Curated model API catalog
Browse DeepSeek, Kimi, Qwen, GLM, Doubao, ERNIE, Hunyuan, MiniMax, StepFun, Spark, Pangu, InternLM, LongCat and other China-first routes by capability, context window and USD token pricing. Each model page includes source links, API examples, practical FAQ and a path into the console.
This catalog focuses on mainstream model families that can be routed through API workflows, not every Chinese generative AI service filing.
DeepSeek
128K context · $0.6/1M in
Moonshot AI
256K context · $0.72/1M in
Alibaba Cloud
128K context · $1.44/1M in
Z.ai
128K context · $0.96/1M in
ByteDance
128K context · $0.84/1M in
Baidu
128K context · $1.08/1M in
Tencent Cloud
128K context · $0.96/1M in
MiniMax
128K context · $0.36/1M in
StepFun
128K context · $0.6/1M in
Baichuan AI
32K context · $1.8/1M in
iFLYTEK
64K context · $0.84/1M in
SenseTime
128K context · $0.96/1M in
Huawei Cloud
32K context · $1.2/1M in
Qihoo 360
32K context · $0.48/1M in
01.AI
32K context · $1.08/1M in
Shanghai AI Laboratory
200K context · $0.24/1M in
Meituan
128K context · $0.48/1M in
Not sure where to start? Read the integration docs
DeepSeek
deepseek-chat
Cost-efficient Chinese frontier chat and coding model for production assistants, agents and high-volume API workloads.
Moonshot AI
kimi-k2
Long-context and agentic model from Moonshot AI, useful for research, codebase reading and complex multi-step workflows.
Alibaba Cloud
qwen-plus
Alibaba's broad model family is popular for multilingual apps, structured output, coding and open ecosystem coverage.
Z.ai
glm-4-flash
Enterprise-friendly Chinese model route with good reasoning, coding and low-latency deployment options.
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.
Tencent Cloud
hunyuan-turbos
Tencent Hunyuan route for Chinese content creation, logic reasoning, code generation and multi-turn dialogue.
MiniMax
minimax-m2
MiniMax M2.7-style route for agentic coding, long-running developer workflows and multimodal platform evaluation.
StepFun
step-3
StepFun model route for developer agents, code tools and cost-controlled high-frequency usage through Step-compatible APIs.
Baichuan AI
baichuan4-turbo
Baichuan route for Chinese enterprise assistants, healthcare-adjacent knowledge workflows and bilingual business tasks.
iFLYTEK
spark-x1
iFLYTEK Spark route for deep reasoning, Chinese-language productivity, education, speech-adjacent and enterprise scenarios.
SenseTime
sensenova-v6
SenseNova route for multimodal reasoning, enterprise visual workflows and text-generation scenarios from SenseTime.
Huawei Cloud
pangu-nlp
Huawei Pangu route for enterprise NLP, industry model applications and Huawei Cloud ModelArts-style deployments.
Qihoo 360
360zhinao2-o1
360 Zhinao route for Chinese reasoning, security-adjacent assistants and long-context experimentation when configured upstream.
01.AI
yi-large
01.AI Yi route for bilingual generation, structured outputs and legacy Yi-family compatibility through supported upstream providers.
Shanghai AI Laboratory
internlm3
InternLM route for open-source Chinese model evaluation, self-hosted deployments and research-friendly application testing.
Meituan
longcat-flash
Meituan LongCat route for open multimodal and reasoning model evaluation, including Flash chat and thinking-style variants.
Need another model? Submit a request and operations can evaluate the route.
Submit request