Update a model pricing rule
curl --request PUT \
--url https://{host}/api/llm-gateway/admin/model-pricing/{id} \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"cache_read_cost_per_million_tokens": 123,
"cache_write_cost_per_million_tokens": 123,
"change_reason": "<string>",
"effective_from": "2023-11-07T05:31:56Z",
"input_cost_per_million_tokens": 123,
"long_context": {
"input_cost_per_million_tokens": 123,
"output_cost_per_million_tokens": 123,
"threshold_prompt_tokens": 123,
"cache_read_cost_per_million_tokens": 123,
"cache_write_cost_per_million_tokens": 123
},
"output_cost_per_million_tokens": 123
}
'import requests
url = "https://{host}/api/llm-gateway/admin/model-pricing/{id}"
payload = {
"cache_read_cost_per_million_tokens": 123,
"cache_write_cost_per_million_tokens": 123,
"change_reason": "<string>",
"effective_from": "2023-11-07T05:31:56Z",
"input_cost_per_million_tokens": 123,
"long_context": {
"input_cost_per_million_tokens": 123,
"output_cost_per_million_tokens": 123,
"threshold_prompt_tokens": 123,
"cache_read_cost_per_million_tokens": 123,
"cache_write_cost_per_million_tokens": 123
},
"output_cost_per_million_tokens": 123
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.put(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'PUT',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({
cache_read_cost_per_million_tokens: 123,
cache_write_cost_per_million_tokens: 123,
change_reason: '<string>',
effective_from: '2023-11-07T05:31:56Z',
input_cost_per_million_tokens: 123,
long_context: {
input_cost_per_million_tokens: 123,
output_cost_per_million_tokens: 123,
threshold_prompt_tokens: 123,
cache_read_cost_per_million_tokens: 123,
cache_write_cost_per_million_tokens: 123
},
output_cost_per_million_tokens: 123
})
};
fetch('https://{host}/api/llm-gateway/admin/model-pricing/{id}', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://{host}/api/llm-gateway/admin/model-pricing/{id}",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "PUT",
CURLOPT_POSTFIELDS => json_encode([
'cache_read_cost_per_million_tokens' => 123,
'cache_write_cost_per_million_tokens' => 123,
'change_reason' => '<string>',
'effective_from' => '2023-11-07T05:31:56Z',
'input_cost_per_million_tokens' => 123,
'long_context' => [
'input_cost_per_million_tokens' => 123,
'output_cost_per_million_tokens' => 123,
'threshold_prompt_tokens' => 123,
'cache_read_cost_per_million_tokens' => 123,
'cache_write_cost_per_million_tokens' => 123
],
'output_cost_per_million_tokens' => 123
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://{host}/api/llm-gateway/admin/model-pricing/{id}"
payload := strings.NewReader("{\n \"cache_read_cost_per_million_tokens\": 123,\n \"cache_write_cost_per_million_tokens\": 123,\n \"change_reason\": \"<string>\",\n \"effective_from\": \"2023-11-07T05:31:56Z\",\n \"input_cost_per_million_tokens\": 123,\n \"long_context\": {\n \"input_cost_per_million_tokens\": 123,\n \"output_cost_per_million_tokens\": 123,\n \"threshold_prompt_tokens\": 123,\n \"cache_read_cost_per_million_tokens\": 123,\n \"cache_write_cost_per_million_tokens\": 123\n },\n \"output_cost_per_million_tokens\": 123\n}")
req, _ := http.NewRequest("PUT", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.put("https://{host}/api/llm-gateway/admin/model-pricing/{id}")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"cache_read_cost_per_million_tokens\": 123,\n \"cache_write_cost_per_million_tokens\": 123,\n \"change_reason\": \"<string>\",\n \"effective_from\": \"2023-11-07T05:31:56Z\",\n \"input_cost_per_million_tokens\": 123,\n \"long_context\": {\n \"input_cost_per_million_tokens\": 123,\n \"output_cost_per_million_tokens\": 123,\n \"threshold_prompt_tokens\": 123,\n \"cache_read_cost_per_million_tokens\": 123,\n \"cache_write_cost_per_million_tokens\": 123\n },\n \"output_cost_per_million_tokens\": 123\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://{host}/api/llm-gateway/admin/model-pricing/{id}")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Put.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"cache_read_cost_per_million_tokens\": 123,\n \"cache_write_cost_per_million_tokens\": 123,\n \"change_reason\": \"<string>\",\n \"effective_from\": \"2023-11-07T05:31:56Z\",\n \"input_cost_per_million_tokens\": 123,\n \"long_context\": {\n \"input_cost_per_million_tokens\": 123,\n \"output_cost_per_million_tokens\": 123,\n \"threshold_prompt_tokens\": 123,\n \"cache_read_cost_per_million_tokens\": 123,\n \"cache_write_cost_per_million_tokens\": 123\n },\n \"output_cost_per_million_tokens\": 123\n}"
response = http.request(request)
puts response.read_body{
"effective_from": "2023-11-07T05:31:56Z",
"id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"input_cost_per_million_tokens": 123,
"model_pattern": "<string>",
"org_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"output_cost_per_million_tokens": 123,
"change_source": "admin_create",
"is_archived": true,
"sync_mode": "tracking",
"cache_read_cost_per_million_tokens": 123,
"cache_write_cost_per_million_tokens": 123,
"catalog_slug": "<string>",
"long_context": {
"input_cost_per_million_tokens": 123,
"output_cost_per_million_tokens": 123,
"threshold_prompt_tokens": 123,
"cache_read_cost_per_million_tokens": 123,
"cache_write_cost_per_million_tokens": 123
},
"model_provider": "<string>",
"provider_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"provider_name": "<string>",
"change_reason": "<string>",
"created_by_email": "<string>",
"created_by_name": "<string>",
"created_by_user_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a"
}LLM Gateway
Update a model pricing rule
PUT
/
api
/
llm-gateway
/
admin
/
model-pricing
/
{id}
Update a model pricing rule
curl --request PUT \
--url https://{host}/api/llm-gateway/admin/model-pricing/{id} \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"cache_read_cost_per_million_tokens": 123,
"cache_write_cost_per_million_tokens": 123,
"change_reason": "<string>",
"effective_from": "2023-11-07T05:31:56Z",
"input_cost_per_million_tokens": 123,
"long_context": {
"input_cost_per_million_tokens": 123,
"output_cost_per_million_tokens": 123,
"threshold_prompt_tokens": 123,
"cache_read_cost_per_million_tokens": 123,
"cache_write_cost_per_million_tokens": 123
},
"output_cost_per_million_tokens": 123
}
'import requests
url = "https://{host}/api/llm-gateway/admin/model-pricing/{id}"
payload = {
"cache_read_cost_per_million_tokens": 123,
"cache_write_cost_per_million_tokens": 123,
"change_reason": "<string>",
"effective_from": "2023-11-07T05:31:56Z",
"input_cost_per_million_tokens": 123,
"long_context": {
"input_cost_per_million_tokens": 123,
"output_cost_per_million_tokens": 123,
"threshold_prompt_tokens": 123,
"cache_read_cost_per_million_tokens": 123,
"cache_write_cost_per_million_tokens": 123
},
"output_cost_per_million_tokens": 123
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.put(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'PUT',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({
cache_read_cost_per_million_tokens: 123,
cache_write_cost_per_million_tokens: 123,
change_reason: '<string>',
effective_from: '2023-11-07T05:31:56Z',
input_cost_per_million_tokens: 123,
long_context: {
input_cost_per_million_tokens: 123,
output_cost_per_million_tokens: 123,
threshold_prompt_tokens: 123,
cache_read_cost_per_million_tokens: 123,
cache_write_cost_per_million_tokens: 123
},
output_cost_per_million_tokens: 123
})
};
fetch('https://{host}/api/llm-gateway/admin/model-pricing/{id}', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://{host}/api/llm-gateway/admin/model-pricing/{id}",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "PUT",
CURLOPT_POSTFIELDS => json_encode([
'cache_read_cost_per_million_tokens' => 123,
'cache_write_cost_per_million_tokens' => 123,
'change_reason' => '<string>',
'effective_from' => '2023-11-07T05:31:56Z',
'input_cost_per_million_tokens' => 123,
'long_context' => [
'input_cost_per_million_tokens' => 123,
'output_cost_per_million_tokens' => 123,
'threshold_prompt_tokens' => 123,
'cache_read_cost_per_million_tokens' => 123,
'cache_write_cost_per_million_tokens' => 123
],
'output_cost_per_million_tokens' => 123
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://{host}/api/llm-gateway/admin/model-pricing/{id}"
payload := strings.NewReader("{\n \"cache_read_cost_per_million_tokens\": 123,\n \"cache_write_cost_per_million_tokens\": 123,\n \"change_reason\": \"<string>\",\n \"effective_from\": \"2023-11-07T05:31:56Z\",\n \"input_cost_per_million_tokens\": 123,\n \"long_context\": {\n \"input_cost_per_million_tokens\": 123,\n \"output_cost_per_million_tokens\": 123,\n \"threshold_prompt_tokens\": 123,\n \"cache_read_cost_per_million_tokens\": 123,\n \"cache_write_cost_per_million_tokens\": 123\n },\n \"output_cost_per_million_tokens\": 123\n}")
req, _ := http.NewRequest("PUT", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.put("https://{host}/api/llm-gateway/admin/model-pricing/{id}")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"cache_read_cost_per_million_tokens\": 123,\n \"cache_write_cost_per_million_tokens\": 123,\n \"change_reason\": \"<string>\",\n \"effective_from\": \"2023-11-07T05:31:56Z\",\n \"input_cost_per_million_tokens\": 123,\n \"long_context\": {\n \"input_cost_per_million_tokens\": 123,\n \"output_cost_per_million_tokens\": 123,\n \"threshold_prompt_tokens\": 123,\n \"cache_read_cost_per_million_tokens\": 123,\n \"cache_write_cost_per_million_tokens\": 123\n },\n \"output_cost_per_million_tokens\": 123\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://{host}/api/llm-gateway/admin/model-pricing/{id}")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Put.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"cache_read_cost_per_million_tokens\": 123,\n \"cache_write_cost_per_million_tokens\": 123,\n \"change_reason\": \"<string>\",\n \"effective_from\": \"2023-11-07T05:31:56Z\",\n \"input_cost_per_million_tokens\": 123,\n \"long_context\": {\n \"input_cost_per_million_tokens\": 123,\n \"output_cost_per_million_tokens\": 123,\n \"threshold_prompt_tokens\": 123,\n \"cache_read_cost_per_million_tokens\": 123,\n \"cache_write_cost_per_million_tokens\": 123\n },\n \"output_cost_per_million_tokens\": 123\n}"
response = http.request(request)
puts response.read_body{
"effective_from": "2023-11-07T05:31:56Z",
"id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"input_cost_per_million_tokens": 123,
"model_pattern": "<string>",
"org_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"output_cost_per_million_tokens": 123,
"change_source": "admin_create",
"is_archived": true,
"sync_mode": "tracking",
"cache_read_cost_per_million_tokens": 123,
"cache_write_cost_per_million_tokens": 123,
"catalog_slug": "<string>",
"long_context": {
"input_cost_per_million_tokens": 123,
"output_cost_per_million_tokens": 123,
"threshold_prompt_tokens": 123,
"cache_read_cost_per_million_tokens": 123,
"cache_write_cost_per_million_tokens": 123
},
"model_provider": "<string>",
"provider_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"provider_name": "<string>",
"change_reason": "<string>",
"created_by_email": "<string>",
"created_by_name": "<string>",
"created_by_user_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a"
}Authorizations
ApiKeyOAuth2
A Barndoor API key, sent as Authorization: Bearer <key>. Keys are prefixed bdai_ and are opaque — do not attempt to decode one. Interchangeable with an OAuth 2.0 access token.
Path Parameters
Identifier, a UUID
Body
application/json
Update prompt-cache rates. Same NULL semantics as
CreatePricingRequest: omitted = leave existing value alone;
JSON null = explicitly clear the override.
Reschedule the activation date. Past values are rejected by the
db layer's update_scheduled guard, but a future timestamp is
fine and a near-now() timestamp effectively "activates now".
Update the long-context surcharge (BCP-3904). Same three-state
semantics as the cache rates: omitted = leave the tier alone, JSON
null = remove the tier entirely, an object = set it.
The tier moves as a unit, so null clears the threshold and every
tier rate together — there is no way to null out one tier rate while
keeping the others, which is what the DB constraint requires anyway.
Show child attributes
Show child attributes
Omit (or pass null) to leave the mode unchanged.
Available options:
tracking, pinned, auto Response
The requested record
Admin-API response shape for a single pricing row. Wraps the
ai_governance::ModelPricing used by the cost calculator so that the hot
path stays sync-mode-agnostic, while the admin surface still gets the
metadata it needs to render badges, the Review-updates dialog, and (as
of BCP-2830 v2 / V34) the per-row history timeline.
How a model_pricing version was produced. Persisted as a
VARCHAR(20) constrained to one of these eight values (see
migrations V34 + V35). Surfaced to admins as the "source" badge on
each entry of the PricingHistoryDialog.
Available options:
admin_create, admin_edit, admin_schedule, import, sync_manual, sync_auto, admin_archive, admin_restore True for tombstone rows produced by archive_rule (V35). When
the latest effective version of a group has is_archived = true,
the rule is considered archived: the cost calculator skips it
and the admin summary list hides it by default. Past non-archived
versions remain in the timeline so the History dialog can show
the rule's full life including the archive event.
Per-row sync behavior. Stored as a VARCHAR(16) constrained to
tracking | pinned | auto (see migration V33).
Available options:
tracking, pinned, auto Per-million-token cost for input tokens served from the prompt
cache. None ⇒ the calculator bills cached input at
input_cost_per_million_tokens.
Per-million-token cost for input tokens added to the prompt cache.
None ⇒ same fallback as cache_read_cost_per_million_tokens.
Catalog slug for provider-level pricing (e.g. "openai", "aws_bedrock").
Optional context-tiered surcharge (BCP-3904). None ⇒ one rate set
at every prompt size, i.e. exactly the pre-BCP-3904 behaviour.
Serialized as long_context, not as the Rust field name. This struct
reaches the admin API through AdminModelPricing's
#[serde(flatten)], so the field name here is the wire key — and
every sibling surface (DefaultPricingEntry, EffectivePricing, the
create/update request bodies) already spells it long_context. Left
unrenamed, the pricing tab would write a tier successfully and then
read back nothing, which is precisely how it behaved before this
attribute existed: the surcharge saved, the dialog reopened unchecked,
and the edit looked silently discarded. Pinned by
admin_model_pricing_serializes_the_tier_as_long_context.
Show child attributes
Show child attributes
Optional reference to a specific LLM Gateway provider instance.