Show description
Ultimate LLM API Documentation - 2025
Ultimate LLM API Documentation - 2025
Ultimate LLM API Documentation
Comprehensive reference for all major Language Model APIs - Updated 2025
📥 Download Full Documentation
📄 Download as JSON
📋 Quick Navigation
OpenAI (GPT)
Anthropic (Claude)
Google (Gemini)
xAI (Grok)
Mistral AI
DeepSeek
Meta (Llama)
Alibaba (Qwen)
Together AI
Groq
Cohere
🤖 OpenAI
Industry-leading AI with GPT-5 (released Aug 7, 2025) - unified reasoning and fast responses
🔗 API Endpoints
Base URL:
https://api.openai.com
Chat Completions:
POST https://api.openai.com/v1/chat/completions
Completions (Legacy):
POST https://api.openai.com/v1/completions
Images:
POST https://api.openai.com/v1/images/generations
Audio (Speech-to-Text):
POST https://api.openai.com/v1/audio/transcriptions
Audio (Text-to-Speech):
POST https://api.openai.com/v1/audio/speech
🎯 Available Models (Updated Aug 8, 2025)
gpt-5 🆕
Latest flagship with built-in reasoning - released Aug 7, 2025
gpt-5-mini 🆕
Lightweight version for cost-sensitive applications
gpt-5-nano 🆕
Ultra-low latency for instant responses
gpt-5-chat 🆕
Advanced natural conversations for enterprise
gpt-4.1
Specialized coding model with 1M token context
gpt-4.1-mini
Fast, efficient coding assistant
gpt-4.1-nano
Fastest and cheapest for low-latency tasks
gpt-4o
Multimodal model (superseded by GPT-5)
o3
Advanced reasoning model
o4-mini
Fast, cost-efficient reasoning model
gpt-image-1
Professional image generation model
📝 Text
🖼️ Images
🎵 Audio
💻 Code
🔧 Function Calling
🧠 Built-in Reasoning
⚡ Real-time Router
🔄 Streaming
🆓 Free Access (GPT-5)
🔑 Authentication
Header: Authorization: Bearer YOUR_API_KEY
🚨 Model Status Updates:
• GPT-5 released Aug 7, 2025 (available to ALL users including free)
• GPT-4.5 being deprecated July 14, 2025
• GPT-4 retired from ChatGPT April 2025 (API still available)
• GPT-4o mini replaced by GPT-4.1 mini
🧠 Anthropic (Claude)
Constitutional AI with advanced reasoning and safety features
🔗 API Endpoints
Base URL:
https://api.anthropic.com
Messages:
POST https://api.anthropic.com/v1/messages
Models List:
GET…
Ultimate LLM API Documentation - 2025
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Ultimate LLM API Documentation - 2025</title>
<style>
* {
margin: 0;
padding: 0;
box-sizing: border-box;
}
body {
font-family: 'Segoe UI', system-ui, -apple-system, sans-serif;
background: linear-gradient(135deg, #0c0c0c 0%, #1a1a1a 100%);
color: #e0e0e0;
line-height: 1.6;
min-height: 100vh;
}
.container {
max-width: 1400px;
margin: 0 auto;
padding: 20px;
}
.header {
text-align: center;
margin-bottom: 40px;
padding: 30px 0;
background: linear-gradient(135deg, #1e3c72 0%, #2a5298 100%);
border-radius: 15px;
box-shadow: 0 10px 30px rgba(0,0,0,0.3);
}
.header h1 {
font-size: 3em;
margin-bottom: 10px;
background: linear-gradient(45deg, #00d4ff, #7c3aed);
-webkit-background-clip: text;
-webkit-text-fill-color: transparent;
background-clip: text;
}
.header p {
font-size: 1.2em;
opacity: 0.9;
}
.download-btn {
background: linear-gradient(45deg, #00d4ff, #7c3aed);
color: white;
padding: 15px 30px;
border: none;
border-radius: 50px;
font-size: 1.1em;
font-weight: bold;
cursor: pointer;
margin: 20px 10px;
transition: all 0.3s ease;
box-shadow: 0 5px 15px rgba(124, 58, 237, 0.4);
}
.download-btn:hover {
transform: translateY(-2px);
box-shadow: 0 8px 25px rgba(124, 58, 237, 0.6);
}
.provider-section {
background: rgba(255, 255, 255, 0.03);
border: 1px solid rgba(255, 255, 255, 0.1);
border-radius: 15px;
margin-bottom: 30px;
overflow: hidden;
transition: all 0.3s ease;
backdrop-filter: blur(10px);
}
.provider-section:hover {
transform: translateY(-5px);
box-shadow: 0 15px 35px rgba(0,0,0,0.2);
border-color: rgba(255, 255, 255, 0.2);
}
.provider-header {
background: linear-gradient(135deg, #2d2d2d 0%, #3d3d3d 100%);
padding: 20px 30px;
border-bottom: 1px solid rgba(255, 255, 255, 0.1);
}
.provider-name {
font-size: 1.8em;
font-weight: bold;
color: #00d4ff;
margin-bottom: 5px;
}
.provider-description {
color: #b0b0b0;
font-size: 1em;
}
.provider-content {
padding: 25px 30px;
}
.endpoint-group {
margin-bottom: 25px;
}
.endpoint-title {
font-size: 1.3em;
color: #00d4ff;
margin-bottom: 15px;
font-weight: 600;
}
.endpoint-item {
background: rgba(0, 0, 0, 0.3);
border: 1px solid rgba(255, 255, 255, 0.1);
border-radius: 8px;
padding: 15px;
margin-bottom: 10px;
transition: all 0.2s ease;
}
.endpoint-item:hover {
background: rgba(0, 0, 0, 0.4);
border-color: rgba(0, 212, 255, 0.3);
}
.endpoint-label {
font-weight: bold;
color: #ffd700;
margin-bottom: 5px;
}
.endpoint-url {
font-family: 'Monaco', monospace;
background: rgba(0, 0, 0, 0.5);
padding: 8px 12px;
border-radius: 5px;
color: #00ff88;
font-size: 0.9em;
word-break: break-all;
border-left: 3px solid #00d4ff;
}
.models-grid {
display: grid;
grid-template-columns: repeat(auto-fit, minmax(250px, 1fr));
gap: 15px;
margin-top: 15px;
}
.model-card {
background: rgba(0, 0, 0, 0.2);
border: 1px solid rgba(255, 255, 255, 0.1);
border-radius: 8px;
padding: 15px;
transition: all 0.2s ease;
}
.model-card:hover {
background: rgba(0, 0, 0, 0.3);
border-color: rgba(124, 58, 237, 0.3);
}
.model-name {
font-weight: bold;
color: #7c3aed;
margin-bottom: 5px;
}
.model-description {
font-size: 0.9em;
color: #b0b0b0;
}
.capabilities {
display: flex;
flex-wrap: wrap;
gap: 8px;
margin-top: 15px;
}
.capability-tag {
background: linear-gradient(45deg, #7c3aed, #00d4ff);
color: white;
padding: 4px 12px;
border-radius: 20px;
font-size: 0.8em;
font-weight: 500;
}
.auth-info {
background: rgba(255, 193, 7, 0.1);
border: 1px solid rgba(255, 193, 7, 0.3);
border-radius: 8px;
padding: 15px;
margin-top: 15px;
}
.auth-title {
color: #ffc107;
font-weight: bold;
margin-bottom: 5px;
}
.last-updated {
text-align: center;
margin-top: 40px;
padding: 20px;
color: #888;
font-style: italic;
}
.search-box {
width: 100%;
max-width: 500px;
margin: 0 auto 30px;
padding: 15px 20px;
background: rgba(255, 255, 255, 0.05);
border: 1px solid rgba(255, 255, 255, 0.1);
border-radius: 50px;
color: #e0e0e0;
font-size: 1em;
outline: none;
transition: all 0.3s ease;
}
.search-box:focus {
border-color: #00d4ff;
box-shadow: 0 0 20px rgba(0, 212, 255, 0.3);
}
.search-box::placeholder {
color: #888;
}
@media (max-width: 768px) {
.container {
padding: 10px;
}
.header h1 {
font-size: 2em;
}
.provider-content,
.provider-header {
padding: 15px 20px;
}
.models-grid {
grid-template-columns: 1fr;
}
}
.toc {
background: rgba(255, 255, 255, 0.03);
border: 1px solid rgba(255, 255, 255, 0.1);
border-radius: 15px;
padding: 25px;
margin-bottom: 30px;
backdrop-filter: blur(10px);
}
.toc h3 {
color: #00d4ff;
margin-bottom: 15px;
font-size: 1.4em;
}
.toc-list {
display: grid;
grid-template-columns: repeat(auto-fit, minmax(200px, 1fr));
gap: 10px;
}
.toc-item {
background: rgba(0, 0, 0, 0.2);
padding: 10px 15px;
border-radius: 8px;
cursor: pointer;
transition: all 0.2s ease;
border: 1px solid rgba(255, 255, 255, 0.1);
}
.toc-item:hover {
background: rgba(0, 212, 255, 0.1);
border-color: #00d4ff;
}
.toc-item a {
color: #e0e0e0;
text-decoration: none;
font-weight: 500;
}
</style>
</head>
<body>
<div class="container">
<div class="header">
<h1>Ultimate LLM API Documentation</h1>
<p>Comprehensive reference for all major Language Model APIs - Updated 2025</p>
<button class="download-btn" onclick="downloadHTML()">📥 Download Full Documentation</button>
<button class="download-btn" onclick="downloadJSON()">📄 Download as JSON</button>
</div>
<input type="text" class="search-box" placeholder="🔍 Search providers, models, or endpoints..." onkeyup="searchContent(this.value)">
<div class="toc">
<h3>📋 Quick Navigation</h3>
<div class="toc-list">
<div class="toc-item"><a href="#openai">OpenAI (GPT)</a></div>
<div class="toc-item"><a href="#anthropic">Anthropic (Claude)</a></div>
<div class="toc-item"><a href="#google">Google (Gemini)</a></div>
<div class="toc-item"><a href="#xai">xAI (Grok)</a></div>
<div class="toc-item"><a href="#mistral">Mistral AI</a></div>
<div class="toc-item"><a href="#deepseek">DeepSeek</a></div>
<div class="toc-item"><a href="#meta">Meta (Llama)</a></div>
<div class="toc-item"><a href="#qwen">Alibaba (Qwen)</a></div>
<div class="toc-item"><a href="#together">Together AI</a></div>
<div class="toc-item"><a href="#groq">Groq</a></div>
<div class="toc-item"><a href="#cohere">Cohere</a></div>
</div>
</div>
<!-- OpenAI -->
<div class="provider-section" id="openai">
<div class="provider-header">
<div class="provider-name">🤖 OpenAI</div>
<div class="provider-description">Industry-leading AI with GPT-5 (released Aug 7, 2025) - unified reasoning and fast responses</div>
</div>
<div class="provider-content">
<div class="endpoint-group">
<div class="endpoint-title">🔗 API Endpoints</div>
<div class="endpoint-item">
<div class="endpoint-label">Base URL:</div>
<div class="endpoint-url">https://api.openai.com</div>
</div>
<div class="endpoint-item">
<div class="endpoint-label">Chat Completions:</div>
<div class="endpoint-url">POST https://api.openai.com/v1/chat/completions</div>
</div>
<div class="endpoint-item">
<div class="endpoint-label">Completions (Legacy):</div>
<div class="endpoint-url">POST https://api.openai.com/v1/completions</div>
</div>
<div class="endpoint-item">
<div class="endpoint-label">Images:</div>
<div class="endpoint-url">POST https://api.openai.com/v1/images/generations</div>
</div>
<div class="endpoint-item">
<div class="endpoint-label">Audio (Speech-to-Text):</div>
<div class="endpoint-url">POST https://api.openai.com/v1/audio/transcriptions</div>
</div>
<div class="endpoint-item">
<div class="endpoint-label">Audio (Text-to-Speech):</div>
<div class="endpoint-url">POST https://api.openai.com/v1/audio/speech</div>
</div>
</div>
<div class="endpoint-group">
<div class="endpoint-title">🎯 Available Models (Updated Aug 8, 2025)</div>
<div class="models-grid">
<div class="model-card">
<div class="model-name">gpt-5 🆕</div>
<div class="model-description">Latest flagship with built-in reasoning - released Aug 7, 2025</div>
</div>
<div class="model-card">
<div class="model-name">gpt-5-mini 🆕</div>
<div class="model-description">Lightweight version for cost-sensitive applications</div>
</div>
<div class="model-card">
<div class="model-name">gpt-5-nano 🆕</div>
<div class="model-description">Ultra-low latency for instant responses</div>
</div>
<div class="model-card">
<div class="model-name">gpt-5-chat 🆕</div>
<div class="model-description">Advanced natural conversations for enterprise</div>
</div>
<div class="model-card">
<div class="model-name">gpt-4.1</div>
<div class="model-description">Specialized coding model with 1M token context</div>
</div>
<div class="model-card">
<div class="model-name">gpt-4.1-mini</div>
<div class="model-description">Fast, efficient coding assistant</div>
</div>
<div class="model-card">
<div class="model-name">gpt-4.1-nano</div>
<div class="model-description">Fastest and cheapest for low-latency tasks</div>
</div>
<div class="model-card">
<div class="model-name">gpt-4o</div>
<div class="model-description">Multimodal model (superseded by GPT-5)</div>
</div>
<div class="model-card">
<div class="model-name">o3</div>
<div class="model-description">Advanced reasoning model</div>
</div>
<div class="model-card">
<div class="model-name">o4-mini</div>
<div class="model-description">Fast, cost-efficient reasoning model</div>
</div>
<div class="model-card">
<div class="model-name">gpt-image-1</div>
<div class="model-description">Professional image generation model</div>
</div>
</div>
</div>
<div class="capabilities">
<span class="capability-tag">📝 Text</span>
<span class="capability-tag">🖼️ Images</span>
<span class="capability-tag">🎵 Audio</span>
<span class="capability-tag">💻 Code</span>
<span class="capability-tag">🔧 Function Calling</span>
<span class="capability-tag">🧠 Built-in Reasoning</span>
<span class="capability-tag">⚡ Real-time Router</span>
<span class="capability-tag">🔄 Streaming</span>
<span class="capability-tag">🆓 Free Access (GPT-5)</span>
</div>
<div class="auth-info">
<div class="auth-title">🔑 Authentication</div>
Header: <code>Authorization: Bearer YOUR_API_KEY</code>
<br><br>
<div style="background: rgba(255, 82, 82, 0.1); border: 1px solid rgba(255, 82, 82, 0.3); border-radius: 8px; padding: 10px; margin-top: 10px;">
<strong>🚨 Model Status Updates:</strong><br>
• GPT-5 released Aug 7, 2025 (available to ALL users including free)<br>
• GPT-4.5 being deprecated July 14, 2025<br>
• GPT-4 retired from ChatGPT April 2025 (API still available)<br>
• GPT-4o mini replaced by GPT-4.1 mini
</div>
</div>
</div>
</div>
<!-- Anthropic Claude -->
<div class="provider-section" id="anthropic">
<div class="provider-header">
<div class="provider-name">🧠 Anthropic (Claude)</div>
<div class="provider-description">Constitutional AI with advanced reasoning and safety features</div>
</div>
<div class="provider-content">
<div class="endpoint-group">
<div class="endpoint-title">🔗 API Endpoints</div>
<div class="endpoint-item">
<div class="endpoint-label">Base URL:</div>
<div class="endpoint-url">https://api.anthropic.com</div>
</div>
<div class="endpoint-item">
<div class="endpoint-label">Messages:</div>
<div class="endpoint-url">POST https://api.anthropic.com/v1/messages</div>
</div>
<div class="endpoint-item">
<div class="endpoint-label">Models List:</div>
<div class="endpoint-url">GET https://api.anthropic.com/v1/models</div>
</div>
<div class="endpoint-item">
<div class="endpoint-label">OpenAI Compatible:</div>
<div class="endpoint-url">POST https://api.anthropic.com/v1/chat/completions</div>
</div>
</div>
<div class="endpoint-group">
<div class="endpoint-title">🎯 Available Models</div>
<div class="models-grid">
<div class="model-card">
<div class="model-name">claude-sonnet-4-20250514</div>
<div class="model-description">Latest Claude 4 Sonnet with thinking capabilities</div>
</div>
<div class="model-card">
<div class="model-name">claude-opus-4.1</div>
<div class="model-description">Most powerful Claude model for complex tasks</div>
</div>
<div class="model-card">
<div class="model-name">claude-3.7-sonnet</div>
<div class="model-description">Extended thinking model with step-by-step reasoning</div>
</div>
<div class="model-card">
<div class="model-name">claude-3.5-sonnet</div>
<div class="model-description">Balanced performance and efficiency</div>
</div>
<div class="model-card">
<div class="model-name">claude-3.5-haiku</div>
<div class="model-description">Fast model for lightweight tasks</div>
</div>
</div>
</div>
<div class="capabilities">
<span class="capability-tag">📝 Text</span>
<span class="capability-tag">🖼️ Images</span>
<span class="capability-tag">📄 Documents</span>
<span class="capability-tag">💻 Code</span>
<span class="capability-tag">🔧 Function Calling</span>
<span class="capability-tag">🧠 Extended Thinking</span>
<span class="capability-tag">🔄 Streaming</span>
</div>
<div class="auth-info">
<div class="auth-title">🔑 Authentication</div>
Headers: <code>x-api-key: YOUR_API_KEY</code>, <code>anthropic-version: 2023-06-01</code>
</div>
</div>
</div>
<!-- Google Gemini -->
<div class="provider-section" id="google">
<div class="provider-header">
<div class="provider-name">🌟 Google (Gemini)</div>
<div class="provider-description">Multimodal AI with native understanding of text, images, video, and audio</div>
</div>
<div class="provider-content">
<div class="endpoint-group">
<div class="endpoint-title">🔗 API Endpoints</div>
<div class="endpoint-item">
<div class="endpoint-label">Base URL (AI Studio):</div>
<div class="endpoint-url">https://generativelanguage.googleapis.com</div>
</div>
<div class="endpoint-item">
<div class="endpoint-label">Generate Content:</div>
<div class="endpoint-url">POST https://generativelanguage.googleapis.com/v1beta/models/{model}:generateContent</div>
</div>
<div class="endpoint-item">
<div class="endpoint-label">Vertex AI:</div>
<div class="endpoint-url">https://{location}-aiplatform.googleapis.com/v1/projects/{project}/locations/{location}/publishers/google/models/{model}:generateContent</div>
</div>
<div class="endpoint-item">
<div class="endpoint-label">Live API (Real-time):</div>
<div class="endpoint-url">wss://generativelanguage.googleapis.com/ws/google.ai.generativelanguage.v1alpha.GenerativeService/BidiGenerateContent</div>
</div>
</div>
<div class="endpoint-group">
<div class="endpoint-title">🎯 Available Models</div>
<div class="models-grid">
<div class="model-card">
<div class="model-name">gemini-2.5-pro</div>
<div class="model-description">State-of-the-art thinking model with advanced reasoning</div>
</div>
<div class="model-card">
<div class="model-name">gemini-2.5-flash</div>
<div class="model-description">Best price-performance multimodal model</div>
</div>
<div class="model-card">
<div class="model-name">gemini-2.0-flash</div>
<div class="model-description">Latest multimodal model with enhanced capabilities</div>
</div>
<div class="model-card">
<div class="model-name">gemini-1.5-pro</div>
<div class="model-description">Large context window, handles 2M tokens</div>
</div>
<div class="model-card">
<div class="model-name">gemini-1.5-flash</div>
<div class="model-description">Fast and efficient for everyday tasks</div>
</div>
</div>
</div>
<div class="capabilities">
<span class="capability-tag">📝 Text</span>
<span class="capability-tag">🖼️ Images</span>
<span class="capability-tag">🎥 Video</span>
<span class="capability-tag">🎵 Audio</span>
<span class="capability-tag">💻 Code</span>
<span class="capability-tag">🔧 Function Calling</span>
<span class="capability-tag">🔍 Grounding</span>
<span class="capability-tag">🎨 Image Generation</span>
<span class="capability-tag">🎭 TTS</span>
</div>
<div class="auth-info">
<div class="auth-title">🔑 Authentication</div>
API Key: <code>?key=YOUR_API_KEY</code> or Header: <code>Authorization: Bearer YOUR_ACCESS_TOKEN</code>
</div>
</div>
</div>
<!-- xAI Grok -->
<div class="provider-section" id="xai">
<div class="provider-header">
<div class="provider-name">🚀 xAI (Grok)</div>
<div class="provider-description">Real-time information and reasoning capabilities with live search integration</div>
</div>
<div class="provider-content">
<div class="endpoint-group">
<div class="endpoint-title">🔗 API Endpoints</div>
<div class="endpoint-item">
<div class="endpoint-label">Base URL:</div>
<div class="endpoint-url">https://api.x.ai/v1</div>
</div>
<div class="endpoint-item">
<div class="endpoint-label">Chat Completions:</div>
<div class="endpoint-url">POST https://api.x.ai/v1/chat/completions</div>
</div>
<div class="endpoint-item">
<div class="endpoint-label">Models:</div>
<div class="endpoint-url">GET https://api.x.ai/v1/models</div>
</div>
</div>
<div class="endpoint-group">
<div class="endpoint-title">🎯 Available Models</div>
<div class="models-grid">
<div class="model-card">
<div class="model-name">grok-4</div>
<div class="model-description">Most intelligent model with native tool use and real-time search</div>
</div>
<div class="model-card">
<div class="model-name">grok-4-heavy</div>
<div class="model-description">Most powerful version of Grok 4</div>
</div>
<div class="model-card">
<div class="model-name">grok-3</div>
<div class="model-description">Advanced reasoning and code generation</div>
</div>
<div class="model-card">
<div class="model-name">grok-3-mini</div>
<div class="model-description">Lightweight version for faster responses</div>
</div>
<div class="model-card">
<div class="model-name">grok-beta</div>
<div class="model-description">Latest experimental model (128k context)</div>
</div>
</div>
</div>
<div class="capabilities">
<span class="capability-tag">📝 Text</span>
<span class="capability-tag">🖼️ Images</span>
<span class="capability-tag">💻 Code</span>
<span class="capability-tag">🔧 Function Calling</span>
<span class="capability-tag">🔍 Live Search</span>
<span class="capability-tag">🧠 Reasoning</span>
<span class="capability-tag">🔄 Streaming</span>
</div>
<div class="auth-info">
<div class="auth-title">🔑 Authentication</div>
Header: <code>Authorization: Bearer YOUR_API_KEY</code>
</div>
</div>
</div>
<!-- Mistral AI -->
<div class="provider-section" id="mistral">
<div class="provider-header">
<div class="provider-name">🇫🇷 Mistral AI</div>
<div class="provider-description">European AI with strong multilingual capabilities and specialized models</div>
</div>
<div class="provider-content">
<div class="endpoint-group">
<div class="endpoint-title">🔗 API Endpoints</div>
<div class="endpoint-item">
<div class="endpoint-label">Base URL:</div>
<div class="endpoint-url">https://api.mistral.ai</div>
</div>
<div class="endpoint-item">
<div class="endpoint-label">Chat Completions:</div>
<div class="endpoint-url">POST https://api.mistral.ai/v1/chat/completions</div>
</div>
<div class="endpoint-item">
<div class="endpoint-label">Embeddings:</div>
<div class="endpoint-url">POST https://api.mistral.ai/v1/embeddings</div>
</div>
<div class="endpoint-item">
<div class="endpoint-label">Fine-tuning:</div>
<div class="endpoint-url">POST https://api.mistral.ai/v1/fine_tuning/jobs</div>
</div>
</div>
<div class="endpoint-group">
<div class="endpoint-title">🎯 Available Models</div>
<div class="models-grid">
<div class="model-card">
<div class="model-name">mistral-large-latest</div>
<div class="model-description">Flagship model for complex reasoning and analysis</div>
</div>
<div class="model-card">
<div class="model-name">mistral-medium-2505</div>
<div class="model-description">Balanced frontier-class multimodal performance</div>
</div>
<div class="model-card">
<div class="model-name">mistral-small-latest</div>
<div class="model-description">Cost-effective model for general tasks</div>
</div>
<div class="model-card">
<div class="model-name">codestral-2501</div>
<div class="model-description">Specialized coding model</div>
</div>
<div class="model-card">
<div class="model-name">mistral-embed</div>
<div class="model-description">High-quality text embeddings</div>
</div>
<div class="model-card">
<div class="model-name">mistral-ocr-2505</div>
<div class="model-description">Document processing and OCR</div>
</div>
</div>
</div>
<div class="capabilities">
<span class="capability-tag">📝 Text</span>
<span class="capability-tag">🖼️ Images</span>
<span class="capability-tag">💻 Code</span>
<span class="capability-tag">🔧 Function Calling</span>
<span class="capability-tag">🌍 Multilingual</span>
<span class="capability-tag">📄 Document Processing</span>
<span class="capability-tag">🎯 Fine-tuning</span>
</div>
<div class="auth-info">
<div class="auth-title">🔑 Authentication</div>
Header: <code>Authorization: Bearer YOUR_API_KEY</code>
</div>
</div>
</div>
<!-- DeepSeek -->
<div class="provider-section" id="deepseek">
<div class="provider-header">
<div class="provider-name">🔍 DeepSeek</div>
<div class="provider-description">High-performance models with advanced reasoning capabilities at competitive pricing</div>
</div>
<div class="provider-content">
<div class="endpoint-group">
<div class="endpoint-title">🔗 API Endpoints</div>
<div class="endpoint-item">
<div class="endpoint-label">Base URL:</div>
<div class="endpoint-url">https://api.deepseek.com</div>
</div>
<div class="endpoint-item">
<div class="endpoint-label">Chat Completions:</div>
<div class="endpoint-url">POST https://api.deepseek.com/chat/completions</div>
</div>
<div class="endpoint-item">
<div class="endpoint-label">OpenAI Compatible:</div>
<div class="endpoint-url">POST https://api.deepseek.com/v1/chat/completions</div>
</div>
<div class="endpoint-item">
<div class="endpoint-label">Models:</div>
<div class="endpoint-url">GET https://api.deepseek.com/models</div>
</div>
</div>
<div class="endpoint-group">
<div class="endpoint-title">🎯 Available Models</div>
<div class="models-grid">
<div class="model-card">
<div class="model-name">deepseek-reasoner (R1-0528)</div>
<div class="model-description">Advanced reasoning model with step-by-step thinking</div>
</div>
<div class="model-card">
<div class="model-name">deepseek-chat (V3-0324)</div>
<div class="model-description">General-purpose model with 671B parameters, 37B active</div>
</div>
<div class="model-card">
<div class="model-name">deepseek-r1</div>
<div class="model-description">Reasoning model comparable to OpenAI o1</div>
</div>
<div class="model-card">
<div class="model-name">deepseek-v3</div>
<div class="model-description">Mixture-of-Experts model for general tasks</div>
</div>
</div>
</div>
<div class="capabilities">
<span class="capability-tag">📝 Text</span>
<span class="capability-tag">💻 Code</span>
<span class="capability-tag">🧠 Reasoning</span>
<span class="capability-tag">🔧 Function Calling</span>
<span class="capability-tag">🎯 Mathematics</span>
<span class="capability-tag">💰 Cost-Effective</span>
<span class="capability-tag">🔄 Streaming</span>
</div>
<div class="auth-info">
<div class="auth-title">🔑 Authentication</div>
Header: <code>Authorization: Bearer YOUR_API_KEY</code>
</div>
</div>
</div>
<!-- Meta Llama -->
<div class="provider-section" id="meta">
<div class="provider-header">
<div class="provider-name">🦙 Meta (Llama)</div>
<div class="provider-description">Open-source multimodal models with native tool use and extended context</div>
</div>
<div class="provider-content">
<div class="endpoint-group">
<div class="endpoint-title">🔗 API Endpoints</div>
<div class="endpoint-item">
<div class="endpoint-label">Official API (Preview):</div>
<div class="endpoint-url">https://api.llama.com/v1</div>
</div>
<div class="endpoint-item">
<div class="endpoint-label">Chat Completions:</div>
<div class="endpoint-url">POST https://api.llama.com/v1/chat/completions</div>
</div>
<div class="endpoint-item">
<div class="endpoint-label">Models:</div>
<div class="endpoint-url">GET https://api.llama.com/v1/models</div>
</div>
<div class="endpoint-item">
<div class="endpoint-label">Via Partners (Groq, Cerebras):</div>
<div class="endpoint-url">Multiple partner APIs available</div>
</div>
</div>
<div class="endpoint-group">
<div class="endpoint-title">🎯 Available Models</div>
<div class="models-grid">
<div class="model-card">
<div class="model-name">llama-4-scout</div>
<div class="model-description">17B active params, 10M context, best multimodal in class</div>
</div>
<div class="model-card">
<div class="model-name">llama-4-maverick</div>
<div class="model-description">17B active params, 128 experts, beats GPT-4o</div>
</div>
<div class="model-card">
<div class="model-name">llama-4-behemoth</div>
<div class="model-description">288B active params, teacher model (in training)</div>
</div>
<div class="model-card">
<div class="model-name">llama-3.3-70b</div>
<div class="model-description">Latest 70B model with improved capabilities</div>
</div>
<div class="model-card">
<div class="model-name">llama-3.1-405b</div>
<div class="model-description">Largest open model with 405B parameters</div>
</div>
<div class="model-card">
<div class="model-name">llama-3.1-70b</div>
<div class="model-description">Balanced performance and efficiency</div>
</div>
</div>
</div>
<div class="capabilities">
<span class="capability-tag">📝 Text</span>
<span class="capability-tag">🖼️ Images</span>
<span class="capability-tag">💻 Code</span>
<span class="capability-tag">🔧 Function Calling</span>
<span class="capability-tag">🌍 Multilingual</span>
<span class="capability-tag">📖 Long Context</span>
<span class="capability-tag">🆓 Open Source</span>
</div>
<div class="auth-info">
<div class="auth-title">🔑 Authentication</div>
Header: <code>Authorization: Bearer YOUR_API_KEY</code> (limited preview access)
</div>
</div>
</div>
<!-- Qwen (Alibaba) -->
<div class="provider-section" id="qwen">
<div class="provider-header">
<div class="provider-name">🇨🇳 Alibaba (Qwen)</div>
<div class="provider-description">Multilingual models with strong Asian language support and coding capabilities</div>
</div>
<div class="provider-content">
<div class="endpoint-group">
<div class="endpoint-title">🔗 API Endpoints</div>
<div class="endpoint-item">
<div class="endpoint-label">International Base URL:</div>
<div class="endpoint-url">https://dashscope-intl.aliyuncs.com</div>
</div>
<div class="endpoint-item">
<div class="endpoint-label">OpenAI Compatible:</div>
<div class="endpoint-url">POST https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions</div>
</div>
<div class="endpoint-item">
<div class="endpoint-label">China Base URL:</div>
<div class="endpoint-url">https://dashscope.aliyuncs.com</div>
</div>
<div class="endpoint-item">
<div class="endpoint-label">Multimodal Generation:</div>
<div class="endpoint-url">POST https://dashscope-intl.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation</div>
</div>
</div>
<div class="endpoint-group">
<div class="endpoint-title">🎯 Available Models</div>
<div class="models-grid">
<div class="model-card">
<div class="model-name">qwen-max-2025-01-25</div>
<div class="model-description">Latest flagship model, outperforms DeepSeek V3</div>
</div>
<div class="model-card">
<div class="model-name">qwen3-235b-a22b-instruct-2507</div>
<div class="model-description">Large model with 256K context, 1M token support</div>
</div>
<div class="model-card">
<div class="model-name">qwen3-30b-a3b-instruct-2507</div>
<div class="model-description">Mid-size model with excellent performance</div>
</div>
<div class="model-card">
<div class="model-name">qwen3-coder-480b-a35b</div>
<div class="model-description">Specialized coding model with 480B params</div>
</div>
<div class="model-card">
<div class="model-name">qwen2.5-72b</div>
<div class="model-description">Powerful model for general tasks</div>
</div>
<div class="model-card">
<div class="model-name">qwen-vl</div>
<div class="model-description">Vision-language model for multimodal tasks</div>
</div>
</div>
</div>
<div class="capabilities">
<span class="capability-tag">📝 Text</span>
<span class="capability-tag">🖼️ Images</span>
<span class="capability-tag">🎥 Video</span>
<span class="capability-tag">💻 Code</span>
<span class="capability-tag">🔧 Function Calling</span>
<span class="capability-tag">🌏 Asian Languages</span>
<span class="capability-tag">🧠 Thinking Mode</span>
</div>
<div class="auth-info">
<div class="auth-title">🔑 Authentication</div>
Header: <code>Authorization: Bearer YOUR_API_KEY</code> (Alibaba Cloud API Key)
</div>
</div>
</div>
<!-- Together AI -->
<div class="provider-section" id="together">
<div class="provider-header">
<div class="provider-name">🤝 Together AI</div>
<div class="provider-description">Platform with 200+ open-source models for various tasks and use cases</div>
</div>
<div class="provider-content">
<div class="endpoint-group">
<div class="endpoint-title">🔗 API Endpoints</div>
<div class="endpoint-item">
<div class="endpoint-label">Base URL:</div>
<div class="endpoint-url">https://api.together.xyz</div>
</div>
<div class="endpoint-item">
<div class="endpoint-label">Chat Completions:</div>
<div class="endpoint-url">POST https://api.together.xyz/v1/chat/completions</div>
</div>
<div class="endpoint-item">
<div class="endpoint-label">Completions:</div>
<div class="endpoint-url">POST https://api.together.xyz/v1/completions</div>
</div>
<div class="endpoint-item">
<div class="endpoint-label">Image Generation:</div>
<div class="endpoint-url">POST https://api.together.xyz/v1/images/generations</div>
</div>
<div class="endpoint-item">
<div class="endpoint-label">Fine-tuning:</div>
<div class="endpoint-url">POST https://api.together.xyz/v1/fine-tuning/jobs</div>
</div>
</div>
<div class="endpoint-group">
<div class="endpoint-title">🎯 Popular Models</div>
<div class="models-grid">
<div class="model-card">
<div class="model-name">meta-llama/Llama-4-Maverick-17B-128E-Instruct</div>
<div class="model-description">Latest Llama 4 model</div>
</div>
<div class="model-card">
<div class="model-name">deepseek-ai/DeepSeek-V3</div>
<div class="model-description">DeepSeek's latest model</div>
</div>
<div class="model-card">
<div class="model-name">Qwen/Qwen2.5-Coder-32B-Instruct</div>
<div class="model-description">Qwen coding specialist</div>
</div>
<div class="model-card">
<div class="model-name">mistralai/Mixtral-8x7B-Instruct-v0.1</div>
<div class="model-description">Mistral's MoE model</div>
</div>
<div class="model-card">
<div class="model-name">togethercomputer/StripedHyena-Nous-7B</div>
<div class="model-description">Fast alternative architecture</div>
</div>
</div>
</div>
<div class="capabilities">
<span class="capability-tag">📝 Text</span>
<span class="capability-tag">🖼️ Images</span>
<span class="capability-tag">💻 Code</span>
<span class="capability-tag">🎨 Image Generation</span>
<span class="capability-tag">🎯 Fine-tuning</span>
<span class="capability-tag">🔧 Custom Models</span>
<span class="capability-tag">⚡ Fast Inference</span>
</div>
<div class="auth-info">
<div class="auth-title">🔑 Authentication</div>
Header: <code>Authorization: Bearer YOUR_API_KEY</code>
</div>
</div>
</div>
<!-- Groq -->
<div class="provider-section" id="groq">
<div class="provider-header">
<div class="provider-name">⚡ Groq</div>
<div class="provider-description">Ultra-fast inference with Language Processing Units (LPUs) for speed-critical applications</div>
</div>
<div class="provider-content">
<div class="endpoint-group">
<div class="endpoint-title">🔗 API Endpoints</div>
<div class="endpoint-item">
<div class="endpoint-label">Base URL:</div>
<div class="endpoint-url">https://api.groq.com</div>
</div>
<div class="endpoint-item">
<div class="endpoint-label">Chat Completions:</div>
<div class="endpoint-url">POST https://api.groq.com/openai/v1/chat/completions</div>
</div>
<div class="endpoint-item">
<div class="endpoint-label">Models:</div>
<div class="endpoint-url">GET https://api.groq.com/openai/v1/models</div>
</div>
</div>
<div class="endpoint-group">
<div class="endpoint-title">🎯 Available Models</div>
<div class="models-grid">
<div class="model-card">
<div class="model-name">llama-3.3-70b-versatile</div>
<div class="model-description">Latest Llama model optimized for Groq</div>
</div>
<div class="model-card">
<div class="model-name">llama-3.1-8b-instant</div>
<div class="model-description">Ultra-fast 8B model for quick responses</div>
</div>
<div class="model-card">
<div class="model-name">mixtral-8x7b-32768</div>
<div class="model-description">Mistral's MoE model with extended context</div>
</div>
<div class="model-card">
<div class="model-name">gemma2-9b-it</div>
<div class="model-description">Google's Gemma model</div>
</div>
<div class="model-card">
<div class="model-name">gpt-oss-120b</div>
<div class="model-description">OpenAI open-source model</div>
</div>
</div>
</div>
<div class="capabilities">
<span class="capability-tag">📝 Text</span>
<span class="capability-tag">💻 Code</span>
<span class="capability-tag">⚡ Ultra-Fast</span>
<span class="capability-tag">🔧 Function Calling</span>
<span class="capability-tag">🏢 Enterprise</span>
<span class="capability-tag">🔄 Streaming</span>
</div>
<div class="auth-info">
<div class="auth-title">🔑 Authentication</div>
Header: <code>Authorization: Bearer YOUR_API_KEY</code>
</div>
</div>
</div>
<!-- Cohere -->
<div class="provider-section" id="cohere">
<div class="provider-header">
<div class="provider-name">🎯 Cohere</div>
<div class="provider-description">Enterprise-focused AI with specialized models for RAG, embeddings, and reranking</div>
</div>
<div class="provider-content">
<div class="endpoint-group">
<div class="endpoint-title">🔗 API Endpoints</div>
<div class="endpoint-item">
<div class="endpoint-label">Base URL:</div>
<div class="endpoint-url">https://api.cohere.ai</div>
</div>
<div class="endpoint-item">
<div class="endpoint-label">Chat:</div>
<div class="endpoint-url">POST https://api.cohere.ai/v1/chat</div>
</div>
<div class="endpoint-item">
<div class="endpoint-label">Embeddings:</div>
<div class="endpoint-url">POST https://api.cohere.ai/v1/embed</div>
</div>
<div class="endpoint-item">
<div class="endpoint-label">Rerank:</div>
<div class="endpoint-url">POST https://api.cohere.ai/v1/rerank</div>
</div>
<div class="endpoint-item">
<div class="endpoint-label">Classify:</div>
<div class="endpoint-url">POST https://api.cohere.ai/v1/classify</div>
</div>
</div>
<div class="endpoint-group">
<div class="endpoint-title">🎯 Available Models</div>
<div class="models-grid">
<div class="model-card">
<div class="model-name">command-r-plus</div>
<div class="model-description">Most powerful model with 128K context for RAG</div>
</div>
<div class="model-card">
<div class="model-name">command-r</div>
<div class="model-description">Balanced model for complex workflows</div>
</div>
<div class="model-card">
<div class="model-name">command-a</div>
<div class="model-description">Advanced model for enterprise use</div>
</div>
<div class="model-card">
<div class="model-name">command-a-vision</div>
<div class="model-description">Multimodal model with image understanding</div>
</div>
<div class="model-card">
<div class="model-name">embed-english-v3.0</div>
<div class="model-description">High-quality English embeddings</div>
</div>
<div class="model-card">
<div class="model-name">rerank-english-v3.0</div>
<div class="model-description">Advanced reranking for search</div>
</div>
</div>
</div>
<div class="capabilities">
<span class="capability-tag">📝 Text</span>
<span class="capability-tag">🖼️ Images</span>
<span class="capability-tag">🔍 RAG</span>
<span class="capability-tag">📊 Embeddings</span>
<span class="capability-tag">🔄 Reranking</span>
<span class="capability-tag">🏷️ Classification</span>
<span class="capability-tag">🏢 Enterprise</span>
</div>
<div class="auth-info">
<div class="auth-title">🔑 Authentication</div>
Header: <code>Authorization: Bearer YOUR_API_KEY</code>
</div>
</div>
</div>
<div class="last-updated">
📅 Last updated: August 8, 2025 | 🔄 Continuously refreshed with the latest API information
<br>
🚨 <strong>BREAKING:</strong> GPT-5 released August 7, 2025 - Available to ALL users including free!
<br>
💡 For the most current pricing and model availability, always check the official documentation
</div>
</div>
<script>
function searchContent(query) {
const sections = document.querySelectorAll('.provider-section');
const searchTerm = query.toLowerCase();
sections.forEach(section => {
const content = section.textContent.toLowerCase();
if (content.includes(searchTerm) || searchTerm === '') {
section.style.display = 'block';
} else {
section.style.display = 'none';
}
});
}
function downloadHTML() {
const htmlContent = document.documentElement.outerHTML;
const blob = new Blob([htmlContent], { type: 'text/html' });
const url = URL.createObjectURL(blob);
const a = document.createElement('a');
a.href = url;
a.download = 'ultimate-llm-api-docs-2025.html';
document.body.appendChild(a);
a.click();
document.body.removeChild(a);
URL.revokeObjectURL(url);
}
function downloadJSON() {
const apiData = {
"lastUpdated": "August 8, 2025",
"majorUpdate": "GPT-5 released August 7, 2025",
"providers": [
{
"name": "OpenAI",
"baseUrl": "https://api.openai.com",
"chatEndpoint": "https://api.openai.com/v1/chat/completions",
"models": ["gpt-5", "gpt-5-mini", "gpt-5-nano", "gpt-5-chat", "gpt-4.1", "gpt-4.1-mini", "gpt-4.1-nano", "gpt-4o", "o3", "o4-mini", "gpt-image-1"],
"capabilities": ["text", "images", "audio", "code", "function_calling", "built_in_reasoning", "real_time_router", "streaming", "free_access"],
"auth": "Bearer token",
"notes": "GPT-5 released Aug 7, 2025. Available to all users including free. GPT-4.5 deprecated July 2025."
},
{
"name": "Anthropic",
"baseUrl": "https://api.anthropic.com",
"chatEndpoint": "https://api.anthropic.com/v1/messages",
"models": ["claude-sonnet-4-20250514", "claude-opus-4.1", "claude-3.7-sonnet", "claude-3.5-sonnet", "claude-3.5-haiku"],
"capabilities": ["text", "images", "documents", "code", "function_calling", "extended_thinking", "streaming"],
"auth": "x-api-key header"
},
{
"name": "Google",
"baseUrl": "https://generativelanguage.googleapis.com",
"chatEndpoint": "https://generativelanguage.googleapis.com/v1beta/models/{model}:generateContent",
"models": ["gemini-2.5-pro", "gemini-2.5-flash", "gemini-2.0-flash", "gemini-1.5-pro", "gemini-1.5-flash"],
"capabilities": ["text", "images", "video", "audio", "code", "function_calling", "grounding", "image_generation", "tts"],
"auth": "API key or Bearer token"
},
{
"name": "xAI",
"baseUrl": "https://api.x.ai/v1",
"chatEndpoint": "https://api.x.ai/v1/chat/completions",
"models": ["grok-4", "grok-4-heavy", "grok-3", "grok-3-mini", "grok-beta"],
"capabilities": ["text", "images", "code", "function_calling", "live_search", "reasoning", "streaming"],
"auth": "Bearer token"
},
{
"name": "Mistral",
"baseUrl": "https://api.mistral.ai",
"chatEndpoint": "https://api.mistral.ai/v1/chat/completions",
"models": ["mistral-large-latest", "mistral-medium-2505", "mistral-small-latest", "codestral-2501", "mistral-embed", "mistral-ocr-2505"],
"capabilities": ["text", "images", "code", "function_calling", "multilingual", "document_processing", "fine_tuning"],
"auth": "Bearer token"
},
{
"name": "DeepSeek",
"baseUrl": "https://api.deepseek.com",
"chatEndpoint": "https://api.deepseek.com/chat/completions",
"models": ["deepseek-reasoner", "deepseek-chat", "deepseek-r1", "deepseek-v3"],
"capabilities": ["text", "code", "reasoning", "function_calling", "mathematics", "cost_effective", "streaming"],
"auth": "Bearer token"
},
{
"name": "Meta",
"baseUrl": "https://api.llama.com/v1",
"chatEndpoint": "https://api.llama.com/v1/chat/completions",
"models": ["llama-4-scout", "llama-4-maverick", "llama-4-behemoth", "llama-3.3-70b", "llama-3.1-405b", "llama-3.1-70b"],
"capabilities": ["text", "images", "code", "function_calling", "multilingual", "long_context", "open_source"],
"auth": "Bearer token (limited preview)"
},
{
"name": "Qwen",
"baseUrl": "https://dashscope-intl.aliyuncs.com",
"chatEndpoint": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions",
"models": ["qwen-max-2025-01-25", "qwen3-235b-a22b-instruct-2507", "qwen3-30b-a3b-instruct-2507", "qwen3-coder-480b-a35b", "qwen2.5-72b", "qwen-vl"],
"capabilities": ["text", "images", "video", "code", "function_calling", "asian_languages", "thinking_mode"],
"auth": "Bearer token (Alibaba Cloud)"
},
{
"name": "Together",
"baseUrl": "https://api.together.xyz",
"chatEndpoint": "https://api.together.xyz/v1/chat/completions",
"models": ["meta-llama/Llama-4-Maverick-17B-128E-Instruct", "deepseek-ai/DeepSeek-V3", "Qwen/Qwen2.5-Coder-32B-Instruct", "mistralai/Mixtral-8x7B-Instruct-v0.1"],
"capabilities": ["text", "images", "code", "image_generation", "fine_tuning", "custom_models", "fast_inference"],
"auth": "Bearer token"
},
{
"name": "Groq",
"baseUrl": "https://api.groq.com",
"chatEndpoint": "https://api.groq.com/openai/v1/chat/completions",
"models": ["llama-3.3-70b-versatile", "llama-3.1-8b-instant", "mixtral-8x7b-32768", "gemma2-9b-it", "gpt-oss-120b"],
"capabilities": ["text", "code", "ultra_fast", "function_calling", "enterprise", "streaming"],
"auth": "Bearer token"
},
{
"name": "Cohere",
"baseUrl": "https://api.cohere.ai",
"chatEndpoint": "https://api.cohere.ai/v1/chat",
"models": ["command-r-plus", "command-r", "command-a", "command-a-vision", "embed-english-v3.0", "rerank-english-v3.0"],
"capabilities": ["text", "images", "rag", "embeddings", "reranking", "classification", "enterprise"],
"auth": "Bearer token"
}
]
};
const jsonString = JSON.stringify(apiData, null, 2);
const blob = new Blob([jsonString], { type: 'application/json' });
const url = URL.createObjectURL(blob);
const a = document.createElement('a');
a.href = url;
a.download = 'llm-api-reference-2025.json';
document.body.appendChild(a);
a.click();
document.body.removeChild(a);
URL.revokeObjectURL(url);
}
// Smooth scrolling for navigation
document.querySelectorAll('.toc-item a').forEach(link => {
link.addEventListener('click', function(e) {
e.preventDefault();
const target = document.querySelector(this.getAttribute('href'));
target.scrollIntoView({ behavior: 'smooth' });
});
});
// Add some interactive elements
document.addEventListener('DOMContentLoaded', function() {
// Add copy functionality to endpoint URLs
document.querySelectorAll('.endpoint-url').forEach(url => {
url.addEventListener('click', function() {
navigator.clipboard.writeText(this.textContent).then(() => {
const original = this.textContent;
this.textContent = '✅ Copied!';
setTimeout(() => {
this.textContent = original;
}, 1000);
});
});
url.style.cursor = 'pointer';
url.title = 'Click to copy';
});
});
</script>
</body>
</html>