@kolisachint/hoocode-ai 0.5.62 → 0.5.64

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.
@@ -1116,6 +1116,23 @@ export const MODELS = {
1116
1116
  contextWindow: 1000000,
1117
1117
  maxTokens: 384000,
1118
1118
  },
1119
+ "accounts/fireworks/models/deepseek-v4p1-flash": {
1120
+ id: "accounts/fireworks/models/deepseek-v4p1-flash",
1121
+ name: "DeepSeek V4.1 Flash",
1122
+ api: "anthropic-messages",
1123
+ provider: "fireworks",
1124
+ baseUrl: "https://api.fireworks.ai/inference",
1125
+ reasoning: true,
1126
+ input: ["text", "image"],
1127
+ cost: {
1128
+ input: 0.22,
1129
+ output: 0.66,
1130
+ cacheRead: 0.007,
1131
+ cacheWrite: 0,
1132
+ },
1133
+ contextWindow: 1000000,
1134
+ maxTokens: 384000,
1135
+ },
1119
1136
  "accounts/fireworks/models/glm-5p2": {
1120
1137
  id: "accounts/fireworks/models/glm-5p2",
1121
1138
  name: "GLM 5.2",
@@ -1269,6 +1286,23 @@ export const MODELS = {
1269
1286
  contextWindow: 512000,
1270
1287
  maxTokens: 512000,
1271
1288
  },
1289
+ "accounts/fireworks/models/mistral-large-3-fp8": {
1290
+ id: "accounts/fireworks/models/mistral-large-3-fp8",
1291
+ name: "Mistral Large 3 675B Instruct 2512",
1292
+ api: "anthropic-messages",
1293
+ provider: "fireworks",
1294
+ baseUrl: "https://api.fireworks.ai/inference",
1295
+ reasoning: false,
1296
+ input: ["text", "image"],
1297
+ cost: {
1298
+ input: 0,
1299
+ output: 0,
1300
+ cacheRead: 0,
1301
+ cacheWrite: 0,
1302
+ },
1303
+ contextWindow: 262144,
1304
+ maxTokens: 262144,
1305
+ },
1272
1306
  "accounts/fireworks/models/muse-glimmer-30b": {
1273
1307
  id: "accounts/fireworks/models/muse-glimmer-30b",
1274
1308
  name: "Muse Glimmer 30B",
@@ -3435,6 +3469,78 @@ export const MODELS = {
3435
3469
  contextWindow: 1000000,
3436
3470
  maxTokens: 384000,
3437
3471
  },
3472
+ "deepseek-ai/DeepSeek-V4.1-Flash": {
3473
+ id: "deepseek-ai/DeepSeek-V4.1-Flash",
3474
+ name: "DeepSeek V4.1 Flash",
3475
+ api: "openai-completions",
3476
+ provider: "huggingface",
3477
+ baseUrl: "https://router.huggingface.co/v1",
3478
+ compat: { "supportsDeveloperRole": false },
3479
+ reasoning: true,
3480
+ input: ["text", "image"],
3481
+ cost: {
3482
+ input: 0.3,
3483
+ output: 1.2,
3484
+ cacheRead: 0,
3485
+ cacheWrite: 0,
3486
+ },
3487
+ contextWindow: 1048576,
3488
+ maxTokens: 384000,
3489
+ },
3490
+ "google/gemma-3-12b-it": {
3491
+ id: "google/gemma-3-12b-it",
3492
+ name: "Gemma 3 12B IT",
3493
+ api: "openai-completions",
3494
+ provider: "huggingface",
3495
+ baseUrl: "https://router.huggingface.co/v1",
3496
+ compat: { "supportsDeveloperRole": false },
3497
+ reasoning: false,
3498
+ input: ["text", "image"],
3499
+ cost: {
3500
+ input: 0.05,
3501
+ output: 0.15,
3502
+ cacheRead: 0,
3503
+ cacheWrite: 0,
3504
+ },
3505
+ contextWindow: 131072,
3506
+ maxTokens: 131072,
3507
+ },
3508
+ "google/gemma-3-27b-it": {
3509
+ id: "google/gemma-3-27b-it",
3510
+ name: "Gemma 3 27B IT",
3511
+ api: "openai-completions",
3512
+ provider: "huggingface",
3513
+ baseUrl: "https://router.huggingface.co/v1",
3514
+ compat: { "supportsDeveloperRole": false },
3515
+ reasoning: false,
3516
+ input: ["text", "image"],
3517
+ cost: {
3518
+ input: 0.08,
3519
+ output: 0.16,
3520
+ cacheRead: 0,
3521
+ cacheWrite: 0,
3522
+ },
3523
+ contextWindow: 131072,
3524
+ maxTokens: 131072,
3525
+ },
3526
+ "google/gemma-3-4b-it": {
3527
+ id: "google/gemma-3-4b-it",
3528
+ name: "Gemma 3 4B IT",
3529
+ api: "openai-completions",
3530
+ provider: "huggingface",
3531
+ baseUrl: "https://router.huggingface.co/v1",
3532
+ compat: { "supportsDeveloperRole": false },
3533
+ reasoning: false,
3534
+ input: ["text", "image"],
3535
+ cost: {
3536
+ input: 0.05,
3537
+ output: 0.1,
3538
+ cacheRead: 0,
3539
+ cacheWrite: 0,
3540
+ },
3541
+ contextWindow: 131072,
3542
+ maxTokens: 131072,
3543
+ },
3438
3544
  "google/gemma-4-26B-A4B-it": {
3439
3545
  id: "google/gemma-4-26B-A4B-it",
3440
3546
  name: "Gemma 4 26B A4B IT",
@@ -5367,6 +5473,23 @@ export const MODELS = {
5367
5473
  contextWindow: 1000000,
5368
5474
  maxTokens: 131072,
5369
5475
  },
5476
+ "z-ai/glm-5.3-flash": {
5477
+ id: "z-ai/glm-5.3-flash",
5478
+ name: "GLM-5.3-Flash",
5479
+ api: "openai-completions",
5480
+ provider: "nvidia",
5481
+ baseUrl: "https://integrate.api.nvidia.com/v1",
5482
+ reasoning: true,
5483
+ input: ["text", "image"],
5484
+ cost: {
5485
+ input: 0,
5486
+ output: 0,
5487
+ cacheRead: 0,
5488
+ cacheWrite: 0,
5489
+ },
5490
+ contextWindow: 1000000,
5491
+ maxTokens: 131072,
5492
+ },
5370
5493
  },
5371
5494
  "openai": {
5372
5495
  "gpt-4": {
@@ -7497,9 +7620,9 @@ export const MODELS = {
7497
7620
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
7498
7621
  input: ["text"],
7499
7622
  cost: {
7500
- input: 0.22,
7501
- output: 0.66,
7502
- cacheRead: 0.007,
7623
+ input: 0.15,
7624
+ output: 0.6,
7625
+ cacheRead: 0.003,
7503
7626
  cacheWrite: 0,
7504
7627
  },
7505
7628
  contextWindow: 1000000,
@@ -7516,9 +7639,9 @@ export const MODELS = {
7516
7639
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
7517
7640
  input: ["text", "image"],
7518
7641
  cost: {
7519
- input: 0.22,
7520
- output: 0.66,
7521
- cacheRead: 0.007,
7642
+ input: 0.15,
7643
+ output: 0.6,
7644
+ cacheRead: 0.003,
7522
7645
  cacheWrite: 0,
7523
7646
  },
7524
7647
  contextWindow: 1000000,
@@ -7543,6 +7666,25 @@ export const MODELS = {
7543
7666
  contextWindow: 1000000,
7544
7667
  maxTokens: 384000,
7545
7668
  },
7669
+ "deepseek-v4.1-flash": {
7670
+ id: "deepseek-v4.1-flash",
7671
+ name: "DeepSeek V4.1 Flash",
7672
+ api: "openai-completions",
7673
+ provider: "opencode-go",
7674
+ baseUrl: "https://opencode.ai/zen/go/v1",
7675
+ compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
7676
+ reasoning: true,
7677
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
7678
+ input: ["text", "image"],
7679
+ cost: {
7680
+ input: 0.15,
7681
+ output: 0.6,
7682
+ cacheRead: 0.003,
7683
+ cacheWrite: 0,
7684
+ },
7685
+ contextWindow: 1000000,
7686
+ maxTokens: 384000,
7687
+ },
7546
7688
  "glm-5.1": {
7547
7689
  id: "glm-5.1",
7548
7690
  name: "GLM-5.1",
@@ -7596,16 +7738,16 @@ export const MODELS = {
7596
7738
  },
7597
7739
  "glm-5.3-flash": {
7598
7740
  id: "glm-5.3-flash",
7599
- name: "GLM-5.3-Flash (2x usage)",
7741
+ name: "GLM-5.3-Flash",
7600
7742
  api: "openai-completions",
7601
7743
  provider: "opencode-go",
7602
7744
  baseUrl: "https://opencode.ai/zen/go/v1",
7603
7745
  reasoning: true,
7604
7746
  input: ["text", "image"],
7605
7747
  cost: {
7606
- input: 0.075,
7607
- output: 0.25,
7608
- cacheRead: 0.015,
7748
+ input: 0.15,
7749
+ output: 0.5,
7750
+ cacheRead: 0.03,
7609
7751
  cacheWrite: 0,
7610
7752
  },
7611
7753
  contextWindow: 1000000,
@@ -7851,23 +7993,6 @@ export const MODELS = {
7851
7993
  contextWindow: 1048576,
7852
7994
  maxTokens: 131072,
7853
7995
  },
7854
- "omen-alpha": {
7855
- id: "omen-alpha",
7856
- name: "Omen Alpha",
7857
- api: "openai-completions",
7858
- provider: "opencode-go",
7859
- baseUrl: "https://opencode.ai/zen/go/v1",
7860
- reasoning: true,
7861
- input: ["text", "image"],
7862
- cost: {
7863
- input: 0.2,
7864
- output: 0.66,
7865
- cacheRead: 0.04,
7866
- cacheWrite: 0,
7867
- },
7868
- contextWindow: 500000,
7869
- maxTokens: 128000,
7870
- },
7871
7996
  "qwen3.6-plus": {
7872
7997
  id: "qwen3.6-plus",
7873
7998
  name: "Qwen3.6 Plus",
@@ -8760,13 +8885,13 @@ export const MODELS = {
8760
8885
  reasoning: false,
8761
8886
  input: ["text"],
8762
8887
  cost: {
8763
- input: 0.32,
8764
- output: 0.8899999999999999,
8888
+ input: 0.2574,
8889
+ output: 1.0287,
8765
8890
  cacheRead: 0,
8766
8891
  cacheWrite: 0,
8767
8892
  },
8768
8893
  contextWindow: 163840,
8769
- maxTokens: 16384,
8894
+ maxTokens: 16000,
8770
8895
  },
8771
8896
  "deepseek/deepseek-chat-v3-0324": {
8772
8897
  id: "deepseek/deepseek-chat-v3-0324",
@@ -8777,9 +8902,9 @@ export const MODELS = {
8777
8902
  reasoning: false,
8778
8903
  input: ["text"],
8779
8904
  cost: {
8780
- input: 0.29,
8781
- output: 1.1400000000000001,
8782
- cacheRead: 0.11,
8905
+ input: 0.25,
8906
+ output: 1,
8907
+ cacheRead: 0,
8783
8908
  cacheWrite: 0,
8784
8909
  },
8785
8910
  contextWindow: 163840,
@@ -8898,9 +9023,9 @@ export const MODELS = {
8898
9023
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
8899
9024
  input: ["text"],
8900
9025
  cost: {
8901
- input: 0.088606,
8902
- output: 0.177212,
8903
- cacheRead: 0.017721200000000003,
9026
+ input: 0.049,
9027
+ output: 0.098,
9028
+ cacheRead: 0.0098,
8904
9029
  cacheWrite: 0,
8905
9030
  },
8906
9031
  contextWindow: 1048576,
@@ -8917,9 +9042,9 @@ export const MODELS = {
8917
9042
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
8918
9043
  input: ["text"],
8919
9044
  cost: {
8920
- input: 0.065,
8921
- output: 0.18,
8922
- cacheRead: 0.016,
9045
+ input: 0.04,
9046
+ output: 0.08,
9047
+ cacheRead: 0.008,
8923
9048
  cacheWrite: 0,
8924
9049
  },
8925
9050
  contextWindow: 1310720,
@@ -8993,13 +9118,13 @@ export const MODELS = {
8993
9118
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
8994
9119
  input: ["text"],
8995
9120
  cost: {
8996
- input: 0.9552599999999999,
8997
- output: 1.9105199999999998,
8998
- cacheRead: 0.07960500000000001,
9121
+ input: 1.5999999999999999,
9122
+ output: 3.1999999999999997,
9123
+ cacheRead: 0.135,
8999
9124
  cacheWrite: 0,
9000
9125
  },
9001
9126
  contextWindow: 1048576,
9002
- maxTokens: 384000,
9127
+ maxTokens: 393216,
9003
9128
  },
9004
9129
  "deepseek/deepseek-v4-pro-0813": {
9005
9130
  id: "deepseek/deepseek-v4-pro-0813",
@@ -9012,13 +9137,13 @@ export const MODELS = {
9012
9137
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
9013
9138
  input: ["text"],
9014
9139
  cost: {
9015
- input: 1.0494,
9016
- output: 3.1482,
9017
- cacheRead: 0.03498,
9140
+ input: 0.57816,
9141
+ output: 1.73448,
9142
+ cacheRead: 0.018396000000000003,
9018
9143
  cacheWrite: 0,
9019
9144
  },
9020
9145
  contextWindow: 1048576,
9021
- maxTokens: 384000,
9146
+ maxTokens: 393216,
9022
9147
  },
9023
9148
  "deepseek/deepseek-v4-pro-0813:batch": {
9024
9149
  id: "deepseek/deepseek-v4-pro-0813:batch",
@@ -9039,6 +9164,25 @@ export const MODELS = {
9039
9164
  contextWindow: 1048576,
9040
9165
  maxTokens: 943718,
9041
9166
  },
9167
+ "deepseek/deepseek-v4.1-flash": {
9168
+ id: "deepseek/deepseek-v4.1-flash",
9169
+ name: "DeepSeek: DeepSeek V4.1 Flash",
9170
+ api: "openai-completions",
9171
+ provider: "openrouter",
9172
+ baseUrl: "https://openrouter.ai/api/v1",
9173
+ compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
9174
+ reasoning: true,
9175
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
9176
+ input: ["text", "image"],
9177
+ cost: {
9178
+ input: 0.15,
9179
+ output: 0.6,
9180
+ cacheRead: 0.003,
9181
+ cacheWrite: 0,
9182
+ },
9183
+ contextWindow: 1048576,
9184
+ maxTokens: 384000,
9185
+ },
9042
9186
  "dots-studio/dots-3-note-preview:free": {
9043
9187
  id: "dots-studio/dots-3-note-preview:free",
9044
9188
  name: "Dots Studio: Dots3-Note Preview (free)",
@@ -9558,13 +9702,13 @@ export const MODELS = {
9558
9702
  reasoning: true,
9559
9703
  input: ["text", "image"],
9560
9704
  cost: {
9561
- input: 0.07,
9562
- output: 0.33999999999999997,
9563
- cacheRead: 0,
9705
+ input: 0.09,
9706
+ output: 0.3,
9707
+ cacheRead: 0.049999999999999996,
9564
9708
  cacheWrite: 0,
9565
9709
  },
9566
9710
  contextWindow: 262144,
9567
- maxTokens: 16384,
9711
+ maxTokens: 235929,
9568
9712
  },
9569
9713
  "google/gemma-4-26b-a4b-it:free": {
9570
9714
  id: "google/gemma-4-26b-a4b-it:free",
@@ -9753,6 +9897,40 @@ export const MODELS = {
9753
9897
  contextWindow: 262144,
9754
9898
  maxTokens: 32768,
9755
9899
  },
9900
+ "inclusionai/ling-3.0-flash-vl": {
9901
+ id: "inclusionai/ling-3.0-flash-vl",
9902
+ name: "inclusionAI: Ling 3.0 Flash VL",
9903
+ api: "openai-completions",
9904
+ provider: "openrouter",
9905
+ baseUrl: "https://openrouter.ai/api/v1",
9906
+ reasoning: true,
9907
+ input: ["text", "image"],
9908
+ cost: {
9909
+ input: 0.06,
9910
+ output: 0.18,
9911
+ cacheRead: 0.012,
9912
+ cacheWrite: 0,
9913
+ },
9914
+ contextWindow: 131072,
9915
+ maxTokens: 32768,
9916
+ },
9917
+ "inclusionai/ling-3.0-flash-vl:free": {
9918
+ id: "inclusionai/ling-3.0-flash-vl:free",
9919
+ name: "inclusionAI: Ling 3.0 Flash VL (free)",
9920
+ api: "openai-completions",
9921
+ provider: "openrouter",
9922
+ baseUrl: "https://openrouter.ai/api/v1",
9923
+ reasoning: true,
9924
+ input: ["text", "image"],
9925
+ cost: {
9926
+ input: 0,
9927
+ output: 0,
9928
+ cacheRead: 0,
9929
+ cacheWrite: 0,
9930
+ },
9931
+ contextWindow: 262144,
9932
+ maxTokens: 32768,
9933
+ },
9756
9934
  "kwaipilot/kat-coder-pro-v2": {
9757
9935
  id: "kwaipilot/kat-coder-pro-v2",
9758
9936
  name: "Kwaipilot: KAT-Coder-Pro V2",
@@ -9915,8 +10093,8 @@ export const MODELS = {
9915
10093
  reasoning: true,
9916
10094
  input: ["text", "image"],
9917
10095
  cost: {
9918
- input: 0.3,
9919
- output: 1.1,
10096
+ input: 0.35,
10097
+ output: 1.5,
9920
10098
  cacheRead: 0.04,
9921
10099
  cacheWrite: 0,
9922
10100
  },
@@ -10161,6 +10339,23 @@ export const MODELS = {
10161
10339
  contextWindow: 256000,
10162
10340
  maxTokens: 204800,
10163
10341
  },
10342
+ "mistralai/codestral-2508:batch": {
10343
+ id: "mistralai/codestral-2508:batch",
10344
+ name: "Mistral: Codestral 2508 (batch)",
10345
+ api: "openai-completions",
10346
+ provider: "openrouter",
10347
+ baseUrl: "https://openrouter.ai/api/v1",
10348
+ reasoning: false,
10349
+ input: ["text"],
10350
+ cost: {
10351
+ input: 0.15,
10352
+ output: 0.44999999999999996,
10353
+ cacheRead: 0.015,
10354
+ cacheWrite: 0,
10355
+ },
10356
+ contextWindow: 256000,
10357
+ maxTokens: 204800,
10358
+ },
10164
10359
  "mistralai/devstral-2512": {
10165
10360
  id: "mistralai/devstral-2512",
10166
10361
  name: "Mistral: Devstral 2 2512",
@@ -10229,18 +10424,35 @@ export const MODELS = {
10229
10424
  contextWindow: 262144,
10230
10425
  maxTokens: 209715,
10231
10426
  },
10232
- "mistralai/mistral-large": {
10233
- id: "mistralai/mistral-large",
10234
- name: "Mistral Large",
10427
+ "mistralai/ministral-8b-2512:batch": {
10428
+ id: "mistralai/ministral-8b-2512:batch",
10429
+ name: "Mistral: Ministral 3 8B 2512 (batch)",
10235
10430
  api: "openai-completions",
10236
10431
  provider: "openrouter",
10237
10432
  baseUrl: "https://openrouter.ai/api/v1",
10238
10433
  reasoning: false,
10239
- input: ["text"],
10434
+ input: ["text", "image"],
10240
10435
  cost: {
10241
- input: 2,
10242
- output: 6,
10243
- cacheRead: 0.19999999999999998,
10436
+ input: 0.075,
10437
+ output: 0.075,
10438
+ cacheRead: 0.0075,
10439
+ cacheWrite: 0,
10440
+ },
10441
+ contextWindow: 262144,
10442
+ maxTokens: 209715,
10443
+ },
10444
+ "mistralai/mistral-large": {
10445
+ id: "mistralai/mistral-large",
10446
+ name: "Mistral Large",
10447
+ api: "openai-completions",
10448
+ provider: "openrouter",
10449
+ baseUrl: "https://openrouter.ai/api/v1",
10450
+ reasoning: false,
10451
+ input: ["text"],
10452
+ cost: {
10453
+ input: 2,
10454
+ output: 6,
10455
+ cacheRead: 0.19999999999999998,
10244
10456
  cacheWrite: 0,
10245
10457
  },
10246
10458
  contextWindow: 128000,
@@ -10280,6 +10492,23 @@ export const MODELS = {
10280
10492
  contextWindow: 262144,
10281
10493
  maxTokens: 209715,
10282
10494
  },
10495
+ "mistralai/mistral-large-2512:batch": {
10496
+ id: "mistralai/mistral-large-2512:batch",
10497
+ name: "Mistral: Mistral Large 3 2512 (batch)",
10498
+ api: "openai-completions",
10499
+ provider: "openrouter",
10500
+ baseUrl: "https://openrouter.ai/api/v1",
10501
+ reasoning: false,
10502
+ input: ["text", "image"],
10503
+ cost: {
10504
+ input: 0.25,
10505
+ output: 0.75,
10506
+ cacheRead: 0.024999999999999998,
10507
+ cacheWrite: 0,
10508
+ },
10509
+ contextWindow: 262144,
10510
+ maxTokens: 209715,
10511
+ },
10283
10512
  "mistralai/mistral-medium-3": {
10284
10513
  id: "mistralai/mistral-medium-3",
10285
10514
  name: "Mistral: Mistral Medium 3",
@@ -10348,6 +10577,23 @@ export const MODELS = {
10348
10577
  contextWindow: 131072,
10349
10578
  maxTokens: 104857,
10350
10579
  },
10580
+ "mistralai/mistral-medium-3.1:batch": {
10581
+ id: "mistralai/mistral-medium-3.1:batch",
10582
+ name: "Mistral: Mistral Medium 3.1 (batch)",
10583
+ api: "openai-completions",
10584
+ provider: "openrouter",
10585
+ baseUrl: "https://openrouter.ai/api/v1",
10586
+ reasoning: false,
10587
+ input: ["text", "image"],
10588
+ cost: {
10589
+ input: 0.19999999999999998,
10590
+ output: 1,
10591
+ cacheRead: 0.02,
10592
+ cacheWrite: 0,
10593
+ },
10594
+ contextWindow: 131072,
10595
+ maxTokens: 104857,
10596
+ },
10351
10597
  "mistralai/mistral-nemo": {
10352
10598
  id: "mistralai/mistral-nemo",
10353
10599
  name: "Mistral: Mistral Nemo",
@@ -10399,6 +10645,23 @@ export const MODELS = {
10399
10645
  contextWindow: 262144,
10400
10646
  maxTokens: 209715,
10401
10647
  },
10648
+ "mistralai/mistral-small-2603:batch": {
10649
+ id: "mistralai/mistral-small-2603:batch",
10650
+ name: "Mistral: Mistral Small 4 (batch)",
10651
+ api: "openai-completions",
10652
+ provider: "openrouter",
10653
+ baseUrl: "https://openrouter.ai/api/v1",
10654
+ reasoning: true,
10655
+ input: ["text", "image"],
10656
+ cost: {
10657
+ input: 0.075,
10658
+ output: 0.3,
10659
+ cacheRead: 0.0075,
10660
+ cacheWrite: 0,
10661
+ },
10662
+ contextWindow: 262144,
10663
+ maxTokens: 209715,
10664
+ },
10402
10665
  "mistralai/mistral-small-3.2-24b-instruct": {
10403
10666
  id: "mistralai/mistral-small-3.2-24b-instruct",
10404
10667
  name: "Mistral: Mistral Small 3.2 24B",
@@ -10413,7 +10676,7 @@ export const MODELS = {
10413
10676
  cacheRead: 0,
10414
10677
  cacheWrite: 0,
10415
10678
  },
10416
- contextWindow: 131072,
10679
+ contextWindow: 256000,
10417
10680
  maxTokens: 16384,
10418
10681
  },
10419
10682
  "mistralai/mixtral-8x22b-instruct": {
@@ -10465,7 +10728,7 @@ export const MODELS = {
10465
10728
  cacheWrite: 0,
10466
10729
  },
10467
10730
  contextWindow: 131072,
10468
- maxTokens: 100352,
10731
+ maxTokens: 98304,
10469
10732
  },
10470
10733
  "moonshotai/kimi-k2-0905": {
10471
10734
  id: "moonshotai/kimi-k2-0905",
@@ -10482,7 +10745,7 @@ export const MODELS = {
10482
10745
  cacheWrite: 0,
10483
10746
  },
10484
10747
  contextWindow: 262144,
10485
- maxTokens: 100352,
10748
+ maxTokens: 98304,
10486
10749
  },
10487
10750
  "moonshotai/kimi-k2-thinking": {
10488
10751
  id: "moonshotai/kimi-k2-thinking",
@@ -10495,11 +10758,11 @@ export const MODELS = {
10495
10758
  cost: {
10496
10759
  input: 0.6,
10497
10760
  output: 2.5,
10498
- cacheRead: 0,
10761
+ cacheRead: 0.15,
10499
10762
  cacheWrite: 0,
10500
10763
  },
10501
10764
  contextWindow: 262144,
10502
- maxTokens: 235929,
10765
+ maxTokens: 98304,
10503
10766
  },
10504
10767
  "moonshotai/kimi-k2.5": {
10505
10768
  id: "moonshotai/kimi-k2.5",
@@ -10561,9 +10824,9 @@ export const MODELS = {
10561
10824
  reasoning: true,
10562
10825
  input: ["text", "image"],
10563
10826
  cost: {
10564
- input: 3,
10565
- output: 15,
10566
- cacheRead: 0.3,
10827
+ input: 2.6481380629999998,
10828
+ output: 13.282724250000001,
10829
+ cacheRead: 0.30264435,
10567
10830
  cacheWrite: 0,
10568
10831
  },
10569
10832
  contextWindow: 1048576,
@@ -10593,7 +10856,7 @@ export const MODELS = {
10593
10856
  provider: "openrouter",
10594
10857
  baseUrl: "https://openrouter.ai/api/v1",
10595
10858
  reasoning: true,
10596
- input: ["text"],
10859
+ input: ["text", "image"],
10597
10860
  cost: {
10598
10861
  input: 0,
10599
10862
  output: 0,
@@ -12484,13 +12747,13 @@ export const MODELS = {
12484
12747
  reasoning: false,
12485
12748
  input: ["text"],
12486
12749
  cost: {
12487
- input: 0.22,
12488
- output: 0.88,
12489
- cacheRead: 0,
12750
+ input: 0.0875,
12751
+ output: 0.35,
12752
+ cacheRead: 0.0175,
12490
12753
  cacheWrite: 0,
12491
12754
  },
12492
12755
  contextWindow: 262144,
12493
- maxTokens: 16384,
12756
+ maxTokens: 235929,
12494
12757
  },
12495
12758
  "qwen/qwen3-235b-a22b-thinking-2507": {
12496
12759
  id: "qwen/qwen3-235b-a22b-thinking-2507",
@@ -12875,13 +13138,13 @@ export const MODELS = {
12875
13138
  reasoning: true,
12876
13139
  input: ["text", "image"],
12877
13140
  cost: {
12878
- input: 0.29,
12879
- output: 2.4,
13141
+ input: 0.26,
13142
+ output: 2.08,
12880
13143
  cacheRead: 0,
12881
13144
  cacheWrite: 0,
12882
13145
  },
12883
13146
  contextWindow: 262144,
12884
- maxTokens: 81920,
13147
+ maxTokens: 65536,
12885
13148
  },
12886
13149
  "qwen/qwen3.5-27b": {
12887
13150
  id: "qwen/qwen3.5-27b",
@@ -13198,9 +13461,9 @@ export const MODELS = {
13198
13461
  reasoning: true,
13199
13462
  input: ["text", "image"],
13200
13463
  cost: {
13201
- input: 0.42,
13202
- output: 3,
13203
- cacheRead: 0.08499999999999999,
13464
+ input: 0.21400000000000002,
13465
+ output: 2.5500000000000003,
13466
+ cacheRead: 0.15,
13204
13467
  cacheWrite: 0,
13205
13468
  },
13206
13469
  contextWindow: 1000000,
@@ -13274,6 +13537,23 @@ export const MODELS = {
13274
13537
  contextWindow: 256000,
13275
13538
  maxTokens: 128000,
13276
13539
  },
13540
+ "sakana/fugu-max": {
13541
+ id: "sakana/fugu-max",
13542
+ name: "Sakana: Fugu Max",
13543
+ api: "openai-completions",
13544
+ provider: "openrouter",
13545
+ baseUrl: "https://openrouter.ai/api/v1",
13546
+ reasoning: true,
13547
+ input: ["text", "image"],
13548
+ cost: {
13549
+ input: 2,
13550
+ output: 6,
13551
+ cacheRead: 0.25,
13552
+ cacheWrite: 0,
13553
+ },
13554
+ contextWindow: 1000000,
13555
+ maxTokens: 128000,
13556
+ },
13277
13557
  "sakana/fugu-ultra": {
13278
13558
  id: "sakana/fugu-ultra",
13279
13559
  name: "Sakana: Fugu Ultra",
@@ -13291,6 +13571,23 @@ export const MODELS = {
13291
13571
  contextWindow: 1000000,
13292
13572
  maxTokens: 128000,
13293
13573
  },
13574
+ "sakana/fugu-ultra-v2": {
13575
+ id: "sakana/fugu-ultra-v2",
13576
+ name: "Sakana: Fugu Ultra v2",
13577
+ api: "openai-completions",
13578
+ provider: "openrouter",
13579
+ baseUrl: "https://openrouter.ai/api/v1",
13580
+ reasoning: true,
13581
+ input: ["text", "image"],
13582
+ cost: {
13583
+ input: 5,
13584
+ output: 30,
13585
+ cacheRead: 0.5,
13586
+ cacheWrite: 0,
13587
+ },
13588
+ contextWindow: 1000000,
13589
+ maxTokens: 128000,
13590
+ },
13294
13591
  "sakana/sakana-namazu": {
13295
13592
  id: "sakana/sakana-namazu",
13296
13593
  name: "Sakana: Sakana Namazu",
@@ -13555,9 +13852,9 @@ export const MODELS = {
13555
13852
  reasoning: true,
13556
13853
  input: ["text"],
13557
13854
  cost: {
13558
- input: 0.03,
13559
- output: 0.12,
13560
- cacheRead: 0.006,
13855
+ input: 0.09,
13856
+ output: 0.36,
13857
+ cacheRead: 0.018,
13561
13858
  cacheWrite: 0,
13562
13859
  },
13563
13860
  contextWindow: 524288,
@@ -13815,7 +14112,7 @@ export const MODELS = {
13815
14112
  cacheRead: 0,
13816
14113
  cacheWrite: 0,
13817
14114
  },
13818
- contextWindow: 202752,
14115
+ contextWindow: 200000,
13819
14116
  maxTokens: 117964,
13820
14117
  },
13821
14118
  "z-ai/glm-5": {
@@ -13878,13 +14175,13 @@ export const MODELS = {
13878
14175
  reasoning: true,
13879
14176
  input: ["text"],
13880
14177
  cost: {
13881
- input: 0.966,
13882
- output: 3.036,
13883
- cacheRead: 0.1932,
14178
+ input: 0.6,
14179
+ output: 2,
14180
+ cacheRead: 0.15,
13884
14181
  cacheWrite: 0,
13885
14182
  },
13886
14183
  contextWindow: 1048576,
13887
- maxTokens: 131072,
14184
+ maxTokens: 182476,
13888
14185
  },
13889
14186
  "z-ai/glm-5.2:batch": {
13890
14187
  id: "z-ai/glm-5.2:batch",
@@ -13912,13 +14209,13 @@ export const MODELS = {
13912
14209
  reasoning: true,
13913
14210
  input: ["text"],
13914
14211
  cost: {
13915
- input: 1.4,
13916
- output: 4.4,
13917
- cacheRead: 0.26,
14212
+ input: 1.092,
14213
+ output: 3.432,
14214
+ cacheRead: 0.20279999999999998,
13918
14215
  cacheWrite: 0,
13919
14216
  },
13920
14217
  contextWindow: 1310720,
13921
- maxTokens: 943718,
14218
+ maxTokens: 131072,
13922
14219
  },
13923
14220
  "z-ai/glm-5.3-flash": {
13924
14221
  id: "z-ai/glm-5.3-flash",
@@ -13929,9 +14226,9 @@ export const MODELS = {
13929
14226
  reasoning: true,
13930
14227
  input: ["text", "image"],
13931
14228
  cost: {
13932
- input: 0.075,
13933
- output: 0.25,
13934
- cacheRead: 0.015,
14229
+ input: 0.15,
14230
+ output: 0.5,
14231
+ cacheRead: 0.03,
13935
14232
  cacheWrite: 0,
13936
14233
  },
13937
14234
  contextWindow: 1310720,
@@ -14008,7 +14305,7 @@ export const MODELS = {
14008
14305
  },
14009
14306
  "~anthropic/claude-haiku-latest": {
14010
14307
  id: "~anthropic/claude-haiku-latest",
14011
- name: "Anthropic Claude Haiku Latest",
14308
+ name: "Anthropic: Claude Haiku Latest",
14012
14309
  api: "openai-completions",
14013
14310
  provider: "openrouter",
14014
14311
  baseUrl: "https://openrouter.ai/api/v1",
@@ -14043,7 +14340,7 @@ export const MODELS = {
14043
14340
  },
14044
14341
  "~anthropic/claude-sonnet-latest": {
14045
14342
  id: "~anthropic/claude-sonnet-latest",
14046
- name: "Anthropic Claude Sonnet Latest",
14343
+ name: "Anthropic: Claude Sonnet Latest",
14047
14344
  api: "openai-completions",
14048
14345
  provider: "openrouter",
14049
14346
  baseUrl: "https://openrouter.ai/api/v1",
@@ -14061,7 +14358,7 @@ export const MODELS = {
14061
14358
  },
14062
14359
  "~deepseek/deepseek-v4-flash-latest": {
14063
14360
  id: "~deepseek/deepseek-v4-flash-latest",
14064
- name: "DeepSeek V4 Flash Latest",
14361
+ name: "DeepSeek: DeepSeek V4 Flash Latest",
14065
14362
  api: "openai-completions",
14066
14363
  provider: "openrouter",
14067
14364
  baseUrl: "https://openrouter.ai/api/v1",
@@ -14070,17 +14367,17 @@ export const MODELS = {
14070
14367
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
14071
14368
  input: ["text"],
14072
14369
  cost: {
14073
- input: 0.049999999999999996,
14074
- output: 0.16,
14075
- cacheRead: 0.013000000000000001,
14370
+ input: 0.035199999999999995,
14371
+ output: 0.1056,
14372
+ cacheRead: 0.0011200000000000001,
14076
14373
  cacheWrite: 0,
14077
14374
  },
14078
14375
  contextWindow: 1310720,
14079
- maxTokens: 393216,
14376
+ maxTokens: 131072,
14080
14377
  },
14081
14378
  "~google/gemini-flash-latest": {
14082
14379
  id: "~google/gemini-flash-latest",
14083
- name: "Google Gemini Flash Latest",
14380
+ name: "Google: Gemini Flash Latest",
14084
14381
  api: "openai-completions",
14085
14382
  provider: "openrouter",
14086
14383
  baseUrl: "https://openrouter.ai/api/v1",
@@ -14097,7 +14394,7 @@ export const MODELS = {
14097
14394
  },
14098
14395
  "~google/gemini-pro-latest": {
14099
14396
  id: "~google/gemini-pro-latest",
14100
- name: "Google Gemini Pro Latest",
14397
+ name: "Google: Gemini Pro Latest",
14101
14398
  api: "openai-completions",
14102
14399
  provider: "openrouter",
14103
14400
  baseUrl: "https://openrouter.ai/api/v1",
@@ -14114,41 +14411,58 @@ export const MODELS = {
14114
14411
  },
14115
14412
  "~moonshotai/kimi-latest": {
14116
14413
  id: "~moonshotai/kimi-latest",
14117
- name: "MoonshotAI Kimi Latest",
14414
+ name: "MoonshotAI: Kimi Latest",
14118
14415
  api: "openai-completions",
14119
14416
  provider: "openrouter",
14120
14417
  baseUrl: "https://openrouter.ai/api/v1",
14121
14418
  reasoning: true,
14122
14419
  input: ["text", "image"],
14123
14420
  cost: {
14124
- input: 2.4,
14125
- output: 12,
14126
- cacheRead: 0.24,
14421
+ input: 2.0999999999999996,
14422
+ output: 10.950000000000001,
14423
+ cacheRead: 0,
14127
14424
  cacheWrite: 0,
14128
14425
  },
14129
14426
  contextWindow: 1048576,
14130
14427
  maxTokens: 943718,
14131
14428
  },
14132
- "~openai/gpt-latest": {
14133
- id: "~openai/gpt-latest",
14134
- name: "OpenAI GPT Latest",
14429
+ "~openai/gpt-astra-latest": {
14430
+ id: "~openai/gpt-astra-latest",
14431
+ name: "OpenAI: GPT Astra Latest",
14135
14432
  api: "openai-completions",
14136
14433
  provider: "openrouter",
14137
14434
  baseUrl: "https://openrouter.ai/api/v1",
14138
14435
  reasoning: true,
14139
14436
  input: ["text", "image"],
14140
14437
  cost: {
14141
- input: 2,
14142
- output: 10,
14143
- cacheRead: 0.19999999999999998,
14144
- cacheWrite: 2.5,
14438
+ input: 10,
14439
+ output: 50,
14440
+ cacheRead: 1,
14441
+ cacheWrite: 12.5,
14442
+ },
14443
+ contextWindow: 1050000,
14444
+ maxTokens: 128000,
14445
+ },
14446
+ "~openai/gpt-luna-latest": {
14447
+ id: "~openai/gpt-luna-latest",
14448
+ name: "OpenAI: GPT Luna Latest",
14449
+ api: "openai-completions",
14450
+ provider: "openrouter",
14451
+ baseUrl: "https://openrouter.ai/api/v1",
14452
+ reasoning: true,
14453
+ input: ["text", "image"],
14454
+ cost: {
14455
+ input: 0.19999999999999998,
14456
+ output: 1.2,
14457
+ cacheRead: 0.02,
14458
+ cacheWrite: 0.25,
14145
14459
  },
14146
14460
  contextWindow: 1050000,
14147
14461
  maxTokens: 128000,
14148
14462
  },
14149
14463
  "~openai/gpt-mini-latest": {
14150
14464
  id: "~openai/gpt-mini-latest",
14151
- name: "OpenAI GPT Mini Latest",
14465
+ name: "OpenAI: GPT Mini Latest",
14152
14466
  api: "openai-completions",
14153
14467
  provider: "openrouter",
14154
14468
  baseUrl: "https://openrouter.ai/api/v1",
@@ -14163,6 +14477,40 @@ export const MODELS = {
14163
14477
  contextWindow: 400000,
14164
14478
  maxTokens: 128000,
14165
14479
  },
14480
+ "~openai/gpt-sol-latest": {
14481
+ id: "~openai/gpt-sol-latest",
14482
+ name: "OpenAI: GPT Sol Latest",
14483
+ api: "openai-completions",
14484
+ provider: "openrouter",
14485
+ baseUrl: "https://openrouter.ai/api/v1",
14486
+ reasoning: true,
14487
+ input: ["text", "image"],
14488
+ cost: {
14489
+ input: 2,
14490
+ output: 10,
14491
+ cacheRead: 0.19999999999999998,
14492
+ cacheWrite: 2.5,
14493
+ },
14494
+ contextWindow: 1050000,
14495
+ maxTokens: 128000,
14496
+ },
14497
+ "~openai/gpt-terra-latest": {
14498
+ id: "~openai/gpt-terra-latest",
14499
+ name: "OpenAI: GPT Terra Latest",
14500
+ api: "openai-completions",
14501
+ provider: "openrouter",
14502
+ baseUrl: "https://openrouter.ai/api/v1",
14503
+ reasoning: true,
14504
+ input: ["text", "image"],
14505
+ cost: {
14506
+ input: 2,
14507
+ output: 12,
14508
+ cacheRead: 0.19999999999999998,
14509
+ cacheWrite: 2.5,
14510
+ },
14511
+ contextWindow: 1050000,
14512
+ maxTokens: 128000,
14513
+ },
14166
14514
  "~x-ai/grok-latest": {
14167
14515
  id: "~x-ai/grok-latest",
14168
14516
  name: "xAI: Grok Latest",
@@ -14195,7 +14543,7 @@ export const MODELS = {
14195
14543
  cacheWrite: 0,
14196
14544
  },
14197
14545
  contextWindow: 1310720,
14198
- maxTokens: 943718,
14546
+ maxTokens: 131072,
14199
14547
  },
14200
14548
  "~z-ai/glm-latest": {
14201
14549
  id: "~z-ai/glm-latest",
@@ -14206,13 +14554,13 @@ export const MODELS = {
14206
14554
  reasoning: true,
14207
14555
  input: ["text"],
14208
14556
  cost: {
14209
- input: 1.113,
14210
- output: 3.4979999999999998,
14211
- cacheRead: 0.2067,
14557
+ input: 0.936,
14558
+ output: 3.168,
14559
+ cacheRead: 0.1872,
14212
14560
  cacheWrite: 0,
14213
14561
  },
14214
14562
  contextWindow: 1310720,
14215
- maxTokens: 128000,
14563
+ maxTokens: 235929,
14216
14564
  },
14217
14565
  },
14218
14566
  "together": {
@@ -14385,6 +14733,25 @@ export const MODELS = {
14385
14733
  contextWindow: 1048576,
14386
14734
  maxTokens: 384000,
14387
14735
  },
14736
+ "deepseek-ai/DeepSeek-V4.1-Flash": {
14737
+ id: "deepseek-ai/DeepSeek-V4.1-Flash",
14738
+ name: "DeepSeek V4.1 Flash",
14739
+ api: "openai-completions",
14740
+ provider: "together",
14741
+ baseUrl: "https://api.together.ai/v1",
14742
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
14743
+ reasoning: true,
14744
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
14745
+ input: ["text", "image"],
14746
+ cost: {
14747
+ input: 0.3,
14748
+ output: 1.2,
14749
+ cacheRead: 0.006,
14750
+ cacheWrite: 0,
14751
+ },
14752
+ contextWindow: 1048576,
14753
+ maxTokens: 384000,
14754
+ },
14388
14755
  "google/gemma-4-31B-it": {
14389
14756
  id: "google/gemma-4-31B-it",
14390
14757
  name: "Gemma 4 31B Instruct",
@@ -15090,23 +15457,6 @@ export const MODELS = {
15090
15457
  contextWindow: 991000,
15091
15458
  maxTokens: 128000,
15092
15459
  },
15093
- "alibaba/qwen3.8-flash-next": {
15094
- id: "alibaba/qwen3.8-flash-next",
15095
- name: "Qwen 3.8 Flash Next",
15096
- api: "anthropic-messages",
15097
- provider: "vercel-ai-gateway",
15098
- baseUrl: "https://ai-gateway.vercel.sh",
15099
- reasoning: true,
15100
- input: ["text", "image"],
15101
- cost: {
15102
- input: 0.12,
15103
- output: 0.39999999999999997,
15104
- cacheRead: 0.01,
15105
- cacheWrite: 0,
15106
- },
15107
- contextWindow: 1048576,
15108
- maxTokens: 1048576,
15109
- },
15110
15460
  "alibaba/qwen3.8-max": {
15111
15461
  id: "alibaba/qwen3.8-max",
15112
15462
  name: "Qwen 3.8 Max",
@@ -15541,6 +15891,23 @@ export const MODELS = {
15541
15891
  contextWindow: 256000,
15542
15892
  maxTokens: 64000,
15543
15893
  },
15894
+ "bytedance/seed-2.1-turbo": {
15895
+ id: "bytedance/seed-2.1-turbo",
15896
+ name: "Seed 2.1 Turbo",
15897
+ api: "anthropic-messages",
15898
+ provider: "vercel-ai-gateway",
15899
+ baseUrl: "https://ai-gateway.vercel.sh",
15900
+ reasoning: true,
15901
+ input: ["text", "image"],
15902
+ cost: {
15903
+ input: 0.5,
15904
+ output: 2.5,
15905
+ cacheRead: 0.09999999999999999,
15906
+ cacheWrite: 0,
15907
+ },
15908
+ contextWindow: 262144,
15909
+ maxTokens: 262144,
15910
+ },
15544
15911
  "cohere/command-a": {
15545
15912
  id: "cohere/command-a",
15546
15913
  name: "Command A",
@@ -15618,9 +15985,9 @@ export const MODELS = {
15618
15985
  reasoning: false,
15619
15986
  input: ["text"],
15620
15987
  cost: {
15621
- input: 0.28,
15622
- output: 0.42,
15623
- cacheRead: 0.028,
15988
+ input: 0.62,
15989
+ output: 1.85,
15990
+ cacheRead: 0,
15624
15991
  cacheWrite: 0,
15625
15992
  },
15626
15993
  contextWindow: 128000,
@@ -15728,22 +16095,22 @@ export const MODELS = {
15728
16095
  contextWindow: 1000000,
15729
16096
  maxTokens: 384000,
15730
16097
  },
15731
- "deepseek/deepseek-v4.1-flash-beta": {
15732
- id: "deepseek/deepseek-v4.1-flash-beta",
15733
- name: "DeepSeek V4.1 Flash Beta",
16098
+ "deepseek/deepseek-v4.1-flash": {
16099
+ id: "deepseek/deepseek-v4.1-flash",
16100
+ name: "DeepSeek V4.1 Flash",
15734
16101
  api: "anthropic-messages",
15735
16102
  provider: "vercel-ai-gateway",
15736
16103
  baseUrl: "https://ai-gateway.vercel.sh",
15737
16104
  reasoning: true,
15738
16105
  input: ["text", "image"],
15739
16106
  cost: {
15740
- input: 0.22,
15741
- output: 0.66,
15742
- cacheRead: 0.007,
16107
+ input: 0.3,
16108
+ output: 1.2,
16109
+ cacheRead: 0.03,
15743
16110
  cacheWrite: 0,
15744
16111
  },
15745
- contextWindow: 1000000,
15746
- maxTokens: 384000,
16112
+ contextWindow: 1048576,
16113
+ maxTokens: 32768,
15747
16114
  },
15748
16115
  "google/gemini-2.5-flash": {
15749
16116
  id: "google/gemini-2.5-flash",
@@ -16102,6 +16469,40 @@ export const MODELS = {
16102
16469
  contextWindow: 256000,
16103
16470
  maxTokens: 32000,
16104
16471
  },
16472
+ "inclusionai/ling-3.0-flash-vl": {
16473
+ id: "inclusionai/ling-3.0-flash-vl",
16474
+ name: "Ling 3.0 Flash VL",
16475
+ api: "anthropic-messages",
16476
+ provider: "vercel-ai-gateway",
16477
+ baseUrl: "https://ai-gateway.vercel.sh",
16478
+ reasoning: true,
16479
+ input: ["text", "image"],
16480
+ cost: {
16481
+ input: 0,
16482
+ output: 0,
16483
+ cacheRead: 0,
16484
+ cacheWrite: 0,
16485
+ },
16486
+ contextWindow: 256000,
16487
+ maxTokens: 32000,
16488
+ },
16489
+ "inclusionai/ling-3.0-flash-vl-free": {
16490
+ id: "inclusionai/ling-3.0-flash-vl-free",
16491
+ name: "Ling 3.0 Flash VL (Free)",
16492
+ api: "anthropic-messages",
16493
+ provider: "vercel-ai-gateway",
16494
+ baseUrl: "https://ai-gateway.vercel.sh",
16495
+ reasoning: true,
16496
+ input: ["text", "image"],
16497
+ cost: {
16498
+ input: 0,
16499
+ output: 0,
16500
+ cacheRead: 0,
16501
+ cacheWrite: 0,
16502
+ },
16503
+ contextWindow: 256000,
16504
+ maxTokens: 32000,
16505
+ },
16105
16506
  "interfaze/interfaze-beta": {
16106
16507
  id: "interfaze/interfaze-beta",
16107
16508
  name: "Interfaze Beta",
@@ -17987,6 +18388,23 @@ export const MODELS = {
17987
18388
  contextWindow: 256000,
17988
18389
  maxTokens: 32768,
17989
18390
  },
18391
+ "sakana/fugu-max": {
18392
+ id: "sakana/fugu-max",
18393
+ name: "Fugu Max",
18394
+ api: "anthropic-messages",
18395
+ provider: "vercel-ai-gateway",
18396
+ baseUrl: "https://ai-gateway.vercel.sh",
18397
+ reasoning: true,
18398
+ input: ["text", "image"],
18399
+ cost: {
18400
+ input: 2,
18401
+ output: 6,
18402
+ cacheRead: 0.25,
18403
+ cacheWrite: 0,
18404
+ },
18405
+ contextWindow: 1000000,
18406
+ maxTokens: 1000000,
18407
+ },
17990
18408
  "sakana/fugu-ultra": {
17991
18409
  id: "sakana/fugu-ultra",
17992
18410
  name: "Fugu Ultra",
@@ -18004,6 +18422,23 @@ export const MODELS = {
18004
18422
  contextWindow: 1000000,
18005
18423
  maxTokens: 1000000,
18006
18424
  },
18425
+ "sakana/fugu-ultra-v2": {
18426
+ id: "sakana/fugu-ultra-v2",
18427
+ name: "Fugu Ultra v2",
18428
+ api: "anthropic-messages",
18429
+ provider: "vercel-ai-gateway",
18430
+ baseUrl: "https://ai-gateway.vercel.sh",
18431
+ reasoning: true,
18432
+ input: ["text", "image"],
18433
+ cost: {
18434
+ input: 5,
18435
+ output: 30,
18436
+ cacheRead: 0.5,
18437
+ cacheWrite: 0,
18438
+ },
18439
+ contextWindow: 1000000,
18440
+ maxTokens: 1000000,
18441
+ },
18007
18442
  "sakana/namazu": {
18008
18443
  id: "sakana/namazu",
18009
18444
  name: "Sakana Namazu",