> ## Documentation Index > Fetch the complete documentation index at: https://openrouter-d02e98a0-mintlify-5b6e02fd.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # GenerationResponseData - Python SDK > GenerationResponseData method reference The Python SDK and docs are currently in beta. Report issues on [GitHub](https://github.com/OpenRouterTeam/python-sdk/issues). Generation data ## Fields | Field | Type | Required | Description | Example | | --------------------------------- | --------------------------------------------------------------------------------------------------- | -------------------- | ------------------------------------------------------------------------------------------------------- | ------------------------------------------------ | | `api_type` | [Nullable\[components.APIType\]](../components/apitype.md) | :heavy\_check\_mark: | Type of API used for the generation | | | `app_id` | *Nullable\[int]* | :heavy\_check\_mark: | ID of the app that made the request | 12345 | | `cache_discount` | *Nullable\[float]* | :heavy\_check\_mark: | Discount applied due to caching | 0.0002 | | `cancelled` | *Nullable\[bool]* | :heavy\_check\_mark: | Whether the generation was cancelled | false | | `created_at` | *str* | :heavy\_check\_mark: | ISO 8601 timestamp of when the generation was created | 2024-07-15T23:33:19.433273+00:00 | | `external_user` | *Nullable\[str]* | :heavy\_check\_mark: | External user identifier | user-123 | | `finish_reason` | *Nullable\[str]* | :heavy\_check\_mark: | Reason the generation finished | stop | | `generation_time` | *Nullable\[float]* | :heavy\_check\_mark: | Time taken for generation in milliseconds | 1200 | | `http_referer` | *Nullable\[str]* | :heavy\_check\_mark: | Referer header from the request | | | `id` | *str* | :heavy\_check\_mark: | Unique identifier for the generation | gen-3bhGkxlo4XFrqiabUM7NDtwDzWwG | | `is_byok` | *bool* | :heavy\_check\_mark: | Whether this used bring-your-own-key | false | | `latency` | *Nullable\[float]* | :heavy\_check\_mark: | Total latency in milliseconds | 1250 | | `model` | *str* | :heavy\_check\_mark: | Model used for the generation | sao10k/l3-stheno-8b | | `moderation_latency` | *Nullable\[float]* | :heavy\_check\_mark: | Moderation latency in milliseconds | 50 | | `native_finish_reason` | *Nullable\[str]* | :heavy\_check\_mark: | Native finish reason as reported by provider | stop | | `native_tokens_cached` | *Nullable\[int]* | :heavy\_check\_mark: | Native cached tokens as reported by provider | 3 | | `native_tokens_completion` | *Nullable\[int]* | :heavy\_check\_mark: | Native completion tokens as reported by provider | 25 | | `native_tokens_completion_images` | *Nullable\[int]* | :heavy\_check\_mark: | Native completion image tokens as reported by provider | 0 | | `native_tokens_prompt` | *Nullable\[int]* | :heavy\_check\_mark: | Native prompt tokens as reported by provider | 10 | | `native_tokens_reasoning` | *Nullable\[int]* | :heavy\_check\_mark: | Native reasoning tokens as reported by provider | 5 | | `num_fetches` | *Nullable\[int]* | :heavy\_check\_mark: | Number of web fetches performed | 0 | | `num_input_audio_prompt` | *Nullable\[int]* | :heavy\_check\_mark: | Number of audio inputs in the prompt | 0 | | `num_media_completion` | *Nullable\[int]* | :heavy\_check\_mark: | Number of media items in the completion | 0 | | `num_media_prompt` | *Nullable\[int]* | :heavy\_check\_mark: | Number of media items in the prompt | 1 | | `num_search_results` | *Nullable\[int]* | :heavy\_check\_mark: | Number of search results included | 5 | | `origin` | *str* | :heavy\_check\_mark: | Origin URL of the request | [https://openrouter.ai/](https://openrouter.ai/) | | `preset_id` | *Nullable\[str]* | :heavy\_check\_mark: | ID of the preset used for this generation, null if no preset was used | a9e8d400-592a-494f-908c-375efa66cafd | | `provider_name` | *Nullable\[str]* | :heavy\_check\_mark: | Name of the provider that served the request | Infermatic | | `provider_responses` | List\[[components.ProviderResponse](/client-sdks/python/api-reference/components/providerresponse)] | :heavy\_check\_mark: | List of provider responses for this generation, including fallback attempts | | | `request_id` | *OptionalNullable\[str]* | :heavy\_minus\_sign: | Unique identifier grouping all generations from a single API request | req-1727282430-aBcDeFgHiJkLmNoPqRsT | | `response_cache_source_id` | *OptionalNullable\[str]* | :heavy\_minus\_sign: | If this generation was served from response cache, contains the original generation ID. Null otherwise. | | | `router` | *Nullable\[str]* | :heavy\_check\_mark: | Router used for the request (e.g., openrouter/auto) | openrouter/auto | | `service_tier` | *Nullable\[str]* | :heavy\_check\_mark: | Service tier the upstream provider reported running this request on, or null if it did not report one. | priority | | `session_id` | *OptionalNullable\[str]* | :heavy\_minus\_sign: | Session identifier grouping multiple generations in the same session | | | `streamed` | *Nullable\[bool]* | :heavy\_check\_mark: | Whether the response was streamed | true | | `tokens_completion` | *Nullable\[int]* | :heavy\_check\_mark: | Number of tokens in the completion | 25 | | `tokens_prompt` | *Nullable\[int]* | :heavy\_check\_mark: | Number of tokens in the prompt | 10 | | `total_cost` | *float* | :heavy\_check\_mark: | Total cost of the generation in USD | 0.0015 | | `upstream_id` | *Nullable\[str]* | :heavy\_check\_mark: | Upstream provider's identifier for this generation | chatcmpl-791bcf62-080e-4568-87d0-94c72e3b4946 | | `upstream_inference_cost` | *Nullable\[float]* | :heavy\_check\_mark: | Cost charged by the upstream provider | 0.0012 | | `usage` | *float* | :heavy\_check\_mark: | Usage amount in USD | 0.0015 | | `user_agent` | *Nullable\[str]* | :heavy\_check\_mark: | User-Agent header from the request | | | `web_search_engine` | *Nullable\[str]* | :heavy\_check\_mark: | The resolved web search engine used for this generation (e.g. exa, firecrawl, parallel) | exa |