diff --git a/metagpt/configs/llm_config.py b/metagpt/configs/llm_config.py
index ef034ca494..733cd5d192 100644
--- a/metagpt/configs/llm_config.py
+++ b/metagpt/configs/llm_config.py
@@ -38,6 +38,7 @@ class LLMType(Enum):
     OPENROUTER = "openrouter"
     BEDROCK = "bedrock"
     ARK = "ark"  # https://www.volcengine.com/docs/82379/1263482#python-sdk
+    ZTEAI = "zte"
 
     def __missing__(self, key):
         return self.OPENAI
diff --git a/metagpt/provider/__init__.py b/metagpt/provider/__init__.py
index c90f5774ab..744e8d5076 100644
--- a/metagpt/provider/__init__.py
+++ b/metagpt/provider/__init__.py
@@ -19,6 +19,8 @@
 from metagpt.provider.anthropic_api import AnthropicLLM
 from metagpt.provider.bedrock_api import BedrockLLM
 from metagpt.provider.ark_api import ArkLLM
+from metagpt.provider.zteai_api import ZTEaiLLM
+
 
 __all__ = [
     "GeminiLLM",
@@ -34,4 +36,5 @@
     "AnthropicLLM",
     "BedrockLLM",
     "ArkLLM",
+    "ZTEaiLLM",
 ]
diff --git a/metagpt/provider/zteai_api.py b/metagpt/provider/zteai_api.py
new file mode 100644
index 0000000000..327601bdf9
--- /dev/null
+++ b/metagpt/provider/zteai_api.py
@@ -0,0 +1,63 @@
+import json
+from typing import Optional, Union
+
+import aiohttp
+
+from metagpt.configs.llm_config import LLMConfig, LLMType
+from metagpt.const import LLM_API_TIMEOUT, USE_CONFIG_TIMEOUT
+from metagpt.provider.base_llm import BaseLLM
+from metagpt.provider.llm_provider_registry import register_provider
+
+
+async def ZTEAI(querytext, appid, apikey, numb, token, modeltype):
+    url = "https://rdcloud.zte.com.cn/zte-studio-ai-platform/openapi/v1/chat"
+    headers = {
+        "Content-Type": "application/json",
+        "Authorization": "Bearer " + appid + "-" + apikey,
+        "X-Emp-No": numb,
+        "X-Auth-Value": token,
+    }
+    data = {"chatUuid": "", "chatName": "", "stream": False, "keep": True, "text": querytext, "model": modeltype}
+    async with aiohttp.ClientSession() as session:
+        async with session.post(url, headers=headers, json=data) as response:
+            nowresult = await response.text()
+            return json.loads(nowresult)["bo"]["result"]
+
+
+@register_provider(LLMType.ZTEAI)
+class ZTEaiLLM(BaseLLM):
+    def __init__(self, config: LLMConfig):
+        self.config = config
+
+    async def ask(self, msg: str, timeout=USE_CONFIG_TIMEOUT) -> str:
+        rsp = await ZTEAI(
+            msg, self.config.app_id, self.config.api_key, self.config.domain, self.config.access_key, self.config.model
+        )
+        return rsp
+
+    async def aask(
+        self,
+        msg: str,
+        system_msgs: Optional[list[str]] = None,
+        format_msgs: Optional[list[dict[str, str]]] = None,
+        images: Optional[Union[str, list[str]]] = None,
+        timeout=USE_CONFIG_TIMEOUT,
+    ) -> str:
+        return await self.ask(msg, timeout=self.get_timeout(timeout))
+
+    async def _achat_completion(self, messages: list[dict], timeout=USE_CONFIG_TIMEOUT):
+        pass
+
+    async def acompletion(self, messages: list[dict], timeout=USE_CONFIG_TIMEOUT):
+        """dummy implementation of abstract method in base"""
+        return []
+
+    async def _achat_completion_stream(self, messages: list[dict], timeout: int = USE_CONFIG_TIMEOUT) -> str:
+        pass
+
+    async def acompletion_text(self, messages: list[dict], stream=False, timeout=USE_CONFIG_TIMEOUT) -> str:
+        """dummy implementation of abstract method in base"""
+        return ""
+
+    def get_timeout(self, timeout: int) -> int:
+        return timeout or LLM_API_TIMEOUT