{ "meta": { "category": "ai", "label": "AI & LLM", "icon": "🤖", "color": "#818cf8", "count": 90, "generated": "2026-03-30T23:25:37.733Z", "source": "https://apimap.dev" }, "apis": [ { "id": "openai", "name": "OpenAI API", "provider": "OpenAI", "category": "ai", "description": "Access GPT-5, GPT-4.1, GPT-4o, o3, o4-mini, DALL·E, Whisper, and text embeddings for any AI-powered application.", "longDescription": "OpenAI provides state-of-the-art AI models via a unified REST API. GPT-4o handles text, vision, and audio; o1 excels at advanced reasoning; DALL·E 3 generates and edits images; Whisper transcribes speech; and embedding models power semantic search and retrieval.", "color": "#10a37f", "tags": [ "gpt-4o", "o1", "vision", "embeddings", "images", "audio" ], "authType": "bearer", "authDescription": "Pass your API key as a Bearer token in the Authorization header. Keys are prefixed with sk-.", "authExample": "Authorization: Bearer sk-proj-...", "baseUrl": "https://api.openai.com/v1", "docsUrl": "https://platform.openai.com/docs", "hasFreeTier": false, "pricing": { "model": "pay-as-you-go", "startingCentsPerMonth": 0, "freeQuota": { "amount": 500, "unit": "credit-cents", "period": "signup", "note": "$5 free credit for new accounts" }, "tiers": [ { "name": "PAYG", "monthlyCents": 0, "included": "No minimum, pay per token" }, { "name": "Plus ($20)", "monthlyCents": 2000, "included": "$20/mo for ChatGPT Plus (not API)" } ], "unitCost": { "amountCents": 250, "per": 1000000, "unit": "input tokens (GPT-4o)" }, "details": "GPT-4o: $2.50/M input, $10/M output. GPT-4.1: $2/M in, $8/M out. GPT-5: $1.25/M in, $10/M out. o3: $2/M in, $8/M out. o4-mini: $1.10/M in, $4.40/M out. GPT-4o mini: $0.15/M in, $0.60/M out. Batch API: 50% off." }, "rateLimit": "3,500 RPM · 200,000 TPM (Tier 1)", "endpoints": [ { "method": "POST", "path": "/chat/completions", "description": "Generate chat completions (GPT-4o, o1, etc.)" }, { "method": "POST", "path": "/embeddings", "description": "Create vector embeddings from text" }, { "method": "POST", "path": "/images/generations", "description": "Generate images with DALL·E 3" }, { "method": "POST", "path": "/images/edits", "description": "Edit existing images using a mask" }, { "method": "POST", "path": "/audio/transcriptions", "description": "Transcribe audio files with Whisper" }, { "method": "POST", "path": "/audio/speech", "description": "Convert text to speech (TTS)" }, { "method": "GET", "path": "/models", "description": "List all available models" } ], "sampleRequest": "curl https://api.openai.com/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n -d '{\n \"model\": \"gpt-4o\",\n \"messages\": [\n {\"role\": \"system\", \"content\": \"You are a helpful assistant.\"},\n {\"role\": \"user\", \"content\": \"Say hello!\"}\n ],\n \"max_tokens\": 100\n }'", "sampleResponse": "{\n \"id\": \"chatcmpl-abc123\",\n \"object\": \"chat.completion\",\n \"model\": \"gpt-4o-2024-08-06\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Hello! How can I help you today?\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 20,\n \"completion_tokens\": 9,\n \"total_tokens\": 29\n }\n}", "scoreDepth": 86, "scoreLatency": 50, "scorePricing": 75, "score": 72, "reachable": true, "verifiedAt": "2026-03-29T20:17:50.246Z", "verifiedStatus": 404, "latencyMs": 117 }, { "id": "anthropic", "name": "Claude API", "provider": "Anthropic", "category": "ai", "description": "Claude Opus 4.6, Sonnet 4.6, and Haiku 4.5 — frontier models with long context, vision, tool use, and computer use.", "longDescription": "Anthropic's Claude API provides access to the Claude 4.x family of models. Claude Sonnet 4.6 is ideal for most tasks; Claude Opus 4.6 handles the most complex reasoning; Claude Haiku 4.5 is fastest and most affordable. All models support extended context windows, vision inputs, tool use, and computer use. Batch API (50% off) and prompt caching (90% off cached inputs) are available.", "color": "#d97757", "tags": [ "claude-sonnet-4-6", "tool-use", "vision", "200k-context", "computer-use" ], "authType": "api-key", "authDescription": "Pass your Anthropic API key in the x-api-key header. Also include the anthropic-version header.", "authExample": "x-api-key: sk-ant-api03-...\nanthropic-version: 2023-06-01", "baseUrl": "https://api.anthropic.com/v1", "docsUrl": "https://docs.anthropic.com", "hasFreeTier": false, "pricing": { "model": "pay-as-you-go", "startingCentsPerMonth": 0, "freeQuota": null, "tiers": [ { "name": "PAYG", "monthlyCents": 0, "included": "No minimum, pay per token" } ], "unitCost": { "amountCents": 100, "per": 1000000, "unit": "input tokens (Haiku 4.5)" }, "details": "Claude Haiku 4.5: $1/M input, $5/M output. Claude Sonnet 4.6: $3/M in, $15/M out. Claude Opus 4.6: $5/M in, $25/M out. Batch API: 50% off. Prompt caching: 90% off cached inputs." }, "rateLimit": "2,000 RPM · 160,000 TPM (default)", "endpoints": [ { "method": "POST", "path": "/messages", "description": "Send a message and receive a response" }, { "method": "POST", "path": "/messages (streaming)", "description": "Stream response tokens as SSE" }, { "method": "GET", "path": "/models", "description": "List available Claude models" } ], "sampleRequest": "curl https://api.anthropic.com/v1/messages \\\n -H \"Content-Type: application/json\" \\\n -H \"x-api-key: $ANTHROPIC_API_KEY\" \\\n -H \"anthropic-version: 2023-06-01\" \\\n -d '{\n \"model\": \"claude-3-5-sonnet-20241022\",\n \"max_tokens\": 1024,\n \"messages\": [\n {\"role\": \"user\", \"content\": \"What is the capital of France?\"}\n ]\n }'", "sampleResponse": "{\n \"id\": \"msg_01XFDUDYJgAACzvnptvVoYEL\",\n \"type\": \"message\",\n \"role\": \"assistant\",\n \"content\": [{\n \"type\": \"text\",\n \"text\": \"The capital of France is Paris.\"\n }],\n \"model\": \"claude-3-5-sonnet-20241022\",\n \"stop_reason\": \"end_turn\",\n \"usage\": {\n \"input_tokens\": 14,\n \"output_tokens\": 10\n }\n}", "scoreDepth": 66, "scoreLatency": 50, "scorePricing": 75, "score": 64, "reachable": true, "verifiedAt": "2026-03-29T20:17:50.257Z", "verifiedStatus": 404, "latencyMs": 119 }, { "id": "google-gemini", "name": "Gemini API", "provider": "Google DeepMind", "category": "ai", "description": "Gemini 2.5 Pro and Gemini 2.5 Flash for multimodal reasoning, code, and long-context tasks.", "longDescription": "Google's Gemini API provides access to Gemini 2.5 Pro and Gemini 2.5 Flash — Google's latest multimodal AI models. Supports text, images, audio, video, and code with up to 2M token context windows. Integrated with Google Search grounding for real-time information access. Note: Gemini 2.0 Flash is deprecated and will be shut down June 1, 2026.", "color": "#4285f4", "tags": [ "gemini-2.5-flash", "multimodal", "2M-context", "grounding", "code" ], "authType": "api-key", "authDescription": "Pass your Google API key as a query parameter or in the x-goog-api-key header.", "authExample": "x-goog-api-key: AIzaSy...", "baseUrl": "https://generativelanguage.googleapis.com/v1beta", "docsUrl": "https://ai.google.dev/gemini-api/docs", "hasFreeTier": true, "pricing": { "model": "pay-as-you-go", "startingCentsPerMonth": 0, "freeQuota": { "amount": null, "unit": null, "period": "month", "note": "15 RPM · 1M TPD (Gemini 2.5 Flash-Lite free tier)" }, "tiers": [], "details": "Gemini 2.5 Flash: $0.15/M input, $0.60/M output. Gemini 2.5 Flash-Lite: $0.10/M input, $0.40/M output. Gemini 2.5 Pro: $1.25/M input, $5/M output (>200K context). Batch: 50% off. Note: Gemini 2.0 Flash deprecated, ends June 1, 2026." }, "rateLimit": "15 RPM (free) · 2,000 RPM (paid)", "endpoints": [ { "method": "POST", "path": "/models/{model}:generateContent", "description": "Generate text, multimodal content" }, { "method": "POST", "path": "/models/{model}:streamGenerateContent", "description": "Stream generated content as SSE" }, { "method": "POST", "path": "/models/{model}:embedContent", "description": "Create text embeddings" }, { "method": "GET", "path": "/models", "description": "List all available models" } ], "sampleRequest": "curl \"https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent\" \\\n -H \"x-goog-api-key: $GEMINI_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\n \"contents\": [{\n \"parts\": [{\"text\": \"Explain quantum entanglement simply.\"}]\n }]\n }'", "sampleResponse": "{\n \"candidates\": [{\n \"content\": {\n \"parts\": [{\"text\": \"Quantum entanglement is when two particles become linked...\"}],\n \"role\": \"model\"\n },\n \"finishReason\": \"STOP\"\n }],\n \"usageMetadata\": {\n \"promptTokenCount\": 9,\n \"candidatesTokenCount\": 120,\n \"totalTokenCount\": 129\n }\n}", "scoreDepth": 68, "scoreLatency": 50, "scorePricing": 75, "score": 65, "reachable": true, "verifiedAt": "2026-03-29T20:17:50.267Z", "verifiedStatus": 404, "latencyMs": 128 }, { "id": "mistral", "name": "Mistral AI API", "provider": "Mistral AI", "category": "ai", "description": "Mistral Medium 3, Small 3.1, Nemo, Codestral, and open-weight models via a simple OpenAI-compatible API.", "longDescription": "Mistral AI offers frontier open and commercial models via REST API. Mistral Large 2 rivals top closed models; Codestral specializes in code generation; Mistral Embed handles semantic search. The API is OpenAI-compatible — simply change the base URL and model name.", "color": "#ff7000", "tags": [ "mistral-large-2", "codestral", "openai-compatible", "function-calling" ], "authType": "bearer", "authDescription": "Standard Bearer token authentication using your Mistral API key.", "authExample": "Authorization: Bearer ...", "baseUrl": "https://api.mistral.ai/v1", "docsUrl": "https://docs.mistral.ai", "hasFreeTier": false, "pricing": { "model": "pay-as-you-go", "startingCentsPerMonth": 10, "freeQuota": { "amount": null, "unit": null, "period": "month", "note": "Experimental models free during preview" }, "tiers": [], "details": "Mistral Medium 3: $0.40/M input, $2.00/M output. Mistral Small 3.1: $0.03/M input, $0.11/M output. Mistral Nemo: $0.02/M. Codestral: $0.20/M input, $0.60/M output. Mistral Large 2: $2.00/M input, $6.00/M output. Free experiment plan available." }, "rateLimit": "1 request/s · 500,000 TPM", "endpoints": [ { "method": "POST", "path": "/chat/completions", "description": "OpenAI-compatible chat completions" }, { "method": "POST", "path": "/embeddings", "description": "Generate text embeddings" }, { "method": "POST", "path": "/fim/completions", "description": "Fill-in-the-middle for code (Codestral)" }, { "method": "GET", "path": "/models", "description": "List available models" } ], "sampleRequest": "curl https://api.mistral.ai/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -H \"Authorization: Bearer $MISTRAL_API_KEY\" \\\n -d '{\n \"model\": \"mistral-large-latest\",\n \"messages\": [{\"role\": \"user\", \"content\": \"Write a haiku about APIs.\"}]\n }'", "sampleResponse": "{\n \"id\": \"cmpl-e5cc70bb28c444948073e77776eb30ef\",\n \"object\": \"chat.completion\",\n \"model\": \"mistral-large-latest\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Keys unlock the gate / Data flows through silent paths / Endpoints never sleep\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\"prompt_tokens\": 15, \"completion_tokens\": 18}\n}", "scoreDepth": 67, "scoreLatency": 45, "scorePricing": 75, "score": 63, "reachable": true, "verifiedAt": "2026-03-29T20:17:50.398Z", "verifiedStatus": 404, "latencyMs": 259 }, { "id": "stability-ai", "name": "Stability AI API", "provider": "Stability AI", "category": "ai", "description": "Stable Diffusion, SDXL, and Stable Video for text-to-image, image-to-image, and video generation.", "longDescription": "Stability AI's REST API provides access to Stable Diffusion 3.5, SDXL, and Stable Video Diffusion. Generate high-quality images from text prompts, transform existing images, upscale, remove backgrounds, and generate short video clips.", "color": "#7c3aed", "tags": [ "stable-diffusion", "SDXL", "text-to-image", "image-to-image", "video" ], "authType": "bearer", "authDescription": "Bearer token authentication using your Stability AI API key.", "authExample": "Authorization: Bearer sk-...", "baseUrl": "https://api.stability.ai/v2beta", "docsUrl": "https://platform.stability.ai/docs/api-reference", "hasFreeTier": true, "pricing": { "model": "pay-as-you-go", "startingCentsPerMonth": 7, "freeQuota": { "amount": null, "unit": null, "period": "month", "note": "25 free credits on signup" }, "tiers": [], "details": "Credits: $10 = 1,000 credits. SD3.5 Large: 6.5 credits/image. SDXL 1.0: 0.2 credits/image. Video: 20 credits/clip." }, "rateLimit": "150 requests/10s", "endpoints": [ { "method": "POST", "path": "/stable-image/generate/sd3", "description": "Text-to-image with Stable Diffusion 3.5" }, { "method": "POST", "path": "/stable-image/generate/core", "description": "Core text-to-image generation" }, { "method": "POST", "path": "/stable-image/upscale/conservative", "description": "Upscale an image up to 4x" }, { "method": "POST", "path": "/stable-image/edit/remove-background", "description": "Remove image background" }, { "method": "POST", "path": "/image-to-video", "description": "Generate video from an image" } ], "sampleRequest": "curl https://api.stability.ai/v2beta/stable-image/generate/sd3 \\\n -H \"Authorization: Bearer $STABILITY_API_KEY\" \\\n -H \"Accept: image/*\" \\\n -F prompt=\"A photorealistic mountain lake at golden hour\" \\\n -F aspect_ratio=\"16:9\" \\\n -F model=\"sd3.5-large\" \\\n --output image.png", "sampleResponse": "# Returns raw image bytes (PNG/JPEG)\n# Headers include:\nContent-Type: image/png\nStability-Finish-Reason: SUCCESS\nStability-Seed: 3456789", "scoreDepth": 74, "scoreLatency": 45, "scorePricing": 75, "score": 66, "reachable": true, "verifiedAt": "2026-03-29T20:17:50.594Z", "verifiedStatus": 404, "latencyMs": 455 }, { "id": "perplexity", "name": "Perplexity AI API", "provider": "Perplexity AI", "category": "ai", "description": "Online LLM with real-time web search grounding — get cited, up-to-date answers from the web.", "longDescription": "Perplexity AI's API provides access to its search-augmented language models. Unlike standard LLMs, Perplexity models fetch current web data to ground responses with citations, making them ideal for research, news summarization, and fact-checking workflows. Supports both online models (with live search) and offline models (standard generation). OpenAI-compatible API format.", "color": "#1fb8cd", "tags": [ "search", "online", "citations", "real-time", "research", "llm" ], "authType": "bearer", "authDescription": "Generate an API key in Perplexity Settings → API. Pass it as a Bearer token in the Authorization header.", "authExample": "Authorization: Bearer pplx-...", "baseUrl": "https://api.perplexity.ai", "docsUrl": "https://docs.perplexity.ai", "hasFreeTier": false, "pricing": { "model": "pay-as-you-go", "startingCentsPerMonth": 20, "freeQuota": { "amount": null, "unit": null, "period": "month", "note": "$5 free credits for new accounts" }, "tiers": [], "details": "Sonar (online): $1 per 1M input tokens + $5 per 1,000 search queries. Sonar Pro: $3/M input + $5/1k searches. Offline models from $0.20/M tokens." }, "rateLimit": "50 requests/min", "endpoints": [ { "method": "POST", "path": "/chat/completions", "description": "Chat completions with optional web search grounding" } ], "sampleRequest": "curl \"https://api.perplexity.ai/chat/completions\" \\\n -H \"Authorization: Bearer $PERPLEXITY_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\"model\":\"sonar\",\"messages\":[{\"role\":\"user\",\"content\":\"What are the latest AI model releases in 2026?\"}]}'", "sampleResponse": "{\n \"id\": \"gen-abc123\",\n \"model\": \"sonar\",\n \"choices\": [{\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"In 2026, notable AI releases include... [1][2]\"\n }\n }],\n \"citations\": [\"https://techcrunch.com/...\", \"https://theverge.com/...\"]\n}", "scoreDepth": 52, "scoreLatency": 38, "scorePricing": 75, "score": 55, "reachable": true, "verifiedAt": "2026-03-29T20:17:51.784Z", "verifiedStatus": 404, "latencyMs": 564 }, { "id": "replicate", "name": "Replicate API", "provider": "Replicate", "category": "ai", "description": "Run open-source AI models in the cloud — image generation, video, audio, language, and more.", "longDescription": "Replicate makes it easy to run machine learning models with a single API call. Access thousands of open-source models for image generation (SDXL, Flux, ControlNet), video generation (Stable Video Diffusion), audio (Whisper, MusicGen), language (Llama 3, Mistral), and specialized tasks like upscaling, background removal, and object detection. Deploy private models and fine-tunes too.", "color": "#000000", "tags": [ "stable-diffusion", "llama", "image-generation", "video", "audio", "open-source", "mlops" ], "authType": "bearer", "authDescription": "Create an API token at replicate.com/account/api-tokens. Pass it as a Bearer token in the Authorization header.", "authExample": "Authorization: Bearer r8_...", "baseUrl": "https://api.replicate.com/v1", "docsUrl": "https://replicate.com/docs", "hasFreeTier": false, "pricing": { "model": "pay-as-you-go", "startingCentsPerMonth": 0, "freeQuota": { "amount": null, "unit": null, "period": "month", "note": "No free tier (pay-as-you-go)" }, "tiers": [], "details": "Billed by the second per hardware tier: CPU $0.000225/sec, Nvidia T4 $0.0012/sec, A40 $0.0023/sec, A100 $0.0115/sec. Image gen ~$0.003–0.012/image." }, "rateLimit": "No hard limit (scales with your account tier)", "endpoints": [ { "method": "POST", "path": "/predictions", "description": "Run a model and create a prediction" }, { "method": "GET", "path": "/predictions/{prediction_id}", "description": "Get prediction status and output" }, { "method": "GET", "path": "/models", "description": "List available public models" }, { "method": "GET", "path": "/models/{owner}/{model_name}", "description": "Get model details and latest version" }, { "method": "POST", "path": "/models/{owner}/{model_name}/versions/{id}/predictions", "description": "Run a specific model version" } ], "sampleRequest": "curl \"https://api.replicate.com/v1/predictions\" \\\n -H \"Authorization: Bearer $REPLICATE_API_TOKEN\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\"version\":\"db21e45d3f7023abc2a46ee38a23973f6dce16bb082a930b0c49861f96d1e5bf\",\"input\":{\"prompt\":\"A photo of a cat wearing a beret in Paris\"}}'", "sampleResponse": "{\n \"id\": \"xyz789abc\",\n \"status\": \"starting\",\n \"model\": \"stability-ai/sdxl\",\n \"urls\": {\n \"get\": \"https://api.replicate.com/v1/predictions/xyz789abc\",\n \"cancel\": \"https://api.replicate.com/v1/predictions/xyz789abc/cancel\"\n }\n}", "scoreDepth": 86, "scoreLatency": 38, "scorePricing": 75, "score": 68, "reachable": true, "verifiedAt": "2026-03-29T20:17:51.889Z", "verifiedStatus": 401, "latencyMs": 650 }, { "id": "groq", "name": "Groq API", "provider": "Groq", "category": "ai", "description": "Ultra-fast LLM inference on custom LPU hardware — run Llama 3.3, Llama 3.1, and other open-source models at 800+ tokens/sec.", "longDescription": "Groq runs open-source LLMs at speeds previously impossible: 800+ tokens per second on their custom Language Processing Unit (LPU) hardware. The API is OpenAI-compatible, so any code targeting OpenAI's chat completions endpoint works with a one-line change. Models include Llama 3.3 70B, Llama 3.1 8B, Mixtral 8x7B, and Gemma 2. Ideal for latency-critical applications like voice assistants, real-time chat, and interactive coding tools.", "color": "#f55036", "tags": [ "llama", "mixtral", "fast-inference", "open-source", "openai-compatible", "lpu" ], "authType": "bearer", "authDescription": "Generate an API key at console.groq.com. Pass it as a Bearer token in the Authorization header. The endpoint is OpenAI-compatible.", "authExample": "Authorization: Bearer gsk_...", "baseUrl": "https://api.groq.com/openai/v1", "docsUrl": "https://console.groq.com/docs", "hasFreeTier": true, "pricing": { "model": "pay-as-you-go", "startingCentsPerMonth": 0, "freeQuota": { "amount": 0, "unit": "credit-cents", "period": "ongoing", "note": "Free tier with rate limits; no credit card required" }, "tiers": [ { "name": "Free", "monthlyCents": 0, "included": "Rate-limited access to all models" }, { "name": "PAYG", "monthlyCents": 0, "included": "Pay per token, higher rate limits" } ], "unitCost": { "amountCents": 59, "per": 1000000, "unit": "input tokens (Llama 3.3 70B)" }, "details": "Llama 3.1 8B Instant: $0.05/M input, $0.08/M output. Llama 3.3 70B Versatile: $0.59/M input, $0.79/M output. Llama 3.1 70B: $0.59/M input, $0.79/M output. Batch API: 50% off." }, "rateLimit": "30 requests/min (free) · Higher on pay-as-you-go", "endpoints": [ { "method": "POST", "path": "/chat/completions", "description": "Chat completions (OpenAI-compatible)" }, { "method": "GET", "path": "/models", "description": "List available models and their context lengths" } ], "sampleRequest": "curl \"https://api.groq.com/openai/v1/chat/completions\" \\\n -H \"Authorization: Bearer $GROQ_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\"model\":\"llama-3.3-70b-versatile\",\"messages\":[{\"role\":\"user\",\"content\":\"Explain quantum computing in one paragraph.\"}]}'", "sampleResponse": "{\n \"id\": \"chatcmpl-abc123\",\n \"model\": \"llama-3.3-70b-versatile\",\n \"choices\": [{\n \"message\": { \"role\": \"assistant\", \"content\": \"Quantum computing harnesses...\" },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": { \"prompt_tokens\": 18, \"completion_tokens\": 87, \"total_tokens\": 105 },\n \"x_groq\": { \"id\": \"req_abc\", \"usage\": { \"queue_time\": 0.0002 } }\n}", "scoreDepth": 61, "scoreLatency": 38, "scorePricing": 75, "score": 58, "reachable": true, "verifiedAt": "2026-03-29T20:17:52.597Z", "verifiedStatus": 404, "latencyMs": 871 }, { "id": "huggingface", "name": "HuggingFace Inference API", "provider": "HuggingFace", "category": "ai", "description": "Run 200,000+ open-source ML models — LLMs, image generation, audio, NLP, and vision — via a single API.", "longDescription": "The HuggingFace Inference API gives serverless access to the entire HuggingFace Hub: 200,000+ models for text generation, text classification, summarization, translation, question answering, image generation, image classification, object detection, speech recognition, and audio synthesis. Models range from tiny to frontier-scale. The Inference Endpoints product offers dedicated deployment for production workloads.", "color": "#ff9d00", "tags": [ "open-source", "transformers", "nlp", "computer-vision", "audio", "diffusion", "bert", "llama" ], "authType": "bearer", "authDescription": "Create a User Access Token at huggingface.co/settings/tokens (read scope is sufficient). Pass it as a Bearer token in the Authorization header.", "authExample": "Authorization: Bearer hf_...", "baseUrl": "https://api-inference.huggingface.co/models", "docsUrl": "https://huggingface.co/docs/api-inference", "hasFreeTier": true, "pricing": { "model": "freemium", "startingCentsPerMonth": 0, "freeQuota": { "amount": null, "unit": "requests", "period": "forever", "note": "Rate-limited free inference on public models" }, "tiers": [ { "name": "Free", "monthlyCents": 0, "included": "Rate-limited serverless inference" }, { "name": "PRO", "monthlyCents": 900, "included": "$9/mo, higher limits, ZeroGPU" }, { "name": "Endpoints", "monthlyCents": 600, "included": "Dedicated endpoints from $0.06/hr" }, { "name": "Enterprise", "monthlyCents": null, "included": "Custom pricing" } ], "details": "Free: serverless inference on public models (rate-limited). PRO: $9/mo. Dedicated Inference Endpoints from $0.06/hr. Enterprise: custom." }, "rateLimit": "Varies by model and plan (free tier is rate-limited)", "endpoints": [ { "method": "POST", "path": "/{model_id}", "description": "Run any model with task-specific input/output" }, { "method": "POST", "path": "/openai/v1/chat/completions", "description": "OpenAI-compatible chat completions (TGI models)" } ], "sampleRequest": "# Text generation with Llama 3\ncurl \"https://api-inference.huggingface.co/models/meta-llama/Meta-Llama-3-8B-Instruct\" \\\n -H \"Authorization: Bearer $HF_TOKEN\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\"inputs\": \"What is the capital of France?\", \"parameters\": {\"max_new_tokens\": 50}}'", "sampleResponse": "[{\n \"generated_text\": \"What is the capital of France?\nThe capital of France is Paris.\"\n}]", "scoreDepth": 66, "scoreLatency": 38, "scorePricing": 90, "score": 65, "reachable": true, "verifiedAt": "2026-03-29T20:17:52.710Z", "verifiedStatus": 410, "latencyMs": 926 }, { "id": "cohere", "name": "Cohere API", "provider": "Cohere", "category": "ai", "description": "Enterprise-grade LLM API for text generation, RAG, embeddings, and reranking with a focus on accuracy.", "longDescription": "Cohere provides production-ready language AI for enterprise teams. Command R+ leads on RAG benchmarks, making it ideal for grounded enterprise search. The Embed v3 model produces high-quality text embeddings for semantic search and retrieval. The Rerank endpoint improves search accuracy by reordering candidate results. All models have built-in tool use (function calling) and citation support for RAG pipelines.", "color": "#39594d", "tags": [ "rag", "embeddings", "rerank", "enterprise", "command-r", "grounding", "citations" ], "authType": "bearer", "authDescription": "Create an API key at dashboard.cohere.com. Pass it as a Bearer token in the Authorization header.", "authExample": "Authorization: Bearer YOUR_COHERE_API_KEY", "baseUrl": "https://api.cohere.com/v2", "docsUrl": "https://docs.cohere.com", "hasFreeTier": true, "pricing": { "model": "pay-as-you-go", "startingCentsPerMonth": 0, "freeQuota": { "amount": null, "unit": "requests", "period": "trial", "note": "Trial key with limited free usage" }, "tiers": [ { "name": "Trial", "monthlyCents": 0, "included": "Limited trial usage" }, { "name": "Production", "monthlyCents": 0, "included": "No minimum, pay per token/query" } ], "unitCost": { "amountCents": 15, "per": 100000, "unit": "input tokens (Command R)" }, "details": "Command R+: $2.50/M in, $10/M out. Command R: $0.15/M in, $0.60/M out. Command R7B: $0.0375/M in, $0.15/M out. Embed: $0.10/M tokens. Rerank: $2/1k queries." }, "rateLimit": "100 API calls/min (trial) · Higher on production", "endpoints": [ { "method": "POST", "path": "/chat", "description": "Chat with Command R / R+ with optional tool use and RAG" }, { "method": "POST", "path": "/embed", "description": "Generate embeddings for semantic search and classification" }, { "method": "POST", "path": "/rerank", "description": "Rerank search results by relevance to a query" }, { "method": "POST", "path": "/classify", "description": "Classify text into predefined categories" } ], "sampleRequest": "curl \"https://api.cohere.com/v2/chat\" \\\n -H \"Authorization: Bearer $COHERE_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\"model\":\"command-r-plus\",\"messages\":[{\"role\":\"user\",\"content\":\"Summarize the benefits of RAG for enterprise AI.\"}]}'", "sampleResponse": "{\n \"id\": \"abc123\",\n \"message\": {\n \"role\": \"assistant\",\n \"content\": [{\"type\":\"text\",\"text\":\"RAG (Retrieval-Augmented Generation) benefits include...\"}]\n },\n \"finish_reason\": \"COMPLETE\",\n \"usage\": { \"billed_units\": { \"input_tokens\": 24, \"output_tokens\": 112 } }\n}", "scoreDepth": 80, "scoreLatency": 30, "scorePricing": 75, "score": 64, "reachable": true, "verifiedAt": "2026-03-29T20:17:52.869Z", "verifiedStatus": 401, "latencyMs": 1048 }, { "id": "together-ai", "name": "Together AI API", "provider": "Together AI", "category": "ai", "description": "Run 200+ open-source AI models with OpenAI-compatible endpoints, fine-tuning, and serverless inference.", "longDescription": "Together AI provides cloud infrastructure for running open-source AI models at scale. The API is fully OpenAI-compatible and supports 200+ models including Llama 3.1 405B, Qwen 2.5, Mistral, DeepSeek, Stable Diffusion, and more. Features include serverless inference (pay per token), dedicated GPU clusters, fine-tuning with LORA, vision models, and function calling. Popular for research, enterprise AI, and teams migrating from proprietary models.", "color": "#5b8ef7", "tags": [ "open-source", "llama", "deepseek", "fine-tuning", "serverless", "openai-compatible", "vision" ], "authType": "bearer", "authDescription": "Create an API key at api.together.ai. The endpoint is OpenAI-compatible — pass your key as a Bearer token in the Authorization header.", "authExample": "Authorization: Bearer YOUR_TOGETHER_API_KEY", "baseUrl": "https://api.together.xyz/v1", "docsUrl": "https://docs.together.ai", "hasFreeTier": false, "pricing": { "model": "pay-as-you-go", "startingCentsPerMonth": 10, "freeQuota": { "amount": null, "unit": null, "period": "month", "note": "$1 free credit on signup" }, "tiers": [], "details": "Llama 3.1 8B: $0.18/M · $0.18/M. Llama 3.1 70B: $0.88/M · $0.88/M. Llama 4 Scout: available. DeepSeek R1: $1.25/M · $1.25/M. Image gen: $0.008 per image. No free tier; minimum $5 credit purchase." }, "rateLimit": "60 requests/min (default) · Scales with plan", "endpoints": [ { "method": "POST", "path": "/chat/completions", "description": "Chat completions (OpenAI-compatible)" }, { "method": "POST", "path": "/completions", "description": "Text completions" }, { "method": "POST", "path": "/embeddings", "description": "Generate text embeddings" }, { "method": "POST", "path": "/images/generations", "description": "Image generation (Stable Diffusion, FLUX)" }, { "method": "GET", "path": "/models", "description": "List all available models with pricing" }, { "method": "POST", "path": "/fine-tunes", "description": "Start a fine-tuning job with LoRA" } ], "sampleRequest": "curl \"https://api.together.xyz/v1/chat/completions\" \\\n -H \"Authorization: Bearer $TOGETHER_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\"model\":\"meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo\",\"messages\":[{\"role\":\"user\",\"content\":\"Write a Python function to parse JSON safely\"}],\"max_tokens\":200}'", "sampleResponse": "{\n \"id\": \"890ab123\",\n \"model\": \"meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo\",\n \"choices\": [{\n \"message\": { \"role\": \"assistant\", \"content\": \"Here's a Python function to safely parse JSON:\n\n```python\nimport json\n\ndef safe_json_parse(data):\n try:\n return json.loads(data)\n except json.JSONDecodeError:\n return None\n```\" },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": { \"prompt_tokens\": 20, \"completion_tokens\": 68 }\n}", "scoreDepth": 86, "scoreLatency": 30, "scorePricing": 75, "score": 66, "reachable": true, "verifiedAt": "2026-03-29T20:17:52.980Z", "verifiedStatus": 404, "latencyMs": 1091 }, { "id": "elevenlabs-api-documentation", "name": "ElevenLabs API Documentation", "provider": "ElevenLabs API Documentation", "category": "ai", "description": "ElevenLabs provides AI-powered voice synthesis and cloning. Generate natural-sounding speech in 29 languages, clone voices from audio samples, and stream audio in real time.", "longDescription": "This is the documentation for the ElevenLabs API. You can use this API to use our service programmatically, this is done by using your xi-api-key.
You can view your xi-api-key using the 'Profile' tab on https://beta.elevenlabs.io. Our API is experimental so all endpoints are subject to change.", "color": "#10b981", "tags": [ "ai", "voice", "text-to-speech", "speech synthesis", "audio" ], "authType": "api-key", "authDescription": "API key in the xi-api-key request header", "authExample": "xi-api-key: YOUR_API_KEY", "baseUrl": "https://api.elevenlabs.io/", "docsUrl": "https://api.elevenlabs.io/", "hasFreeTier": true, "pricing": { "model": "freemium", "startingCentsPerMonth": 0, "freeQuota": { "amount": 10000, "unit": "characters", "period": "month" }, "tiers": [ { "name": "Free", "monthlyCents": 0, "included": "10,000 chars/mo" }, { "name": "Starter", "monthlyCents": 500, "included": "30,000 chars/mo" }, { "name": "Creator", "monthlyCents": 2200, "included": "100,000 chars/mo" }, { "name": "Pro", "monthlyCents": 9900, "included": "500,000 chars/mo" }, { "name": "Scale", "monthlyCents": 33000, "included": "2,000,000 chars/mo" } ], "details": "Free: 10k chars/mo. Starter $5/mo (30k chars). Creator $22/mo (100k chars). Pro $99/mo (500k chars). Scale $330/mo (2M chars)." }, "rateLimit": "2 concurrent requests (free); up to 10 (paid)", "endpoints": [ { "method": "GET", "path": "/v1/history", "description": "Get Generated Items" }, { "method": "POST", "path": "/v1/history/delete", "description": "Delete History Items" }, { "method": "POST", "path": "/v1/history/download", "description": "Download History Items" }, { "method": "DELETE", "path": "/v1/history/{history_item_id}", "description": "Delete History Item" }, { "method": "GET", "path": "/v1/history/{history_item_id}/audio", "description": "Get Audio From History Item" }, { "method": "POST", "path": "/v1/text-to-speech/{voice_id}", "description": "Text To Speech" }, { "method": "POST", "path": "/v1/text-to-speech/{voice_id}/stream", "description": "Text To Speech" }, { "method": "GET", "path": "/v1/user", "description": "Get User Info" } ], "sampleRequest": "curl -X GET 'https://api.elevenlabs.io//v1/history' \\\n -H '# No auth required'", "sampleResponse": "{}", "scoreDepth": 86, "scoreLatency": 38, "scorePricing": 90, "score": 73, "reachable": true, "verifiedAt": "2026-03-29T20:17:54.302Z", "verifiedStatus": 404, "latencyMs": 723 }, { "id": "powertools-developer", "name": "PowerTools Developer", "provider": "PowerTools Developer", "category": "ai", "description": "Apptigent PowerTools Developer Edition is a powerful suite of API endpoints for custom applications running on any stack. Manipulate text, modify collections, format dates and times, convert currency, perform advanced mathematical calculations, shorten URL's, encode strings, convert text to speech,", "longDescription": "Apptigent PowerTools Developer Edition is a powerful suite of API endpoints for custom applications running on any stack. Manipulate text, modify collections, format dates and times, convert currency, perform advanced mathematical calculations, shorten URL's, encode strings, convert text to speech,", "color": "#10b981", "tags": [ "ai", "apptigent" ], "authType": "api-key", "authDescription": "API key in the request header (X-IBM-Client-Id)", "authExample": "X-IBM-Client-Id: YOUR_API_KEY", "baseUrl": "https://connect.apptigent.com/api/utilities", "docsUrl": "https://www.apptigent.com/help/", "hasFreeTier": true, "pricing": { "model": "subscription", "startingCentsPerMonth": null, "freeQuota": null, "tiers": [], "details": "Free with account. Developer productivity toolset API." }, "rateLimit": "Not officially published", "endpoints": [ { "method": "POST", "path": "/AddToCollection", "description": "Collections - Add to collection" }, { "method": "POST", "path": "/CSVtoJSON", "description": "Data - CSV to JSON" }, { "method": "POST", "path": "/CalculateAbsolute", "description": "Math - Calculate Absolute" }, { "method": "POST", "path": "/CalculateAddition", "description": "Math - Calculate Addition" }, { "method": "POST", "path": "/CalculateAverage", "description": "Math - Calculate average" }, { "method": "POST", "path": "/CalculateCosine", "description": "Math - Calculate Cosine" }, { "method": "POST", "path": "/CalculateDivision", "description": "Math - Calculate Division" }, { "method": "POST", "path": "/CalculateLogarithm", "description": "Math - Calculate Logarithm" } ], "sampleRequest": "curl -X GET 'https://connect.apptigent.com/api/utilities/AddToCollection' \\\n -H 'X-IBM-Client-Id: YOUR_API_KEY'", "sampleResponse": "{}", "scoreDepth": 72, "scoreLatency": 0, "scorePricing": 28, "score": 37, "reachable": false, "verifiedAt": "2026-03-29T20:17:55.106Z", "verifiedStatus": null, "latencyMs": null }, { "id": "digitalnz", "name": "DigitalNZ API", "provider": "DigitalNZ", "category": "ai", "description": "OpenAPI specification of DigitalNZ's Record API. \nFor more information about the API see digitalnz.org/developers. \nTo learn more about the metadata/fields used in the API see the [Metadata Dictionary](https://docs.google.com/document/pub?id=1Z3I_ckQWjnQQ4SzpORb", "longDescription": "OpenAPI specification of DigitalNZ's Record API. \nFor more information about the API see digitalnz.org/developers. \nTo learn more about the metadata/fields used in the API see the [Metadata Dictionary](https://docs.google.com/document/pub?id=1Z3I_ckQWjnQQ4SzpORb", "color": "#10b981", "tags": [ "ai", "digitalnz" ], "authType": "api-key", "authDescription": "API key as a query parameter (api_key)", "authExample": "GET /endpoint?api_key=YOUR_KEY", "baseUrl": "https://api.digitalnz.org", "docsUrl": "https://api.digitalnz.org", "hasFreeTier": true, "pricing": { "model": "subscription", "startingCentsPerMonth": null, "freeQuota": null, "tiers": [], "details": "Free with API key. DigitalNZ New Zealand digital heritage collections." }, "rateLimit": "10,000 req/day", "endpoints": [ { "method": "GET", "path": "/records.{format}", "description": "Run queries against DigitalNZ metadata search service." }, { "method": "GET", "path": "/records/{record_id}.{format}", "description": "View metadata associated with a single record." }, { "method": "GET", "path": "/records/{record_id}/more_like_this.{format}", "description": "The \"More Like This\" call returns similar records to the specified ID.\n" } ], "sampleRequest": "curl -X GET 'https://api.digitalnz.org/records.{format}' \\\n -H 'GET /endpoint?api_key=YOUR_KEY'", "sampleResponse": "{}", "scoreDepth": 52, "scoreLatency": 20, "scorePricing": 28, "score": 35, "reachable": true, "verifiedAt": "2026-03-29T20:18:04.087Z", "verifiedStatus": 200, "latencyMs": 6966 }, { "id": "fire-financial-services-business", "name": "Fire Financial Services Business API", "provider": "Fire Financial Services Business", "category": "ai", "description": "The fire.com API allows you to deeply integrate Business Account features into your application or back-office systems.\n\nThe API provides read access to your profile, accounts and transactions, event-driven notifications of activity on the account and payment initiation via batches. Each feature has", "longDescription": "The fire.com API allows you to deeply integrate Business Account features into your application or back-office systems.\n\nThe API provides read access to your profile, accounts and transactions, event-driven notifications of activity on the account and payment initiation via batches. Each feature has", "color": "#10b981", "tags": [ "ai", "fire" ], "authType": "bearer", "authDescription": "Bearer token in the Authorization header", "authExample": "Authorization: Bearer YOUR_TOKEN", "baseUrl": "https://api.fire.com/business", "docsUrl": "https://docs.fire.com", "hasFreeTier": false, "pricing": { "model": "subscription", "startingCentsPerMonth": null, "freeQuota": null, "tiers": [], "details": "Paid. Fire.com Irish/UK business banking API; pricing per transaction." }, "rateLimit": "Not officially published", "endpoints": [ { "method": "GET", "path": "/v1/accounts", "description": "List all fire.com Accounts" }, { "method": "POST", "path": "/v1/accounts", "description": "Add a new account" }, { "method": "GET", "path": "/v1/accounts/{ican}", "description": "Retrieve the details of a fire.com Account" }, { "method": "GET", "path": "/v1/accounts/{ican}/transactions", "description": "List transactions for an account (v1)" }, { "method": "GET", "path": "/v1/accounts/{ican}/transactions/filter", "description": "Filtered list of transactions for an account (v1)" }, { "method": "POST", "path": "/v1/apps", "description": "Create a new API Application" }, { "method": "POST", "path": "/v1/apps/accesstokens", "description": "Authenticate with the API." }, { "method": "GET", "path": "/v1/aspsps", "description": "Get list of ASPSPs / Banks" } ], "sampleRequest": "curl -X GET 'https://api.fire.com/business/v1/accounts' \\\n -H 'Authorization: Bearer YOUR_TOKEN'", "sampleResponse": "{}", "scoreDepth": 72, "scoreLatency": 20, "scorePricing": 28, "score": 43, "reachable": true, "verifiedAt": "2026-03-29T20:18:01.281Z", "verifiedStatus": 400, "latencyMs": 2942 }, { "id": "goog-io-unoffical-google-search", "name": "goog.io | Unoffical Google Search API", "provider": "goog.io | Unoffical Google Search", "category": "ai", "description": "Intoduction\n\nThis is the OpenAPI V3 documentation for https://api.goog.io\n\nAn API to perform Google Searches. Extremely fast and accurate. Zero proxies. Clean USA IPs.\n\nSimple to use API, but advance enough to support special parameters such as languages, country and geographic locality.\n\nGoogio i", "longDescription": "Intoduction\n\nThis is the OpenAPI V3 documentation for https://api.goog.io\n\nAn API to perform Google Searches. Extremely fast and accurate. Zero proxies. Clean USA IPs.\n\nSimple to use API, but advance enough to support special parameters such as languages, country and geographic locality.\n\nGoogio i", "color": "#10b981", "tags": [ "ai", "goog" ], "authType": "api-key", "authDescription": "API key in the request header (apikey)", "authExample": "apikey: YOUR_API_KEY", "baseUrl": "https://api.goog.io", "docsUrl": "https://goog.io", "hasFreeTier": true, "pricing": { "model": "subscription", "startingCentsPerMonth": null, "freeQuota": null, "tiers": [], "details": "Free unofficial Google Search API. Third-party wrapper; no paid tiers." }, "rateLimit": "Not officially published", "endpoints": [ { "method": "GET", "path": "/", "description": "Status" }, { "method": "GET", "path": "/v1/crawl/{query}", "description": "Crawl" }, { "method": "GET", "path": "/v1/images/{query}", "description": "Images" }, { "method": "GET", "path": "/v1/news/{query}", "description": "News" }, { "method": "GET", "path": "/v1/search/{query}", "description": "Search" }, { "method": "POST", "path": "/v1/serp/", "description": "SERP" } ], "sampleRequest": "curl -X GET 'https://api.goog.io/' \\\n -H 'apikey: YOUR_API_KEY'", "sampleResponse": "{}", "scoreDepth": 64, "scoreLatency": 0, "scorePricing": 28, "score": 34, "reachable": false, "verifiedAt": "2026-03-29T20:18:03.622Z", "verifiedStatus": null, "latencyMs": null }, { "id": "image-charts", "name": "Image-Charts", "provider": "Image-Charts", "category": "ai", "description": "Charts, simple as a URL. A safe and fast replacement for Google Image Charts", "longDescription": "Charts, simple as a URL. A safe and fast replacement for Google Image Charts", "color": "#10b981", "tags": [ "ai", "image-charts" ], "authType": "none", "authDescription": "No authentication required", "authExample": "# No auth required", "baseUrl": "https://image-charts.com/", "docsUrl": "https://image-charts.com/", "hasFreeTier": true, "pricing": { "model": "subscription", "startingCentsPerMonth": null, "freeQuota": null, "tiers": [], "details": "Free — open public API, no authentication required." }, "rateLimit": "See documentation", "endpoints": [ { "method": "GET", "path": "/chart", "description": "Image-Charts API" }, { "method": "GET", "path": "/chart.js/2.8.0", "description": "Chart.js as image API" } ], "sampleRequest": "curl -X GET 'https://image-charts.com//chart' \\\n -H '# No auth required'", "sampleResponse": "{}", "scoreDepth": 33, "scoreLatency": 40, "scorePricing": 28, "score": 34, "reachable": true, "verifiedAt": "2026-03-29T20:18:05.225Z", "verifiedStatus": 200, "latencyMs": 2310 }, { "id": "languagetool", "name": "LanguageTool API", "provider": "LanguageTool", "category": "ai", "description": "Check texts for style and grammar issues with LanguageTool. Please consider the following default limitations: