mirror of
https://github.com/decolua/9router.git
synced 2026-05-08 12:01:28 +00:00
feat(usage): implement cost tracking backend and pricing configuration
- Add pricing constants with default rates for all providers - Update localDb to support pricing configuration schema - Add cost calculation logic to usageDb - Add pricing management API endpoints - Fix provider alias mapping for accurate cost lookups 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
This commit is contained in:
Catalin Stanciu
134
src/app/api/pricing/route.js
Normal file
134
src/app/api/pricing/route.js
Normal file
@@ -0,0 +1,134 @@
|
||||
import { NextResponse } from "next/server";
|
||||
import { getPricing, updatePricing, resetPricing, resetAllPricing } from "@/lib/localDb.js";
|
||||
import { getDefaultPricing } from "@/shared/constants/pricing.js";
|
||||
|
||||
/**
|
||||
* GET /api/pricing
|
||||
* Get current pricing configuration (merged user + defaults)
|
||||
*/
|
||||
export async function GET() {
|
||||
try {
|
||||
const pricing = await getPricing();
|
||||
return NextResponse.json(pricing);
|
||||
} catch (error) {
|
||||
console.error("Error fetching pricing:", error);
|
||||
return NextResponse.json(
|
||||
{ error: "Failed to fetch pricing" },
|
||||
{ status: 500 }
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* PATCH /api/pricing
|
||||
* Update pricing configuration
|
||||
* Body: { provider: { model: { input: number, output: number, cached: number, ... } } }
|
||||
*/
|
||||
export async function PATCH(request) {
|
||||
try {
|
||||
const body = await request.json();
|
||||
|
||||
// Validate body structure
|
||||
if (typeof body !== "object" || body === null) {
|
||||
return NextResponse.json(
|
||||
{ error: "Invalid pricing data format" },
|
||||
{ status: 400 }
|
||||
);
|
||||
}
|
||||
|
||||
// Validate pricing structure
|
||||
for (const [provider, models] of Object.entries(body)) {
|
||||
if (typeof models !== "object" || models === null) {
|
||||
return NextResponse.json(
|
||||
{ error: `Invalid pricing for provider: ${provider}` },
|
||||
{ status: 400 }
|
||||
);
|
||||
}
|
||||
|
||||
for (const [model, pricing] of Object.entries(models)) {
|
||||
if (typeof pricing !== "object" || pricing === null) {
|
||||
return NextResponse.json(
|
||||
{ error: `Invalid pricing for model: ${provider}/${model}` },
|
||||
{ status: 400 }
|
||||
);
|
||||
}
|
||||
|
||||
// Validate pricing fields
|
||||
const validFields = ["input", "output", "cached", "reasoning", "cache_creation"];
|
||||
for (const [key, value] of Object.entries(pricing)) {
|
||||
if (!validFields.includes(key)) {
|
||||
return NextResponse.json(
|
||||
{ error: `Invalid pricing field: ${key} for ${provider}/${model}` },
|
||||
{ status: 400 }
|
||||
);
|
||||
}
|
||||
if (typeof value !== "number" || isNaN(value) || value < 0) {
|
||||
return NextResponse.json(
|
||||
{ error: `Invalid pricing value for ${key} in ${provider}/${model}: must be non-negative number` },
|
||||
{ status: 400 }
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
const updatedPricing = await updatePricing(body);
|
||||
return NextResponse.json(updatedPricing);
|
||||
} catch (error) {
|
||||
console.error("Error updating pricing:", error);
|
||||
return NextResponse.json(
|
||||
{ error: "Failed to update pricing" },
|
||||
{ status: 500 }
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* DELETE /api/pricing
|
||||
* Reset pricing to defaults
|
||||
* Query params: ?provider=xxx&model=yyy (optional)
|
||||
*/
|
||||
export async function DELETE(request) {
|
||||
try {
|
||||
const { searchParams } = new URL(request.url);
|
||||
const provider = searchParams.get("provider");
|
||||
const model = searchParams.get("model");
|
||||
|
||||
if (provider && model) {
|
||||
// Reset specific model
|
||||
await resetPricing(provider, model);
|
||||
} else if (provider) {
|
||||
// Reset entire provider
|
||||
await resetPricing(provider);
|
||||
} else {
|
||||
// Reset all pricing
|
||||
await resetAllPricing();
|
||||
}
|
||||
|
||||
const pricing = await getPricing();
|
||||
return NextResponse.json(pricing);
|
||||
} catch (error) {
|
||||
console.error("Error resetting pricing:", error);
|
||||
return NextResponse.json(
|
||||
{ error: "Failed to reset pricing" },
|
||||
{ status: 500 }
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* GET /api/pricing/defaults
|
||||
* Get default pricing configuration
|
||||
*/
|
||||
export async function GET_DEFAULTS() {
|
||||
try {
|
||||
const defaultPricing = getDefaultPricing();
|
||||
return NextResponse.json(defaultPricing);
|
||||
} catch (error) {
|
||||
console.error("Error fetching default pricing:", error);
|
||||
return NextResponse.json(
|
||||
{ error: "Failed to fetch default pricing" },
|
||||
{ status: 500 }
|
||||
);
|
||||
}
|
||||
}
|
||||
@@ -41,7 +41,8 @@ const defaultData = {
|
||||
settings: {
|
||||
cloudEnabled: false,
|
||||
stickyRoundRobinLimit: 3
|
||||
}
|
||||
},
|
||||
pricing: {} // NEW: pricing configuration
|
||||
};
|
||||
|
||||
// Singleton instance
|
||||
@@ -528,3 +529,158 @@ export async function isCloudEnabled() {
|
||||
return settings.cloudEnabled === true;
|
||||
}
|
||||
|
||||
// ============ Pricing ============
|
||||
|
||||
/**
|
||||
* Get pricing configuration
|
||||
* Returns merged user pricing with defaults
|
||||
*/
|
||||
export async function getPricing() {
|
||||
const db = await getDb();
|
||||
const userPricing = db.data.pricing || {};
|
||||
|
||||
// Import default pricing
|
||||
const { getDefaultPricing } = await import("@/shared/constants/pricing.js");
|
||||
const defaultPricing = getDefaultPricing();
|
||||
|
||||
// Merge user pricing with defaults
|
||||
// User pricing overrides defaults for specific provider/model combinations
|
||||
const mergedPricing = {};
|
||||
|
||||
for (const [provider, models] of Object.entries(defaultPricing)) {
|
||||
mergedPricing[provider] = { ...models };
|
||||
|
||||
// Apply user overrides if they exist
|
||||
if (userPricing[provider]) {
|
||||
for (const [model, pricing] of Object.entries(userPricing[provider])) {
|
||||
if (mergedPricing[provider][model]) {
|
||||
mergedPricing[provider][model] = { ...mergedPricing[provider][model], ...pricing };
|
||||
} else {
|
||||
mergedPricing[provider][model] = pricing;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Add any user-only pricing entries
|
||||
for (const [provider, models] of Object.entries(userPricing)) {
|
||||
if (!mergedPricing[provider]) {
|
||||
mergedPricing[provider] = { ...models };
|
||||
} else {
|
||||
for (const [model, pricing] of Object.entries(models)) {
|
||||
if (!mergedPricing[provider][model]) {
|
||||
mergedPricing[provider][model] = pricing;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return mergedPricing;
|
||||
}
|
||||
|
||||
/**
|
||||
* Get pricing for a specific provider and model
|
||||
*/
|
||||
export async function getPricingForModel(provider, model) {
|
||||
const pricing = await getPricing();
|
||||
|
||||
// Try direct lookup
|
||||
if (pricing[provider] && pricing[provider][model]) {
|
||||
return pricing[provider][model];
|
||||
}
|
||||
|
||||
// Try mapping provider ID to alias
|
||||
// We need to duplicate the mapping here or import it
|
||||
// Since we can't easily import from open-sse, we'll implement the mapping locally
|
||||
const PROVIDER_ID_TO_ALIAS = {
|
||||
claude: "cc",
|
||||
codex: "cx",
|
||||
"gemini-cli": "gc",
|
||||
qwen: "qw",
|
||||
iflow: "if",
|
||||
antigravity: "ag",
|
||||
github: "gh",
|
||||
openai: "openai",
|
||||
anthropic: "anthropic",
|
||||
gemini: "gemini",
|
||||
openrouter: "openrouter",
|
||||
glm: "glm",
|
||||
kimi: "kimi",
|
||||
minimax: "minimax",
|
||||
};
|
||||
|
||||
const alias = PROVIDER_ID_TO_ALIAS[provider];
|
||||
if (alias && pricing[alias]) {
|
||||
return pricing[alias][model] || null;
|
||||
}
|
||||
|
||||
return null;
|
||||
}
|
||||
|
||||
/**
|
||||
* Update pricing configuration
|
||||
* @param {object} pricingData - New pricing data to merge
|
||||
*/
|
||||
export async function updatePricing(pricingData) {
|
||||
const db = await getDb();
|
||||
|
||||
// Ensure pricing object exists
|
||||
if (!db.data.pricing) {
|
||||
db.data.pricing = {};
|
||||
}
|
||||
|
||||
// Merge new pricing data
|
||||
for (const [provider, models] of Object.entries(pricingData)) {
|
||||
if (!db.data.pricing[provider]) {
|
||||
db.data.pricing[provider] = {};
|
||||
}
|
||||
|
||||
for (const [model, pricing] of Object.entries(models)) {
|
||||
db.data.pricing[provider][model] = pricing;
|
||||
}
|
||||
}
|
||||
|
||||
await db.write();
|
||||
return db.data.pricing;
|
||||
}
|
||||
|
||||
/**
|
||||
* Reset pricing to defaults for specific provider/model
|
||||
* @param {string} provider - Provider ID
|
||||
* @param {string} model - Model ID (optional, if not provided resets entire provider)
|
||||
*/
|
||||
export async function resetPricing(provider, model) {
|
||||
const db = await getDb();
|
||||
|
||||
if (!db.data.pricing) {
|
||||
db.data.pricing = {};
|
||||
}
|
||||
|
||||
if (model) {
|
||||
// Reset specific model
|
||||
if (db.data.pricing[provider]) {
|
||||
delete db.data.pricing[provider][model];
|
||||
// Clean up empty provider objects
|
||||
if (Object.keys(db.data.pricing[provider]).length === 0) {
|
||||
delete db.data.pricing[provider];
|
||||
}
|
||||
}
|
||||
} else {
|
||||
// Reset entire provider
|
||||
delete db.data.pricing[provider];
|
||||
}
|
||||
|
||||
await db.write();
|
||||
return db.data.pricing;
|
||||
}
|
||||
|
||||
/**
|
||||
* Reset all pricing to defaults
|
||||
*/
|
||||
export async function resetAllPricing() {
|
||||
const db = await getDb();
|
||||
db.data.pricing = {};
|
||||
await db.write();
|
||||
return db.data.pricing;
|
||||
}
|
||||
|
||||
|
||||
@@ -229,6 +229,62 @@ export async function getRecentLogs(limit = 200) {
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Calculate cost for a usage entry
|
||||
* @param {string} provider - Provider ID
|
||||
* @param {string} model - Model ID
|
||||
* @param {object} tokens - Token counts
|
||||
* @returns {number} Cost in dollars
|
||||
*/
|
||||
async function calculateCost(provider, model, tokens) {
|
||||
if (!tokens || !provider || !model) return 0;
|
||||
|
||||
try {
|
||||
const { getPricingForModel } = await import("@/lib/localDb.js");
|
||||
const pricing = await getPricingForModel(provider, model);
|
||||
|
||||
if (!pricing) return 0;
|
||||
|
||||
let cost = 0;
|
||||
|
||||
// Input tokens (non-cached)
|
||||
const inputTokens = tokens.prompt_tokens || tokens.input_tokens || 0;
|
||||
const cachedTokens = tokens.cached_tokens || tokens.cache_read_input_tokens || 0;
|
||||
const nonCachedInput = Math.max(0, inputTokens - cachedTokens);
|
||||
|
||||
cost += (nonCachedInput * (pricing.input / 1000000));
|
||||
|
||||
// Cached tokens
|
||||
if (cachedTokens > 0) {
|
||||
const cachedRate = pricing.cached || pricing.input; // Fallback to input rate
|
||||
cost += (cachedTokens * (cachedRate / 1000000));
|
||||
}
|
||||
|
||||
// Output tokens
|
||||
const outputTokens = tokens.completion_tokens || tokens.output_tokens || 0;
|
||||
cost += (outputTokens * (pricing.output / 1000000));
|
||||
|
||||
// Reasoning tokens
|
||||
const reasoningTokens = tokens.reasoning_tokens || 0;
|
||||
if (reasoningTokens > 0) {
|
||||
const reasoningRate = pricing.reasoning || pricing.output; // Fallback to output rate
|
||||
cost += (reasoningTokens * (reasoningRate / 1000000));
|
||||
}
|
||||
|
||||
// Cache creation tokens
|
||||
const cacheCreationTokens = tokens.cache_creation_input_tokens || 0;
|
||||
if (cacheCreationTokens > 0) {
|
||||
const cacheCreationRate = pricing.cache_creation || pricing.input; // Fallback to input rate
|
||||
cost += (cacheCreationTokens * (cacheCreationRate / 1000000));
|
||||
}
|
||||
|
||||
return cost;
|
||||
} catch (error) {
|
||||
console.error("Error calculating cost:", error);
|
||||
return 0;
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Get aggregated usage stats
|
||||
*/
|
||||
@@ -258,6 +314,7 @@ export async function getUsageStats() {
|
||||
totalRequests: history.length,
|
||||
totalPromptTokens: 0,
|
||||
totalCompletionTokens: 0,
|
||||
totalCost: 0, // NEW
|
||||
byProvider: {},
|
||||
byModel: {},
|
||||
byAccount: {},
|
||||
@@ -300,7 +357,8 @@ export async function getUsageStats() {
|
||||
bucketMap[bucketKey] = {
|
||||
requests: 0,
|
||||
promptTokens: 0,
|
||||
completionTokens: 0
|
||||
completionTokens: 0,
|
||||
cost: 0
|
||||
};
|
||||
stats.last10Minutes.push(bucketMap[bucketKey]);
|
||||
}
|
||||
@@ -310,8 +368,12 @@ export async function getUsageStats() {
|
||||
const completionTokens = entry.tokens?.completion_tokens || 0;
|
||||
const entryTime = new Date(entry.timestamp);
|
||||
|
||||
// Calculate cost for this entry
|
||||
const entryCost = await calculateCost(entry.provider, entry.model, entry.tokens);
|
||||
|
||||
stats.totalPromptTokens += promptTokens;
|
||||
stats.totalCompletionTokens += completionTokens;
|
||||
stats.totalCost += entryCost;
|
||||
|
||||
// Last 10 minutes aggregation - floor entry time to its minute
|
||||
if (entryTime >= tenMinutesAgo && entryTime <= now) {
|
||||
@@ -320,6 +382,7 @@ export async function getUsageStats() {
|
||||
bucketMap[entryMinuteStart].requests++;
|
||||
bucketMap[entryMinuteStart].promptTokens += promptTokens;
|
||||
bucketMap[entryMinuteStart].completionTokens += completionTokens;
|
||||
bucketMap[entryMinuteStart].cost += entryCost;
|
||||
}
|
||||
}
|
||||
|
||||
@@ -328,12 +391,14 @@ export async function getUsageStats() {
|
||||
stats.byProvider[entry.provider] = {
|
||||
requests: 0,
|
||||
promptTokens: 0,
|
||||
completionTokens: 0
|
||||
completionTokens: 0,
|
||||
cost: 0
|
||||
};
|
||||
}
|
||||
stats.byProvider[entry.provider].requests++;
|
||||
stats.byProvider[entry.provider].promptTokens += promptTokens;
|
||||
stats.byProvider[entry.provider].completionTokens += completionTokens;
|
||||
stats.byProvider[entry.provider].cost += entryCost;
|
||||
|
||||
// By Model
|
||||
// Format: "modelName (provider)" if provider is known
|
||||
@@ -344,6 +409,7 @@ export async function getUsageStats() {
|
||||
requests: 0,
|
||||
promptTokens: 0,
|
||||
completionTokens: 0,
|
||||
cost: 0,
|
||||
rawModel: entry.model,
|
||||
provider: entry.provider,
|
||||
lastUsed: entry.timestamp
|
||||
@@ -352,6 +418,7 @@ export async function getUsageStats() {
|
||||
stats.byModel[modelKey].requests++;
|
||||
stats.byModel[modelKey].promptTokens += promptTokens;
|
||||
stats.byModel[modelKey].completionTokens += completionTokens;
|
||||
stats.byModel[modelKey].cost += entryCost;
|
||||
if (new Date(entry.timestamp) > new Date(stats.byModel[modelKey].lastUsed)) {
|
||||
stats.byModel[modelKey].lastUsed = entry.timestamp;
|
||||
}
|
||||
@@ -367,6 +434,7 @@ export async function getUsageStats() {
|
||||
requests: 0,
|
||||
promptTokens: 0,
|
||||
completionTokens: 0,
|
||||
cost: 0,
|
||||
rawModel: entry.model,
|
||||
provider: entry.provider,
|
||||
connectionId: entry.connectionId,
|
||||
@@ -377,6 +445,7 @@ export async function getUsageStats() {
|
||||
stats.byAccount[accountKey].requests++;
|
||||
stats.byAccount[accountKey].promptTokens += promptTokens;
|
||||
stats.byAccount[accountKey].completionTokens += completionTokens;
|
||||
stats.byAccount[accountKey].cost += entryCost;
|
||||
if (new Date(entry.timestamp) > new Date(stats.byAccount[accountKey].lastUsed)) {
|
||||
stats.byAccount[accountKey].lastUsed = entry.timestamp;
|
||||
}
|
||||
|
||||
598
src/shared/constants/pricing.js
Normal file
598
src/shared/constants/pricing.js
Normal file
@@ -0,0 +1,598 @@
|
||||
// Default pricing rates for AI models
|
||||
// All rates are in dollars per million tokens ($/1M tokens)
|
||||
// Based on user-provided pricing for Antigravity models and industry standards for others
|
||||
|
||||
export const DEFAULT_PRICING = {
|
||||
// OAuth Providers (using aliases)
|
||||
|
||||
// Claude Code (cc)
|
||||
cc: {
|
||||
"claude-opus-4-5-20251101": {
|
||||
input: 15.00,
|
||||
output: 75.00,
|
||||
cached: 7.50,
|
||||
reasoning: 75.00,
|
||||
cache_creation: 15.00
|
||||
},
|
||||
"claude-sonnet-4-5-20250929": {
|
||||
input: 3.00,
|
||||
output: 15.00,
|
||||
cached: 1.50,
|
||||
reasoning: 15.00,
|
||||
cache_creation: 3.00
|
||||
},
|
||||
"claude-haiku-4-5-20251001": {
|
||||
input: 0.50,
|
||||
output: 2.50,
|
||||
cached: 0.25,
|
||||
reasoning: 2.50,
|
||||
cache_creation: 0.50
|
||||
}
|
||||
},
|
||||
|
||||
// OpenAI Codex (cx)
|
||||
cx: {
|
||||
"gpt-5.2-codex": {
|
||||
input: 5.00,
|
||||
output: 20.00,
|
||||
cached: 2.50,
|
||||
reasoning: 30.00,
|
||||
cache_creation: 5.00
|
||||
},
|
||||
"gpt-5.2": {
|
||||
input: 5.00,
|
||||
output: 20.00,
|
||||
cached: 2.50,
|
||||
reasoning: 30.00,
|
||||
cache_creation: 5.00
|
||||
},
|
||||
"gpt-5.1-codex-max": {
|
||||
input: 8.00,
|
||||
output: 32.00,
|
||||
cached: 4.00,
|
||||
reasoning: 48.00,
|
||||
cache_creation: 8.00
|
||||
},
|
||||
"gpt-5.1-codex": {
|
||||
input: 4.00,
|
||||
output: 16.00,
|
||||
cached: 2.00,
|
||||
reasoning: 24.00,
|
||||
cache_creation: 4.00
|
||||
},
|
||||
"gpt-5.1-codex-mini": {
|
||||
input: 1.50,
|
||||
output: 6.00,
|
||||
cached: 0.75,
|
||||
reasoning: 9.00,
|
||||
cache_creation: 1.50
|
||||
},
|
||||
"gpt-5.1": {
|
||||
input: 4.00,
|
||||
output: 16.00,
|
||||
cached: 2.00,
|
||||
reasoning: 24.00,
|
||||
cache_creation: 4.00
|
||||
},
|
||||
"gpt-5-codex": {
|
||||
input: 3.00,
|
||||
output: 12.00,
|
||||
cached: 1.50,
|
||||
reasoning: 18.00,
|
||||
cache_creation: 3.00
|
||||
},
|
||||
"gpt-5-codex-mini": {
|
||||
input: 1.00,
|
||||
output: 4.00,
|
||||
cached: 0.50,
|
||||
reasoning: 6.00,
|
||||
cache_creation: 1.00
|
||||
}
|
||||
},
|
||||
|
||||
// Gemini CLI (gc)
|
||||
gc: {
|
||||
"gemini-3-flash-preview": {
|
||||
input: 0.50,
|
||||
output: 3.00,
|
||||
cached: 0.03,
|
||||
reasoning: 4.50,
|
||||
cache_creation: 0.50
|
||||
},
|
||||
"gemini-3-pro-preview": {
|
||||
input: 2.00,
|
||||
output: 12.00,
|
||||
cached: 0.25,
|
||||
reasoning: 18.00,
|
||||
cache_creation: 2.00
|
||||
},
|
||||
"gemini-2.5-pro": {
|
||||
input: 2.00,
|
||||
output: 12.00,
|
||||
cached: 0.25,
|
||||
reasoning: 18.00,
|
||||
cache_creation: 2.00
|
||||
},
|
||||
"gemini-2.5-flash": {
|
||||
input: 0.30,
|
||||
output: 2.50,
|
||||
cached: 0.03,
|
||||
reasoning: 3.75,
|
||||
cache_creation: 0.30
|
||||
},
|
||||
"gemini-2.5-flash-lite": {
|
||||
input: 0.15,
|
||||
output: 1.25,
|
||||
cached: 0.015,
|
||||
reasoning: 1.875,
|
||||
cache_creation: 0.15
|
||||
}
|
||||
},
|
||||
|
||||
// Qwen Code (qw)
|
||||
qw: {
|
||||
"qwen3-coder-plus": {
|
||||
input: 1.00,
|
||||
output: 4.00,
|
||||
cached: 0.50,
|
||||
reasoning: 6.00,
|
||||
cache_creation: 1.00
|
||||
},
|
||||
"qwen3-coder-flash": {
|
||||
input: 0.50,
|
||||
output: 2.00,
|
||||
cached: 0.25,
|
||||
reasoning: 3.00,
|
||||
cache_creation: 0.50
|
||||
},
|
||||
"vision-model": {
|
||||
input: 1.50,
|
||||
output: 6.00,
|
||||
cached: 0.75,
|
||||
reasoning: 9.00,
|
||||
cache_creation: 1.50
|
||||
}
|
||||
},
|
||||
|
||||
// iFlow AI (if)
|
||||
if: {
|
||||
"qwen3-coder-plus": {
|
||||
input: 1.00,
|
||||
output: 4.00,
|
||||
cached: 0.50,
|
||||
reasoning: 6.00,
|
||||
cache_creation: 1.00
|
||||
},
|
||||
"kimi-k2": {
|
||||
input: 1.00,
|
||||
output: 4.00,
|
||||
cached: 0.50,
|
||||
reasoning: 6.00,
|
||||
cache_creation: 1.00
|
||||
},
|
||||
"kimi-k2-thinking": {
|
||||
input: 1.50,
|
||||
output: 6.00,
|
||||
cached: 0.75,
|
||||
reasoning: 9.00,
|
||||
cache_creation: 1.50
|
||||
},
|
||||
"deepseek-r1": {
|
||||
input: 0.75,
|
||||
output: 3.00,
|
||||
cached: 0.375,
|
||||
reasoning: 4.50,
|
||||
cache_creation: 0.75
|
||||
},
|
||||
"deepseek-v3.2-chat": {
|
||||
input: 0.50,
|
||||
output: 2.00,
|
||||
cached: 0.25,
|
||||
reasoning: 3.00,
|
||||
cache_creation: 0.50
|
||||
},
|
||||
"deepseek-v3.2-reasoner": {
|
||||
input: 0.75,
|
||||
output: 3.00,
|
||||
cached: 0.375,
|
||||
reasoning: 4.50,
|
||||
cache_creation: 0.75
|
||||
},
|
||||
"minimax-m2": {
|
||||
input: 0.50,
|
||||
output: 2.00,
|
||||
cached: 0.25,
|
||||
reasoning: 3.00,
|
||||
cache_creation: 0.50
|
||||
},
|
||||
"glm-4.6": {
|
||||
input: 0.50,
|
||||
output: 2.00,
|
||||
cached: 0.25,
|
||||
reasoning: 3.00,
|
||||
cache_creation: 0.50
|
||||
},
|
||||
"glm-4.7": {
|
||||
input: 0.75,
|
||||
output: 3.00,
|
||||
cached: 0.375,
|
||||
reasoning: 4.50,
|
||||
cache_creation: 0.75
|
||||
}
|
||||
},
|
||||
|
||||
// Antigravity (ag) - User-provided pricing
|
||||
ag: {
|
||||
"gemini-3-pro-low": {
|
||||
input: 2.00,
|
||||
output: 12.00,
|
||||
cached: 0.25,
|
||||
reasoning: 18.00,
|
||||
cache_creation: 2.00
|
||||
},
|
||||
"gemini-3-pro-high": {
|
||||
input: 4.00,
|
||||
output: 18.00,
|
||||
cached: 0.50,
|
||||
reasoning: 27.00,
|
||||
cache_creation: 4.00
|
||||
},
|
||||
"gemini-3-flash": {
|
||||
input: 0.50,
|
||||
output: 3.00,
|
||||
cached: 0.03,
|
||||
reasoning: 4.50,
|
||||
cache_creation: 0.50
|
||||
},
|
||||
"gemini-2.5-flash": {
|
||||
input: 0.30,
|
||||
output: 2.50,
|
||||
cached: 0.03,
|
||||
reasoning: 3.75,
|
||||
cache_creation: 0.30
|
||||
},
|
||||
"claude-sonnet-4-5": {
|
||||
input: 3.00,
|
||||
output: 15.00,
|
||||
cached: 0.30,
|
||||
reasoning: 22.50,
|
||||
cache_creation: 3.00
|
||||
},
|
||||
"claude-sonnet-4-5-thinking": {
|
||||
input: 3.00,
|
||||
output: 15.00,
|
||||
cached: 0.30,
|
||||
reasoning: 22.50,
|
||||
cache_creation: 3.00
|
||||
},
|
||||
"claude-opus-4-5-thinking": {
|
||||
input: 5.00,
|
||||
output: 25.00,
|
||||
cached: 0.50,
|
||||
reasoning: 37.50,
|
||||
cache_creation: 5.00
|
||||
}
|
||||
},
|
||||
|
||||
// GitHub Copilot (gh)
|
||||
gh: {
|
||||
"gpt-5": {
|
||||
input: 3.00,
|
||||
output: 12.00,
|
||||
cached: 1.50,
|
||||
reasoning: 18.00,
|
||||
cache_creation: 3.00
|
||||
},
|
||||
"gpt-5-mini": {
|
||||
input: 0.75,
|
||||
output: 3.00,
|
||||
cached: 0.375,
|
||||
reasoning: 4.50,
|
||||
cache_creation: 0.75
|
||||
},
|
||||
"gpt-5.1-codex": {
|
||||
input: 4.00,
|
||||
output: 16.00,
|
||||
cached: 2.00,
|
||||
reasoning: 24.00,
|
||||
cache_creation: 4.00
|
||||
},
|
||||
"gpt-5.1-codex-max": {
|
||||
input: 8.00,
|
||||
output: 32.00,
|
||||
cached: 4.00,
|
||||
reasoning: 48.00,
|
||||
cache_creation: 8.00
|
||||
},
|
||||
"gpt-4.1": {
|
||||
input: 2.50,
|
||||
output: 10.00,
|
||||
cached: 1.25,
|
||||
reasoning: 15.00,
|
||||
cache_creation: 2.50
|
||||
},
|
||||
"claude-4.5-sonnet": {
|
||||
input: 3.00,
|
||||
output: 15.00,
|
||||
cached: 0.30,
|
||||
reasoning: 22.50,
|
||||
cache_creation: 3.00
|
||||
},
|
||||
"claude-4.5-opus": {
|
||||
input: 5.00,
|
||||
output: 25.00,
|
||||
cached: 0.50,
|
||||
reasoning: 37.50,
|
||||
cache_creation: 5.00
|
||||
},
|
||||
"claude-4.5-haiku": {
|
||||
input: 0.50,
|
||||
output: 2.50,
|
||||
cached: 0.05,
|
||||
reasoning: 3.75,
|
||||
cache_creation: 0.50
|
||||
},
|
||||
"gemini-3-pro": {
|
||||
input: 2.00,
|
||||
output: 12.00,
|
||||
cached: 0.25,
|
||||
reasoning: 18.00,
|
||||
cache_creation: 2.00
|
||||
},
|
||||
"gemini-3-flash": {
|
||||
input: 0.50,
|
||||
output: 3.00,
|
||||
cached: 0.03,
|
||||
reasoning: 4.50,
|
||||
cache_creation: 0.50
|
||||
},
|
||||
"gemini-2.5-pro": {
|
||||
input: 2.00,
|
||||
output: 12.00,
|
||||
cached: 0.25,
|
||||
reasoning: 18.00,
|
||||
cache_creation: 2.00
|
||||
},
|
||||
"grok-code-fast-1": {
|
||||
input: 0.50,
|
||||
output: 2.00,
|
||||
cached: 0.25,
|
||||
reasoning: 3.00,
|
||||
cache_creation: 0.50
|
||||
}
|
||||
},
|
||||
|
||||
// API Key Providers (alias = id)
|
||||
|
||||
// OpenAI
|
||||
openai: {
|
||||
"gpt-4o": {
|
||||
input: 2.50,
|
||||
output: 10.00,
|
||||
cached: 1.25,
|
||||
reasoning: 15.00,
|
||||
cache_creation: 2.50
|
||||
},
|
||||
"gpt-4o-mini": {
|
||||
input: 0.15,
|
||||
output: 0.60,
|
||||
cached: 0.075,
|
||||
reasoning: 0.90,
|
||||
cache_creation: 0.15
|
||||
},
|
||||
"gpt-4-turbo": {
|
||||
input: 10.00,
|
||||
output: 30.00,
|
||||
cached: 5.00,
|
||||
reasoning: 45.00,
|
||||
cache_creation: 10.00
|
||||
},
|
||||
"o1": {
|
||||
input: 15.00,
|
||||
output: 60.00,
|
||||
cached: 7.50,
|
||||
reasoning: 90.00,
|
||||
cache_creation: 15.00
|
||||
},
|
||||
"o1-mini": {
|
||||
input: 3.00,
|
||||
output: 12.00,
|
||||
cached: 1.50,
|
||||
reasoning: 18.00,
|
||||
cache_creation: 3.00
|
||||
}
|
||||
},
|
||||
|
||||
// Anthropic
|
||||
anthropic: {
|
||||
"claude-sonnet-4-20250514": {
|
||||
input: 3.00,
|
||||
output: 15.00,
|
||||
cached: 1.50,
|
||||
reasoning: 15.00,
|
||||
cache_creation: 3.00
|
||||
},
|
||||
"claude-opus-4-20250514": {
|
||||
input: 15.00,
|
||||
output: 75.00,
|
||||
cached: 7.50,
|
||||
reasoning: 112.50,
|
||||
cache_creation: 15.00
|
||||
},
|
||||
"claude-3-5-sonnet-20241022": {
|
||||
input: 3.00,
|
||||
output: 15.00,
|
||||
cached: 1.50,
|
||||
reasoning: 15.00,
|
||||
cache_creation: 3.00
|
||||
}
|
||||
},
|
||||
|
||||
// Gemini
|
||||
gemini: {
|
||||
"gemini-3-pro-preview": {
|
||||
input: 2.00,
|
||||
output: 12.00,
|
||||
cached: 0.25,
|
||||
reasoning: 18.00,
|
||||
cache_creation: 2.00
|
||||
},
|
||||
"gemini-2.5-pro": {
|
||||
input: 2.00,
|
||||
output: 12.00,
|
||||
cached: 0.25,
|
||||
reasoning: 18.00,
|
||||
cache_creation: 2.00
|
||||
},
|
||||
"gemini-2.5-flash": {
|
||||
input: 0.30,
|
||||
output: 2.50,
|
||||
cached: 0.03,
|
||||
reasoning: 3.75,
|
||||
cache_creation: 0.30
|
||||
},
|
||||
"gemini-2.5-flash-lite": {
|
||||
input: 0.15,
|
||||
output: 1.25,
|
||||
cached: 0.015,
|
||||
reasoning: 1.875,
|
||||
cache_creation: 0.15
|
||||
}
|
||||
},
|
||||
|
||||
// OpenRouter
|
||||
openrouter: {
|
||||
"auto": {
|
||||
input: 2.00,
|
||||
output: 8.00,
|
||||
cached: 1.00,
|
||||
reasoning: 12.00,
|
||||
cache_creation: 2.00
|
||||
}
|
||||
},
|
||||
|
||||
// GLM
|
||||
glm: {
|
||||
"glm-4.7": {
|
||||
input: 0.75,
|
||||
output: 3.00,
|
||||
cached: 0.375,
|
||||
reasoning: 4.50,
|
||||
cache_creation: 0.75
|
||||
},
|
||||
"glm-4.6": {
|
||||
input: 0.50,
|
||||
output: 2.00,
|
||||
cached: 0.25,
|
||||
reasoning: 3.00,
|
||||
cache_creation: 0.50
|
||||
},
|
||||
"glm-4.6v": {
|
||||
input: 0.75,
|
||||
output: 3.00,
|
||||
cached: 0.375,
|
||||
reasoning: 4.50,
|
||||
cache_creation: 0.75
|
||||
}
|
||||
},
|
||||
|
||||
// Kimi
|
||||
kimi: {
|
||||
"kimi-latest": {
|
||||
input: 1.00,
|
||||
output: 4.00,
|
||||
cached: 0.50,
|
||||
reasoning: 6.00,
|
||||
cache_creation: 1.00
|
||||
}
|
||||
},
|
||||
|
||||
// MiniMax
|
||||
minimax: {
|
||||
"MiniMax-M2.1": {
|
||||
input: 0.50,
|
||||
output: 2.00,
|
||||
cached: 0.25,
|
||||
reasoning: 3.00,
|
||||
cache_creation: 0.50
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
/**
|
||||
* Get pricing for a specific provider and model
|
||||
* @param {string} provider - Provider ID (e.g., "openai", "cc", "gc")
|
||||
* @param {string} model - Model ID
|
||||
* @returns {object|null} Pricing object or null if not found
|
||||
*/
|
||||
export function getPricingForModel(provider, model) {
|
||||
if (!provider || !model) return null;
|
||||
|
||||
const providerPricing = DEFAULT_PRICING[provider];
|
||||
if (!providerPricing) return null;
|
||||
|
||||
return providerPricing[model] || null;
|
||||
}
|
||||
|
||||
/**
|
||||
* Get all pricing data
|
||||
* @returns {object} All default pricing
|
||||
*/
|
||||
export function getDefaultPricing() {
|
||||
return DEFAULT_PRICING;
|
||||
}
|
||||
|
||||
/**
|
||||
* Format cost for display
|
||||
* @param {number} cost - Cost in dollars
|
||||
* @returns {string} Formatted cost string
|
||||
*/
|
||||
export function formatCost(cost) {
|
||||
if (cost === null || cost === undefined || isNaN(cost)) return "$0.00";
|
||||
return `$${cost.toFixed(2)}`;
|
||||
}
|
||||
|
||||
/**
|
||||
* Calculate cost from tokens and pricing
|
||||
* @param {object} tokens - Token counts
|
||||
* @param {object} pricing - Pricing object
|
||||
* @returns {number} Cost in dollars
|
||||
*/
|
||||
export function calculateCostFromTokens(tokens, pricing) {
|
||||
if (!tokens || !pricing) return 0;
|
||||
|
||||
let cost = 0;
|
||||
|
||||
// Input tokens (non-cached)
|
||||
const inputTokens = tokens.prompt_tokens || tokens.input_tokens || 0;
|
||||
const cachedTokens = tokens.cached_tokens || tokens.cache_read_input_tokens || 0;
|
||||
const nonCachedInput = Math.max(0, inputTokens - cachedTokens);
|
||||
|
||||
cost += (nonCachedInput * (pricing.input / 1000000));
|
||||
|
||||
// Cached tokens
|
||||
if (cachedTokens > 0) {
|
||||
const cachedRate = pricing.cached || pricing.input; // Fallback to input rate
|
||||
cost += (cachedTokens * (cachedRate / 1000000));
|
||||
}
|
||||
|
||||
// Output tokens
|
||||
const outputTokens = tokens.completion_tokens || tokens.output_tokens || 0;
|
||||
cost += (outputTokens * (pricing.output / 1000000));
|
||||
|
||||
// Reasoning tokens
|
||||
const reasoningTokens = tokens.reasoning_tokens || 0;
|
||||
if (reasoningTokens > 0) {
|
||||
const reasoningRate = pricing.reasoning || pricing.output; // Fallback to output rate
|
||||
cost += (reasoningTokens * (reasoningRate / 1000000));
|
||||
}
|
||||
|
||||
// Cache creation tokens
|
||||
const cacheCreationTokens = tokens.cache_creation_input_tokens || 0;
|
||||
if (cacheCreationTokens > 0) {
|
||||
const cacheCreationRate = pricing.cache_creation || pricing.input; // Fallback to input rate
|
||||
cost += (cacheCreationTokens * (cacheCreationRate / 1000000));
|
||||
}
|
||||
|
||||
return cost;
|
||||
}
|
||||
Reference in New Issue
Block a user