[Update] Default LLM (#3587)

LLM.md

@@ -103,7 +103,7 @@ memory = Memory()
 # With custom configuration
 config = MemoryConfig(
     vector_store={"provider": "qdrant", "config": {"host": "localhost"}},
-    llm={"provider": "openai", "config": {"model": "gpt-4o-mini"}},
+    llm={"provider": "openai", "config": {"model": "gpt-4.1-nano-2025-04-14"}},
     embedder={"provider": "openai", "config": {"model": "text-embedding-3-small"}}
 )
 memory = Memory(config)
@@ -339,7 +339,7 @@ config = MemoryConfig(
     llm={
         "provider": "openai",
         "config": {
-            "model": "gpt-4o-mini",
+            "model": "gpt-4.1-nano-2025-04-14",
             "temperature": 0.1,
             "max_tokens": 1000
         }
@@ -527,7 +527,7 @@ const memory = new Memory({
   },
   llm: {
     provider: 'openai',
-    config: { model: 'gpt-4o-mini' }
+    config: { model: 'gpt-4.1-nano' }
   }
 });
 

README.md

@@ -95,7 +95,7 @@ npm install mem0ai
 
 ### Basic Usage
 
-Mem0 requires an LLM to function, with `gpt-4o-mini` from OpenAI as the default. However, it supports a variety of LLMs; for details, refer to our [Supported LLMs documentation](https://docs.mem0.ai/components/llms/overview).
+Mem0 requires an LLM to function, with `gpt-4.1-nano-2025-04-14 from OpenAI as the default. However, it supports a variety of LLMs; for details, refer to our [Supported LLMs documentation](https://docs.mem0.ai/components/llms/overview).
 
 First step is to instantiate the memory:
 
@@ -114,7 +114,7 @@ def chat_with_memories(message: str, user_id: str = "default_user") -> str:
     # Generate Assistant response
     system_prompt = f"You are a helpful AI. Answer the question based on query and memories.\nUser Memories:\n{memories_str}"
     messages = [{"role": "system", "content": system_prompt}, {"role": "user", "content": message}]
-    response = openai_client.chat.completions.create(model="gpt-4o-mini", messages=messages)
+    response = openai_client.chat.completions.create(model="gpt-4.1-nano-2025-04-14", messages=messages)
     assistant_response = response.choices[0].message.content
 
     # Create new memories from the conversation

docs/components/llms/models/langchain.mdx

@@ -20,7 +20,7 @@ os.environ["OPENAI_API_KEY"] = "your-api-key"
 
 # Initialize a LangChain model directly
 openai_model = ChatOpenAI(
-    model="gpt-4o",
+    model="gpt-4.1-nano-2025-04-14",
     temperature=0.2,
     max_tokens=2000
 )

docs/components/llms/models/litellm.mdx

@@ -12,7 +12,7 @@ config = {
     "llm": {
         "provider": "litellm",
         "config": {
-            "model": "gpt-4o-mini",
+            "model": "gpt-4.1-nano-2025-04-14",
             "temperature": 0.2,
             "max_tokens": 2000,
         }

docs/components/llms/models/openai.mdx

@@ -19,7 +19,7 @@ config = {
     "llm": {
         "provider": "openai",
         "config": {
-            "model": "gpt-4o",
+            "model": "gpt-4.1-nano-2025-04-14",
             "temperature": 0.2,
             "max_tokens": 2000,
         }
@@ -85,7 +85,7 @@ config = {
     "llm": {
         "provider": "openai_structured",
         "config": {
-            "model": "gpt-4o-2024-08-06",
+            "model": "gpt-4.1-nano-2025-04-14",
             "temperature": 0.0,
         }
     }

docs/examples/ai_companion_js.mdx

@@ -45,7 +45,7 @@ ${memoriesStr}`;
   ];
   
   const response = await openaiClient.chat.completions.create({
-    model: "gpt-4o-mini",
+    model: "gpt-4.1-nano-2025-04-14",
     messages: messages
   });
   

docs/examples/collaborative-task-agent.mdx

@@ -51,7 +51,7 @@ class CollaborativeAgent:
             {"role": "user", "content": f"Prompt: {prompt}\nContext:\n{context}"}
         ]
         reply = client.chat.completions.create(
-            model="gpt-4o-mini",
+            model="gpt-4.1-nano-2025-04-14",
             messages=messages
         ).choices[0].message.content.strip()
         self.add_message("assistant", "assistant", reply)

docs/examples/eliza_os.mdx

@@ -44,7 +44,7 @@ MEM0_API_KEY= # Mem0 API Key (get from https://app.mem0.ai/dashboard/api-keys)
 MEM0_USER_ID= # Default: eliza-os-user
 MEM0_PROVIDER= # Default: openai
 MEM0_PROVIDER_API_KEY= # API Key for the provider (OpenAI, Anthropic, etc.)
-SMALL_MEM0_MODEL= # Default: gpt-4o-mini
+SMALL_MEM0_MODEL= # Default: gpt-4.1-nano
 MEDIUM_MEM0_MODEL= # Default: gpt-4o
 LARGE_MEM0_MODEL= # Default: gpt-4o
 ```

docs/examples/llama-index-mem0.mdx

@@ -20,7 +20,7 @@ import os
 from llama_index.llms.openai import OpenAI
 
 os.environ["OPENAI_API_KEY"] = "<your-openai-api-key>"
-llm = OpenAI(model="gpt-4o")
+llm = OpenAI(model="gpt-4.1-nano-2025-04-14")
 ```
 
 Initialize the Mem0 client. You can find your API key [here](https://app.mem0.ai/dashboard/api-keys). Read about Mem0 [Open Source](https://docs.mem0.ai/open-source/overview).

docs/examples/llamaindex-multiagent-learning-system.mdx

@@ -81,7 +81,7 @@ class MultiAgentLearningSystem:
 
     def __init__(self, student_id: str):
         self.student_id = student_id
-        self.llm = OpenAI(model="gpt-4o", temperature=0.2)
+        self.llm = OpenAI(model="gpt-4.1-nano-2025-04-14", temperature=0.2)
 
         # Memory context for this student
         self.memory_context = {"user_id": student_id, "app": "learning_assistant"}

docs/examples/mem0-mastra.mdx

@@ -97,7 +97,7 @@ export const mem0Agent = new Agent({
   instructions: `
     You are a helpful assistant that has the ability to memorize and remember facts using Mem0.
   `,
-  model: openai('gpt-4o'),
+  model: openai('gpt-4.1-nano'),
   tools: { mem0RememberTool, mem0MemorizeTool },
 });
 ```

docs/examples/mem0-openai-voice-demo.mdx

@@ -162,7 +162,7 @@ def create_memory_voice_agent():
             Use the search_memories tool when you need context from past conversations or user asks you to recall something.
             """,
         ),
-        model="gpt-4o",
+        model="gpt-4.1-nano-2025-04-14",
         tools=[save_memories, search_memories],
     )
     
@@ -171,7 +171,7 @@ def create_memory_voice_agent():
 
 This function:
 - Creates an OpenAI Agent with specific instructions
-- Configures it to use gpt-4o (you can use other models)
+- Configures it to use gpt-4.1-nano (you can use other models)
 - Registers the memory-related tools with the agent
 - Uses `prompt_with_handoff_instructions` to include standard voice agent behaviors
 
@@ -369,7 +369,7 @@ def create_memory_voice_agent():
             Use the search_memories tool when you need context from past conversations or user asks you to recall something.
             """,
         ),
-        model="gpt-4o",
+        model="gpt-4.1-nano-2025-04-14",
         tools=[save_memories, search_memories],
     )
     

docs/examples/memory-guided-content-writing.mdx

@@ -103,7 +103,7 @@ Preferences:
     ]
 
     response = openai.chat.completions.create(
-        model="gpt-4o-mini",
+        model="gpt-4.1-nano-2025-04-14",
         messages=messages
     )
     clean_response = response.choices[0].message.content.strip()

docs/examples/openai-inbuilt-tools.mdx

@@ -119,7 +119,7 @@ const carRecommendationTool = zodResponsesFunction({
 
 // Use the tool in your OpenAI request
 const response = await openAIClient.responses.create({
-    model: "gpt-4o",
+    model: "gpt-4.1-nano-2025-04-14",
     tools: [{ type: "web_search_preview" }, carRecommendationTool],
     input: `${getMemoryString(relevantMemories)}\n${userInput}`,
 });
@@ -131,7 +131,7 @@ Combine memory with web search for up-to-date recommendations:
 
 ```javascript
 const response = await openAIClient.responses.create({
-    model: "gpt-4o",
+    model: "gpt-4.1-nano-2025-04-14",
     tools: [{ type: "web_search_preview" }, carRecommendationTool],
     input: `${getMemoryString(relevantMemories)}\n${userInput}`,
 });
@@ -202,7 +202,7 @@ async function main(memory = false) {
   }
 
   const response = await openAIClient.responses.create({
-    model: "gpt-4o",
+    model: "gpt-4.1-nano-2025-04-14",
     tools: [{ type: "web_search_preview" }, tool],
     input: `${getMemoryString(relevantMemories)}\n${input}`,
   });

docs/examples/personal-ai-tutor.mdx

@@ -58,7 +58,7 @@ class PersonalAITutor:
         """
         # Start a streaming response request to the AI
         response = self.client.responses.create(
-            model="gpt-4o",
+            model="gpt-4.1-nano-2025-04-14",
             instructions="You are a personal AI Tutor.",
             input=question,
             stream=True

docs/examples/personal-travel-assistant.mdx

@@ -35,7 +35,7 @@ config = {
     "llm": {
         "provider": "openai",
         "config": {
-            "model": "gpt-4o",
+            "model": "gpt-4.1-nano-2025-04-14",
             "temperature": 0.1,
             "max_tokens": 2000,
         }
@@ -76,7 +76,7 @@ class PersonalTravelAssistant:
 
         # Generate response using Responses API
         response = self.client.responses.create(
-            model="gpt-4o",
+            model="gpt-4.1-nano-2025-04-14",
             input=prompt
         )
 
@@ -140,9 +140,9 @@ class PersonalTravelAssistant:
             prompt = f"User input: {question}\n Previous memories: {previous_memories}"
         self.messages.append({"role": "user", "content": prompt})
 
-        # Generate response using GPT-4o
+        # Generate response using gpt-4.1-nano
         response = self.client.chat.completions.create(
-            model="gpt-4o",
+            model="gpt-4.1-nano-2025-04-14"2025-04-14",
             messages=self.messages
         )
         answer = response.choices[0].message.content

docs/integrations/agentops.mdx

@@ -49,7 +49,7 @@ local_config = {
     "llm": {
         "provider": "openai",
         "config": {
-            "model": "gpt-4o-mini",
+            "model": "gpt-4.1-nano-2025-04-14",
             "temperature": 0.1,
             "max_tokens": 2000,
         },

docs/integrations/agno.mdx

@@ -36,7 +36,7 @@ from agno.tools.mem0 import Mem0Tools
 
 agent = Agent(
     name="Memory Agent",
-    model=OpenAIChat(id="gpt-4o-mini"),
+    model=OpenAIChat(id="gpt-4.1-nano-2025-04-14"),
     tools=[Mem0Tools()],
     description="An assistant that remembers and personalizes using Mem0 memory."
 )

docs/integrations/keywords.mdx

@@ -55,7 +55,7 @@ config = {
     "llm": {
         "provider": "openai",
         "config": {
-            "model": "gpt-4o-mini",
+            "model": "gpt-4.1-nano-2025-04-14",
             "temperature": 0.0,
             "api_key": keywordsai_api_key,
             "openai_base_url": base_url,
@@ -101,7 +101,7 @@ messages = [
 
 # Add memory and generate a response
 response = client.chat.completions.create(
-    model="openai/gpt-4o",
+    model="openai/gpt-4.1-nano",
     messages=messages,
     extra_body={
         "mem0_params": {

docs/integrations/langchain.mdx

@@ -39,7 +39,7 @@ load_dotenv()
 # os.environ["MEM0_API_KEY"] = "your-mem0-api-key"
 
 # Initialize LangChain and Mem0
-llm = ChatOpenAI(model="gpt-4o-mini")
+llm = ChatOpenAI(model="gpt-4.1-nano-2025-04-14")
 mem0 = MemoryClient()
 ```
 

docs/integrations/livekit.mdx

@@ -147,7 +147,7 @@ async def entrypoint(ctx: JobContext):
 
     session = AgentSession(
         stt=deepgram.STT(),
-        llm=openai.LLM(model="gpt-4o-mini"),
+        llm=openai.LLM(model="gpt-4.1-nano-2025-04-14"),
         tts=openai.TTS(voice="ash",),
         turn_detection=EnglishModel(),
         vad=silero.VAD.load(),

docs/integrations/llama-index.mdx

@@ -83,7 +83,7 @@ config = {
     "llm": {
         "provider": "openai",
         "config": {
-            "model": "gpt-4o",
+            "model": "gpt-4.1-nano-2025-04-14",
             "temperature": 0.2,
             "max_tokens": 2000,
         },
@@ -116,7 +116,7 @@ from dotenv import load_dotenv
 load_dotenv()
 
 # os.environ["OPENAI_API_KEY"] = "<your-openai-api-key>"
-llm = OpenAI(model="gpt-4o-mini")
+llm = OpenAI(model="gpt-4.1-nano-2025-04-14")
 ```
 
 ### SimpleChatEngine

docs/integrations/mastra.mdx

@@ -106,7 +106,7 @@ const mem0Agent = new Agent({
     Use the Mem0-memorize tool to save important information that might be useful later.
     Use the Mem0-remember tool to recall previously saved information when answering questions.
   `,
-  model: openai('gpt-4o'),
+  model: openai('gpt-4.1-nano'),
   tools: { mem0RememberTool, mem0MemorizeTool },
 });
 ```

docs/integrations/openai-agents-sdk.mdx

@@ -63,7 +63,7 @@ agent = Agent(
     Use the save_memory tool to store important information about the user.
     Always personalize your responses based on available memory.""",
     tools=[search_memory, save_memory],
-    model="gpt-4o"
+    model="gpt-4.1-nano-2025-04-14"
 )
 
 def chat_with_agent(user_input: str, user_id: str) -> str:
@@ -114,7 +114,7 @@ travel_agent = Agent(
     understand the user's travel preferences and history before making recommendations.
     After providing your response, use store_conversation to save important details.""",
     tools=[search_memory, save_memory],
-    model="gpt-4o"
+    model="gpt-4.1-nano-2025-04-14"
 )
 
 health_agent = Agent(
@@ -123,7 +123,7 @@ health_agent = Agent(
     understand the user's health goals and dietary preferences.
     After providing advice, use store_conversation to save relevant information.""",
     tools=[search_memory, save_memory],
-    model="gpt-4o"
+    model="gpt-4.1-nano-2025-04-14"
 )
 
 # Triage agent with handoffs
@@ -134,7 +134,7 @@ triage_agent = Agent(
     For health-related questions (fitness, diet, wellness, exercise), hand off to the Health Advisor.
     For general questions, handle them directly using available tools.""",
     handoffs=[travel_agent, health_agent],
-    model="gpt-4o"
+    model="gpt-4.1-nano-2025-04-14"
 )
 
 def chat_with_handoffs(user_input: str, user_id: str) -> str:

docs/open-source/features/async-memory.mdx

@@ -202,7 +202,7 @@ async def chat_with_memories(message: str, user_id: str = "default_user") -> str
         # Generate assistant response
         system_prompt = f"You are a helpful AI. Answer the question based on query and memories.\nUser Memories:\n{memories_str}"
         messages = [{"role": "system", "content": system_prompt}, {"role": "user", "content": message}]
-        response = await async_openai_client.chat.completions.create(model="gpt-4o-mini", messages=messages)
+        response = await async_openai_client.chat.completions.create(model="gpt-4.1-nano-2025-04-14", messages=messages)
         assistant_response = response.choices[0].message.content
 
         # Create new memories from the conversation
@@ -249,7 +249,7 @@ async def handle_initialization_errors():
         # Initialize with custom config
         config = MemoryConfig(
             vector_store={"provider": "chroma", "config": {"path": "./chroma_db"}},
-            llm={"provider": "openai", "config": {"model": "gpt-4o-mini"}}
+            llm={"provider": "openai", "config": {"model": "gpt-4.1-nano-2025-04-14"}}
         )
         memory = AsyncMemory(config=config)
         print("AsyncMemory initialized successfully")

docs/open-source/features/custom-fact-extraction-prompt.mdx

@@ -76,7 +76,7 @@ config = {
     "llm": {
         "provider": "openai",
         "config": {
-            "model": "gpt-4o",
+            "model": "gpt-4.1-nano-2025-04-14",
             "temperature": 0.2,
             "max_tokens": 2000,
         }

docs/open-source/features/openai_compatibility.mdx

@@ -27,7 +27,7 @@ messages = [
 user_id = "alice"
 chat_completion = client.chat.completions.create(
     messages=messages,
-    model="gpt-4o-mini",
+    model="gpt-4.1-nano-2025-04-14",
     user_id=user_id
 )
 # Memory saved after this will look like: "Loves Indian food. Allergic to cheese and cannot eat pizza."
@@ -42,7 +42,7 @@ messages = [
 
 chat_completion = client.chat.completions.create(
     messages=messages,
-    model="gpt-4o-mini",
+    model="gpt-4.1-nano-2025-04-14",
     user_id=user_id
 )
 print(chat_completion.choices[0].message.content)
@@ -73,7 +73,7 @@ chat_completion = client.chat.completions.create(
             "content": "What's the capital of France?",
         }
     ],
-    model="gpt-4o",
+    model="gpt-4.1-nano-2025-04-14",
 )
 ```
 

docs/open-source/graph_memory/overview.mdx

@@ -54,7 +54,7 @@ You can also customize the LLM for Graph Memory from the [Supported LLM list](ht
 
 1. **Main Configuration**: If `llm` is set in the main config, it will be used for all graph operations.
 2. **Graph Store Configuration**: If `llm` is set in the graph_store config, it will override the main config `llm` and be used specifically for graph operations.
-3. **Default Configuration**: If no custom LLM is set, the default LLM (`gpt-4o-2024-08-06`) will be used for all graph operations.
+3. **Default Configuration**: If no custom LLM is set, the default LLM (`gpt-4.1-nano-2025-04-14) will be used for all graph operations.
 
 Here's how you can do it:
 
@@ -100,7 +100,7 @@ config = {
     "llm": {
         "provider": "openai",
         "config": {
-            "model": "gpt-4o",
+            "model": "gpt-4.1-nano-2025-04-14",
             "temperature": 0.2,
             "max_tokens": 2000,
         }
@@ -115,7 +115,7 @@ config = {
         "llm" : {
             "provider": "openai",
             "config": {
-                "model": "gpt-4o-mini",
+                "model": "gpt-4.1-nano-2025-04-14",
                 "temperature": 0.0,
             }
         }
@@ -130,7 +130,7 @@ const config = {
     llm: {
         provider: "openai",
         config: {
-            model: "gpt-4o",
+            model: "gpt-4.1-nano-2025-04-14",
             temperature: 0.2,
             max_tokens: 2000,
         }
@@ -146,7 +146,7 @@ const config = {
         llm: {
             provider: "openai",
             config: {
-                model: "gpt-4o-mini",
+                model: "gpt-4.1-nano-2025-04-14",
                 temperature: 0.0,
             }
         }
@@ -177,7 +177,7 @@ You can also customize the LLM for Graph Memory from the [Supported LLM list](ht
 
 1. **Main Configuration**: If `llm` is set in the main config, it will be used for all graph operations.
 2. **Graph Store Configuration**: If `llm` is set in the graph_store config, it will override the main config `llm` and be used specifically for graph operations.
-3. **Default Configuration**: If no custom LLM is set, the default LLM (`gpt-4o-2024-08-06`) will be used for all graph operations.
+3. **Default Configuration**: If no custom LLM is set, the default LLM (`gpt-4.1-nano-2025-04-142025-04-14) will be used for all graph operations.
 
 Here's how you can do it:
 
@@ -241,7 +241,7 @@ User can also customize the LLM for Graph Memory from the [Supported LLM list](h
 
 1. **Main Configuration**: If `llm` is set in the main config, it will be used for all graph operations.
 2. **Graph Store Configuration**: If `llm` is set in the graph_store config, it will override the main config `llm` and be used specifically for graph operations.
-3. **Default Configuration**: If no custom LLM is set, the default LLM (`gpt-4o-2024-08-06`) will be used for all graph operations.
+3. **Default Configuration**: If no custom LLM is set, the default LLM (`gpt-4.1-nano-2025-04-14) will be used for all graph operations.
 
 Here's how you can do it:
 
@@ -290,7 +290,7 @@ User can also customize the LLM for Graph Memory from the [Supported LLM list](h
 
 1. **Main Configuration**: If `llm` is set in the main config, it will be used for all graph operations.
 2. **Graph Store Configuration**: If `llm` is set in the graph_store config, it will override the main config `llm` and be used specifically for graph operations.
-3. **Default Configuration**: If no custom LLM is set, the default LLM (`gpt-4o-2024-08-06`) will be used for all graph operations.
+3. **Default Configuration**: If no custom LLM is set, the default LLM (`gpt-4.1-nano-2025-04-14) will be used for all graph operations.
 
 Here's how you can do it:
 

docs/open-source/python-quickstart.mdx

@@ -504,7 +504,7 @@ chat_completion = client.chat.completions.create(
             "content": "What's the capital of France?",
         }
     ],
-    model="gpt-4o",
+    model="gpt-4.1-nano-2025-04-14",
 )
 ```
 

docs/v0x/components/llms/models/langchain.mdx

@@ -20,7 +20,7 @@ os.environ["OPENAI_API_KEY"] = "your-api-key"
 
 # Initialize a LangChain model directly
 openai_model = ChatOpenAI(
-    model="gpt-4o",
+    model="gpt-4.1-nano-2025-04-14",
     temperature=0.2,
     max_tokens=2000
 )

docs/v0x/components/llms/models/litellm.mdx

@@ -12,7 +12,7 @@ config = {
     "llm": {
         "provider": "litellm",
         "config": {
-            "model": "gpt-4o-mini",
+            "model": "gpt-4.1-nano-2025-04-14",
             "temperature": 0.2,
             "max_tokens": 2000,
         }

docs/v0x/components/llms/models/openai.mdx

@@ -19,7 +19,7 @@ config = {
     "llm": {
         "provider": "openai",
         "config": {
-            "model": "gpt-4o",
+            "model": "gpt-4.1-nano-2025-04-14",
             "temperature": 0.2,
             "max_tokens": 2000,
         }
@@ -85,7 +85,7 @@ config = {
     "llm": {
         "provider": "openai_structured",
         "config": {
-            "model": "gpt-4o-2024-08-06",
+            "model": "gpt-4.1-nano-2025-04-14",
             "temperature": 0.0,
         }
     }

docs/v0x/examples/ai_companion_js.mdx

@@ -45,7 +45,7 @@ ${memoriesStr}`;
   ];
   
   const response = await openaiClient.chat.completions.create({
-    model: "gpt-4o-mini",
+    model: "gpt-4.1-nano-2025-04-14",
     messages: messages
   });
   

docs/v0x/examples/collaborative-task-agent.mdx

@@ -51,7 +51,7 @@ class CollaborativeAgent:
             {"role": "user", "content": f"Prompt: {prompt}\nContext:\n{context}"}
         ]
         reply = client.chat.completions.create(
-            model="gpt-4o-mini",
+            model="gpt-4.1-nano-2025-04-14",
             messages=messages
         ).choices[0].message.content.strip()
         self.add_message("assistant", "assistant", reply)

docs/v0x/examples/eliza_os.mdx

@@ -43,7 +43,7 @@ MEM0_API_KEY= # Mem0 API Key ( Get from https://app.mem0.ai/dashboard/api-keys )
 MEM0_USER_ID= # Default: eliza-os-user
 MEM0_PROVIDER= # Default: openai
 MEM0_PROVIDER_API_KEY= # API Key for the provider (openai, anthropic, etc.)
-SMALL_MEM0_MODEL= # Default: gpt-4o-mini
+SMALL_MEM0_MODEL= # Default: gpt-4.1-nano
 MEDIUM_MEM0_MODEL= # Default: gpt-4o
 LARGE_MEM0_MODEL= # Default: gpt-4o
 ```

docs/v0x/examples/llama-index-mem0.mdx

@@ -18,7 +18,7 @@ import os
 from llama_index.llms.openai import OpenAI
 
 os.environ["OPENAI_API_KEY"] = "<your-openai-api-key>"
-llm = OpenAI(model="gpt-4o")
+llm = OpenAI(model="gpt-4.1-nano-2025-04-14")
 ```
 
 Initialize the Mem0 client. You can find your API key [here](https://app.mem0.ai/dashboard/api-keys). Read about Mem0 [Open Source](https://docs.mem0.ai/open-source/overview).

docs/v0x/examples/llamaindex-multiagent-learning-system.mdx

@@ -81,7 +81,7 @@ class MultiAgentLearningSystem:
 
     def __init__(self, student_id: str):
         self.student_id = student_id
-        self.llm = OpenAI(model="gpt-4o", temperature=0.2)
+        self.llm = OpenAI(model="gpt-4.1-nano-2025-04-14", temperature=0.2)
 
         # Memory context for this student
         self.memory_context = {"user_id": student_id, "app": "learning_assistant"}

docs/v0x/examples/mem0-mastra.mdx

@@ -98,7 +98,7 @@ export const mem0Agent = new Agent({
   instructions: `
     You are a helpful assistant that has the ability to memorize and remember facts using Mem0.
   `,
-  model: openai('gpt-4o'),
+  model: openai('gpt-4.1-nano'),
   tools: { mem0RememberTool, mem0MemorizeTool },
 });
 ```

docs/v0x/examples/mem0-openai-voice-demo.mdx

@@ -162,7 +162,7 @@ def create_memory_voice_agent():
             Use the search_memories tool when you need context from past conversations or user asks you to recall something.
             """,
         ),
-        model="gpt-4o",
+        model="gpt-4.1-nano-2025-04-14",
         tools=[save_memories, search_memories],
     )
     
@@ -171,7 +171,7 @@ def create_memory_voice_agent():
 
 This function:
 - Creates an OpenAI Agent with specific instructions
-- Configures it to use gpt-4o (you can use other models)
+- Configures it to use gpt-4.1-nano (you can use other models)
 - Registers the memory-related tools with the agent
 - Uses `prompt_with_handoff_instructions` to include standard voice agent behaviors
 
@@ -369,7 +369,7 @@ def create_memory_voice_agent():
             Use the search_memories tool when you need context from past conversations or user asks you to recall something.
             """,
         ),
-        model="gpt-4o",
+        model="gpt-4.1-nano-2025-04-14",
         tools=[save_memories, search_memories],
     )
     

docs/v0x/examples/memory-guided-content-writing.mdx

@@ -103,7 +103,7 @@ Preferences:
     ]
 
     response = openai.chat.completions.create(
-        model="gpt-4o-mini",
+        model="gpt-4.1-nano-2025-04-14",
         messages=messages
     )
     clean_response = response.choices[0].message.content.strip()

docs/v0x/examples/openai-inbuilt-tools.mdx

@@ -119,7 +119,7 @@ const carRecommendationTool = zodResponsesFunction({
 
 // Use the tool in your OpenAI request
 const response = await openAIClient.responses.create({
-    model: "gpt-4o",
+    model: "gpt-4.1-nano-2025-04-14",
     tools: [{ type: "web_search_preview" }, carRecommendationTool],
     input: `${getMemoryString(relevantMemories)}\n${userInput}`,
 });
@@ -131,7 +131,7 @@ Combine memory with web search for up-to-date recommendations:
 
 ```javascript
 const response = await openAIClient.responses.create({
-    model: "gpt-4o",
+    model: "gpt-4.1-nano-2025-04-14",
     tools: [{ type: "web_search_preview" }, carRecommendationTool],
     input: `${getMemoryString(relevantMemories)}\n${userInput}`,
 });
@@ -202,7 +202,7 @@ async function main(memory = false) {
   }
 
   const response = await openAIClient.responses.create({
-    model: "gpt-4o",
+    model: "gpt-4.1-nano-2025-04-14",
     tools: [{ type: "web_search_preview" }, tool],
     input: `${getMemoryString(relevantMemories)}\n${input}`,
   });

docs/v0x/examples/personal-ai-tutor.mdx

@@ -57,7 +57,7 @@ class PersonalAITutor:
         """
         # Start a streaming response request to the AI
         response = self.client.responses.create(
-            model="gpt-4o",
+            model="gpt-4.1-nano-2025-04-14",
             instructions="You are a personal AI Tutor.",
             input=question,
             stream=True

docs/v0x/examples/personal-travel-assistant.mdx

@@ -35,7 +35,7 @@ config = {
     "llm": {
         "provider": "openai",
         "config": {
-            "model": "gpt-4o",
+            "model": "gpt-4.1-nano-2025-04-14",
             "temperature": 0.1,
             "max_tokens": 2000,
         }
@@ -76,7 +76,7 @@ class PersonalTravelAssistant:
 
         # Generate response using Responses API
         response = self.client.responses.create(
-            model="gpt-4o",
+            model="gpt-4.1-nano-2025-04-14",
             input=prompt
         )
 
@@ -140,9 +140,9 @@ class PersonalTravelAssistant:
             prompt = f"User input: {question}\n Previous memories: {previous_memories}"
         self.messages.append({"role": "user", "content": prompt})
 
-        # Generate response using GPT-4o
+        # Generate response using gpt-4.1-nano
         response = self.client.chat.completions.create(
-            model="gpt-4o",
+            model="gpt-4.1-nano-2025-04-14"2025-04-14",
             messages=self.messages
         )
         answer = response.choices[0].message.content

docs/v0x/integrations/agentops.mdx

@@ -49,7 +49,7 @@ local_config = {
     "llm": {
         "provider": "openai",
         "config": {
-            "model": "gpt-4o-mini",
+            "model": "gpt-4.1-nano-2025-04-14",
             "temperature": 0.1,
             "max_tokens": 2000,
         },

docs/v0x/integrations/agno.mdx

@@ -36,7 +36,7 @@ from agno.tools.mem0 import Mem0Tools
 
 agent = Agent(
     name="Memory Agent",
-    model=OpenAIChat(id="gpt-4o-mini"),
+    model=OpenAIChat(id="gpt-4.1-nano-2025-04-14"2025-04-14"),
     tools=[Mem0Tools()],
     description="An assistant that remembers and personalizes using Mem0 memory."
 )

docs/v0x/integrations/keywords.mdx

@@ -55,7 +55,7 @@ config = {
     "llm": {
         "provider": "openai",
         "config": {
-            "model": "gpt-4o-mini",
+            "model": "gpt-4.1-nano-2025-04-14",
             "temperature": 0.0,
             "api_key": keywordsai_api_key,
             "openai_base_url": base_url,
@@ -101,7 +101,7 @@ messages = [
 
 # Add memory and generate a response
 response = client.chat.completions.create(
-    model="openai/gpt-4o",
+    model="openai/gpt-4.1-nano",
     messages=messages,
     extra_body={
         "mem0_params": {

docs/v0x/integrations/langchain.mdx

@@ -39,7 +39,7 @@ load_dotenv()
 # os.environ["MEM0_API_KEY"] = "your-mem0-api-key"
 
 # Initialize LangChain and Mem0
-llm = ChatOpenAI(model="gpt-4o-mini")
+llm = ChatOpenAI(model="gpt-4.1-nano-2025-04-14")
 mem0 = MemoryClient()
 ```
 

docs/v0x/integrations/livekit.mdx

@@ -147,7 +147,7 @@ async def entrypoint(ctx: JobContext):
 
     session = AgentSession(
         stt=deepgram.STT(),
-        llm=openai.LLM(model="gpt-4o-mini"),
+        llm=openai.LLM(model="gpt-4.1-nano-2025-04-14"2025-04-14"),
         tts=openai.TTS(voice="ash",),
         turn_detection=EnglishModel(),
         vad=silero.VAD.load(),

docs/v0x/integrations/llama-index.mdx

@@ -83,7 +83,7 @@ config = {
     "llm": {
         "provider": "openai",
         "config": {
-            "model": "gpt-4o",
+            "model": "gpt-4.1-nano-2025-04-14",
             "temperature": 0.2,
             "max_tokens": 2000,
         },
@@ -116,7 +116,7 @@ from dotenv import load_dotenv
 load_dotenv()
 
 # os.environ["OPENAI_API_KEY"] = "<your-openai-api-key>"
-llm = OpenAI(model="gpt-4o-mini")
+llm = OpenAI(model="gpt-4.1-nano-2025-04-14"2025-04-14")
 ```
 
 ### SimpleChatEngine

docs/v0x/integrations/mastra.mdx

@@ -106,7 +106,7 @@ const mem0Agent = new Agent({
     Use the Mem0-memorize tool to save important information that might be useful later.
     Use the Mem0-remember tool to recall previously saved information when answering questions.
   `,
-  model: openai('gpt-4o'),
+  model: openai('gpt-4.1-nano'),
   tools: { mem0RememberTool, mem0MemorizeTool },
 });
 ```

docs/v0x/integrations/openai-agents-sdk.mdx

@@ -63,7 +63,7 @@ agent = Agent(
     Use the save_memory tool to store important information about the user.
     Always personalize your responses based on available memory.""",
     tools=[search_memory, save_memory],
-    model="gpt-4o"
+    model="gpt-4.1-nano-2025-04-14"
 )
 
 def chat_with_agent(user_input: str, user_id: str) -> str:
@@ -114,7 +114,7 @@ travel_agent = Agent(
     understand the user's travel preferences and history before making recommendations.
     After providing your response, use store_conversation to save important details.""",
     tools=[search_memory, save_memory],
-    model="gpt-4o"
+    model="gpt-4.1-nano-2025-04-14"
 )
 
 health_agent = Agent(
@@ -123,7 +123,7 @@ health_agent = Agent(
     understand the user's health goals and dietary preferences.
     After providing advice, use store_conversation to save relevant information.""",
     tools=[search_memory, save_memory],
-    model="gpt-4o"
+    model="gpt-4.1-nano-2025-04-14"
 )
 
 # Triage agent with handoffs
@@ -134,7 +134,7 @@ triage_agent = Agent(
     For health-related questions (fitness, diet, wellness, exercise), hand off to Health Advisor.
     For general questions, you can handle them directly using available tools.""",
     handoffs=[travel_agent, health_agent],
-    model="gpt-4o"
+    model="gpt-4.1-nano-2025-04-14"
 )
 
 def chat_with_handoffs(user_input: str, user_id: str) -> str:

docs/v0x/open-source/python-quickstart.mdx

@@ -504,7 +504,7 @@ chat_completion = client.chat.completions.create(
             "content": "What's the capital of France?",
         }
     ],
-    model="gpt-4o",
+    model="gpt-4.1-nano-2025-04-14",
 )
 ```
 

examples/graph-db-demo/kuzu-example.ipynb

@@ -225,7 +225,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 24,
+      "execution_count": null,
       "metadata": {},
       "outputs": [],
       "source": [
@@ -239,7 +239,7 @@
         "    # Generate Assistant response\n",
         "    system_prompt = f\"You are a helpful AI. Answer the question based on query and memories.\\nUser Memories:\\n{memories_str}\"\n",
         "    messages = [{\"role\": \"system\", \"content\": system_prompt}, {\"role\": \"user\", \"content\": message}]\n",
-        "    response = openai_client.chat.completions.create(model=\"gpt-4o-mini\", messages=messages)\n",
+        "    response = openai_client.chat.completions.create(model=\"gpt-4.1-nano-2025-04-14\", messages=messages)\n",
         "    assistant_response = response.choices[0].message.content\n",
         "\n",
         "    # Create new memories from the conversation\n",

examples/misc/diet_assistant_voice_cartesia.py

@@ -37,7 +37,7 @@ food_agent = Agent(
     name="Personal Food Assistant",
     description="Provides personalized food recommendations with memory and generates voice responses using Cartesia TTS tools.",
     instructions=agent_instructions,
-    model=OpenAIChat(id="gpt-4o"),
+    model=OpenAIChat(id="gpt-4.1-nano-2025-04-14"),
     tools=[CartesiaTools(voice_localize_enabled=True)],
     show_tool_calls=True,
 )

examples/misc/fitness_checker.py

@@ -1,6 +1,6 @@
 """
 Simple Fitness Memory Tracker that tracks your fitness progress and knows your health priorities.
-Uses Mem0 for memory and GPT-4o for image understanding.
+Uses Mem0 for memory and gpt-4.1-nano for image understanding.
 
 In order to run this file, you need to set up your Mem0 API at Mem0 platform and also need an OpenAI API key.
 export OPENAI_API_KEY="your_openai_api_key"
@@ -18,7 +18,7 @@ USER_ID = "Anish"
 
 agent = Agent(
     name="Fitness Agent",
-    model=OpenAIChat(id="gpt-4o"),
+    model=OpenAIChat(id="gpt-4.1-nano-2025-04-14"),
     description="You are a helpful fitness assistant who remembers past logs and gives personalized suggestions for Anish's training and diet.",
     markdown=True,
 )

examples/misc/multillm_memory.py

@@ -34,7 +34,7 @@ memory = MemoryClient()
 # Research team models with specialized roles
 RESEARCH_TEAM = {
     "tech_analyst": {
-        "model": "gpt-4o",
+        "model": "gpt-4.1-nano-2025-04-14",
         "role": "Technical Analyst - Code review, architecture, and technical decisions",
     },
     "writer": {
@@ -42,7 +42,7 @@ RESEARCH_TEAM = {
         "role": "Documentation Writer - Clear explanations and user guides",
     },
     "data_analyst": {
-        "model": "gpt-4o-mini",
+        "model": "gpt-4.1-nano-2025-04-14",
         "role": "Data Analyst - Insights, trends, and data-driven recommendations",
     },
 }

examples/misc/personal_assistant_agno.py

@@ -21,7 +21,7 @@ client = MemoryClient()
 # Define the agent
 agent = Agent(
     name="Personal Agent",
-    model=OpenAIChat(id="gpt-4o"),
+    model=OpenAIChat(id="gpt-4.1-nano-2025-04-14"),
     description="You are a helpful personal agent that helps me with day to day activities."
     "You can process both text and images.",
     markdown=True,

examples/misc/personalized_search.py

@@ -35,7 +35,7 @@ BE IT TIME, LOCATION, USER'S PERSONAL LIFE, CHOICES, USER'S PREFERENCES, we need
 '''
 )
 
-llm = ChatOpenAI(model="gpt-4o-mini", temperature=0.2)
+llm = ChatOpenAI(model="gpt-4.1-nano-2025-04-14", temperature=0.2)
 
 
 def setup_user_history(user_id):

examples/misc/test.py

@@ -35,7 +35,7 @@ travel_agent = Agent(
     understand the user's travel preferences and history before making recommendations.
     After providing your response, use store_conversation to save important details.""",
     tools=[search_memory, save_memory],
-    model="gpt-4o",
+    model="gpt-4.1-nano-2025-04-14",
 )
 
 health_agent = Agent(
@@ -44,7 +44,7 @@ health_agent = Agent(
     understand the user's health goals and dietary preferences.
     After providing advice, use store_conversation to save relevant information.""",
     tools=[search_memory, save_memory],
-    model="gpt-4o",
+    model="gpt-4.1-nano-2025-04-14",
 )
 
 # Triage agent with handoffs
@@ -55,7 +55,7 @@ triage_agent = Agent(
     For health-related questions (fitness, diet, wellness, exercise), hand off to Health Advisor.
     For general questions, you can handle them directly using available tools.""",
     handoffs=[travel_agent, health_agent],
-    model="gpt-4o",
+    model="gpt-4.1-nano-2025-04-14",
 )
 
 

examples/multiagents/llamaindex_learning_system.py

@@ -42,7 +42,7 @@ class MultiAgentLearningSystem:
 
     def __init__(self, student_id: str):
         self.student_id = student_id
-        self.llm = OpenAI(model="gpt-4o", temperature=0.2)
+        self.llm = OpenAI(model="gpt-4.1-nano-2025-04-14", temperature=0.2)
 
         # Memory context for this student
         self.memory_context = {"user_id": student_id, "app": "learning_assistant"}

examples/multimodal-demo/src/hooks/useChat.ts

@@ -172,7 +172,7 @@ export const useChat = ({ user, mem0ApiKey, openaiApiKey }: UseChatProps): UseCh
       }
 
       const completion = await openai.chat.completions.create({
-        model: "gpt-4o-mini",
+        model: "gpt-4.1-nano-2025-04-14",
         // eslint-disable-next-line @typescript-eslint/ban-ts-comment
         // @ts-expect-error
         messages: messagesForLLM.map(msg => ({

examples/multimodal-demo/useChat.ts

@@ -172,7 +172,7 @@ export const useChat = ({ user, mem0ApiKey, openaiApiKey }: UseChatProps): UseCh
       }
 
       const completion = await openai.chat.completions.create({
-        model: "gpt-4o-mini",
+        model: "gpt-4.1-nano-2025-04-14",
         // eslint-disable-next-line @typescript-eslint/ban-ts-comment
         // @ts-expect-error
         messages: messagesForLLM.map(msg => ({

mem0-ts/src/oss/src/llms/openai.ts

@@ -11,7 +11,7 @@ export class OpenAILLM implements LLM {
       apiKey: config.apiKey,
       baseURL: config.baseURL,
     });
-    this.model = config.model || "gpt-4o-mini";
+    this.model = config.model || "gpt-4.1-nano-2025-04-14";
   }
 
   async generateResponse(

mem0/configs/llms/base.py

@@ -29,7 +29,7 @@ class BaseLlmConfig(ABC):
         Initialize a base configuration class instance for the LLM.
 
         Args:
-            model: The model identifier to use (e.g., "gpt-4o-mini", "claude-3-5-sonnet-20240620")
+            model: The model identifier to use (e.g., "gpt-4.1-nano-2025-04-14", "claude-3-5-sonnet-20240620")
                 Defaults to None (will be set by provider-specific configs)
             temperature: Controls the randomness of the model's output.
                 Higher values (closer to 1) make output more random, lower values make it more deterministic.

mem0/llms/azure_openai.py

@@ -38,7 +38,7 @@ class AzureOpenAILLM(LLMBase):
 
         # Model name should match the custom deployment name chosen for it.
         if not self.config.model:
-            self.config.model = "gpt-4o"
+            self.config.model = "gpt-4.1-nano-2025-04-14"
 
         api_key = self.config.azure_kwargs.api_key or os.getenv("LLM_AZURE_OPENAI_API_KEY")
         azure_deployment = self.config.azure_kwargs.azure_deployment or os.getenv("LLM_AZURE_DEPLOYMENT")

mem0/llms/azure_openai_structured.py

@@ -16,7 +16,7 @@ class AzureOpenAIStructuredLLM(LLMBase):
 
         # Model name should match the custom deployment name chosen for it.
         if not self.config.model:
-            self.config.model = "gpt-4o-2024-08-06"
+            self.config.model = "gpt-4.1-nano-2025-04-14"
 
         api_key = self.config.azure_kwargs.api_key or os.getenv("LLM_AZURE_OPENAI_API_KEY")
         azure_deployment = self.config.azure_kwargs.azure_deployment or os.getenv("LLM_AZURE_DEPLOYMENT")

mem0/llms/litellm.py

@@ -16,7 +16,7 @@ class LiteLLM(LLMBase):
         super().__init__(config)
 
         if not self.config.model:
-            self.config.model = "gpt-4o-mini"
+            self.config.model = "gpt-4.1-nano-2025-04-14"
 
     def _parse_response(self, response, tools):
         """

mem0/llms/openai.py

@@ -35,7 +35,7 @@ class OpenAILLM(LLMBase):
         super().__init__(config)
 
         if not self.config.model:
-            self.config.model = "gpt-4o-mini"
+            self.config.model = "gpt-4.1-nano-2025-04-14"
 
         if os.environ.get("OPENROUTER_API_KEY"):  # Use OpenRouter
             self.client = OpenAI(

server/main.py

@@ -50,7 +50,7 @@ DEFAULT_CONFIG = {
         "provider": "neo4j",
         "config": {"url": NEO4J_URI, "username": NEO4J_USERNAME, "password": NEO4J_PASSWORD},
     },
-    "llm": {"provider": "openai", "config": {"api_key": OPENAI_API_KEY, "temperature": 0.2, "model": "gpt-4o"}},
+    "llm": {"provider": "openai", "config": {"api_key": OPENAI_API_KEY, "temperature": 0.2, "model": "gpt-4.1-nano-2025-04-14"}},
     "embedder": {"provider": "openai", "config": {"api_key": OPENAI_API_KEY, "model": "text-embedding-3-small"}},
     "history_db_path": HISTORY_DB_PATH,
 }

tests/llms/test_azure_openai.py

@@ -5,7 +5,7 @@ import pytest
 from mem0.configs.llms.azure import AzureOpenAIConfig
 from mem0.llms.azure_openai import AzureOpenAILLM
 
-MODEL = "gpt-4o"  # or your custom deployment name
+MODEL = "gpt-4.1-nano-2025-04-14"  # or your custom deployment name
 TEMPERATURE = 0.7
 MAX_TOKENS = 100
 TOP_P = 1.0
@@ -191,8 +191,8 @@ def test_init_with_env_vars(monkeypatch):
             http_client=None,
             default_headers=None,
         )
-        # Should default to "gpt-4o" if model is None
+        # Should default to "gpt-4.1-nano-2025-04-14" if model is None
-        assert llm.config.model == "gpt-4o"
+        assert llm.config.model == "gpt-4.1-nano-2025-04-14"
 
 
 def test_init_with_default_azure_credential(monkeypatch):

tests/llms/test_azure_openai_structured.py

@@ -56,7 +56,7 @@ def test_init_with_default_credential(mock_credential, mock_token_provider, mock
     mock_token_provider.return_value = "token-provider"
     llm = AzureOpenAIStructuredLLM(config)
     # Should set default model if not provided
-    assert llm.config.model == "gpt-4o-2024-08-06"
+    assert llm.config.model == "gpt-4.1-nano-2025-04-14"
     mock_credential.assert_called_once()
     mock_token_provider.assert_called_once_with(mock_credential.return_value, SCOPE)
     mock_azure_openai.assert_called_once()
@@ -91,7 +91,7 @@ def test_init_with_placeholder_api_key_uses_default_credential(
         config = DummyConfig(model=None, azure_kwargs=DummyAzureKwargs(api_key="your-api-key"))
         mock_token_provider.return_value = "token-provider"
         llm = AzureOpenAIStructuredLLM(config)
-        assert llm.config.model == "gpt-4o-2024-08-06"
+        assert llm.config.model == "gpt-4.1-nano-2025-04-14"
         mock_credential.assert_called_once()
         mock_token_provider.assert_called_once_with(mock_credential.return_value, SCOPE)
         mock_azure_openai.assert_called_once()

tests/llms/test_litellm.py

@@ -24,7 +24,7 @@ def test_generate_response_with_unsupported_model(mock_litellm):
 
 
 def test_generate_response_without_tools(mock_litellm):
-    config = BaseLlmConfig(model="gpt-4o", temperature=0.7, max_tokens=100, top_p=1)
+    config = BaseLlmConfig(model="gpt-4.1-nano-2025-04-14", temperature=0.7, max_tokens=100, top_p=1)
     llm = litellm.LiteLLM(config)
     messages = [
         {"role": "system", "content": "You are a helpful assistant."},
@@ -39,13 +39,13 @@ def test_generate_response_without_tools(mock_litellm):
     response = llm.generate_response(messages)
 
     mock_litellm.completion.assert_called_once_with(
-        model="gpt-4o", messages=messages, temperature=0.7, max_tokens=100, top_p=1.0
+        model="gpt-4.1-nano-2025-04-14", messages=messages, temperature=0.7, max_tokens=100, top_p=1.0
     )
     assert response == "I'm doing well, thank you for asking!"
 
 
 def test_generate_response_with_tools(mock_litellm):
-    config = BaseLlmConfig(model="gpt-4o", temperature=0.7, max_tokens=100, top_p=1)
+    config = BaseLlmConfig(model="gpt-4.1-nano-2025-04-14", temperature=0.7, max_tokens=100, top_p=1)
     llm = litellm.LiteLLM(config)
     messages = [
         {"role": "system", "content": "You are a helpful assistant."},
@@ -82,7 +82,7 @@ def test_generate_response_with_tools(mock_litellm):
     response = llm.generate_response(messages, tools=tools)
 
     mock_litellm.completion.assert_called_once_with(
-        model="gpt-4o", messages=messages, temperature=0.7, max_tokens=100, top_p=1, tools=tools, tool_choice="auto"
+        model="gpt-4.1-nano-2025-04-14", messages=messages, temperature=0.7, max_tokens=100, top_p=1, tools=tools, tool_choice="auto"
     )
 
     assert response["content"] == "I've added the memory for you."

tests/llms/test_openai.py

@@ -17,7 +17,7 @@ def mock_openai_client():
 
 def test_openai_llm_base_url():
     # case1: default config: with openai official base url
-    config = OpenAIConfig(model="gpt-4o", temperature=0.7, max_tokens=100, top_p=1.0, api_key="api_key")
+    config = OpenAIConfig(model="gpt-4.1-nano-2025-04-14", temperature=0.7, max_tokens=100, top_p=1.0, api_key="api_key")
     llm = OpenAILLM(config)
     # Note: openai client will parse the raw base_url into a URL object, which will have a trailing slash
     assert str(llm.client.base_url) == "https://api.openai.com/v1/"
@@ -25,7 +25,7 @@ def test_openai_llm_base_url():
     # case2: with env variable OPENAI_API_BASE
     provider_base_url = "https://api.provider.com/v1"
     os.environ["OPENAI_BASE_URL"] = provider_base_url
-    config = OpenAIConfig(model="gpt-4o", temperature=0.7, max_tokens=100, top_p=1.0, api_key="api_key")
+    config = OpenAIConfig(model="gpt-4.1-nano-2025-04-14", temperature=0.7, max_tokens=100, top_p=1.0, api_key="api_key")
     llm = OpenAILLM(config)
     # Note: openai client will parse the raw base_url into a URL object, which will have a trailing slash
     assert str(llm.client.base_url) == provider_base_url + "/"
@@ -33,7 +33,7 @@ def test_openai_llm_base_url():
     # case3: with config.openai_base_url
     config_base_url = "https://api.config.com/v1"
     config = OpenAIConfig(
-        model="gpt-4o", temperature=0.7, max_tokens=100, top_p=1.0, api_key="api_key", openai_base_url=config_base_url
+        model="gpt-4.1-nano-2025-04-14", temperature=0.7, max_tokens=100, top_p=1.0, api_key="api_key", openai_base_url=config_base_url
     )
     llm = OpenAILLM(config)
     # Note: openai client will parse the raw base_url into a URL object, which will have a trailing slash
@@ -41,7 +41,7 @@ def test_openai_llm_base_url():
 
 
 def test_generate_response_without_tools(mock_openai_client):
-    config = OpenAIConfig(model="gpt-4o", temperature=0.7, max_tokens=100, top_p=1.0)
+    config = OpenAIConfig(model="gpt-4.1-nano-2025-04-14", temperature=0.7, max_tokens=100, top_p=1.0)
     llm = OpenAILLM(config)
     messages = [
         {"role": "system", "content": "You are a helpful assistant."},
@@ -55,13 +55,13 @@ def test_generate_response_without_tools(mock_openai_client):
     response = llm.generate_response(messages)
 
     mock_openai_client.chat.completions.create.assert_called_once_with(
-        model="gpt-4o", messages=messages, temperature=0.7, max_tokens=100, top_p=1.0, store=False
+        model="gpt-4.1-nano-2025-04-14", messages=messages, temperature=0.7, max_tokens=100, top_p=1.0, store=False
     )
     assert response == "I'm doing well, thank you for asking!"
 
 
 def test_generate_response_with_tools(mock_openai_client):
-    config = OpenAIConfig(model="gpt-4o", temperature=0.7, max_tokens=100, top_p=1.0)
+    config = OpenAIConfig(model="gpt-4.1-nano-2025-04-14", temperature=0.7, max_tokens=100, top_p=1.0)
     llm = OpenAILLM(config)
     messages = [
         {"role": "system", "content": "You are a helpful assistant."},
@@ -97,7 +97,7 @@ def test_generate_response_with_tools(mock_openai_client):
     response = llm.generate_response(messages, tools=tools)
 
     mock_openai_client.chat.completions.create.assert_called_once_with(
-        model="gpt-4o", messages=messages, temperature=0.7, max_tokens=100, top_p=1.0, tools=tools, tool_choice="auto", store=False
+        model="gpt-4.1-nano-2025-04-14", messages=messages, temperature=0.7, max_tokens=100, top_p=1.0, tools=tools, tool_choice="auto", store=False
     )
 
     assert response["content"] == "I've added the memory for you."
@@ -110,7 +110,7 @@ def test_response_callback_invocation(mock_openai_client):
     # Setup mock callback
     mock_callback = Mock()
     
-    config = OpenAIConfig(model="gpt-4o", response_callback=mock_callback)
+    config = OpenAIConfig(model="gpt-4.1-nano-2025-04-14", response_callback=mock_callback)
     llm = OpenAILLM(config)
     messages = [{"role": "user", "content": "Test callback"}]
     
@@ -131,7 +131,7 @@ def test_response_callback_invocation(mock_openai_client):
 
 
 def test_no_response_callback(mock_openai_client):
-    config = OpenAIConfig(model="gpt-4o")
+    config = OpenAIConfig(model="gpt-4.1-nano-2025-04-14")
     llm = OpenAILLM(config)
     messages = [{"role": "user", "content": "Test no callback"}]
     
@@ -153,7 +153,7 @@ def test_callback_exception_handling(mock_openai_client):
     def faulty_callback(*args):
         raise ValueError("Callback error")
     
-    config = OpenAIConfig(model="gpt-4o", response_callback=faulty_callback)
+    config = OpenAIConfig(model="gpt-4.1-nano-2025-04-14", response_callback=faulty_callback)
     llm = OpenAILLM(config)
     messages = [{"role": "user", "content": "Test exception"}]
     
@@ -172,7 +172,7 @@ def test_callback_exception_handling(mock_openai_client):
 
 def test_callback_with_tools(mock_openai_client):
     mock_callback = Mock()
-    config = OpenAIConfig(model="gpt-4o", response_callback=mock_callback)
+    config = OpenAIConfig(model="gpt-4.1-nano-2025-04-14", response_callback=mock_callback)
     llm = OpenAILLM(config)
     messages = [{"role": "user", "content": "Test tools"}]
     tools = [

tests/test_proxy.py

@@ -68,14 +68,14 @@ def test_completions_create(mock_memory_client, mock_litellm):
     mock_litellm.completion.return_value = {"choices": [{"message": {"content": "I'm doing well, thank you!"}}]}
     mock_litellm.supports_function_calling.return_value = True
 
-    response = completions.create(model="gpt-4o-mini", messages=messages, user_id="test_user", temperature=0.7)
+    response = completions.create(model="gpt-4.1-nano-2025-04-14", messages=messages, user_id="test_user", temperature=0.7)
 
     mock_memory_client.add.assert_called_once()
     mock_memory_client.search.assert_called_once()
 
     mock_litellm.completion.assert_called_once()
     call_args = mock_litellm.completion.call_args[1]
-    assert call_args["model"] == "gpt-4o-mini"
+    assert call_args["model"] == "gpt-4.1-nano-2025-04-14"
     assert len(call_args["messages"]) == 2
     assert call_args["temperature"] == 0.7
 
@@ -93,7 +93,7 @@ def test_completions_create_with_system_message(mock_memory_client, mock_litellm
     mock_litellm.completion.return_value = {"choices": [{"message": {"content": "I'm doing well, thank you!"}}]}
     mock_litellm.supports_function_calling.return_value = True
 
-    completions.create(model="gpt-4o-mini", messages=messages, user_id="test_user")
+    completions.create(model="gpt-4.1-nano-2025-04-14", messages=messages, user_id="test_user")
 
     call_args = mock_litellm.completion.call_args[1]
     assert call_args["messages"][0]["role"] == "system"