Create a model 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"
}LLM Gateway
Create a model pricing rule
POST
/
api
/
llm-gateway
/
admin
/
model-pricing
Create a model 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"
}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.
Body
application/json
Per-million-tokens rate billed for prompt-cache reads. Omit to inherit the Barndoor default (or leave NULL if the default has none, in which case the cost calculator falls back to the full input rate). Storing NULL preserves the "no override" semantics so a future seeder update can repopulate the default rate without the org row blocking it.
Per-million-tokens rate billed for the cache-creation premium
that Anthropic-family models charge on the request that populates
the prompt cache. Same NULL semantics as cache_read_cost.
Optional free-text note ("Q1 pricing review", "Negotiated discount") surfaced on the History dialog timeline.
When the price should take effect. Omit (or pass null) for
"right now". A timestamp in the future schedules the change and
records the row with change_source = 'admin_schedule' so the
History dialog can distinguish it from an immediate edit.
Optional context-tiered surcharge (BCP-3904). Omit for the normal case of one rate set at every prompt size.
Show child attributes
Show child attributes
Per-row sync behavior. Stored as a VARCHAR(16) constrained to
tracking | pinned | auto (see migration V33).
Available options:
tracking, pinned, auto Response
The created 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.