DoroAI Supported Models: Limits and API Coverage
DoroAI lists 2 models: GPT-4o and Claude 3.5 Sonnet. This is a bare-bones relay aimed at developers who just want Codex access without paying.
DoroAI lists 2 models: GPT-4o and Claude 3.5 Sonnet. This is a bare-bones relay aimed at developers who just want Codex access without paying.
GPT-4o input costs $0 per million tokens — but only for your first ¥4 worth of usage. DawCode is a Chinese relay station that gives developers.
100% uptime on paper sounds great — until you actually measure response times from a Chinese ISP and see 1975ms latency for a single GPT-4o.
DawCode lists 2 models: GPT-4o and Claude 3.5 Sonnet. No Gemini, no DeepSeek, no open-source Llama variants. Best for developers needing a narrow catalog.
DawCode vs OpenRouter review records dated pricing, supported models, API limits, and author-reported reliability notes for solo developers.
Cubence Pricing review records dated pricing, supported models, API limits, and author-reported reliability notes for solo developers.
Claude 3.5 Sonnet through Cubence ranks in the top 3 on the hvoy.ai Claude Speed leaderboard — that’s the headline for anyone who’s tired of.
ClaudeCN routes exclusively to GPT-4o and Claude 3.5 Sonnet with a max context of 100,000 tokens, but its 94% uptime sits below the industry.
Claude 3.5 Sonnet via CCFly runs ¥2300/month for a dedicated MAX carpool seat — that's more than the official API subscription. Pricing.
100% uptime and 514ms average latency from Chinese ISPs — CCFly makes a narrow bet that developers in China want one thing: reliable Claude.