awesome-generative-ai-apis
A curated list of useful Generative AI APIs for developers
https://github.com/foss42/awesome-generative-ai-apis
Last synced: 21 days ago
JSON representation
AI Gateway/Aggregator
- Vercel AI Gateway - gateway) | Unified API endpoint across multiple AI model providers; supports model switching, fallback, spend monitoring, and OpenAI-compatible endpoints |
- OmniRoute - hostable AI gateway with 4-tier cascading fallback and multi-provider load balancing. Supports 200+ models across OpenAI, Anthropic, Google, and local providers via OpenAI-compatible API |
- Glio - effective access to 50+ SOTA models. Kling, NanoBanana, Sora2, Veo3, Suno, ElevenLabs and more |
- EvoLink
- deAPI.ai
- Agent LLM Router - gateway-kappa.vercel.app/v1/agent-llm/docs) | Unified LLM gateway — route to OpenAI, Anthropic, Google Gemini, Groq, Together AI, DeepSeek through one OpenAI-compatible API. BYOK, response caching, auto retries. 24+ models |
- PixelAPI - per-use AI image API offering SDXL, FLUX image generation, background removal, and 4x upscaling. Python and JS SDKs available. |
- XiuRouter - model API with OpenAI Responses and Chat Completions, Anthropic Messages, Gemini GenerateContent, scoped API keys, usage-based pricing, and request-level usage and cost records. |
- UnificAlly
- MuAPI - compatible generative media API aggregating 44+ image, video, and audio models (Flux, Midjourney, Kling, Suno, and more) via a single unified endpoint. |
- AnyRouter - compatible API gateway for 150+ models across 28+ providers with unified billing, audit logs, real-time pricing, BYOK, and provider routing with automatic fallbacks |
- OfoxAI - 5.4, and Gemini; native OpenAI, Anthropic, and Gemini SDK support with China direct access via Hong Kong routes |
- Magic Hour - image, Nano Banana Pro, Flux), plus face swap, lip sync and talking photo |
- Bifrost - native, OpenAI-compatible AI gateway with multi-provider routing, automatic failover, load balancing, guardrails, MCP gateway support, and built-in logs, metrics, and tracing |
- NovAI - pro.com/docs) | OpenAI-compatible gateway to Chinese frontier models (DeepSeek, Qwen, GLM, Kimi, MiniMax, Doubao, Hunyuan) plus image and video generation on one endpoint |
- RouterPlex - compatible AI gateway — one API key for 25+ models (Claude, GPT, Gemini, DeepSeek) across 11 providers |
- RunAPI
- routerbase - compatible AI gateway for 200+ models with smart routing, automatic fallback, unified billing, and usage analytics. |
- OpenPaths - compatible endpoint. |
- TeamoRouter - compatible endpoints plus a native Anthropic Messages API — Claude Code and Codex connect by changing only the base URL |
- EmpirioLabs AI - compatible AI API platform for text, image, video, audio, search, and 3D models with a live model catalog |
- WanAPIs - compatible AI API gateway for GPT, Claude, Gemini, DeepSeek, image, video, and audio models. Includes a model marketplace, usage logs, quota controls, multi-channel routing, and failover |
- FuturMix - compatible API |
GenAI APIs (By Model Developers/Well Known Inference Providers)
- OpenAI - reference) | OpenAI APIs offer state-of-the-art GenAI models that can generate human-like text, answer questions, translate languages, generate and understand images, turn text to speech or speech to text thus empowering developers to create advanced AI-powered applications with ease. |
- Gemini - api/docs) | designed to understand and interact with multiple data types, including text, images, audio, and video. |
- Groq - 7b-lt, Llama3-70b-8192, Llama3-8b-8192, Mixtral-8x7b-32768. |
- Cohere AI - api) | Cohere AI offers a chat API that enables developers to create conversational interfaces with ease, leveraging advanced natural language understanding capabilities. |
- Anthropic - started) | Anthropic is an AI safety and research company behind the powerful Claude 3 model family. |
- HuggingFace API - inference/index) | HuggingFace provides API access to many open source Generative AI models, datasets and Spaces which are free to use. |
- Stability AI - reference) | Stability AI offers open-access AI models with minimal resource requirements in imaging, language, code and audio. |
- ElevenLabs - reference/getting-started) | ElevenLabs offers a voice generation API to produce highly realistic and natural-sounding voices. |
- Perplexity AI - started) | Perplexity is like an AI-powered swiss army knife helping in information discovery, summarizing content, exploring new topics etc. |
- Mistral AI
GenAI APIs (Other API Providers)
- DeepAI - friendly platform providing state-of-the-art AI tools & APIs that unlock and enhance creativity across industries, widely democratizing access to AI technologies for both developers and non-tech users. |
- Clarifai API - guide/api-overview/) | Clarifai offers access to various popular generative AI models (LLM, multimodal, image, video). |
- Lovo AI - started) | Lovo lets you generate advanced AI voices for any use case. |
- Jasper AI - started-1) | Jasper assist marketers in creating, optimizing and publishing content effectively using AI. |
- Tavus AI - reference/phoenix-replica-model/create-replica) | Tavus offers an AI voice API converting text to video with features like voice cloning, lip-syncing, and script generation, realistic avatars and others. |
- Colossyan
- Synthesia - started) | Synthesia offers an API to turn text to video in minutes with AI avatars and voiceovers in 130+ languages. |
- IBM Watson AI
- Writer - reference/list-models) | Writer provides APIs for generating, enhancing, and personalizing content. |
- Together AI - source models in a couple lines of code. |
- GooseAI - as-a-Service, offering various GPT-based models with high customization and speed. |
- Voyage AI - api) | Voyage AI provides API endpoints for embedding and reranking models. |
- AI/ML API
- Wit.ai
- PlayHT - getting-started) | Play.ht provides realistic text-to-speech voices and audio generation for various applications. |
- Chooch AI
- Clipdrop
- Astria AI - tuning and customization of generative image models. |
- Magic Slides - api/docs) | Professional Presentations in Seconds with AI. |
- Mubert
- SharpAPI - Commerce, Marketing, Content Management, HR Tech, Travel, etc.|
- Leonardo AI
- Pollinations.AI - signup APIs for text, image, and audio generation with no API keys required. |
- Llama AI - api.com/quickstart) | Offers APIs to access Llama models to answer complex queries and generate text.|
- Deepbrain AI - started) | DeepBrain AI offers natural text-to-speech capabilities & a powerful video generator that converts various inputs like text prompts, URLs, PDFs, and articles into engaging, professional-quality videos. |
- QuickSilver Pro - compatible inference API for open-weight LLMs (DeepSeek, Qwen, Kimi) and the Google Gemini family. Drop-in base URL, with a machine-readable pricing feed at /pricing.json. |
- Text-Generator - generator.io/docs) | Unified text, vision, and speech API with privacy-first design. ChatGPT-compatible endpoint for text generation, image understanding, and speech processing. |
- Netwrck
- HeyGen AI - | Heygen let's you create produce studio-quality videos with AI-generated avatars and voices. |
- Vedika - powered Vedic astrology API. Natural language queries for birth charts, compatibility analysis, and predictions |
- Tunova - song music generation — REST + a hosted MCP server, async signed webhooks, billed only on successful renders (failed generations auto-refund) |
- Databricks - learning/foundation-models/api-reference.html) | Databricks supports Foundation Model APIs which allow you to access and query state-of-the-art open models. You can quickly and easily build applications that leverage a high-quality generative AI model without maintaining your own model deployment. |
Other AI Tools
- Arch Tools
- GEOScore - txt-generator) | Free AI search visibility scanner that checks if your site can be found by ChatGPT, Perplexity, Claude & Gemini. Includes AI Robots.txt Generator and AI Crawler Checker |
- Prompeteer.ai - save cloud library |
- LLM Latency Tracker - latency-tracker) | Measured latency (TTFB, plus real time-to-first-token) and uptime for ~45 AI inference APIs from 4 regions, updated continuously. Free JSON API, MCP server, model deprecation calendar; data CC-BY-4.0 |
- ChangeRadar
- peyeeye - sealed blobs |
- unslop - 14/unslop) | CLI that strips AI writing patterns from content before publishing: sycophantic openers, stock vocabulary, hedging stacks, em-dash overuse. Code blocks, URLs, and technical terms pass through unchanged. Pipe mode for scripting |
- prompt-to-asset - 14/prompt-to-asset) | MCP server that generates production-ready visual assets (app icons, favicons, OG images, logos, wordmarks) by routing prompts across 30+ image generation models. Zero API key required for first run via free tiers |
- AceTagGen Suno Scorer - prompt-scorer) | Free CORS-enabled REST API that scores Suno AI music prompts on a 100-point scale across 4 metrics (length, tag collisions, specificity, density) |
- Not Human Search - first search engine indexing 9,000+ AI-accessible tools. REST API and MCP server for discovering tools with APIs, MCP endpoints, and structured data. |
- Consensus Room
- Humanizer PRO - pro-mcp) | Humanizer PRO API transforms AI-generated text into natural human-like writing and provides AI detection analysis tools |
- BGPT - mcp) | MCP server and API for searching scientific papers and returning structured experimental data (methods, results, sample sizes, quality scores) extracted from full-text studies |
- Superhighway - per-call |