli>\n\u003Cli>\u003Ca href=\"#desktop-app\" rel=\"nofollow ugc noopener\">Desktop app\u003C\u002Fa>\u003C\u002Fli>\n\u003Cli>\u003Ca href=\"#languages\" rel=\"nofollow ugc noopener\">Languages\u003C\u002Fa>\u003C\u002Fli>\n\u003Cli>\u003Ca href=\"#premium-live-catalog\" rel=\"nofollow ugc noopener\">Premium (live catalog)\u003C\u002Fa>\u003C\u002Fli>\n\u003Cli>\u003Ca href=\"#using-the-api\" rel=\"nofollow ugc noopener\">Using the API\u003C\u002Fa>\u003C\u002Fli>\n\u003Cli>\u003Ca href=\"#screenshots\" rel=\"nofollow ugc noopener\">Screenshots\u003C\u002Fa>\u003C\u002Fli>\n\u003Cli>\u003Ca href=\"#how-it-works\" rel=\"nofollow ugc noopener\">How it works\u003C\u002Fa>\u003C\u002Fli>\n\u003Cli>\u003Ca href=\"#context-handoff\" rel=\"nofollow ugc noopener\">Context Handoff\u003C\u002Fa>\u003C\u002Fli>\n\u003Cli>\u003Ca href=\"#limitations\" rel=\"nofollow ugc noopener\">Limitations\u003C\u002Fa>\u003C\u002Fli>\n\u003Cli>\u003Ca href=\"#contributing\" rel=\"nofollow ugc noopener\">Contributing\u003C\u002Fa>\u003C\u002Fli>\n\u003Cli>\u003Ca href=\"#terms-of-service-review\" rel=\"nofollow ugc noopener\">Terms of Service review\u003C\u002Fa>\u003C\u002Fli>\n\u003Cli>\u003Ca href=\"#disclaimer\" rel=\"nofollow ugc noopener\">Disclaimer\u003C\u002Fa>\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Ch2>Why this exists\u003C\u002Fh2>\n\u003Cp>Every serious AI lab now offers a free tier — a few million tokens a month, a few thousand requests a day. On its own each tier is a toy. Stacked together, they add up to roughly \u003Cstrong>1.7 billion tokens per month\u003C\u002Fstrong> of working inference capacity, across 160+ models from small-and-fast to reasonably capable.\u003C\u002Fp>\n\u003Cp>The problem is that stacking them by hand is painful: twenty-one different SDKs, twenty-one different rate limits, twenty-one places a request can fail. FreeLLMAPI collapses that into one OpenAI-compatible endpoint. Point any OpenAI client library at your local server, and it routes transparently across whichever providers you've added keys for.\u003C\u002Fp>\n\u003Cp>And the free-tier landscape shifts weekly: providers launch models, retire them, and change quotas without notice. FreeLLMAPI tracks all of that for you. The router pulls a signed model catalog from \u003Ca href=\"https:\u002F\u002Ffreellmapi.co\" rel=\"nofollow ugc noopener\">freellmapi.co\u003C\u002Fa> on its own, so your install keeps up without a \u003Ccode>git pull\u003C\u002Fcode>. See \u003Ca href=\"#premium-live-catalog\" rel=\"nofollow ugc noopener\">Premium (live catalog)\u003C\u002Fa> for how fast it keeps up.\u003C\u002Fp>\n\u003Ch2>Supported providers\u003C\u002Fh2>\n\u003Ctable>\n\u003Ctr>\n\u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fai.google.dev\" rel=\"nofollow ugc noopener\">\u003Cb>Google\u003C\u002Fb>\u003Cbr \u002F>Gemini 2.5 Flash · 3.x previews\u003C\u002Fa>\u003C\u002Ftd>\n\u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgroq.com\" rel=\"nofollow ugc noopener\">\u003Cb>Groq\u003C\u002Fb>\u003Cbr \u002F>Llama 3.3, Llama 4, GPT-OSS, Qwen3\u003C\u002Fa>\u003C\u002Ftd>\n\u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fcerebras.ai\" rel=\"nofollow ugc noopener\">\u003Cb>Cerebras\u003C\u002Fb>\u003Cbr \u002F>Qwen3 235B\u003C\u002Fa>\u003C\u002Ftd>\n\u003C\u002Ftr>\u003C\u002Ftable>",1784240407240]