One gateway behind every agent
Use XinoAPI as the model provider behind developer agents. Keep one billing account while routing tasks across Chinese frontier models.
Codex CLI
Point Codex at https://api.xinoapi.com/v1 and use deepseek-v4-pro-0813 for code planning or deepseek-v4-flash-0731 for fast edits.
Claude Code
Claude Code uses Anthropic's Messages API shape. Planned — not available for production. Do not configure Claude Code against an XinoAPI Anthropic endpoint. Use a client with an OpenAI-compatible provider mode for current integrations.
OpenClaw
Configure OpenClaw as an OpenAI-compatible provider with a XinoAPI key, then select agent-ready aliases or explicit model IDs.
CC Switch
Add XinoAPI as a custom OpenAI-compatible provider in CC Switch, then reuse the same endpoint for supported coding CLIs where the client supports the OpenAI-compatible protocol. Claude Code requires a separate adapter; the native bridge is planned.
Configure your client
Use these snippets as starting points. Replace xino-your-key with an API key from the XinoAPI dashboard.
Anthropic-compatible bridge
Claude Code uses Anthropic Messages. The native XinoAPI bridge is planned. Use the OpenAI-compatible client configurations on this page for current integrations.
Current integration guidanceCommercial positioning: XinoAPI is not trying to be the cheapest router. It is built for stable coding-agent sessions, China-model coverage, Stripe billing, no China KYC, spend control, and support for production teams.
Recommended agent models
Use model choice as a workflow decision: fast edits, complex planning, Chinese codebases, or enterprise reliability.
| Model | Best for | Price | Protocol |
|---|---|---|---|
| deepseek-v4-flash-0731 | General chat and code edits | Pending verification input · Pending verification output / 1M tokens | OpenAI |
| deepseek-v4-pro-0813 | Planning and code review | Pending verification input · Pending verification output / 1M tokens | OpenAI |
| qwen3.7-plus | General language tasks | $0.3011 input · $1.2045 output / 1M tokens | OpenAI |
| glm-5.3-flash | Evaluate for agent workflows | Pending verification input · Pending verification output / 1M tokens | OpenAI |
Public pricing snapshot: 2026-10-14. Pending prices require account quote confirmation. Context, output limits, and parameter support must be confirmed for the selected route. Full pricing.
Agent-ready by design
Stable long-running tasks
Agent sessions depend on continuous SSE streaming, predictable retries, and clean timeout behavior.
Function calling support
Use tool calls for search, shell planning, patch generation, structured extraction, and verifier loops.
Spend control
Minimum $20 top-up, published featured-model savings, clear usage logs, and enterprise billing for production teams.
Where the gateway is going
- OpenAI-compatible
/v1/chat/completions - Streaming responses
- DeepSeek, Qwen, GLM, Kimi, MiniMax routing
- Stripe billing and usage accounting
- Anthropic-compatible bridge for Claude Code — planned, not available for production
- Agent aliases like
xino-agent-fastandxino-agent-pro - Per-agent spend caps and fallback chains
- Agent logs for enterprise debugging
Not just another generic router
The pitch is reliability and China-model specialization, not lowest token price alone.
| Need | XinoAPI advantage | Why it matters for agents |
|---|---|---|
| China model access | DeepSeek, Qwen, GLM, Kimi, MiniMax focus | One provider for teams building on Chinese frontier models |
| No China-specific KYC for standard self-service use | Stripe and USD billing | Overseas developers can start without Chinese phone or payment rails |
| Agent reliability | Routing, fallback, and spend controls | Long coding tasks fail less often and are easier to audit |
| Commercial support | Invoice and enterprise support path | Production teams need support paths, routing controls, and predictable billing |