create
Create a Responses request using a saved, disclosed provider profile. Parameters use Responses names and are forwarded intact. Unsupported provider controls fail explicitly in Telion. ``messages`` is a convenience alias for role/content input; it cannot be combined with ``input``. ``context`` explicitly supplies model context. ``extra_body`` supplies provider extensions without overriding standard controls or credentials. ``timeout`` is the request deadline in seconds. Provider credentials remain inside Telion. Function tools describe outputs for the caller to handle; this call never grants AI permission to mutate the model.
Reference
| Field | Value | Description |
|---|---|---|
| symbol | telion_api.AiResponses.create | — |
| signature | (*, input: 'str | Sequence[Mapping[str, Any]] | None' = None, messages: 'Sequence[Mapping[str, Any]] | None' = None, model: 'str | None' = None, provider_profile: 'str | None' = None, temperature: 'float | None' = None, top_p: 'float | None' = None, max_output_tokens: 'int | None' = None, instructions: 'str | None' = None, reasoning: 'Mapping[str, Any] | None' = None, text: 'Mapping[str, Any] | None' = None, tools: 'Sequence[Mapping[str, Any]] | None' = None, tool_choice: 'str | Mapping[str, Any] | None' = None, parallel_tool_calls: 'bool | None' = None, max_tool_calls: 'int | None' = None, previous_response_id: 'str | None' = None, conversation: 'str | Mapping[str, Any] | None' = None, conversation_id: 'str | None' = None, include: 'Sequence[str] | None' = None, metadata: 'Mapping[str, str] | None' = None, service_tier: 'str | None' = None, store: 'bool | None' = None, background: 'bool | None' = None, truncation: 'str | None' = None, prompt: 'Mapping[str, Any] | None' = None, prompt_cache_key: 'str | None' = None, prompt_cache_retention: 'str | None' = None, safety_identifier: 'str | None' = None, user: 'str | None' = None, top_logprobs: 'int | None' = None, stream: 'bool' = False, stream_options: 'Mapping[str, Any] | None' = None, context: 'Mapping[str, Any] | None' = None, timeout: 'float | None' = None, extra_body: 'Mapping[str, Any] | None' = None) -> 'AiResponse | AiStream' | — |
| return | AiResponse | AiStream | — |
Create a Responses request using a saved, disclosed provider profile. Parameters use Responses names and are forwarded intact. Unsupported provider controls fail explicitly in Telion. messages is a convenience alias for role/content input; it cannot be combined with input. context explicitly supplies model context. extra_body supplies provider extensions without overriding standard controls or credentials. timeout is the request deadline in seconds. Provider credentials remain inside Telion. Function tools describe outputs for the caller to handle; this call never grants AI permission to mutate the model.
Contract
| Property | Value |
|---|---|
| symbol | telion_api.AiResponses.create |
| signature | (*, input: 'str | Sequence[Mapping[str, Any]] | None' = None, messages: 'Sequence[Mapping[str, Any]] | None' = None, model: 'str | None' = None, provider_profile: 'str | None' = None, temperature: 'float | None' = None, top_p: 'float | None' = None, max_output_tokens: 'int | None' = None, instructions: 'str | None' = None, reasoning: 'Mapping[str, Any] | None' = None, text: 'Mapping[str, Any] | None' = None, tools: 'Sequence[Mapping[str, Any]] | None' = None, tool_choice: 'str | ... |
| return | AiResponse | AiStream |
Signature
telion_api.AiResponses.create(*, input: 'str | Sequence[Mapping[str, Any]] | None' = None, messages: 'Sequence[Mapping[str, Any]] | None' = None, model: 'str | None' = None, provider_profile: 'str | None' = None, temperature: 'float | None' = None, top_p: 'float | None' = None, max_output_tokens: 'int | None' = None, instructions: 'str | None' = None, reasoning: 'Mapping[str, Any] | None' = None, text: 'Mapping[str, Any] | None' = None, tools: 'Sequence[Mapping[str, Any]] | None' = None, tool_choice: 'str | Mapping[str, Any] | None' = None, parallel_tool_calls: 'bool | None' = None, max_tool_calls: 'int | None' = None, previous_response_id: 'str | None' = None, conversation: 'str | Mapping[str, Any] | None' = None, conversation_id: 'str | None' = None, include: 'Sequence[str] | None' = None, metadata: 'Mapping[str, str] | None' = None, service_tier: 'str | None' = None, store: 'bool | None' = None, background: 'bool | None' = None, truncation: 'str | None' = None, prompt: 'Mapping[str, Any] | None' = None, prompt_cache_key: 'str | None' = None, prompt_cache_retention: 'str | None' = None, safety_identifier: 'str | None' = None, user: 'str | None' = None, top_logprobs: 'int | None' = None, stream: 'bool' = False, stream_options: 'Mapping[str, Any] | None' = None, context: 'Mapping[str, Any] | None' = None, timeout: 'float | None' = None, extra_body: 'Mapping[str, Any] | None' = None) -> 'AiResponse | AiStream'