@kolisachint/hoocode-ai 0.5.63 → 0.5.65

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",
@@ -1259,7 +1276,7 @@ export const MODELS = {
1259
1276
  provider: "fireworks",
1260
1277
  baseUrl: "https://api.fireworks.ai/inference",
1261
1278
  reasoning: true,
1262
- input: ["text", "image"],
1279
+ input: ["text"],
1263
1280
  cost: {
1264
1281
  input: 0.3,
1265
1282
  output: 1.2,
@@ -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",
@@ -1297,7 +1331,7 @@ export const MODELS = {
1297
1331
  cost: {
1298
1332
  input: 0.6,
1299
1333
  output: 2.4,
1300
- cacheRead: 0.119,
1334
+ cacheRead: 0.12,
1301
1335
  cacheWrite: 0,
1302
1336
  },
1303
1337
  contextWindow: 262144,
@@ -1361,7 +1395,7 @@ export const MODELS = {
1361
1395
  provider: "fireworks",
1362
1396
  baseUrl: "https://api.fireworks.ai/inference",
1363
1397
  reasoning: true,
1364
- input: ["text"],
1398
+ input: ["text", "image"],
1365
1399
  cost: {
1366
1400
  input: 2,
1367
1401
  output: 6,
@@ -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",
@@ -4015,7 +4121,7 @@ export const MODELS = {
4015
4121
  },
4016
4122
  "kimi-for-coding": {
4017
4123
  id: "kimi-for-coding",
4018
- name: "Kimi K2.7 Code",
4124
+ name: "kimi-for-coding",
4019
4125
  api: "anthropic-messages",
4020
4126
  provider: "kimi-coding",
4021
4127
  baseUrl: "https://api.kimi.com/coding",
@@ -4028,7 +4134,7 @@ export const MODELS = {
4028
4134
  cacheRead: 0,
4029
4135
  cacheWrite: 0,
4030
4136
  },
4031
- contextWindow: 262144,
4137
+ contextWindow: 1048576,
4032
4138
  maxTokens: 32768,
4033
4139
  },
4034
4140
  "kimi-for-coding-highspeed": {
@@ -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: 0.08707999999999999,
9027
+ output: 0.17415999999999998,
9028
+ cacheRead: 0.017415999999999997,
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: 0.06,
9046
+ output: 0.12,
9047
+ cacheRead: 0.012,
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: 0.57948,
9141
+ output: 1.73844,
9142
+ cacheRead: 0.018438,
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,
@@ -9177,23 +9302,6 @@ export const MODELS = {
9177
9302
  contextWindow: 1048576,
9178
9303
  maxTokens: 65536,
9179
9304
  },
9180
- "google/gemini-2.5-pro-preview-05-06": {
9181
- id: "google/gemini-2.5-pro-preview-05-06",
9182
- name: "Google: Gemini 2.5 Pro Preview 05-06",
9183
- api: "openai-completions",
9184
- provider: "openrouter",
9185
- baseUrl: "https://openrouter.ai/api/v1",
9186
- reasoning: true,
9187
- input: ["text", "image"],
9188
- cost: {
9189
- input: 1.25,
9190
- output: 10,
9191
- cacheRead: 0.125,
9192
- cacheWrite: 0.375,
9193
- },
9194
- contextWindow: 1048576,
9195
- maxTokens: 65535,
9196
- },
9197
9305
  "google/gemini-2.5-pro:batch": {
9198
9306
  id: "google/gemini-2.5-pro:batch",
9199
9307
  name: "Google: Gemini 2.5 Pro (batch)",
@@ -9577,13 +9685,13 @@ export const MODELS = {
9577
9685
  reasoning: true,
9578
9686
  input: ["text", "image"],
9579
9687
  cost: {
9580
- input: 0.07,
9581
- output: 0.33999999999999997,
9582
- cacheRead: 0,
9688
+ input: 0.09,
9689
+ output: 0.3,
9690
+ cacheRead: 0.049999999999999996,
9583
9691
  cacheWrite: 0,
9584
9692
  },
9585
9693
  contextWindow: 262144,
9586
- maxTokens: 16384,
9694
+ maxTokens: 235929,
9587
9695
  },
9588
9696
  "google/gemma-4-26b-a4b-it:free": {
9589
9697
  id: "google/gemma-4-26b-a4b-it:free",
@@ -9772,6 +9880,40 @@ export const MODELS = {
9772
9880
  contextWindow: 262144,
9773
9881
  maxTokens: 32768,
9774
9882
  },
9883
+ "inclusionai/ling-3.0-flash-vl": {
9884
+ id: "inclusionai/ling-3.0-flash-vl",
9885
+ name: "inclusionAI: Ling 3.0 Flash VL",
9886
+ api: "openai-completions",
9887
+ provider: "openrouter",
9888
+ baseUrl: "https://openrouter.ai/api/v1",
9889
+ reasoning: true,
9890
+ input: ["text", "image"],
9891
+ cost: {
9892
+ input: 0.06,
9893
+ output: 0.18,
9894
+ cacheRead: 0.012,
9895
+ cacheWrite: 0,
9896
+ },
9897
+ contextWindow: 131072,
9898
+ maxTokens: 32768,
9899
+ },
9900
+ "inclusionai/ling-3.0-flash-vl:free": {
9901
+ id: "inclusionai/ling-3.0-flash-vl:free",
9902
+ name: "inclusionAI: Ling 3.0 Flash VL (free)",
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,
9910
+ output: 0,
9911
+ cacheRead: 0,
9912
+ cacheWrite: 0,
9913
+ },
9914
+ contextWindow: 262144,
9915
+ maxTokens: 32768,
9916
+ },
9775
9917
  "kwaipilot/kat-coder-pro-v2": {
9776
9918
  id: "kwaipilot/kat-coder-pro-v2",
9777
9919
  name: "Kwaipilot: KAT-Coder-Pro V2",
@@ -9900,13 +10042,13 @@ export const MODELS = {
9900
10042
  reasoning: false,
9901
10043
  input: ["text", "image"],
9902
10044
  cost: {
9903
- input: 0.19999999999999998,
9904
- output: 0.696,
10045
+ input: 0.1875,
10046
+ output: 0.6525,
9905
10047
  cacheRead: 0,
9906
10048
  cacheWrite: 0,
9907
10049
  },
9908
10050
  contextWindow: 1048576,
9909
- maxTokens: 115200,
10051
+ maxTokens: 16384,
9910
10052
  },
9911
10053
  "meta-llama/llama-4-scout": {
9912
10054
  id: "meta-llama/llama-4-scout",
@@ -9934,8 +10076,8 @@ export const MODELS = {
9934
10076
  reasoning: true,
9935
10077
  input: ["text", "image"],
9936
10078
  cost: {
9937
- input: 0.3,
9938
- output: 1.1,
10079
+ input: 0.35,
10080
+ output: 1.5,
9939
10081
  cacheRead: 0.04,
9940
10082
  cacheWrite: 0,
9941
10083
  },
@@ -10104,13 +10246,13 @@ export const MODELS = {
10104
10246
  reasoning: true,
10105
10247
  input: ["text"],
10106
10248
  cost: {
10107
- input: 0.3,
10108
- output: 1.2,
10109
- cacheRead: 0.03,
10249
+ input: 0.27,
10250
+ output: 1.08,
10251
+ cacheRead: 0.027,
10110
10252
  cacheWrite: 0,
10111
10253
  },
10112
10254
  contextWindow: 204800,
10113
- maxTokens: 131072,
10255
+ maxTokens: 128000,
10114
10256
  },
10115
10257
  "minimax/minimax-m2.7": {
10116
10258
  id: "minimax/minimax-m2.7",
@@ -10517,7 +10659,7 @@ export const MODELS = {
10517
10659
  cacheRead: 0,
10518
10660
  cacheWrite: 0,
10519
10661
  },
10520
- contextWindow: 131072,
10662
+ contextWindow: 256000,
10521
10663
  maxTokens: 16384,
10522
10664
  },
10523
10665
  "mistralai/mixtral-8x22b-instruct": {
@@ -10569,7 +10711,7 @@ export const MODELS = {
10569
10711
  cacheWrite: 0,
10570
10712
  },
10571
10713
  contextWindow: 131072,
10572
- maxTokens: 100352,
10714
+ maxTokens: 98304,
10573
10715
  },
10574
10716
  "moonshotai/kimi-k2-0905": {
10575
10717
  id: "moonshotai/kimi-k2-0905",
@@ -10586,7 +10728,7 @@ export const MODELS = {
10586
10728
  cacheWrite: 0,
10587
10729
  },
10588
10730
  contextWindow: 262144,
10589
- maxTokens: 100352,
10731
+ maxTokens: 98304,
10590
10732
  },
10591
10733
  "moonshotai/kimi-k2-thinking": {
10592
10734
  id: "moonshotai/kimi-k2-thinking",
@@ -10603,7 +10745,7 @@ export const MODELS = {
10603
10745
  cacheWrite: 0,
10604
10746
  },
10605
10747
  contextWindow: 262144,
10606
- maxTokens: 100352,
10748
+ maxTokens: 98304,
10607
10749
  },
10608
10750
  "moonshotai/kimi-k2.5": {
10609
10751
  id: "moonshotai/kimi-k2.5",
@@ -10665,9 +10807,9 @@ export const MODELS = {
10665
10807
  reasoning: true,
10666
10808
  input: ["text", "image"],
10667
10809
  cost: {
10668
- input: 3,
10669
- output: 15,
10670
- cacheRead: 0.3,
10810
+ input: 2.6481380629999998,
10811
+ output: 13.282724250000001,
10812
+ cacheRead: 0.30264435,
10671
10813
  cacheWrite: 0,
10672
10814
  },
10673
10815
  contextWindow: 1048576,
@@ -10767,13 +10909,13 @@ export const MODELS = {
10767
10909
  reasoning: true,
10768
10910
  input: ["text"],
10769
10911
  cost: {
10770
- input: 0.08499999999999999,
10771
- output: 0.39999999999999997,
10912
+ input: 0.08,
10913
+ output: 0.44999999999999996,
10772
10914
  cacheRead: 0,
10773
10915
  cacheWrite: 0,
10774
10916
  },
10775
10917
  contextWindow: 262144,
10776
- maxTokens: 16384,
10918
+ maxTokens: 235929,
10777
10919
  },
10778
10920
  "nvidia/nemotron-3-super-120b-a12b:free": {
10779
10921
  id: "nvidia/nemotron-3-super-120b-a12b:free",
@@ -10801,13 +10943,13 @@ export const MODELS = {
10801
10943
  reasoning: true,
10802
10944
  input: ["text"],
10803
10945
  cost: {
10804
- input: 0.625,
10805
- output: 3.125,
10806
- cacheRead: 0.1875,
10946
+ input: 0.6,
10947
+ output: 2.4,
10948
+ cacheRead: 0.12,
10807
10949
  cacheWrite: 0,
10808
10950
  },
10809
10951
  contextWindow: 262144,
10810
- maxTokens: 32768,
10952
+ maxTokens: 182520,
10811
10953
  },
10812
10954
  "nvidia/nemotron-3-ultra-550b-a55b:free": {
10813
10955
  id: "nvidia/nemotron-3-ultra-550b-a55b:free",
@@ -10962,23 +11104,6 @@ export const MODELS = {
10962
11104
  contextWindow: 128000,
10963
11105
  maxTokens: 4096,
10964
11106
  },
10965
- "openai/gpt-4-turbo-preview": {
10966
- id: "openai/gpt-4-turbo-preview",
10967
- name: "OpenAI: GPT-4 Turbo Preview",
10968
- api: "openai-completions",
10969
- provider: "openrouter",
10970
- baseUrl: "https://openrouter.ai/api/v1",
10971
- reasoning: false,
10972
- input: ["text"],
10973
- cost: {
10974
- input: 10,
10975
- output: 30,
10976
- cacheRead: 0,
10977
- cacheWrite: 0,
10978
- },
10979
- contextWindow: 128000,
10980
- maxTokens: 4096,
10981
- },
10982
11107
  "openai/gpt-4-turbo:batch": {
10983
11108
  id: "openai/gpt-4-turbo:batch",
10984
11109
  name: "OpenAI: GPT-4 Turbo (batch)",
@@ -12554,13 +12679,13 @@ export const MODELS = {
12554
12679
  reasoning: true,
12555
12680
  input: ["text"],
12556
12681
  cost: {
12557
- input: 0.22749999999999998,
12558
- output: 0.9099999999999999,
12682
+ input: 0.12,
12683
+ output: 0.24,
12559
12684
  cacheRead: 0,
12560
12685
  cacheWrite: 0,
12561
12686
  },
12562
12687
  contextWindow: 131072,
12563
- maxTokens: 8192,
12688
+ maxTokens: 16384,
12564
12689
  },
12565
12690
  "qwen/qwen3-235b-a22b": {
12566
12691
  id: "qwen/qwen3-235b-a22b",
@@ -12588,13 +12713,13 @@ export const MODELS = {
12588
12713
  reasoning: false,
12589
12714
  input: ["text"],
12590
12715
  cost: {
12591
- input: 0.22,
12592
- output: 0.88,
12593
- cacheRead: 0,
12716
+ input: 0.0875,
12717
+ output: 0.35,
12718
+ cacheRead: 0.0175,
12594
12719
  cacheWrite: 0,
12595
12720
  },
12596
12721
  contextWindow: 262144,
12597
- maxTokens: 16384,
12722
+ maxTokens: 235929,
12598
12723
  },
12599
12724
  "qwen/qwen3-235b-a22b-thinking-2507": {
12600
12725
  id: "qwen/qwen3-235b-a22b-thinking-2507",
@@ -12639,13 +12764,13 @@ export const MODELS = {
12639
12764
  reasoning: false,
12640
12765
  input: ["text"],
12641
12766
  cost: {
12642
- input: 0.09,
12643
- output: 0.3,
12767
+ input: 0.04815,
12768
+ output: 0.19305,
12644
12769
  cacheRead: 0,
12645
12770
  cacheWrite: 0,
12646
12771
  },
12647
12772
  contextWindow: 262144,
12648
- maxTokens: 235929,
12773
+ maxTokens: 32000,
12649
12774
  },
12650
12775
  "qwen/qwen3-30b-a3b-thinking-2507": {
12651
12776
  id: "qwen/qwen3-30b-a3b-thinking-2507",
@@ -12849,7 +12974,7 @@ export const MODELS = {
12849
12974
  cacheWrite: 0,
12850
12975
  },
12851
12976
  contextWindow: 262144,
12852
- maxTokens: 235929,
12977
+ maxTokens: 32768,
12853
12978
  },
12854
12979
  "qwen/qwen3-vl-235b-a22b-instruct": {
12855
12980
  id: "qwen/qwen3-vl-235b-a22b-instruct",
@@ -13013,13 +13138,13 @@ export const MODELS = {
13013
13138
  reasoning: true,
13014
13139
  input: ["text", "image"],
13015
13140
  cost: {
13016
- input: 0.3125,
13017
- output: 1.25,
13018
- cacheRead: 0.15625,
13141
+ input: 0.1625,
13142
+ output: 1.3,
13143
+ cacheRead: 0,
13019
13144
  cacheWrite: 0,
13020
13145
  },
13021
13146
  contextWindow: 262144,
13022
- maxTokens: 16384,
13147
+ maxTokens: 65536,
13023
13148
  },
13024
13149
  "qwen/qwen3.5-397b-a17b": {
13025
13150
  id: "qwen/qwen3.5-397b-a17b",
@@ -13302,9 +13427,9 @@ export const MODELS = {
13302
13427
  reasoning: true,
13303
13428
  input: ["text", "image"],
13304
13429
  cost: {
13305
- input: 0.42,
13306
- output: 3,
13307
- cacheRead: 0.08499999999999999,
13430
+ input: 0.21400000000000002,
13431
+ output: 2.5500000000000003,
13432
+ cacheRead: 0.15,
13308
13433
  cacheWrite: 0,
13309
13434
  },
13310
13435
  contextWindow: 1000000,
@@ -13378,6 +13503,23 @@ export const MODELS = {
13378
13503
  contextWindow: 256000,
13379
13504
  maxTokens: 128000,
13380
13505
  },
13506
+ "sakana/fugu-max": {
13507
+ id: "sakana/fugu-max",
13508
+ name: "Sakana: Fugu Max",
13509
+ api: "openai-completions",
13510
+ provider: "openrouter",
13511
+ baseUrl: "https://openrouter.ai/api/v1",
13512
+ reasoning: true,
13513
+ input: ["text", "image"],
13514
+ cost: {
13515
+ input: 2,
13516
+ output: 6,
13517
+ cacheRead: 0.25,
13518
+ cacheWrite: 0,
13519
+ },
13520
+ contextWindow: 1000000,
13521
+ maxTokens: 128000,
13522
+ },
13381
13523
  "sakana/fugu-ultra": {
13382
13524
  id: "sakana/fugu-ultra",
13383
13525
  name: "Sakana: Fugu Ultra",
@@ -13395,6 +13537,23 @@ export const MODELS = {
13395
13537
  contextWindow: 1000000,
13396
13538
  maxTokens: 128000,
13397
13539
  },
13540
+ "sakana/fugu-ultra-v2": {
13541
+ id: "sakana/fugu-ultra-v2",
13542
+ name: "Sakana: Fugu Ultra v2",
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: 5,
13550
+ output: 30,
13551
+ cacheRead: 0.5,
13552
+ cacheWrite: 0,
13553
+ },
13554
+ contextWindow: 1000000,
13555
+ maxTokens: 128000,
13556
+ },
13398
13557
  "sakana/sakana-namazu": {
13399
13558
  id: "sakana/sakana-namazu",
13400
13559
  name: "Sakana: Sakana Namazu",
@@ -13546,7 +13705,7 @@ export const MODELS = {
13546
13705
  cacheWrite: 0,
13547
13706
  },
13548
13707
  contextWindow: 1048576,
13549
- maxTokens: 32768,
13708
+ maxTokens: 471859,
13550
13709
  },
13551
13710
  "thinkingmachines/inkling-small": {
13552
13711
  id: "thinkingmachines/inkling-small",
@@ -13659,9 +13818,9 @@ export const MODELS = {
13659
13818
  reasoning: true,
13660
13819
  input: ["text"],
13661
13820
  cost: {
13662
- input: 0.03,
13663
- output: 0.12,
13664
- cacheRead: 0.006,
13821
+ input: 0.09,
13822
+ output: 0.36,
13823
+ cacheRead: 0.018,
13665
13824
  cacheWrite: 0,
13666
13825
  },
13667
13826
  contextWindow: 524288,
@@ -13919,7 +14078,7 @@ export const MODELS = {
13919
14078
  cacheRead: 0,
13920
14079
  cacheWrite: 0,
13921
14080
  },
13922
- contextWindow: 202752,
14081
+ contextWindow: 200000,
13923
14082
  maxTokens: 117964,
13924
14083
  },
13925
14084
  "z-ai/glm-5": {
@@ -13982,13 +14141,13 @@ export const MODELS = {
13982
14141
  reasoning: true,
13983
14142
  input: ["text"],
13984
14143
  cost: {
13985
- input: 0.966,
13986
- output: 3.036,
13987
- cacheRead: 0.1932,
14144
+ input: 1.4,
14145
+ output: 4.4,
14146
+ cacheRead: 0.14,
13988
14147
  cacheWrite: 0,
13989
14148
  },
13990
14149
  contextWindow: 1048576,
13991
- maxTokens: 131072,
14150
+ maxTokens: 128000,
13992
14151
  },
13993
14152
  "z-ai/glm-5.2:batch": {
13994
14153
  id: "z-ai/glm-5.2:batch",
@@ -14022,7 +14181,7 @@ export const MODELS = {
14022
14181
  cacheWrite: 0,
14023
14182
  },
14024
14183
  contextWindow: 1310720,
14025
- maxTokens: 943718,
14184
+ maxTokens: 943717,
14026
14185
  },
14027
14186
  "z-ai/glm-5.3-flash": {
14028
14187
  id: "z-ai/glm-5.3-flash",
@@ -14112,7 +14271,7 @@ export const MODELS = {
14112
14271
  },
14113
14272
  "~anthropic/claude-haiku-latest": {
14114
14273
  id: "~anthropic/claude-haiku-latest",
14115
- name: "Anthropic Claude Haiku Latest",
14274
+ name: "Anthropic: Claude Haiku Latest",
14116
14275
  api: "openai-completions",
14117
14276
  provider: "openrouter",
14118
14277
  baseUrl: "https://openrouter.ai/api/v1",
@@ -14147,7 +14306,7 @@ export const MODELS = {
14147
14306
  },
14148
14307
  "~anthropic/claude-sonnet-latest": {
14149
14308
  id: "~anthropic/claude-sonnet-latest",
14150
- name: "Anthropic Claude Sonnet Latest",
14309
+ name: "Anthropic: Claude Sonnet Latest",
14151
14310
  api: "openai-completions",
14152
14311
  provider: "openrouter",
14153
14312
  baseUrl: "https://openrouter.ai/api/v1",
@@ -14163,9 +14322,43 @@ export const MODELS = {
14163
14322
  contextWindow: 1000000,
14164
14323
  maxTokens: 128000,
14165
14324
  },
14325
+ "~deepseek/deepseek-flash-latest": {
14326
+ id: "~deepseek/deepseek-flash-latest",
14327
+ name: "DeepSeek: DeepSeek Flash Latest",
14328
+ api: "openai-completions",
14329
+ provider: "openrouter",
14330
+ baseUrl: "https://openrouter.ai/api/v1",
14331
+ reasoning: true,
14332
+ input: ["text", "image"],
14333
+ cost: {
14334
+ input: 0.15,
14335
+ output: 0.6,
14336
+ cacheRead: 0.015,
14337
+ cacheWrite: 0,
14338
+ },
14339
+ contextWindow: 1048576,
14340
+ maxTokens: 393216,
14341
+ },
14342
+ "~deepseek/deepseek-pro-latest": {
14343
+ id: "~deepseek/deepseek-pro-latest",
14344
+ name: "DeepSeek: DeepSeek Pro Latest",
14345
+ api: "openai-completions",
14346
+ provider: "openrouter",
14347
+ baseUrl: "https://openrouter.ai/api/v1",
14348
+ reasoning: true,
14349
+ input: ["text"],
14350
+ cost: {
14351
+ input: 0.57948,
14352
+ output: 1.73844,
14353
+ cacheRead: 0.018438,
14354
+ cacheWrite: 0,
14355
+ },
14356
+ contextWindow: 1048576,
14357
+ maxTokens: 393216,
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",
@@ -14174,9 +14367,9 @@ 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: 0.04,
14371
+ output: 0.09999999999999999,
14372
+ cacheRead: 0.01,
14180
14373
  cacheWrite: 0,
14181
14374
  },
14182
14375
  contextWindow: 1310720,
@@ -14184,7 +14377,7 @@ export const MODELS = {
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: 0.22999999999999998,
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: 0.8775,
14558
+ output: 2.9699999999999998,
14559
+ cacheRead: 0.1755,
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",
@@ -14797,7 +15060,7 @@ export const MODELS = {
14797
15060
  cost: {
14798
15061
  input: 1.3,
14799
15062
  output: 7.8,
14800
- cacheRead: 0.26,
15063
+ cacheRead: 0.13,
14801
15064
  cacheWrite: 1.625,
14802
15065
  },
14803
15066
  contextWindow: 240000,
@@ -15035,7 +15298,7 @@ export const MODELS = {
15035
15298
  cost: {
15036
15299
  input: 0.09999999999999999,
15037
15300
  output: 0.39999999999999997,
15038
- cacheRead: 0.001,
15301
+ cacheRead: 0.01,
15039
15302
  cacheWrite: 0.125,
15040
15303
  },
15041
15304
  contextWindow: 1000000,
@@ -15051,7 +15314,7 @@ export const MODELS = {
15051
15314
  input: ["text", "image"],
15052
15315
  cost: {
15053
15316
  input: 0.39999999999999997,
15054
- output: 2.4,
15317
+ output: 2.5,
15055
15318
  cacheRead: 0.04,
15056
15319
  cacheWrite: 0.5,
15057
15320
  },
@@ -15086,7 +15349,7 @@ export const MODELS = {
15086
15349
  cost: {
15087
15350
  input: 0.5,
15088
15351
  output: 3,
15089
- cacheRead: 0.09999999999999999,
15352
+ cacheRead: 0.049999999999999996,
15090
15353
  cacheWrite: 0.625,
15091
15354
  },
15092
15355
  contextWindow: 1000000,
@@ -15186,7 +15449,7 @@ export const MODELS = {
15186
15449
  reasoning: true,
15187
15450
  input: ["text", "image"],
15188
15451
  cost: {
15189
- input: 0.16,
15452
+ input: 0.15,
15190
15453
  output: 0.47,
15191
15454
  cacheRead: 0.016,
15192
15455
  cacheWrite: 0.19999999999999998,
@@ -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",
@@ -15843,7 +16106,7 @@ export const MODELS = {
15843
16106
  cost: {
15844
16107
  input: 0.15,
15845
16108
  output: 0.6,
15846
- cacheRead: 0.003,
16109
+ cacheRead: 0.015,
15847
16110
  cacheWrite: 0,
15848
16111
  },
15849
16112
  contextWindow: 1000000,
@@ -16130,9 +16393,9 @@ export const MODELS = {
16130
16393
  reasoning: true,
16131
16394
  input: ["text"],
16132
16395
  cost: {
16133
- input: 0.06,
16134
- output: 0.18,
16135
- cacheRead: 0.012,
16396
+ input: 0.020999999999999998,
16397
+ output: 0.063,
16398
+ cacheRead: 0.004200000000000001,
16136
16399
  cacheWrite: 0,
16137
16400
  },
16138
16401
  contextWindow: 256000,
@@ -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",
@@ -16625,46 +16922,12 @@ export const MODELS = {
16625
16922
  cost: {
16626
16923
  input: 0.3,
16627
16924
  output: 0.8999999999999999,
16628
- cacheRead: 0,
16925
+ cacheRead: 0.03,
16629
16926
  cacheWrite: 0,
16630
16927
  },
16631
16928
  contextWindow: 128000,
16632
16929
  maxTokens: 4000,
16633
16930
  },
16634
- "mistral/devstral-2": {
16635
- id: "mistral/devstral-2",
16636
- name: "Devstral 2",
16637
- api: "anthropic-messages",
16638
- provider: "vercel-ai-gateway",
16639
- baseUrl: "https://ai-gateway.vercel.sh",
16640
- reasoning: false,
16641
- input: ["text"],
16642
- cost: {
16643
- input: 0.39999999999999997,
16644
- output: 2,
16645
- cacheRead: 0,
16646
- cacheWrite: 0,
16647
- },
16648
- contextWindow: 256000,
16649
- maxTokens: 256000,
16650
- },
16651
- "mistral/devstral-small-2": {
16652
- id: "mistral/devstral-small-2",
16653
- name: "Devstral Small 2",
16654
- api: "anthropic-messages",
16655
- provider: "vercel-ai-gateway",
16656
- baseUrl: "https://ai-gateway.vercel.sh",
16657
- reasoning: false,
16658
- input: ["text", "image"],
16659
- cost: {
16660
- input: 0.09999999999999999,
16661
- output: 0.3,
16662
- cacheRead: 0,
16663
- cacheWrite: 0,
16664
- },
16665
- contextWindow: 256000,
16666
- maxTokens: 256000,
16667
- },
16668
16931
  "mistral/ministral-14b": {
16669
16932
  id: "mistral/ministral-14b",
16670
16933
  name: "Ministral 14B",
@@ -16676,10 +16939,10 @@ export const MODELS = {
16676
16939
  cost: {
16677
16940
  input: 0.19999999999999998,
16678
16941
  output: 0.19999999999999998,
16679
- cacheRead: 0,
16942
+ cacheRead: 0.02,
16680
16943
  cacheWrite: 0,
16681
16944
  },
16682
- contextWindow: 256000,
16945
+ contextWindow: 262144,
16683
16946
  maxTokens: 256000,
16684
16947
  },
16685
16948
  "mistral/ministral-3b": {
@@ -16693,10 +16956,10 @@ export const MODELS = {
16693
16956
  cost: {
16694
16957
  input: 0.09999999999999999,
16695
16958
  output: 0.09999999999999999,
16696
- cacheRead: 0,
16959
+ cacheRead: 0.01,
16697
16960
  cacheWrite: 0,
16698
16961
  },
16699
- contextWindow: 128000,
16962
+ contextWindow: 131072,
16700
16963
  maxTokens: 4000,
16701
16964
  },
16702
16965
  "mistral/ministral-8b": {
@@ -16710,10 +16973,10 @@ export const MODELS = {
16710
16973
  cost: {
16711
16974
  input: 0.15,
16712
16975
  output: 0.15,
16713
- cacheRead: 0,
16976
+ cacheRead: 0.015,
16714
16977
  cacheWrite: 0,
16715
16978
  },
16716
- contextWindow: 128000,
16979
+ contextWindow: 262144,
16717
16980
  maxTokens: 4000,
16718
16981
  },
16719
16982
  "mistral/mistral-large-3": {
@@ -16727,29 +16990,12 @@ export const MODELS = {
16727
16990
  cost: {
16728
16991
  input: 0.5,
16729
16992
  output: 1.5,
16730
- cacheRead: 0,
16993
+ cacheRead: 0.049999999999999996,
16731
16994
  cacheWrite: 0,
16732
16995
  },
16733
- contextWindow: 256000,
16996
+ contextWindow: 262144,
16734
16997
  maxTokens: 256000,
16735
16998
  },
16736
- "mistral/mistral-medium": {
16737
- id: "mistral/mistral-medium",
16738
- name: "Mistral Medium 3.1",
16739
- api: "anthropic-messages",
16740
- provider: "vercel-ai-gateway",
16741
- baseUrl: "https://ai-gateway.vercel.sh",
16742
- reasoning: false,
16743
- input: ["text", "image"],
16744
- cost: {
16745
- input: 0.39999999999999997,
16746
- output: 2,
16747
- cacheRead: 0,
16748
- cacheWrite: 0,
16749
- },
16750
- contextWindow: 128000,
16751
- maxTokens: 64000,
16752
- },
16753
16999
  "mistral/mistral-medium-3.5": {
16754
17000
  id: "mistral/mistral-medium-3.5",
16755
17001
  name: "Mistral Medium Latest",
@@ -16761,10 +17007,10 @@ export const MODELS = {
16761
17007
  cost: {
16762
17008
  input: 1.5,
16763
17009
  output: 7.5,
16764
- cacheRead: 0,
17010
+ cacheRead: 0.15,
16765
17011
  cacheWrite: 0,
16766
17012
  },
16767
- contextWindow: 256000,
17013
+ contextWindow: 262144,
16768
17014
  maxTokens: 256000,
16769
17015
  },
16770
17016
  "mistral/mistral-nemo": {
@@ -16774,15 +17020,15 @@ export const MODELS = {
16774
17020
  provider: "vercel-ai-gateway",
16775
17021
  baseUrl: "https://ai-gateway.vercel.sh",
16776
17022
  reasoning: false,
16777
- input: ["text", "image"],
17023
+ input: ["text"],
16778
17024
  cost: {
16779
- input: 0.15,
16780
- output: 0.15,
17025
+ input: 0.04,
17026
+ output: 0.16999999999999998,
16781
17027
  cacheRead: 0,
16782
17028
  cacheWrite: 0,
16783
17029
  },
16784
- contextWindow: 128000,
16785
- maxTokens: 128000,
17030
+ contextWindow: 60288,
17031
+ maxTokens: 16000,
16786
17032
  },
16787
17033
  "mistral/mistral-small": {
16788
17034
  id: "mistral/mistral-small",
@@ -16792,30 +17038,13 @@ export const MODELS = {
16792
17038
  baseUrl: "https://ai-gateway.vercel.sh",
16793
17039
  reasoning: false,
16794
17040
  input: ["text", "image"],
16795
- cost: {
16796
- input: 0.09999999999999999,
16797
- output: 0.3,
16798
- cacheRead: 0,
16799
- cacheWrite: 0,
16800
- },
16801
- contextWindow: 32000,
16802
- maxTokens: 4000,
16803
- },
16804
- "mistral/pixtral-12b": {
16805
- id: "mistral/pixtral-12b",
16806
- name: "Pixtral 12B 2409",
16807
- api: "anthropic-messages",
16808
- provider: "vercel-ai-gateway",
16809
- baseUrl: "https://ai-gateway.vercel.sh",
16810
- reasoning: false,
16811
- input: ["text", "image"],
16812
17041
  cost: {
16813
17042
  input: 0.15,
16814
- output: 0.15,
16815
- cacheRead: 0,
17043
+ output: 0.6,
17044
+ cacheRead: 0.015,
16816
17045
  cacheWrite: 0,
16817
17046
  },
16818
- contextWindow: 128000,
17047
+ contextWindow: 262144,
16819
17048
  maxTokens: 4000,
16820
17049
  },
16821
17050
  "moonshotai/kimi-k2": {
@@ -16964,8 +17193,8 @@ export const MODELS = {
16964
17193
  input: ["text"],
16965
17194
  cost: {
16966
17195
  input: 0.049999999999999996,
16967
- output: 0.24,
16968
- cacheRead: 0,
17196
+ output: 0.19999999999999998,
17197
+ cacheRead: 0.024999999999999998,
16969
17198
  cacheWrite: 0,
16970
17199
  },
16971
17200
  contextWindow: 262144,
@@ -18091,6 +18320,23 @@ export const MODELS = {
18091
18320
  contextWindow: 256000,
18092
18321
  maxTokens: 32768,
18093
18322
  },
18323
+ "sakana/fugu-max": {
18324
+ id: "sakana/fugu-max",
18325
+ name: "Fugu Max",
18326
+ api: "anthropic-messages",
18327
+ provider: "vercel-ai-gateway",
18328
+ baseUrl: "https://ai-gateway.vercel.sh",
18329
+ reasoning: true,
18330
+ input: ["text", "image"],
18331
+ cost: {
18332
+ input: 2,
18333
+ output: 6,
18334
+ cacheRead: 0.25,
18335
+ cacheWrite: 0,
18336
+ },
18337
+ contextWindow: 1000000,
18338
+ maxTokens: 1000000,
18339
+ },
18094
18340
  "sakana/fugu-ultra": {
18095
18341
  id: "sakana/fugu-ultra",
18096
18342
  name: "Fugu Ultra",
@@ -18108,6 +18354,23 @@ export const MODELS = {
18108
18354
  contextWindow: 1000000,
18109
18355
  maxTokens: 1000000,
18110
18356
  },
18357
+ "sakana/fugu-ultra-v2": {
18358
+ id: "sakana/fugu-ultra-v2",
18359
+ name: "Fugu Ultra v2",
18360
+ api: "anthropic-messages",
18361
+ provider: "vercel-ai-gateway",
18362
+ baseUrl: "https://ai-gateway.vercel.sh",
18363
+ reasoning: true,
18364
+ input: ["text", "image"],
18365
+ cost: {
18366
+ input: 5,
18367
+ output: 30,
18368
+ cacheRead: 0.5,
18369
+ cacheWrite: 0,
18370
+ },
18371
+ contextWindow: 1000000,
18372
+ maxTokens: 1000000,
18373
+ },
18111
18374
  "sakana/namazu": {
18112
18375
  id: "sakana/namazu",
18113
18376
  name: "Sakana Namazu",