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 ultimate llm api docs AI
Download Open
Show description 220 chars · AI

ultimate llm api docs

ultimate llm api docs




ultimate llm api docs - aug 2025 updated

aggregated info on all major llm apis. click sections to expand. data from official docs/searches as of aug 08 2025.

refresh data
download docs

ultimate llm api docs

22,126 bytes · HTML source
<!doctype html>
<html lang="en">
<head>
    <meta charset="utf-8">
    <meta name="viewport" content="width=device-width, initial-scale=1">
    <title>ultimate llm api docs</title>
    <style>
        body {
            background-color: #121212;
            color: #e0e0e0;
            font-family: 'arial', sans-serif;
            margin: 0;
            padding: 20px;
            line-height: 1.6;
        }
        h1, h2, h3 {
            color: #ffffff;
        }
        .container {
            max-width: 1200px;
            margin: 0 auto;
        }
        .section {
            margin-bottom: 20px;
            border: 1px solid #333;
            border-radius: 8px;
            overflow: hidden;
        }
        .section-header {
            background-color: #1f1f1f;
            padding: 15px;
            cursor: pointer;
            display: flex;
            justify-content: space-between;
            align-items: center;
        }
        .section-header:hover {
            background-color: #292929;
        }
        .section-content {
            padding: 15px;
            display: none;
        }
        .active .section-content {
            display: block;
        }
        ul {
            list-style-type: disc;
            padding-left: 20px;
        }
        pre {
            background-color: #1f1f1f;
            padding: 10px;
            border-radius: 4px;
            overflow-x: auto;
        }
        button {
            background-color: #333;
            color: #fff;
            border: none;
            padding: 10px 20px;
            cursor: pointer;
            border-radius: 4px;
        }
        button:hover {
            background-color: #444;
        }
        #refresh-btn {
            margin-bottom: 20px;
        }
    </style>
</head>
<body>
    <div class="container">
        <h1>ultimate llm api docs - aug 2025 updated</h1>
        <p>aggregated info on all major llm apis. click sections to expand. data from official docs/searches as of aug 08 2025.</p>
        <button id="refresh-btn">refresh data</button>
        <button id="download-btn">download docs</button>

        <div id="providers"></div>
    </div>

    <script>
        // embedded data fallback - updated from latest searches/browses aug 08 2025
        const fallbackData = [
            {
                name: 'openai',
                models: ['gpt-5', 'gpt-5-mini', 'gpt-5-nano', 'gpt-5-chat', 'gpt-oss-120b', 'gpt-oss-20b', 'gpt-4.1', 'gpt-4.1-nano', 'gpt-4.1-mini'], // pulled from azure as proxy
                baseUrl: 'https://api.openai.com/v1',
                endpoints: {
                    chat: '/chat/completions (post) - text/chat',
                    text: '/completions (post) - legacy text gen',
                    images: '/images/generations (post) - dall-e image gen, /images/edits, /images/variations',
                    audio: '/audio/transcriptions (post) - whisper stt, /audio/translations (post), /audio/speech (post) - tts',
                    video: 'no dedicated, but vision in /chat/completions with image/video frames'
                }
            },
            {
                name: 'anthropic',
                models: ['claude-opus-4-1-20250805', 'claude-opus-4-20250514', 'claude-sonnet-4-20250514', 'claude-3-7-sonnet-20250219', 'claude-3-5-sonnet-20241022', 'claude-3-5-sonnet-20240620', 'claude-3-5-haiku-20241022', 'claude-3-haiku-20240307'],
                baseUrl: 'https://api.anthropic.com/v1',
                endpoints: {
                    chat: '/messages (post) - chat/text',
                    text: '/messages (post) - same as chat',
                    images: '/messages (post) - vision with base64 images (jpeg/png/gif/webp)',
                    audio: 'none',
                    video: 'none'
                }
            },
            {
                name: 'xai',
                models: ['grok-4', 'grok-3', 'grok-3-mini', 'grok-2-image-1212'],
                baseUrl: 'https://api.x.ai/v1 (assumed, sdk compat)',
                endpoints: {
                    chat: '/chat/completions (openai/anthropic compat) - text/chat',
                    text: 'same as chat',
                    images: 'image gen for grok-2-image-1212, no specific path listed',
                    audio: 'none',
                    video: 'none'
                }
            },
            {
                name: 'google gemini',
                models: ['gemini-2.5-pro', 'gemini-2.5-flash', 'gemini-2.5-flash-lite', 'gemini-live-2.5-flash-preview', 'gemini-2.5-flash-preview-native-audio-dialog', 'gemini-2.5-flash-exp-native-audio-thinking-dialog', 'gemini-2.5-flash-preview-tts', 'gemini-2.5-pro-preview-tts', 'gemini-2.0-flash', 'gemini-2.0-flash-preview-image-generation', 'gemini-2.0-flash-lite', 'gemini-2.0-flash-live-001', 'gemini-1.5-flash (deprecated)', 'gemini-1.5-flash-8b (deprecated)', 'gemini-1.5-pro (deprecated)'],
                baseUrl: 'https://generativelanguage.googleapis.com/v1beta',
                endpoints: {
                    chat: '/models/{model}:generateContent (post) - text/chat',
                    text: 'same as above',
                    images: 'native image gen/support in generateContent',
                    audio: 'support in generateContent for audio',
                    video: 'support in generateContent for video frames'
                }
            },
            {
                name: 'mistral',
                models: ['mistral-medium-2505', 'magistral-medium-2507', 'codestral-2508', 'voxtral-mini-2507', 'devstral-medium-2507', 'mistral-ocr-2505', 'magistral-medium-2506', 'ministral-3b-2410', 'ministral-8b-2410', 'codestral-2501', 'mistral-large-2411', 'pixtral-large-2411', 'mistral-small-2407', 'mistral-embed', 'codestral-embed', 'mistral-moderation-2411', 'magistral-small-2507', 'voxtral-small-2507', 'voxtral-mini-2507', 'mistral-small-2506', 'magistral-small-2506', 'devstral-small-2507', 'mistral-small-3.1'],
                baseUrl: 'https://api.mistral.ai/v1',
                endpoints: {
                    chat: '/chat/completions',
                    text: '/completions',
                    images: '/vision, /ocr/basic_ocr - image analysis/ocr',
                    audio: '/audio/transcriptions - for voxtral models',
                    video: 'none'
                }
            },
            {
                name: 'deepseek',
                models: ['deepseek-chat (v3-0324)', 'deepseek-reasoner (r1-0528)'], // no update, fallback
                baseUrl: 'https://api.deepseek.com/v1',
                endpoints: {
                    chat: '/chat/completions - text/chat',
                    text: 'same',
                    images: 'none',
                    audio: 'none',
                    video: 'none'
                }
            },
            {
                name: 'qwen (alibaba)',
                models: ['qwen-max', 'qwen-plus', 'qwen-turbo', 'qwen-vl-max (vision)'], // no update, fallback
                baseUrl: 'https://dashscope.aliyuncs.com/api/v1',
                endpoints: {
                    chat: '/services/aigc/text-generation/generation - chat/text',
                    text: 'same',
                    images: '/services/aigc/multimodal-generation/generation - images/video',
                    audio: '/services/aigc/text2audio/generation - tts, /services/aigc/speech-recognition/recognition - stt',
                    video: 'support in multimodal'
                }
            },
            {
                name: 'meta llama',
                models: ['llama3-8b-instruct-v1:0', 'llama3-70b-instruct-v1:0', 'llama3-1-8b-instruct-v1:0', 'llama3-1-70b-instruct-v1:0', 'llama3-1-405b-instruct-v1:0', 'llama3-2-1b-instruct-v1:0', 'llama3-2-3b-instruct-v1:0', 'llama3-2-11b-instruct-v1:0', 'llama3-2-90b-instruct-v1:0'], // updated from bedrock
                baseUrl: 'no official, hosted on groq/together/hf/bedrock',
                endpoints: {
                    chat: 'depends on host, e.g. openai compat',
                    text: 'same',
                    images: 'none native',
                    audio: 'none',
                    video: 'none'
                }
            },
            {
                name: 'groq',
                models: ['gemma2-9b-it', 'llama-3.1-8b-instant', 'llama-3.3-70b-versatile', 'meta-llama/llama-guard-4-12b', 'whisper-large-v3', 'whisper-large-v3-turbo', 'deepseek-r1-distill-llama-70b', 'meta-llama/llama-4-maverick-17b-128e-instruct', 'meta-llama/llama-4-scout-17b-16e-instruct', 'meta-llama/llama-prompt-guard-2-22m', 'meta-llama/llama-prompt-guard-2-86m', 'moonshotai/kimi-k2-instruct', 'openai/gpt-oss-120b', 'openai/gpt-oss-20b', 'playai-tts', 'playai-tts-arabic', 'qwen/qwen3-32b', 'compound-beta', 'compound-beta-mini'],
                baseUrl: 'https://api.groq.com/openai/v1',
                endpoints: {
                    chat: '/chat/completions - text/chat',
                    text: '/completions',
                    images: 'none',
                    audio: 'whisper models for stt',
                    video: 'none'
                }
            },
            {
                name: 'together ai',
                models: ['01-ai/yi-chat-34b', 'austism/chronos-hermes-13b', 'cognitivecomputations/dolphin-2.5-mixtral-8x7b', 'databricks/dbrx-instruct', 'deepseek/deepseek-coder-instruct-33b', 'deepseek/deepseek-llm-chat-67b', 'garage-baind/platypus2-instruct-70b', 'google/gemma-instruct-2b', 'google/gemma-instruct-7b', 'gryphe/mythomax-l2-13b', 'gryphe/mythomax-l2-lite-13b', 'lmsys/vicuna-v1.5-13b', 'lmsys/vicuna-v1.5-7b', 'meta/code-llama-instruct-13b', 'meta/code-llama-instruct-34b', 'meta/code-llama-instruct-70b', 'meta/code-llama-instruct-7b', 'meta/llama-2-chat-70b', 'meta/llama-2-chat-13b', 'meta/llama-2-chat-7b', 'meta/llama-3-chat-8b', 'meta/llama-3-chat-70b', 'meta/llama-3-chat-8b-turbo', 'meta/llama-3-chat-70b-turbo', 'meta/llama-3.1-8b-instruct-turbo', 'meta/llama-3.1-70b-instruct-turbo', 'meta/llama-3.1-405b-instruct-turbo', 'mistralai/mistral-7b-instruct', 'mistralai/mistral-7b-instruct-v0.2', 'mistralai/mistral-7b-instruct-v0.3', 'mistralai/mixtral-8x7b-instruct-46.7b', 'mistralai/mixtral-8x22b-instruct-141b', 'nousresearch/nous-capybara-v1.9-7b', 'nousresearch/nous-hermes-2-mistral-dpo-7b', 'nousresearch/nous-hermes-2-mixtral-8x7b-dpo-46.7b', 'nousresearch/nous-hermes-2-mixtral-8x7b-sft-46.7b', 'nousresearch/nous-hermes-llama-2-7b', 'nousresearch/nous-hermes-llama-2-13b', 'nousresearch/nous-hermes-2-yi-34b', 'openchat/openchat-3.5-7b', 'openorca/openorca-mistral-7b-8k', 'qwen/qwen-1.5-chat-0.5b', 'qwen/qwen-1.5-chat-1.8b', 'qwen/qwen-1.5-chat-4b', 'qwen/qwen-1.5-chat-7b', 'qwen/qwen-1.5-chat-14b', 'qwen/qwen-1.5-chat-32b', 'qwen/qwen-1.5-chat-72b', 'qwen/qwen-1.5-chat-110b', 'qwen/qwen-2-instruct-72b', 'snorkel-ai/snorkel-mistral-pairrm-dpo-7b', 'snowflake/snowflake-arctic-instruct', 'stanford/alpaca-7b', 'teknium/openhermes-2-mistral-7b', 'teknium/openhermes-2.5-mistral-7b', 'together/llama-2-7b-32k-instruct-7b', 'together/redpajama-incite-chat-3b', 'together/redpajama-incite-chat-7b', 'together/stripedhyena-nous-7b', 'undi95/remm-slerp-l2-13b', 'undi95/toppy-m-7b', 'wizardlm/wizardlm-v1.2-13b', 'upstage/upstage-solar-instruct-v1-11b', '01-ai/yi-base-34b', '01-ai/yi-base-6b', 'mistralai/mixtral-8x22b', 'google/gemma-2b', 'google/gemma-7b', 'meta/llama-2-70b', 'meta/llama-2-13b', 'meta/llama-2-7b', 'meta/llama-3-8b', 'meta/llama-3-70b', 'microsoft/microsoft-phi-2', 'nexusflow/nexusraven-13b', 'qwen/qwen-1.5-0.5b', 'qwen/qwen-1.5-1.8b', 'qwen/qwen-1.5-4b', 'qwen/qwen-1.5-7b', 'qwen/qwen-1.5-14b', 'qwen/qwen-1.5-32b', 'qwen/qwen-1.5-72b', 'together/gpt-jt-moderation-6b-7b'],
                baseUrl: 'https://api.together.xyz/v1',
                endpoints: {
                    chat: '/chat/completions',
                    text: '/completions',
                    images: '/images/generate - text-to-image',
                    audio: 'none',
                    video: 'none'
                }
            },
            {
                name: 'hugging face inference',
                models: ['thousands open-source, e.g. meta-llama/llama-3-8b', 'mistralai/mistral-7b', 'many more via providers'],
                baseUrl: 'https://api-inference.huggingface.co/models/{model} or https://router.huggingface.co/v1',
                endpoints: {
                    chat: '/chat/completions - for llm/vlm',
                    text: '/{model} (post) - inference for text/chat',
                    images: 'support for vision/text-to-image models',
                    audio: 'support for audio/speech-to-text models',
                    video: 'support for text-to-video models'
                }
            },
            {
                name: 'cohere',
                models: ['command-a-03-2025', 'command-r7b-12-2024', 'command-a-vision-07-2025', 'command-r-plus-04-2024', 'command-r-08-2024', 'command-r-03-2024', 'command', 'command-nightly', 'command-light', 'command-light-nightly', 'embed-v4.0', 'embed-english-v3.0', 'embed-english-light-v3.0', 'embed-multilingual-v3.0', 'embed-multilingual-light-v3.0', 'rerank-v3.5', 'rerank-english-v3.0', 'rerank-multilingual-v3.0', 'c4ai-aya-expanse-8b', 'c4ai-aya-expanse-32b', 'c4ai-aya-vision-8b', 'c4ai-aya-vision-32b'],
                baseUrl: 'https://api.cohere.ai/v1',
                endpoints: {
                    chat: '/chat - conversational',
                    text: '/generate - text gen',
                    images: 'support in vision models like command-a-vision',
                    audio: 'none',
                    video: 'none'
                }
            },
            {
                name: 'perplexity',
                models: ['sonar', 'sonar-reasoning', 'sonar-deep-research'],
                baseUrl: 'https://api.perplexity.ai',
                endpoints: {
                    chat: '/chat/completions - with search',
                    text: 'same',
                    images: 'none',
                    audio: 'none',
                    video: 'none'
                }
            },
            {
                name: 'fireworks ai',
                models: ['custom models supported, e.g. huggingface uploads like config.json/safetensors'], // no predefined list
                baseUrl: 'https://api.fireworks.ai/v1',
                endpoints: {
                    chat: '/chat/completions',
                    text: '/completions',
                    images: 'support for image models',
                    audio: 'support for audio',
                    video: 'support for video'
                }
            },
            {
                name: 'openrouter',
                models: ['aggregates 400+: e.g. google/gemini-2.5-pro-preview, openai/gpt-4o, anthropic/claude-3.5-sonnet, etc.'],
                baseUrl: 'https://openrouter.ai/api/v1',
                endpoints: {
                    chat: '/chat/completions',
                    text: 'same',
                    images: 'depends on model',
                    audio: 'depends on model',
                    video: 'depends on model'
                }
            },
            {
                name: 'replicate',
                models: ['many multimodal, e.g. replicate/hello-world', 'stability-ai/sdxl', 'black-forest-labs/flux-schnell', 'meta/meta-llama-3-70b-instruct', 'minimax/video-01'],
                baseUrl: 'https://api.replicate.com/v1',
                endpoints: {
                    chat: '/predictions (post) - run model',
                    text: 'same',
                    images: 'yes, for image models',
                    audio: 'yes',
                    video: 'yes'
                }
            },
            {
                name: 'aws bedrock',
                models: ['ai21.jamba-1-5-large-v1:0', 'ai21.jamba-1-5-mini-v1:0', 'amazon.nova-canvas-v1:0', 'amazon.nova-lite-v1:0', 'amazon.nova-micro-v1:0', 'amazon.nova-premier-v1:0', 'amazon.nova-pro-v1:0', 'amazon.nova-reel-v1:0', 'amazon.nova-reel-v1:1', 'amazon.nova-sonic-v1:0', 'amazon.rerank-v1:0', 'amazon.titan-embed-text-v1', 'amazon.titan-image-generator-v2:0', 'amazon.titan-image-generator-v1', 'amazon.titan-embed-image-v1', 'amazon.titan-embed-text-v2:0', 'amazon.titan-text-express-v1', 'amazon.titan-text-lite-v1', 'amazon.titan-text-premier-v1:0', 'anthropic.claude-3-haiku-20240307-v1:0', 'anthropic.claude-3-opus-20240229-v1:0', 'anthropic.claude-3-sonnet-20240229-v1:0', 'anthropic.claude-3-5-haiku-20241022-v1:0', 'anthropic.claude-3-5-sonnet-20241022-v2:0', 'anthropic.claude-3-5-sonnet-20240620-v1:0', 'anthropic.claude-3-7-sonnet-20250219-v1:0', 'anthropic.claude-opus-4-1-20250805-v1:0', 'anthropic.claude-opus-4-20250514-v1:0', 'anthropic.claude-sonnet-4-20250514-v1:0', 'cohere.command-light-text-v14', 'cohere.command-r-plus-v1:0', 'cohere.command-r-v1:0', 'cohere.command-text-v14', 'cohere.embed-english-v3', 'cohere.embed-multilingual-v3', 'cohere.rerank-v3-5:0', 'deepseek.r1-v1:0', 'luma.ray-v2:0', 'meta.llama3-8b-instruct-v1:0', 'meta.llama3-70b-instruct-v1:0', 'meta.llama3-1-8b-instruct-v1:0', 'meta.llama3-1-70b-instruct-v1:0', 'meta.llama3-1-405b-instruct-v1:0', 'meta.llama3-2-1b-instruct-v1:0', 'meta.llama3-2-3b-instruct-v1:0', 'meta.llama3-2-11b-instruct-v1:0', 'meta.llama3-2-90b-instruct-v1:0'],
                baseUrl: 'https://bedrock-runtime.{region}.amazonaws.com',
                endpoints: {
                    chat: '/model/{model-id}/invoke - post for invoke',
                    text: 'same',
                    images: 'depends on model, e.g. titan-image-generator',
                    audio: 'none native',
                    video: 'none native'
                }
            },
            {
                name: 'azure openai',
                models: ['gpt-5', 'gpt-5-mini', 'gpt-5-nano', 'gpt-5-chat', 'gpt-oss-120b', 'gpt-oss-20b', 'gpt-4.1', 'gpt-4.1-nano', 'gpt-4.1-mini', 'model-router (2025-08-07)', 'model-router (2025-05-19)', 'computer-use-preview'],
                baseUrl: 'https://{resource-name}.openai.azure.com/openai',
                endpoints: {
                    chat: '/deployments/{deployment}/chat/completions?api-version=2024-10-21',
                    text: '/deployments/{deployment}/completions?api-version=2024-10-21',
                    images: '/deployments/{deployment}/images/generations?api-version=2024-10-21',
                    audio: '/deployments/{deployment}/audio/transcriptions?api-version=2024-10-21, /audio/translations, /audio/speech',
                    video: 'no dedicated'
                }
            }
        ];

        // function to render providers
        function renderProviders(data) {
            const container = document.getElementById('providers');
            container.innerHTML = '';
            data.forEach(provider => {
                const section = document.createElement('div');
                section.classList.add('section');
                section.innerHTML = `
                    <div class="section-header">
                        <h2>${provider.name}</h2>
                        <span>▼</span>
                    </div>
                    <div class="section-content">
                        <h3>models</h3>
                        <ul>${provider.models.map(m => `<li>${m}</li>`).join('')}</ul>
                        <h3>base url</h3>
                        <pre>${provider.baseUrl}</pre>
                        <h3>endpoints</h3>
                        <ul>
                            <li>chat: ${provider.endpoints.chat}</li>
                            <li>text: ${provider.endpoints.text}</li>
                            <li>images: ${provider.endpoints.images}</li>
                            <li>audio: ${provider.endpoints.audio}</li>
                            <li>video: ${provider.endpoints.video}</li>
                        </ul>
                    </div>
                `;
                container.appendChild(section);
                section.querySelector('.section-header').addEventListener('click', () => {
                    section.classList.toggle('active');
                });
            });
        }

        // initial render
        renderProviders(fallbackData);

        // refresh data - fetch from your api or fallback
        async function refreshData() {
            try {
                // replace with your actual json endpoint for updates
                const response = await fetch('https://your-server.com/llm-api-data.json');
                if (!response.ok) throw new Error('fetch failed');
                const data = await response.json();
                renderProviders(data);
                console.log('data refreshed');
            } catch (error) {
                console.error('refresh error:', error);
                renderProviders(fallbackData); // fallback
            }
        }

        // download current html
        function download() {
            const html = document.documentElement.outerHTML;
            const blob = new Blob([html], {type: 'text/html'});
            const url = URL.createObjectURL(blob);
            const a = document.createElement('a');
            a.href = url;
            a.download = 'llm-api-docs.html';
            a.click();
            URL.revokeObjectURL(url);
        }

        // event listeners
        document.getElementById('refresh-btn').addEventListener('click', refreshData);
        document.getElementById('download-btn').addEventListener('click', download);

        // auto-refresh every 5 min? uncomment if wanted
        // setInterval(refreshData, 300000);
    </script>
</body>
</html>