Skip to content

armgit / mem0

Public Imported from GitHub
0

The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.

[Update] Default LLM (#3587)

Parshva Daftari41cfb3ab1aa9
diff --git a/LLM.md b/LLM.md
index baa0db241..69c08cccc 100644
--- a/LLM.md
+++ b/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' }
}
});
diff --git a/README.md b/README.md
index 0149738ec..421c1f6dc 100644
--- a/README.md
+++ b/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
diff --git a/docs/components/llms/models/langchain.mdx b/docs/components/llms/models/langchain.mdx
index 4de3ba58e..a440f61a3 100644
--- a/docs/components/llms/models/langchain.mdx
+++ b/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
)
diff --git a/docs/components/llms/models/litellm.mdx b/docs/components/llms/models/litellm.mdx
index cd3061a3d..f2a041c68 100644
--- a/docs/components/llms/models/litellm.mdx
+++ b/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,
}
diff --git a/docs/components/llms/models/openai.mdx b/docs/components/llms/models/openai.mdx
index 50fa707f4..4a2468d6d 100644
--- a/docs/components/llms/models/openai.mdx
+++ b/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,
}
}
diff --git a/docs/examples/ai_companion_js.mdx b/docs/examples/ai_companion_js.mdx
index ca820df7d..8222ecfa5 100644
--- a/docs/examples/ai_companion_js.mdx
+++ b/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
});
diff --git a/docs/examples/collaborative-task-agent.mdx b/docs/examples/collaborative-task-agent.mdx
index c46e8881f..1b18f32d2 100644
--- a/docs/examples/collaborative-task-agent.mdx
+++ b/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)
diff --git a/docs/examples/eliza_os.mdx b/docs/examples/eliza_os.mdx
index 498ea9ad7..b60c9e745 100644
--- a/docs/examples/eliza_os.mdx
+++ b/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
```
diff --git a/docs/examples/llama-index-mem0.mdx b/docs/examples/llama-index-mem0.mdx
index fcdc078a0..d2621197c 100644
--- a/docs/examples/llama-index-mem0.mdx
+++ b/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).
diff --git a/docs/examples/llamaindex-multiagent-learning-system.mdx b/docs/examples/llamaindex-multiagent-learning-system.mdx
index 146fddd98..b7c95d740 100644
--- a/docs/examples/llamaindex-multiagent-learning-system.mdx
+++ b/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"}
diff --git a/docs/examples/mem0-mastra.mdx b/docs/examples/mem0-mastra.mdx
index 181a414ed..950897fec 100644
--- a/docs/examples/mem0-mastra.mdx
+++ b/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 },
});
```
diff --git a/docs/examples/mem0-openai-voice-demo.mdx b/docs/examples/mem0-openai-voice-demo.mdx
index 1a9e97771..73d0000d7 100644
--- a/docs/examples/mem0-openai-voice-demo.mdx
+++ b/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],
)
diff --git a/docs/examples/memory-guided-content-writing.mdx b/docs/examples/memory-guided-content-writing.mdx
index 2986cb37c..d5b7ff08e 100644
--- a/docs/examples/memory-guided-content-writing.mdx
+++ b/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()
diff --git a/docs/examples/openai-inbuilt-tools.mdx b/docs/examples/openai-inbuilt-tools.mdx
index edecca381..e0bcdeec3 100644
--- a/docs/examples/openai-inbuilt-tools.mdx
+++ b/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}`,
});
diff --git a/docs/examples/personal-ai-tutor.mdx b/docs/examples/personal-ai-tutor.mdx
index f432137fb..4e0663bec 100644
--- a/docs/examples/personal-ai-tutor.mdx
+++ b/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
diff --git a/docs/examples/personal-travel-assistant.mdx b/docs/examples/personal-travel-assistant.mdx
index 81fb753db..640538be9 100644
--- a/docs/examples/personal-travel-assistant.mdx
+++ b/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
diff --git a/docs/integrations/agentops.mdx b/docs/integrations/agentops.mdx
index 3791423f7..cd89aa839 100644
--- a/docs/integrations/agentops.mdx
+++ b/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,
},
diff --git a/docs/integrations/agno.mdx b/docs/integrations/agno.mdx
index 8cd91bd8a..aa71e9f43 100644
--- a/docs/integrations/agno.mdx
+++ b/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."
)
diff --git a/docs/integrations/keywords.mdx b/docs/integrations/keywords.mdx
index c9783ef02..d5c681761 100644
--- a/docs/integrations/keywords.mdx
+++ b/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": {
diff --git a/docs/integrations/langchain.mdx b/docs/integrations/langchain.mdx
index 23da9c220..5d89494b3 100644
--- a/docs/integrations/langchain.mdx
+++ b/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()
```
diff --git a/docs/integrations/livekit.mdx b/docs/integrations/livekit.mdx
index 2e5961585..3b77b7209 100644
--- a/docs/integrations/livekit.mdx
+++ b/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(),
diff --git a/docs/integrations/llama-index.mdx b/docs/integrations/llama-index.mdx
index ec20a3b83..7d6e3142a 100644
--- a/docs/integrations/llama-index.mdx
+++ b/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
diff --git a/docs/integrations/mastra.mdx b/docs/integrations/mastra.mdx
index bcb480088..bf36eb3ba 100644
--- a/docs/integrations/mastra.mdx
+++ b/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 },
});
```
diff --git a/docs/integrations/openai-agents-sdk.mdx b/docs/integrations/openai-agents-sdk.mdx
index 0bfa129c0..81cf3889b 100644
--- a/docs/integrations/openai-agents-sdk.mdx
+++ b/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:
diff --git a/docs/open-source/features/async-memory.mdx b/docs/open-source/features/async-memory.mdx
index 2534413d9..59b9f12a7 100644
--- a/docs/open-source/features/async-memory.mdx
+++ b/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")
diff --git a/docs/open-source/features/custom-fact-extraction-prompt.mdx b/docs/open-source/features/custom-fact-extraction-prompt.mdx
index 8c3bd75f5..e9ebb6036 100644
--- a/docs/open-source/features/custom-fact-extraction-prompt.mdx
+++ b/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,
}
diff --git a/docs/open-source/features/openai_compatibility.mdx b/docs/open-source/features/openai_compatibility.mdx
index ccb758e8f..d8cc45b39 100644
--- a/docs/open-source/features/openai_compatibility.mdx
+++ b/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",
)
```
diff --git a/docs/open-source/graph_memory/overview.mdx b/docs/open-source/graph_memory/overview.mdx
index b43682366..3b21382cb 100644
--- a/docs/open-source/graph_memory/overview.mdx
+++ b/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:
diff --git a/docs/open-source/python-quickstart.mdx b/docs/open-source/python-quickstart.mdx
index cf6cb41d3..79aebc1ca 100644
--- a/docs/open-source/python-quickstart.mdx
+++ b/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",
)
```
diff --git a/docs/v0x/components/llms/models/langchain.mdx b/docs/v0x/components/llms/models/langchain.mdx
index 624d86425..43bea471a 100644
--- a/docs/v0x/components/llms/models/langchain.mdx
+++ b/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
)
diff --git a/docs/v0x/components/llms/models/litellm.mdx b/docs/v0x/components/llms/models/litellm.mdx
index d66669f86..9b38fcb01 100644
--- a/docs/v0x/components/llms/models/litellm.mdx
+++ b/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,
}
diff --git a/docs/v0x/components/llms/models/openai.mdx b/docs/v0x/components/llms/models/openai.mdx
index d31723838..e54ff2ddc 100644
--- a/docs/v0x/components/llms/models/openai.mdx
+++ b/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,
}
}
diff --git a/docs/v0x/examples/ai_companion_js.mdx b/docs/v0x/examples/ai_companion_js.mdx
index d170d12bd..a02c2f596 100644
--- a/docs/v0x/examples/ai_companion_js.mdx
+++ b/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
});
diff --git a/docs/v0x/examples/collaborative-task-agent.mdx b/docs/v0x/examples/collaborative-task-agent.mdx
index c46e8881f..1b18f32d2 100644
--- a/docs/v0x/examples/collaborative-task-agent.mdx
+++ b/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)
diff --git a/docs/v0x/examples/eliza_os.mdx b/docs/v0x/examples/eliza_os.mdx
index 8d0178008..c46120ac4 100644
--- a/docs/v0x/examples/eliza_os.mdx
+++ b/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
```
diff --git a/docs/v0x/examples/llama-index-mem0.mdx b/docs/v0x/examples/llama-index-mem0.mdx
index d7d57715b..8dba93c31 100644
--- a/docs/v0x/examples/llama-index-mem0.mdx
+++ b/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).
diff --git a/docs/v0x/examples/llamaindex-multiagent-learning-system.mdx b/docs/v0x/examples/llamaindex-multiagent-learning-system.mdx
index 149a503a6..f5897ab55 100644
--- a/docs/v0x/examples/llamaindex-multiagent-learning-system.mdx
+++ b/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"}
diff --git a/docs/v0x/examples/mem0-mastra.mdx b/docs/v0x/examples/mem0-mastra.mdx
index 8c8f58650..c4ae1491c 100644
--- a/docs/v0x/examples/mem0-mastra.mdx
+++ b/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 },
});
```
diff --git a/docs/v0x/examples/mem0-openai-voice-demo.mdx b/docs/v0x/examples/mem0-openai-voice-demo.mdx
index 42013d45a..d61d40868 100644
--- a/docs/v0x/examples/mem0-openai-voice-demo.mdx
+++ b/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],
)
diff --git a/docs/v0x/examples/memory-guided-content-writing.mdx b/docs/v0x/examples/memory-guided-content-writing.mdx
index 1f8b4f195..bc17ac5ca 100644
--- a/docs/v0x/examples/memory-guided-content-writing.mdx
+++ b/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()
diff --git a/docs/v0x/examples/openai-inbuilt-tools.mdx b/docs/v0x/examples/openai-inbuilt-tools.mdx
index e1afa6b90..f870ec839 100644
--- a/docs/v0x/examples/openai-inbuilt-tools.mdx
+++ b/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}`,
});
diff --git a/docs/v0x/examples/personal-ai-tutor.mdx b/docs/v0x/examples/personal-ai-tutor.mdx
index 220577aa7..e7d8a1519 100644
--- a/docs/v0x/examples/personal-ai-tutor.mdx
+++ b/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
diff --git a/docs/v0x/examples/personal-travel-assistant.mdx b/docs/v0x/examples/personal-travel-assistant.mdx
index 81fb753db..640538be9 100644
--- a/docs/v0x/examples/personal-travel-assistant.mdx
+++ b/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
diff --git a/docs/v0x/integrations/agentops.mdx b/docs/v0x/integrations/agentops.mdx
index ba25c4057..3fb04dc42 100644
--- a/docs/v0x/integrations/agentops.mdx
+++ b/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,
},
diff --git a/docs/v0x/integrations/agno.mdx b/docs/v0x/integrations/agno.mdx
index f04c69aa4..99584fa79 100644
--- a/docs/v0x/integrations/agno.mdx
+++ b/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."
)
diff --git a/docs/v0x/integrations/keywords.mdx b/docs/v0x/integrations/keywords.mdx
index fff71f1ec..f8df09ae1 100644
--- a/docs/v0x/integrations/keywords.mdx
+++ b/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": {
diff --git a/docs/v0x/integrations/langchain.mdx b/docs/v0x/integrations/langchain.mdx
index f79499e7a..67509be28 100644
--- a/docs/v0x/integrations/langchain.mdx
+++ b/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()
```
diff --git a/docs/v0x/integrations/livekit.mdx b/docs/v0x/integrations/livekit.mdx
index ad44235e5..46947fefa 100644
--- a/docs/v0x/integrations/livekit.mdx
+++ b/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(),
diff --git a/docs/v0x/integrations/llama-index.mdx b/docs/v0x/integrations/llama-index.mdx
index 8316a449d..cc7546615 100644
--- a/docs/v0x/integrations/llama-index.mdx
+++ b/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
diff --git a/docs/v0x/integrations/mastra.mdx b/docs/v0x/integrations/mastra.mdx
index 9b126a44a..0f490e119 100644
--- a/docs/v0x/integrations/mastra.mdx
+++ b/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 },
});
```
diff --git a/docs/v0x/integrations/openai-agents-sdk.mdx b/docs/v0x/integrations/openai-agents-sdk.mdx
index 084a89607..f8ab3bd47 100644
--- a/docs/v0x/integrations/openai-agents-sdk.mdx
+++ b/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:
diff --git a/docs/v0x/open-source/python-quickstart.mdx b/docs/v0x/open-source/python-quickstart.mdx
index 622310ef7..eeeb0c456 100644
--- a/docs/v0x/open-source/python-quickstart.mdx
+++ b/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",
)
```
diff --git a/examples/graph-db-demo/kuzu-example.ipynb b/examples/graph-db-demo/kuzu-example.ipynb
index f1922d67e..1838be632 100644
--- a/examples/graph-db-demo/kuzu-example.ipynb
+++ b/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",
diff --git a/examples/misc/diet_assistant_voice_cartesia.py b/examples/misc/diet_assistant_voice_cartesia.py
index 2fb2f6c1a..2d4a83473 100644
--- a/examples/misc/diet_assistant_voice_cartesia.py
+++ b/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,
)
diff --git a/examples/misc/fitness_checker.py b/examples/misc/fitness_checker.py
index bbd50bcec..5bd92ec01 100644
--- a/examples/misc/fitness_checker.py
+++ b/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,
)
diff --git a/examples/misc/multillm_memory.py b/examples/misc/multillm_memory.py
index ab024b171..a30290c94 100644
--- a/examples/misc/multillm_memory.py
+++ b/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",
},
}
diff --git a/examples/misc/personal_assistant_agno.py b/examples/misc/personal_assistant_agno.py
index bd2f04c91..5a770a522 100644
--- a/examples/misc/personal_assistant_agno.py
+++ b/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,
diff --git a/examples/misc/personalized_search.py b/examples/misc/personalized_search.py
index 34939fbbd..0c8d0e890 100644
--- a/examples/misc/personalized_search.py
+++ b/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):
diff --git a/examples/misc/test.py b/examples/misc/test.py
index ec21f6ac6..39c4ae57f 100644
--- a/examples/misc/test.py
+++ b/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",
)
diff --git a/examples/multiagents/llamaindex_learning_system.py b/examples/multiagents/llamaindex_learning_system.py
index 2896c4676..b568a1981 100644
--- a/examples/multiagents/llamaindex_learning_system.py
+++ b/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"}
diff --git a/examples/multimodal-demo/src/hooks/useChat.ts b/examples/multimodal-demo/src/hooks/useChat.ts
index 4f3f37c17..59f0cc864 100644
--- a/examples/multimodal-demo/src/hooks/useChat.ts
+++ b/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 => ({
diff --git a/examples/multimodal-demo/useChat.ts b/examples/multimodal-demo/useChat.ts
index 4f3f37c17..59f0cc864 100644
--- a/examples/multimodal-demo/useChat.ts
+++ b/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 => ({
diff --git a/mem0-ts/src/oss/src/llms/openai.ts b/mem0-ts/src/oss/src/llms/openai.ts
index bc995f7b8..96a36f971 100644
--- a/mem0-ts/src/oss/src/llms/openai.ts
+++ b/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(
diff --git a/mem0/configs/llms/base.py b/mem0/configs/llms/base.py
index 55561c632..93d5052d0 100644
--- a/mem0/configs/llms/base.py
+++ b/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.
diff --git a/mem0/llms/azure_openai.py b/mem0/llms/azure_openai.py
index 6ddb50b66..76ed83f8f 100644
--- a/mem0/llms/azure_openai.py
+++ b/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")
diff --git a/mem0/llms/azure_openai_structured.py b/mem0/llms/azure_openai_structured.py
index fd2bae023..3b97b492f 100644
--- a/mem0/llms/azure_openai_structured.py
+++ b/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")
diff --git a/mem0/llms/litellm.py b/mem0/llms/litellm.py
index 3a5ef60c6..d04aa43d0 100644
--- a/mem0/llms/litellm.py
+++ b/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):
"""
diff --git a/mem0/llms/openai.py b/mem0/llms/openai.py
index b6ad538d0..a486ff86b 100644
--- a/mem0/llms/openai.py
+++ b/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(
diff --git a/server/main.py b/server/main.py
index a9f4dfdc1..85c7cc7ea 100644
--- a/server/main.py
+++ b/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,
}
diff --git a/tests/llms/test_azure_openai.py b/tests/llms/test_azure_openai.py
index f9bfbe4c4..8febe386c 100644
--- a/tests/llms/test_azure_openai.py
+++ b/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
- assert llm.config.model == "gpt-4o"
+ # Should default to "gpt-4.1-nano-2025-04-14" if model is None
+ assert llm.config.model == "gpt-4.1-nano-2025-04-14"
def test_init_with_default_azure_credential(monkeypatch):
diff --git a/tests/llms/test_azure_openai_structured.py b/tests/llms/test_azure_openai_structured.py
index d8655d136..4098bed88 100644
--- a/tests/llms/test_azure_openai_structured.py
+++ b/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()
diff --git a/tests/llms/test_litellm.py b/tests/llms/test_litellm.py
index d7be93c9f..db4d174f2 100644
--- a/tests/llms/test_litellm.py
+++ b/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."
diff --git a/tests/llms/test_openai.py b/tests/llms/test_openai.py
index a98feb07d..700698ba1 100644
--- a/tests/llms/test_openai.py
+++ b/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 = [
diff --git a/tests/test_proxy.py b/tests/test_proxy.py
index ba3188421..b19ca70a9 100644
--- a/tests/test_proxy.py
+++ b/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"