China-first catalog
Model pages, use cases and pricing focus on DeepSeek, Qwen, Kimi, GLM and other Chinese families.
OpenRouter migration
SmarToken gives global developers one OpenAI-compatible API for DeepSeek, Qwen, Kimi, GLM, Doubao, Hunyuan and MiniMax. Keep familiar SDKs while moving China-model traffic to a gateway built for that job.
Model pages, use cases and pricing focus on DeepSeek, Qwen, Kimi, GLM and other Chinese families.
Common OpenRouter-style aliases are normalized so SDK code needs fewer model-name changes.
Budget-limited keys, usage logs and prepaid balance help teams test Chinese models without runaway spend.
If your OpenRouter traffic is mostly Chinese models, the migration path can be as small as replacing credentials and keeping the model alias.
const client = new OpenAI({
apiKey: process.env.OPENROUTER_API_KEY,
baseURL: "https://openrouter.ai/api/v1",
});
await client.chat.completions.create({
model: "deepseek/deepseek-chat",
messages,
});const client = new OpenAI({
apiKey: process.env.SMTOKEN_API_KEY,
baseURL: "https://thesmartoken.com/v1",
});
await client.chat.completions.create({
model: "deepseek/deepseek-chat",
messages,
});Alias map
| SmarToken model | Provider | OpenRouter-style aliases | Best for |
|---|---|---|---|
| deepseek-chat | DeepSeek | deepseek/deepseek-chat | coding copilots, support agents |
| kimi-k2 | Moonshot AI | moonshot/kimi-k2 | research assistants, codebase analysis |
| qwen-plus | Alibaba Cloud | qwen/qwen-plus, alibaba/qwen-plus | multilingual chat, structured extraction |
| glm-4-flash | Z.ai | z-ai/glm-4-flash, thudm/glm-4-flash | internal tools, knowledge assistants |
| doubao-seed | ByteDance | bytedance/doubao-seed | consumer chat, content workflows |
| ernie-4-turbo | Baidu | baidu/ernie-4-turbo | Chinese knowledge QA, enterprise search |
| hunyuan-turbos | Tencent Cloud | tencent/hunyuan-turbos | enterprise assistants, code generation |
| minimax-m2 | MiniMax | minimax/minimax-m2 | coding agents, tool-use workflows |
| step-3 | StepFun | stepfun/step-3 | coding tools, agent platforms |
| baichuan4-turbo | Baichuan AI | baichuan/baichuan4-turbo | domain assistants, Chinese knowledge QA |
SmarToken is not trying to mirror every global model on OpenRouter. It is a focused alternative for teams whose priority is Chinese frontier models such as DeepSeek, Qwen, Kimi, GLM, Doubao, Hunyuan and MiniMax.
Yes. Keep the OpenAI SDK, set baseURL to https://thesmartoken.com/v1, use a SmarToken API key and choose a supported model ID or OpenRouter-style alias.
Common Chinese model aliases such as deepseek/deepseek-chat, qwen/qwen-plus and moonshot/kimi-k2 are normalized to SmarToken model IDs.