Add OpenRouterModel as OpenAIChatModel subclass

pydantic_ai_slim/pydantic_ai/models/openrouter.py

@@ -0,0 +1,267 @@
+from typing import Any, Literal, cast
+
+from openai import AsyncOpenAI
+from openai.types.chat import ChatCompletion
+from typing_extensions import TypedDict
+
+from ..messages import ModelResponse
+from ..profiles import ModelProfileSpec
+from ..providers import Provider
+from ..settings import ModelSettings
+from . import ModelRequestParameters
+from .openai import OpenAIChatModel, OpenAIChatModelSettings
+
+
+class OpenRouterMaxprice(TypedDict, total=False):
+    """The object specifying the maximum price you want to pay for this request. USD price per million tokens, for prompt and completion."""
+
+    prompt: int
+    completion: int
+    image: int
+    audio: int
+    request: int
+
+
+LatestOpenRouterSlugs = Literal[
+    'z-ai',
+    'cerebras',
+    'venice',
+    'moonshotai',
+    'morph',
+    'stealth',
+    'wandb',
+    'klusterai',
+    'openai',
+    'sambanova',
+    'amazon-bedrock',
+    'mistral',
+    'nextbit',
+    'atoma',
+    'ai21',
+    'minimax',
+    'baseten',
+    'anthropic',
+    'featherless',
+    'groq',
+    'lambda',
+    'azure',
+    'ncompass',
+    'deepseek',
+    'hyperbolic',
+    'crusoe',
+    'cohere',
+    'mancer',
+    'avian',
+    'perplexity',
+    'novita',
+    'siliconflow',
+    'switchpoint',
+    'xai',
+    'inflection',
+    'fireworks',
+    'deepinfra',
+    'inference-net',
+    'inception',
+    'atlas-cloud',
+    'nvidia',
+    'alibaba',
+    'friendli',
+    'infermatic',
+    'targon',
+    'ubicloud',
+    'aion-labs',
+    'liquid',
+    'nineteen',
+    'cloudflare',
+    'nebius',
+    'chutes',
+    'enfer',
+    'crofai',
+    'open-inference',
+    'phala',
+    'gmicloud',
+    'meta',
+    'relace',
+    'parasail',
+    'together',
+    'google-ai-studio',
+    'google-vertex',
+]
+"""Known providers in the OpenRouter marketplace"""
+
+OpenRouterSlug = str | LatestOpenRouterSlugs
+"""Possible OpenRouter provider slugs.
+
+Since OpenRouter is constantly updating their list of providers, we explicitly list some known providers but
+allow any name in the type hints.
+See [the OpenRouter API](https://openrouter.ai/docs/api-reference/list-available-providers) for a full list.
+"""
+
+Transforms = Literal['middle-out']
+"""Available messages transforms for OpenRouter models with limited token windows.
+
+Currently only supports 'middle-out', but is expected to grow in the future.
+"""
+
+
+class OpenRouterPreferences(TypedDict, total=False):
+    """Represents the 'Provider' object from the OpenRouter API."""
+
+    order: list[OpenRouterSlug]
+    """List of provider slugs to try in order (e.g. ["anthropic", "openai"]). [See details](https://openrouter.ai/docs/features/provider-routing#ordering-specific-providers)"""
+
+    allow_fallbacks: bool
+    """Whether to allow backup providers when the primary is unavailable. [See details](https://openrouter.ai/docs/features/provider-routing#disabling-fallbacks)"""
+
+    require_parameters: bool
+    """Only use providers that support all parameters in your request."""
+
+    data_collection: Literal['allow', 'deny']
+    """Control whether to use providers that may store data. [See details](https://openrouter.ai/docs/features/provider-routing#requiring-providers-to-comply-with-data-policies)"""
+
+    zdr: bool
+    """Restrict routing to only ZDR (Zero Data Retention) endpoints. [See details](https://openrouter.ai/docs/features/provider-routing#zero-data-retention-enforcement)"""
+
+    only: list[OpenRouterSlug]
+    """List of provider slugs to allow for this request. [See details](https://openrouter.ai/docs/features/provider-routing#allowing-only-specific-providers)"""
+
+    ignore: list[str]
+    """List of provider slugs to skip for this request. [See details](https://openrouter.ai/docs/features/provider-routing#ignoring-providers)"""
+
+    quantizations: list[Literal['int4', 'int8', 'fp4', 'fp6', 'fp8', 'fp16', 'bf16', 'fp32', 'unknown']]
+    """List of quantization levels to filter by (e.g. ["int4", "int8"]). [See details](https://openrouter.ai/docs/features/provider-routing#quantization)"""
+
+    sort: Literal['price', 'throughput', 'latency']
+    """Sort providers by price or throughput. (e.g. "price" or "throughput"). [See details](https://openrouter.ai/docs/features/provider-routing#provider-sorting)"""
+
+    max_price: OpenRouterMaxprice
+    """The maximum pricing you want to pay for this request. [See details](https://openrouter.ai/docs/features/provider-routing#max-price)"""
+
+
+class OpenRouterReasoning(TypedDict, total=False):
+    """Configuration for reasoning tokens in OpenRouter requests.
+
+    Reasoning tokens allow models to show their step-by-step thinking process.
+    You can configure this using either OpenAI-style effort levels or Anthropic-style
+    token limits, but not both simultaneously.
+    """
+
+    effort: Literal['high', 'medium', 'low']
+    """OpenAI-style reasoning effort level. Cannot be used with max_tokens."""
+
+    max_tokens: int
+    """Anthropic-style specific token limit for reasoning. Cannot be used with effort."""
+
+    exclude: bool
+    """Whether to exclude reasoning tokens from the response. Default is False. All models support this."""
+
+    enabled: bool
+    """Whether to enable reasoning with default parameters. Default is inferred from effort or max_tokens."""
+
+
+class OpenRouterModelSettings(ModelSettings, total=False):
+    """Settings used for an OpenRouter model request."""
+
+    # ALL FIELDS MUST BE `openrouter_` PREFIXED SO YOU CAN MERGE THEM WITH OTHER MODELS.
+
+    openrouter_models: list[str]
+    """A list of fallback models.
+
+    These models will be tried, in order, if the main model returns an error. [See details](https://openrouter.ai/docs/features/model-routing#the-models-parameter)
+    """
+
+    openrouter_preferences: OpenRouterPreferences
+    """OpenRouter routes requests to the best available providers for your model. By default, requests are load balanced across the top providers to maximize uptime.
+
+    You can customize how your requests are routed using the provider object. [See more](https://openrouter.ai/docs/features/provider-routing)"""
+
+    openrouter_preset: str
+    """Presets allow you to separate your LLM configuration from your code.
+
+    Create and manage presets through the OpenRouter web application to control provider routing, model selection, system prompts, and other parameters, then reference them in OpenRouter API requests. [See more](https://openrouter.ai/docs/features/presets)"""
+
+    openrouter_transforms: list[Transforms]
+    """To help with prompts that exceed the maximum context size of a model.
+
+    Transforms work by removing or truncating messages from the middle of the prompt, until the prompt fits within the model's context window. [See more](https://openrouter.ai/docs/features/message-transforms)
+    """
+
+    openrouter_reasoning: OpenRouterReasoning
+    """To control the reasoning tokens in the request.
+
+    The reasoning config object consolidates settings for controlling reasoning strength across different models. [See more](https://openrouter.ai/docs/use-cases/reasoning-tokens)
+    """
+
+
+def _openrouter_settings_to_openai_settings(model_settings: OpenRouterModelSettings) -> OpenAIChatModelSettings:
+    """Transforms a 'OpenRouterModelSettings' object into an 'OpenAIChatModelSettings' object.
+
+    Args:
+        model_settings: The 'OpenRouterModelSettings' object to transform.
+
+    Returns:
+        An 'OpenAIChatModelSettings' object with equivalent settings.
+    """
+    extra_body: dict[str, Any] = {}
+
+    if models := model_settings.get('openrouter_models'):
+        extra_body['models'] = models
+    if provider := model_settings.get('openrouter_preferences'):
+        extra_body['provider'] = provider
+    if preset := model_settings.get('openrouter_preset'):
+        extra_body['preset'] = preset
+    if transforms := model_settings.get('openrouter_transforms'):
+        extra_body['transforms'] = transforms
+
+    base_keys = ModelSettings.__annotations__.keys()
+    base_data: dict[str, Any] = {k: model_settings[k] for k in base_keys if k in model_settings}
+
+    new_settings = OpenAIChatModelSettings(**base_data, extra_body=extra_body)
+
+    return new_settings
+
+
+class OpenRouterModel(OpenAIChatModel):
+    """Extends OpenAIModel to capture extra metadata for Openrouter."""
+
+    def __init__(
+        self,
+        model_name: str,
+        *,
+        provider: Literal['openrouter'] | Provider[AsyncOpenAI] = 'openrouter',
+        profile: ModelProfileSpec | None = None,
+        settings: ModelSettings | None = None,
+    ):
+        """Initialize an OpenRouter model.
+
+        Args:
+            model_name: The name of the model to use.
+            provider: The provider to use for authentication and API access. Currently, uses OpenAI as the internal client. Can be either the string
+                'openrouter' or an instance of `Provider[AsyncOpenAI]`. If not provided, a new provider will be
+                created using the other parameters.
+            profile: The model profile to use. Defaults to a profile picked by the provider based on the model name.
+            settings: Model-specific settings that will be used as defaults for this model.
+        """
+        super().__init__(model_name, provider=provider, profile=profile, settings=settings)
+
+    def prepare_request(
+        self,
+        model_settings: ModelSettings | None,
+        model_request_parameters: ModelRequestParameters,
+    ) -> tuple[ModelSettings | None, ModelRequestParameters]:
+        merged_settings, customized_parameters = super().prepare_request(model_settings, model_request_parameters)
+        new_settings = _openrouter_settings_to_openai_settings(cast(OpenRouterModelSettings, merged_settings or {}))
+        return new_settings, customized_parameters
+
+    def _process_response(self, response: ChatCompletion | str) -> ModelResponse:
+        model_response = super()._process_response(response=response)
+        response = cast(ChatCompletion, response)  # If above did not raise an error, we can assume response != str
+
+        provider_details: dict[str, str] = {}
+
+        if openrouter_provider := getattr(response, 'provider', None):  # pragma: lax no cover
+            provider_details['downstream_provider'] = openrouter_provider
+
+        model_response.provider_details = provider_details
+
+        return model_response

pydantic_ai_slim/pydantic_ai/providers/openrouter.py

@@ -81,13 +81,21 @@ def __init__(self, *, api_key: str) -> None: ...
     @overload
     def __init__(self, *, api_key: str, http_client: httpx.AsyncClient) -> None: ...
 
+    @overload
+    def __init__(self, *, api_key: str, http_referer: str, x_title: str) -> None: ...
+
+    @overload
+    def __init__(self, *, api_key: str, http_referer: str, x_title: str, http_client: httpx.AsyncClient) -> None: ...
+
     @overload
     def __init__(self, *, openai_client: AsyncOpenAI | None = None) -> None: ...
 
     def __init__(
         self,
         *,
         api_key: str | None = None,
+        http_referer: str | None = None,
+        x_title: str | None = None,
         openai_client: AsyncOpenAI | None = None,
         http_client: httpx.AsyncClient | None = None,
     ) -> None:
@@ -98,10 +106,20 @@ def __init__(
                 'to use the OpenRouter provider.'
             )
 
+        attribution_headers: dict[str, str] = {}
+        if http_referer := http_referer or os.getenv('OPENROUTER_HTTP_REFERER'):
+            attribution_headers['HTTP-Referer'] = http_referer
+        if x_title := x_title or os.getenv('OPENROUTER_X_TITLE'):
+            attribution_headers['X-Title'] = x_title
+
         if openai_client is not None:
             self._client = openai_client
         elif http_client is not None:
-            self._client = AsyncOpenAI(base_url=self.base_url, api_key=api_key, http_client=http_client)
+            self._client = AsyncOpenAI(
+                base_url=self.base_url, api_key=api_key, http_client=http_client, default_headers=attribution_headers
+            )
         else:
             http_client = cached_async_http_client(provider='openrouter')
-            self._client = AsyncOpenAI(base_url=self.base_url, api_key=api_key, http_client=http_client)
+            self._client = AsyncOpenAI(
+                base_url=self.base_url, api_key=api_key, http_client=http_client, default_headers=attribution_headers
+            )