Matt Apperson
5fc522c72f
Auto-generated Python SDK for OpenRouter API, providing comprehensive client library with: - Chat completions and streaming support - Embeddings API - Model and provider information - API key management - Analytics and usage tracking - OAuth authentication flows - Full type hints and error handling
41 KiB
openrouter
Developer-friendly & type-safe Python SDK specifically catered to leverage openrouter API.
Important
This SDK is not yet ready for production use. To complete setup please follow the steps outlined in your workspace. Delete this section before > publishing to a package manager.
Summary
OpenRouter API: OpenAI-compatible Chat Completions and Completions API with additional OpenRouter features
For more information about the API: OpenRouter Documentation
Table of Contents
SDK Installation
Tip
To finish publishing your SDK to PyPI you must run your first generation action.
Note
Python version upgrade policy
Once a Python version reaches its official end of life date, a 3-month grace period is provided for users to upgrade. Following this grace period, the minimum python version supported in the SDK will be updated.
The SDK can be installed with uv, pip, or poetry package managers.
uv
uv is a fast Python package installer and resolver, designed as a drop-in replacement for pip and pip-tools. It's recommended for its speed and modern Python tooling capabilities.
uv add git+<UNSET>.git
PIP
PIP is the default package installer for Python, enabling easy installation and management of packages from PyPI via the command line.
pip install git+<UNSET>.git
Poetry
Poetry is a modern tool that simplifies dependency management and package publishing by using a single pyproject.toml file to handle project metadata and dependencies.
poetry add git+<UNSET>.git
Shell and script usage with uv
You can use this SDK in a Python shell with uv and the uvx command that comes with it like so:
uvx --from openrouter python
It's also possible to write a standalone Python script without needing to set up a whole project like so:
#!/usr/bin/env -S uv run --script
# /// script
# requires-python = ">=3.9"
# dependencies = [
# "openrouter",
# ]
# ///
from openrouter import OpenRouter
sdk = OpenRouter(
# SDK arguments
)
# Rest of script here...
Once that is saved to a file, you can run it with uv run script.py where
script.py can be replaced with the actual file name.
IDE Support
PyCharm
Generally, the SDK will work well with most IDEs out of the box. However, when using PyCharm, you can enjoy much better integration with Pydantic by installing an additional plugin.
SDK Example Usage
Example
# Synchronous Example
from openrouter import OpenRouter
import os
with OpenRouter(
api_key=os.getenv("OPENROUTER_API_KEY", ""),
) as open_router:
res = open_router.beta.responses.send(input=[
{
"type": "message",
"role": "user",
"content": "Hello, how are you?",
},
], metadata={
"user_id": "123",
"session_id": "abc-def-ghi",
}, tools=[
{
"type": "function",
"name": "get_current_weather",
"description": "Get the current weather in a given location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
},
},
},
},
], model="anthropic/claude-4.5-sonnet-20250929", text={
"format_": {
"type": "text",
},
"verbosity": "medium",
}, reasoning={
"summary": "auto",
"enabled": True,
}, temperature=0.7, top_p=0.9, prompt={
"id": "<id>",
"variables": {
"key": {
"type": "input_text",
"text": "Hello, how can I help you?",
},
},
}, service_tier="auto", truncation="auto", stream=False, provider={
"data_collection": "deny",
"zdr": True,
"enforce_distillable_text": True,
"order": [
"OpenAI",
],
"only": [
"OpenAI",
],
"ignore": [
"OpenAI",
],
"quantizations": None,
"sort": "price",
})
with res as event_stream:
for event in event_stream:
# handle event
print(event, flush=True)
The same SDK client can also be used to make asynchronous requests by importing asyncio.
# Asynchronous Example
import asyncio
from openrouter import OpenRouter
import os
async def main():
async with OpenRouter(
api_key=os.getenv("OPENROUTER_API_KEY", ""),
) as open_router:
res = await open_router.beta.responses.send_async(input=[
{
"type": "message",
"role": "user",
"content": "Hello, how are you?",
},
], metadata={
"user_id": "123",
"session_id": "abc-def-ghi",
}, tools=[
{
"type": "function",
"name": "get_current_weather",
"description": "Get the current weather in a given location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
},
},
},
},
], model="anthropic/claude-4.5-sonnet-20250929", text={
"format_": {
"type": "text",
},
"verbosity": "medium",
}, reasoning={
"summary": "auto",
"enabled": True,
}, temperature=0.7, top_p=0.9, prompt={
"id": "<id>",
"variables": {
"key": {
"type": "input_text",
"text": "Hello, how can I help you?",
},
},
}, service_tier="auto", truncation="auto", stream=False, provider={
"data_collection": "deny",
"zdr": True,
"enforce_distillable_text": True,
"order": [
"OpenAI",
],
"only": [
"OpenAI",
],
"ignore": [
"OpenAI",
],
"quantizations": None,
"sort": "price",
})
async with res as event_stream:
async for event in event_stream:
# handle event
print(event, flush=True)
asyncio.run(main())
Authentication
Per-Client Security Schemes
This SDK supports the following security scheme globally:
| Name | Type | Scheme | Environment Variable |
|---|---|---|---|
api_key |
http | HTTP Bearer | OPENROUTER_API_KEY |
To authenticate with the API the api_key parameter must be set when initializing the SDK client instance. For example:
from openrouter import OpenRouter
import os
with OpenRouter(
api_key=os.getenv("OPENROUTER_API_KEY", ""),
) as open_router:
res = open_router.beta.responses.send(input=[
{
"type": "message",
"role": "user",
"content": "Hello, how are you?",
},
], metadata={
"user_id": "123",
"session_id": "abc-def-ghi",
}, tools=[
{
"type": "function",
"name": "get_current_weather",
"description": "Get the current weather in a given location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
},
},
},
},
], model="anthropic/claude-4.5-sonnet-20250929", text={
"format_": {
"type": "text",
},
"verbosity": "medium",
}, reasoning={
"summary": "auto",
"enabled": True,
}, temperature=0.7, top_p=0.9, prompt={
"id": "<id>",
"variables": {
"key": {
"type": "input_text",
"text": "Hello, how can I help you?",
},
},
}, service_tier="auto", truncation="auto", stream=False, provider={
"data_collection": "deny",
"zdr": True,
"enforce_distillable_text": True,
"order": [
"OpenAI",
],
"only": [
"OpenAI",
],
"ignore": [
"OpenAI",
],
"quantizations": None,
"sort": "price",
})
with res as event_stream:
for event in event_stream:
# handle event
print(event, flush=True)
Per-Operation Security Schemes
Some operations in this SDK require the security scheme to be specified at the request level. For example:
from openrouter import OpenRouter, models
import os
with OpenRouter() as open_router:
res = open_router.credits.create_coinbase_charge(security=models.CreateCoinbaseChargeSecurity(
bearer=os.getenv("OPENROUTER_BEARER", ""),
), amount=100, sender="0x1234567890123456789012345678901234567890", chain_id=1)
# Handle response
print(res)
Available Resources and Operations
Available methods
analytics
- get_user_activity - Get user activity grouped by endpoint
api_keys
- list - List API keys
- create - Create a new API key
- update - Update an API key
- delete - Delete an API key
- get - Get a single API key
- get_current_key_metadata - Get current API key
beta.responses
- send - Create a response
chat
- send - Create a chat completion
completions
- generate - Create a completion
credits
- get_credits - Get remaining credits
- create_coinbase_charge - Create a Coinbase charge for crypto payment
embeddings
- generate - Submit an embedding request
- list_models - List all embeddings models
endpoints
- list - List all endpoints for a model
- list_zdr_endpoints - Preview the impact of ZDR on the available endpoints
generations
- get_generation - Get request & usage metadata for a generation
models
- count - Get total count of available models
- list - List all models and their properties
- list_for_user - List models filtered by user provider preferences
o_auth
- exchange_auth_code_for_api_key - Exchange authorization code for API key
- create_auth_code - Create authorization code
parameters
- get_parameters - Get a model's supported parameters and data about which are most popular
providers
- list - List all providers
Server-sent event streaming
Server-sent events are used to stream content from certain
operations. These operations will expose the stream as Generator that
can be consumed using a simple for loop. The loop will
terminate when the server no longer has any events to send and closes the
underlying connection.
The stream is also a Context Manager and can be used with the with statement and will close the
underlying connection when the context is exited.
from openrouter import OpenRouter
import os
with OpenRouter(
api_key=os.getenv("OPENROUTER_API_KEY", ""),
) as open_router:
res = open_router.beta.responses.send(input=[
{
"type": "message",
"role": "user",
"content": "Hello, how are you?",
},
], metadata={
"user_id": "123",
"session_id": "abc-def-ghi",
}, tools=[
{
"type": "function",
"name": "get_current_weather",
"description": "Get the current weather in a given location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
},
},
},
},
], model="anthropic/claude-4.5-sonnet-20250929", text={
"format_": {
"type": "text",
},
"verbosity": "medium",
}, reasoning={
"summary": "auto",
"enabled": True,
}, temperature=0.7, top_p=0.9, prompt={
"id": "<id>",
"variables": {
"key": {
"type": "input_text",
"text": "Hello, how can I help you?",
},
},
}, service_tier="auto", truncation="auto", stream=False, provider={
"data_collection": "deny",
"zdr": True,
"enforce_distillable_text": True,
"order": [
"OpenAI",
],
"only": [
"OpenAI",
],
"ignore": [
"OpenAI",
],
"quantizations": None,
"sort": "price",
})
with res as event_stream:
for event in event_stream:
# handle event
print(event, flush=True)
Retries
Some of the endpoints in this SDK support retries. If you use the SDK without any configuration, it will fall back to the default retry strategy provided by the API. However, the default retry strategy can be overridden on a per-operation basis, or across the entire SDK.
To change the default retry strategy for a single API call, simply provide a RetryConfig object to the call:
from openrouter import OpenRouter
from openrouter.utils import BackoffStrategy, RetryConfig
import os
with OpenRouter(
api_key=os.getenv("OPENROUTER_API_KEY", ""),
) as open_router:
res = open_router.beta.responses.send(input=[
{
"type": "message",
"role": "user",
"content": "Hello, how are you?",
},
], metadata={
"user_id": "123",
"session_id": "abc-def-ghi",
}, tools=[
{
"type": "function",
"name": "get_current_weather",
"description": "Get the current weather in a given location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
},
},
},
},
], model="anthropic/claude-4.5-sonnet-20250929", text={
"format_": {
"type": "text",
},
"verbosity": "medium",
}, reasoning={
"summary": "auto",
"enabled": True,
}, temperature=0.7, top_p=0.9, prompt={
"id": "<id>",
"variables": {
"key": {
"type": "input_text",
"text": "Hello, how can I help you?",
},
},
}, service_tier="auto", truncation="auto", stream=False, provider={
"data_collection": "deny",
"zdr": True,
"enforce_distillable_text": True,
"order": [
"OpenAI",
],
"only": [
"OpenAI",
],
"ignore": [
"OpenAI",
],
"quantizations": None,
"sort": "price",
},
RetryConfig("backoff", BackoffStrategy(1, 50, 1.1, 100), False))
with res as event_stream:
for event in event_stream:
# handle event
print(event, flush=True)
If you'd like to override the default retry strategy for all operations that support retries, you can use the retry_config optional parameter when initializing the SDK:
from openrouter import OpenRouter
from openrouter.utils import BackoffStrategy, RetryConfig
import os
with OpenRouter(
retry_config=RetryConfig("backoff", BackoffStrategy(1, 50, 1.1, 100), False),
api_key=os.getenv("OPENROUTER_API_KEY", ""),
) as open_router:
res = open_router.beta.responses.send(input=[
{
"type": "message",
"role": "user",
"content": "Hello, how are you?",
},
], metadata={
"user_id": "123",
"session_id": "abc-def-ghi",
}, tools=[
{
"type": "function",
"name": "get_current_weather",
"description": "Get the current weather in a given location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
},
},
},
},
], model="anthropic/claude-4.5-sonnet-20250929", text={
"format_": {
"type": "text",
},
"verbosity": "medium",
}, reasoning={
"summary": "auto",
"enabled": True,
}, temperature=0.7, top_p=0.9, prompt={
"id": "<id>",
"variables": {
"key": {
"type": "input_text",
"text": "Hello, how can I help you?",
},
},
}, service_tier="auto", truncation="auto", stream=False, provider={
"data_collection": "deny",
"zdr": True,
"enforce_distillable_text": True,
"order": [
"OpenAI",
],
"only": [
"OpenAI",
],
"ignore": [
"OpenAI",
],
"quantizations": None,
"sort": "price",
})
with res as event_stream:
for event in event_stream:
# handle event
print(event, flush=True)
Error Handling
OpenRouterError is the base class for all HTTP error responses. It has the following properties:
| Property | Type | Description |
|---|---|---|
err.message |
str |
Error message |
err.status_code |
int |
HTTP response status code eg 404 |
err.headers |
httpx.Headers |
HTTP response headers |
err.body |
str |
HTTP body. Can be empty string if no body is returned. |
err.raw_response |
httpx.Response |
Raw HTTP response |
err.data |
Optional. Some errors may contain structured data. See Error Classes. |
Example
from openrouter import OpenRouter, errors
import os
with OpenRouter(
api_key=os.getenv("OPENROUTER_API_KEY", ""),
) as open_router:
res = None
try:
res = open_router.beta.responses.send(input=[
{
"type": "message",
"role": "user",
"content": "Hello, how are you?",
},
], metadata={
"user_id": "123",
"session_id": "abc-def-ghi",
}, tools=[
{
"type": "function",
"name": "get_current_weather",
"description": "Get the current weather in a given location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
},
},
},
},
], model="anthropic/claude-4.5-sonnet-20250929", text={
"format_": {
"type": "text",
},
"verbosity": "medium",
}, reasoning={
"summary": "auto",
"enabled": True,
}, temperature=0.7, top_p=0.9, prompt={
"id": "<id>",
"variables": {
"key": {
"type": "input_text",
"text": "Hello, how can I help you?",
},
},
}, service_tier="auto", truncation="auto", stream=False, provider={
"data_collection": "deny",
"zdr": True,
"enforce_distillable_text": True,
"order": [
"OpenAI",
],
"only": [
"OpenAI",
],
"ignore": [
"OpenAI",
],
"quantizations": None,
"sort": "price",
})
with res as event_stream:
for event in event_stream:
# handle event
print(event, flush=True)
except errors.OpenRouterError as e:
# The base class for HTTP error responses
print(e.message)
print(e.status_code)
print(e.body)
print(e.headers)
print(e.raw_response)
# Depending on the method different errors may be thrown
if isinstance(e, errors.BadRequestResponseError):
print(e.data.error) # models.BadRequestResponseErrorData
print(e.data.user_id) # OptionalNullable[str]
Error Classes
Primary errors:
OpenRouterError: The base class for HTTP error responses.InternalServerResponseError: Internal Server Error - Unexpected server error. Status code500. *
Less common errors (19)
Network errors:
httpx.RequestError: Base class for request errors.httpx.ConnectError: HTTP client was unable to make a request to a server.httpx.TimeoutException: HTTP request timed out.
Inherit from OpenRouterError:
UnauthorizedResponseError: Unauthorized - Authentication required or invalid credentials. Status code401. Applicable to 15 of 24 methods.*BadRequestResponseError: Bad Request - Invalid request parameters or malformed input. Status code400. Applicable to 10 of 24 methods.*TooManyRequestsResponseError: Too Many Requests - Rate limit exceeded. Status code429. Applicable to 9 of 24 methods.*NotFoundResponseError: Not Found - Resource does not exist. Status code404. Applicable to 8 of 24 methods.*PaymentRequiredResponseError: Payment Required - Insufficient credits or quota to complete request. Status code402. Applicable to 3 of 24 methods.*ForbiddenResponseError: Forbidden - Authentication successful but insufficient permissions. Status code403. Applicable to 3 of 24 methods.*BadGatewayResponseError: Bad Gateway - Provider/upstream API failure. Status code502. Applicable to 3 of 24 methods.*EdgeNetworkTimeoutResponseError: Infrastructure Timeout - Provider request timed out at edge network. Status code524. Applicable to 3 of 24 methods.*ProviderOverloadedResponseError: Provider Overloaded - Provider is temporarily overloaded. Status code529. Applicable to 3 of 24 methods.*ChatError: Bad request - invalid parameters. Applicable to 2 of 24 methods.*ServiceUnavailableResponseError: Service Unavailable - Service temporarily unavailable. Status code503. Applicable to 2 of 24 methods.*RequestTimeoutResponseError: Request Timeout - Operation exceeded time limit. Status code408. Applicable to 1 of 24 methods.*PayloadTooLargeResponseError: Payload Too Large - Request payload exceeds size limits. Status code413. Applicable to 1 of 24 methods.*UnprocessableEntityResponseError: Unprocessable Entity - Semantic validation failure. Status code422. Applicable to 1 of 24 methods.*ResponseValidationError: Type mismatch between the response data and the expected Pydantic model. Provides access to the Pydantic validation error via thecauseattribute.
* Check the method documentation to see if the error is applicable.
Server Selection
Select Server by Name
You can override the default server globally by passing a server name to the server: str optional parameter when initializing the SDK client instance. The selected server will then be used as the default on the operations that use it. This table lists the names associated with the available servers:
| Name | Server | Description |
|---|---|---|
production |
https://openrouter.ai/api/v1 |
Production server |
Example
from openrouter import OpenRouter
import os
with OpenRouter(
server="production",
api_key=os.getenv("OPENROUTER_API_KEY", ""),
) as open_router:
res = open_router.beta.responses.send(input=[
{
"type": "message",
"role": "user",
"content": "Hello, how are you?",
},
], metadata={
"user_id": "123",
"session_id": "abc-def-ghi",
}, tools=[
{
"type": "function",
"name": "get_current_weather",
"description": "Get the current weather in a given location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
},
},
},
},
], model="anthropic/claude-4.5-sonnet-20250929", text={
"format_": {
"type": "text",
},
"verbosity": "medium",
}, reasoning={
"summary": "auto",
"enabled": True,
}, temperature=0.7, top_p=0.9, prompt={
"id": "<id>",
"variables": {
"key": {
"type": "input_text",
"text": "Hello, how can I help you?",
},
},
}, service_tier="auto", truncation="auto", stream=False, provider={
"data_collection": "deny",
"zdr": True,
"enforce_distillable_text": True,
"order": [
"OpenAI",
],
"only": [
"OpenAI",
],
"ignore": [
"OpenAI",
],
"quantizations": None,
"sort": "price",
})
with res as event_stream:
for event in event_stream:
# handle event
print(event, flush=True)
Override Server URL Per-Client
The default server can also be overridden globally by passing a URL to the server_url: str optional parameter when initializing the SDK client instance. For example:
from openrouter import OpenRouter
import os
with OpenRouter(
server_url="https://openrouter.ai/api/v1",
api_key=os.getenv("OPENROUTER_API_KEY", ""),
) as open_router:
res = open_router.beta.responses.send(input=[
{
"type": "message",
"role": "user",
"content": "Hello, how are you?",
},
], metadata={
"user_id": "123",
"session_id": "abc-def-ghi",
}, tools=[
{
"type": "function",
"name": "get_current_weather",
"description": "Get the current weather in a given location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
},
},
},
},
], model="anthropic/claude-4.5-sonnet-20250929", text={
"format_": {
"type": "text",
},
"verbosity": "medium",
}, reasoning={
"summary": "auto",
"enabled": True,
}, temperature=0.7, top_p=0.9, prompt={
"id": "<id>",
"variables": {
"key": {
"type": "input_text",
"text": "Hello, how can I help you?",
},
},
}, service_tier="auto", truncation="auto", stream=False, provider={
"data_collection": "deny",
"zdr": True,
"enforce_distillable_text": True,
"order": [
"OpenAI",
],
"only": [
"OpenAI",
],
"ignore": [
"OpenAI",
],
"quantizations": None,
"sort": "price",
})
with res as event_stream:
for event in event_stream:
# handle event
print(event, flush=True)
Custom HTTP Client
The Python SDK makes API calls using the httpx HTTP library. In order to provide a convenient way to configure timeouts, cookies, proxies, custom headers, and other low-level configuration, you can initialize the SDK client with your own HTTP client instance.
Depending on whether you are using the sync or async version of the SDK, you can pass an instance of HttpClient or AsyncHttpClient respectively, which are Protocol's ensuring that the client has the necessary methods to make API calls.
This allows you to wrap the client with your own custom logic, such as adding custom headers, logging, or error handling, or you can just pass an instance of httpx.Client or httpx.AsyncClient directly.
For example, you could specify a header for every request that this sdk makes as follows:
from openrouter import OpenRouter
import httpx
http_client = httpx.Client(headers={"x-custom-header": "someValue"})
s = OpenRouter(client=http_client)
or you could wrap the client with your own custom logic:
from openrouter import OpenRouter
from openrouter.httpclient import AsyncHttpClient
import httpx
class CustomClient(AsyncHttpClient):
client: AsyncHttpClient
def __init__(self, client: AsyncHttpClient):
self.client = client
async def send(
self,
request: httpx.Request,
*,
stream: bool = False,
auth: Union[
httpx._types.AuthTypes, httpx._client.UseClientDefault, None
] = httpx.USE_CLIENT_DEFAULT,
follow_redirects: Union[
bool, httpx._client.UseClientDefault
] = httpx.USE_CLIENT_DEFAULT,
) -> httpx.Response:
request.headers["Client-Level-Header"] = "added by client"
return await self.client.send(
request, stream=stream, auth=auth, follow_redirects=follow_redirects
)
def build_request(
self,
method: str,
url: httpx._types.URLTypes,
*,
content: Optional[httpx._types.RequestContent] = None,
data: Optional[httpx._types.RequestData] = None,
files: Optional[httpx._types.RequestFiles] = None,
json: Optional[Any] = None,
params: Optional[httpx._types.QueryParamTypes] = None,
headers: Optional[httpx._types.HeaderTypes] = None,
cookies: Optional[httpx._types.CookieTypes] = None,
timeout: Union[
httpx._types.TimeoutTypes, httpx._client.UseClientDefault
] = httpx.USE_CLIENT_DEFAULT,
extensions: Optional[httpx._types.RequestExtensions] = None,
) -> httpx.Request:
return self.client.build_request(
method,
url,
content=content,
data=data,
files=files,
json=json,
params=params,
headers=headers,
cookies=cookies,
timeout=timeout,
extensions=extensions,
)
s = OpenRouter(async_client=CustomClient(httpx.AsyncClient()))
Resource Management
The OpenRouter class implements the context manager protocol and registers a finalizer function to close the underlying sync and async HTTPX clients it uses under the hood. This will close HTTP connections, release memory and free up other resources held by the SDK. In short-lived Python programs and notebooks that make a few SDK method calls, resource management may not be a concern. However, in longer-lived programs, it is beneficial to create a single SDK instance via a context manager and reuse it across the application.
from openrouter import OpenRouter
import os
def main():
with OpenRouter(
api_key=os.getenv("OPENROUTER_API_KEY", ""),
) as open_router:
# Rest of application here...
# Or when using async:
async def amain():
async with OpenRouter(
api_key=os.getenv("OPENROUTER_API_KEY", ""),
) as open_router:
# Rest of application here...
Debugging
You can setup your SDK to emit debug logs for SDK requests and responses.
You can pass your own logger class directly into your SDK.
from openrouter import OpenRouter
import logging
logging.basicConfig(level=logging.DEBUG)
s = OpenRouter(debug_logger=logging.getLogger("openrouter"))
You can also enable a default debug logger by setting an environment variable OPENROUTER_DEBUG to true.
Development
Maturity
This SDK is in beta, and there may be breaking changes between versions without a major version update. Therefore, we recommend pinning usage to a specific package version. This way, you can install the same version each time without breaking changes unless you are intentionally looking for the latest version.
Contributions
While we value open-source contributions to this SDK, this library is generated programmatically. Any manual changes added to internal files will be overwritten on the next generation. We look forward to hearing your feedback. Feel free to open a PR or an issue with a proof of concept and we'll do our best to include it in a future release.