Files
openrouter-python-sdk-retry…/docs/operations/getgenerationdata.md
T
2025-11-13 14:21:27 -05:00

41 lines
9.9 KiB
Markdown

# GetGenerationData
Generation data
## Fields
| Field | Type | Required | Description | Example |
| -------------------------------------------------------- | -------------------------------------------------------- | -------------------------------------------------------- | -------------------------------------------------------- | -------------------------------------------------------- |
| `id` | *str* | :heavy_check_mark: | Unique identifier for the generation | gen-3bhGkxlo4XFrqiabUM7NDtwDzWwG |
| `upstream_id` | *Nullable[str]* | :heavy_check_mark: | Upstream provider's identifier for this generation | chatcmpl-791bcf62-080e-4568-87d0-94c72e3b4946 |
| `total_cost` | *float* | :heavy_check_mark: | Total cost of the generation in USD | 0.0015 |
| `cache_discount` | *Nullable[float]* | :heavy_check_mark: | Discount applied due to caching | 0.0002 |
| `upstream_inference_cost` | *Nullable[float]* | :heavy_check_mark: | Cost charged by the upstream provider | 0.0012 |
| `created_at` | *str* | :heavy_check_mark: | ISO 8601 timestamp of when the generation was created | 2024-07-15T23:33:19.433273+00:00 |
| `model` | *str* | :heavy_check_mark: | Model used for the generation | sao10k/l3-stheno-8b |
| `app_id` | *Nullable[float]* | :heavy_check_mark: | ID of the app that made the request | 12345 |
| `streamed` | *Nullable[bool]* | :heavy_check_mark: | Whether the response was streamed | true |
| `cancelled` | *Nullable[bool]* | :heavy_check_mark: | Whether the generation was cancelled | false |
| `provider_name` | *Nullable[str]* | :heavy_check_mark: | Name of the provider that served the request | Infermatic |
| `latency` | *Nullable[float]* | :heavy_check_mark: | Total latency in milliseconds | 1250 |
| `moderation_latency` | *Nullable[float]* | :heavy_check_mark: | Moderation latency in milliseconds | 50 |
| `generation_time` | *Nullable[float]* | :heavy_check_mark: | Time taken for generation in milliseconds | 1200 |
| `finish_reason` | *Nullable[str]* | :heavy_check_mark: | Reason the generation finished | stop |
| `tokens_prompt` | *Nullable[float]* | :heavy_check_mark: | Number of tokens in the prompt | 10 |
| `tokens_completion` | *Nullable[float]* | :heavy_check_mark: | Number of tokens in the completion | 25 |
| `native_tokens_prompt` | *Nullable[float]* | :heavy_check_mark: | Native prompt tokens as reported by provider | 10 |
| `native_tokens_completion` | *Nullable[float]* | :heavy_check_mark: | Native completion tokens as reported by provider | 25 |
| `native_tokens_completion_images` | *Nullable[float]* | :heavy_check_mark: | Native completion image tokens as reported by provider | 0 |
| `native_tokens_reasoning` | *Nullable[float]* | :heavy_check_mark: | Native reasoning tokens as reported by provider | 5 |
| `native_tokens_cached` | *Nullable[float]* | :heavy_check_mark: | Native cached tokens as reported by provider | 3 |
| `num_media_prompt` | *Nullable[float]* | :heavy_check_mark: | Number of media items in the prompt | 1 |
| `num_input_audio_prompt` | *Nullable[float]* | :heavy_check_mark: | Number of audio inputs in the prompt | 0 |
| `num_media_completion` | *Nullable[float]* | :heavy_check_mark: | Number of media items in the completion | 0 |
| `num_search_results` | *Nullable[float]* | :heavy_check_mark: | Number of search results included | 5 |
| `origin` | *str* | :heavy_check_mark: | Origin URL of the request | https://openrouter.ai/ |
| `usage` | *float* | :heavy_check_mark: | Usage amount in USD | 0.0015 |
| `is_byok` | *bool* | :heavy_check_mark: | Whether this used bring-your-own-key | false |
| `native_finish_reason` | *Nullable[str]* | :heavy_check_mark: | Native finish reason as reported by provider | stop |
| `external_user` | *Nullable[str]* | :heavy_check_mark: | External user identifier | user-123 |
| `api_type` | [Nullable[operations.APIType]](../operations/apitype.md) | :heavy_check_mark: | Type of API used for the generation | |