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 '
{
"input_cost_per_million_tokens": 123,
"model_pattern": "<string>",
"output_cost_per_million_tokens": 123,
"cache_read_cost_per_million_tokens": 123,
"cache_write_cost_per_million_tokens": 123,
"catalog_slug": "<string>",
"change_reason": "<string>",
"effective_from": "2023-11-07T05:31:56Z",
"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"
}
'import requests
url = "https://{host}/api/llm-gateway/admin/model-pricing"
payload = {
"input_cost_per_million_tokens": 123,
"model_pattern": "<string>",
"output_cost_per_million_tokens": 123,
"cache_read_cost_per_million_tokens": 123,
"cache_write_cost_per_million_tokens": 123,
"catalog_slug": "<string>",
"change_reason": "<string>",
"effective_from": "2023-11-07T05:31:56Z",
"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"
}
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({
input_cost_per_million_tokens: 123,
model_pattern: '<string>',
output_cost_per_million_tokens: 123,
cache_read_cost_per_million_tokens: 123,
cache_write_cost_per_million_tokens: 123,
catalog_slug: '<string>',
change_reason: '<string>',
effective_from: '2023-11-07T05:31:56Z',
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'
})
};
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([
'input_cost_per_million_tokens' => 123,
'model_pattern' => '<string>',
'output_cost_per_million_tokens' => 123,
'cache_read_cost_per_million_tokens' => 123,
'cache_write_cost_per_million_tokens' => 123,
'catalog_slug' => '<string>',
'change_reason' => '<string>',
'effective_from' => '2023-11-07T05:31:56Z',
'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'
]),
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 \"input_cost_per_million_tokens\": 123,\n \"model_pattern\": \"<string>\",\n \"output_cost_per_million_tokens\": 123,\n \"cache_read_cost_per_million_tokens\": 123,\n \"cache_write_cost_per_million_tokens\": 123,\n \"catalog_slug\": \"<string>\",\n \"change_reason\": \"<string>\",\n \"effective_from\": \"2023-11-07T05:31:56Z\",\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 \"model_provider\": \"<string>\",\n \"provider_id\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\"\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 \"input_cost_per_million_tokens\": 123,\n \"model_pattern\": \"<string>\",\n \"output_cost_per_million_tokens\": 123,\n \"cache_read_cost_per_million_tokens\": 123,\n \"cache_write_cost_per_million_tokens\": 123,\n \"catalog_slug\": \"<string>\",\n \"change_reason\": \"<string>\",\n \"effective_from\": \"2023-11-07T05:31:56Z\",\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 \"model_provider\": \"<string>\",\n \"provider_id\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\"\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 \"input_cost_per_million_tokens\": 123,\n \"model_pattern\": \"<string>\",\n \"output_cost_per_million_tokens\": 123,\n \"cache_read_cost_per_million_tokens\": 123,\n \"cache_write_cost_per_million_tokens\": 123,\n \"catalog_slug\": \"<string>\",\n \"change_reason\": \"<string>\",\n \"effective_from\": \"2023-11-07T05:31:56Z\",\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 \"model_provider\": \"<string>\",\n \"provider_id\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\"\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"
}{
"error": {
"message": "retry_on_429_count must be between 0 and 10",
"type": "invalid_request_error"
}
}{
"error": {
"message": "retry_on_429_count must be between 0 and 10",
"type": "invalid_request_error"
}
}{
"error": {
"message": "retry_on_429_count must be between 0 and 10",
"type": "invalid_request_error"
}
}{
"error": {
"message": "retry_on_429_count must be between 0 and 10",
"type": "invalid_request_error"
}
}LLM Gateway: Model Pricing
Create or Schedule Pricing
Creates a pricing rule, or appends a new version to an existing one. A rule is identified by model_provider and model_pattern.
- Omit
effective_from(or sendnull) to activate the price now. - Send a future
effective_fromto schedule the change.
Past versions are never modified; each price change adds a version to the rule’s history.
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 '
{
"input_cost_per_million_tokens": 123,
"model_pattern": "<string>",
"output_cost_per_million_tokens": 123,
"cache_read_cost_per_million_tokens": 123,
"cache_write_cost_per_million_tokens": 123,
"catalog_slug": "<string>",
"change_reason": "<string>",
"effective_from": "2023-11-07T05:31:56Z",
"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"
}
'import requests
url = "https://{host}/api/llm-gateway/admin/model-pricing"
payload = {
"input_cost_per_million_tokens": 123,
"model_pattern": "<string>",
"output_cost_per_million_tokens": 123,
"cache_read_cost_per_million_tokens": 123,
"cache_write_cost_per_million_tokens": 123,
"catalog_slug": "<string>",
"change_reason": "<string>",
"effective_from": "2023-11-07T05:31:56Z",
"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"
}
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({
input_cost_per_million_tokens: 123,
model_pattern: '<string>',
output_cost_per_million_tokens: 123,
cache_read_cost_per_million_tokens: 123,
cache_write_cost_per_million_tokens: 123,
catalog_slug: '<string>',
change_reason: '<string>',
effective_from: '2023-11-07T05:31:56Z',
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'
})
};
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([
'input_cost_per_million_tokens' => 123,
'model_pattern' => '<string>',
'output_cost_per_million_tokens' => 123,
'cache_read_cost_per_million_tokens' => 123,
'cache_write_cost_per_million_tokens' => 123,
'catalog_slug' => '<string>',
'change_reason' => '<string>',
'effective_from' => '2023-11-07T05:31:56Z',
'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'
]),
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 \"input_cost_per_million_tokens\": 123,\n \"model_pattern\": \"<string>\",\n \"output_cost_per_million_tokens\": 123,\n \"cache_read_cost_per_million_tokens\": 123,\n \"cache_write_cost_per_million_tokens\": 123,\n \"catalog_slug\": \"<string>\",\n \"change_reason\": \"<string>\",\n \"effective_from\": \"2023-11-07T05:31:56Z\",\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 \"model_provider\": \"<string>\",\n \"provider_id\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\"\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 \"input_cost_per_million_tokens\": 123,\n \"model_pattern\": \"<string>\",\n \"output_cost_per_million_tokens\": 123,\n \"cache_read_cost_per_million_tokens\": 123,\n \"cache_write_cost_per_million_tokens\": 123,\n \"catalog_slug\": \"<string>\",\n \"change_reason\": \"<string>\",\n \"effective_from\": \"2023-11-07T05:31:56Z\",\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 \"model_provider\": \"<string>\",\n \"provider_id\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\"\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 \"input_cost_per_million_tokens\": 123,\n \"model_pattern\": \"<string>\",\n \"output_cost_per_million_tokens\": 123,\n \"cache_read_cost_per_million_tokens\": 123,\n \"cache_write_cost_per_million_tokens\": 123,\n \"catalog_slug\": \"<string>\",\n \"change_reason\": \"<string>\",\n \"effective_from\": \"2023-11-07T05:31:56Z\",\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 \"model_provider\": \"<string>\",\n \"provider_id\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\"\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"
}{
"error": {
"message": "retry_on_429_count must be between 0 and 10",
"type": "invalid_request_error"
}
}{
"error": {
"message": "retry_on_429_count must be between 0 and 10",
"type": "invalid_request_error"
}
}{
"error": {
"message": "retry_on_429_count must be between 0 and 10",
"type": "invalid_request_error"
}
}{
"error": {
"message": "retry_on_429_count must be between 0 and 10",
"type": "invalid_request_error"
}
}Creates a new pricing version for a model. Pricing drives every cost-aware
feature on the platform — usage attribution, spend reporting, and
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 indicator in the Barndoor app.
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_TOKEN" \
-H "Content-Type: application/json" \
-d '{
"model_provider": "openai",
"model_pattern": "gpt-5.4-mini",
"input_cost_per_million_tokens": 0.60,
"output_cost_per_million_tokens": 3.60,
"sync_mode": "pinned",
"change_reason": "Q1 2026 negotiated discount"
}'
For wildcards, scheduling, and the four-tier resolution order, see
Manage Model Pricing.
Authorizations
An access token from Barndoor's identity provider, sent as Authorization: Bearer <token>. Use a service-account token from the OAuth 2.0 client-credentials grant for scripts and CI, or a signed-in user's token. The caller needs the admin role in the organization. Gateway API keys (bd-...) are not accepted here.
Body
application/json
Model name or glob pattern the rule prices, such as gpt-5.5 or claude-*.
Rate for input tokens read from the prompt cache. Omit to use the Barndoor default, or the input rate when there is none.
Rate for input tokens written to the prompt cache (the cache-creation premium some models charge). Omit for no override.
Provider catalog slug for provider-level pricing, such as openai or aws_bedrock.
Optional free-text note ("Q1 pricing review", "Negotiated discount") surfaced on the History dialog timeline.
When the price takes effect. Omit or send null for now; a future time schedules the change.
Optional higher rate set for large prompts. Omit when the model has one rate at every prompt size.
Show child attributes
Show child attributes
Provider family the rule applies to, such as openai. Omit to match any provider.
Limit the rule to one provider in your organization.
How the rule reacts to changes in Barndoor's default pricing. Defaults to pinned.
Available options:
tracking, pinned, auto Response
Created
One version of a pricing rule, with its sync mode and how the version was created.
When this version takes effect. The version with the latest effective_from in the past is the one billed.
How a pricing version was created: admin_create, admin_edit, admin_schedule, import, sync_manual, sync_auto, admin_archive, or admin_restore.
Available options:
admin_create, admin_edit, admin_schedule, import, sync_manual, sync_auto, admin_archive, admin_restore True for the version that archived the rule. Archived rules are excluded from GET /admin/model-pricing.
How the rule reacts to changes in Barndoor's default pricing.
Available options:
tracking, pinned, auto Rate for input tokens read from the prompt cache. Null means cached input is billed at the input rate.
Rate for input tokens written to the prompt cache. Null means no separate rate.
Catalog slug for provider-level pricing (e.g. "openai", "aws_bedrock").
Optional higher rate set for large prompts.
Show child attributes
Show child attributes
Optional reference to a specific LLM Gateway provider instance.
Free-text note recorded with this version.