mirror of
https://github.com/wassname/openrouter-python-sdk-retry-errors.git
synced 2026-07-30 12:20:57 +08:00
1354 lines
67 KiB
Python
1354 lines
67 KiB
Python
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
|
|
|
from .basesdk import BaseSDK
|
|
from enum import Enum
|
|
from openrouter import components, errors, operations, utils
|
|
from openrouter._hooks import HookContext
|
|
from openrouter.types import OptionalNullable, UNSET
|
|
from openrouter.utils import eventstreaming, get_security_from_env
|
|
from openrouter.utils.unmarshal_json_response import unmarshal_json_response
|
|
from typing import Any, Dict, List, Literal, Mapping, Optional, Union, overload
|
|
|
|
|
|
class SendAcceptEnum(str, Enum):
|
|
APPLICATION_JSON = "application/json"
|
|
TEXT_EVENT_STREAM = "text/event-stream"
|
|
|
|
|
|
class Chat(BaseSDK):
|
|
@overload
|
|
def send(
|
|
self,
|
|
*,
|
|
messages: Union[
|
|
List[components.ChatMessages], List[components.ChatMessagesTypedDict]
|
|
],
|
|
http_referer: Optional[str] = None,
|
|
x_open_router_title: Optional[str] = None,
|
|
x_open_router_categories: Optional[str] = None,
|
|
cache_control: Optional[
|
|
Union[
|
|
components.AnthropicCacheControlDirective,
|
|
components.AnthropicCacheControlDirectiveTypedDict,
|
|
]
|
|
] = None,
|
|
debug: Optional[
|
|
Union[components.ChatDebugOptions, components.ChatDebugOptionsTypedDict]
|
|
] = None,
|
|
frequency_penalty: OptionalNullable[float] = UNSET,
|
|
image_config: Optional[
|
|
Union[
|
|
Dict[str, components.ImageConfig],
|
|
Dict[str, components.ImageConfigTypedDict],
|
|
]
|
|
] = None,
|
|
logit_bias: OptionalNullable[Dict[str, float]] = UNSET,
|
|
logprobs: OptionalNullable[bool] = UNSET,
|
|
max_completion_tokens: OptionalNullable[int] = UNSET,
|
|
max_tokens: OptionalNullable[int] = UNSET,
|
|
metadata: Optional[Dict[str, str]] = None,
|
|
modalities: Optional[List[components.Modality]] = None,
|
|
model: Optional[str] = None,
|
|
models: Optional[List[str]] = None,
|
|
parallel_tool_calls: OptionalNullable[bool] = UNSET,
|
|
plugins: Optional[
|
|
Union[
|
|
List[components.ChatRequestPlugin],
|
|
List[components.ChatRequestPluginTypedDict],
|
|
]
|
|
] = None,
|
|
presence_penalty: OptionalNullable[float] = UNSET,
|
|
provider: OptionalNullable[
|
|
Union[
|
|
components.ProviderPreferences, components.ProviderPreferencesTypedDict
|
|
]
|
|
] = UNSET,
|
|
reasoning: Optional[
|
|
Union[components.Reasoning, components.ReasoningTypedDict]
|
|
] = None,
|
|
response_format: Optional[
|
|
Union[components.ResponseFormat, components.ResponseFormatTypedDict]
|
|
] = None,
|
|
seed: OptionalNullable[int] = UNSET,
|
|
service_tier: OptionalNullable[components.ChatRequestServiceTier] = UNSET,
|
|
session_id: Optional[str] = None,
|
|
stop: OptionalNullable[
|
|
Union[components.Stop, components.StopTypedDict]
|
|
] = UNSET,
|
|
stream: Union[Literal[False], None] = None,
|
|
stream_options: OptionalNullable[
|
|
Union[components.ChatStreamOptions, components.ChatStreamOptionsTypedDict]
|
|
] = UNSET,
|
|
temperature: OptionalNullable[float] = UNSET,
|
|
tool_choice: Optional[
|
|
Union[components.ChatToolChoice, components.ChatToolChoiceTypedDict]
|
|
] = None,
|
|
tools: Optional[
|
|
Union[
|
|
List[components.ChatFunctionTool],
|
|
List[components.ChatFunctionToolTypedDict],
|
|
]
|
|
] = None,
|
|
top_logprobs: OptionalNullable[int] = UNSET,
|
|
top_p: OptionalNullable[float] = UNSET,
|
|
trace: Optional[
|
|
Union[components.TraceConfig, components.TraceConfigTypedDict]
|
|
] = None,
|
|
user: Optional[str] = None,
|
|
retries: OptionalNullable[utils.RetryConfig] = UNSET,
|
|
server_url: Optional[str] = None,
|
|
timeout_ms: Optional[int] = None,
|
|
http_headers: Optional[Mapping[str, str]] = None,
|
|
) -> components.ChatResult:
|
|
r"""Create a chat completion
|
|
|
|
Sends a request for a model response for the given chat conversation. Supports both streaming and non-streaming modes.
|
|
|
|
:param messages: List of messages for the conversation
|
|
:param http_referer: The app identifier should be your app's URL and is used as the primary identifier for rankings.
|
|
This is used to track API usage per application.
|
|
|
|
:param x_open_router_title: The app display name allows you to customize how your app appears in OpenRouter's dashboard.
|
|
|
|
:param x_open_router_categories: Comma-separated list of app categories (e.g. \"cli-agent,cloud-agent\"). Used for marketplace rankings.
|
|
|
|
:param cache_control:
|
|
:param debug: Debug options for inspecting request transformations (streaming only)
|
|
:param frequency_penalty: Frequency penalty (-2.0 to 2.0)
|
|
:param image_config: Provider-specific image configuration options. Keys and values vary by model/provider. See https://openrouter.ai/docs/guides/overview/multimodal/image-generation for more details.
|
|
:param logit_bias: Token logit bias adjustments
|
|
:param logprobs: Return log probabilities
|
|
:param max_completion_tokens: Maximum tokens in completion
|
|
:param max_tokens: Maximum tokens (deprecated, use max_completion_tokens). Note: some providers enforce a minimum of 16.
|
|
:param metadata: Key-value pairs for additional object information (max 16 pairs, 64 char keys, 512 char values)
|
|
:param modalities: Output modalities for the response. Supported values are \"text\", \"image\", and \"audio\".
|
|
:param model: Model to use for completion
|
|
:param models: Models to use for completion
|
|
:param parallel_tool_calls: Whether to enable parallel function calling during tool use. When true, the model may generate multiple tool calls in a single response.
|
|
:param plugins: Plugins you want to enable for this request, including their settings.
|
|
:param presence_penalty: Presence penalty (-2.0 to 2.0)
|
|
:param provider: When multiple model providers are available, optionally indicate your routing preference.
|
|
:param reasoning: Configuration options for reasoning models
|
|
:param response_format: Response format configuration
|
|
:param seed: Random seed for deterministic outputs
|
|
:param service_tier: The service tier to use for processing this request.
|
|
:param session_id: A unique identifier for grouping related requests (e.g., a conversation or agent workflow) for observability. If provided in both the request body and the x-session-id header, the body value takes precedence. Maximum of 256 characters.
|
|
:param stop: Stop sequences (up to 4)
|
|
:param stream: Enable streaming response
|
|
:param stream_options: Streaming configuration options
|
|
:param temperature: Sampling temperature (0-2)
|
|
:param tool_choice: Tool choice configuration
|
|
:param tools: Available tools for function calling
|
|
:param top_logprobs: Number of top log probabilities to return (0-20)
|
|
:param top_p: Nucleus sampling parameter (0-1)
|
|
:param trace: Metadata for observability and tracing. Known keys (trace_id, trace_name, span_name, generation_name, parent_span_id) have special handling. Additional keys are passed through as custom metadata to configured broadcast destinations.
|
|
:param user: Unique user identifier
|
|
:param retries: Override the default retry configuration for this method
|
|
:param server_url: Override the default server URL for this method
|
|
:param timeout_ms: Override the default request timeout configuration for this method in milliseconds
|
|
:param accept_header_override: Override the default accept header for this method
|
|
:param http_headers: Additional headers to set or replace on requests.
|
|
"""
|
|
|
|
@overload
|
|
def send(
|
|
self,
|
|
*,
|
|
messages: Union[
|
|
List[components.ChatMessages], List[components.ChatMessagesTypedDict]
|
|
],
|
|
http_referer: Optional[str] = None,
|
|
x_open_router_title: Optional[str] = None,
|
|
x_open_router_categories: Optional[str] = None,
|
|
cache_control: Optional[
|
|
Union[
|
|
components.AnthropicCacheControlDirective,
|
|
components.AnthropicCacheControlDirectiveTypedDict,
|
|
]
|
|
] = None,
|
|
debug: Optional[
|
|
Union[components.ChatDebugOptions, components.ChatDebugOptionsTypedDict]
|
|
] = None,
|
|
frequency_penalty: OptionalNullable[float] = UNSET,
|
|
image_config: Optional[
|
|
Union[
|
|
Dict[str, components.ImageConfig],
|
|
Dict[str, components.ImageConfigTypedDict],
|
|
]
|
|
] = None,
|
|
logit_bias: OptionalNullable[Dict[str, float]] = UNSET,
|
|
logprobs: OptionalNullable[bool] = UNSET,
|
|
max_completion_tokens: OptionalNullable[int] = UNSET,
|
|
max_tokens: OptionalNullable[int] = UNSET,
|
|
metadata: Optional[Dict[str, str]] = None,
|
|
modalities: Optional[List[components.Modality]] = None,
|
|
model: Optional[str] = None,
|
|
models: Optional[List[str]] = None,
|
|
parallel_tool_calls: OptionalNullable[bool] = UNSET,
|
|
plugins: Optional[
|
|
Union[
|
|
List[components.ChatRequestPlugin],
|
|
List[components.ChatRequestPluginTypedDict],
|
|
]
|
|
] = None,
|
|
presence_penalty: OptionalNullable[float] = UNSET,
|
|
provider: OptionalNullable[
|
|
Union[
|
|
components.ProviderPreferences, components.ProviderPreferencesTypedDict
|
|
]
|
|
] = UNSET,
|
|
reasoning: Optional[
|
|
Union[components.Reasoning, components.ReasoningTypedDict]
|
|
] = None,
|
|
response_format: Optional[
|
|
Union[components.ResponseFormat, components.ResponseFormatTypedDict]
|
|
] = None,
|
|
seed: OptionalNullable[int] = UNSET,
|
|
service_tier: OptionalNullable[components.ChatRequestServiceTier] = UNSET,
|
|
session_id: Optional[str] = None,
|
|
stop: OptionalNullable[
|
|
Union[components.Stop, components.StopTypedDict]
|
|
] = UNSET,
|
|
stream: Literal[True],
|
|
stream_options: OptionalNullable[
|
|
Union[components.ChatStreamOptions, components.ChatStreamOptionsTypedDict]
|
|
] = UNSET,
|
|
temperature: OptionalNullable[float] = UNSET,
|
|
tool_choice: Optional[
|
|
Union[components.ChatToolChoice, components.ChatToolChoiceTypedDict]
|
|
] = None,
|
|
tools: Optional[
|
|
Union[
|
|
List[components.ChatFunctionTool],
|
|
List[components.ChatFunctionToolTypedDict],
|
|
]
|
|
] = None,
|
|
top_logprobs: OptionalNullable[int] = UNSET,
|
|
top_p: OptionalNullable[float] = UNSET,
|
|
trace: Optional[
|
|
Union[components.TraceConfig, components.TraceConfigTypedDict]
|
|
] = None,
|
|
user: Optional[str] = None,
|
|
retries: OptionalNullable[utils.RetryConfig] = UNSET,
|
|
server_url: Optional[str] = None,
|
|
timeout_ms: Optional[int] = None,
|
|
http_headers: Optional[Mapping[str, str]] = None,
|
|
) -> eventstreaming.EventStream[components.ChatStreamChunk]:
|
|
r"""Create a chat completion
|
|
|
|
Sends a request for a model response for the given chat conversation. Supports both streaming and non-streaming modes.
|
|
|
|
:param messages: List of messages for the conversation
|
|
:param http_referer: The app identifier should be your app's URL and is used as the primary identifier for rankings.
|
|
This is used to track API usage per application.
|
|
|
|
:param x_open_router_title: The app display name allows you to customize how your app appears in OpenRouter's dashboard.
|
|
|
|
:param x_open_router_categories: Comma-separated list of app categories (e.g. \"cli-agent,cloud-agent\"). Used for marketplace rankings.
|
|
|
|
:param cache_control:
|
|
:param debug: Debug options for inspecting request transformations (streaming only)
|
|
:param frequency_penalty: Frequency penalty (-2.0 to 2.0)
|
|
:param image_config: Provider-specific image configuration options. Keys and values vary by model/provider. See https://openrouter.ai/docs/guides/overview/multimodal/image-generation for more details.
|
|
:param logit_bias: Token logit bias adjustments
|
|
:param logprobs: Return log probabilities
|
|
:param max_completion_tokens: Maximum tokens in completion
|
|
:param max_tokens: Maximum tokens (deprecated, use max_completion_tokens). Note: some providers enforce a minimum of 16.
|
|
:param metadata: Key-value pairs for additional object information (max 16 pairs, 64 char keys, 512 char values)
|
|
:param modalities: Output modalities for the response. Supported values are \"text\", \"image\", and \"audio\".
|
|
:param model: Model to use for completion
|
|
:param models: Models to use for completion
|
|
:param parallel_tool_calls: Whether to enable parallel function calling during tool use. When true, the model may generate multiple tool calls in a single response.
|
|
:param plugins: Plugins you want to enable for this request, including their settings.
|
|
:param presence_penalty: Presence penalty (-2.0 to 2.0)
|
|
:param provider: When multiple model providers are available, optionally indicate your routing preference.
|
|
:param reasoning: Configuration options for reasoning models
|
|
:param response_format: Response format configuration
|
|
:param seed: Random seed for deterministic outputs
|
|
:param service_tier: The service tier to use for processing this request.
|
|
:param session_id: A unique identifier for grouping related requests (e.g., a conversation or agent workflow) for observability. If provided in both the request body and the x-session-id header, the body value takes precedence. Maximum of 256 characters.
|
|
:param stop: Stop sequences (up to 4)
|
|
:param stream: Enable streaming response
|
|
:param stream_options: Streaming configuration options
|
|
:param temperature: Sampling temperature (0-2)
|
|
:param tool_choice: Tool choice configuration
|
|
:param tools: Available tools for function calling
|
|
:param top_logprobs: Number of top log probabilities to return (0-20)
|
|
:param top_p: Nucleus sampling parameter (0-1)
|
|
:param trace: Metadata for observability and tracing. Known keys (trace_id, trace_name, span_name, generation_name, parent_span_id) have special handling. Additional keys are passed through as custom metadata to configured broadcast destinations.
|
|
:param user: Unique user identifier
|
|
:param retries: Override the default retry configuration for this method
|
|
:param server_url: Override the default server URL for this method
|
|
:param timeout_ms: Override the default request timeout configuration for this method in milliseconds
|
|
:param accept_header_override: Override the default accept header for this method
|
|
:param http_headers: Additional headers to set or replace on requests.
|
|
"""
|
|
|
|
def send(
|
|
self,
|
|
*,
|
|
messages: Union[
|
|
List[components.ChatMessages], List[components.ChatMessagesTypedDict]
|
|
],
|
|
http_referer: Optional[str] = None,
|
|
x_open_router_title: Optional[str] = None,
|
|
x_open_router_categories: Optional[str] = None,
|
|
cache_control: Optional[
|
|
Union[
|
|
components.AnthropicCacheControlDirective,
|
|
components.AnthropicCacheControlDirectiveTypedDict,
|
|
]
|
|
] = None,
|
|
debug: Optional[
|
|
Union[components.ChatDebugOptions, components.ChatDebugOptionsTypedDict]
|
|
] = None,
|
|
frequency_penalty: OptionalNullable[float] = UNSET,
|
|
image_config: Optional[
|
|
Union[
|
|
Dict[str, components.ImageConfig],
|
|
Dict[str, components.ImageConfigTypedDict],
|
|
]
|
|
] = None,
|
|
logit_bias: OptionalNullable[Dict[str, float]] = UNSET,
|
|
logprobs: OptionalNullable[bool] = UNSET,
|
|
max_completion_tokens: OptionalNullable[int] = UNSET,
|
|
max_tokens: OptionalNullable[int] = UNSET,
|
|
metadata: Optional[Dict[str, str]] = None,
|
|
modalities: Optional[List[components.Modality]] = None,
|
|
model: Optional[str] = None,
|
|
models: Optional[List[str]] = None,
|
|
parallel_tool_calls: OptionalNullable[bool] = UNSET,
|
|
plugins: Optional[
|
|
Union[
|
|
List[components.ChatRequestPlugin],
|
|
List[components.ChatRequestPluginTypedDict],
|
|
]
|
|
] = None,
|
|
presence_penalty: OptionalNullable[float] = UNSET,
|
|
provider: OptionalNullable[
|
|
Union[
|
|
components.ProviderPreferences, components.ProviderPreferencesTypedDict
|
|
]
|
|
] = UNSET,
|
|
reasoning: Optional[
|
|
Union[components.Reasoning, components.ReasoningTypedDict]
|
|
] = None,
|
|
response_format: Optional[
|
|
Union[components.ResponseFormat, components.ResponseFormatTypedDict]
|
|
] = None,
|
|
seed: OptionalNullable[int] = UNSET,
|
|
service_tier: OptionalNullable[components.ChatRequestServiceTier] = UNSET,
|
|
session_id: Optional[str] = None,
|
|
stop: OptionalNullable[
|
|
Union[components.Stop, components.StopTypedDict]
|
|
] = UNSET,
|
|
stream: Optional[bool] = False,
|
|
stream_options: OptionalNullable[
|
|
Union[components.ChatStreamOptions, components.ChatStreamOptionsTypedDict]
|
|
] = UNSET,
|
|
temperature: OptionalNullable[float] = UNSET,
|
|
tool_choice: Optional[
|
|
Union[components.ChatToolChoice, components.ChatToolChoiceTypedDict]
|
|
] = None,
|
|
tools: Optional[
|
|
Union[
|
|
List[components.ChatFunctionTool],
|
|
List[components.ChatFunctionToolTypedDict],
|
|
]
|
|
] = None,
|
|
top_logprobs: OptionalNullable[int] = UNSET,
|
|
top_p: OptionalNullable[float] = UNSET,
|
|
trace: Optional[
|
|
Union[components.TraceConfig, components.TraceConfigTypedDict]
|
|
] = None,
|
|
user: Optional[str] = None,
|
|
retries: OptionalNullable[utils.RetryConfig] = UNSET,
|
|
server_url: Optional[str] = None,
|
|
timeout_ms: Optional[int] = None,
|
|
http_headers: Optional[Mapping[str, str]] = None,
|
|
) -> operations.SendChatCompletionRequestResponse:
|
|
r"""Create a chat completion
|
|
|
|
Sends a request for a model response for the given chat conversation. Supports both streaming and non-streaming modes.
|
|
|
|
:param messages: List of messages for the conversation
|
|
:param http_referer: The app identifier should be your app's URL and is used as the primary identifier for rankings.
|
|
This is used to track API usage per application.
|
|
|
|
:param x_open_router_title: The app display name allows you to customize how your app appears in OpenRouter's dashboard.
|
|
|
|
:param x_open_router_categories: Comma-separated list of app categories (e.g. \"cli-agent,cloud-agent\"). Used for marketplace rankings.
|
|
|
|
:param cache_control:
|
|
:param debug: Debug options for inspecting request transformations (streaming only)
|
|
:param frequency_penalty: Frequency penalty (-2.0 to 2.0)
|
|
:param image_config: Provider-specific image configuration options. Keys and values vary by model/provider. See https://openrouter.ai/docs/guides/overview/multimodal/image-generation for more details.
|
|
:param logit_bias: Token logit bias adjustments
|
|
:param logprobs: Return log probabilities
|
|
:param max_completion_tokens: Maximum tokens in completion
|
|
:param max_tokens: Maximum tokens (deprecated, use max_completion_tokens). Note: some providers enforce a minimum of 16.
|
|
:param metadata: Key-value pairs for additional object information (max 16 pairs, 64 char keys, 512 char values)
|
|
:param modalities: Output modalities for the response. Supported values are \"text\", \"image\", and \"audio\".
|
|
:param model: Model to use for completion
|
|
:param models: Models to use for completion
|
|
:param parallel_tool_calls: Whether to enable parallel function calling during tool use. When true, the model may generate multiple tool calls in a single response.
|
|
:param plugins: Plugins you want to enable for this request, including their settings.
|
|
:param presence_penalty: Presence penalty (-2.0 to 2.0)
|
|
:param provider: When multiple model providers are available, optionally indicate your routing preference.
|
|
:param reasoning: Configuration options for reasoning models
|
|
:param response_format: Response format configuration
|
|
:param seed: Random seed for deterministic outputs
|
|
:param service_tier: The service tier to use for processing this request.
|
|
:param session_id: A unique identifier for grouping related requests (e.g., a conversation or agent workflow) for observability. If provided in both the request body and the x-session-id header, the body value takes precedence. Maximum of 256 characters.
|
|
:param stop: Stop sequences (up to 4)
|
|
:param stream: Enable streaming response
|
|
:param stream_options: Streaming configuration options
|
|
:param temperature: Sampling temperature (0-2)
|
|
:param tool_choice: Tool choice configuration
|
|
:param tools: Available tools for function calling
|
|
:param top_logprobs: Number of top log probabilities to return (0-20)
|
|
:param top_p: Nucleus sampling parameter (0-1)
|
|
:param trace: Metadata for observability and tracing. Known keys (trace_id, trace_name, span_name, generation_name, parent_span_id) have special handling. Additional keys are passed through as custom metadata to configured broadcast destinations.
|
|
:param user: Unique user identifier
|
|
:param retries: Override the default retry configuration for this method
|
|
:param server_url: Override the default server URL for this method
|
|
:param timeout_ms: Override the default request timeout configuration for this method in milliseconds
|
|
:param accept_header_override: Override the default accept header for this method
|
|
:param http_headers: Additional headers to set or replace on requests.
|
|
"""
|
|
base_url = None
|
|
url_variables = None
|
|
if timeout_ms is None:
|
|
timeout_ms = self.sdk_configuration.timeout_ms
|
|
|
|
if server_url is not None:
|
|
base_url = server_url
|
|
else:
|
|
base_url = self._get_url(base_url, url_variables)
|
|
|
|
request = operations.SendChatCompletionRequestRequest(
|
|
http_referer=http_referer,
|
|
x_open_router_title=x_open_router_title,
|
|
x_open_router_categories=x_open_router_categories,
|
|
chat_request=components.ChatRequest(
|
|
cache_control=utils.get_pydantic_model(
|
|
cache_control, Optional[components.AnthropicCacheControlDirective]
|
|
),
|
|
debug=utils.get_pydantic_model(
|
|
debug, Optional[components.ChatDebugOptions]
|
|
),
|
|
frequency_penalty=frequency_penalty,
|
|
image_config=image_config,
|
|
logit_bias=logit_bias,
|
|
logprobs=logprobs,
|
|
max_completion_tokens=max_completion_tokens,
|
|
max_tokens=max_tokens,
|
|
messages=utils.get_pydantic_model(
|
|
messages, List[components.ChatMessages]
|
|
),
|
|
metadata=metadata,
|
|
modalities=modalities,
|
|
model=model,
|
|
models=models,
|
|
parallel_tool_calls=parallel_tool_calls,
|
|
plugins=utils.get_pydantic_model(
|
|
plugins, Optional[List[components.ChatRequestPlugin]]
|
|
),
|
|
presence_penalty=presence_penalty,
|
|
provider=utils.get_pydantic_model(
|
|
provider, OptionalNullable[components.ProviderPreferences]
|
|
),
|
|
reasoning=utils.get_pydantic_model(
|
|
reasoning, Optional[components.Reasoning]
|
|
),
|
|
response_format=utils.get_pydantic_model(
|
|
response_format, Optional[components.ResponseFormat]
|
|
),
|
|
seed=seed,
|
|
service_tier=service_tier,
|
|
session_id=session_id,
|
|
stop=stop,
|
|
stream=stream,
|
|
stream_options=utils.get_pydantic_model(
|
|
stream_options, OptionalNullable[components.ChatStreamOptions]
|
|
),
|
|
temperature=temperature,
|
|
tool_choice=utils.get_pydantic_model(
|
|
tool_choice, Optional[components.ChatToolChoice]
|
|
),
|
|
tools=utils.get_pydantic_model(
|
|
tools, Optional[List[components.ChatFunctionTool]]
|
|
),
|
|
top_logprobs=top_logprobs,
|
|
top_p=top_p,
|
|
trace=utils.get_pydantic_model(trace, Optional[components.TraceConfig]),
|
|
user=user,
|
|
),
|
|
)
|
|
|
|
req = self._build_request(
|
|
method="POST",
|
|
path="/chat/completions",
|
|
base_url=base_url,
|
|
url_variables=url_variables,
|
|
request=request,
|
|
request_body_required=True,
|
|
request_has_path_params=False,
|
|
request_has_query_params=True,
|
|
user_agent_header="user-agent",
|
|
accept_header_value="text/event-stream" if stream else "application/json",
|
|
http_headers=http_headers,
|
|
_globals=operations.SendChatCompletionRequestGlobals(
|
|
http_referer=self.sdk_configuration.globals.http_referer,
|
|
x_open_router_title=self.sdk_configuration.globals.x_open_router_title,
|
|
x_open_router_categories=self.sdk_configuration.globals.x_open_router_categories,
|
|
),
|
|
security=self.sdk_configuration.security,
|
|
get_serialized_body=lambda: utils.serialize_request_body(
|
|
request.chat_request, False, False, "json", components.ChatRequest
|
|
),
|
|
allow_empty_value=None,
|
|
timeout_ms=timeout_ms,
|
|
)
|
|
|
|
if retries == UNSET:
|
|
if self.sdk_configuration.retry_config is not UNSET:
|
|
retries = self.sdk_configuration.retry_config
|
|
else:
|
|
retries = utils.RetryConfig(
|
|
"backoff", utils.BackoffStrategy(500, 60000, 1.5, 3600000), True
|
|
)
|
|
|
|
retry_config = None
|
|
if isinstance(retries, utils.RetryConfig):
|
|
retry_config = (retries, ["5XX"])
|
|
|
|
http_res = self.do_request(
|
|
hook_ctx=HookContext(
|
|
config=self.sdk_configuration,
|
|
base_url=base_url or "",
|
|
operation_id="sendChatCompletionRequest",
|
|
oauth2_scopes=None,
|
|
security_source=get_security_from_env(
|
|
self.sdk_configuration.security, components.Security
|
|
),
|
|
),
|
|
request=req,
|
|
error_status_codes=[
|
|
"400",
|
|
"401",
|
|
"402",
|
|
"404",
|
|
"408",
|
|
"413",
|
|
"422",
|
|
"429",
|
|
"4XX",
|
|
"500",
|
|
"502",
|
|
"503",
|
|
"524",
|
|
"529",
|
|
"5XX",
|
|
],
|
|
stream=True,
|
|
retry_config=retry_config,
|
|
)
|
|
|
|
response_data: Any = None
|
|
if utils.match_response(http_res, "200", "application/json"):
|
|
http_res_text = utils.stream_to_text(http_res)
|
|
return unmarshal_json_response(
|
|
components.ChatResult, http_res, http_res_text
|
|
)
|
|
if utils.match_response(http_res, "200", "text/event-stream"):
|
|
return eventstreaming.EventStream(
|
|
http_res,
|
|
lambda raw: utils.unmarshal_json(
|
|
raw, operations.SendChatCompletionRequestResponseBody
|
|
).data,
|
|
sentinel="[DONE]",
|
|
client_ref=self,
|
|
)
|
|
if utils.match_response(http_res, "400", "application/json"):
|
|
http_res_text = utils.stream_to_text(http_res)
|
|
response_data = unmarshal_json_response(
|
|
errors.BadRequestResponseErrorData, http_res, http_res_text
|
|
)
|
|
raise errors.BadRequestResponseError(response_data, http_res, http_res_text)
|
|
if utils.match_response(http_res, "401", "application/json"):
|
|
http_res_text = utils.stream_to_text(http_res)
|
|
response_data = unmarshal_json_response(
|
|
errors.UnauthorizedResponseErrorData, http_res, http_res_text
|
|
)
|
|
raise errors.UnauthorizedResponseError(
|
|
response_data, http_res, http_res_text
|
|
)
|
|
if utils.match_response(http_res, "402", "application/json"):
|
|
http_res_text = utils.stream_to_text(http_res)
|
|
response_data = unmarshal_json_response(
|
|
errors.PaymentRequiredResponseErrorData, http_res, http_res_text
|
|
)
|
|
raise errors.PaymentRequiredResponseError(
|
|
response_data, http_res, http_res_text
|
|
)
|
|
if utils.match_response(http_res, "404", "application/json"):
|
|
http_res_text = utils.stream_to_text(http_res)
|
|
response_data = unmarshal_json_response(
|
|
errors.NotFoundResponseErrorData, http_res, http_res_text
|
|
)
|
|
raise errors.NotFoundResponseError(response_data, http_res, http_res_text)
|
|
if utils.match_response(http_res, "408", "application/json"):
|
|
http_res_text = utils.stream_to_text(http_res)
|
|
response_data = unmarshal_json_response(
|
|
errors.RequestTimeoutResponseErrorData, http_res, http_res_text
|
|
)
|
|
raise errors.RequestTimeoutResponseError(
|
|
response_data, http_res, http_res_text
|
|
)
|
|
if utils.match_response(http_res, "413", "application/json"):
|
|
http_res_text = utils.stream_to_text(http_res)
|
|
response_data = unmarshal_json_response(
|
|
errors.PayloadTooLargeResponseErrorData, http_res, http_res_text
|
|
)
|
|
raise errors.PayloadTooLargeResponseError(
|
|
response_data, http_res, http_res_text
|
|
)
|
|
if utils.match_response(http_res, "422", "application/json"):
|
|
http_res_text = utils.stream_to_text(http_res)
|
|
response_data = unmarshal_json_response(
|
|
errors.UnprocessableEntityResponseErrorData, http_res, http_res_text
|
|
)
|
|
raise errors.UnprocessableEntityResponseError(
|
|
response_data, http_res, http_res_text
|
|
)
|
|
if utils.match_response(http_res, "429", "application/json"):
|
|
http_res_text = utils.stream_to_text(http_res)
|
|
response_data = unmarshal_json_response(
|
|
errors.TooManyRequestsResponseErrorData, http_res, http_res_text
|
|
)
|
|
raise errors.TooManyRequestsResponseError(
|
|
response_data, http_res, http_res_text
|
|
)
|
|
if utils.match_response(http_res, "500", "application/json"):
|
|
http_res_text = utils.stream_to_text(http_res)
|
|
response_data = unmarshal_json_response(
|
|
errors.InternalServerResponseErrorData, http_res, http_res_text
|
|
)
|
|
raise errors.InternalServerResponseError(
|
|
response_data, http_res, http_res_text
|
|
)
|
|
if utils.match_response(http_res, "502", "application/json"):
|
|
http_res_text = utils.stream_to_text(http_res)
|
|
response_data = unmarshal_json_response(
|
|
errors.BadGatewayResponseErrorData, http_res, http_res_text
|
|
)
|
|
raise errors.BadGatewayResponseError(response_data, http_res, http_res_text)
|
|
if utils.match_response(http_res, "503", "application/json"):
|
|
http_res_text = utils.stream_to_text(http_res)
|
|
response_data = unmarshal_json_response(
|
|
errors.ServiceUnavailableResponseErrorData, http_res, http_res_text
|
|
)
|
|
raise errors.ServiceUnavailableResponseError(
|
|
response_data, http_res, http_res_text
|
|
)
|
|
if utils.match_response(http_res, "524", "application/json"):
|
|
http_res_text = utils.stream_to_text(http_res)
|
|
response_data = unmarshal_json_response(
|
|
errors.EdgeNetworkTimeoutResponseErrorData, http_res, http_res_text
|
|
)
|
|
raise errors.EdgeNetworkTimeoutResponseError(
|
|
response_data, http_res, http_res_text
|
|
)
|
|
if utils.match_response(http_res, "529", "application/json"):
|
|
http_res_text = utils.stream_to_text(http_res)
|
|
response_data = unmarshal_json_response(
|
|
errors.ProviderOverloadedResponseErrorData, http_res, http_res_text
|
|
)
|
|
raise errors.ProviderOverloadedResponseError(
|
|
response_data, http_res, http_res_text
|
|
)
|
|
if utils.match_response(http_res, "4XX", "*"):
|
|
http_res_text = utils.stream_to_text(http_res)
|
|
raise errors.OpenRouterDefaultError(
|
|
"API error occurred", http_res, http_res_text
|
|
)
|
|
if utils.match_response(http_res, "5XX", "*"):
|
|
http_res_text = utils.stream_to_text(http_res)
|
|
raise errors.OpenRouterDefaultError(
|
|
"API error occurred", http_res, http_res_text
|
|
)
|
|
|
|
http_res_text = utils.stream_to_text(http_res)
|
|
raise errors.OpenRouterDefaultError(
|
|
"Unexpected response received", http_res, http_res_text
|
|
)
|
|
|
|
@overload
|
|
async def send_async(
|
|
self,
|
|
*,
|
|
messages: Union[
|
|
List[components.ChatMessages], List[components.ChatMessagesTypedDict]
|
|
],
|
|
http_referer: Optional[str] = None,
|
|
x_open_router_title: Optional[str] = None,
|
|
x_open_router_categories: Optional[str] = None,
|
|
cache_control: Optional[
|
|
Union[
|
|
components.AnthropicCacheControlDirective,
|
|
components.AnthropicCacheControlDirectiveTypedDict,
|
|
]
|
|
] = None,
|
|
debug: Optional[
|
|
Union[components.ChatDebugOptions, components.ChatDebugOptionsTypedDict]
|
|
] = None,
|
|
frequency_penalty: OptionalNullable[float] = UNSET,
|
|
image_config: Optional[
|
|
Union[
|
|
Dict[str, components.ImageConfig],
|
|
Dict[str, components.ImageConfigTypedDict],
|
|
]
|
|
] = None,
|
|
logit_bias: OptionalNullable[Dict[str, float]] = UNSET,
|
|
logprobs: OptionalNullable[bool] = UNSET,
|
|
max_completion_tokens: OptionalNullable[int] = UNSET,
|
|
max_tokens: OptionalNullable[int] = UNSET,
|
|
metadata: Optional[Dict[str, str]] = None,
|
|
modalities: Optional[List[components.Modality]] = None,
|
|
model: Optional[str] = None,
|
|
models: Optional[List[str]] = None,
|
|
parallel_tool_calls: OptionalNullable[bool] = UNSET,
|
|
plugins: Optional[
|
|
Union[
|
|
List[components.ChatRequestPlugin],
|
|
List[components.ChatRequestPluginTypedDict],
|
|
]
|
|
] = None,
|
|
presence_penalty: OptionalNullable[float] = UNSET,
|
|
provider: OptionalNullable[
|
|
Union[
|
|
components.ProviderPreferences, components.ProviderPreferencesTypedDict
|
|
]
|
|
] = UNSET,
|
|
reasoning: Optional[
|
|
Union[components.Reasoning, components.ReasoningTypedDict]
|
|
] = None,
|
|
response_format: Optional[
|
|
Union[components.ResponseFormat, components.ResponseFormatTypedDict]
|
|
] = None,
|
|
seed: OptionalNullable[int] = UNSET,
|
|
service_tier: OptionalNullable[components.ChatRequestServiceTier] = UNSET,
|
|
session_id: Optional[str] = None,
|
|
stop: OptionalNullable[
|
|
Union[components.Stop, components.StopTypedDict]
|
|
] = UNSET,
|
|
stream: Union[Literal[False], None] = None,
|
|
stream_options: OptionalNullable[
|
|
Union[components.ChatStreamOptions, components.ChatStreamOptionsTypedDict]
|
|
] = UNSET,
|
|
temperature: OptionalNullable[float] = UNSET,
|
|
tool_choice: Optional[
|
|
Union[components.ChatToolChoice, components.ChatToolChoiceTypedDict]
|
|
] = None,
|
|
tools: Optional[
|
|
Union[
|
|
List[components.ChatFunctionTool],
|
|
List[components.ChatFunctionToolTypedDict],
|
|
]
|
|
] = None,
|
|
top_logprobs: OptionalNullable[int] = UNSET,
|
|
top_p: OptionalNullable[float] = UNSET,
|
|
trace: Optional[
|
|
Union[components.TraceConfig, components.TraceConfigTypedDict]
|
|
] = None,
|
|
user: Optional[str] = None,
|
|
retries: OptionalNullable[utils.RetryConfig] = UNSET,
|
|
server_url: Optional[str] = None,
|
|
timeout_ms: Optional[int] = None,
|
|
http_headers: Optional[Mapping[str, str]] = None,
|
|
) -> components.ChatResult:
|
|
r"""Create a chat completion
|
|
|
|
Sends a request for a model response for the given chat conversation. Supports both streaming and non-streaming modes.
|
|
|
|
:param messages: List of messages for the conversation
|
|
:param http_referer: The app identifier should be your app's URL and is used as the primary identifier for rankings.
|
|
This is used to track API usage per application.
|
|
|
|
:param x_open_router_title: The app display name allows you to customize how your app appears in OpenRouter's dashboard.
|
|
|
|
:param x_open_router_categories: Comma-separated list of app categories (e.g. \"cli-agent,cloud-agent\"). Used for marketplace rankings.
|
|
|
|
:param cache_control:
|
|
:param debug: Debug options for inspecting request transformations (streaming only)
|
|
:param frequency_penalty: Frequency penalty (-2.0 to 2.0)
|
|
:param image_config: Provider-specific image configuration options. Keys and values vary by model/provider. See https://openrouter.ai/docs/guides/overview/multimodal/image-generation for more details.
|
|
:param logit_bias: Token logit bias adjustments
|
|
:param logprobs: Return log probabilities
|
|
:param max_completion_tokens: Maximum tokens in completion
|
|
:param max_tokens: Maximum tokens (deprecated, use max_completion_tokens). Note: some providers enforce a minimum of 16.
|
|
:param metadata: Key-value pairs for additional object information (max 16 pairs, 64 char keys, 512 char values)
|
|
:param modalities: Output modalities for the response. Supported values are \"text\", \"image\", and \"audio\".
|
|
:param model: Model to use for completion
|
|
:param models: Models to use for completion
|
|
:param parallel_tool_calls: Whether to enable parallel function calling during tool use. When true, the model may generate multiple tool calls in a single response.
|
|
:param plugins: Plugins you want to enable for this request, including their settings.
|
|
:param presence_penalty: Presence penalty (-2.0 to 2.0)
|
|
:param provider: When multiple model providers are available, optionally indicate your routing preference.
|
|
:param reasoning: Configuration options for reasoning models
|
|
:param response_format: Response format configuration
|
|
:param seed: Random seed for deterministic outputs
|
|
:param service_tier: The service tier to use for processing this request.
|
|
:param session_id: A unique identifier for grouping related requests (e.g., a conversation or agent workflow) for observability. If provided in both the request body and the x-session-id header, the body value takes precedence. Maximum of 256 characters.
|
|
:param stop: Stop sequences (up to 4)
|
|
:param stream: Enable streaming response
|
|
:param stream_options: Streaming configuration options
|
|
:param temperature: Sampling temperature (0-2)
|
|
:param tool_choice: Tool choice configuration
|
|
:param tools: Available tools for function calling
|
|
:param top_logprobs: Number of top log probabilities to return (0-20)
|
|
:param top_p: Nucleus sampling parameter (0-1)
|
|
:param trace: Metadata for observability and tracing. Known keys (trace_id, trace_name, span_name, generation_name, parent_span_id) have special handling. Additional keys are passed through as custom metadata to configured broadcast destinations.
|
|
:param user: Unique user identifier
|
|
:param retries: Override the default retry configuration for this method
|
|
:param server_url: Override the default server URL for this method
|
|
:param timeout_ms: Override the default request timeout configuration for this method in milliseconds
|
|
:param accept_header_override: Override the default accept header for this method
|
|
:param http_headers: Additional headers to set or replace on requests.
|
|
"""
|
|
|
|
@overload
|
|
async def send_async(
|
|
self,
|
|
*,
|
|
messages: Union[
|
|
List[components.ChatMessages], List[components.ChatMessagesTypedDict]
|
|
],
|
|
http_referer: Optional[str] = None,
|
|
x_open_router_title: Optional[str] = None,
|
|
x_open_router_categories: Optional[str] = None,
|
|
cache_control: Optional[
|
|
Union[
|
|
components.AnthropicCacheControlDirective,
|
|
components.AnthropicCacheControlDirectiveTypedDict,
|
|
]
|
|
] = None,
|
|
debug: Optional[
|
|
Union[components.ChatDebugOptions, components.ChatDebugOptionsTypedDict]
|
|
] = None,
|
|
frequency_penalty: OptionalNullable[float] = UNSET,
|
|
image_config: Optional[
|
|
Union[
|
|
Dict[str, components.ImageConfig],
|
|
Dict[str, components.ImageConfigTypedDict],
|
|
]
|
|
] = None,
|
|
logit_bias: OptionalNullable[Dict[str, float]] = UNSET,
|
|
logprobs: OptionalNullable[bool] = UNSET,
|
|
max_completion_tokens: OptionalNullable[int] = UNSET,
|
|
max_tokens: OptionalNullable[int] = UNSET,
|
|
metadata: Optional[Dict[str, str]] = None,
|
|
modalities: Optional[List[components.Modality]] = None,
|
|
model: Optional[str] = None,
|
|
models: Optional[List[str]] = None,
|
|
parallel_tool_calls: OptionalNullable[bool] = UNSET,
|
|
plugins: Optional[
|
|
Union[
|
|
List[components.ChatRequestPlugin],
|
|
List[components.ChatRequestPluginTypedDict],
|
|
]
|
|
] = None,
|
|
presence_penalty: OptionalNullable[float] = UNSET,
|
|
provider: OptionalNullable[
|
|
Union[
|
|
components.ProviderPreferences, components.ProviderPreferencesTypedDict
|
|
]
|
|
] = UNSET,
|
|
reasoning: Optional[
|
|
Union[components.Reasoning, components.ReasoningTypedDict]
|
|
] = None,
|
|
response_format: Optional[
|
|
Union[components.ResponseFormat, components.ResponseFormatTypedDict]
|
|
] = None,
|
|
seed: OptionalNullable[int] = UNSET,
|
|
service_tier: OptionalNullable[components.ChatRequestServiceTier] = UNSET,
|
|
session_id: Optional[str] = None,
|
|
stop: OptionalNullable[
|
|
Union[components.Stop, components.StopTypedDict]
|
|
] = UNSET,
|
|
stream: Literal[True],
|
|
stream_options: OptionalNullable[
|
|
Union[components.ChatStreamOptions, components.ChatStreamOptionsTypedDict]
|
|
] = UNSET,
|
|
temperature: OptionalNullable[float] = UNSET,
|
|
tool_choice: Optional[
|
|
Union[components.ChatToolChoice, components.ChatToolChoiceTypedDict]
|
|
] = None,
|
|
tools: Optional[
|
|
Union[
|
|
List[components.ChatFunctionTool],
|
|
List[components.ChatFunctionToolTypedDict],
|
|
]
|
|
] = None,
|
|
top_logprobs: OptionalNullable[int] = UNSET,
|
|
top_p: OptionalNullable[float] = UNSET,
|
|
trace: Optional[
|
|
Union[components.TraceConfig, components.TraceConfigTypedDict]
|
|
] = None,
|
|
user: Optional[str] = None,
|
|
retries: OptionalNullable[utils.RetryConfig] = UNSET,
|
|
server_url: Optional[str] = None,
|
|
timeout_ms: Optional[int] = None,
|
|
http_headers: Optional[Mapping[str, str]] = None,
|
|
) -> eventstreaming.EventStreamAsync[components.ChatStreamChunk]:
|
|
r"""Create a chat completion
|
|
|
|
Sends a request for a model response for the given chat conversation. Supports both streaming and non-streaming modes.
|
|
|
|
:param messages: List of messages for the conversation
|
|
:param http_referer: The app identifier should be your app's URL and is used as the primary identifier for rankings.
|
|
This is used to track API usage per application.
|
|
|
|
:param x_open_router_title: The app display name allows you to customize how your app appears in OpenRouter's dashboard.
|
|
|
|
:param x_open_router_categories: Comma-separated list of app categories (e.g. \"cli-agent,cloud-agent\"). Used for marketplace rankings.
|
|
|
|
:param cache_control:
|
|
:param debug: Debug options for inspecting request transformations (streaming only)
|
|
:param frequency_penalty: Frequency penalty (-2.0 to 2.0)
|
|
:param image_config: Provider-specific image configuration options. Keys and values vary by model/provider. See https://openrouter.ai/docs/guides/overview/multimodal/image-generation for more details.
|
|
:param logit_bias: Token logit bias adjustments
|
|
:param logprobs: Return log probabilities
|
|
:param max_completion_tokens: Maximum tokens in completion
|
|
:param max_tokens: Maximum tokens (deprecated, use max_completion_tokens). Note: some providers enforce a minimum of 16.
|
|
:param metadata: Key-value pairs for additional object information (max 16 pairs, 64 char keys, 512 char values)
|
|
:param modalities: Output modalities for the response. Supported values are \"text\", \"image\", and \"audio\".
|
|
:param model: Model to use for completion
|
|
:param models: Models to use for completion
|
|
:param parallel_tool_calls: Whether to enable parallel function calling during tool use. When true, the model may generate multiple tool calls in a single response.
|
|
:param plugins: Plugins you want to enable for this request, including their settings.
|
|
:param presence_penalty: Presence penalty (-2.0 to 2.0)
|
|
:param provider: When multiple model providers are available, optionally indicate your routing preference.
|
|
:param reasoning: Configuration options for reasoning models
|
|
:param response_format: Response format configuration
|
|
:param seed: Random seed for deterministic outputs
|
|
:param service_tier: The service tier to use for processing this request.
|
|
:param session_id: A unique identifier for grouping related requests (e.g., a conversation or agent workflow) for observability. If provided in both the request body and the x-session-id header, the body value takes precedence. Maximum of 256 characters.
|
|
:param stop: Stop sequences (up to 4)
|
|
:param stream: Enable streaming response
|
|
:param stream_options: Streaming configuration options
|
|
:param temperature: Sampling temperature (0-2)
|
|
:param tool_choice: Tool choice configuration
|
|
:param tools: Available tools for function calling
|
|
:param top_logprobs: Number of top log probabilities to return (0-20)
|
|
:param top_p: Nucleus sampling parameter (0-1)
|
|
:param trace: Metadata for observability and tracing. Known keys (trace_id, trace_name, span_name, generation_name, parent_span_id) have special handling. Additional keys are passed through as custom metadata to configured broadcast destinations.
|
|
:param user: Unique user identifier
|
|
:param retries: Override the default retry configuration for this method
|
|
:param server_url: Override the default server URL for this method
|
|
:param timeout_ms: Override the default request timeout configuration for this method in milliseconds
|
|
:param accept_header_override: Override the default accept header for this method
|
|
:param http_headers: Additional headers to set or replace on requests.
|
|
"""
|
|
|
|
async def send_async(
|
|
self,
|
|
*,
|
|
messages: Union[
|
|
List[components.ChatMessages], List[components.ChatMessagesTypedDict]
|
|
],
|
|
http_referer: Optional[str] = None,
|
|
x_open_router_title: Optional[str] = None,
|
|
x_open_router_categories: Optional[str] = None,
|
|
cache_control: Optional[
|
|
Union[
|
|
components.AnthropicCacheControlDirective,
|
|
components.AnthropicCacheControlDirectiveTypedDict,
|
|
]
|
|
] = None,
|
|
debug: Optional[
|
|
Union[components.ChatDebugOptions, components.ChatDebugOptionsTypedDict]
|
|
] = None,
|
|
frequency_penalty: OptionalNullable[float] = UNSET,
|
|
image_config: Optional[
|
|
Union[
|
|
Dict[str, components.ImageConfig],
|
|
Dict[str, components.ImageConfigTypedDict],
|
|
]
|
|
] = None,
|
|
logit_bias: OptionalNullable[Dict[str, float]] = UNSET,
|
|
logprobs: OptionalNullable[bool] = UNSET,
|
|
max_completion_tokens: OptionalNullable[int] = UNSET,
|
|
max_tokens: OptionalNullable[int] = UNSET,
|
|
metadata: Optional[Dict[str, str]] = None,
|
|
modalities: Optional[List[components.Modality]] = None,
|
|
model: Optional[str] = None,
|
|
models: Optional[List[str]] = None,
|
|
parallel_tool_calls: OptionalNullable[bool] = UNSET,
|
|
plugins: Optional[
|
|
Union[
|
|
List[components.ChatRequestPlugin],
|
|
List[components.ChatRequestPluginTypedDict],
|
|
]
|
|
] = None,
|
|
presence_penalty: OptionalNullable[float] = UNSET,
|
|
provider: OptionalNullable[
|
|
Union[
|
|
components.ProviderPreferences, components.ProviderPreferencesTypedDict
|
|
]
|
|
] = UNSET,
|
|
reasoning: Optional[
|
|
Union[components.Reasoning, components.ReasoningTypedDict]
|
|
] = None,
|
|
response_format: Optional[
|
|
Union[components.ResponseFormat, components.ResponseFormatTypedDict]
|
|
] = None,
|
|
seed: OptionalNullable[int] = UNSET,
|
|
service_tier: OptionalNullable[components.ChatRequestServiceTier] = UNSET,
|
|
session_id: Optional[str] = None,
|
|
stop: OptionalNullable[
|
|
Union[components.Stop, components.StopTypedDict]
|
|
] = UNSET,
|
|
stream: Optional[bool] = False,
|
|
stream_options: OptionalNullable[
|
|
Union[components.ChatStreamOptions, components.ChatStreamOptionsTypedDict]
|
|
] = UNSET,
|
|
temperature: OptionalNullable[float] = UNSET,
|
|
tool_choice: Optional[
|
|
Union[components.ChatToolChoice, components.ChatToolChoiceTypedDict]
|
|
] = None,
|
|
tools: Optional[
|
|
Union[
|
|
List[components.ChatFunctionTool],
|
|
List[components.ChatFunctionToolTypedDict],
|
|
]
|
|
] = None,
|
|
top_logprobs: OptionalNullable[int] = UNSET,
|
|
top_p: OptionalNullable[float] = UNSET,
|
|
trace: Optional[
|
|
Union[components.TraceConfig, components.TraceConfigTypedDict]
|
|
] = None,
|
|
user: Optional[str] = None,
|
|
retries: OptionalNullable[utils.RetryConfig] = UNSET,
|
|
server_url: Optional[str] = None,
|
|
timeout_ms: Optional[int] = None,
|
|
http_headers: Optional[Mapping[str, str]] = None,
|
|
) -> operations.SendChatCompletionRequestResponse:
|
|
r"""Create a chat completion
|
|
|
|
Sends a request for a model response for the given chat conversation. Supports both streaming and non-streaming modes.
|
|
|
|
:param messages: List of messages for the conversation
|
|
:param http_referer: The app identifier should be your app's URL and is used as the primary identifier for rankings.
|
|
This is used to track API usage per application.
|
|
|
|
:param x_open_router_title: The app display name allows you to customize how your app appears in OpenRouter's dashboard.
|
|
|
|
:param x_open_router_categories: Comma-separated list of app categories (e.g. \"cli-agent,cloud-agent\"). Used for marketplace rankings.
|
|
|
|
:param cache_control:
|
|
:param debug: Debug options for inspecting request transformations (streaming only)
|
|
:param frequency_penalty: Frequency penalty (-2.0 to 2.0)
|
|
:param image_config: Provider-specific image configuration options. Keys and values vary by model/provider. See https://openrouter.ai/docs/guides/overview/multimodal/image-generation for more details.
|
|
:param logit_bias: Token logit bias adjustments
|
|
:param logprobs: Return log probabilities
|
|
:param max_completion_tokens: Maximum tokens in completion
|
|
:param max_tokens: Maximum tokens (deprecated, use max_completion_tokens). Note: some providers enforce a minimum of 16.
|
|
:param metadata: Key-value pairs for additional object information (max 16 pairs, 64 char keys, 512 char values)
|
|
:param modalities: Output modalities for the response. Supported values are \"text\", \"image\", and \"audio\".
|
|
:param model: Model to use for completion
|
|
:param models: Models to use for completion
|
|
:param parallel_tool_calls: Whether to enable parallel function calling during tool use. When true, the model may generate multiple tool calls in a single response.
|
|
:param plugins: Plugins you want to enable for this request, including their settings.
|
|
:param presence_penalty: Presence penalty (-2.0 to 2.0)
|
|
:param provider: When multiple model providers are available, optionally indicate your routing preference.
|
|
:param reasoning: Configuration options for reasoning models
|
|
:param response_format: Response format configuration
|
|
:param seed: Random seed for deterministic outputs
|
|
:param service_tier: The service tier to use for processing this request.
|
|
:param session_id: A unique identifier for grouping related requests (e.g., a conversation or agent workflow) for observability. If provided in both the request body and the x-session-id header, the body value takes precedence. Maximum of 256 characters.
|
|
:param stop: Stop sequences (up to 4)
|
|
:param stream: Enable streaming response
|
|
:param stream_options: Streaming configuration options
|
|
:param temperature: Sampling temperature (0-2)
|
|
:param tool_choice: Tool choice configuration
|
|
:param tools: Available tools for function calling
|
|
:param top_logprobs: Number of top log probabilities to return (0-20)
|
|
:param top_p: Nucleus sampling parameter (0-1)
|
|
:param trace: Metadata for observability and tracing. Known keys (trace_id, trace_name, span_name, generation_name, parent_span_id) have special handling. Additional keys are passed through as custom metadata to configured broadcast destinations.
|
|
:param user: Unique user identifier
|
|
:param retries: Override the default retry configuration for this method
|
|
:param server_url: Override the default server URL for this method
|
|
:param timeout_ms: Override the default request timeout configuration for this method in milliseconds
|
|
:param accept_header_override: Override the default accept header for this method
|
|
:param http_headers: Additional headers to set or replace on requests.
|
|
"""
|
|
base_url = None
|
|
url_variables = None
|
|
if timeout_ms is None:
|
|
timeout_ms = self.sdk_configuration.timeout_ms
|
|
|
|
if server_url is not None:
|
|
base_url = server_url
|
|
else:
|
|
base_url = self._get_url(base_url, url_variables)
|
|
|
|
request = operations.SendChatCompletionRequestRequest(
|
|
http_referer=http_referer,
|
|
x_open_router_title=x_open_router_title,
|
|
x_open_router_categories=x_open_router_categories,
|
|
chat_request=components.ChatRequest(
|
|
cache_control=utils.get_pydantic_model(
|
|
cache_control, Optional[components.AnthropicCacheControlDirective]
|
|
),
|
|
debug=utils.get_pydantic_model(
|
|
debug, Optional[components.ChatDebugOptions]
|
|
),
|
|
frequency_penalty=frequency_penalty,
|
|
image_config=image_config,
|
|
logit_bias=logit_bias,
|
|
logprobs=logprobs,
|
|
max_completion_tokens=max_completion_tokens,
|
|
max_tokens=max_tokens,
|
|
messages=utils.get_pydantic_model(
|
|
messages, List[components.ChatMessages]
|
|
),
|
|
metadata=metadata,
|
|
modalities=modalities,
|
|
model=model,
|
|
models=models,
|
|
parallel_tool_calls=parallel_tool_calls,
|
|
plugins=utils.get_pydantic_model(
|
|
plugins, Optional[List[components.ChatRequestPlugin]]
|
|
),
|
|
presence_penalty=presence_penalty,
|
|
provider=utils.get_pydantic_model(
|
|
provider, OptionalNullable[components.ProviderPreferences]
|
|
),
|
|
reasoning=utils.get_pydantic_model(
|
|
reasoning, Optional[components.Reasoning]
|
|
),
|
|
response_format=utils.get_pydantic_model(
|
|
response_format, Optional[components.ResponseFormat]
|
|
),
|
|
seed=seed,
|
|
service_tier=service_tier,
|
|
session_id=session_id,
|
|
stop=stop,
|
|
stream=stream,
|
|
stream_options=utils.get_pydantic_model(
|
|
stream_options, OptionalNullable[components.ChatStreamOptions]
|
|
),
|
|
temperature=temperature,
|
|
tool_choice=utils.get_pydantic_model(
|
|
tool_choice, Optional[components.ChatToolChoice]
|
|
),
|
|
tools=utils.get_pydantic_model(
|
|
tools, Optional[List[components.ChatFunctionTool]]
|
|
),
|
|
top_logprobs=top_logprobs,
|
|
top_p=top_p,
|
|
trace=utils.get_pydantic_model(trace, Optional[components.TraceConfig]),
|
|
user=user,
|
|
),
|
|
)
|
|
|
|
req = self._build_request_async(
|
|
method="POST",
|
|
path="/chat/completions",
|
|
base_url=base_url,
|
|
url_variables=url_variables,
|
|
request=request,
|
|
request_body_required=True,
|
|
request_has_path_params=False,
|
|
request_has_query_params=True,
|
|
user_agent_header="user-agent",
|
|
accept_header_value="text/event-stream" if stream else "application/json",
|
|
http_headers=http_headers,
|
|
_globals=operations.SendChatCompletionRequestGlobals(
|
|
http_referer=self.sdk_configuration.globals.http_referer,
|
|
x_open_router_title=self.sdk_configuration.globals.x_open_router_title,
|
|
x_open_router_categories=self.sdk_configuration.globals.x_open_router_categories,
|
|
),
|
|
security=self.sdk_configuration.security,
|
|
get_serialized_body=lambda: utils.serialize_request_body(
|
|
request.chat_request, False, False, "json", components.ChatRequest
|
|
),
|
|
allow_empty_value=None,
|
|
timeout_ms=timeout_ms,
|
|
)
|
|
|
|
if retries == UNSET:
|
|
if self.sdk_configuration.retry_config is not UNSET:
|
|
retries = self.sdk_configuration.retry_config
|
|
else:
|
|
retries = utils.RetryConfig(
|
|
"backoff", utils.BackoffStrategy(500, 60000, 1.5, 3600000), True
|
|
)
|
|
|
|
retry_config = None
|
|
if isinstance(retries, utils.RetryConfig):
|
|
retry_config = (retries, ["5XX"])
|
|
|
|
http_res = await self.do_request_async(
|
|
hook_ctx=HookContext(
|
|
config=self.sdk_configuration,
|
|
base_url=base_url or "",
|
|
operation_id="sendChatCompletionRequest",
|
|
oauth2_scopes=None,
|
|
security_source=get_security_from_env(
|
|
self.sdk_configuration.security, components.Security
|
|
),
|
|
),
|
|
request=req,
|
|
error_status_codes=[
|
|
"400",
|
|
"401",
|
|
"402",
|
|
"404",
|
|
"408",
|
|
"413",
|
|
"422",
|
|
"429",
|
|
"4XX",
|
|
"500",
|
|
"502",
|
|
"503",
|
|
"524",
|
|
"529",
|
|
"5XX",
|
|
],
|
|
stream=True,
|
|
retry_config=retry_config,
|
|
)
|
|
|
|
response_data: Any = None
|
|
if utils.match_response(http_res, "200", "application/json"):
|
|
http_res_text = await utils.stream_to_text_async(http_res)
|
|
return unmarshal_json_response(
|
|
components.ChatResult, http_res, http_res_text
|
|
)
|
|
if utils.match_response(http_res, "200", "text/event-stream"):
|
|
return eventstreaming.EventStreamAsync(
|
|
http_res,
|
|
lambda raw: utils.unmarshal_json(
|
|
raw, operations.SendChatCompletionRequestResponseBody
|
|
).data,
|
|
sentinel="[DONE]",
|
|
client_ref=self,
|
|
)
|
|
if utils.match_response(http_res, "400", "application/json"):
|
|
http_res_text = await utils.stream_to_text_async(http_res)
|
|
response_data = unmarshal_json_response(
|
|
errors.BadRequestResponseErrorData, http_res, http_res_text
|
|
)
|
|
raise errors.BadRequestResponseError(response_data, http_res, http_res_text)
|
|
if utils.match_response(http_res, "401", "application/json"):
|
|
http_res_text = await utils.stream_to_text_async(http_res)
|
|
response_data = unmarshal_json_response(
|
|
errors.UnauthorizedResponseErrorData, http_res, http_res_text
|
|
)
|
|
raise errors.UnauthorizedResponseError(
|
|
response_data, http_res, http_res_text
|
|
)
|
|
if utils.match_response(http_res, "402", "application/json"):
|
|
http_res_text = await utils.stream_to_text_async(http_res)
|
|
response_data = unmarshal_json_response(
|
|
errors.PaymentRequiredResponseErrorData, http_res, http_res_text
|
|
)
|
|
raise errors.PaymentRequiredResponseError(
|
|
response_data, http_res, http_res_text
|
|
)
|
|
if utils.match_response(http_res, "404", "application/json"):
|
|
http_res_text = await utils.stream_to_text_async(http_res)
|
|
response_data = unmarshal_json_response(
|
|
errors.NotFoundResponseErrorData, http_res, http_res_text
|
|
)
|
|
raise errors.NotFoundResponseError(response_data, http_res, http_res_text)
|
|
if utils.match_response(http_res, "408", "application/json"):
|
|
http_res_text = await utils.stream_to_text_async(http_res)
|
|
response_data = unmarshal_json_response(
|
|
errors.RequestTimeoutResponseErrorData, http_res, http_res_text
|
|
)
|
|
raise errors.RequestTimeoutResponseError(
|
|
response_data, http_res, http_res_text
|
|
)
|
|
if utils.match_response(http_res, "413", "application/json"):
|
|
http_res_text = await utils.stream_to_text_async(http_res)
|
|
response_data = unmarshal_json_response(
|
|
errors.PayloadTooLargeResponseErrorData, http_res, http_res_text
|
|
)
|
|
raise errors.PayloadTooLargeResponseError(
|
|
response_data, http_res, http_res_text
|
|
)
|
|
if utils.match_response(http_res, "422", "application/json"):
|
|
http_res_text = await utils.stream_to_text_async(http_res)
|
|
response_data = unmarshal_json_response(
|
|
errors.UnprocessableEntityResponseErrorData, http_res, http_res_text
|
|
)
|
|
raise errors.UnprocessableEntityResponseError(
|
|
response_data, http_res, http_res_text
|
|
)
|
|
if utils.match_response(http_res, "429", "application/json"):
|
|
http_res_text = await utils.stream_to_text_async(http_res)
|
|
response_data = unmarshal_json_response(
|
|
errors.TooManyRequestsResponseErrorData, http_res, http_res_text
|
|
)
|
|
raise errors.TooManyRequestsResponseError(
|
|
response_data, http_res, http_res_text
|
|
)
|
|
if utils.match_response(http_res, "500", "application/json"):
|
|
http_res_text = await utils.stream_to_text_async(http_res)
|
|
response_data = unmarshal_json_response(
|
|
errors.InternalServerResponseErrorData, http_res, http_res_text
|
|
)
|
|
raise errors.InternalServerResponseError(
|
|
response_data, http_res, http_res_text
|
|
)
|
|
if utils.match_response(http_res, "502", "application/json"):
|
|
http_res_text = await utils.stream_to_text_async(http_res)
|
|
response_data = unmarshal_json_response(
|
|
errors.BadGatewayResponseErrorData, http_res, http_res_text
|
|
)
|
|
raise errors.BadGatewayResponseError(response_data, http_res, http_res_text)
|
|
if utils.match_response(http_res, "503", "application/json"):
|
|
http_res_text = await utils.stream_to_text_async(http_res)
|
|
response_data = unmarshal_json_response(
|
|
errors.ServiceUnavailableResponseErrorData, http_res, http_res_text
|
|
)
|
|
raise errors.ServiceUnavailableResponseError(
|
|
response_data, http_res, http_res_text
|
|
)
|
|
if utils.match_response(http_res, "524", "application/json"):
|
|
http_res_text = await utils.stream_to_text_async(http_res)
|
|
response_data = unmarshal_json_response(
|
|
errors.EdgeNetworkTimeoutResponseErrorData, http_res, http_res_text
|
|
)
|
|
raise errors.EdgeNetworkTimeoutResponseError(
|
|
response_data, http_res, http_res_text
|
|
)
|
|
if utils.match_response(http_res, "529", "application/json"):
|
|
http_res_text = await utils.stream_to_text_async(http_res)
|
|
response_data = unmarshal_json_response(
|
|
errors.ProviderOverloadedResponseErrorData, http_res, http_res_text
|
|
)
|
|
raise errors.ProviderOverloadedResponseError(
|
|
response_data, http_res, http_res_text
|
|
)
|
|
if utils.match_response(http_res, "4XX", "*"):
|
|
http_res_text = await utils.stream_to_text_async(http_res)
|
|
raise errors.OpenRouterDefaultError(
|
|
"API error occurred", http_res, http_res_text
|
|
)
|
|
if utils.match_response(http_res, "5XX", "*"):
|
|
http_res_text = await utils.stream_to_text_async(http_res)
|
|
raise errors.OpenRouterDefaultError(
|
|
"API error occurred", http_res, http_res_text
|
|
)
|
|
|
|
http_res_text = await utils.stream_to_text_async(http_res)
|
|
raise errors.OpenRouterDefaultError(
|
|
"Unexpected response received", http_res, http_res_text
|
|
)
|