Sample - OpenAI API
POST/realtime/calls/{call_id}/accept

Accept an incoming SIP call

Triggers acceptance of an incoming SIP call and applies the Realtime session configuration that handles the call. Supply call_id from the incoming-call webhook and configure the session body, including the required type field. The caller is bridged to the model after the session configuration is accepted.

  • RetriesRetries up to 2×, 500ms backoff, 30s timeout.

1 parameter · 14 body fields
call_idstringrequired
The identifier for the incoming SIP call provided in the `realtime.call.incoming` webhook.

Realtime session configuration to apply before bridging the caller to the model.

typestringrequired
The type of session to create. Always `realtime` for the Realtime API.
Allowed:realtime
output_modalitiesarray<string>optional
The set of modalities the model can respond with. It defaults to `["audio"]`, indicating that the model will respond with audio plus a transcript. `["text"]` can be used to make the model respond with text only. It is not possible to request both `text` and `audio` at the same time.
Default:["audio"]
modelstringoptional
The Realtime model used for this session.
instructionsstringoptional
The default system instructions (i.e. system message) prepended to model calls. This field allows the client to guide the model on desired responses. The model can be instructed on response content and format, (e.g. "be extremely succinct", "act friendly", "here are examples of good responses") and on audio behavior (e.g. "talk quickly", "inject emotion into your voice", "laugh frequently"). The instructions are not guaranteed to be followed by the model, but they provide guidance to the model on the desired behavior. Note that the server sets default instructions which will be used if this field is not set and are visible in the `session.created` event at the start of the session.
audioobjectoptional
Configuration for input and output audio.
includearray<string>optional
Additional fields to include in server outputs. `item.input_audio_transcription.logprobs`: Include logprobs for input audio transcription.
tracingstringoptional
Realtime API can write session traces to the [Traces Dashboard](https://platform.openai.com/logs?api=traces). Set to null to disable tracing. Once tracing is enabled for a session, the configuration cannot be modified. `auto` will create a trace for the session with default values for the workflow name, group id, and metadata.
Allowed:autoDefault:null
toolsarray<FunctionTool>optional
Tools available to the model.
tool_choicestringoptional
How the model chooses tools. Provide one of the string modes or force a specific function/MCP tool.
Allowed:noneautorequiredDefault:auto
parallel_tool_callsbooleanoptional
Whether the model may call multiple tools in parallel. Only supported by reasoning Realtime models such as `gpt-realtime-2`.
reasoningobjectoptional
Configuration for reasoning-capable Realtime models such as `gpt-realtime-2`.
max_output_tokensintegeroptional
Maximum number of output tokens for a single assistant response, inclusive of tool calls. Provide an integer between 1 and 4096 to limit output tokens, or `inf` for the maximum available tokens for a given model. Defaults to `inf`.
truncationstringoptional
When the number of tokens in a conversation exceeds the model's input token limit, the conversation be truncated, meaning messages (starting from the oldest) will not be included in the model's context. A 32k context model with 4,096 max output tokens can only include 28,224 tokens in the context before truncation occurs. Clients can configure truncation behavior to truncate with a lower max token limit, which is an effective way to control token usage and cost. Truncation will reduce the number of cached tokens on the next turn (busting the cache), since messages are dropped from the beginning of the context. However, clients can also configure truncation to retain messages up to a fraction of the maximum context size, which will reduce the need for future truncations and thus improve the cache rate. Truncation can be disabled entirely, which means the server will never truncate but would instead return an error if the conversation exceeds the model's input token limit.
Allowed:autodisabled
promptobjectoptional
A prompt template reference with an `id`, optional version and variables, or null.

1 status code
200Returns confirmation that the incoming SIP call was accepted successfully.

Error handling

The request body must include type with the value realtime. If provided, output_modalities can contain text or audio, but it cannot request both together; max_output_tokens must be an integer from 1 to 4096 or inf.