> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://openrouter.ai/docs/llms.txt. > For full documentation content, see https://openrouter.ai/docs/llms-full.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://openrouter.ai/docs/_mcp/server. # Presets - Python SDK The Python SDK and docs are currently in beta. Report issues on [GitHub](https://github.com/OpenRouterTeam/python-sdk/issues). ## Overview Presets endpoints ### Available Operations * [create\_presets\_chat\_completions](#create_presets_chat_completions) - Create a preset from a chat-completions request body * [create\_presets\_messages](#create_presets_messages) - Create a preset from a messages request body * [create\_presets\_responses](#create_presets_responses) - Create a preset from a responses request body ## create\_presets\_chat\_completions Creates a preset (or a new version of an existing one) from an inference request body. Only fields that overlap with the preset config are persisted; other fields (e.g. `messages`, `stream`, `prompt`) are silently ignored. ### Example Usage ```python from openrouter import OpenRouter import os with OpenRouter( http_referer="", x_open_router_title="", x_open_router_categories="", api_key=os.getenv("OPENROUTER_API_KEY", ""), ) as open_router: res = open_router.presets.create_presets_chat_completions(slug="my-preset", messages=[ { "content": "You are a helpful assistant.", "role": "system", }, { "content": "Hello!", "role": "user", }, ], model="openai/gpt-5.4", stream=False, temperature=0.7) # Handle response print(res) ``` ### Parameters | Parameter | Type | Required | Description | Example | | -------------------------- | ------------------------------------------------------------------------------------------------------------------------- | -------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------ | | `slug` | *str* | :heavy\_check\_mark: | URL-safe slug identifying the preset. Created if it does not exist. | my-preset | | `messages` | List\[[components.ChatMessages](/docs/sdks/python/api-reference/components/chatmessages)] | :heavy\_check\_mark: | List of messages for the conversation | \[
`{"content": "Hello!","role": "user"}`
] | | `http_referer` | *Optional\[str]* | :heavy\_minus\_sign: | 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.
| | | `x_open_router_title` | *Optional\[str]* | :heavy\_minus\_sign: | The app display name allows you to customize how your app appears in OpenRouter's dashboard.
| | | `x_open_router_categories` | *Optional\[str]* | :heavy\_minus\_sign: | Comma-separated list of app categories (e.g. "cli-agent,cloud-agent"). Used for marketplace rankings.
| | | `cache_control` | [Optional\[components.AnthropicCacheControlDirective\]](../../components/anthropiccachecontroldirective.md) | :heavy\_minus\_sign: | Enable automatic prompt caching. When set at the top level, the system automatically applies cache breakpoints to the last cacheable block in the request. Currently supported for Anthropic Claude models. | `{"type": "ephemeral"}` | | `debug` | [Optional\[components.ChatDebugOptions\]](../../components/chatdebugoptions.md) | :heavy\_minus\_sign: | Debug options for inspecting request transformations (streaming only) | `{"echo_upstream_body": true}` | | `frequency_penalty` | *OptionalNullable\[float]* | :heavy\_minus\_sign: | Frequency penalty (-2.0 to 2.0) | 0 | | `image_config` | Dict\[str, [components.ImageConfig](/docs/sdks/python/api-reference/components/imageconfig)] | :heavy\_minus\_sign: | Provider-specific image configuration options. Keys and values vary by model/provider. See [https://openrouter.ai/docs/guides/overview/multimodal/image-generation](https://openrouter.ai/docs/guides/overview/multimodal/image-generation) for more details. | `{"aspect_ratio": "16:9","quality": "high"}` | | `logit_bias` | Dict\[str, *float*] | :heavy\_minus\_sign: | Token logit bias adjustments | `{"50256": -100}` | | `logprobs` | *OptionalNullable\[bool]* | :heavy\_minus\_sign: | Return log probabilities | false | | `max_completion_tokens` | *OptionalNullable\[int]* | :heavy\_minus\_sign: | Maximum tokens in completion | 100 | | `max_tokens` | *OptionalNullable\[int]* | :heavy\_minus\_sign: | Maximum tokens (deprecated, use max\_completion\_tokens). Note: some providers enforce a minimum of 16. | 100 | | `metadata` | Dict\[str, *str*] | :heavy\_minus\_sign: | Key-value pairs for additional object information (max 16 pairs, 64 char keys, 512 char values) | `{"session_id": "session-456","user_id": "user-123"}` | | `modalities` | List\[[components.Modality](/docs/sdks/python/api-reference/components/modality)] | :heavy\_minus\_sign: | Output modalities for the response. Supported values are "text", "image", and "audio". | \[
"text",
"image"
] | | `model` | *Optional\[str]* | :heavy\_minus\_sign: | Model to use for completion | openai/gpt-4 | | `models` | List\[*str*] | :heavy\_minus\_sign: | Models to use for completion | \[
"openai/gpt-4",
"openai/gpt-4o"
] | | `parallel_tool_calls` | *OptionalNullable\[bool]* | :heavy\_minus\_sign: | Whether to enable parallel function calling during tool use. When true, the model may generate multiple tool calls in a single response. | true | | `plugins` | List\[[components.ChatRequestPlugin](/docs/sdks/python/api-reference/components/chatrequestplugin)] | :heavy\_minus\_sign: | Plugins you want to enable for this request, including their settings. | | | `presence_penalty` | *OptionalNullable\[float]* | :heavy\_minus\_sign: | Presence penalty (-2.0 to 2.0) | 0 | | `provider` | [OptionalNullable\[components.ProviderPreferences\]](../../components/providerpreferences.md) | :heavy\_minus\_sign: | When multiple model providers are available, optionally indicate your routing preference. | `{"allow_fallbacks": true}` | | `reasoning` | [Optional\[components.ChatRequestReasoning\]](../../components/chatrequestreasoning.md) | :heavy\_minus\_sign: | Configuration options for reasoning models | `{"effort": "medium","summary": "concise"}` | | `response_format` | [Optional\[components.ResponseFormat\]](../../components/responseformat.md) | :heavy\_minus\_sign: | Response format configuration | `{"type": "json_object"}` | | `seed` | *OptionalNullable\[int]* | :heavy\_minus\_sign: | Random seed for deterministic outputs | 42 | | `service_tier` | [OptionalNullable\[components.ChatRequestServiceTier\]](../../components/chatrequestservicetier.md) | :heavy\_minus\_sign: | The service tier to use for processing this request. | auto | | `session_id` | *Optional\[str]* | :heavy\_minus\_sign: | A unique identifier for grouping related requests (e.g., a conversation or agent workflow). When provided, OpenRouter uses it as the sticky routing key, routing all requests in the session to the same provider to maximize prompt cache hits. Also used for observability grouping. If provided in both the request body and the x-session-id header, the body value takes precedence. Maximum of 256 characters. | | | `stop` | [OptionalNullable\[components.Stop\]](../../components/stop.md) | :heavy\_minus\_sign: | Stop sequences (up to 4) | \[
""
] | | `stop_server_tools_when` | List\[[components.StopServerToolsWhenCondition](/docs/sdks/python/api-reference/components/stopservertoolswhencondition)] | :heavy\_minus\_sign: | Stop conditions for the server-tool agent loop. Any condition firing halts the loop (OR logic). When set, this overrides `max_tool_calls`. | \[
`{"step_count": 5,"type": "step_count_is"}`,
`{"max_cost_in_dollars": 0.5,"type": "max_cost"}`
] | | `stream` | *Optional\[bool]* | :heavy\_minus\_sign: | Enable streaming response | false | | `stream_options` | [OptionalNullable\[components.ChatStreamOptions\]](../../components/chatstreamoptions.md) | :heavy\_minus\_sign: | Streaming configuration options | `{"include_usage": true}` | | `temperature` | *OptionalNullable\[float]* | :heavy\_minus\_sign: | Sampling temperature (0-2) | 0.7 | | `tool_choice` | [Optional\[components.ChatToolChoice\]](../../components/chattoolchoice.md) | :heavy\_minus\_sign: | Tool choice configuration | auto | | `tools` | List\[[components.ChatFunctionTool](/docs/sdks/python/api-reference/components/chatfunctiontool)] | :heavy\_minus\_sign: | Available tools for function calling | \[
`{"function": {"description": "Get weather","name": "get_weather"}`,
"type": "function"
}
] | | `top_logprobs` | *OptionalNullable\[int]* | :heavy\_minus\_sign: | Number of top log probabilities to return (0-20) | 5 | | `top_p` | *OptionalNullable\[float]* | :heavy\_minus\_sign: | Nucleus sampling parameter (0-1) | 1 | | `trace` | [Optional\[components.TraceConfig\]](../../components/traceconfig.md) | :heavy\_minus\_sign: | 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. | `{"trace_id": "trace-abc123","trace_name": "my-app-trace"}` | | `user` | *Optional\[str]* | :heavy\_minus\_sign: | Unique user identifier | user-123 | | `retries` | [Optional\[utils.RetryConfig\]](../../models/utils/retryconfig.md) | :heavy\_minus\_sign: | Configuration to override the default retry behavior of the client. | | ### Response **[components.CreatePresetFromInferenceResponse](/docs/sdks/python/api-reference/components/createpresetfrominferenceresponse)** ### Errors | Error Type | Status Code | Content Type | | ---------------------------------- | ----------- | ---------------- | | errors.BadRequestResponseError | 400 | application/json | | errors.UnauthorizedResponseError | 401 | application/json | | errors.ForbiddenResponseError | 403 | application/json | | errors.NotFoundResponseError | 404 | application/json | | errors.ConflictResponseError | 409 | application/json | | errors.InternalServerResponseError | 500 | application/json | | errors.OpenRouterDefaultError | 4XX, 5XX | \*/\* | ## create\_presets\_messages Creates a preset (or a new version of an existing one) from an inference request body. Only fields that overlap with the preset config are persisted; other fields (e.g. `messages`, `stream`, `prompt`) are silently ignored. ### Example Usage ```python from openrouter import OpenRouter import os with OpenRouter( http_referer="", x_open_router_title="", x_open_router_categories="", api_key=os.getenv("OPENROUTER_API_KEY", ""), ) as open_router: res = open_router.presets.create_presets_messages(slug="my-preset", messages=[ { "content": "Hello!", "role": "user", }, ], model="anthropic/claude-4.6-sonnet", max_tokens=1024, system="You are a helpful assistant.") # Handle response print(res) ``` ### Parameters | Parameter | Type | Required | Description | Example | | -------------------------- | ------------------------------------------------------------------------------------------------------------------------- | -------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------ | | `slug` | *str* | :heavy\_check\_mark: | URL-safe slug identifying the preset. Created if it does not exist. | my-preset | | `messages` | List\[[components.MessagesMessageParam](/docs/sdks/python/api-reference/components/messagesmessageparam)] | :heavy\_check\_mark: | N/A | | | `model` | *str* | :heavy\_check\_mark: | N/A | | | `http_referer` | *Optional\[str]* | :heavy\_minus\_sign: | 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.
| | | `x_open_router_title` | *Optional\[str]* | :heavy\_minus\_sign: | The app display name allows you to customize how your app appears in OpenRouter's dashboard.
| | | `x_open_router_categories` | *Optional\[str]* | :heavy\_minus\_sign: | Comma-separated list of app categories (e.g. "cli-agent,cloud-agent"). Used for marketplace rankings.
| | | `cache_control` | [Optional\[components.AnthropicCacheControlDirective\]](../../components/anthropiccachecontroldirective.md) | :heavy\_minus\_sign: | Enable automatic prompt caching. When set at the top level, the system automatically applies cache breakpoints to the last cacheable block in the request. Currently supported for Anthropic Claude models. | `{"type": "ephemeral"}` | | `context_management` | [OptionalNullable\[components.ContextManagement\]](../../components/contextmanagement.md) | :heavy\_minus\_sign: | N/A | | | `max_tokens` | *Optional\[int]* | :heavy\_minus\_sign: | N/A | | | `metadata` | [Optional\[components.Metadata\]](../../components/metadata.md) | :heavy\_minus\_sign: | N/A | | | `models` | List\[*str*] | :heavy\_minus\_sign: | N/A | | | `output_config` | [Optional\[components.MessagesOutputConfig\]](../../components/messagesoutputconfig.md) | :heavy\_minus\_sign: | Configuration for controlling output behavior. Supports the effort parameter and structured output format. | `{"effort": "medium"}` | | `plugins` | List\[[components.MessagesRequestPlugin](/docs/sdks/python/api-reference/components/messagesrequestplugin)] | :heavy\_minus\_sign: | Plugins you want to enable for this request, including their settings. | | | `provider` | [OptionalNullable\[components.ProviderPreferences\]](../../components/providerpreferences.md) | :heavy\_minus\_sign: | When multiple model providers are available, optionally indicate your routing preference. | `{"allow_fallbacks": true}` | | `service_tier` | *Optional\[str]* | :heavy\_minus\_sign: | N/A | | | `session_id` | *Optional\[str]* | :heavy\_minus\_sign: | A unique identifier for grouping related requests (e.g., a conversation or agent workflow). When provided, OpenRouter uses it as the sticky routing key, routing all requests in the session to the same provider to maximize prompt cache hits. Also used for observability grouping. If provided in both the request body and the x-session-id header, the body value takes precedence. Maximum of 256 characters. | | | `speed` | [OptionalNullable\[components.Speed\]](../../components/speed.md) | :heavy\_minus\_sign: | N/A | standard | | `stop_sequences` | List\[*str*] | :heavy\_minus\_sign: | N/A | | | `stop_server_tools_when` | List\[[components.StopServerToolsWhenCondition](/docs/sdks/python/api-reference/components/stopservertoolswhencondition)] | :heavy\_minus\_sign: | Stop conditions for the server-tool agent loop. Any condition firing halts the loop (OR logic). When set, this overrides `max_tool_calls`. | \[
`{"step_count": 5,"type": "step_count_is"}`,
`{"max_cost_in_dollars": 0.5,"type": "max_cost"}`
] | | `stream` | *Optional\[bool]* | :heavy\_minus\_sign: | N/A | | | `system` | [Optional\[components.System\]](../../components/system.md) | :heavy\_minus\_sign: | N/A | | | `temperature` | *Optional\[float]* | :heavy\_minus\_sign: | N/A | | | `thinking` | [Optional\[components.Thinking\]](../../components/thinking.md) | :heavy\_minus\_sign: | N/A | | | `tool_choice` | [Optional\[components.ToolChoice\]](../../components/toolchoice.md) | :heavy\_minus\_sign: | N/A | | | `tools` | List\[[components.MessagesRequestToolUnion](/docs/sdks/python/api-reference/components/messagesrequesttoolunion)] | :heavy\_minus\_sign: | N/A | | | `top_k` | *Optional\[int]* | :heavy\_minus\_sign: | N/A | | | `top_p` | *Optional\[float]* | :heavy\_minus\_sign: | N/A | | | `trace` | [Optional\[components.TraceConfig\]](../../components/traceconfig.md) | :heavy\_minus\_sign: | 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. | `{"trace_id": "trace-abc123","trace_name": "my-app-trace"}` | | `user` | *Optional\[str]* | :heavy\_minus\_sign: | A unique identifier representing your end-user, which helps distinguish between different users of your app. This allows your app to identify specific users in case of abuse reports, preventing your entire app from being affected by the actions of individual users. Maximum of 256 characters. | | | `retries` | [Optional\[utils.RetryConfig\]](../../models/utils/retryconfig.md) | :heavy\_minus\_sign: | Configuration to override the default retry behavior of the client. | | ### Response **[components.CreatePresetFromInferenceResponse](/docs/sdks/python/api-reference/components/createpresetfrominferenceresponse)** ### Errors | Error Type | Status Code | Content Type | | ---------------------------------- | ----------- | ---------------- | | errors.BadRequestResponseError | 400 | application/json | | errors.UnauthorizedResponseError | 401 | application/json | | errors.ForbiddenResponseError | 403 | application/json | | errors.NotFoundResponseError | 404 | application/json | | errors.ConflictResponseError | 409 | application/json | | errors.InternalServerResponseError | 500 | application/json | | errors.OpenRouterDefaultError | 4XX, 5XX | \*/\* | ## create\_presets\_responses Creates a preset (or a new version of an existing one) from an inference request body. Only fields that overlap with the preset config are persisted; other fields (e.g. `messages`, `stream`, `prompt`) are silently ignored. ### Example Usage ```python from openrouter import OpenRouter import os with OpenRouter( http_referer="", x_open_router_title="", x_open_router_categories="", api_key=os.getenv("OPENROUTER_API_KEY", ""), ) as open_router: res = open_router.presets.create_presets_responses(slug="my-preset", input="Hello!", instructions="You are a helpful assistant.", model="openai/gpt-5.4", service_tier="auto", stream=False) # Handle response print(res) ``` ### Parameters | Parameter | Type | Required | Description | Example | | -------------------------- | ------------------------------------------------------------------------------------------------------------------------- | -------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------ | | `slug` | *str* | :heavy\_check\_mark: | URL-safe slug identifying the preset. Created if it does not exist. | my-preset | | `http_referer` | *Optional\[str]* | :heavy\_minus\_sign: | 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.
| | | `x_open_router_title` | *Optional\[str]* | :heavy\_minus\_sign: | The app display name allows you to customize how your app appears in OpenRouter's dashboard.
| | | `x_open_router_categories` | *Optional\[str]* | :heavy\_minus\_sign: | Comma-separated list of app categories (e.g. "cli-agent,cloud-agent"). Used for marketplace rankings.
| | | `background` | *OptionalNullable\[bool]* | :heavy\_minus\_sign: | N/A | | | `cache_control` | [Optional\[components.AnthropicCacheControlDirective\]](../../components/anthropiccachecontroldirective.md) | :heavy\_minus\_sign: | Enable automatic prompt caching. When set at the top level, the system automatically applies cache breakpoints to the last cacheable block in the request. Currently supported for Anthropic Claude models. | `{"type": "ephemeral"}` | | `frequency_penalty` | *OptionalNullable\[float]* | :heavy\_minus\_sign: | N/A | | | `image_config` | Dict\[str, [components.ImageConfig](/docs/sdks/python/api-reference/components/imageconfig)] | :heavy\_minus\_sign: | Provider-specific image configuration options. Keys and values vary by model/provider. See [https://openrouter.ai/docs/guides/overview/multimodal/image-generation](https://openrouter.ai/docs/guides/overview/multimodal/image-generation) for more details. | `{"aspect_ratio": "16:9","quality": "high"}` | | `include` | List\[[components.ResponseIncludesEnum](/docs/sdks/python/api-reference/components/responseincludesenum)] | :heavy\_minus\_sign: | N/A | | | `input` | [Optional\[components.InputsUnion\]](../../components/inputsunion.md) | :heavy\_minus\_sign: | Input for a response request - can be a string or array of items | \[
`{"content": "What is the weather today?","role": "user"}`
] | | `instructions` | *OptionalNullable\[str]* | :heavy\_minus\_sign: | N/A | | | `max_output_tokens` | *OptionalNullable\[int]* | :heavy\_minus\_sign: | N/A | | | `max_tool_calls` | *OptionalNullable\[int]* | :heavy\_minus\_sign: | N/A | | | `metadata` | Dict\[str, *str*] | :heavy\_minus\_sign: | 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. | `{"session_id": "abc-def-ghi","user_id": "123"}` | | `modalities` | List\[[components.OutputModalityEnum](/docs/sdks/python/api-reference/components/outputmodalityenum)] | :heavy\_minus\_sign: | Output modalities for the response. Supported values are "text" and "image". | \[
"text",
"image"
] | | `model` | *Optional\[str]* | :heavy\_minus\_sign: | N/A | | | `models` | List\[*str*] | :heavy\_minus\_sign: | N/A | | | `parallel_tool_calls` | *OptionalNullable\[bool]* | :heavy\_minus\_sign: | N/A | | | `plugins` | List\[[components.ResponsesRequestPlugin](/docs/sdks/python/api-reference/components/responsesrequestplugin)] | :heavy\_minus\_sign: | Plugins you want to enable for this request, including their settings. | | | `presence_penalty` | *OptionalNullable\[float]* | :heavy\_minus\_sign: | N/A | | | `previous_response_id` | *OptionalNullable\[str]* | :heavy\_minus\_sign: | N/A | | | `prompt` | [OptionalNullable\[components.StoredPromptTemplate\]](../../components/storedprompttemplate.md) | :heavy\_minus\_sign: | N/A | `{"id": "prompt-abc123","variables": {"name": "John"}`
} | | `prompt_cache_key` | *OptionalNullable\[str]* | :heavy\_minus\_sign: | N/A | | | `provider` | [OptionalNullable\[components.ProviderPreferences\]](../../components/providerpreferences.md) | :heavy\_minus\_sign: | When multiple model providers are available, optionally indicate your routing preference. | `{"allow_fallbacks": true}` | | `reasoning` | [OptionalNullable\[components.ReasoningConfig\]](../../components/reasoningconfig.md) | :heavy\_minus\_sign: | Configuration for reasoning mode in the response | `{"effort": "medium","summary": "auto"}` | | `safety_identifier` | *OptionalNullable\[str]* | :heavy\_minus\_sign: | N/A | | | `service_tier` | [OptionalNullable\[components.ResponsesRequestServiceTier\]](../../components/responsesrequestservicetier.md) | :heavy\_minus\_sign: | N/A | | | `session_id` | *Optional\[str]* | :heavy\_minus\_sign: | A unique identifier for grouping related requests (e.g., a conversation or agent workflow). When provided, OpenRouter uses it as the sticky routing key, routing all requests in the session to the same provider to maximize prompt cache hits. Also used for observability grouping. If provided in both the request body and the x-session-id header, the body value takes precedence. Maximum of 256 characters. | | | `stop_server_tools_when` | List\[[components.StopServerToolsWhenCondition](/docs/sdks/python/api-reference/components/stopservertoolswhencondition)] | :heavy\_minus\_sign: | Stop conditions for the server-tool agent loop. Any condition firing halts the loop (OR logic). When set, this overrides `max_tool_calls`. | \[
`{"step_count": 5,"type": "step_count_is"}`,
`{"max_cost_in_dollars": 0.5,"type": "max_cost"}`
] | | `stream` | *Optional\[bool]* | :heavy\_minus\_sign: | N/A | | | `temperature` | *OptionalNullable\[float]* | :heavy\_minus\_sign: | N/A | | | `text` | [Optional\[components.TextExtendedConfig\]](../../components/textextendedconfig.md) | :heavy\_minus\_sign: | Text output configuration including format and verbosity | `{"format": {"type": "text"}`,
"verbosity": "medium"
} | | `tool_choice` | [Optional\[components.OpenAIResponsesToolChoiceUnion\]](../../components/openairesponsestoolchoiceunion.md) | :heavy\_minus\_sign: | N/A | auto | | `tools` | List\[[components.ResponsesRequestToolUnion](/docs/sdks/python/api-reference/components/responsesrequesttoolunion)] | :heavy\_minus\_sign: | N/A | | | `top_k` | *Optional\[int]* | :heavy\_minus\_sign: | N/A | | | `top_logprobs` | *OptionalNullable\[int]* | :heavy\_minus\_sign: | N/A | | | `top_p` | *OptionalNullable\[float]* | :heavy\_minus\_sign: | N/A | | | `trace` | [Optional\[components.TraceConfig\]](../../components/traceconfig.md) | :heavy\_minus\_sign: | 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. | `{"trace_id": "trace-abc123","trace_name": "my-app-trace"}` | | `truncation` | [OptionalNullable\[components.OpenAIResponsesTruncation\]](../../components/openairesponsestruncation.md) | :heavy\_minus\_sign: | N/A | auto | | `user` | *Optional\[str]* | :heavy\_minus\_sign: | A unique identifier representing your end-user, which helps distinguish between different users of your app. This allows your app to identify specific users in case of abuse reports, preventing your entire app from being affected by the actions of individual users. Maximum of 256 characters. | | | `retries` | [Optional\[utils.RetryConfig\]](../../models/utils/retryconfig.md) | :heavy\_minus\_sign: | Configuration to override the default retry behavior of the client. | | ### Response **[components.CreatePresetFromInferenceResponse](/docs/sdks/python/api-reference/components/createpresetfrominferenceresponse)** ### Errors | Error Type | Status Code | Content Type | | ---------------------------------- | ----------- | ---------------- | | errors.BadRequestResponseError | 400 | application/json | | errors.UnauthorizedResponseError | 401 | application/json | | errors.ForbiddenResponseError | 403 | application/json | | errors.NotFoundResponseError | 404 | application/json | | errors.ConflictResponseError | 409 | application/json | | errors.InternalServerResponseError | 500 | application/json | | errors.OpenRouterDefaultError | 4XX, 5XX | \*/\* |