mirror of
https://github.com/wassname/openrouter-python-sdk-retry-errors.git
synced 2026-07-29 11:23:49 +08:00
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
40 lines
52 KiB
Markdown
40 lines
52 KiB
Markdown
# OpenResponsesNonStreamingResponse
|
|
|
|
Complete non-streaming response from the Responses API
|
|
|
|
|
|
## Fields
|
|
|
|
| Field | Type | Required | Description | Example |
|
|
| --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
|
| `id` | *str* | :heavy_check_mark: | N/A | |
|
|
| `object` | [models.Object](../models/object.md) | :heavy_check_mark: | N/A | |
|
|
| `created_at` | *float* | :heavy_check_mark: | N/A | |
|
|
| `model` | *str* | :heavy_check_mark: | N/A | |
|
|
| `status` | [Optional[models.OpenAIResponsesResponseStatus]](../models/openairesponsesresponsestatus.md) | :heavy_minus_sign: | N/A | |
|
|
| `output` | List[[models.ResponsesOutputItem](../models/responsesoutputitem.md)] | :heavy_check_mark: | N/A | |
|
|
| `user` | *OptionalNullable[str]* | :heavy_minus_sign: | N/A | |
|
|
| `output_text` | *Optional[str]* | :heavy_minus_sign: | N/A | |
|
|
| `prompt_cache_key` | *OptionalNullable[str]* | :heavy_minus_sign: | N/A | |
|
|
| `safety_identifier` | *OptionalNullable[str]* | :heavy_minus_sign: | N/A | |
|
|
| `error` | [Nullable[models.ResponsesErrorField]](../models/responseserrorfield.md) | :heavy_check_mark: | Error information returned from the API | {<br/>"code": "rate_limit_exceeded",<br/>"message": "Rate limit exceeded. Please try again later."<br/>} |
|
|
| `incomplete_details` | [Nullable[models.OpenAIResponsesIncompleteDetails]](../models/openairesponsesincompletedetails.md) | :heavy_check_mark: | N/A | |
|
|
| `usage` | [Optional[models.OpenResponsesUsage]](../models/openresponsesusage.md) | :heavy_minus_sign: | Token usage information for the response | {<br/>"input_tokens": 10,<br/>"output_tokens": 25,<br/>"total_tokens": 35,<br/>"input_tokens_details": {<br/>"cached_tokens": 0<br/>},<br/>"output_tokens_details": {<br/>"reasoning_tokens": 0<br/>},<br/>"cost": 0.0012,<br/>"cost_details": {<br/>"upstream_inference_cost": null,<br/>"upstream_inference_input_cost": 0.0008,<br/>"upstream_inference_output_cost": 0.0004<br/>}<br/>} |
|
|
| `max_tool_calls` | *OptionalNullable[float]* | :heavy_minus_sign: | N/A | |
|
|
| `top_logprobs` | *Optional[float]* | :heavy_minus_sign: | N/A | |
|
|
| `max_output_tokens` | *OptionalNullable[float]* | :heavy_minus_sign: | N/A | |
|
|
| `temperature` | *Nullable[float]* | :heavy_check_mark: | N/A | |
|
|
| `top_p` | *Nullable[float]* | :heavy_check_mark: | N/A | |
|
|
| `instructions` | [Nullable[models.OpenAIResponsesInputUnion]](../models/openairesponsesinputunion.md) | :heavy_check_mark: | N/A | |
|
|
| `metadata` | Dict[str, *str*] | :heavy_check_mark: | Metadata key-value pairs for the request. Keys must be ≤64 characters and cannot contain brackets. Values must be ≤512 characters. Maximum 16 pairs allowed. | {<br/>"user_id": "123",<br/>"session_id": "abc-def-ghi"<br/>} |
|
|
| `tools` | List[[models.OpenResponsesNonStreamingResponseToolUnion](../models/openresponsesnonstreamingresponsetoolunion.md)] | :heavy_check_mark: | N/A | |
|
|
| `tool_choice` | [models.OpenAIResponsesToolChoiceUnion](../models/openairesponsestoolchoiceunion.md) | :heavy_check_mark: | N/A | |
|
|
| `parallel_tool_calls` | *bool* | :heavy_check_mark: | N/A | |
|
|
| `prompt` | [OptionalNullable[models.OpenAIResponsesPrompt]](../models/openairesponsesprompt.md) | :heavy_minus_sign: | N/A | |
|
|
| `background` | *OptionalNullable[bool]* | :heavy_minus_sign: | N/A | |
|
|
| `previous_response_id` | *OptionalNullable[str]* | :heavy_minus_sign: | N/A | |
|
|
| `reasoning` | [OptionalNullable[models.OpenAIResponsesReasoningConfig]](../models/openairesponsesreasoningconfig.md) | :heavy_minus_sign: | N/A | |
|
|
| `service_tier` | [OptionalNullable[models.OpenAIResponsesServiceTier]](../models/openairesponsesservicetier.md) | :heavy_minus_sign: | N/A | |
|
|
| `store` | *Optional[bool]* | :heavy_minus_sign: | N/A | |
|
|
| `truncation` | [OptionalNullable[models.OpenAIResponsesTruncation]](../models/openairesponsestruncation.md) | :heavy_minus_sign: | N/A | |
|
|
| `text` | [Optional[models.ResponseTextConfig]](../models/responsetextconfig.md) | :heavy_minus_sign: | Text output configuration including format and verbosity | {<br/>"format": {<br/>"type": "text"<br/>},<br/>"verbosity": "medium"<br/>} | |