@kolisachint/hoocode-ai 0.5.63 → 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": {
@@ -7486,23 +7609,6 @@ export const MODELS = {
7486
7609
  },
7487
7610
  },
7488
7611
  "opencode-go": {
7489
- "deepseek-flash": {
7490
- id: "deepseek-flash",
7491
- name: "DeepSeek V4.1 Flash",
7492
- api: "openai-completions",
7493
- provider: "opencode-go",
7494
- baseUrl: "https://opencode.ai/zen/go/v1",
7495
- reasoning: true,
7496
- input: ["text", "image"],
7497
- cost: {
7498
- input: 0.15,
7499
- output: 0.6,
7500
- cacheRead: 0.003,
7501
- cacheWrite: 0,
7502
- },
7503
- contextWindow: 1000000,
7504
- maxTokens: 384000,
7505
- },
7506
7612
  "deepseek-v4-flash": {
7507
7613
  id: "deepseek-v4-flash",
7508
7614
  name: "DeepSeek V4 Flash",
@@ -7560,6 +7666,25 @@ export const MODELS = {
7560
7666
  contextWindow: 1000000,
7561
7667
  maxTokens: 384000,
7562
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
+ },
7563
7688
  "glm-5.1": {
7564
7689
  id: "glm-5.1",
7565
7690
  name: "GLM-5.1",
@@ -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",
@@ -9050,9 +9175,9 @@ export const MODELS = {
9050
9175
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
9051
9176
  input: ["text", "image"],
9052
9177
  cost: {
9053
- input: 0.3,
9054
- output: 1.2,
9055
- cacheRead: 0.006,
9178
+ input: 0.15,
9179
+ output: 0.6,
9180
+ cacheRead: 0.003,
9056
9181
  cacheWrite: 0,
9057
9182
  },
9058
9183
  contextWindow: 1048576,
@@ -9577,13 +9702,13 @@ export const MODELS = {
9577
9702
  reasoning: true,
9578
9703
  input: ["text", "image"],
9579
9704
  cost: {
9580
- input: 0.07,
9581
- output: 0.33999999999999997,
9582
- cacheRead: 0,
9705
+ input: 0.09,
9706
+ output: 0.3,
9707
+ cacheRead: 0.049999999999999996,
9583
9708
  cacheWrite: 0,
9584
9709
  },
9585
9710
  contextWindow: 262144,
9586
- maxTokens: 16384,
9711
+ maxTokens: 235929,
9587
9712
  },
9588
9713
  "google/gemma-4-26b-a4b-it:free": {
9589
9714
  id: "google/gemma-4-26b-a4b-it:free",
@@ -9772,6 +9897,40 @@ export const MODELS = {
9772
9897
  contextWindow: 262144,
9773
9898
  maxTokens: 32768,
9774
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
+ },
9775
9934
  "kwaipilot/kat-coder-pro-v2": {
9776
9935
  id: "kwaipilot/kat-coder-pro-v2",
9777
9936
  name: "Kwaipilot: KAT-Coder-Pro V2",
@@ -9934,8 +10093,8 @@ export const MODELS = {
9934
10093
  reasoning: true,
9935
10094
  input: ["text", "image"],
9936
10095
  cost: {
9937
- input: 0.3,
9938
- output: 1.1,
10096
+ input: 0.35,
10097
+ output: 1.5,
9939
10098
  cacheRead: 0.04,
9940
10099
  cacheWrite: 0,
9941
10100
  },
@@ -10104,13 +10263,13 @@ export const MODELS = {
10104
10263
  reasoning: true,
10105
10264
  input: ["text"],
10106
10265
  cost: {
10107
- input: 0.3,
10108
- output: 1.2,
10109
- cacheRead: 0.03,
10266
+ input: 0.27,
10267
+ output: 1.08,
10268
+ cacheRead: 0.027,
10110
10269
  cacheWrite: 0,
10111
10270
  },
10112
10271
  contextWindow: 204800,
10113
- maxTokens: 131072,
10272
+ maxTokens: 128000,
10114
10273
  },
10115
10274
  "minimax/minimax-m2.7": {
10116
10275
  id: "minimax/minimax-m2.7",
@@ -10517,7 +10676,7 @@ export const MODELS = {
10517
10676
  cacheRead: 0,
10518
10677
  cacheWrite: 0,
10519
10678
  },
10520
- contextWindow: 131072,
10679
+ contextWindow: 256000,
10521
10680
  maxTokens: 16384,
10522
10681
  },
10523
10682
  "mistralai/mixtral-8x22b-instruct": {
@@ -10569,7 +10728,7 @@ export const MODELS = {
10569
10728
  cacheWrite: 0,
10570
10729
  },
10571
10730
  contextWindow: 131072,
10572
- maxTokens: 100352,
10731
+ maxTokens: 98304,
10573
10732
  },
10574
10733
  "moonshotai/kimi-k2-0905": {
10575
10734
  id: "moonshotai/kimi-k2-0905",
@@ -10586,7 +10745,7 @@ export const MODELS = {
10586
10745
  cacheWrite: 0,
10587
10746
  },
10588
10747
  contextWindow: 262144,
10589
- maxTokens: 100352,
10748
+ maxTokens: 98304,
10590
10749
  },
10591
10750
  "moonshotai/kimi-k2-thinking": {
10592
10751
  id: "moonshotai/kimi-k2-thinking",
@@ -10603,7 +10762,7 @@ export const MODELS = {
10603
10762
  cacheWrite: 0,
10604
10763
  },
10605
10764
  contextWindow: 262144,
10606
- maxTokens: 100352,
10765
+ maxTokens: 98304,
10607
10766
  },
10608
10767
  "moonshotai/kimi-k2.5": {
10609
10768
  id: "moonshotai/kimi-k2.5",
@@ -10665,9 +10824,9 @@ export const MODELS = {
10665
10824
  reasoning: true,
10666
10825
  input: ["text", "image"],
10667
10826
  cost: {
10668
- input: 3,
10669
- output: 15,
10670
- cacheRead: 0.3,
10827
+ input: 2.6481380629999998,
10828
+ output: 13.282724250000001,
10829
+ cacheRead: 0.30264435,
10671
10830
  cacheWrite: 0,
10672
10831
  },
10673
10832
  contextWindow: 1048576,
@@ -12588,13 +12747,13 @@ export const MODELS = {
12588
12747
  reasoning: false,
12589
12748
  input: ["text"],
12590
12749
  cost: {
12591
- input: 0.22,
12592
- output: 0.88,
12593
- cacheRead: 0,
12750
+ input: 0.0875,
12751
+ output: 0.35,
12752
+ cacheRead: 0.0175,
12594
12753
  cacheWrite: 0,
12595
12754
  },
12596
12755
  contextWindow: 262144,
12597
- maxTokens: 16384,
12756
+ maxTokens: 235929,
12598
12757
  },
12599
12758
  "qwen/qwen3-235b-a22b-thinking-2507": {
12600
12759
  id: "qwen/qwen3-235b-a22b-thinking-2507",
@@ -12639,13 +12798,13 @@ export const MODELS = {
12639
12798
  reasoning: false,
12640
12799
  input: ["text"],
12641
12800
  cost: {
12642
- input: 0.09,
12643
- output: 0.3,
12801
+ input: 0.04815,
12802
+ output: 0.19305,
12644
12803
  cacheRead: 0,
12645
12804
  cacheWrite: 0,
12646
12805
  },
12647
12806
  contextWindow: 262144,
12648
- maxTokens: 235929,
12807
+ maxTokens: 32000,
12649
12808
  },
12650
12809
  "qwen/qwen3-30b-a3b-thinking-2507": {
12651
12810
  id: "qwen/qwen3-30b-a3b-thinking-2507",
@@ -13302,9 +13461,9 @@ export const MODELS = {
13302
13461
  reasoning: true,
13303
13462
  input: ["text", "image"],
13304
13463
  cost: {
13305
- input: 0.42,
13306
- output: 3,
13307
- cacheRead: 0.08499999999999999,
13464
+ input: 0.21400000000000002,
13465
+ output: 2.5500000000000003,
13466
+ cacheRead: 0.15,
13308
13467
  cacheWrite: 0,
13309
13468
  },
13310
13469
  contextWindow: 1000000,
@@ -13378,6 +13537,23 @@ export const MODELS = {
13378
13537
  contextWindow: 256000,
13379
13538
  maxTokens: 128000,
13380
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
+ },
13381
13557
  "sakana/fugu-ultra": {
13382
13558
  id: "sakana/fugu-ultra",
13383
13559
  name: "Sakana: Fugu Ultra",
@@ -13395,6 +13571,23 @@ export const MODELS = {
13395
13571
  contextWindow: 1000000,
13396
13572
  maxTokens: 128000,
13397
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
+ },
13398
13591
  "sakana/sakana-namazu": {
13399
13592
  id: "sakana/sakana-namazu",
13400
13593
  name: "Sakana: Sakana Namazu",
@@ -13546,7 +13739,7 @@ export const MODELS = {
13546
13739
  cacheWrite: 0,
13547
13740
  },
13548
13741
  contextWindow: 1048576,
13549
- maxTokens: 32768,
13742
+ maxTokens: 471859,
13550
13743
  },
13551
13744
  "thinkingmachines/inkling-small": {
13552
13745
  id: "thinkingmachines/inkling-small",
@@ -13659,9 +13852,9 @@ export const MODELS = {
13659
13852
  reasoning: true,
13660
13853
  input: ["text"],
13661
13854
  cost: {
13662
- input: 0.03,
13663
- output: 0.12,
13664
- cacheRead: 0.006,
13855
+ input: 0.09,
13856
+ output: 0.36,
13857
+ cacheRead: 0.018,
13665
13858
  cacheWrite: 0,
13666
13859
  },
13667
13860
  contextWindow: 524288,
@@ -13919,7 +14112,7 @@ export const MODELS = {
13919
14112
  cacheRead: 0,
13920
14113
  cacheWrite: 0,
13921
14114
  },
13922
- contextWindow: 202752,
14115
+ contextWindow: 200000,
13923
14116
  maxTokens: 117964,
13924
14117
  },
13925
14118
  "z-ai/glm-5": {
@@ -13982,13 +14175,13 @@ export const MODELS = {
13982
14175
  reasoning: true,
13983
14176
  input: ["text"],
13984
14177
  cost: {
13985
- input: 0.966,
13986
- output: 3.036,
13987
- cacheRead: 0.1932,
14178
+ input: 0.6,
14179
+ output: 2,
14180
+ cacheRead: 0.15,
13988
14181
  cacheWrite: 0,
13989
14182
  },
13990
14183
  contextWindow: 1048576,
13991
- maxTokens: 131072,
14184
+ maxTokens: 182476,
13992
14185
  },
13993
14186
  "z-ai/glm-5.2:batch": {
13994
14187
  id: "z-ai/glm-5.2:batch",
@@ -14016,13 +14209,13 @@ export const MODELS = {
14016
14209
  reasoning: true,
14017
14210
  input: ["text"],
14018
14211
  cost: {
14019
- input: 1.4,
14020
- output: 4.4,
14021
- cacheRead: 0.26,
14212
+ input: 1.092,
14213
+ output: 3.432,
14214
+ cacheRead: 0.20279999999999998,
14022
14215
  cacheWrite: 0,
14023
14216
  },
14024
14217
  contextWindow: 1310720,
14025
- maxTokens: 943718,
14218
+ maxTokens: 131072,
14026
14219
  },
14027
14220
  "z-ai/glm-5.3-flash": {
14028
14221
  id: "z-ai/glm-5.3-flash",
@@ -14033,9 +14226,9 @@ export const MODELS = {
14033
14226
  reasoning: true,
14034
14227
  input: ["text", "image"],
14035
14228
  cost: {
14036
- input: 0.075,
14037
- output: 0.25,
14038
- cacheRead: 0.015,
14229
+ input: 0.15,
14230
+ output: 0.5,
14231
+ cacheRead: 0.03,
14039
14232
  cacheWrite: 0,
14040
14233
  },
14041
14234
  contextWindow: 1310720,
@@ -14112,7 +14305,7 @@ export const MODELS = {
14112
14305
  },
14113
14306
  "~anthropic/claude-haiku-latest": {
14114
14307
  id: "~anthropic/claude-haiku-latest",
14115
- name: "Anthropic Claude Haiku Latest",
14308
+ name: "Anthropic: Claude Haiku Latest",
14116
14309
  api: "openai-completions",
14117
14310
  provider: "openrouter",
14118
14311
  baseUrl: "https://openrouter.ai/api/v1",
@@ -14147,7 +14340,7 @@ export const MODELS = {
14147
14340
  },
14148
14341
  "~anthropic/claude-sonnet-latest": {
14149
14342
  id: "~anthropic/claude-sonnet-latest",
14150
- name: "Anthropic Claude Sonnet Latest",
14343
+ name: "Anthropic: Claude Sonnet Latest",
14151
14344
  api: "openai-completions",
14152
14345
  provider: "openrouter",
14153
14346
  baseUrl: "https://openrouter.ai/api/v1",
@@ -14165,7 +14358,7 @@ export const MODELS = {
14165
14358
  },
14166
14359
  "~deepseek/deepseek-v4-flash-latest": {
14167
14360
  id: "~deepseek/deepseek-v4-flash-latest",
14168
- name: "DeepSeek V4 Flash Latest",
14361
+ name: "DeepSeek: DeepSeek V4 Flash Latest",
14169
14362
  api: "openai-completions",
14170
14363
  provider: "openrouter",
14171
14364
  baseUrl: "https://openrouter.ai/api/v1",
@@ -14174,17 +14367,17 @@ export const MODELS = {
14174
14367
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
14175
14368
  input: ["text"],
14176
14369
  cost: {
14177
- input: 0.049999999999999996,
14178
- output: 0.16,
14179
- cacheRead: 0.013000000000000001,
14370
+ input: 0.035199999999999995,
14371
+ output: 0.1056,
14372
+ cacheRead: 0.0011200000000000001,
14180
14373
  cacheWrite: 0,
14181
14374
  },
14182
14375
  contextWindow: 1310720,
14183
- maxTokens: 393216,
14376
+ maxTokens: 131072,
14184
14377
  },
14185
14378
  "~google/gemini-flash-latest": {
14186
14379
  id: "~google/gemini-flash-latest",
14187
- name: "Google Gemini Flash Latest",
14380
+ name: "Google: Gemini Flash Latest",
14188
14381
  api: "openai-completions",
14189
14382
  provider: "openrouter",
14190
14383
  baseUrl: "https://openrouter.ai/api/v1",
@@ -14201,7 +14394,7 @@ export const MODELS = {
14201
14394
  },
14202
14395
  "~google/gemini-pro-latest": {
14203
14396
  id: "~google/gemini-pro-latest",
14204
- name: "Google Gemini Pro Latest",
14397
+ name: "Google: Gemini Pro Latest",
14205
14398
  api: "openai-completions",
14206
14399
  provider: "openrouter",
14207
14400
  baseUrl: "https://openrouter.ai/api/v1",
@@ -14218,41 +14411,58 @@ export const MODELS = {
14218
14411
  },
14219
14412
  "~moonshotai/kimi-latest": {
14220
14413
  id: "~moonshotai/kimi-latest",
14221
- name: "MoonshotAI Kimi Latest",
14414
+ name: "MoonshotAI: Kimi Latest",
14222
14415
  api: "openai-completions",
14223
14416
  provider: "openrouter",
14224
14417
  baseUrl: "https://openrouter.ai/api/v1",
14225
14418
  reasoning: true,
14226
14419
  input: ["text", "image"],
14227
14420
  cost: {
14228
- input: 2.4,
14229
- output: 12,
14230
- cacheRead: 0.24,
14421
+ input: 2.0999999999999996,
14422
+ output: 10.950000000000001,
14423
+ cacheRead: 0,
14231
14424
  cacheWrite: 0,
14232
14425
  },
14233
14426
  contextWindow: 1048576,
14234
14427
  maxTokens: 943718,
14235
14428
  },
14236
- "~openai/gpt-latest": {
14237
- id: "~openai/gpt-latest",
14238
- name: "OpenAI GPT Latest",
14429
+ "~openai/gpt-astra-latest": {
14430
+ id: "~openai/gpt-astra-latest",
14431
+ name: "OpenAI: GPT Astra Latest",
14239
14432
  api: "openai-completions",
14240
14433
  provider: "openrouter",
14241
14434
  baseUrl: "https://openrouter.ai/api/v1",
14242
14435
  reasoning: true,
14243
14436
  input: ["text", "image"],
14244
14437
  cost: {
14245
- input: 2,
14246
- output: 10,
14247
- cacheRead: 0.19999999999999998,
14248
- 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,
14249
14459
  },
14250
14460
  contextWindow: 1050000,
14251
14461
  maxTokens: 128000,
14252
14462
  },
14253
14463
  "~openai/gpt-mini-latest": {
14254
14464
  id: "~openai/gpt-mini-latest",
14255
- name: "OpenAI GPT Mini Latest",
14465
+ name: "OpenAI: GPT Mini Latest",
14256
14466
  api: "openai-completions",
14257
14467
  provider: "openrouter",
14258
14468
  baseUrl: "https://openrouter.ai/api/v1",
@@ -14267,6 +14477,40 @@ export const MODELS = {
14267
14477
  contextWindow: 400000,
14268
14478
  maxTokens: 128000,
14269
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
+ },
14270
14514
  "~x-ai/grok-latest": {
14271
14515
  id: "~x-ai/grok-latest",
14272
14516
  name: "xAI: Grok Latest",
@@ -14310,13 +14554,13 @@ export const MODELS = {
14310
14554
  reasoning: true,
14311
14555
  input: ["text"],
14312
14556
  cost: {
14313
- input: 1.085,
14314
- output: 3.41,
14315
- cacheRead: 0.20149999999999998,
14557
+ input: 0.936,
14558
+ output: 3.168,
14559
+ cacheRead: 0.1872,
14316
14560
  cacheWrite: 0,
14317
14561
  },
14318
14562
  contextWindow: 1310720,
14319
- maxTokens: 128000,
14563
+ maxTokens: 235929,
14320
14564
  },
14321
14565
  },
14322
14566
  "together": {
@@ -14489,6 +14733,25 @@ export const MODELS = {
14489
14733
  contextWindow: 1048576,
14490
14734
  maxTokens: 384000,
14491
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
+ },
14492
14755
  "google/gemma-4-31B-it": {
14493
14756
  id: "google/gemma-4-31B-it",
14494
14757
  name: "Gemma 4 31B Instruct",
@@ -15194,23 +15457,6 @@ export const MODELS = {
15194
15457
  contextWindow: 991000,
15195
15458
  maxTokens: 128000,
15196
15459
  },
15197
- "alibaba/qwen3.8-flash-next": {
15198
- id: "alibaba/qwen3.8-flash-next",
15199
- name: "Qwen 3.8 Flash Next",
15200
- api: "anthropic-messages",
15201
- provider: "vercel-ai-gateway",
15202
- baseUrl: "https://ai-gateway.vercel.sh",
15203
- reasoning: true,
15204
- input: ["text", "image"],
15205
- cost: {
15206
- input: 0.12,
15207
- output: 0.39999999999999997,
15208
- cacheRead: 0.01,
15209
- cacheWrite: 0,
15210
- },
15211
- contextWindow: 1048576,
15212
- maxTokens: 1048576,
15213
- },
15214
15460
  "alibaba/qwen3.8-max": {
15215
15461
  id: "alibaba/qwen3.8-max",
15216
15462
  name: "Qwen 3.8 Max",
@@ -15645,6 +15891,23 @@ export const MODELS = {
15645
15891
  contextWindow: 256000,
15646
15892
  maxTokens: 64000,
15647
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
+ },
15648
15911
  "cohere/command-a": {
15649
15912
  id: "cohere/command-a",
15650
15913
  name: "Command A",
@@ -15841,13 +16104,13 @@ export const MODELS = {
15841
16104
  reasoning: true,
15842
16105
  input: ["text", "image"],
15843
16106
  cost: {
15844
- input: 0.15,
15845
- output: 0.6,
15846
- cacheRead: 0.003,
16107
+ input: 0.3,
16108
+ output: 1.2,
16109
+ cacheRead: 0.03,
15847
16110
  cacheWrite: 0,
15848
16111
  },
15849
- contextWindow: 1000000,
15850
- maxTokens: 384000,
16112
+ contextWindow: 1048576,
16113
+ maxTokens: 32768,
15851
16114
  },
15852
16115
  "google/gemini-2.5-flash": {
15853
16116
  id: "google/gemini-2.5-flash",
@@ -16206,6 +16469,40 @@ export const MODELS = {
16206
16469
  contextWindow: 256000,
16207
16470
  maxTokens: 32000,
16208
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
+ },
16209
16506
  "interfaze/interfaze-beta": {
16210
16507
  id: "interfaze/interfaze-beta",
16211
16508
  name: "Interfaze Beta",
@@ -18091,6 +18388,23 @@ export const MODELS = {
18091
18388
  contextWindow: 256000,
18092
18389
  maxTokens: 32768,
18093
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
+ },
18094
18408
  "sakana/fugu-ultra": {
18095
18409
  id: "sakana/fugu-ultra",
18096
18410
  name: "Fugu Ultra",
@@ -18108,6 +18422,23 @@ export const MODELS = {
18108
18422
  contextWindow: 1000000,
18109
18423
  maxTokens: 1000000,
18110
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
+ },
18111
18442
  "sakana/namazu": {
18112
18443
  id: "sakana/namazu",
18113
18444
  name: "Sakana Namazu",