Chinese LLM APIs
Language models from DeepSeek, Alibaba Qwen, Moonshot Kimi, Zhipu GLM, MiniMax, Xiaomi MiMo, ByteDance Seed, Tencent Hunyuan and StepFun, on one OpenAI-compatible API.
All Chinese LLM APIs
Preview the output style, compare capabilities, then open any model for full specs, pricing, and a live Playground.
DeepSeek V4.1 Flash
DeepSeek V4.1 Flash is the smallest model in DeepSeek's V4.1 architecture family, released in September 2026 with native visual understanding. It is a 552B-parameter mixture-of-experts model using a C...
DeepSeek V4 Pro
DeepSeek V4 Pro is the large tier of DeepSeek's V4 family, a 1.6T-parameter mixture-of-experts model with 49B active parameters, introduced as an open-weight preview in April 2026 with a 1M-token cont...
DeepSeek V4 Flash
DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fa...
DeepSeek V3.2
DeepSeek-V3.2 is DeepSeek's open-weight, reasoning-first model released in December 2025 as the official successor to V3.2-Exp. It introduces DeepSeek Sparse Attention to reduce long-context training ...
Qwen3.8 Max
Qwen3.8 Max is Alibaba's flagship Qwen3.8 model, a 2.4-trillion-parameter Mixture-of-Experts reasoning model with native vision understanding, released in August 2026. Alibaba positions it for long-ho...
Qwen3.7 Plus
Qwen3.7 Plus is the balanced Plus tier of Alibaba's Qwen3.7 series, a reasoning model with text and image input released in June 2026. Alibaba highlights its multimodal hybrid agent abilities: perceiv...
Qwen3.6 Plus
Qwen3.6 Plus is the Plus tier of Alibaba's Qwen3.6 series, a hosted native vision-language reasoning model released in April 2026. Alibaba reports marked gains over the Qwen3.5 series in agentic codin...
Kimi K3.1 Pro
Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model, a post-trained successor to Kimi K3 with a 1M-token context window. It accepts text, image and video input and is built ...
Kimi K3
Kimi K3 is Moonshot AI's flagship model, a 2.8-trillion-parameter open-weight mixture-of-experts model with native visual understanding and a 1M-token context. It is built on Kimi Delta Attention, a h...
Kimi K2.6
Kimi K2.6 is Moonshot AI's general-purpose multimodal model, taking text, image and video input with both thinking and non-thinking modes and a 256K-token context. Moonshot highlights more reliable lo...
GLM 5.3
GLM-5.3 is Z.ai's flagship text model for complex software engineering and long-horizon agent work, built on the same base model as GLM-5.2 with all gains coming from expanded post-training. Z.ai high...
GLM 5.2
GLM-5.2 is Z.ai's open-weight flagship text model released in June 2026 for long-horizon tasks, and the first GLM model to deliver that capability on a usable 1M-token context. Z.ai positions it for p...
MiniMax M3.1 Flash
MiniMax-M3.1-Flash is the fast, cost-efficient tier of MiniMax's M3.1 generation, which MiniMax describes as an ultra-efficient open-weight model for everyday work. It is a multimodal coding model tha...
MiniMax M3
MiniMax-M3 is MiniMax's flagship multimodal foundation model, which MiniMax describes as open-weight. It is built on MiniMax Sparse Attention, which selects key-value blocks to cut long-context comput...
MiniMax M2.7
MiniMax-M2.7 is a MiniMax M2-series language model that MiniMax describes as its first model to take part in its own development, building agent harnesses, skills and memory for reinforcement learning...
MiMo-V2.6-Pro
MiMo-V2.6-Pro is the flagship of Xiaomi's open-source MiMo-V2.6 series, a trillion-parameter, natively omni-modal reasoning model released in September 2026 that takes text, image, video and audio inp...
Seed-2.1-Pro
Seed 2.1 Pro is the larger of the two models in ByteDance Seed's Seed2.1 family, offered as Doubao-Seed-2.1-Pro through Doubao and Volcano Engine. ByteDance built Seed2.1 for real-world productivity: ...
Hy4 preview
Hy4 preview is Tencent Hunyuan's open-source preview of its Hy4 generation, a mixture-of-experts language model with 770B total and 49B active parameters and a context window exceeding 1M tokens. Tenc...
Step 5 Preview
Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture with 27B active and 600B total parameters. It accepts text, image, and video input with a...
Model lineup
Context window and positioning from each provider.
| Model | Context | Positioning |
|---|---|---|
| DeepSeek V4 Flash | 1049K | DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters,… |
| DeepSeek V4 Pro | 1049K | DeepSeek V4 Pro is the large tier of DeepSeek's V4 family, a 1.6T-parameter mixture-of-experts model with 49B active parameters, introduced as an… |
| Kimi K3 | 1049K | Kimi K3 is Moonshot AI's flagship model, a 2.8-trillion-parameter open-weight mixture-of-experts model with native visual understanding and a… |
| Kimi K2.6 | 262K | Kimi K2.6 is Moonshot AI's general-purpose multimodal model, taking text, image and video input with both thinking and non-thinking modes and a… |
| GLM 5.2 | 1049K | GLM-5.2 is Z.ai's open-weight flagship text model released in June 2026 for long-horizon tasks, and the first GLM model to deliver that capability… |
| DeepSeek V3.2 | 131K | DeepSeek-V3.2 is DeepSeek's open-weight, reasoning-first model released in December 2025 as the official successor to V3.2-Exp |
| GLM 5.3 | 1049K | GLM-5.3 is Z.ai's flagship text model for complex software engineering and long-horizon agent work, built on the same base model as GLM-5.2 with all… |
| MiniMax M3 | 1000K | MiniMax-M3 is MiniMax's flagship multimodal foundation model, which MiniMax describes as open-weight |
| Qwen3.8 Max | 1000K | Qwen3.8 Max is Alibaba's flagship Qwen3.8 model, a 2.4-trillion-parameter Mixture-of-Experts reasoning model with native vision understanding,… |
| MiniMax M2.7 | 205K | MiniMax-M2.7 is a MiniMax M2-series language model that MiniMax describes as its first model to take part in its own development, building agent… |
| DeepSeek V4.1 Flash | 1049K | DeepSeek V4.1 Flash is the smallest model in DeepSeek's V4.1 architecture family, released in September 2026 with native visual understanding |
| Seed-2.1-Pro | 1049K | Seed 2.1 Pro is the larger of the two models in ByteDance Seed's Seed2.1 family, offered as Doubao-Seed-2.1-Pro through Doubao and Volcano Engine |
Leading Chinese language models, one key
Chinese labs ship competitive reasoning, coding and multimodal models, often with open weights and low token prices. SandBase serves them on the OpenAI-compatible POST /v1/chat/completions. You do not need a separate account with each provider.
On this page
- DeepSeek V4.1, V4 and V3.2; see DeepSeek.
- Qwen 3.8, 3.7 and 3.6 from Alibaba; see Qwen API.
- Kimi K3.1, K3 and K2.6 from Moonshot AI; see Moonshot AI.
- GLM 5.3 and 5.2 from Zhipu (Z.ai); see Z.ai.
- MiniMax M3.1 Flash, M3 and M2.7; Xiaomi MiMo V2.6; ByteDance Seed 2.1; Tencent Hunyuan 4; StepFun Step 5.
Open-weight options are collected on Open-Source LLMs.
Start using Chinese LLM APIs on SandBase
Switch models by changing one field.
- 01
Create an API key
Sign in to the SandBase Console and create a key on the API Keys page. Keep it in an environment variable and never commit it to source control.
TERMINALexport SANDBASE_API_KEY="YOUR_SANDBASE_API_KEY" - 02
Send a chat request
Call the OpenAI-compatible Chat Completions API with model deepseek/deepseek-v4-pro. Any OpenAI SDK works with base URL https://api.sandbase.ai/v1.
TERMINALcurl https://api.sandbase.ai/v1/chat/completions \ -H "Authorization: Bearer $SANDBASE_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model": "deepseek/deepseek-v4-pro", "messages": [{"role": "user", "content": "Explain vector databases in two sentences."}]}' - 03
Connect your AI tools
Use the same key in Claude Code, Codex, Cursor and other clients. See Use in AI tools for setup.
Questions, answered
Do I need a Chinese phone number or account?
No. Use your SandBase key; SandBase handles provider access and billing.
Are these models OpenAI-compatible?
Yes. Call them with the OpenAI SDK or any OpenAI-compatible client by setting the base URL.
Which Chinese model is the most used on SandBase?
DeepSeek V4 Flash, followed by Kimi K2.5 and DeepSeek V4 Pro.
Do they handle English well?
Yes. These models are multilingual and widely used for English tasks; test on your own prompts.
Build with Chinese LLM APIs.
One key, consistent APIs, and usage-based pricing across every model on this page.