Use latest OpenAI, Google, Anthropic models in all examples (#3278)

Author: DouweM

CLAUDE.md

@@ -28,7 +28,7 @@ This file provides guidance to Claude Code (claude.ai/code) when working with co
 
 **Model Integration (`pydantic_ai_slim/pydantic_ai/models/`)**
 - Unified interface across providers: OpenAI, Anthropic, Google, Groq, Cohere, Mistral, Bedrock, HuggingFace
-- Model strings: `"openai:gpt-4o"`, `"anthropic:claude-3-5-sonnet"`, `"google:gemini-1.5-pro"`
+- Model strings: `"openai:gpt-5"`, `"anthropic:claude-sonnet-4-5"`, `"google:gemini-2.5-pro"`
 - `ModelRequestParameters` for configuration, `StreamedResponse` for streaming
 
 **Graph-based Execution (`pydantic_graph/` + `_agent_graph.py`)**
@@ -55,7 +55,7 @@ This file provides guidance to Claude Code (claude.ai/code) when working with co
 class MyDeps:
     database: DatabaseConn
 
-agent = Agent('openai:gpt-4o', deps_type=MyDeps)
+agent = Agent('openai:gpt-5', deps_type=MyDeps)
 
 @agent.tool
 async def get_data(ctx: RunContext[MyDeps]) -> str:
@@ -69,7 +69,7 @@ class OutputModel(BaseModel):
     confidence: float
 
 agent: Agent[MyDeps, OutputModel] = Agent(
-    'openai:gpt-4o',
+    'openai:gpt-5',
     deps_type=MyDeps,
     output_type=OutputModel
 )

clai/README.md

@@ -70,7 +70,7 @@ positional arguments:
 options:
   -h, --help            show this help message and exit
   -m [MODEL], --model [MODEL]
-                        Model to use, in format "<provider>:<model>" e.g. "openai:gpt-4.1" or "anthropic:claude-sonnet-4-0". Defaults to "openai:gpt-4.1".
+                        Model to use, in format "<provider>:<model>" e.g. "openai:gpt-5" or "anthropic:claude-sonnet-4-5". Defaults to "openai:gpt-5".
   -a AGENT, --agent AGENT
                         Custom Agent to use, in format "module:variable", e.g. "mymodule.submodule:my_agent"
   -l, --list-models     List all available models and exit

docs/a2a.md

@@ -10,7 +10,7 @@ We also built a convenience method that expose Pydantic AI agents as A2A servers
 ```py {title="agent_to_a2a.py" hl_lines="4"}
 from pydantic_ai import Agent
 
-agent = Agent('openai:gpt-4.1', instructions='Be fun!')
+agent = Agent('openai:gpt-5', instructions='Be fun!')
 app = agent.to_a2a()
 ```
 
@@ -104,7 +104,7 @@ To expose a Pydantic AI agent as an A2A server, you can use the `to_a2a` method:
 ```python {title="agent_to_a2a.py"}
 from pydantic_ai import Agent
 
-agent = Agent('openai:gpt-4.1', instructions='Be fun!')
+agent = Agent('openai:gpt-5', instructions='Be fun!')
 app = agent.to_a2a()
 ```
 

docs/ag-ui.md

@@ -55,7 +55,7 @@ from pydantic import ValidationError
 from pydantic_ai import Agent
 from pydantic_ai.ag_ui import SSE_CONTENT_TYPE, run_ag_ui
 
-agent = Agent('openai:gpt-4.1', instructions='Be fun!')
+agent = Agent('openai:gpt-5', instructions='Be fun!')
 
 app = FastAPI()
 
@@ -97,7 +97,7 @@ from starlette.responses import Response
 from pydantic_ai import Agent
 from pydantic_ai.ag_ui import handle_ag_ui_request
 
-agent = Agent('openai:gpt-4.1', instructions='Be fun!')
+agent = Agent('openai:gpt-5', instructions='Be fun!')
 
 app = FastAPI()
 
@@ -121,7 +121,7 @@ This example uses [`Agent.to_ag_ui()`][pydantic_ai.agent.AbstractAgent.to_ag_ui]
 ```py {title="agent_to_ag_ui.py" hl_lines="4"}
 from pydantic_ai import Agent
 
-agent = Agent('openai:gpt-4.1', instructions='Be fun!')
+agent = Agent('openai:gpt-5', instructions='Be fun!')
 app = agent.to_ag_ui()
 ```
 
@@ -184,7 +184,7 @@ class DocumentState(BaseModel):
 
 
 agent = Agent(
-    'openai:gpt-4.1',
+    'openai:gpt-5',
     instructions='Be fun!',
     deps_type=StateDeps[DocumentState],
 )
@@ -224,7 +224,7 @@ class DocumentState(BaseModel):
 
 
 agent = Agent(
-    'openai:gpt-4.1',
+    'openai:gpt-5',
     instructions='Be fun!',
     deps_type=StateDeps[DocumentState],
 )

docs/agents.md

@@ -24,7 +24,7 @@ Here's a toy example of an agent that simulates a roulette wheel:
 from pydantic_ai import Agent, RunContext
 
 roulette_agent = Agent(  # (1)!
-    'openai:gpt-4o',
+    'openai:gpt-5',
     deps_type=int,
     output_type=bool,
     system_prompt=(
@@ -74,7 +74,7 @@ Here's a simple example demonstrating the first four:
 ```python {title="run_agent.py"}
 from pydantic_ai import Agent, AgentRunResultEvent, AgentStreamEvent
 
-agent = Agent('openai:gpt-4o')
+agent = Agent('openai:gpt-5')
 
 result_sync = agent.run_sync('What is the capital of Italy?')
 print(result_sync.output)
@@ -148,7 +148,7 @@ from pydantic_ai import (
 )
 
 weather_agent = Agent(
-    'openai:gpt-4o',
+    'openai:gpt-5',
     system_prompt='Providing a weather forecast at the locations the user provides.',
 )
 
@@ -290,7 +290,7 @@ Here's an example of using `async for` with `iter` to record each node the agent
 ```python {title="agent_iter_async_for.py"}
 from pydantic_ai import Agent
 
-agent = Agent('openai:gpt-4o')
+agent = Agent('openai:gpt-5')
 
 
 async def main():
@@ -324,7 +324,7 @@ async def main():
             model_response=ModelResponse(
                 parts=[TextPart(content='The capital of France is Paris.')],
                 usage=RequestUsage(input_tokens=56, output_tokens=7),
-                model_name='gpt-4o',
+                model_name='gpt-5',
                 timestamp=datetime.datetime(...),
             )
         ),
@@ -348,7 +348,7 @@ You can also drive the iteration manually by passing the node you want to run ne
 from pydantic_ai import Agent
 from pydantic_graph import End
 
-agent = Agent('openai:gpt-4o')
+agent = Agent('openai:gpt-5')
 
 
 async def main():
@@ -386,7 +386,7 @@ async def main():
                 model_response=ModelResponse(
                     parts=[TextPart(content='The capital of France is Paris.')],
                     usage=RequestUsage(input_tokens=56, output_tokens=7),
-                    model_name='gpt-4o',
+                    model_name='gpt-5',
                     timestamp=datetime.datetime(...),
                 )
             ),
@@ -443,7 +443,7 @@ class WeatherService:
 
 
 weather_agent = Agent[WeatherService, str](
-    'openai:gpt-4o',
+    'openai:gpt-5',
     deps_type=WeatherService,
     output_type=str,  # We'll produce a final answer as plain text
     system_prompt='Providing a weather forecast at the locations the user provides.',
@@ -572,7 +572,7 @@ Consider the following example, where we limit the number of response tokens:
 ```py
 from pydantic_ai import Agent, UsageLimitExceeded, UsageLimits
 
-agent = Agent('anthropic:claude-3-5-sonnet-latest')
+agent = Agent('anthropic:claude-sonnet-4-5')
 
 result_sync = agent.run_sync(
     'What is the capital of Italy? Answer with just the city.',
@@ -610,7 +610,7 @@ class NeverOutputType(TypedDict):
 
 
 agent = Agent(
-    'anthropic:claude-3-5-sonnet-latest',
+    'anthropic:claude-sonnet-4-5',
     retries=3,
     output_type=NeverOutputType,
     system_prompt='Any time you get a response, call the `infinite_retry_tool` to produce another response.',
@@ -643,7 +643,7 @@ from pydantic_ai import Agent
 from pydantic_ai.exceptions import UsageLimitExceeded
 from pydantic_ai.usage import UsageLimits
 
-agent = Agent('anthropic:claude-3-5-sonnet-latest')
+agent = Agent('anthropic:claude-sonnet-4-5')
 
 @agent.tool_plain
 def do_work() -> str:
@@ -682,7 +682,7 @@ from pydantic_ai.models.openai import OpenAIChatModel
 
 # 1. Model-level defaults
 model = OpenAIChatModel(
-    'gpt-4o',
+    'gpt-5',
     settings=ModelSettings(temperature=0.8, max_tokens=500)  # Base defaults
 )
 
@@ -714,7 +714,7 @@ For example:
 from pydantic_ai import Agent, UnexpectedModelBehavior
 from pydantic_ai.models.google import GoogleModelSettings
 
-agent = Agent('google-gla:gemini-1.5-flash')
+agent = Agent('google-gla:gemini-2.5-flash')
 
 try:
     result = agent.run_sync(
@@ -752,7 +752,7 @@ Here's an example of a conversation comprised of multiple runs:
 ```python {title="conversation_example.py" hl_lines="13"}
 from pydantic_ai import Agent
 
-agent = Agent('openai:gpt-4o')
+agent = Agent('openai:gpt-5')
 
 # First run
 result1 = agent.run_sync('Who was Albert Einstein?')
@@ -860,7 +860,7 @@ from datetime import date
 from pydantic_ai import Agent, RunContext
 
 agent = Agent(
-    'openai:gpt-4o',
+    'openai:gpt-5',
     deps_type=str,  # (1)!
     system_prompt="Use the customer's name while replying to them.",  # (2)!
 )
@@ -916,7 +916,7 @@ from datetime import date
 from pydantic_ai import Agent, RunContext
 
 agent = Agent(
-    'openai:gpt-4o',
+    'openai:gpt-5',
     deps_type=str,  # (1)!
     instructions="Use the customer's name while replying to them.",  # (2)!
 )
@@ -973,7 +973,7 @@ class ChatResult(BaseModel):
 
 
 agent = Agent(
-    'openai:gpt-4o',
+    'openai:gpt-5',
     deps_type=DatabaseConn,
     output_type=ChatResult,
 )
@@ -1011,7 +1011,7 @@ In these cases, [`capture_run_messages`][pydantic_ai.capture_run_messages] can b
 ```python {title="agent_model_errors.py"}
 from pydantic_ai import Agent, ModelRetry, UnexpectedModelBehavior, capture_run_messages
 
-agent = Agent('openai:gpt-4o')
+agent = Agent('openai:gpt-5')
 
 
 @agent.tool_plain
@@ -1051,7 +1051,7 @@ with capture_run_messages() as messages:  # (2)!
                     )
                 ],
                 usage=RequestUsage(input_tokens=62, output_tokens=4),
-                model_name='gpt-4o',
+                model_name='gpt-5',
                 timestamp=datetime.datetime(...),
             ),
             ModelRequest(
@@ -1073,7 +1073,7 @@ with capture_run_messages() as messages:  # (2)!
                     )
                 ],
                 usage=RequestUsage(input_tokens=72, output_tokens=8),
-                model_name='gpt-4o',
+                model_name='gpt-5',
                 timestamp=datetime.datetime(...),
             ),
         ]

docs/api/models/function.md

@@ -14,7 +14,7 @@ from pydantic_ai import Agent
 from pydantic_ai import ModelMessage, ModelResponse, TextPart
 from pydantic_ai.models.function import FunctionModel, AgentInfo
 
-my_agent = Agent('openai:gpt-4o')
+my_agent = Agent('openai:gpt-5')
 
 
 async def model_function(

docs/api/models/test.md

@@ -8,7 +8,7 @@ Here's a minimal example:
 from pydantic_ai import Agent
 from pydantic_ai.models.test import TestModel
 
-my_agent = Agent('openai:gpt-4o', system_prompt='...')
+my_agent = Agent('openai:gpt-5', system_prompt='...')
 
 
 async def test_my_agent():

docs/builtin-tools.md

@@ -59,7 +59,7 @@ With OpenAI, you must use their Responses API to access the web search tool.
 ```py {title="web_search_openai.py"}
 from pydantic_ai import Agent, WebSearchTool
 
-agent = Agent('openai-responses:gpt-4.1', builtin_tools=[WebSearchTool()])
+agent = Agent('openai-responses:gpt-5', builtin_tools=[WebSearchTool()])
 
 result = agent.run_sync('Give me a sentence with the biggest news in AI this week.')
 print(result.output)
@@ -201,7 +201,7 @@ The [`ImageGenerationTool`][pydantic_ai.builtin_tools.ImageGenerationTool] enabl
 
 | Provider | Supported | Notes |
 |----------|-----------|-------|
-| OpenAI Responses | ✅ | Full feature support. Only supported by models newer than `gpt-4o`. Metadata about the generated image, like the [`revised_prompt`](https://platform.openai.com/docs/guides/tools-image-generation#revised-prompt) sent to the underlying image model, is available on the [`BuiltinToolReturnPart`][pydantic_ai.messages.BuiltinToolReturnPart] that's available via [`ModelResponse.builtin_tool_calls`][pydantic_ai.messages.ModelResponse.builtin_tool_calls]. |
+| OpenAI Responses | ✅ | Full feature support. Only supported by models newer than `gpt-5`. Metadata about the generated image, like the [`revised_prompt`](https://platform.openai.com/docs/guides/tools-image-generation#revised-prompt) sent to the underlying image model, is available on the [`BuiltinToolReturnPart`][pydantic_ai.messages.BuiltinToolReturnPart] that's available via [`ModelResponse.builtin_tool_calls`][pydantic_ai.messages.ModelResponse.builtin_tool_calls]. |
 | Google | ✅ | No parameter support. Only supported by [image generation models](https://ai.google.dev/gemini-api/docs/image-generation) like `gemini-2.5-flash-image`. These models do not support [structured output](output.md) or [function tools](tools.md). These models will always generate images, even if this built-in tool is not explicitly specified. |
 | Anthropic | ❌ | |
 | Groq | ❌ | |

docs/cli.md

@@ -73,7 +73,7 @@ You can specify a custom agent using the `--agent` flag with a module path and v
 ```python {title="custom_agent.py" test="skip"}
 from pydantic_ai import Agent
 
-agent = Agent('openai:gpt-4.1', instructions='You always respond in Italian.')
+agent = Agent('openai:gpt-5', instructions='You always respond in Italian.')
 ```
 
 Then run:
@@ -92,7 +92,7 @@ Additionally, you can directly launch CLI mode from an `Agent` instance using `A
 ```python {title="agent_to_cli_sync.py" test="skip" hl_lines=4}
 from pydantic_ai import Agent
 
-agent = Agent('openai:gpt-4.1', instructions='You always respond in Italian.')
+agent = Agent('openai:gpt-5', instructions='You always respond in Italian.')
 agent.to_cli_sync()
 ```
 
@@ -101,7 +101,7 @@ You can also use the async interface with `Agent.to_cli()`:
 ```python {title="agent_to_cli.py" test="skip" hl_lines=6}
 from pydantic_ai import Agent
 
-agent = Agent('openai:gpt-4.1', instructions='You always respond in Italian.')
+agent = Agent('openai:gpt-5', instructions='You always respond in Italian.')
 
 async def main():
     await agent.to_cli()
@@ -123,7 +123,7 @@ from pydantic_ai import (
     UserPromptPart,
 )
 
-agent = Agent('openai:gpt-4.1')
+agent = Agent('openai:gpt-5')
 
 # Create some conversation history
 message_history: list[ModelMessage] = [

docs/dependencies.md

@@ -27,7 +27,7 @@ class MyDeps:  # (1)!
 
 
 agent = Agent(
-    'openai:gpt-4o',
+    'openai:gpt-5',
     deps_type=MyDeps,  # (2)!
 )
 
@@ -68,7 +68,7 @@ class MyDeps:
 
 
 agent = Agent(
-    'openai:gpt-4o',
+    'openai:gpt-5',
     deps_type=MyDeps,
 )
 
@@ -126,7 +126,7 @@ class MyDeps:
 
 
 agent = Agent(
-    'openai:gpt-4o',
+    'openai:gpt-5',
     deps_type=MyDeps,
 )
 
@@ -174,7 +174,7 @@ class MyDeps:
 
 
 agent = Agent(
-    'openai:gpt-4o',
+    'openai:gpt-5',
     deps_type=MyDeps,
 )
 
@@ -251,7 +251,7 @@ class MyDeps:
         return f'Prompt: {response.text}'
 
 
-joke_agent = Agent('openai:gpt-4o', deps_type=MyDeps)
+joke_agent = Agent('openai:gpt-5', deps_type=MyDeps)
 
 
 @joke_agent.system_prompt