DeepSeek
Live Flash + V4 Pro. Highest overseas API search demand.
Curated model API catalog
Browse Live and Integrating Chinese model routes on one OpenAI-compatible API. Filter by type or provider, then open a model page for IDs and pricing.
17 providers · 33 catalog routes · 11 live · Base URL https://thesmartoken.com/v1
DeepSeek reference prices use peak hours and uncached input. Off-peak rates are 50% lower; cached input is billed at its discounted rate. View all DeepSeek rates
Live Flash + V4 Pro. Highest overseas API search demand.
Long-context Kimi K2 / K2.6 / K3 family. Integrating routes listed.
Qwen Plus, Qwen3.7 Plus, and Integrating Wan / HappyHorse video rows.
GLM-4 Flash plus GLM-5.x and GLM-5V Turbo Integrating entries.
MiniMax text agents plus Integrating video catalog entries.
DeepSeek
deepseek-chat
Cost-efficient Chinese frontier chat and coding model for production assistants, agents and high-volume API workloads.
Z.ai
glm-5.3
Zhipu GLM-5.3 frontier text route with a 1M-class context window for enterprise and developer workloads. Available through the configured text route.
Moonshot AI
kimi-k3
Moonshot Kimi K3 frontier text route with a 1M-class context window for deep research and multi-step agents. Available through the configured text route.
DeepSeek
deepseek-v4-pro
DeepSeek V4 Pro text chat and reasoning through a verified dedicated route.
DeepSeek
deepseek-tokenhub-pro
Text chat via the configured TokenHub Singapore route.
DeepSeek
deepseek-v4.1-flash
Text chat via the configured TokenHub Singapore route.
DeepSeek
deepseek-tokenhub-flash
Text chat via the configured TokenHub Singapore route.
Z.ai
glm-5.2
Zhipu GLM-5.2 text route for enterprise assistants and coding support. Available through the configured text route.
Moonshot AI
kimi-k2.7-code
Text chat via the configured TokenHub Singapore route.
Moonshot AI
kimi-k3.1-pro
Text chat via the configured TokenHub Singapore route.
MiniMax
minimax-m2
MiniMax M2.7 text route for agentic coding, long-running developer workflows.
MiniMax
minimax-m3
MiniMax M3 text route for agentic coding and high-context developer workflows. Catalogued as Integrating on SmarToken.
Alibaba Cloud
qwen3.7-plus
Alibaba Qwen3.7 Plus multimodal route for text, vision and long-context app workloads. Catalogued as Integrating until the live route is confirmed.
Qihoo 360
360zhinao2-o1
360 Zhinao route for Chinese reasoning, security-adjacent assistants and long-context experimentation when configured upstream.
Baichuan AI
baichuan4-turbo
Baichuan route for Chinese enterprise assistants, healthcare-adjacent knowledge workflows and bilingual business tasks.
ByteDance
doubao-seed
ByteDance model family route for conversational, multimodal and consumer-facing workloads at scale.
Baidu
ernie-4-turbo
Baidu's enterprise model line is useful for Chinese-language knowledge, search-adjacent and business workflows.
Z.ai
glm-4-flash
Enterprise-friendly Chinese model route with good reasoning, coding and low-latency deployment options.
Z.ai
glm-5v-turbo
Zhipu GLM-5V Turbo multimodal route for vision-language tasks. Catalogued as Integrating until the live multimodal path is confirmed.
Alibaba Cloud
happyhorse-t2v
HappyHorse-class Chinese text-to-video catalog entry for overseas AI video generation API research. Marked Integrating while the SmarToken media route is being wired.
Tencent Cloud
hunyuan-turbos
Tencent Hunyuan route for Chinese content creation, logic reasoning, code generation and multi-turn dialogue.
Shanghai AI Laboratory
internlm3
InternLM route for open-source Chinese model evaluation, self-hosted deployments and research-friendly application testing.
Moonshot AI
kimi-k2
Long-context and agentic model from Moonshot AI, useful for research, codebase reading and complex multi-step workflows.
Moonshot AI
kimi-k2.6
Moonshot Kimi K2.6 text route for long-context research and agent workflows. Catalogued while the dedicated SmarToken route is being wired.
Meituan
longcat-flash
Meituan LongCat route for open multimodal and reasoning model evaluation, including Flash chat and thinking-style variants.
MiniMax
minimax-video-01
MiniMax video generation route for text-to-video and image-to-video style experiments. Integrating on SmarToken; not a Live production media endpoint yet.
Huawei Cloud
pangu-nlp
Huawei Pangu route for enterprise NLP, industry model applications and Huawei Cloud ModelArts-style deployments.
Alibaba Cloud
qwen-plus
Alibaba's broad model family is popular for multilingual apps, structured output, coding and open ecosystem coverage.
SenseTime
sensenova-v6
SenseNova route for multimodal reasoning, enterprise visual workflows and text-generation scenarios from SenseTime.
iFLYTEK
spark-x1
iFLYTEK Spark route for deep reasoning, Chinese-language productivity, education, speech-adjacent and enterprise scenarios.
StepFun
step-3
StepFun model route for developer agents, code tools and cost-controlled high-frequency usage through Step-compatible APIs.
Alibaba Cloud
wan-t2v
Alibaba Wan-class text-to-video route for short AI video generation API workloads. Catalogued as Integrating on SmarToken until the live media endpoint is confirmed.
01.AI
yi-large
01.AI Yi route for bilingual generation, structured outputs and legacy Yi-family compatibility through supported upstream providers.
Production traffic should use Live model IDs only. Integrating entries are catalogued so you can plan migrations, but they are not promised as production-stable until status flips to Live.
Need another model? Submit a request and operations can evaluate the route.
Submit request