@apholdings/jensen-ai 1.1.2 → 1.1.4

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.
@@ -1260,6 +1260,57 @@ export const MODELS = {
1260
1260
  contextWindow: 272000,
1261
1261
  maxTokens: 128000,
1262
1262
  },
1263
+ "openai.gpt-5.6-luna": {
1264
+ id: "openai.gpt-5.6-luna",
1265
+ name: "GPT-5.6 Luna",
1266
+ api: "bedrock-converse-stream",
1267
+ provider: "amazon-bedrock",
1268
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1269
+ reasoning: true,
1270
+ input: ["text", "image"],
1271
+ cost: {
1272
+ input: 1,
1273
+ output: 6,
1274
+ cacheRead: 0.1,
1275
+ cacheWrite: 1.25,
1276
+ },
1277
+ contextWindow: 272000,
1278
+ maxTokens: 128000,
1279
+ },
1280
+ "openai.gpt-5.6-sol": {
1281
+ id: "openai.gpt-5.6-sol",
1282
+ name: "GPT-5.6 Sol",
1283
+ api: "bedrock-converse-stream",
1284
+ provider: "amazon-bedrock",
1285
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1286
+ reasoning: true,
1287
+ input: ["text", "image"],
1288
+ cost: {
1289
+ input: 5,
1290
+ output: 30,
1291
+ cacheRead: 0.5,
1292
+ cacheWrite: 6.25,
1293
+ },
1294
+ contextWindow: 272000,
1295
+ maxTokens: 128000,
1296
+ },
1297
+ "openai.gpt-5.6-terra": {
1298
+ id: "openai.gpt-5.6-terra",
1299
+ name: "GPT-5.6 Terra",
1300
+ api: "bedrock-converse-stream",
1301
+ provider: "amazon-bedrock",
1302
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1303
+ reasoning: true,
1304
+ input: ["text", "image"],
1305
+ cost: {
1306
+ input: 2.5,
1307
+ output: 15,
1308
+ cacheRead: 0.25,
1309
+ cacheWrite: 3.125,
1310
+ },
1311
+ contextWindow: 272000,
1312
+ maxTokens: 128000,
1313
+ },
1263
1314
  "openai.gpt-oss-120b": {
1264
1315
  id: "openai.gpt-oss-120b",
1265
1316
  name: "gpt-oss-120b",
@@ -2624,6 +2675,91 @@ export const MODELS = {
2624
2675
  contextWindow: 1050000,
2625
2676
  maxTokens: 128000,
2626
2677
  },
2678
+ "gpt-5.6": {
2679
+ id: "gpt-5.6",
2680
+ name: "GPT-5.6",
2681
+ api: "azure-openai-responses",
2682
+ provider: "azure-openai-responses",
2683
+ baseUrl: "",
2684
+ reasoning: true,
2685
+ input: ["text", "image"],
2686
+ cost: {
2687
+ input: 5,
2688
+ output: 30,
2689
+ cacheRead: 0.5,
2690
+ cacheWrite: 6.25,
2691
+ },
2692
+ contextWindow: 1050000,
2693
+ maxTokens: 128000,
2694
+ },
2695
+ "gpt-5.6-luna": {
2696
+ id: "gpt-5.6-luna",
2697
+ name: "GPT-5.6 Luna",
2698
+ api: "azure-openai-responses",
2699
+ provider: "azure-openai-responses",
2700
+ baseUrl: "",
2701
+ reasoning: true,
2702
+ input: ["text", "image"],
2703
+ cost: {
2704
+ input: 1,
2705
+ output: 6,
2706
+ cacheRead: 0.1,
2707
+ cacheWrite: 1.25,
2708
+ },
2709
+ contextWindow: 1050000,
2710
+ maxTokens: 128000,
2711
+ },
2712
+ "gpt-5.6-sol": {
2713
+ id: "gpt-5.6-sol",
2714
+ name: "GPT-5.6 Sol",
2715
+ api: "azure-openai-responses",
2716
+ provider: "azure-openai-responses",
2717
+ baseUrl: "",
2718
+ reasoning: true,
2719
+ input: ["text", "image"],
2720
+ cost: {
2721
+ input: 5,
2722
+ output: 30,
2723
+ cacheRead: 0.5,
2724
+ cacheWrite: 6.25,
2725
+ },
2726
+ contextWindow: 1050000,
2727
+ maxTokens: 128000,
2728
+ },
2729
+ "gpt-5.6-terra": {
2730
+ id: "gpt-5.6-terra",
2731
+ name: "GPT-5.6 Terra",
2732
+ api: "azure-openai-responses",
2733
+ provider: "azure-openai-responses",
2734
+ baseUrl: "",
2735
+ reasoning: true,
2736
+ input: ["text", "image"],
2737
+ cost: {
2738
+ input: 2.5,
2739
+ output: 15,
2740
+ cacheRead: 0.25,
2741
+ cacheWrite: 3.125,
2742
+ },
2743
+ contextWindow: 1050000,
2744
+ maxTokens: 128000,
2745
+ },
2746
+ "gpt-realtime-2.1": {
2747
+ id: "gpt-realtime-2.1",
2748
+ name: "GPT-Realtime-2.1",
2749
+ api: "azure-openai-responses",
2750
+ provider: "azure-openai-responses",
2751
+ baseUrl: "",
2752
+ reasoning: true,
2753
+ input: ["text", "image"],
2754
+ cost: {
2755
+ input: 4,
2756
+ output: 24,
2757
+ cacheRead: 0.4,
2758
+ cacheWrite: 0,
2759
+ },
2760
+ contextWindow: 128000,
2761
+ maxTokens: 32000,
2762
+ },
2627
2763
  "o1": {
2628
2764
  id: "o1",
2629
2765
  name: "o1",
@@ -2807,7 +2943,7 @@ export const MODELS = {
2807
2943
  cost: {
2808
2944
  input: 2.25,
2809
2945
  output: 2.75,
2810
- cacheRead: 0,
2946
+ cacheRead: 2.25,
2811
2947
  cacheWrite: 0,
2812
2948
  },
2813
2949
  contextWindow: 131072,
@@ -3051,7 +3187,7 @@ export const MODELS = {
3051
3187
  cacheRead: 0.2,
3052
3188
  cacheWrite: 0,
3053
3189
  },
3054
- contextWindow: 200000,
3190
+ contextWindow: 1000000,
3055
3191
  maxTokens: 64000,
3056
3192
  },
3057
3193
  "gemini-3.5-flash": {
@@ -3179,7 +3315,7 @@ export const MODELS = {
3179
3315
  cacheRead: 0.25,
3180
3316
  cacheWrite: 0,
3181
3317
  },
3182
- contextWindow: 400000,
3318
+ contextWindow: 1050000,
3183
3319
  maxTokens: 128000,
3184
3320
  },
3185
3321
  "gpt-5.4-mini": {
@@ -3233,7 +3369,61 @@ export const MODELS = {
3233
3369
  cacheRead: 0.5,
3234
3370
  cacheWrite: 0,
3235
3371
  },
3236
- contextWindow: 400000,
3372
+ contextWindow: 1050000,
3373
+ maxTokens: 128000,
3374
+ },
3375
+ "gpt-5.6-luna": {
3376
+ id: "gpt-5.6-luna",
3377
+ name: "GPT-5.6 Luna",
3378
+ api: "openai-responses",
3379
+ provider: "github-copilot",
3380
+ baseUrl: "https://api.individual.githubcopilot.com",
3381
+ headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
3382
+ reasoning: true,
3383
+ input: ["text", "image"],
3384
+ cost: {
3385
+ input: 1,
3386
+ output: 6,
3387
+ cacheRead: 0.1,
3388
+ cacheWrite: 0,
3389
+ },
3390
+ contextWindow: 1050000,
3391
+ maxTokens: 128000,
3392
+ },
3393
+ "gpt-5.6-sol": {
3394
+ id: "gpt-5.6-sol",
3395
+ name: "GPT-5.6 Sol",
3396
+ api: "openai-responses",
3397
+ provider: "github-copilot",
3398
+ baseUrl: "https://api.individual.githubcopilot.com",
3399
+ headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
3400
+ reasoning: true,
3401
+ input: ["text", "image"],
3402
+ cost: {
3403
+ input: 5,
3404
+ output: 30,
3405
+ cacheRead: 0.5,
3406
+ cacheWrite: 0,
3407
+ },
3408
+ contextWindow: 1050000,
3409
+ maxTokens: 128000,
3410
+ },
3411
+ "gpt-5.6-terra": {
3412
+ id: "gpt-5.6-terra",
3413
+ name: "GPT-5.6 Terra",
3414
+ api: "openai-responses",
3415
+ provider: "github-copilot",
3416
+ baseUrl: "https://api.individual.githubcopilot.com",
3417
+ headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
3418
+ reasoning: true,
3419
+ input: ["text", "image"],
3420
+ cost: {
3421
+ input: 2.5,
3422
+ output: 15,
3423
+ cacheRead: 0.25,
3424
+ cacheWrite: 0,
3425
+ },
3426
+ contextWindow: 1050000,
3237
3427
  maxTokens: 128000,
3238
3428
  },
3239
3429
  "kimi-k2.7-code": {
@@ -6405,6 +6595,91 @@ export const MODELS = {
6405
6595
  contextWindow: 1050000,
6406
6596
  maxTokens: 128000,
6407
6597
  },
6598
+ "gpt-5.6": {
6599
+ id: "gpt-5.6",
6600
+ name: "GPT-5.6",
6601
+ api: "openai-responses",
6602
+ provider: "openai",
6603
+ baseUrl: "https://api.openai.com/v1",
6604
+ reasoning: true,
6605
+ input: ["text", "image"],
6606
+ cost: {
6607
+ input: 5,
6608
+ output: 30,
6609
+ cacheRead: 0.5,
6610
+ cacheWrite: 6.25,
6611
+ },
6612
+ contextWindow: 1050000,
6613
+ maxTokens: 128000,
6614
+ },
6615
+ "gpt-5.6-luna": {
6616
+ id: "gpt-5.6-luna",
6617
+ name: "GPT-5.6 Luna",
6618
+ api: "openai-responses",
6619
+ provider: "openai",
6620
+ baseUrl: "https://api.openai.com/v1",
6621
+ reasoning: true,
6622
+ input: ["text", "image"],
6623
+ cost: {
6624
+ input: 1,
6625
+ output: 6,
6626
+ cacheRead: 0.1,
6627
+ cacheWrite: 1.25,
6628
+ },
6629
+ contextWindow: 1050000,
6630
+ maxTokens: 128000,
6631
+ },
6632
+ "gpt-5.6-sol": {
6633
+ id: "gpt-5.6-sol",
6634
+ name: "GPT-5.6 Sol",
6635
+ api: "openai-responses",
6636
+ provider: "openai",
6637
+ baseUrl: "https://api.openai.com/v1",
6638
+ reasoning: true,
6639
+ input: ["text", "image"],
6640
+ cost: {
6641
+ input: 5,
6642
+ output: 30,
6643
+ cacheRead: 0.5,
6644
+ cacheWrite: 6.25,
6645
+ },
6646
+ contextWindow: 1050000,
6647
+ maxTokens: 128000,
6648
+ },
6649
+ "gpt-5.6-terra": {
6650
+ id: "gpt-5.6-terra",
6651
+ name: "GPT-5.6 Terra",
6652
+ api: "openai-responses",
6653
+ provider: "openai",
6654
+ baseUrl: "https://api.openai.com/v1",
6655
+ reasoning: true,
6656
+ input: ["text", "image"],
6657
+ cost: {
6658
+ input: 2.5,
6659
+ output: 15,
6660
+ cacheRead: 0.25,
6661
+ cacheWrite: 3.125,
6662
+ },
6663
+ contextWindow: 1050000,
6664
+ maxTokens: 128000,
6665
+ },
6666
+ "gpt-realtime-2.1": {
6667
+ id: "gpt-realtime-2.1",
6668
+ name: "GPT-Realtime-2.1",
6669
+ api: "openai-responses",
6670
+ provider: "openai",
6671
+ baseUrl: "https://api.openai.com/v1",
6672
+ reasoning: true,
6673
+ input: ["text", "image"],
6674
+ cost: {
6675
+ input: 4,
6676
+ output: 24,
6677
+ cacheRead: 0.4,
6678
+ cacheWrite: 0,
6679
+ },
6680
+ contextWindow: 128000,
6681
+ maxTokens: 32000,
6682
+ },
6408
6683
  "o1": {
6409
6684
  id: "o1",
6410
6685
  name: "o1",
@@ -7327,36 +7602,87 @@ export const MODELS = {
7327
7602
  contextWindow: 1050000,
7328
7603
  maxTokens: 128000,
7329
7604
  },
7330
- "grok-4.5": {
7331
- id: "grok-4.5",
7332
- name: "Grok 4.5",
7333
- api: "openai-completions",
7605
+ "gpt-5.6-luna": {
7606
+ id: "gpt-5.6-luna",
7607
+ name: "GPT-5.6 Luna",
7608
+ api: "openai-responses",
7334
7609
  provider: "opencode",
7335
7610
  baseUrl: "https://opencode.ai/zen/v1",
7336
7611
  reasoning: true,
7337
7612
  input: ["text", "image"],
7338
7613
  cost: {
7339
- input: 2,
7614
+ input: 1,
7340
7615
  output: 6,
7341
- cacheRead: 0.5,
7342
- cacheWrite: 0,
7616
+ cacheRead: 0.1,
7617
+ cacheWrite: 1.25,
7343
7618
  },
7344
- contextWindow: 500000,
7345
- maxTokens: 500000,
7619
+ contextWindow: 1050000,
7620
+ maxTokens: 128000,
7346
7621
  },
7347
- "grok-build-0.1": {
7348
- id: "grok-build-0.1",
7349
- name: "Grok Build 0.1",
7350
- api: "openai-completions",
7622
+ "gpt-5.6-sol": {
7623
+ id: "gpt-5.6-sol",
7624
+ name: "GPT-5.6 Sol",
7625
+ api: "openai-responses",
7351
7626
  provider: "opencode",
7352
7627
  baseUrl: "https://opencode.ai/zen/v1",
7353
7628
  reasoning: true,
7354
7629
  input: ["text", "image"],
7355
7630
  cost: {
7356
- input: 1,
7357
- output: 2,
7358
- cacheRead: 0.2,
7359
- cacheWrite: 0,
7631
+ input: 5,
7632
+ output: 30,
7633
+ cacheRead: 0.5,
7634
+ cacheWrite: 6.25,
7635
+ },
7636
+ contextWindow: 1050000,
7637
+ maxTokens: 128000,
7638
+ },
7639
+ "gpt-5.6-terra": {
7640
+ id: "gpt-5.6-terra",
7641
+ name: "GPT-5.6 Terra",
7642
+ api: "openai-responses",
7643
+ provider: "opencode",
7644
+ baseUrl: "https://opencode.ai/zen/v1",
7645
+ reasoning: true,
7646
+ input: ["text", "image"],
7647
+ cost: {
7648
+ input: 2.5,
7649
+ output: 15,
7650
+ cacheRead: 0.25,
7651
+ cacheWrite: 3.125,
7652
+ },
7653
+ contextWindow: 1050000,
7654
+ maxTokens: 128000,
7655
+ },
7656
+ "grok-4.5": {
7657
+ id: "grok-4.5",
7658
+ name: "Grok 4.5",
7659
+ api: "openai-completions",
7660
+ provider: "opencode",
7661
+ baseUrl: "https://opencode.ai/zen/v1",
7662
+ reasoning: true,
7663
+ input: ["text", "image"],
7664
+ cost: {
7665
+ input: 2,
7666
+ output: 6,
7667
+ cacheRead: 0.5,
7668
+ cacheWrite: 0,
7669
+ },
7670
+ contextWindow: 500000,
7671
+ maxTokens: 500000,
7672
+ },
7673
+ "grok-build-0.1": {
7674
+ id: "grok-build-0.1",
7675
+ name: "Grok Build 0.1",
7676
+ api: "openai-completions",
7677
+ provider: "opencode",
7678
+ baseUrl: "https://opencode.ai/zen/v1",
7679
+ reasoning: true,
7680
+ input: ["text", "image"],
7681
+ cost: {
7682
+ input: 1,
7683
+ output: 2,
7684
+ cacheRead: 0.2,
7685
+ cacheWrite: 0,
7360
7686
  },
7361
7687
  contextWindow: 256000,
7362
7688
  maxTokens: 256000,
@@ -7375,7 +7701,7 @@ export const MODELS = {
7375
7701
  cacheRead: 0,
7376
7702
  cacheWrite: 0,
7377
7703
  },
7378
- contextWindow: 256000,
7704
+ contextWindow: 190000,
7379
7705
  maxTokens: 64000,
7380
7706
  },
7381
7707
  "kimi-k2.5": {
@@ -8215,23 +8541,6 @@ export const MODELS = {
8215
8541
  contextWindow: 262144,
8216
8542
  maxTokens: 80000,
8217
8543
  },
8218
- "arcee-ai/trinity-mini": {
8219
- id: "arcee-ai/trinity-mini",
8220
- name: "Arcee AI: Trinity Mini",
8221
- api: "openai-completions",
8222
- provider: "openrouter",
8223
- baseUrl: "https://openrouter.ai/api/v1",
8224
- reasoning: true,
8225
- input: ["text"],
8226
- cost: {
8227
- input: 0.045,
8228
- output: 0.15,
8229
- cacheRead: 0,
8230
- cacheWrite: 0,
8231
- },
8232
- contextWindow: 131072,
8233
- maxTokens: 131072,
8234
- },
8235
8544
  "arcee-ai/virtuoso-large": {
8236
8545
  id: "arcee-ai/virtuoso-large",
8237
8546
  name: "Arcee AI: Virtuoso Large",
@@ -8428,8 +8737,8 @@ export const MODELS = {
8428
8737
  reasoning: true,
8429
8738
  input: ["text"],
8430
8739
  cost: {
8431
- input: 0.21,
8432
- output: 0.7899999999999999,
8740
+ input: 0.25,
8741
+ output: 0.95,
8433
8742
  cacheRead: 0.13,
8434
8743
  cacheWrite: 0,
8435
8744
  },
@@ -8496,9 +8805,9 @@ export const MODELS = {
8496
8805
  reasoning: true,
8497
8806
  input: ["text"],
8498
8807
  cost: {
8499
- input: 0.2288,
8500
- output: 0.3432,
8501
- cacheRead: 0.02288,
8808
+ input: 0.2145,
8809
+ output: 0.32175,
8810
+ cacheRead: 0.02145,
8502
8811
  cacheWrite: 0,
8503
8812
  },
8504
8813
  contextWindow: 131072,
@@ -8836,13 +9145,13 @@ export const MODELS = {
8836
9145
  reasoning: true,
8837
9146
  input: ["text", "image"],
8838
9147
  cost: {
8839
- input: 0.12,
9148
+ input: 0.06,
8840
9149
  output: 0.35,
8841
- cacheRead: 0.09,
9150
+ cacheRead: 0,
8842
9151
  cacheWrite: 0,
8843
9152
  },
8844
9153
  contextWindow: 262144,
8845
- maxTokens: 262144,
9154
+ maxTokens: 8192,
8846
9155
  },
8847
9156
  "google/gemma-4-31b-it:free": {
8848
9157
  id: "google/gemma-4-31b-it:free",
@@ -8859,7 +9168,7 @@ export const MODELS = {
8859
9168
  cacheWrite: 0,
8860
9169
  },
8861
9170
  contextWindow: 262144,
8862
- maxTokens: 8192,
9171
+ maxTokens: 32768,
8863
9172
  },
8864
9173
  "ibm-granite/granite-4.1-8b": {
8865
9174
  id: "ibm-granite/granite-4.1-8b",
@@ -8946,6 +9255,23 @@ export const MODELS = {
8946
9255
  contextWindow: 262144,
8947
9256
  maxTokens: 65536,
8948
9257
  },
9258
+ "kwaipilot/kat-coder-air-v2.5": {
9259
+ id: "kwaipilot/kat-coder-air-v2.5",
9260
+ name: "Kwaipilot: KAT-Coder-Air V2.5",
9261
+ api: "openai-completions",
9262
+ provider: "openrouter",
9263
+ baseUrl: "https://openrouter.ai/api/v1",
9264
+ reasoning: false,
9265
+ input: ["text"],
9266
+ cost: {
9267
+ input: 0.15,
9268
+ output: 0.6,
9269
+ cacheRead: 0.03,
9270
+ cacheWrite: 0,
9271
+ },
9272
+ contextWindow: 256000,
9273
+ maxTokens: 80000,
9274
+ },
8949
9275
  "kwaipilot/kat-coder-pro-v2": {
8950
9276
  id: "kwaipilot/kat-coder-pro-v2",
8951
9277
  name: "Kwaipilot: KAT-Coder-Pro V2",
@@ -8963,22 +9289,22 @@ export const MODELS = {
8963
9289
  contextWindow: 256000,
8964
9290
  maxTokens: 80000,
8965
9291
  },
8966
- "liquid/lfm-2.5-1.2b-thinking:free": {
8967
- id: "liquid/lfm-2.5-1.2b-thinking:free",
8968
- name: "LiquidAI: LFM2.5-1.2B-Thinking (free)",
9292
+ "kwaipilot/kat-coder-pro-v2.5": {
9293
+ id: "kwaipilot/kat-coder-pro-v2.5",
9294
+ name: "Kwaipilot: KAT-Coder-Pro V2.5",
8969
9295
  api: "openai-completions",
8970
9296
  provider: "openrouter",
8971
9297
  baseUrl: "https://openrouter.ai/api/v1",
8972
- reasoning: true,
9298
+ reasoning: false,
8973
9299
  input: ["text"],
8974
9300
  cost: {
8975
- input: 0,
8976
- output: 0,
8977
- cacheRead: 0,
9301
+ input: 0.74,
9302
+ output: 2.96,
9303
+ cacheRead: 0.15,
8978
9304
  cacheWrite: 0,
8979
9305
  },
8980
- contextWindow: 32768,
8981
- maxTokens: 4096,
9306
+ contextWindow: 256000,
9307
+ maxTokens: 80000,
8982
9308
  },
8983
9309
  "meta-llama/llama-3.1-70b-instruct": {
8984
9310
  id: "meta-llama/llama-3.1-70b-instruct",
@@ -9057,8 +9383,8 @@ export const MODELS = {
9057
9383
  reasoning: false,
9058
9384
  input: ["text", "image"],
9059
9385
  cost: {
9060
- input: 0.15,
9061
- output: 0.6,
9386
+ input: 0.19999999999999998,
9387
+ output: 0.7999999999999999,
9062
9388
  cacheRead: 0,
9063
9389
  cacheWrite: 0,
9064
9390
  },
@@ -9182,7 +9508,7 @@ export const MODELS = {
9182
9508
  cacheWrite: 0,
9183
9509
  },
9184
9510
  contextWindow: 1048576,
9185
- maxTokens: 512000,
9511
+ maxTokens: 131072,
9186
9512
  },
9187
9513
  "mistralai/codestral-2508": {
9188
9514
  id: "mistralai/codestral-2508",
@@ -9550,9 +9876,9 @@ export const MODELS = {
9550
9876
  reasoning: true,
9551
9877
  input: ["text", "image"],
9552
9878
  cost: {
9553
- input: 0.65,
9879
+ input: 0.66,
9554
9880
  output: 3.41,
9555
- cacheRead: 0.14,
9881
+ cacheRead: 0.15,
9556
9882
  cacheWrite: 0,
9557
9883
  },
9558
9884
  contextWindow: 262144,
@@ -9567,9 +9893,9 @@ export const MODELS = {
9567
9893
  reasoning: true,
9568
9894
  input: ["text", "image"],
9569
9895
  cost: {
9570
- input: 0.72,
9571
- output: 3.5,
9572
- cacheRead: 0.15,
9896
+ input: 0.719,
9897
+ output: 3.49,
9898
+ cacheRead: 0.149,
9573
9899
  cacheWrite: 0,
9574
9900
  },
9575
9901
  contextWindow: 262144,
@@ -10096,11 +10422,11 @@ export const MODELS = {
10096
10422
  cost: {
10097
10423
  input: 0.049999999999999996,
10098
10424
  output: 0.39999999999999997,
10099
- cacheRead: 0.01,
10425
+ cacheRead: 0.005,
10100
10426
  cacheWrite: 0,
10101
10427
  },
10102
10428
  contextWindow: 400000,
10103
- maxTokens: 4096,
10429
+ maxTokens: 128000,
10104
10430
  },
10105
10431
  "openai/gpt-5-pro": {
10106
10432
  id: "openai/gpt-5-pro",
@@ -10130,7 +10456,7 @@ export const MODELS = {
10130
10456
  cost: {
10131
10457
  input: 1.25,
10132
10458
  output: 10,
10133
- cacheRead: 0.13,
10459
+ cacheRead: 0.125,
10134
10460
  cacheWrite: 0,
10135
10461
  },
10136
10462
  contextWindow: 400000,
@@ -10420,7 +10746,24 @@ export const MODELS = {
10420
10746
  input: 1,
10421
10747
  output: 6,
10422
10748
  cacheRead: 0.09999999999999999,
10423
- cacheWrite: 0,
10749
+ cacheWrite: 1.25,
10750
+ },
10751
+ contextWindow: 1050000,
10752
+ maxTokens: 128000,
10753
+ },
10754
+ "openai/gpt-5.6-luna-pro": {
10755
+ id: "openai/gpt-5.6-luna-pro",
10756
+ name: "OpenAI: GPT-5.6 Luna Pro",
10757
+ api: "openai-completions",
10758
+ provider: "openrouter",
10759
+ baseUrl: "https://openrouter.ai/api/v1",
10760
+ reasoning: true,
10761
+ input: ["text", "image"],
10762
+ cost: {
10763
+ input: 1,
10764
+ output: 6,
10765
+ cacheRead: 0.09999999999999999,
10766
+ cacheWrite: 1.25,
10424
10767
  },
10425
10768
  contextWindow: 1050000,
10426
10769
  maxTokens: 128000,
@@ -10437,7 +10780,24 @@ export const MODELS = {
10437
10780
  input: 5,
10438
10781
  output: 30,
10439
10782
  cacheRead: 0.5,
10440
- cacheWrite: 0,
10783
+ cacheWrite: 6.25,
10784
+ },
10785
+ contextWindow: 1050000,
10786
+ maxTokens: 128000,
10787
+ },
10788
+ "openai/gpt-5.6-sol-pro": {
10789
+ id: "openai/gpt-5.6-sol-pro",
10790
+ name: "OpenAI: GPT-5.6 Sol Pro",
10791
+ api: "openai-completions",
10792
+ provider: "openrouter",
10793
+ baseUrl: "https://openrouter.ai/api/v1",
10794
+ reasoning: true,
10795
+ input: ["text", "image"],
10796
+ cost: {
10797
+ input: 5,
10798
+ output: 30,
10799
+ cacheRead: 0.5,
10800
+ cacheWrite: 6.25,
10441
10801
  },
10442
10802
  contextWindow: 1050000,
10443
10803
  maxTokens: 128000,
@@ -10454,7 +10814,24 @@ export const MODELS = {
10454
10814
  input: 2.5,
10455
10815
  output: 15,
10456
10816
  cacheRead: 0.25,
10457
- cacheWrite: 0,
10817
+ cacheWrite: 3.125,
10818
+ },
10819
+ contextWindow: 1050000,
10820
+ maxTokens: 128000,
10821
+ },
10822
+ "openai/gpt-5.6-terra-pro": {
10823
+ id: "openai/gpt-5.6-terra-pro",
10824
+ name: "OpenAI: GPT-5.6 Terra Pro",
10825
+ api: "openai-completions",
10826
+ provider: "openrouter",
10827
+ baseUrl: "https://openrouter.ai/api/v1",
10828
+ reasoning: true,
10829
+ input: ["text", "image"],
10830
+ cost: {
10831
+ input: 2.5,
10832
+ output: 15,
10833
+ cacheRead: 0.25,
10834
+ cacheWrite: 3.125,
10458
10835
  },
10459
10836
  contextWindow: 1050000,
10460
10837
  maxTokens: 128000,
@@ -10519,25 +10896,8 @@ export const MODELS = {
10519
10896
  reasoning: true,
10520
10897
  input: ["text"],
10521
10898
  cost: {
10522
- input: 0.036,
10523
- output: 0.18,
10524
- cacheRead: 0,
10525
- cacheWrite: 0,
10526
- },
10527
- contextWindow: 131072,
10528
- maxTokens: 4096,
10529
- },
10530
- "openai/gpt-oss-120b:free": {
10531
- id: "openai/gpt-oss-120b:free",
10532
- name: "OpenAI: gpt-oss-120b (free)",
10533
- api: "openai-completions",
10534
- provider: "openrouter",
10535
- baseUrl: "https://openrouter.ai/api/v1",
10536
- reasoning: true,
10537
- input: ["text"],
10538
- cost: {
10539
- input: 0,
10540
- output: 0,
10899
+ input: 0.03,
10900
+ output: 0.15,
10541
10901
  cacheRead: 0,
10542
10902
  cacheWrite: 0,
10543
10903
  },
@@ -10979,7 +11339,7 @@ export const MODELS = {
10979
11339
  input: ["text"],
10980
11340
  cost: {
10981
11341
  input: 0.09,
10982
- output: 0.09999999999999999,
11342
+ output: 0.55,
10983
11343
  cacheRead: 0,
10984
11344
  cacheWrite: 0,
10985
11345
  },
@@ -11539,13 +11899,13 @@ export const MODELS = {
11539
11899
  reasoning: true,
11540
11900
  input: ["text", "image"],
11541
11901
  cost: {
11542
- input: 0.28500000000000003,
11902
+ input: 0.28900000000000003,
11543
11903
  output: 2.4,
11544
- cacheRead: 0.15,
11904
+ cacheRead: 0,
11545
11905
  cacheWrite: 0,
11546
11906
  },
11547
11907
  contextWindow: 262144,
11548
- maxTokens: 262140,
11908
+ maxTokens: 131072,
11549
11909
  },
11550
11910
  "qwen/qwen3.6-35b-a3b": {
11551
11911
  id: "qwen/qwen3.6-35b-a3b",
@@ -11999,12 +12359,12 @@ export const MODELS = {
11999
12359
  input: ["text"],
12000
12360
  cost: {
12001
12361
  input: 0.43,
12002
- output: 1.74,
12362
+ output: 1.75,
12003
12363
  cacheRead: 0.08,
12004
12364
  cacheWrite: 0,
12005
12365
  },
12006
- contextWindow: 202752,
12007
- maxTokens: 131072,
12366
+ contextWindow: 200000,
12367
+ maxTokens: 16384,
12008
12368
  },
12009
12369
  "z-ai/glm-4.6v": {
12010
12370
  id: "z-ai/glm-4.6v",
@@ -12072,7 +12432,7 @@ export const MODELS = {
12072
12432
  cacheWrite: 0,
12073
12433
  },
12074
12434
  contextWindow: 202752,
12075
- maxTokens: 4096,
12435
+ maxTokens: 128000,
12076
12436
  },
12077
12437
  "z-ai/glm-5-turbo": {
12078
12438
  id: "z-ai/glm-5-turbo",
@@ -12117,9 +12477,9 @@ export const MODELS = {
12117
12477
  reasoning: true,
12118
12478
  input: ["text"],
12119
12479
  cost: {
12120
- input: 0.546,
12121
- output: 1.716,
12122
- cacheRead: 0.10139999999999999,
12480
+ input: 0.9281999999999999,
12481
+ output: 2.9172000000000002,
12482
+ cacheRead: 0.17238,
12123
12483
  cacheWrite: 0,
12124
12484
  },
12125
12485
  contextWindow: 1048576,
@@ -12253,9 +12613,9 @@ export const MODELS = {
12253
12613
  reasoning: true,
12254
12614
  input: ["text", "image"],
12255
12615
  cost: {
12256
- input: 0.65,
12616
+ input: 0.66,
12257
12617
  output: 3.41,
12258
- cacheRead: 0.14,
12618
+ cacheRead: 0.15,
12259
12619
  cacheWrite: 0,
12260
12620
  },
12261
12621
  contextWindow: 262144,
@@ -12273,7 +12633,7 @@ export const MODELS = {
12273
12633
  input: 5,
12274
12634
  output: 30,
12275
12635
  cacheRead: 0.5,
12276
- cacheWrite: 0,
12636
+ cacheWrite: 6.25,
12277
12637
  },
12278
12638
  contextWindow: 1050000,
12279
12639
  maxTokens: 128000,
@@ -12807,23 +13167,6 @@ export const MODELS = {
12807
13167
  contextWindow: 200000,
12808
13168
  maxTokens: 4096,
12809
13169
  },
12810
- "anthropic/claude-3.5-haiku": {
12811
- id: "anthropic/claude-3.5-haiku",
12812
- name: "Claude 3.5 Haiku",
12813
- api: "anthropic-messages",
12814
- provider: "vercel-ai-gateway",
12815
- baseUrl: "https://ai-gateway.vercel.sh",
12816
- reasoning: false,
12817
- input: ["text", "image"],
12818
- cost: {
12819
- input: 0.7999999999999999,
12820
- output: 4,
12821
- cacheRead: 0.08,
12822
- cacheWrite: 1,
12823
- },
12824
- contextWindow: 200000,
12825
- maxTokens: 8192,
12826
- },
12827
13170
  "anthropic/claude-fable-5": {
12828
13171
  id: "anthropic/claude-fable-5",
12829
13172
  name: "Claude Fable 5",
@@ -12873,7 +13216,7 @@ export const MODELS = {
12873
13216
  cacheWrite: 18.75,
12874
13217
  },
12875
13218
  contextWindow: 200000,
12876
- maxTokens: 32000,
13219
+ maxTokens: 8192,
12877
13220
  },
12878
13221
  "anthropic/claude-opus-4.1": {
12879
13222
  id: "anthropic/claude-opus-4.1",
@@ -12975,7 +13318,7 @@ export const MODELS = {
12975
13318
  cacheWrite: 3.75,
12976
13319
  },
12977
13320
  contextWindow: 1000000,
12978
- maxTokens: 64000,
13321
+ maxTokens: 8192,
12979
13322
  },
12980
13323
  "anthropic/claude-sonnet-4.5": {
12981
13324
  id: "anthropic/claude-sonnet-4.5",
@@ -13028,23 +13371,6 @@ export const MODELS = {
13028
13371
  contextWindow: 1000000,
13029
13372
  maxTokens: 128000,
13030
13373
  },
13031
- "arcee-ai/trinity-large-preview": {
13032
- id: "arcee-ai/trinity-large-preview",
13033
- name: "Trinity Large Preview",
13034
- api: "anthropic-messages",
13035
- provider: "vercel-ai-gateway",
13036
- baseUrl: "https://ai-gateway.vercel.sh",
13037
- reasoning: false,
13038
- input: ["text"],
13039
- cost: {
13040
- input: 0.25,
13041
- output: 1,
13042
- cacheRead: 0,
13043
- cacheWrite: 0,
13044
- },
13045
- contextWindow: 131000,
13046
- maxTokens: 131000,
13047
- },
13048
13374
  "arcee-ai/trinity-large-thinking": {
13049
13375
  id: "arcee-ai/trinity-large-thinking",
13050
13376
  name: "Trinity Large Thinking",
@@ -13173,12 +13499,12 @@ export const MODELS = {
13173
13499
  reasoning: true,
13174
13500
  input: ["text"],
13175
13501
  cost: {
13176
- input: 0.6,
13177
- output: 1.7,
13178
- cacheRead: 0,
13502
+ input: 0.21,
13503
+ output: 0.7899999999999999,
13504
+ cacheRead: 0.13,
13179
13505
  cacheWrite: 0,
13180
13506
  },
13181
- contextWindow: 128000,
13507
+ contextWindow: 163840,
13182
13508
  maxTokens: 128000,
13183
13509
  },
13184
13510
  "deepseek/deepseek-v3.1-terminus": {
@@ -13243,7 +13569,7 @@ export const MODELS = {
13243
13569
  cost: {
13244
13570
  input: 0.14,
13245
13571
  output: 0.28,
13246
- cacheRead: 0.0028,
13572
+ cacheRead: 0.028,
13247
13573
  cacheWrite: 0,
13248
13574
  },
13249
13575
  contextWindow: 1000000,
@@ -13504,6 +13830,23 @@ export const MODELS = {
13504
13830
  contextWindow: 1000000,
13505
13831
  maxTokens: 32000,
13506
13832
  },
13833
+ "kwaipilot/kat-coder-air-v2.5": {
13834
+ id: "kwaipilot/kat-coder-air-v2.5",
13835
+ name: "Kat Coder Air V2.5",
13836
+ api: "anthropic-messages",
13837
+ provider: "vercel-ai-gateway",
13838
+ baseUrl: "https://ai-gateway.vercel.sh",
13839
+ reasoning: true,
13840
+ input: ["text"],
13841
+ cost: {
13842
+ input: 0.15,
13843
+ output: 0.6,
13844
+ cacheRead: 0.03,
13845
+ cacheWrite: 0,
13846
+ },
13847
+ contextWindow: 256000,
13848
+ maxTokens: 80000,
13849
+ },
13507
13850
  "kwaipilot/kat-coder-pro-v1": {
13508
13851
  id: "kwaipilot/kat-coder-pro-v1",
13509
13852
  name: "KAT-Coder-Pro V1",
@@ -13538,39 +13881,22 @@ export const MODELS = {
13538
13881
  contextWindow: 256000,
13539
13882
  maxTokens: 256000,
13540
13883
  },
13541
- "meituan/longcat-flash-chat": {
13542
- id: "meituan/longcat-flash-chat",
13543
- name: "LongCat Flash Chat",
13544
- api: "anthropic-messages",
13545
- provider: "vercel-ai-gateway",
13546
- baseUrl: "https://ai-gateway.vercel.sh",
13547
- reasoning: false,
13548
- input: ["text"],
13549
- cost: {
13550
- input: 0,
13551
- output: 0,
13552
- cacheRead: 0,
13553
- cacheWrite: 0,
13554
- },
13555
- contextWindow: 128000,
13556
- maxTokens: 100000,
13557
- },
13558
- "meituan/longcat-flash-thinking-2601": {
13559
- id: "meituan/longcat-flash-thinking-2601",
13560
- name: "LongCat Flash Thinking 2601",
13884
+ "kwaipilot/kat-coder-pro-v2.5": {
13885
+ id: "kwaipilot/kat-coder-pro-v2.5",
13886
+ name: "Kat Coder Pro V2.5",
13561
13887
  api: "anthropic-messages",
13562
13888
  provider: "vercel-ai-gateway",
13563
13889
  baseUrl: "https://ai-gateway.vercel.sh",
13564
13890
  reasoning: true,
13565
13891
  input: ["text"],
13566
13892
  cost: {
13567
- input: 0,
13568
- output: 0,
13569
- cacheRead: 0,
13893
+ input: 0.74,
13894
+ output: 2.96,
13895
+ cacheRead: 0.15,
13570
13896
  cacheWrite: 0,
13571
13897
  },
13572
- contextWindow: 32768,
13573
- maxTokens: 32768,
13898
+ contextWindow: 256000,
13899
+ maxTokens: 80000,
13574
13900
  },
13575
13901
  "meta/llama-3.1-70b": {
13576
13902
  id: "meta/llama-3.1-70b",
@@ -13691,6 +14017,23 @@ export const MODELS = {
13691
14017
  contextWindow: 128000,
13692
14018
  maxTokens: 8192,
13693
14019
  },
14020
+ "meta/muse-spark-1.1": {
14021
+ id: "meta/muse-spark-1.1",
14022
+ name: "Muse Spark 1.1",
14023
+ api: "anthropic-messages",
14024
+ provider: "vercel-ai-gateway",
14025
+ baseUrl: "https://ai-gateway.vercel.sh",
14026
+ reasoning: true,
14027
+ input: ["text", "image"],
14028
+ cost: {
14029
+ input: 1.25,
14030
+ output: 4.25,
14031
+ cacheRead: 0.15,
14032
+ cacheWrite: 0,
14033
+ },
14034
+ contextWindow: 1048576,
14035
+ maxTokens: 1048576,
14036
+ },
13694
14037
  "minimax/minimax-m2": {
13695
14038
  id: "minimax/minimax-m2",
13696
14039
  name: "MiniMax M2",
@@ -13861,23 +14204,6 @@ export const MODELS = {
13861
14204
  contextWindow: 256000,
13862
14205
  maxTokens: 256000,
13863
14206
  },
13864
- "mistral/devstral-small": {
13865
- id: "mistral/devstral-small",
13866
- name: "Devstral Small 1.1",
13867
- api: "anthropic-messages",
13868
- provider: "vercel-ai-gateway",
13869
- baseUrl: "https://ai-gateway.vercel.sh",
13870
- reasoning: false,
13871
- input: ["text"],
13872
- cost: {
13873
- input: 0.09999999999999999,
13874
- output: 0.3,
13875
- cacheRead: 0,
13876
- cacheWrite: 0,
13877
- },
13878
- contextWindow: 128000,
13879
- maxTokens: 64000,
13880
- },
13881
14207
  "mistral/devstral-small-2": {
13882
14208
  id: "mistral/devstral-small-2",
13883
14209
  name: "Devstral Small 2",
@@ -14082,23 +14408,6 @@ export const MODELS = {
14082
14408
  contextWindow: 128000,
14083
14409
  maxTokens: 4000,
14084
14410
  },
14085
- "mistral/pixtral-large": {
14086
- id: "mistral/pixtral-large",
14087
- name: "Pixtral Large",
14088
- api: "anthropic-messages",
14089
- provider: "vercel-ai-gateway",
14090
- baseUrl: "https://ai-gateway.vercel.sh",
14091
- reasoning: false,
14092
- input: ["text", "image"],
14093
- cost: {
14094
- input: 2,
14095
- output: 6,
14096
- cacheRead: 0,
14097
- cacheWrite: 0,
14098
- },
14099
- contextWindow: 128000,
14100
- maxTokens: 4000,
14101
- },
14102
14411
  "moonshotai/kimi-k2": {
14103
14412
  id: "moonshotai/kimi-k2",
14104
14413
  name: "Kimi K2 Instruct",
@@ -14796,6 +15105,57 @@ export const MODELS = {
14796
15105
  contextWindow: 1000000,
14797
15106
  maxTokens: 128000,
14798
15107
  },
15108
+ "openai/gpt-5.6-luna": {
15109
+ id: "openai/gpt-5.6-luna",
15110
+ name: "GPT 5.6 Luna",
15111
+ api: "anthropic-messages",
15112
+ provider: "vercel-ai-gateway",
15113
+ baseUrl: "https://ai-gateway.vercel.sh",
15114
+ reasoning: true,
15115
+ input: ["text", "image"],
15116
+ cost: {
15117
+ input: 1,
15118
+ output: 6,
15119
+ cacheRead: 0.09999999999999999,
15120
+ cacheWrite: 1.25,
15121
+ },
15122
+ contextWindow: 1050000,
15123
+ maxTokens: 128000,
15124
+ },
15125
+ "openai/gpt-5.6-sol": {
15126
+ id: "openai/gpt-5.6-sol",
15127
+ name: "GPT 5.6 Sol",
15128
+ api: "anthropic-messages",
15129
+ provider: "vercel-ai-gateway",
15130
+ baseUrl: "https://ai-gateway.vercel.sh",
15131
+ reasoning: true,
15132
+ input: ["text", "image"],
15133
+ cost: {
15134
+ input: 5,
15135
+ output: 30,
15136
+ cacheRead: 0.5,
15137
+ cacheWrite: 6.25,
15138
+ },
15139
+ contextWindow: 1050000,
15140
+ maxTokens: 128000,
15141
+ },
15142
+ "openai/gpt-5.6-terra": {
15143
+ id: "openai/gpt-5.6-terra",
15144
+ name: "GPT 5.6 Terra",
15145
+ api: "anthropic-messages",
15146
+ provider: "vercel-ai-gateway",
15147
+ baseUrl: "https://ai-gateway.vercel.sh",
15148
+ reasoning: true,
15149
+ input: ["text", "image"],
15150
+ cost: {
15151
+ input: 2.5,
15152
+ output: 15,
15153
+ cacheRead: 0.25,
15154
+ cacheWrite: 3.125,
15155
+ },
15156
+ contextWindow: 1050000,
15157
+ maxTokens: 128000,
15158
+ },
14799
15159
  "openai/gpt-oss-120b": {
14800
15160
  id: "openai/gpt-oss-120b",
14801
15161
  name: "GPT OSS 120B",
@@ -15187,40 +15547,6 @@ export const MODELS = {
15187
15547
  contextWindow: 256000,
15188
15548
  maxTokens: 256000,
15189
15549
  },
15190
- "xiaomi/mimo-v2-flash": {
15191
- id: "xiaomi/mimo-v2-flash",
15192
- name: "MiMo V2 Flash",
15193
- api: "anthropic-messages",
15194
- provider: "vercel-ai-gateway",
15195
- baseUrl: "https://ai-gateway.vercel.sh",
15196
- reasoning: true,
15197
- input: ["text"],
15198
- cost: {
15199
- input: 0.09999999999999999,
15200
- output: 0.3,
15201
- cacheRead: 0.01,
15202
- cacheWrite: 0,
15203
- },
15204
- contextWindow: 262144,
15205
- maxTokens: 32000,
15206
- },
15207
- "xiaomi/mimo-v2-pro": {
15208
- id: "xiaomi/mimo-v2-pro",
15209
- name: "MiMo V2 Pro",
15210
- api: "anthropic-messages",
15211
- provider: "vercel-ai-gateway",
15212
- baseUrl: "https://ai-gateway.vercel.sh",
15213
- reasoning: true,
15214
- input: ["text"],
15215
- cost: {
15216
- input: 1,
15217
- output: 3,
15218
- cacheRead: 0.19999999999999998,
15219
- cacheWrite: 0,
15220
- },
15221
- contextWindow: 1000000,
15222
- maxTokens: 128000,
15223
- },
15224
15550
  "xiaomi/mimo-v2.5": {
15225
15551
  id: "xiaomi/mimo-v2.5",
15226
15552
  name: "MiMo M2.5",
@@ -15485,9 +15811,9 @@ export const MODELS = {
15485
15811
  reasoning: true,
15486
15812
  input: ["text"],
15487
15813
  cost: {
15488
- input: 3,
15489
- output: 10.25,
15490
- cacheRead: 0.5,
15814
+ input: 2.0999999999999996,
15815
+ output: 6.6000000000000005,
15816
+ cacheRead: 0.21,
15491
15817
  cacheWrite: 0,
15492
15818
  },
15493
15819
  contextWindow: 1000000,