A valid request URL is required to generate request examples{
"id": "<string>",
"object": "response.compaction",
"model": "<string>",
"created_at": 123,
"output": [
{
"id": "<string>",
"type": "message",
"status": "in_progress",
"role": "assistant",
"content": "<string>",
"call_id": "<string>",
"name": "<string>",
"arguments": "<string>",
"output": {},
"action": {},
"error": "<string>",
"queries": [
"<string>"
],
"results": [
{}
],
"summary": [
{
"type": "summary_text",
"text": "<string>"
}
],
"encrypted_content": "<string>"
}
],
"usage": {
"input_tokens": 123,
"input_tokens_details": {
"text_tokens": 123,
"audio_tokens": 123,
"image_tokens": 123,
"cached_read_tokens": 123,
"cached_write_tokens": 123
},
"output_tokens": 123,
"output_tokens_details": {
"text_tokens": 123,
"accepted_prediction_tokens": 123,
"audio_tokens": 123,
"reasoning_tokens": 123,
"rejected_prediction_tokens": 123,
"citation_tokens": 123,
"num_search_queries": 123
},
"total_tokens": 123,
"cost": {
"input_tokens_cost": 123,
"output_tokens_cost": 123,
"reasoning_tokens_cost": 123,
"citation_tokens_cost": 123,
"search_queries_cost": 123,
"request_cost": 123,
"total_cost": 123
}
},
"extra_fields": {
"request_type": "<string>",
"provider": "openai",
"model_requested": "<string>",
"model_deployment": "<string>",
"latency": 123,
"chunk_index": 123,
"raw_request": {},
"raw_response": {},
"cache_debug": {
"cache_hit": true,
"cache_id": "<string>",
"hit_type": "<string>",
"requested_provider": "<string>",
"requested_model": "<string>",
"provider_used": "<string>",
"model_used": "<string>",
"input_tokens": 123,
"threshold": 123,
"similarity": 123
}
}
}{
"event_id": "<string>",
"type": "<string>",
"is_vikat_error": true,
"status_code": 123,
"error": {
"type": "<string>",
"code": "<string>",
"message": "<string>",
"param": "<string>",
"event_id": "<string>"
},
"extra_fields": {
"provider": "openai",
"model_requested": "<string>",
"request_type": "<string>"
}
}{
"event_id": "<string>",
"type": "<string>",
"is_vikat_error": true,
"status_code": 123,
"error": {
"type": "<string>",
"code": "<string>",
"message": "<string>",
"param": "<string>",
"event_id": "<string>"
},
"extra_fields": {
"provider": "openai",
"model_requested": "<string>",
"request_type": "<string>"
}
}Compact context (OpenAI)
Compresses a conversation into an opaque compaction item using the OpenAI-compatible
/v1/responses/compact endpoint. Drop-in compatible with the OpenAI SDK.
The response output contains the user messages plus a final item with
type: "response.compaction" and encrypted_content. Pass this output as input
to future Responses API calls to continue the conversation using the compacted context.
Note: This endpoint also works without the /v1 prefix (e.g., /openai/responses/compact).
A valid request URL is required to generate request examples{
"id": "<string>",
"object": "response.compaction",
"model": "<string>",
"created_at": 123,
"output": [
{
"id": "<string>",
"type": "message",
"status": "in_progress",
"role": "assistant",
"content": "<string>",
"call_id": "<string>",
"name": "<string>",
"arguments": "<string>",
"output": {},
"action": {},
"error": "<string>",
"queries": [
"<string>"
],
"results": [
{}
],
"summary": [
{
"type": "summary_text",
"text": "<string>"
}
],
"encrypted_content": "<string>"
}
],
"usage": {
"input_tokens": 123,
"input_tokens_details": {
"text_tokens": 123,
"audio_tokens": 123,
"image_tokens": 123,
"cached_read_tokens": 123,
"cached_write_tokens": 123
},
"output_tokens": 123,
"output_tokens_details": {
"text_tokens": 123,
"accepted_prediction_tokens": 123,
"audio_tokens": 123,
"reasoning_tokens": 123,
"rejected_prediction_tokens": 123,
"citation_tokens": 123,
"num_search_queries": 123
},
"total_tokens": 123,
"cost": {
"input_tokens_cost": 123,
"output_tokens_cost": 123,
"reasoning_tokens_cost": 123,
"citation_tokens_cost": 123,
"search_queries_cost": 123,
"request_cost": 123,
"total_cost": 123
}
},
"extra_fields": {
"request_type": "<string>",
"provider": "openai",
"model_requested": "<string>",
"model_deployment": "<string>",
"latency": 123,
"chunk_index": 123,
"raw_request": {},
"raw_response": {},
"cache_debug": {
"cache_hit": true,
"cache_id": "<string>",
"hit_type": "<string>",
"requested_provider": "<string>",
"requested_model": "<string>",
"provider_used": "<string>",
"model_used": "<string>",
"input_tokens": 123,
"threshold": 123,
"similarity": 123
}
}
}{
"event_id": "<string>",
"type": "<string>",
"is_vikat_error": true,
"status_code": 123,
"error": {
"type": "<string>",
"code": "<string>",
"message": "<string>",
"param": "<string>",
"event_id": "<string>"
},
"extra_fields": {
"provider": "openai",
"model_requested": "<string>",
"request_type": "<string>"
}
}{
"event_id": "<string>",
"type": "<string>",
"is_vikat_error": true,
"status_code": 123,
"error": {
"type": "<string>",
"code": "<string>",
"message": "<string>",
"param": "<string>",
"event_id": "<string>"
},
"extra_fields": {
"provider": "openai",
"model_requested": "<string>",
"request_type": "<string>"
}
}Authorizations
Bearer token authentication. Use your provider API key or Vikat authentication token.
Virtual keys (prefixed with sk-vk-, or the legacy sk-bf-) can also be passed here.
Body
Model identifier (e.g., "gpt-4o"). When routing through Vikat's provider-prefixed path, use "provider/model" format.
Conversation to compact. Required unless previous_response_id is set. Compaction items (type "response.compaction") from prior responses may be included.
System instructions that persist across the compacted context.
ID of a previous response to extend rather than sending full input.
Vikat-specific — fallback model list in provider/model format.
Response
Successful compaction response
Always "response.compaction"
"response.compaction"
The compacted output — the original user messages plus a final item of type "response.compaction" whose encrypted_content holds the opaque compacted state. Pass the full output array as input to a future Responses API request.
Show child attributes
Show child attributes
Show child attributes
Show child attributes
Additional fields included in responses
Show child attributes
Show child attributes