File size: 21,378 Bytes
88c4c60 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 | // Pricing rates for AI models — all rates in $/1M tokens
//
// Fallback order (first match wins):
// 1. PROVIDER_PRICING[provider][model] — provider-specific override
// 2. MODEL_PRICING[model] — canonical model price (provider-agnostic)
// 3. PATTERN_PRICING — glob pattern match (e.g. "codex-*")
/**
* Canonical model pricing — provider-agnostic.
* Cover all known models; deduplicated across providers.
*/
export const MODEL_PRICING = {
// === Anthropic / Claude ===
"claude-opus-4-6": { input: 5.00, output: 25.00, cached: 0.50, reasoning: 25.00, cache_creation: 6.25 },
"claude-opus-4-5-20251101": { input: 5.00, output: 25.00, cached: 0.50, reasoning: 25.00, cache_creation: 6.25 },
"claude-sonnet-4-6": { input: 3.00, output: 15.00, cached: 0.30, reasoning: 15.00, cache_creation: 3.75 },
"claude-sonnet-4-5-20250929": { input: 3.00, output: 15.00, cached: 0.30, reasoning: 15.00, cache_creation: 3.75 },
"claude-haiku-4-5-20251001": { input: 1.00, output: 5.00, cached: 0.10, reasoning: 5.00, cache_creation: 1.25 },
"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: 25.00, 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 },
"claude-haiku-4.5": { input: 0.50, output: 2.50, cached: 0.05, reasoning: 3.75, cache_creation: 0.50 },
"claude-opus-4.1": { input: 5.00, output: 25.00, cached: 0.50, reasoning: 37.50, cache_creation: 5.00 },
"claude-opus-4.5": { input: 5.00, output: 25.00, cached: 0.50, reasoning: 37.50, cache_creation: 5.00 },
"claude-opus-4.6": { input: 5.00, output: 25.00, cached: 0.50, reasoning: 37.50, cache_creation: 5.00 },
"claude-sonnet-4": { input: 3.00, output: 15.00, cached: 0.30, reasoning: 22.50, cache_creation: 3.00 },
"claude-sonnet-4.5": { input: 3.00, output: 15.00, cached: 0.30, reasoning: 22.50, cache_creation: 3.00 },
"claude-sonnet-4.6": { 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 },
"claude-opus-4-6-thinking": { input: 5.00, output: 25.00, cached: 0.50, reasoning: 37.50, cache_creation: 5.00 },
// === OpenAI / GPT ===
"gpt-3.5-turbo": { input: 0.50, output: 1.50, cached: 0.25, reasoning: 2.25, cache_creation: 0.50 },
"gpt-4": { input: 2.50, output: 10.00, cached: 1.25, reasoning: 15.00, cache_creation: 2.50 },
"gpt-4-turbo": { input: 10.00, output: 30.00, cached: 5.00, reasoning: 45.00, cache_creation: 10.00 },
"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-4.1": { input: 2.50, output: 10.00, cached: 1.25, reasoning: 15.00, cache_creation: 2.50 },
"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-codex": { input: 3.00, output: 12.00, cached: 1.50, reasoning: 18.00, cache_creation: 3.00 },
"gpt-5.1": { input: 4.00, output: 16.00, cached: 2.00, reasoning: 24.00, cache_creation: 4.00 },
"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-codex-mini-high": { input: 2.00, output: 8.00, cached: 1.00, reasoning: 12.00, cache_creation: 2.00 },
"gpt-5.1-codex-max": { input: 8.00, output: 32.00, cached: 4.00, reasoning: 48.00, cache_creation: 8.00 },
"gpt-5.2": { input: 5.00, output: 20.00, cached: 2.50, reasoning: 30.00, cache_creation: 5.00 },
"gpt-5.2-codex": { input: 5.00, output: 20.00, cached: 2.50, reasoning: 30.00, cache_creation: 5.00 },
"gpt-5.3-codex": { input: 6.00, output: 24.00, cached: 3.00, reasoning: 36.00, cache_creation: 6.00 },
"gpt-5.3-codex-xhigh": { input: 10.00, output: 40.00, cached: 5.00, reasoning: 60.00, cache_creation: 10.00 },
"gpt-5.3-codex-high": { input: 8.00, output: 32.00, cached: 4.00, reasoning: 48.00, cache_creation: 8.00 },
"gpt-5.3-codex-low": { input: 4.00, output: 16.00, cached: 2.00, reasoning: 24.00, cache_creation: 4.00 },
"gpt-5.3-codex-none": { input: 3.00, output: 12.00, cached: 1.50, reasoning: 18.00, cache_creation: 3.00 },
"gpt-5.3-codex-spark": { input: 3.00, output: 12.00, cached: 0.30, reasoning: 12.00, cache_creation: 3.00 },
"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 },
// === Gemini ===
"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-3.1-pro-low": { input: 2.00, output: 12.00, cached: 0.25, reasoning: 18.00, cache_creation: 2.00 },
"gemini-3.1-pro-high": { input: 4.00, output: 18.00, cached: 0.50, reasoning: 27.00, cache_creation: 4.00 },
"gemini-pro-agent": { input: 4.00, output: 18.00, cached: 0.50, reasoning: 27.00, cache_creation: 4.00 },
"gemini-3-flash-agent": { input: 0.50, output: 3.00, cached: 0.03, reasoning: 4.50, cache_creation: 0.50 },
"gemini-3.5-flash-low": { input: 0.50, output: 3.00, cached: 0.03, reasoning: 4.50, cache_creation: 0.50 },
"gemini-3.5-flash-extra-low": { input: 0.50, output: 3.00, cached: 0.03, reasoning: 4.50, cache_creation: 0.50 },
"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 },
"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 ===
"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 },
// === Kimi ===
"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 },
"kimi-k2.5": { input: 1.20, output: 4.80, cached: 0.60, reasoning: 7.20, cache_creation: 1.20 },
"kimi-k2.5-thinking": { input: 1.80, output: 7.20, cached: 0.90, reasoning: 10.80, cache_creation: 1.80 },
"kimi-latest": { input: 1.00, output: 4.00, cached: 0.50, reasoning: 6.00, cache_creation: 1.00 },
// === DeepSeek ===
"deepseek-chat": { input: 0.14, output: 0.28, cached: 0.0028, reasoning: 0.28, cache_creation: 0.14 },
"deepseek-reasoner": { input: 0.14, output: 0.28, cached: 0.0028, reasoning: 0.28, cache_creation: 0.14 },
"deepseek-r1": { input: 0.14, output: 0.28, cached: 0.0028, reasoning: 0.28, cache_creation: 0.14 },
"deepseek-v3.2-chat": { input: 0.14, output: 0.28, cached: 0.0028, reasoning: 0.28, cache_creation: 0.14 },
"deepseek-v3.2-reasoner": { input: 0.14, output: 0.28, cached: 0.0028, reasoning: 0.28, cache_creation: 0.14 },
"deepseek-v4-flash": { input: 0.14, output: 0.28, cached: 0.0028, reasoning: 0.28, cache_creation: 0.14 },
"deepseek-v4-pro": { input: 0.435, output: 0.87, cached: 0.003625, reasoning: 0.87, cache_creation: 0.435 },
// === GLM ===
"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 },
"glm-4.7": { input: 0.75, output: 3.00, cached: 0.375, reasoning: 4.50, cache_creation: 0.75 },
"glm-5": { input: 1.00, output: 4.00, cached: 0.50, reasoning: 6.00, cache_creation: 1.00 },
// === MiniMax ===
"MiniMax-M3": { input: 0.30, output: 1.20, cached: 0.06, reasoning: 1.80, cache_creation: 0.30 },
"MiniMax-M2.1": { input: 0.50, output: 2.00, cached: 0.25, reasoning: 3.00, cache_creation: 0.50 },
"MiniMax-M2.5": { input: 0.50, output: 2.00, cached: 0.25, reasoning: 3.00, cache_creation: 0.50 },
"MiniMax-M2.7": { input: 0.50, output: 2.00, cached: 0.25, reasoning: 3.00, cache_creation: 0.50 },
"minimax-m2.1": { input: 0.50, output: 2.00, cached: 0.25, reasoning: 3.00, cache_creation: 0.50 },
"minimax-m2.5": { input: 0.60, output: 2.40, cached: 0.30, reasoning: 3.60, cache_creation: 0.60 },
// === Grok ===
"grok-code-fast-1": { input: 0.50, output: 2.00, cached: 0.25, reasoning: 3.00, cache_creation: 0.50 },
// === OpenRouter fallback ===
"auto": { input: 2.00, output: 8.00, cached: 1.00, reasoning: 12.00, cache_creation: 2.00 },
// === Misc ===
"oswe-vscode-prime": { input: 1.00, output: 4.00, cached: 0.50, reasoning: 6.00, cache_creation: 1.00 },
"gpt-oss-120b-medium": { 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 },
"coder-model": { input: 1.50, output: 6.00, cached: 0.75, reasoning: 9.00, cache_creation: 1.50 },
};
/**
* Provider-specific pricing overrides.
* Only include entries where price DIFFERS from MODEL_PRICING.
* Keyed by provider alias (cc, cx, gc, gh, ...) or provider id (openai, anthropic, ...).
*/
export const PROVIDER_PRICING = {
// GitHub Copilot (gh) — gpt-5.3-codex has different rate than canonical
gh: {
"gpt-5.3-codex": { input: 1.75, output: 14.00, cached: 0.175, reasoning: 14.00, cache_creation: 1.75 },
},
};
/**
* Pattern-based pricing fallback — matched when no exact model entry found.
* Patterns use simple glob: "*" matches any substring.
* First match wins — order matters.
*/
export const PATTERN_PRICING = [
// --- Codex variants ---
{ pattern: "*-codex-xhigh", pricing: { input: 10.00, output: 40.00, cached: 5.00, reasoning: 60.00, cache_creation: 10.00 } },
{ pattern: "*-codex-high", pricing: { input: 8.00, output: 32.00, cached: 4.00, reasoning: 48.00, cache_creation: 8.00 } },
{ pattern: "*-codex-max", pricing: { input: 8.00, output: 32.00, cached: 4.00, reasoning: 48.00, cache_creation: 8.00 } },
{ pattern: "*-codex-mini-*", pricing: { input: 1.50, output: 6.00, cached: 0.75, reasoning: 9.00, cache_creation: 1.50 } },
{ pattern: "*-codex-mini", pricing: { input: 1.50, output: 6.00, cached: 0.75, reasoning: 9.00, cache_creation: 1.50 } },
{ pattern: "*-codex-low", pricing: { input: 4.00, output: 16.00, cached: 2.00, reasoning: 24.00, cache_creation: 4.00 } },
{ pattern: "*-codex-none", pricing: { input: 3.00, output: 12.00, cached: 1.50, reasoning: 18.00, cache_creation: 3.00 } },
{ pattern: "*-codex-spark", pricing: { input: 3.00, output: 12.00, cached: 0.30, reasoning: 12.00, cache_creation: 3.00 } },
{ pattern: "codex-*", pricing: { input: 3.00, output: 12.00, cached: 1.50, reasoning: 18.00, cache_creation: 3.00 } },
{ pattern: "*-codex", pricing: { input: 3.00, output: 12.00, cached: 1.50, reasoning: 18.00, cache_creation: 3.00 } },
// --- Claude ---
{ pattern: "claude-opus-*", pricing: { input: 5.00, output: 25.00, cached: 0.50, reasoning: 25.00, cache_creation: 6.25 } },
{ pattern: "claude-sonnet-*", pricing: { input: 3.00, output: 15.00, cached: 0.30, reasoning: 15.00, cache_creation: 3.75 } },
{ pattern: "claude-haiku-*", pricing: { input: 1.00, output: 5.00, cached: 0.10, reasoning: 5.00, cache_creation: 1.25 } },
{ pattern: "claude-*", pricing: { input: 3.00, output: 15.00, cached: 0.30, reasoning: 15.00, cache_creation: 3.75 } },
// --- Gemini (specific first, generic last) ---
{ pattern: "gemini-*-flash-lite", pricing: { input: 0.15, output: 1.25, cached: 0.015, reasoning: 1.875, cache_creation: 0.15 } },
{ pattern: "gemini-*-flash", pricing: { input: 0.30, output: 2.50, cached: 0.03, reasoning: 3.75, cache_creation: 0.30 } },
{ pattern: "gemini-*-pro", pricing: { input: 2.00, output: 12.00, cached: 0.25, reasoning: 18.00, cache_creation: 2.00 } },
{ pattern: "gemini-3-*", pricing: { input: 0.50, output: 3.00, cached: 0.03, reasoning: 4.50, cache_creation: 0.50 } },
{ pattern: "gemini-2.5-*", pricing: { input: 0.30, output: 2.50, cached: 0.03, reasoning: 3.75, cache_creation: 0.30 } },
{ pattern: "gemini-*", pricing: { input: 0.50, output: 3.00, cached: 0.03, reasoning: 4.50, cache_creation: 0.50 } },
// --- GPT (specific first, generic last) ---
{ pattern: "gpt-5.3-*", pricing: { input: 6.00, output: 24.00, cached: 3.00, reasoning: 36.00, cache_creation: 6.00 } },
{ pattern: "gpt-5.2-*", pricing: { input: 5.00, output: 20.00, cached: 2.50, reasoning: 30.00, cache_creation: 5.00 } },
{ pattern: "gpt-5.1-*", pricing: { input: 4.00, output: 16.00, cached: 2.00, reasoning: 24.00, cache_creation: 4.00 } },
{ pattern: "gpt-5-*", pricing: { input: 3.00, output: 12.00, cached: 1.50, reasoning: 18.00, cache_creation: 3.00 } },
{ pattern: "gpt-5*", pricing: { input: 3.00, output: 12.00, cached: 1.50, reasoning: 18.00, cache_creation: 3.00 } },
{ pattern: "gpt-4o-*", pricing: { input: 0.15, output: 0.60, cached: 0.075, reasoning: 0.90, cache_creation: 0.15 } },
{ pattern: "gpt-4o", pricing: { input: 2.50, output: 10.00, cached: 1.25, reasoning: 15.00, cache_creation: 2.50 } },
{ pattern: "gpt-4*", pricing: { input: 2.50, output: 10.00, cached: 1.25, reasoning: 15.00, cache_creation: 2.50 } },
// --- o1 / o-series ---
{ pattern: "o1-*", pricing: { input: 3.00, output: 12.00, cached: 1.50, reasoning: 18.00, cache_creation: 3.00 } },
{ pattern: "o1", pricing: { input: 15.00, output: 60.00, cached: 7.50, reasoning: 90.00, cache_creation: 15.00 } },
{ pattern: "o3-*", pricing: { input: 10.00, output: 40.00, cached: 5.00, reasoning: 60.00, cache_creation: 10.00 } },
{ pattern: "o4-*", pricing: { input: 2.00, output: 8.00, cached: 1.00, reasoning: 12.00, cache_creation: 2.00 } },
// --- Qwen ---
{ pattern: "qwen3-coder-*", pricing: { input: 1.00, output: 4.00, cached: 0.50, reasoning: 6.00, cache_creation: 1.00 } },
{ pattern: "qwen*-coder-*", pricing: { input: 1.00, output: 4.00, cached: 0.50, reasoning: 6.00, cache_creation: 1.00 } },
{ pattern: "qwen*", pricing: { input: 0.50, output: 2.00, cached: 0.25, reasoning: 3.00, cache_creation: 0.50 } },
// --- Kimi ---
{ pattern: "kimi-*-thinking", pricing: { input: 1.80, output: 7.20, cached: 0.90, reasoning: 10.80, cache_creation: 1.80 } },
{ pattern: "kimi-k2*", pricing: { input: 1.20, output: 4.80, cached: 0.60, reasoning: 7.20, cache_creation: 1.20 } },
{ pattern: "kimi-*", pricing: { input: 1.00, output: 4.00, cached: 0.50, reasoning: 6.00, cache_creation: 1.00 } },
// --- DeepSeek ---
{ pattern: "deepseek-*reasoner*", pricing: { input: 0.14, output: 0.28, cached: 0.0028, reasoning: 0.28, cache_creation: 0.14 } },
{ pattern: "deepseek-r*", pricing: { input: 0.14, output: 0.28, cached: 0.0028, reasoning: 0.28, cache_creation: 0.14 } },
{ pattern: "deepseek-v*", pricing: { input: 0.14, output: 0.28, cached: 0.0028, reasoning: 0.28, cache_creation: 0.14 } },
{ pattern: "deepseek-*", pricing: { input: 0.14, output: 0.28, cached: 0.0028, reasoning: 0.28, cache_creation: 0.14 } },
// --- GLM ---
{ pattern: "glm-5*", pricing: { input: 1.00, output: 4.00, cached: 0.50, reasoning: 6.00, cache_creation: 1.00 } },
{ pattern: "glm-4*", pricing: { input: 0.75, output: 3.00, cached: 0.375, reasoning: 4.50, cache_creation: 0.75 } },
{ pattern: "glm-*", pricing: { input: 0.50, output: 2.00, cached: 0.25, reasoning: 3.00, cache_creation: 0.50 } },
// --- MiniMax ---
{ pattern: "MiniMax-*", pricing: { input: 0.50, output: 2.00, cached: 0.25, reasoning: 3.00, cache_creation: 0.50 } },
{ pattern: "minimax-*", pricing: { input: 0.50, output: 2.00, cached: 0.25, reasoning: 3.00, cache_creation: 0.50 } },
// --- Grok ---
{ pattern: "grok-code-*", pricing: { input: 0.50, output: 2.00, cached: 0.25, reasoning: 3.00, cache_creation: 0.50 } },
{ pattern: "grok-*", pricing: { input: 0.50, output: 2.00, cached: 0.25, reasoning: 3.00, cache_creation: 0.50 } },
];
/**
* Match a model ID against a glob pattern (* = wildcard).
*/
function matchPattern(pattern, model) {
const regex = new RegExp("^" + pattern.split("*").map(s => s.replace(/[.*+?^${}()|[\]\\]/g, "\\$&")).join(".*") + "$");
return regex.test(model);
}
/**
* Resolve pricing for a model using the 3-step fallback chain:
* 1. PROVIDER_PRICING[provider][model]
* 2. MODEL_PRICING[model]
* 3. PATTERN_PRICING (glob match)
*
* @param {string} provider
* @param {string} model
* @returns {object|null}
*/
export function getPricingForModel(provider, model) {
if (!model) return null;
// 1. Provider-specific override
if (provider && PROVIDER_PRICING[provider]?.[model]) {
return PROVIDER_PRICING[provider][model];
}
// 2. Canonical model pricing (strip vendor prefix if needed: "deepseek/deepseek-chat" → "deepseek-chat")
const baseModel = model.includes("/") ? model.split("/").pop() : model;
if (MODEL_PRICING[baseModel]) return MODEL_PRICING[baseModel];
if (MODEL_PRICING[model]) return MODEL_PRICING[model];
// 3. Pattern match
for (const { pattern, pricing } of PATTERN_PRICING) {
if (matchPattern(pattern, baseModel) || matchPattern(pattern, model)) {
return pricing;
}
}
return null;
}
/**
* Get all provider pricing (for UI / API).
* Returns PROVIDER_PRICING — consumers should fall back to MODEL_PRICING for unlisted models.
*/
export function getDefaultPricing() {
return PROVIDER_PRICING;
}
/**
* Format cost for display
* @param {number} cost
* @returns {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
* @param {object} pricing
* @returns {number} cost in dollars
*/
export function calculateCostFromTokens(tokens, pricing) {
if (!tokens || !pricing) return 0;
let cost = 0;
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);
if (cachedTokens > 0) {
cost += cachedTokens * ((pricing.cached || pricing.input) / 1000000);
}
const outputTokens = tokens.completion_tokens || tokens.output_tokens || 0;
cost += outputTokens * (pricing.output / 1000000);
const reasoningTokens = tokens.reasoning_tokens || 0;
if (reasoningTokens > 0) {
cost += reasoningTokens * ((pricing.reasoning || pricing.output) / 1000000);
}
const cacheCreationTokens = tokens.cache_creation_input_tokens || 0;
if (cacheCreationTokens > 0) {
cost += cacheCreationTokens * ((pricing.cache_creation || pricing.input) / 1000000);
}
return cost;
}
|