@ryanfw/prompt-orchestration-pipeline 1.2.6 → 1.2.7

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -20230,41 +20230,41 @@ const MODEL_CONFIG_RAW = {
20230
20230
  tokenCostInPerMillion: 0.1,
20231
20231
  tokenCostOutPerMillion: 0.4
20232
20232
  },
20233
- "openai:gpt-4o": {
20233
+ "openai:gpt-5.4": {
20234
20234
  provider: "openai",
20235
- model: "gpt-4o",
20235
+ model: "gpt-5.4",
20236
20236
  tokenCostInPerMillion: 2.5,
20237
- tokenCostOutPerMillion: 10
20237
+ tokenCostOutPerMillion: 15
20238
20238
  },
20239
- "openai:gpt-4o-mini": {
20239
+ "openai:gpt-5.4-mini": {
20240
20240
  provider: "openai",
20241
- model: "gpt-4o-mini",
20242
- tokenCostInPerMillion: 0.15,
20243
- tokenCostOutPerMillion: 0.6
20241
+ model: "gpt-5.4-mini",
20242
+ tokenCostInPerMillion: 0.75,
20243
+ tokenCostOutPerMillion: 4.5
20244
20244
  },
20245
- "openai:gpt-5.2": {
20245
+ "openai:gpt-5.4-nano": {
20246
20246
  provider: "openai",
20247
- model: "gpt-5.2",
20248
- tokenCostInPerMillion: 2,
20249
- tokenCostOutPerMillion: 10
20247
+ model: "gpt-5.4-nano",
20248
+ tokenCostInPerMillion: 0.2,
20249
+ tokenCostOutPerMillion: 1.25
20250
20250
  },
20251
- "openai:gpt-5.2-pro": {
20251
+ "openai:gpt-5.5": {
20252
20252
  provider: "openai",
20253
- model: "gpt-5.2-pro",
20254
- tokenCostInPerMillion: 15,
20255
- tokenCostOutPerMillion: 60
20253
+ model: "gpt-5.5",
20254
+ tokenCostInPerMillion: 5,
20255
+ tokenCostOutPerMillion: 30
20256
20256
  },
20257
- "openai:o3": {
20257
+ "openai:gpt-5.5-pro": {
20258
20258
  provider: "openai",
20259
- model: "o3",
20260
- tokenCostInPerMillion: 10,
20261
- tokenCostOutPerMillion: 40
20259
+ model: "gpt-5.5-pro",
20260
+ tokenCostInPerMillion: 30,
20261
+ tokenCostOutPerMillion: 180
20262
20262
  },
20263
- "openai:o3-mini": {
20263
+ "openai:o3": {
20264
20264
  provider: "openai",
20265
- model: "o3-mini",
20266
- tokenCostInPerMillion: 1.1,
20267
- tokenCostOutPerMillion: 4.4
20265
+ model: "o3",
20266
+ tokenCostInPerMillion: 2,
20267
+ tokenCostOutPerMillion: 8
20268
20268
  },
20269
20269
  "openai:o4-mini": {
20270
20270
  provider: "openai",
@@ -20303,13 +20303,13 @@ const MODEL_CONFIG_RAW = {
20303
20303
  tokenCostInPerMillion: 3,
20304
20304
  tokenCostOutPerMillion: 15
20305
20305
  },
20306
- "anthropic:haiku-4-6": {
20306
+ "anthropic:opus-4-7": {
20307
20307
  provider: "anthropic",
20308
- model: "claude-haiku-4-6",
20309
- tokenCostInPerMillion: 1,
20310
- tokenCostOutPerMillion: 5
20308
+ model: "claude-opus-4-7",
20309
+ tokenCostInPerMillion: 5,
20310
+ tokenCostOutPerMillion: 25
20311
20311
  },
20312
- // Gemini
20312
+ // Gemini — base (≤200k context) pricing for tiered models
20313
20313
  "gemini:flash-2.5": {
20314
20314
  provider: "gemini",
20315
20315
  model: "gemini-2.5-flash",
@@ -20328,31 +20328,49 @@ const MODEL_CONFIG_RAW = {
20328
20328
  tokenCostInPerMillion: 1.25,
20329
20329
  tokenCostOutPerMillion: 10
20330
20330
  },
20331
+ "gemini:pro-3.1-preview": {
20332
+ provider: "gemini",
20333
+ model: "gemini-3.1-pro-preview",
20334
+ tokenCostInPerMillion: 2,
20335
+ tokenCostOutPerMillion: 12
20336
+ },
20337
+ "gemini:flash-3-preview": {
20338
+ provider: "gemini",
20339
+ model: "gemini-3-flash-preview",
20340
+ tokenCostInPerMillion: 0.5,
20341
+ tokenCostOutPerMillion: 3
20342
+ },
20343
+ "gemini:flash-3.1-lite-preview": {
20344
+ provider: "gemini",
20345
+ model: "gemini-3.1-flash-lite-preview",
20346
+ tokenCostInPerMillion: 0.25,
20347
+ tokenCostOutPerMillion: 1.5
20348
+ },
20331
20349
  // DeepSeek — cache miss prices
20332
- "deepseek:deepseek-chat": {
20350
+ "deepseek:v4-flash": {
20333
20351
  provider: "deepseek",
20334
- model: "deepseek-chat",
20335
- tokenCostInPerMillion: 0.28,
20336
- tokenCostOutPerMillion: 0.42
20352
+ model: "deepseek-v4-flash",
20353
+ tokenCostInPerMillion: 0.14,
20354
+ tokenCostOutPerMillion: 0.28
20337
20355
  },
20338
- "deepseek:deepseek-reasoner": {
20356
+ "deepseek:v4-pro": {
20339
20357
  provider: "deepseek",
20340
- model: "deepseek-reasoner",
20341
- tokenCostInPerMillion: 0.28,
20342
- tokenCostOutPerMillion: 0.42
20358
+ model: "deepseek-v4-pro",
20359
+ tokenCostInPerMillion: 1.74,
20360
+ tokenCostOutPerMillion: 3.48
20343
20361
  },
20344
- // Moonshot / Kimi
20362
+ // Moonshot / Kimi — cache miss prices
20345
20363
  "moonshot:kimi-k2.5": {
20346
20364
  provider: "moonshot",
20347
20365
  model: "kimi-k2.5",
20348
- tokenCostInPerMillion: 0.5,
20366
+ tokenCostInPerMillion: 0.6,
20349
20367
  tokenCostOutPerMillion: 2.5
20350
20368
  },
20351
- "moonshot:kimi-k1.5": {
20369
+ "moonshot:kimi-k2.6": {
20352
20370
  provider: "moonshot",
20353
- model: "kimi-k1.5",
20354
- tokenCostInPerMillion: 0.5,
20355
- tokenCostOutPerMillion: 2.5
20371
+ model: "kimi-k2.6",
20372
+ tokenCostInPerMillion: 0.95,
20373
+ tokenCostOutPerMillion: 4
20356
20374
  },
20357
20375
  // Claude Code — subscription-based, zero token cost
20358
20376
  "claude-code:sonnet": {
@@ -20374,17 +20392,23 @@ const MODEL_CONFIG_RAW = {
20374
20392
  tokenCostOutPerMillion: 0
20375
20393
  },
20376
20394
  // Z.ai
20395
+ "zai:glm-5-1": {
20396
+ provider: "zai",
20397
+ model: "glm-5.1",
20398
+ tokenCostInPerMillion: 1.4,
20399
+ tokenCostOutPerMillion: 4.4
20400
+ },
20377
20401
  "zai:glm-5": {
20378
20402
  provider: "zai",
20379
20403
  model: "glm-5",
20380
20404
  tokenCostInPerMillion: 1,
20381
20405
  tokenCostOutPerMillion: 3.2
20382
20406
  },
20383
- "zai:glm-5-code": {
20407
+ "zai:glm-5-turbo": {
20384
20408
  provider: "zai",
20385
- model: "glm-5-code",
20409
+ model: "glm-5-turbo",
20386
20410
  tokenCostInPerMillion: 1.2,
20387
- tokenCostOutPerMillion: 5
20411
+ tokenCostOutPerMillion: 4
20388
20412
  },
20389
20413
  "zai:glm-4-7": {
20390
20414
  provider: "zai",
@@ -20410,6 +20434,12 @@ const MODEL_CONFIG_RAW = {
20410
20434
  tokenCostInPerMillion: 0.6,
20411
20435
  tokenCostOutPerMillion: 2.2
20412
20436
  },
20437
+ "zai:glm-4-5-x": {
20438
+ provider: "zai",
20439
+ model: "glm-4.5-x",
20440
+ tokenCostInPerMillion: 2.2,
20441
+ tokenCostOutPerMillion: 8.9
20442
+ },
20413
20443
  "zai:glm-4-5-air": {
20414
20444
  provider: "zai",
20415
20445
  model: "glm-4.5-air",
@@ -20422,30 +20452,42 @@ const MODEL_CONFIG_RAW = {
20422
20452
  tokenCostInPerMillion: 1.1,
20423
20453
  tokenCostOutPerMillion: 4.5
20424
20454
  },
20425
- // Alibaba (Qwen via DashScope)
20455
+ // Alibaba (Qwen via DashScope, international/Singapore deployment, base tier)
20426
20456
  "alibaba:qwen3-max": {
20427
20457
  provider: "alibaba",
20428
20458
  model: "qwen3-max",
20429
- tokenCostInPerMillion: 0.359,
20430
- tokenCostOutPerMillion: 1.434
20459
+ tokenCostInPerMillion: 1.2,
20460
+ tokenCostOutPerMillion: 6
20461
+ },
20462
+ "alibaba:qwen3.6-plus": {
20463
+ provider: "alibaba",
20464
+ model: "qwen3.6-plus",
20465
+ tokenCostInPerMillion: 0.276,
20466
+ tokenCostOutPerMillion: 1.651
20431
20467
  },
20432
20468
  "alibaba:qwen3.5-plus": {
20433
20469
  provider: "alibaba",
20434
20470
  model: "qwen3.5-plus",
20435
- tokenCostInPerMillion: 0.115,
20436
- tokenCostOutPerMillion: 0.688
20471
+ tokenCostInPerMillion: 0.4,
20472
+ tokenCostOutPerMillion: 2.4
20473
+ },
20474
+ "alibaba:qwen3.5-flash": {
20475
+ provider: "alibaba",
20476
+ model: "qwen3.5-flash",
20477
+ tokenCostInPerMillion: 0.1,
20478
+ tokenCostOutPerMillion: 0.4
20437
20479
  },
20438
20480
  "alibaba:qwen-plus": {
20439
20481
  provider: "alibaba",
20440
20482
  model: "qwen-plus",
20441
- tokenCostInPerMillion: 0.115,
20442
- tokenCostOutPerMillion: 0.287
20483
+ tokenCostInPerMillion: 0.4,
20484
+ tokenCostOutPerMillion: 1.2
20443
20485
  },
20444
20486
  "alibaba:qwen-flash": {
20445
20487
  provider: "alibaba",
20446
20488
  model: "qwen-flash",
20447
- tokenCostInPerMillion: 0.022,
20448
- tokenCostOutPerMillion: 0.216
20489
+ tokenCostInPerMillion: 0.05,
20490
+ tokenCostOutPerMillion: 0.4
20449
20491
  },
20450
20492
  "alibaba:qwq-plus": {
20451
20493
  provider: "alibaba",
@@ -20456,14 +20498,14 @@ const MODEL_CONFIG_RAW = {
20456
20498
  "alibaba:qwen3-coder-plus": {
20457
20499
  provider: "alibaba",
20458
20500
  model: "qwen3-coder-plus",
20459
- tokenCostInPerMillion: 0.574,
20460
- tokenCostOutPerMillion: 2.294
20501
+ tokenCostInPerMillion: 1,
20502
+ tokenCostOutPerMillion: 5
20461
20503
  },
20462
20504
  "alibaba:qwen3-coder-flash": {
20463
20505
  provider: "alibaba",
20464
20506
  model: "qwen3-coder-flash",
20465
- tokenCostInPerMillion: 0.144,
20466
- tokenCostOutPerMillion: 0.574
20507
+ tokenCostInPerMillion: 0.3,
20508
+ tokenCostOutPerMillion: 1.5
20467
20509
  }
20468
20510
  };
20469
20511
  const MODEL_CONFIG = deepFreeze(MODEL_CONFIG_RAW);