Chinese model APIs on one OpenAI-compatible key. Browse models

Curated model API catalog

Chinese AI models and API availability

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

Showing 33 models

DeepSeek

DeepSeek Flash

deepseek-chat

LivePopular

Cost-efficient Chinese frontier chat and coding model for production assistants, agents and high-volume API workloads.

Context
1M
Speed
Balanced
Input / 1M
$0.3
Output / 1M
$1.2
reasoningcodingjsonlow cost

Z.ai

GLM-5.3

glm-5.3

LivePopularNew

Zhipu GLM-5.3 frontier text route with a 1M-class context window for enterprise and developer workloads. Available through the configured text route.

Context
1M
Speed
Reasoning
Input / 1M
$1.4
Output / 1M
$4.4
reasoningcodinglong context

Moonshot AI

Kimi K3

kimi-k3

LivePopularNew

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.

Context
1M
Speed
Reasoning
Input / 1M
$3
Output / 1M
$15
reasoningcodinglong context

DeepSeek

DeepSeek V4 Pro

deepseek-v4-pro

Live

DeepSeek V4 Pro text chat and reasoning through a verified dedicated route.

Context
1M
Speed
Reasoning
Input / 1M
$1.32
Output / 1M
$3.96
reasoningcodinglong context

DeepSeek

DeepSeek V4 Pro (TokenHub)

deepseek-tokenhub-pro

Live

Text chat via the configured TokenHub Singapore route.

Context
1M
Speed
Balanced
Input / 1M
$1.74
Output / 1M
$3.48
reasoningcodinglong context

DeepSeek

DeepSeek V4.1 Flash

deepseek-v4.1-flash

Live

Text chat via the configured TokenHub Singapore route.

Context
1M
Speed
Balanced
Input / 1M
$0.3
Output / 1M
$1.2
reasoningcodinglong context

DeepSeek

DeepSeek V4.1 Flash (Vendor Direct)

deepseek-tokenhub-flash

Live

Text chat via the configured TokenHub Singapore route.

Context
1M
Speed
Balanced
Input / 1M
$0.3
Output / 1M
$1.2
reasoningcodinglong context

Z.ai

GLM-5.2

glm-5.2

LiveNew

Zhipu GLM-5.2 text route for enterprise assistants and coding support. Available through the configured text route.

Context
1M
Speed
Balanced
Input / 1M
$1.4
Output / 1M
$4.4
reasoningcodinglong context

Moonshot AI

Kimi K2.7 Code

kimi-k2.7-code

Live

Text chat via the configured TokenHub Singapore route.

Context
256K
Speed
Balanced
Input / 1M
$0.95
Output / 1M
$4
reasoningcodinglong context

Moonshot AI

Kimi K3.1 Pro

kimi-k3.1-pro

Live

Text chat via the configured TokenHub Singapore route.

Context
1M
Speed
Balanced
Input / 1M
$2
Output / 1M
$10
reasoningcodinglong context

MiniMax

MiniMax M2.7

minimax-m2

Live

MiniMax M2.7 text route for agentic coding, long-running developer workflows.

Context
200K
Speed
Balanced
Input / 1M
$0.3
Output / 1M
$1.2
reasoningcodinglow cost

MiniMax

MiniMax M3

minimax-m3

IntegratingNew

MiniMax M3 text route for agentic coding and high-context developer workflows. Catalogued as Integrating on SmarToken.

Context
512K
Speed
Balanced
Input / 1M
$0.6
Output / 1M
$2.4
reasoningcodingtool callingjson

Alibaba Cloud

Qwen3.7 Plus

qwen3.7-plus

IntegratingNew

Alibaba Qwen3.7 Plus multimodal route for text, vision and long-context app workloads. Catalogued as Integrating until the live route is confirmed.

Context
1M
Speed
Fast
Input / 1M
$0.276
Output / 1M
$1.101
reasoningcodingjsonmultilingual

Qihoo 360

360 Zhinao

360zhinao2-o1

Integrating

360 Zhinao route for Chinese reasoning, security-adjacent assistants and long-context experimentation when configured upstream.

Context
32K
Speed
Balanced
Input / 1M
$0.4
Output / 1M
$1
reasoningjsonlong context

Baichuan AI

Baichuan4 Turbo

baichuan4-turbo

Integrating

Baichuan route for Chinese enterprise assistants, healthcare-adjacent knowledge workflows and bilingual business tasks.

Context
32K
Speed
Balanced
Input / 1M
$1.5
Output / 1M
$1.5
reasoningjsonmultilingual

ByteDance

Doubao Seed

doubao-seed

IntegratingNew

ByteDance model family route for conversational, multimodal and consumer-facing workloads at scale.

Context
128K
Speed
Fast
Input / 1M
$0.7
Output / 1M
$2.8
fastmultilingualvisionjson

Baidu

ERNIE 4 Turbo

ernie-4-turbo

Integrating

Baidu's enterprise model line is useful for Chinese-language knowledge, search-adjacent and business workflows.

Context
128K
Speed
Balanced
Input / 1M
$0.9
Output / 1M
$3.6
reasoningmultilingualjson

Z.ai

GLM-4 Flash

glm-4-flash

Integrating

Enterprise-friendly Chinese model route with good reasoning, coding and low-latency deployment options.

Context
128K
Speed
Fast
Input / 1M
$0.8
Output / 1M
$3.2
reasoningcodingfastjson

Z.ai

GLM-5V Turbo

glm-5v-turbo

IntegratingNew

Zhipu GLM-5V Turbo multimodal route for vision-language tasks. Catalogued as Integrating until the live multimodal path is confirmed.

Context
200K
Speed
Fast
Input / 1M
$1.2
Output / 1M
$4
visionreasoningjsonfast

Alibaba Cloud

HappyHorse Text-to-Video

happyhorse-t2v

IntegratingNew

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.

Context
Video clip
Speed
Media
Input / 1M
$2.8
Output / 1M
$2.8
video generation

Tencent Cloud

Hunyuan TurboS

hunyuan-turbos

Integrating

Tencent Hunyuan route for Chinese content creation, logic reasoning, code generation and multi-turn dialogue.

Context
128K
Speed
Fast
Input / 1M
$0.8
Output / 1M
$3.2
reasoningcodingtool callingjson

Shanghai AI Laboratory

InternLM3

internlm3

Integrating

InternLM route for open-source Chinese model evaluation, self-hosted deployments and research-friendly application testing.

Context
200K
Speed
Self-hosted
Input / 1M
$0.2
Output / 1M
$0.8
reasoningcodingjsonlong context

Moonshot AI

Kimi K2

kimi-k2

Integrating

Long-context and agentic model from Moonshot AI, useful for research, codebase reading and complex multi-step workflows.

Context
256K
Speed
Balanced
Input / 1M
$0.6
Output / 1M
$2.5
reasoningcodingtool callinglong context

Moonshot AI

Kimi K2.6

kimi-k2.6

IntegratingNew

Moonshot Kimi K2.6 text route for long-context research and agent workflows. Catalogued while the dedicated SmarToken route is being wired.

Context
262K
Speed
Balanced
Input / 1M
$0.95
Output / 1M
$4
reasoningcodingtool callinglong context

Meituan

LongCat Flash

longcat-flash

IntegratingNew

Meituan LongCat route for open multimodal and reasoning model evaluation, including Flash chat and thinking-style variants.

Context
128K
Speed
Fast
Input / 1M
$0.4
Output / 1M
$1.6
reasoningcodingvisiontool calling

MiniMax

MiniMax Video-01

minimax-video-01

IntegratingNew

MiniMax video generation route for text-to-video and image-to-video style experiments. Integrating on SmarToken; not a Live production media endpoint yet.

Context
Video clip
Speed
Media
Input / 1M
$3
Output / 1M
$3
video generationvision

Huawei Cloud

Pangu NLP

pangu-nlp

Integrating

Huawei Pangu route for enterprise NLP, industry model applications and Huawei Cloud ModelArts-style deployments.

Context
32K
Speed
Enterprise
Input / 1M
$1
Output / 1M
$4
reasoningjsonmultilingual

Alibaba Cloud

Qwen Plus

qwen-plus

Integrating

Alibaba's broad model family is popular for multilingual apps, structured output, coding and open ecosystem coverage.

Context
128K
Speed
Fast
Input / 1M
$1.2
Output / 1M
$4.8
reasoningcodingjsonmultilingual

SenseTime

SenseNova V6

sensenova-v6

Integrating

SenseNova route for multimodal reasoning, enterprise visual workflows and text-generation scenarios from SenseTime.

Context
128K
Speed
Balanced
Input / 1M
$0.8
Output / 1M
$3.2
reasoningvisiontool callingjson

iFLYTEK

Spark X1

spark-x1

Integrating

iFLYTEK Spark route for deep reasoning, Chinese-language productivity, education, speech-adjacent and enterprise scenarios.

Context
64K
Speed
Balanced
Input / 1M
$0.7
Output / 1M
$2.8
reasoningcodingmultilingualtool calling

StepFun

Step-3

step-3

IntegratingNew

StepFun model route for developer agents, code tools and cost-controlled high-frequency usage through Step-compatible APIs.

Context
128K
Speed
Balanced
Input / 1M
$0.5
Output / 1M
$2
reasoningcodingtool callinglong context

Alibaba Cloud

Wan Text-to-Video

wan-t2v

IntegratingNew

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.

Context
Video clip
Speed
Media
Input / 1M
$2.5
Output / 1M
$2.5
video generationmultilingual

01.AI

Yi Large

yi-large

Integrating

01.AI Yi route for bilingual generation, structured outputs and legacy Yi-family compatibility through supported upstream providers.

Context
32K
Speed
Balanced
Input / 1M
$0.9
Output / 1M
$0.9
reasoningcodingjsonmultilingual

Live routes first

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.

Facts for SEO / GEO citation

  • Product: SmarToken Chinese-model API gateway with prepaid USD wallet.
  • Protocol: OpenAI-compatible Chat Completions via https://thesmartoken.com/v1.
  • Live DeepSeek IDs: deepseek-chat, deepseek-v4-pro.
  • Signup for overseas developers: Google sign-in, no Chinese phone required.
  • Status language: Live vs Integrating is explicit on every catalog card.

Need another model? Submit a request and operations can evaluate the route.

Submit request