Express API

Express API is an AI model-aggregator API that gives developers access to Chinese AI models — including DeepSeek, Kimi, Qwen, Doubao, GLM, ERNIE, MiniMax, and Hunyuan — through a single OpenAI-compatible endpoint. Because it is 100% OpenAI-compatible, you switch to it by changing only the base_url in an existing OpenAI SDK setup, with no other code rewrites. Billing is pay-as-you-go with transparent per-token pricing that lists input and output rates separately per model, so there is no subscription. Published examples include DeepSeek deepseek-v4-pro at $0.60 per 1M input tokens and $1.80 per 1M output tokens, deepseek-v4-flash at $0.20/$0.85 per 1M, and Kimi kimi-k3 (a multimodal vision model) at $3.00/$12.00 per 1M. Payments are handled in USD via Stripe, and new signups receive a small free credit to test the endpoint. The catalog spans reasoning, fast code, long-context (128K), and vision models across multiple Chinese vendors, letting teams route to the cheapest or most capable model for each task without managing separate provider accounts. It targets developers building agents, chat apps, and code tools who want low-latency access to Chinese models priced in USD.

Best for developers who want to call DeepSeek, Kimi, Qwen, and other Chinese models through one OpenAI-compatible API billed per token in USD.