Create or schedule a pricing rule
curl --request POST \
--url https://{host}/api/llm-gateway/admin/model-pricing \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model_pattern": "gpt-4o-mini",
"input_cost_per_million_tokens": 123,
"output_cost_per_million_tokens": 123,
"model_provider": "<string>",
"effective_from": "2023-11-07T05:31:56Z",
"provider_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"catalog_slug": "<string>",
"change_reason": "Q1 negotiated pricing",
"cache_read_cost_per_million_tokens": 123,
"cache_write_cost_per_million_tokens": 123
}
'import requests
url = "https://{host}/api/llm-gateway/admin/model-pricing"
payload = {
"model_pattern": "gpt-4o-mini",
"input_cost_per_million_tokens": 123,
"output_cost_per_million_tokens": 123,
"model_provider": "<string>",
"effective_from": "2023-11-07T05:31:56Z",
"provider_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"catalog_slug": "<string>",
"change_reason": "Q1 negotiated pricing",
"cache_read_cost_per_million_tokens": 123,
"cache_write_cost_per_million_tokens": 123
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({
model_pattern: 'gpt-4o-mini',
input_cost_per_million_tokens: 123,
output_cost_per_million_tokens: 123,
model_provider: '<string>',
effective_from: '2023-11-07T05:31:56Z',
provider_id: '3c90c3cc-0d44-4b50-8888-8dd25736052a',
catalog_slug: '<string>',
change_reason: 'Q1 negotiated pricing',
cache_read_cost_per_million_tokens: 123,
cache_write_cost_per_million_tokens: 123
})
};
fetch('https://{host}/api/llm-gateway/admin/model-pricing', 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",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'model_pattern' => 'gpt-4o-mini',
'input_cost_per_million_tokens' => 123,
'output_cost_per_million_tokens' => 123,
'model_provider' => '<string>',
'effective_from' => '2023-11-07T05:31:56Z',
'provider_id' => '3c90c3cc-0d44-4b50-8888-8dd25736052a',
'catalog_slug' => '<string>',
'change_reason' => 'Q1 negotiated pricing',
'cache_read_cost_per_million_tokens' => 123,
'cache_write_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"
payload := strings.NewReader("{\n \"model_pattern\": \"gpt-4o-mini\",\n \"input_cost_per_million_tokens\": 123,\n \"output_cost_per_million_tokens\": 123,\n \"model_provider\": \"<string>\",\n \"effective_from\": \"2023-11-07T05:31:56Z\",\n \"provider_id\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\",\n \"catalog_slug\": \"<string>\",\n \"change_reason\": \"Q1 negotiated pricing\",\n \"cache_read_cost_per_million_tokens\": 123,\n \"cache_write_cost_per_million_tokens\": 123\n}")
req, _ := http.NewRequest("POST", 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.post("https://{host}/api/llm-gateway/admin/model-pricing")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"model_pattern\": \"gpt-4o-mini\",\n \"input_cost_per_million_tokens\": 123,\n \"output_cost_per_million_tokens\": 123,\n \"model_provider\": \"<string>\",\n \"effective_from\": \"2023-11-07T05:31:56Z\",\n \"provider_id\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\",\n \"catalog_slug\": \"<string>\",\n \"change_reason\": \"Q1 negotiated pricing\",\n \"cache_read_cost_per_million_tokens\": 123,\n \"cache_write_cost_per_million_tokens\": 123\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://{host}/api/llm-gateway/admin/model-pricing")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"model_pattern\": \"gpt-4o-mini\",\n \"input_cost_per_million_tokens\": 123,\n \"output_cost_per_million_tokens\": 123,\n \"model_provider\": \"<string>\",\n \"effective_from\": \"2023-11-07T05:31:56Z\",\n \"provider_id\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\",\n \"catalog_slug\": \"<string>\",\n \"change_reason\": \"Q1 negotiated pricing\",\n \"cache_read_cost_per_million_tokens\": 123,\n \"cache_write_cost_per_million_tokens\": 123\n}"
response = http.request(request)
puts response.read_body{
"id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"org_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"model_pattern": "gpt-4o-mini",
"input_cost_per_million_tokens": 0.15,
"output_cost_per_million_tokens": 0.6,
"effective_from": "2023-11-07T05:31:56Z",
"sync_mode": "tracking",
"change_source": "admin_create",
"is_archived": true,
"model_provider": "<string>",
"provider_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"catalog_slug": "<string>",
"cache_read_cost_per_million_tokens": 123,
"cache_write_cost_per_million_tokens": 123,
"change_reason": "<string>",
"created_by_user_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"created_by_email": "<string>"
}{
"error": "BadRequest",
"message": "request_timeout_secs must be between 1 and 3600"
}LLM Gateway: Model Pricing
Create or Schedule Pricing
- Omit (or
null)effective_fromto activate the price now. - Pass a future
effective_fromto schedule the change ahead of time.
POST
/
admin
/
model-pricing
Create or schedule a pricing rule
curl --request POST \
--url https://{host}/api/llm-gateway/admin/model-pricing \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model_pattern": "gpt-4o-mini",
"input_cost_per_million_tokens": 123,
"output_cost_per_million_tokens": 123,
"model_provider": "<string>",
"effective_from": "2023-11-07T05:31:56Z",
"provider_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"catalog_slug": "<string>",
"change_reason": "Q1 negotiated pricing",
"cache_read_cost_per_million_tokens": 123,
"cache_write_cost_per_million_tokens": 123
}
'import requests
url = "https://{host}/api/llm-gateway/admin/model-pricing"
payload = {
"model_pattern": "gpt-4o-mini",
"input_cost_per_million_tokens": 123,
"output_cost_per_million_tokens": 123,
"model_provider": "<string>",
"effective_from": "2023-11-07T05:31:56Z",
"provider_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"catalog_slug": "<string>",
"change_reason": "Q1 negotiated pricing",
"cache_read_cost_per_million_tokens": 123,
"cache_write_cost_per_million_tokens": 123
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({
model_pattern: 'gpt-4o-mini',
input_cost_per_million_tokens: 123,
output_cost_per_million_tokens: 123,
model_provider: '<string>',
effective_from: '2023-11-07T05:31:56Z',
provider_id: '3c90c3cc-0d44-4b50-8888-8dd25736052a',
catalog_slug: '<string>',
change_reason: 'Q1 negotiated pricing',
cache_read_cost_per_million_tokens: 123,
cache_write_cost_per_million_tokens: 123
})
};
fetch('https://{host}/api/llm-gateway/admin/model-pricing', 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",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'model_pattern' => 'gpt-4o-mini',
'input_cost_per_million_tokens' => 123,
'output_cost_per_million_tokens' => 123,
'model_provider' => '<string>',
'effective_from' => '2023-11-07T05:31:56Z',
'provider_id' => '3c90c3cc-0d44-4b50-8888-8dd25736052a',
'catalog_slug' => '<string>',
'change_reason' => 'Q1 negotiated pricing',
'cache_read_cost_per_million_tokens' => 123,
'cache_write_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"
payload := strings.NewReader("{\n \"model_pattern\": \"gpt-4o-mini\",\n \"input_cost_per_million_tokens\": 123,\n \"output_cost_per_million_tokens\": 123,\n \"model_provider\": \"<string>\",\n \"effective_from\": \"2023-11-07T05:31:56Z\",\n \"provider_id\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\",\n \"catalog_slug\": \"<string>\",\n \"change_reason\": \"Q1 negotiated pricing\",\n \"cache_read_cost_per_million_tokens\": 123,\n \"cache_write_cost_per_million_tokens\": 123\n}")
req, _ := http.NewRequest("POST", 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.post("https://{host}/api/llm-gateway/admin/model-pricing")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"model_pattern\": \"gpt-4o-mini\",\n \"input_cost_per_million_tokens\": 123,\n \"output_cost_per_million_tokens\": 123,\n \"model_provider\": \"<string>\",\n \"effective_from\": \"2023-11-07T05:31:56Z\",\n \"provider_id\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\",\n \"catalog_slug\": \"<string>\",\n \"change_reason\": \"Q1 negotiated pricing\",\n \"cache_read_cost_per_million_tokens\": 123,\n \"cache_write_cost_per_million_tokens\": 123\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://{host}/api/llm-gateway/admin/model-pricing")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"model_pattern\": \"gpt-4o-mini\",\n \"input_cost_per_million_tokens\": 123,\n \"output_cost_per_million_tokens\": 123,\n \"model_provider\": \"<string>\",\n \"effective_from\": \"2023-11-07T05:31:56Z\",\n \"provider_id\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\",\n \"catalog_slug\": \"<string>\",\n \"change_reason\": \"Q1 negotiated pricing\",\n \"cache_read_cost_per_million_tokens\": 123,\n \"cache_write_cost_per_million_tokens\": 123\n}"
response = http.request(request)
puts response.read_body{
"id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"org_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"model_pattern": "gpt-4o-mini",
"input_cost_per_million_tokens": 0.15,
"output_cost_per_million_tokens": 0.6,
"effective_from": "2023-11-07T05:31:56Z",
"sync_mode": "tracking",
"change_source": "admin_create",
"is_archived": true,
"model_provider": "<string>",
"provider_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"catalog_slug": "<string>",
"cache_read_cost_per_million_tokens": 123,
"cache_write_cost_per_million_tokens": 123,
"change_reason": "<string>",
"created_by_user_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"created_by_email": "<string>"
}{
"error": "BadRequest",
"message": "request_timeout_secs must be between 1 and 3600"
}Creates a new pricing version for a model. Pricing drives every cost-aware
feature on the platform — usage attribution, spend reporting, and
token budgets with a
cost_limit.
Activate now or schedule for later
Theeffective_from field decides whether the change is immediate or
scheduled:
- Omit (or
null) — the price activates immediately and replaces the current effective price for this rule. - Future timestamp — the price activates on that date, recorded as a scheduled change. Visible to admins via the history endpoint and the Scheduled affordance in the portal.
effective_from.
Sync mode
sync_mode controls whether Barndoor’s seeded defaults can move this row
later:
pinned(default for manually-created rules) — never auto-sync.tracking— show the user a prompt when defaults change.auto— silently follow the default. Useful when you want to outsource pricing maintenance entirely to Barndoor.
Example
curl -X POST https://app.barndoor.ai/api/llm-gateway/admin/model-pricing \
-H "Authorization: Bearer $BARNDOOR_JWT" \
-H "Content-Type: application/json" \
-d '{
"model_provider": "openai",
"model_pattern": "gpt-4o-mini",
"input_cost_per_million_tokens": 0.15,
"output_cost_per_million_tokens": 0.60,
"sync_mode": "pinned",
"change_reason": "Q1 2026 negotiated discount"
}'
For wildcards, scheduling, and the four-tier resolution order, see
Manage Model Pricing.
Authorizations
JWT obtained through Barndoor's authentication flow. Pass the token
verbatim in Authorization: Bearer <token>. Use the Barndoor SDK's
loginInteractive() helper to obtain a token in scripts and notebooks.
Body
application/json
Example:
"gpt-4o-mini"
Optional. Defaults to catalog_slug if both are unset.
When the price activates. Omit (or null) for "now". A future
timestamp creates a scheduled change.
How the row tracks Barndoor's managed defaults:
tracking— show the user a prompt when defaults changepinned— never sync; this is your numberauto— silently follow updates to the managed defaults
Available options:
tracking, pinned, auto Example:
"Q1 negotiated pricing"
Response
The created or no-op'd pricing version
A single pricing rule version. Each "rule" (logical row) has a stack
of versions; the latest version with effective_from <= now() is the
one that bills.
Upstream model name (or * wildcard)
Example:
"gpt-4o-mini"
Example:
0.15
Example:
0.6
When this version takes effect. Past = active; future = scheduled
How the row tracks Barndoor's managed defaults:
tracking— show the user a prompt when defaults changepinned— never sync; this is your numberauto— silently follow updates to the managed defaults
Available options:
tracking, pinned, auto How this version of the pricing rule was produced
Available options:
admin_create, admin_edit, admin_schedule, import, sync_manual, sync_auto, admin_archive, admin_restore When set, the rule only applies to routes served by this provider