Skip to content

Retrieve a stored response

GET
/responses/{response_id}
curl --request GET \
--url https://api.katara.com/v1/responses/example \
--header 'Authorization: Bearer <token>'

A response stored with a key is read with a key of the same account; one stored without a key, by whoever holds its id. Reads do not extend its 30-day retention.

response_id
required
string
/^resp_[A-Za-z0-9_-]{1,120}$/

The id of a stored response.

The stored response.

Media typeapplication/json
object
id
required
string
object
required
string
Allowed value: response
created_at
required

Unix seconds.

integer
status
required
string
Allowed values: in_progress completed incomplete failed
model
required
string
Allowed value: katara/cortex
previous_response_id
string | null
output
required

Assistant messages with output_text (and url_citation annotations for pages the answer quotes), function_call and custom_tool_call items, reasoning items and web_search_call items with their sources.

Array<object>
object
id
string
type
string
Allowed values: message reasoning function_call custom_tool_call web_search_call
status
string
Allowed values: in_progress completed incomplete
role
string
Allowed value: assistant
call_id
string
name
string
arguments
string
input
string
content
Array<object>
object
type
string
Allowed values: output_text reasoning_text
text
string
annotations
Array<object>
object
key
additional properties
any
key
additional properties
any
key
additional properties
any
usage
required
object
input_tokens
integer
output_tokens
integer
total_tokens
integer
input_tokens_details
object
cached_tokens
integer
cache_write_tokens
integer
output_tokens_details
object
reasoning_tokens
integer
katara
Any of:

What this reply cost.

object
cost_usdc
required

The settled price, in USDC, as a decimal string. For a request paid with x402 it is the charge, the model’s minimum included (0.025 USDC, 0.05 for katara/cortex-genius, 0.01 for katara/cortex-smart).

string
cost_usd

The Credits charge as a decimal string. This legacy field name is retained for compatibility; display Credits without a dollar sign.

string
billing_method
string
Allowed values: credits usdc
payment

On a request paid with x402, the payment that settles the reply.

object
scheme
string
Allowed values: upto exact
network
string
asset

The token paid.

string
amount

The charge in the token’s base units, the same as amount in PAYMENT-RESPONSE.

string
provider

The provider’s address, or managed when a vendor answered.

string
cached_tokens

Prompt tokens the vendor read from its cache, billed at the cached input rate.

integer
cache_saving_usdc

What the cached tokens saved against the input rate, in USDC.

string
cache_saving_usd

The same saving in Credits, on a reply paid with account credits.

string
compaction

When katara.compaction summarised the conversation.

object
message

The system message to send in place of the summarised messages.

object
replaces_from

First index in this request’s messages that the summary replaces.

integer
replaces_to

First index kept after it.

integer
model
string
tokens_before
integer
summary

The summary request’s usage and its cost (cost_usdc or cost_usd).

object
skipped

Why no summary was made; the request went whole.

string
context_edits
object
cleared_tool_results
integer
cleared_tokens
integer
through_turn
integer
cache_written_tokens

Tokens this request wrote to a new explicit cache (katara.cache).

integer
cache_ttl_seconds

How long that cache is kept.

integer
cache_storage_usdc

What keeping it costs, in USDC; included in cost_usdc.

string
simulated

On Test, a reply with fixed text that no model wrote, served when no Test provider was free.

boolean
stop_sequence

The stop sequence at which Katara ended the reply.

string
web_search

The searches this request was charged for.

object
requests

The successful searches; only those are charged, and none when the request ended without an answer.

integer
cost_usdc
string
cost_usd
string
model_calls

On a web search request, how many model calls it made.

integer
web_searches

Every search the model made, in order. Not on stream chunks, which carry each search as it runs.

Array<object>
object
id
required
string
query
required
string
results
required
Array<object>
object
url
string
title
string
page_age
string
content
string
error
string
Allowed values: invalid_input query_too_long too_many_requests unavailable max_uses_exceeded insufficient_quota
edit_id

On an image reply from a model that edits, the id to send as previous_edit_id.

string
metadata
object | null
incomplete_details
object
reason
string
Allowed values: max_output_tokens content_filter
error
object
code
string
message
string
Example
{
"object": "response",
"status": "in_progress",
"model": "katara/cortex",
"output": [
{
"type": "message",
"status": "in_progress",
"role": "assistant",
"content": [
{
"type": "output_text"
}
]
}
],
"katara": {
"cost_usdc": "0.000018",
"cost_usd": "0.000018",
"billing_method": "credits",
"payment": {
"scheme": "upto",
"network": "eip155:43114",
"amount": "25000"
},
"web_searches": [
{
"error": "invalid_input"
}
]
},
"incomplete_details": {
"reason": "max_output_tokens"
}
}

stream=true was asked for (unsupported_parameter).

Media typeapplication/json
object
error
required
object
type
string
code
required

Stable error code.

string
message
required

Explanation for the caller.

string
param
string | null
Examplegenerated
{
"error": {
"type": "example",
"code": "example",
"message": "example",
"param": "example"
}
}

The response is missing, expired, deleted or someone else’s (response_not_found).

Media typeapplication/json
object
error
required
object
type
string
code
required

Stable error code.

string
message
required

Explanation for the caller.

string
param
string | null
Examplegenerated
{
"error": {
"type": "example",
"code": "example",
"message": "example",
"param": "example"
}
}