laantungir/routstr-core
1
0
Fork 0
mirror of https://github.com/Routstr/routstr-core.git synced 2026-08-12 04:03:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #583 from Routstr/fix/cache-pricing-ui

Browse Source 
make cache prices configurable
This commit is contained in:
9qeklajc
2026-07-04 21:54:30 +02:00
committed by GitHub
parent 81658d0ba6 12c4c1f030
commit c81de0de0a
3 changed files with 281 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/integration/test_admin_model_cache_pricing.py
+229
View File
@@ -0,0 +1,229 @@
import json
from datetime import datetime, timedelta, timezone
from unittest.mock import patch
import pytest
from httpx import AsyncClient
from sqlmodel.ext.asyncio.session import AsyncSession
from routstr.core.admin import admin_sessions
from routstr.core.db import ModelRow, UpstreamProviderRow
from routstr.payment.cost_calculation import CostData, calculate_cost
from routstr.proxy import get_model_instance, reinitialize_upstreams
def _admin_headers() -> dict[str, str]:
token = "test-admin-cache-pricing-token"
admin_sessions[token] = int(
(datetime.now(timezone.utc) + timedelta(minutes=5)).timestamp()
)
return {"Authorization": f"Bearer {token}"}
def _model_payload(
provider_id: int,
*,
cache_read: float,
cache_write: float,
) -> dict[str, object]:
return {
"id": "custom-cache-model",
"name": "Custom Cache Model",
"description": "custom model with explicit cache pricing",
"created": 0,
"context_length": 128000,
"architecture": {
"modality": "text",
"input_modalities": ["text"],
"output_modalities": ["text"],
"tokenizer": "unknown",
"instruct_type": None,
},
"pricing": {
"prompt": 1.4e-7,
"completion": 2.8e-7,
"input_cache_read": cache_read,
"input_cache_write": cache_write,
"request": 0.0,
"image": 0.0,
"web_search": 0.0,
"internal_reasoning": 0.0,
},
"per_request_limits": None,
"top_provider": None,
"upstream_provider_id": provider_id,
"canonical_slug": None,
"alias_ids": [],
"enabled": True,
"forwarded_model_id": "custom-cache-model",
}
@pytest.mark.integration
@pytest.mark.asyncio
async def test_admin_provider_model_api_persists_cache_pricing_on_create_and_update(
integration_client: AsyncClient,
integration_session: AsyncSession,
) -> None:
provider = UpstreamProviderRow(
provider_type="generic",
base_url="https://custom-upstream.example/v1",
api_key="test-key",
provider_fee=1.0,
)
integration_session.add(provider)
await integration_session.commit()
await integration_session.refresh(provider)
assert provider.id is not None
await reinitialize_upstreams()
headers = _admin_headers()
create_payload = _model_payload(
provider.id,
cache_read=2.8e-9,
cache_write=3.5e-9,
)
with patch("routstr.payment.models.sats_usd_price", return_value=1e-6):
create_response = await integration_client.post(
f"/admin/api/upstream-providers/{provider.id}/models",
headers=headers,
json=create_payload,
)
assert create_response.status_code == 200
create_body = create_response.json()
assert create_body["pricing"]["input_cache_read"] == pytest.approx(2.8e-9)
assert create_body["pricing"]["input_cache_write"] == pytest.approx(3.5e-9)
row = await integration_session.get(ModelRow, ("custom-cache-model", provider.id))
assert row is not None
stored_pricing = json.loads(row.pricing)
assert stored_pricing["input_cache_read"] == pytest.approx(2.8e-9)
assert stored_pricing["input_cache_write"] == pytest.approx(3.5e-9)
update_payload = _model_payload(
provider.id,
cache_read=1.25e-9,
cache_write=4.5e-9,
)
with patch("routstr.payment.models.sats_usd_price", return_value=1e-6):
update_response = await integration_client.post(
f"/admin/api/upstream-providers/{provider.id}/models",
headers=headers,
json=update_payload,
)
assert update_response.status_code == 200
update_body = update_response.json()
assert update_body["pricing"]["input_cache_read"] == pytest.approx(1.25e-9)
assert update_body["pricing"]["input_cache_write"] == pytest.approx(4.5e-9)
await integration_session.refresh(row)
updated_pricing = json.loads(row.pricing)
assert updated_pricing["input_cache_read"] == pytest.approx(1.25e-9)
assert updated_pricing["input_cache_write"] == pytest.approx(4.5e-9)
model = get_model_instance("custom-cache-model")
assert model is not None
assert model.sats_pricing is not None
assert model.sats_pricing.input_cache_read == pytest.approx(0.00125)
assert model.sats_pricing.input_cache_write == pytest.approx(0.0045)
with patch("routstr.payment.cost_calculation.sats_usd_price", return_value=1e-6):
cost = await calculate_cost(
{
"model": "custom-cache-model",
"usage": {
"prompt_tokens": 1000,
"completion_tokens": 100,
"prompt_tokens_details": {"cached_tokens": 800},
},
},
max_cost=1_000_000,
)
assert isinstance(cost, CostData)
assert cost.input_tokens == 200
assert cost.cache_read_input_tokens == 800
assert cost.cache_read_msats == 1000
assert cost.output_msats == 28000
assert cost.input_msats == 29000
assert cost.total_msats == 57000
@pytest.mark.integration
@pytest.mark.asyncio
async def test_upstream_response_cost_uses_model_cache_pricing(
integration_session: AsyncSession,
patched_db_engine: None,
) -> None:
"""A model's configured cache price must discount upstream cached-token usage."""
provider = UpstreamProviderRow(
provider_type="generic",
base_url="https://cache-priced-upstream.example/v1",
api_key="test-key",
provider_fee=1.0,
)
integration_session.add(provider)
await integration_session.commit()
await integration_session.refresh(provider)
assert provider.id is not None
row = ModelRow(
id="cache-priced-model",
name="Cache Priced Model",
description="model seeded with explicit cache pricing",
created=0,
context_length=128000,
architecture=json.dumps(
{
"modality": "text",
"input_modalities": ["text"],
"output_modalities": ["text"],
"tokenizer": "unknown",
"instruct_type": None,
}
),
pricing=json.dumps(
{
"prompt": 1.4e-7,
"completion": 2.8e-7,
"input_cache_read": 1.25e-9,
"input_cache_write": 4.5e-9,
}
),
upstream_provider_id=provider.id,
enabled=True,
forwarded_model_id="cache-priced-model",
)
integration_session.add(row)
await integration_session.commit()
with patch("routstr.payment.models.sats_usd_price", return_value=1e-6):
await reinitialize_upstreams()
with patch("routstr.payment.cost_calculation.sats_usd_price", return_value=1e-6):
cost = await calculate_cost(
{
"model": "cache-priced-model",
"usage": {
"prompt_tokens": 1000,
"completion_tokens": 100,
"prompt_tokens_details": {"cached_tokens": 800},
},
},
max_cost=1_000_000,
)
assert isinstance(cost, CostData)
# prompt 1.4e-7 USD/token -> 0.14 sats/token -> 140 msats/token
# cache 1.25e-9 USD/token -> 0.00125 sats/token -> 1.25 msats/token
# completion 2.8e-7 USD/token -> 0.28 sats/token -> 280 msats/token
assert cost.input_tokens == 200
assert cost.cache_read_input_tokens == 800
assert cost.cache_read_msats == 1000
assert cost.input_msats == 29000
assert cost.output_msats == 28000
assert cost.total_msats == 57000
ui/components/add-provider-model-dialog.tsx
+44
View File
@@ -68,6 +68,8 @@ const FormSchema = z.object({
upstream_provider_id: z.string().default(''),
input_cost: z.coerce.number().min(0).default(0),
output_cost: z.coerce.number().min(0).default(0),
cache_read_cost: z.coerce.number().min(0).default(0),
cache_write_cost: z.coerce.number().min(0).default(0),
request_cost: z.coerce.number().min(0).default(0),
image_cost: z.coerce.number().min(0).default(0),
web_search_cost: z.coerce.number().min(0).default(0),
@@ -125,6 +127,8 @@ export function AddProviderModelDialog({
upstream_provider_id: '',
input_cost: 0,
output_cost: 0,
cache_read_cost: 0,
cache_write_cost: 0,
request_cost: 0,
image_cost: 0,
web_search_cost: 0,
@@ -190,6 +194,8 @@ export function AddProviderModelDialog({
: initialData.upstream_provider_id?.toString() || '',
input_cost: pricing?.prompt ?? 0,
output_cost: pricing?.completion ?? 0,
cache_read_cost: pricing?.input_cache_read ?? 0,
cache_write_cost: pricing?.input_cache_write ?? 0,
request_cost: pricing?.request ?? 0,
image_cost: pricing?.image ?? 0,
web_search_cost: pricing?.web_search ?? 0,
@@ -231,6 +237,8 @@ export function AddProviderModelDialog({
upstream_provider_id: '',
input_cost: 0,
output_cost: 0,
cache_read_cost: 0,
cache_write_cost: 0,
request_cost: 0,
image_cost: 0,
web_search_cost: 0,
@@ -294,6 +302,8 @@ export function AddProviderModelDialog({
);
form.setValue('input_cost', pricing?.prompt ?? 0);
form.setValue('output_cost', pricing?.completion ?? 0);
form.setValue('cache_read_cost', pricing?.input_cache_read ?? 0);
form.setValue('cache_write_cost', pricing?.input_cache_write ?? 0);
form.setValue('request_cost', pricing?.request ?? 0);
form.setValue('image_cost', pricing?.image ?? 0);
form.setValue('web_search_cost', pricing?.web_search ?? 0);
@@ -365,6 +375,8 @@ export function AddProviderModelDialog({
pricing: {
prompt: data.input_cost,
completion: data.output_cost,
input_cache_read: data.cache_read_cost,
input_cache_write: data.cache_write_cost,
request: data.request_cost,
image: data.image_cost,
web_search: data.web_search_cost,
@@ -810,6 +822,38 @@ export function AddProviderModelDialog({
</FormItem>
)}
/>
<FormField
control={form.control}
name='cache_read_cost'
render={({ field }) => (
<FormItem>
<FormLabel>Cache Read Cost</FormLabel>
<FormControl>
<Input type='number' step='0.000001' {...field} />
</FormControl>
<FormDescription>
Discounted cached-input read price per 1M tokens.
</FormDescription>
<FormMessage />
</FormItem>
)}
/>
<FormField
control={form.control}
name='cache_write_cost'
render={({ field }) => (
<FormItem>
<FormLabel>Cache Write Cost</FormLabel>
<FormControl>
<Input type='number' step='0.000001' {...field} />
</FormControl>
<FormDescription>
Cached-input creation price per 1M tokens.
</FormDescription>
<FormMessage />
</FormItem>
)}
/>
<FormField
control={form.control}
name='request_cost'
ui/lib/api/services/admin.ts
+8 -2
View File
@@ -53,6 +53,8 @@ export const AdminModelPricingSchema = z.object({
image: z.number().optional(),
web_search: z.number().optional(),
internal_reasoning: z.number().optional(),
input_cache_read: z.number().optional(),
input_cache_write: z.number().optional(),
});
export const AdminModelArchitectureSchema = z.object({
@@ -149,7 +151,7 @@ export class AdminService {
if (!pricing) return pricing;
const result = { ...pricing };
// Only prompt and completion are per-token and need scaling to per-1M
// Token-priced fields are stored per-token by the API and shown per-1M in the UI.
const convertField = (field: string) => {
const val = result[field];
if (val !== undefined && val !== null) {
@@ -164,6 +166,8 @@ export class AdminService {
convertField('prompt');
convertField('completion');
convertField('input_cache_read');
convertField('input_cache_write');
// Other fields (request, image, etc.) are already flat fees (per item)
// so we do NOT scale them.
@@ -177,7 +181,7 @@ export class AdminService {
if (!pricing) return pricing;
const result = { ...pricing };
// Only prompt and completion are per-1M in UI and need scaling down to per-token
// Token-priced fields are per-1M in the UI and need scaling down to per-token.
const convertField = (field: string) => {
const val = result[field];
if (val !== undefined && val !== null) {
@@ -190,6 +194,8 @@ export class AdminService {
convertField('prompt');
convertField('completion');
convertField('input_cache_read');
convertField('input_cache_write');
// Other fields stay as flat fees