Skip to content

7.4 billion tokens per month. 34 free LLM providers. 635 free model endpoints. All behind one /v1 endpoint, plus any custom OpenAI-compatible endpoint. Smart routing, automatic failover, encrypted keys. Personal experimentation only.

TypeScript

docs(site): update landing page to 16 providers / ~1.7B tokens (#150)

Tashfeendd5b0155c79c
diff --git a/docs/index.html b/docs/index.html
index 54d47b3a..99a67204 100644
--- a/docs/index.html
+++ b/docs/index.html
@@ -3,26 +3,26 @@
<head>
<meta charset="UTF-8" />
<meta name="viewport" content="width=device-width, initial-scale=1" />
-<title>FreeLLMAPI — One key. One billion free LLM tokens. Every month.</title>
-<meta name="description" content="A self-hosted, OpenAI-compatible proxy that routes across 11 free-tier LLM providers — Gemini, OpenRouter, Cerebras, Groq, Mistral, GitHub Models, SambaNova, Cohere, Cloudflare, Z.ai, NVIDIA. ~1B free tokens / month, 60 models." />
+<title>FreeLLMAPI — One key. 1.7 billion free LLM tokens. Every month.</title>
+<meta name="description" content="A self-hosted, OpenAI-compatible proxy that routes across 16 free-tier LLM providers — Gemini, OpenRouter, Cerebras, Groq, Mistral, GitHub Models, SambaNova, Cohere, Cloudflare, Z.ai, NVIDIA, HuggingFace, Ollama, Kilo, Pollinations, LLM7 — plus any custom OpenAI-compatible endpoint. ~1.7B free tokens / month, 100+ models." />
<meta name="theme-color" content="#0a0a0a" />
<link rel="canonical" href="https://tashfeenahmed.github.io/freellmapi/" />
<!-- Open Graph -->
<meta property="og:type" content="website" />
<meta property="og:site_name" content="FreeLLMAPI" />
-<meta property="og:title" content="FreeLLMAPI — 1B free LLM tokens / month" />
-<meta property="og:description" content="One self-hosted, OpenAI-compatible proxy across 11 free-tier LLM providers. 60 models. ~1B free tokens per month." />
+<meta property="og:title" content="FreeLLMAPI — 1.7B free LLM tokens / month" />
+<meta property="og:description" content="One self-hosted, OpenAI-compatible proxy across 16 free-tier LLM providers. 100+ models. ~1.7B free tokens per month." />
<meta property="og:url" content="https://tashfeenahmed.github.io/freellmapi/" />
<meta property="og:image" content="https://tashfeenahmed.github.io/freellmapi/og.png" />
<meta property="og:image:width" content="1200" />
<meta property="og:image:height" content="630" />
-<meta property="og:image:alt" content="FreeLLMAPI — 1B free tokens / month, across 11 providers and 60 models." />
+<meta property="og:image:alt" content="FreeLLMAPI — 1.7B free tokens / month, across 16 providers and 100+ models." />
<!-- Twitter -->
<meta name="twitter:card" content="summary_large_image" />
-<meta name="twitter:title" content="FreeLLMAPI — 1B free LLM tokens / month" />
-<meta name="twitter:description" content="One self-hosted, OpenAI-compatible proxy across 11 free-tier LLM providers. 60 models. ~1B free tokens per month." />
+<meta name="twitter:title" content="FreeLLMAPI — 1.7B free LLM tokens / month" />
+<meta name="twitter:description" content="One self-hosted, OpenAI-compatible proxy across 16 free-tier LLM providers. 100+ models. ~1.7B free tokens per month." />
<meta name="twitter:image" content="https://tashfeenahmed.github.io/freellmapi/og.png" />
<link rel="icon" href="data:image/svg+xml;utf8,%3Csvg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 32 32'%3E%3Crect width='32' height='32' rx='9' fill='%230a0a0a'/%3E%3Ccircle cx='16' cy='16' r='9' fill='%23ffffff'/%3E%3Ccircle cx='16' cy='16' r='3.2' fill='%230a0a0a'/%3E%3C/svg%3E" />
<style>
@@ -292,8 +292,8 @@
</nav>
<header class="hero">
- <span class="badge"><span class="badge-dot"></span> 60 free models · 11 providers · self-hosted</span>
- <h1>One key.<br><span class="gradient">One billion</span> free tokens.<br>Every month.</h1>
+ <span class="badge"><span class="badge-dot"></span> 100+ free models · 16 providers · self-hosted</span>
+ <h1>One key.<br><span class="gradient">1.7 billion</span> free tokens.<br>Every month.</h1>
<p class="subtitle">A self-hosted, OpenAI-compatible proxy that routes across every credible free-tier LLM provider. Bring your own keys; we just point requests at whichever provider still has budget left.</p>
<div class="cta-row">
<a class="btn btn-primary" href="https://github.com/tashfeenahmed/freellmapi" target="_blank" rel="noopener">View on GitHub →</a>
@@ -303,9 +303,9 @@
<div class="tokens-stat">
<div class="tokens-label">Aggregate monthly free budget</div>
- <div class="tokens-number">1B</div>
+ <div class="tokens-number">1.7B</div>
<div class="tokens-unit">tokens · per month</div>
- <div class="tokens-sub">Across 60 free-tier models on 11 providers. Mistral alone contributes ~1B; everything else is bonus.</div>
+ <div class="tokens-sub">Across 100+ free-tier models on 16 providers, plus any custom OpenAI-compatible endpoint. Mistral alone contributes ~1B; everything else is bonus.</div>
</div>
<section id="providers">
@@ -370,6 +370,36 @@
<div class="provider-tokens"><span class="num">credits</span><span class="unit"></span><span class="label">disabled</span></div>
<div class="provider-models">Llama 3.1 70B. Disabled by default — credit-based, not recurring.</div>
</div>
+ <div class="provider-card">
+ <div class="provider-name"><span class="provider-icon" style="font-size:12px;font-weight:700;color:var(--muted)">HF</span>HuggingFace</div>
+ <div class="provider-tokens"><span class="num">~3M</span><span class="unit">/mo</span><span class="label">router credit</span></div>
+ <div class="provider-models">Inference Providers router → DeepSeek V4 · Kimi K2.6 · Qwen3. Recurring router credit, no card.</div>
+ </div>
+ <div class="provider-card">
+ <div class="provider-name"><span class="provider-icon" style="font-size:12px;font-weight:700;color:var(--muted)">OL</span>Ollama Cloud</div>
+ <div class="provider-tokens"><span class="num">free</span><span class="unit"></span><span class="label">GPU-time</span></div>
+ <div class="provider-models">GLM-4.7 · Kimi K2 · gpt-oss · Qwen3. Free plan: 1 concurrent model, session/GPU-time caps.</div>
+ </div>
+ <div class="provider-card">
+ <div class="provider-name"><span class="provider-icon" style="font-size:14px;font-weight:700;color:var(--muted)">K</span>Kilo Gateway</div>
+ <div class="provider-tokens"><span class="num">anon</span><span class="unit"></span><span class="label">~200/hr</span></div>
+ <div class="provider-models"><code>:free</code> routes — anonymous access works per-IP; a key raises the limit.</div>
+ </div>
+ <div class="provider-card">
+ <div class="provider-name"><span class="provider-icon" style="font-size:14px;font-weight:700;color:var(--muted)">P</span>Pollinations</div>
+ <div class="provider-tokens"><span class="num">anon</span><span class="unit"></span><span class="label">free tier</span></div>
+ <div class="provider-models">GPT-OSS 20B (<code>openai-fast</code>), tools supported. Anonymous tier, no key.</div>
+ </div>
+ <div class="provider-card">
+ <div class="provider-name"><span class="provider-icon" style="font-size:12px;font-weight:700;color:var(--muted)">L7</span>LLM7</div>
+ <div class="provider-tokens"><span class="num">anon</span><span class="unit"></span><span class="label">~100/hr</span></div>
+ <div class="provider-models">GPT-OSS · Llama 3.1 Turbo · Codestral · GLM via one token. Anonymous access works.</div>
+ </div>
+ <div class="provider-card">
+ <div class="provider-name"><span class="provider-icon" style="font-size:18px;font-weight:700;color:var(--muted)">+</span>Custom endpoint</div>
+ <div class="provider-tokens"><span class="num">∞</span><span class="unit"></span><span class="label">your server</span></div>
+ <div class="provider-models">Point at any OpenAI-compatible URL — llama.cpp, LM Studio, vLLM, a local Ollama, or a remote gateway.</div>
+ </div>
</div>
</section>
diff --git a/docs/og.png b/docs/og.png
index d87b9afe..44f17a3f 100644
Binary files a/docs/og.png and b/docs/og.png differ
diff --git a/docs/og.svg b/docs/og.svg
index dbd7ed23..d635274a 100644
--- a/docs/og.svg
+++ b/docs/og.svg
@@ -1,7 +1,18 @@
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 1200 630" width="1200" height="630">
+ <defs>
+ <linearGradient id="grad" x1="0" y1="0" x2="1" y2="0.3">
+ <stop offset="0" stop-color="#a78bfa"/>
+ <stop offset="1" stop-color="#22d3ee"/>
+ </linearGradient>
+ </defs>
<rect width="1200" height="630" fill="#0a0a0a"/>
- <g transform="translate(600 315)">
- <circle r="180" fill="#ffffff"/>
- <circle r="65" fill="#0a0a0a"/>
+ <!-- logo mark -->
+ <g transform="translate(600 138)">
+ <circle r="46" fill="#ffffff"/>
+ <circle r="17" fill="#0a0a0a"/>
</g>
+ <text x="600" y="250" text-anchor="middle" font-family="Helvetica, Arial, sans-serif" font-size="34" font-weight="700" letter-spacing="2" fill="#fafafa">FreeLLMAPI</text>
+ <text x="600" y="430" text-anchor="middle" font-family="Helvetica, Arial, sans-serif" font-size="210" font-weight="800" letter-spacing="-6" fill="url(#grad)">1.7B</text>
+ <text x="600" y="498" text-anchor="middle" font-family="Helvetica, Arial, sans-serif" font-size="46" font-weight="600" fill="#fafafa">free LLM tokens / month</text>
+ <text x="600" y="560" text-anchor="middle" font-family="Helvetica, Arial, sans-serif" font-size="29" font-weight="500" fill="#a1a1aa">16 providers · 100+ models · OpenAI-compatible · self-hosted</text>
</svg>