Access DeepSeek, Qwen, GLM, Kimi, and MiniMax through one API. Built for global developers outside mainland China, with Stripe billing, agent-ready routing, and privacy-conscious defaults.
Routing is optimized through Singapore, Hong Kong, and Tokyo paths, with dedicated enterprise routes available on request.
XinoAPI does not retain plaintext prompts or completions by default. Billing and abuse-prevention use metadata, and optional local redaction helps protect sensitive inputs.
Automatic channel switching across compatible upstream routes helps reduce interruptions when a model or provider path is degraded.
| Model | Context | Input Price | Output Price | Latency (TTFT) |
|---|---|---|---|---|
| DeepSeek V4-Flash NEW | 1M | $0.175/M | $0.35/M | |
| DeepSeek V4-Pro FLAGSHIP | 1M | $0.533/M | $1.066/M | |
| Qwen 3.6 Plus NEW | 1M | $0.50/M | $1.50/M | |
| Qwen 3.6 Max Preview FLAGSHIP | 260K | $2.00/M | $8.00/M | |
| GLM-5.1 NEW | 200K | $1.25/M | $5.00/M | |
| GLM-5 HOT | 200K | $1.25/M | $4.00/M | |
| GLM-4.7 STABLE | 128K | $0.1875/M | $0.75/M | |
| Kimi K2.6 NEW | 256K | $0.75/M | $3.75/M | |
| Kimi K2.5 STABLE | 256K | $0.75/M | $3.75/M | |
| MiniMax M2.7 STABLE | 205K | $0.375/M | $1.50/M |
* Prices include XinoAPI routing markup. Updated daily. All endpoints are OpenAI API-compatible.
Sign up for self-service access, claim $2.00 free credits, and test 5 LLM provider families through one OpenAI-compatible API.
Self-service onboarding - supported regions only - Privacy SDK available