APIMODELS (apimodels.app) is a multi-model AI API platform for developers and teams. One API key and one prepaid USD balance give access to 160+ models for image generation and editing, video generation, text-to-speech and other audio, embeddings, and large language models, including Claude, GPT, Gemini, Grok, DeepSeek, Qwen, GLM, Seedream, FLUX, Seedance, Kling, Veo, Wan, MiniMax and ElevenLabs.
Drop-in compatible: language models are served in OpenAI-compatible (Chat Completions and Responses), Anthropic-compatible (Messages) and native Gemini formats, so existing SDKs and tools such as Claude Code, Codex, Cursor and Cherry Studio work by changing the base URL and key. Image, video and speech models use REST endpoints with the same key, and the model list endpoint can be read without a key.
Stability first: popular models run on more than one upstream channel. If the primary provider errors, rate-limits or times out, the request is retried on another channel automatically. Failed calls are never charged, and every response carries a request ID that returns the exact amount deducted for that call.
Agents and MCP: a hosted MCP server and the apimodels-mcp npm package let Claude Desktop, Cursor and Cherry Studio generate images, video and voice-overs.
Pricing: pay as you go, no subscription. LLMs are billed per token, images per image and video per second, at the rate shown on each model page; many models are priced below the official list price, up to 95% lower. Top-ups start at $10 by card, PayPal, Alipay or USDT.
Limits: generated files are kept for 30 days and then deleted, so download anything you need to keep. If you only use one provider and already have a direct account with it, calling that provider directly is simpler.
No comments or reviews, maybe you want to be first?