Skip to content
LAM
Read Home Blog
Make Projects HTML Tools Games
Touch grass Notes Resume Links
Home Blog HTML Projects
Tools Games Notes Resume Links
Back The Ultimate LLM API Documentation Programming
Download Open
Show description 1,729 chars · Programming

The Ultimate LLM API Documentation

The Ultimate LLM API Documentation










The Ultimate LLM API Documentation

A comprehensive guide to the APIs of major Large Language Models.




Download Full API Doc







OpenAI

Official Documentation



Core Info

Base URL: https://api.openai.com/v1

Authentication: Bearer Token in Authorization header.



August 2025 Update: OpenAI has introduced GPT-5 and new open-weight models. GPT-4o is expected to be phased out for API users in favor of GPT-5.




Models & Endpoints





Model Name

API Endpoint

Modalities






gpt-5, gpt-5-mini, gpt-5-nano

/chat/completions

Text, Images, Advanced Tool Use




gpt-oss-120b, gpt-oss-20b

/chat/completions

Text (Open-weight reasoning models)




gpt-image-1

/images/generations

Text-to-Image




TTS (Text-to-Speech)

/audio/speech

Text-to-Audio




Whisper

/audio/transcriptions

Audio-to-Text















Anthropic

Official Documentation



Core Info

Base URL: https://api.anthropic.com/v1

Authentication: API Key via `x-api-key` header.



August 2025 Update: Anthropic released Claude Opus 4.1 on Aug 5, 2025, with improved coding and reasoning.




Models & Endpoints





Model Name

API Endpoint

Modalities






claude-opus-4-1-20250805 (Claude Opus 4.1)

/messages

Text, Images




claude-opus-4, claude-sonnet-4, etc.

/messages

Text, Images (Older versions)















Google

Official Documentation



Core Info

Base URL: https://generativelanguage.googleapis.com/v1beta

Authentication: API Key passed as a `key` query parameter.



August 2025 Update: Gemini 2.5 models are now the primary recommendation.…

The Ultimate LLM API Documentation

23,584 bytes · HTML source
<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <meta name="viewport" content="width=device-width, initial-scale=1.0">
    <title>The Ultimate LLM API Documentation</title>
    <script src="https://cdn.tailwindcss.com"></script>
    <link rel="preconnect" href="https://fonts.googleapis.com">
    <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
    <link href="https://fonts.googleapis.com/css2?family=Press+Start+2P&family=VT323&display=swap" rel="stylesheet">
    <style>
        /* --- Video Game Theme Styles --- */
        body {
            font-family: 'VT323', monospace;
            background-color: #000000;
            color: #FFFFFF;
            font-size: 1.25rem; /* Larger base font for pixel style */
        }
        h1, h2, h3, button {
            font-family: 'Press Start 2P', cursive;
        }
        .api-section {
            border: 3px solid #FFFFFF;
            border-radius: 0;
            margin-bottom: 2rem;
            overflow: hidden;
            background-color: #000000;
            box-shadow: 8px 8px 0px #FFFFFF; /* Pixelated shadow effect */
        }
        .api-header {
            background-color: #000000;
            padding: 1rem 1.5rem;
            border-bottom: 3px solid #FFFFFF;
        }
        .api-content {
            padding: 1.5rem;
            background-color: #000000;
        }
        .code-block {
            background-color: #1a1a1a;
            color: #00FF00; /* Green terminal text */
            padding: 1rem;
            border-radius: 0;
            border: 2px solid #555555;
            font-family: 'VT323', monospace;
            white-space: pre-wrap;
            word-wrap: break-word;
            font-size: 1.1rem;
        }
        .table-wrapper {
            overflow-x: auto;
        }
        table {
            width: 100%;
            border-collapse: collapse;
            border: 2px solid #FFFFFF;
        }
        th, td {
            padding: 0.75rem 1rem;
            text-align: left;
            border: 2px solid #FFFFFF;
        }
        th {
            background-color: #000000;
            color: #FFFFFF;
        }
        .note {
            background-color: #000000;
            border: 3px dashed #FFFFFF;
            padding: 1rem;
            margin-top: 1rem;
            border-radius: 0;
        }
        .note strong {
             color: #FFFF00; /* Yellow for emphasis */
        }
        #download-btn {
            background-color: #FFFFFF;
            color: #000000;
            border: 3px solid #FFFFFF;
            padding: 0.75rem 1.5rem;
            text-transform: uppercase;
            transition: all 0.2s ease-in-out;
            box-shadow: 4px 4px 0px #FFFFFF;
        }
        #download-btn:hover {
            background-color: #000000;
            color: #FFFFFF;
            box-shadow: none;
            transform: translate(4px, 4px);
        }
        a {
            color: #00FFFF; /* Cyan for links */
            text-decoration: underline;
        }
        a:hover {
            color: #FFFFFF;
            background-color: #00FFFF;
        }
    </style>
</head>
<body class="bg-black text-white">

    <div id="docs-container" class="max-w-7xl mx-auto p-4 sm:p-6 lg:p-8">
        <header class="text-center mb-16">
            <h1 class="text-4xl sm:text-5xl font-bold text-white mb-4">The Ultimate LLM API Documentation</h1>
            <p class="mt-4 text-xl text-gray-300 tracking-wider">A comprehensive guide to the APIs of major Large Language Models.</p>
            <p class="text-base text-gray-500 mt-2" id="last-updated"></p>
            <button id="download-btn" class="mt-8">
                Download Full API Doc
            </button>
        </header>

        <!-- OpenAI Section -->
        <section class="api-section">
            <div class="api-header">
                <h2 class="text-2xl font-semibold text-white">OpenAI</h2>
                <a href="https://platform.openai.com/docs/api-reference" target="_blank">Official Documentation</a>
            </div>
            <div class="api-content">
                <h3 class="text-xl font-semibold text-white mb-2">Core Info</h3>
                <p><strong class="text-gray-200">Base URL:</strong> <span class="code-block inline-block mt-1">https://api.openai.com/v1</span></p>
                <p class="mt-2"><strong class="text-gray-200">Authentication:</strong> Bearer Token in Authorization header.</p>
                
                <div class="note">
                    <p><strong class="text-indigo-400">August 2025 Update:</strong> OpenAI has introduced GPT-5 and new open-weight models. GPT-4o is expected to be phased out for API users in favor of GPT-5.</p>
                </div>

                <h3 class="text-xl font-semibold text-white mt-6 mb-4">Models & Endpoints</h3>
                <div class="table-wrapper">
                    <table>
                        <thead>
                            <tr>
                                <th>Model Name</th>
                                <th>API Endpoint</th>
                                <th>Modalities</th>
                            </tr>
                        </thead>
                        <tbody>
                            <tr>
                                <td>gpt-5, gpt-5-mini, gpt-5-nano</td>
                                <td><span class="code-block">/chat/completions</span></td>
                                <td>Text, Images, Advanced Tool Use</td>
                            </tr>
                             <tr>
                                <td>gpt-oss-120b, gpt-oss-20b</td>
                                <td><span class="code-block">/chat/completions</span></td>
                                <td>Text (Open-weight reasoning models)</td>
                            </tr>
                            <tr>
                                <td>gpt-image-1</td>
                                <td><span class="code-block">/images/generations</span></td>
                                <td>Text-to-Image</td>
                            </tr>
                            <tr>
                                <td>TTS (Text-to-Speech)</td>
                                <td><span class="code-block">/audio/speech</span></td>
                                <td>Text-to-Audio</td>
                            </tr>
                            <tr>
                                <td>Whisper</td>
                                <td><span class="code-block">/audio/transcriptions</span></td>
                                <td>Audio-to-Text</td>
                            </tr>
                        </tbody>
                    </table>
                </div>
            </div>
        </section>

        <!-- Anthropic Section -->
        <section class="api-section">
            <div class="api-header">
                <h2 class="text-2xl font-semibold text-white">Anthropic</h2>
                <a href="https://docs.anthropic.com/claude/reference/getting-started-with-the-api" target="_blank">Official Documentation</a>
            </div>
            <div class="api-content">
                <h3 class="text-xl font-semibold text-white mb-2">Core Info</h3>
                <p><strong class="text-gray-200">Base URL:</strong> <span class="code-block inline-block mt-1">https://api.anthropic.com/v1</span></p>
                <p class="mt-2"><strong class="text-gray-200">Authentication:</strong> API Key via `x-api-key` header.</p>
                
                 <div class="note">
                    <p><strong class="text-indigo-400">August 2025 Update:</strong> Anthropic released Claude Opus 4.1 on Aug 5, 2025, with improved coding and reasoning.</p>
                </div>

                <h3 class="text-xl font-semibold text-white mt-6 mb-4">Models & Endpoints</h3>
                <div class="table-wrapper">
                    <table>
                        <thead>
                            <tr>
                                <th>Model Name</th>
                                <th>API Endpoint</th>
                                <th>Modalities</th>
                            </tr>
                        </thead>
                        <tbody>
                            <tr>
                                <td>claude-opus-4-1-20250805 (Claude Opus 4.1)</td>
                                <td><span class="code-block">/messages</span></td>
                                <td>Text, Images</td>
                            </tr>
                             <tr>
                                <td>claude-opus-4, claude-sonnet-4, etc.</td>
                                <td><span class="code-block">/messages</span></td>
                                <td>Text, Images (Older versions)</td>
                            </tr>
                        </tbody>
                    </table>
                </div>
            </div>
        </section>

        <!-- Google Section -->
        <section class="api-section">
            <div class="api-header">
                <h2 class="text-2xl font-semibold text-white">Google</h2>
                <a href="https://ai.google.dev/docs/api/rest" target="_blank">Official Documentation</a>
            </div>
            <div class="api-content">
                <h3 class="text-xl font-semibold text-white mb-2">Core Info</h3>
                <p><strong class="text-gray-200">Base URL:</strong> <span class="code-block inline-block mt-1">https://generativelanguage.googleapis.com/v1beta</span></p>
                <p class="mt-2"><strong class="text-gray-200">Authentication:</strong> API Key passed as a `key` query parameter.</p>
                
                <div class="note">
                    <p><strong class="text-indigo-400">August 2025 Update:</strong> Gemini 2.5 models are now the primary recommendation. Gemini 1.5 models are no longer available for new projects.</p>
                </div>

                <h3 class="text-xl font-semibold text-white mt-6 mb-4">Models & Endpoints</h3>
                <div class="table-wrapper">
                    <table>
                        <thead>
                            <tr>
                                <th>Model Name</th>
                                <th>API Endpoint</th>
                                <th>Modalities</th>
                            </tr>
                        </thead>
                        <tbody>
                            <tr>
                                <td>gemini-2.5-pro</td>
                                <td><span class="code-block">/models/gemini-2.5-pro:generateContent</span></td>
                                <td>Text, Images, Audio, Video</td>
                            </tr>
                             <tr>
                                <td>gemini-2.5-flash</td>
                                <td><span class="code-block">/models/gemini-2.5-flash:generateContent</span></td>
                                <td>Text, Images, Audio, Video</td>
                            </tr>
                            <tr>
                                <td>Veo (Video Generation)</td>
                                <td><span class="code-block">/models/veo-3.0-generate-preview:predict</span></td>
                                <td>Image/Text-to-Video</td>
                            </tr>
                            <tr>
                                <td>gemini-embedding-001</td>
                                <td><span class="code-block">/models/gemini-embedding-001:embedContent</span></td>
                                <td>Text</td>
                            </tr>
                        </tbody>
                    </table>
                </div>
            </div>
        </section>

        <!-- Mistral AI Section -->
        <section class="api-section">
            <div class="api-header">
                <h2 class="text-2xl font-semibold text-white">Mistral AI</h2>
                <a href="https://docs.mistral.ai/api/" target="_blank">Official Documentation</a>
            </div>
            <div class="api-content">
                <h3 class="text-xl font-semibold text-white mb-2">Core Info</h3>
                <p><strong class="text-gray-200">Base URL:</strong> <span class="code-block inline-block mt-1">https://api.mistral.ai/v1</span></p>
                <p class="mt-2"><strong class="text-gray-200">Authentication:</strong> Bearer Token in Authorization header.</p>
                
                <div class="note">
                    <p><strong class="text-indigo-400">August 2025 Update:</strong> Mistral announced Codestral 25.08, a new version of their coding model with significant performance improvements.</p>
                </div>

                <h3 class="text-xl font-semibold text-white mt-6 mb-4">Models & Endpoints</h3>
                <div class="table-wrapper">
                    <table>
                        <thead>
                            <tr>
                                <th>Model Name</th>
                                <th>API Endpoint</th>
                                <th>Modalities</th>
                            </tr>
                        </thead>
                        <tbody>
                            <tr>
                                <td>mistral-large-latest, mistral-small-latest, etc.</td>
                                <td><span class="code-block">/chat/completions</span></td>
                                <td>Text</td>
                            </tr>
                            <tr>
                                <td>codestral-2508</td>
                                <td><span class="code-block">/chat/completions</span></td>
                                <td>Code</td>
                            </tr>
                            <tr>
                                <td>mistral-embed</td>
                                <td><span class="code-block">/embeddings</span></td>
                                <td>Text</td>
                            </tr>
                        </tbody>
                    </table>
                </div>
            </div>
        </section>
        
        <!-- xAI Section -->
        <section class="api-section">
            <div class="api-header">
                <h2 class="text-2xl font-semibold text-white">xAI</h2>
                <a href="https://docs.x.ai/" target="_blank">Official Documentation</a>
            </div>
            <div class="api-content">
                <h3 class="text-xl font-semibold text-white mb-2">Core Info</h3>
                <p><strong class="text-gray-200">Base URL:</strong> <span class="code-block inline-block mt-1">https://api.x.ai/v1</span></p>
                <p class="mt-2"><strong class="text-gray-200">Authentication:</strong> Bearer Token in Authorization header.</p>
                
                <div class="note">
                    <p><strong class="text-indigo-400">August 2025 Update:</strong> Elon Musk announced that Grok 2 will be open-sourced soon. An official API release for Grok 2 is anticipated to follow.</p>
                </div>

                <h3 class="text-xl font-semibold text-white mt-6 mb-4">Models & Endpoints</h3>
                <div class="table-wrapper">
                    <table>
                        <thead>
                            <tr>
                                <th>Model Name</th>
                                <th>API Endpoint</th>
                                <th>Modalities</th>
                            </tr>
                        </thead>
                        <tbody>
                            <tr>
                                <td>grok-1.5-vision-preview, grok-1.5</td>
                                <td><span class="code-block">/chat/completions</span></td>
                                <td>Text, Images</td>
                            </tr>
                        </tbody>
                    </table>
                </div>
            </div>
        </section>

        <!-- DeepSeek Section -->
        <section class="api-section">
            <div class="api-header">
                <h2 class="text-2xl font-semibold text-white">DeepSeek</h2>
                <a href="https://platform.deepseek.com/api-docs" target="_blank">Official Documentation</a>
            </div>
            <div class="api-content">
                <h3 class="text-xl font-semibold text-white mb-2">Core Info</h3>
                <p><strong class="text-gray-200">Base URL:</strong> <span class="code-block inline-block mt-1">https://api.deepseek.com</span></p>
                <p class="mt-2"><strong class="text-gray-200">Authentication:</strong> Bearer Token in Authorization header.</p>
                
                <h3 class="text-xl font-semibold text-white mt-6 mb-4">Models & Endpoints</h3>
                <div class="table-wrapper">
                    <table>
                        <thead>
                            <tr>
                                <th>Model Name</th>
                                <th>API Endpoint</th>
                                <th>Modalities</th>
                            </tr>
                        </thead>
                        <tbody>
                            <tr>
                                <td>deepseek-chat, deepseek-coder</td>
                                <td><span class="code-block">/chat/completions</span></td>
                                <td>Text</td>
                            </tr>
                        </tbody>
                    </table>
                </div>
            </div>
        </section>
        
        <!-- Qwen (Alibaba Cloud) Section -->
        <section class="api-section">
            <div class="api-header">
                <h2 class="text-2xl font-semibold text-white">Qwen (Alibaba Cloud)</h2>
                <a href="https://help.aliyun.com/en/model-studio/developer-reference/api-details" target="_blank">Official Documentation</a>
            </div>
            <div class="api-content">
                <h3 class="text-xl font-semibold text-white mb-2">Core Info</h3>
                <p><strong class="text-gray-200">Base URL:</strong> <span class="code-block inline-block mt-1">https://dashscope.aliyuncs.com/api/v1</span></p>
                <p class="mt-2"><strong class="text-gray-200">Authentication:</strong> API Key in Authorization header (e.g., `Authorization: Bearer YOUR_API_KEY`).</p>
                 <div class="note">
                    <p><strong class="text-indigo-400">August 2025 Update:</strong> The powerful `Qwen3 Coder 480B` model was announced, available through partners like Cerebras.</p>
                </div>
                
                <h3 class="text-xl font-semibold text-white mt-6 mb-4">Models & Endpoints</h3>
                <div class="table-wrapper">
                    <table>
                        <thead>
                            <tr>
                                <th>Model Name</th>
                                <th>API Endpoint</th>
                                <th>Modalities</th>
                            </tr>
                        </thead>
                        <tbody>
                            <tr>
                                <td>qwen-max, qwen-vl-max, etc.</td>
                                <td><span class="code-block">/services/aigc/text-generation/generation</span></td>
                                <td>Text, Image, Video, Audio</td>
                            </tr>
                        </tbody>
                    </table>
                </div>
            </div>
        </section>
        
        <!-- Llama (Meta) Section -->
        <section class="api-section">
            <div class="api-header">
                <h2 class="text-2xl font-semibold text-white">Llama (Hosted by Meta)</h2>
                <a href="https://llama.meta.com/docs/" target="_blank">Official Documentation</a>
            </div>
            <div class="api-content">
                <h3 class="text-xl font-semibold text-white mb-2">Core Info</h3>
                <p><strong class="text-gray-200">Base URL:</strong> <span class="code-block inline-block mt-1">https://api.llama.com/v1</span></p>
                <p class="mt-2"><strong class="text-gray-200">Authentication:</strong> Bearer Token in Authorization header.</p>
                <div class="note">
                    <p><strong class="text-indigo-400">Future Update:</strong> Meta has announced the Llama 4 family of models, which will be faster and more capable. Keep an eye out for their official API release.</p>
                </div>
                
                <h3 class="text-xl font-semibold text-white mt-6 mb-4">Models & Endpoints</h3>
                <div class="table-wrapper">
                    <table>
                        <thead>
                            <tr>
                                <th>Model Name</th>
                                <th>API Endpoint</th>
                                <th>Modalities</th>
                            </tr>
                        </thead>
                        <tbody>
                            <tr>
                                <td>Llama 3</td>
                                <td><span class="code-block">/chat/completions</span></td>
                                <td>Text</td>
                            </tr>
                        </tbody>
                    </table>
                </div>
            </div>
        </section>

    </div>

    <script>
        // --- Download Functionality ---
        document.getElementById('download-btn').addEventListener('click', function() {
            // Get the entire HTML content of the page
            const htmlContent = document.documentElement.outerHTML;
            
            // Create a Blob from the HTML content
            const blob = new Blob([htmlContent], { type: 'text/html' });
            
            // Create a temporary link element
            const a = document.createElement('a');
            a.href = URL.createObjectURL(blob);
            a.download = 'llm-api-documentation.html';
            
            // Programmatically click the link to trigger the download
            document.body.appendChild(a);
            a.click();
            
            // Clean up by removing the link
            document.body.removeChild(a);
            URL.revokeObjectURL(a.href);
        });

        // --- Last Updated Timestamp ---
        function setLastUpdated() {
            const lastUpdatedElement = document.getElementById('last-updated');
            // Using a specific locale for consistent formatting
            const formattedDate = 'August 8, 2025';
            lastUpdatedElement.textContent = `Last Updated: ${formattedDate}. Note: This is a snapshot. Always refer to official docs for the latest updates.`;
        }

        // Set the timestamp when the page loads
        window.onload = setLastUpdated;
    </script>

</body>
</html>