@dreb/ai 2.43.3 → 2.44.0

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.
@@ -3653,6 +3653,40 @@ export const MODELS = {
3653
3653
  contextWindow: 1048576,
3654
3654
  maxTokens: 65536,
3655
3655
  },
3656
+ "gemini-3.5-flash-lite": {
3657
+ id: "gemini-3.5-flash-lite",
3658
+ name: "Gemini 3.5 Flash Lite",
3659
+ api: "google-generative-ai",
3660
+ provider: "google",
3661
+ baseUrl: "https://generativelanguage.googleapis.com/v1beta",
3662
+ reasoning: true,
3663
+ input: ["text", "image"],
3664
+ cost: {
3665
+ input: 0.3,
3666
+ output: 2.5,
3667
+ cacheRead: 0.03,
3668
+ cacheWrite: 0,
3669
+ },
3670
+ contextWindow: 1048576,
3671
+ maxTokens: 65536,
3672
+ },
3673
+ "gemini-3.6-flash": {
3674
+ id: "gemini-3.6-flash",
3675
+ name: "Gemini 3.6 Flash",
3676
+ api: "google-generative-ai",
3677
+ provider: "google",
3678
+ baseUrl: "https://generativelanguage.googleapis.com/v1beta",
3679
+ reasoning: true,
3680
+ input: ["text", "image"],
3681
+ cost: {
3682
+ input: 1.5,
3683
+ output: 7.5,
3684
+ cacheRead: 0.15,
3685
+ cacheWrite: 0,
3686
+ },
3687
+ contextWindow: 1048576,
3688
+ maxTokens: 65536,
3689
+ },
3656
3690
  "gemini-flash-latest": {
3657
3691
  id: "gemini-flash-latest",
3658
3692
  name: "Gemini Flash Latest",
@@ -4687,6 +4721,24 @@ export const MODELS = {
4687
4721
  contextWindow: 262144,
4688
4722
  maxTokens: 4096,
4689
4723
  },
4724
+ "XiaomiMiMo/MiMo-V2.5": {
4725
+ id: "XiaomiMiMo/MiMo-V2.5",
4726
+ name: "MiMo-V2.5",
4727
+ api: "openai-completions",
4728
+ provider: "huggingface",
4729
+ baseUrl: "https://router.huggingface.co/v1",
4730
+ compat: { "supportsDeveloperRole": false },
4731
+ reasoning: true,
4732
+ input: ["text"],
4733
+ cost: {
4734
+ input: 0.4,
4735
+ output: 2,
4736
+ cacheRead: 0,
4737
+ cacheWrite: 0,
4738
+ },
4739
+ contextWindow: 262144,
4740
+ maxTokens: 131072,
4741
+ },
4690
4742
  "XiaomiMiMo/MiMo-V2.5-Pro": {
4691
4743
  id: "XiaomiMiMo/MiMo-V2.5-Pro",
4692
4744
  name: "MiMo-V2.5-Pro",
@@ -5210,9 +5262,9 @@ export const MODELS = {
5210
5262
  contextWindow: 262144,
5211
5263
  maxTokens: 32768,
5212
5264
  },
5213
- "k2p7": {
5214
- id: "k2p7",
5215
- name: "Kimi K2.7 Code",
5265
+ "k3": {
5266
+ id: "k3",
5267
+ name: "Kimi K3",
5216
5268
  api: "anthropic-messages",
5217
5269
  provider: "kimi-coding",
5218
5270
  baseUrl: "https://api.kimi.com/coding",
@@ -5224,12 +5276,12 @@ export const MODELS = {
5224
5276
  cacheRead: 0,
5225
5277
  cacheWrite: 0,
5226
5278
  },
5227
- contextWindow: 262144,
5228
- maxTokens: 32768,
5279
+ contextWindow: 1048576,
5280
+ maxTokens: 131072,
5229
5281
  },
5230
- "k3": {
5231
- id: "k3",
5232
- name: "Kimi K3",
5282
+ "kimi-for-coding": {
5283
+ id: "kimi-for-coding",
5284
+ name: "Kimi K2.7 Code",
5233
5285
  api: "anthropic-messages",
5234
5286
  provider: "kimi-coding",
5235
5287
  baseUrl: "https://api.kimi.com/coding",
@@ -5241,8 +5293,8 @@ export const MODELS = {
5241
5293
  cacheRead: 0,
5242
5294
  cacheWrite: 0,
5243
5295
  },
5244
- contextWindow: 1048576,
5245
- maxTokens: 131072,
5296
+ contextWindow: 262144,
5297
+ maxTokens: 32768,
5246
5298
  },
5247
5299
  "kimi-for-coding-highspeed": {
5248
5300
  id: "kimi-for-coding-highspeed",
@@ -7199,6 +7251,40 @@ export const MODELS = {
7199
7251
  contextWindow: 1048576,
7200
7252
  maxTokens: 65536,
7201
7253
  },
7254
+ "gemini-3.5-flash-lite": {
7255
+ id: "gemini-3.5-flash-lite",
7256
+ name: "Gemini 3.5 Flash Lite",
7257
+ api: "google-generative-ai",
7258
+ provider: "opencode",
7259
+ baseUrl: "https://opencode.ai/zen/v1",
7260
+ reasoning: true,
7261
+ input: ["text", "image"],
7262
+ cost: {
7263
+ input: 0.3,
7264
+ output: 2.5,
7265
+ cacheRead: 0.03,
7266
+ cacheWrite: 0,
7267
+ },
7268
+ contextWindow: 1048576,
7269
+ maxTokens: 65536,
7270
+ },
7271
+ "gemini-3.6-flash": {
7272
+ id: "gemini-3.6-flash",
7273
+ name: "Gemini 3.6 Flash",
7274
+ api: "google-generative-ai",
7275
+ provider: "opencode",
7276
+ baseUrl: "https://opencode.ai/zen/v1",
7277
+ reasoning: true,
7278
+ input: ["text", "image"],
7279
+ cost: {
7280
+ input: 1.5,
7281
+ output: 7.5,
7282
+ cacheRead: 0.15,
7283
+ cacheWrite: 0,
7284
+ },
7285
+ contextWindow: 1048576,
7286
+ maxTokens: 65536,
7287
+ },
7202
7288
  "glm-5": {
7203
7289
  id: "glm-5",
7204
7290
  name: "GLM-5",
@@ -7607,23 +7693,6 @@ export const MODELS = {
7607
7693
  contextWindow: 256000,
7608
7694
  maxTokens: 256000,
7609
7695
  },
7610
- "hy3-free": {
7611
- id: "hy3-free",
7612
- name: "Hy3 Free",
7613
- api: "openai-completions",
7614
- provider: "opencode",
7615
- baseUrl: "https://opencode.ai/zen/v1",
7616
- reasoning: true,
7617
- input: ["text"],
7618
- cost: {
7619
- input: 0,
7620
- output: 0,
7621
- cacheRead: 0,
7622
- cacheWrite: 0,
7623
- },
7624
- contextWindow: 190000,
7625
- maxTokens: 64000,
7626
- },
7627
7696
  "kimi-k2.5": {
7628
7697
  id: "kimi-k2.5",
7629
7698
  name: "Kimi K2.5",
@@ -7675,6 +7744,23 @@ export const MODELS = {
7675
7744
  contextWindow: 262144,
7676
7745
  maxTokens: 262144,
7677
7746
  },
7747
+ "laguna-s-2.1-free": {
7748
+ id: "laguna-s-2.1-free",
7749
+ name: "Laguna S 2.1 Free",
7750
+ api: "openai-completions",
7751
+ provider: "opencode",
7752
+ baseUrl: "https://opencode.ai/zen/v1",
7753
+ reasoning: true,
7754
+ input: ["text"],
7755
+ cost: {
7756
+ input: 0,
7757
+ output: 0,
7758
+ cacheRead: 0,
7759
+ cacheWrite: 0,
7760
+ },
7761
+ contextWindow: 256000,
7762
+ maxTokens: 32000,
7763
+ },
7678
7764
  "mimo-v2.5-free": {
7679
7765
  id: "mimo-v2.5-free",
7680
7766
  name: "MiMo V2.5 Free",
@@ -7898,6 +7984,23 @@ export const MODELS = {
7898
7984
  contextWindow: 500000,
7899
7985
  maxTokens: 500000,
7900
7986
  },
7987
+ "hy3": {
7988
+ id: "hy3",
7989
+ name: "Hy3",
7990
+ api: "openai-completions",
7991
+ provider: "opencode-go",
7992
+ baseUrl: "https://opencode.ai/zen/go/v1",
7993
+ reasoning: true,
7994
+ input: ["text"],
7995
+ cost: {
7996
+ input: 0.14,
7997
+ output: 0.58,
7998
+ cacheRead: 0.035,
7999
+ cacheWrite: 0,
8000
+ },
8001
+ contextWindow: 256000,
8002
+ maxTokens: 64000,
8003
+ },
7901
8004
  "kimi-k2.6": {
7902
8005
  id: "kimi-k2.6",
7903
8006
  name: "Kimi K2.6",
@@ -8662,7 +8765,7 @@ export const MODELS = {
8662
8765
  cacheRead: 0,
8663
8766
  cacheWrite: 0,
8664
8767
  },
8665
- contextWindow: 131072,
8768
+ contextWindow: 163840,
8666
8769
  maxTokens: 16000,
8667
8770
  },
8668
8771
  "deepseek/deepseek-chat-v3-0324": {
@@ -8747,7 +8850,7 @@ export const MODELS = {
8747
8850
  cacheRead: 0.135,
8748
8851
  cacheWrite: 0,
8749
8852
  },
8750
- contextWindow: 131072,
8853
+ contextWindow: 163840,
8751
8854
  maxTokens: 32768,
8752
8855
  },
8753
8856
  "deepseek/deepseek-v3.2": {
@@ -8934,7 +9037,7 @@ export const MODELS = {
8934
9037
  cacheRead: 0.19999999999999998,
8935
9038
  cacheWrite: 0.375,
8936
9039
  },
8937
- contextWindow: 65536,
9040
+ contextWindow: 131072,
8938
9041
  maxTokens: 32768,
8939
9042
  },
8940
9043
  "google/gemini-3.1-flash-lite": {
@@ -9002,7 +9105,7 @@ export const MODELS = {
9002
9105
  cacheRead: 0.19999999999999998,
9003
9106
  cacheWrite: 0.375,
9004
9107
  },
9005
- contextWindow: 1048756,
9108
+ contextWindow: 1048576,
9006
9109
  maxTokens: 65536,
9007
9110
  },
9008
9111
  "google/gemini-3.5-flash": {
@@ -9022,6 +9125,40 @@ export const MODELS = {
9022
9125
  contextWindow: 1048576,
9023
9126
  maxTokens: 65536,
9024
9127
  },
9128
+ "google/gemini-3.5-flash-lite": {
9129
+ id: "google/gemini-3.5-flash-lite",
9130
+ name: "Google: Gemini 3.5 Flash Lite",
9131
+ api: "openai-completions",
9132
+ provider: "openrouter",
9133
+ baseUrl: "https://openrouter.ai/api/v1",
9134
+ reasoning: true,
9135
+ input: ["text", "image"],
9136
+ cost: {
9137
+ input: 0.3,
9138
+ output: 2.5,
9139
+ cacheRead: 0.03,
9140
+ cacheWrite: 0.08333333333333334,
9141
+ },
9142
+ contextWindow: 1048576,
9143
+ maxTokens: 65536,
9144
+ },
9145
+ "google/gemini-3.6-flash": {
9146
+ id: "google/gemini-3.6-flash",
9147
+ name: "Google: Gemini 3.6 Flash",
9148
+ api: "openai-completions",
9149
+ provider: "openrouter",
9150
+ baseUrl: "https://openrouter.ai/api/v1",
9151
+ reasoning: true,
9152
+ input: ["text", "image"],
9153
+ cost: {
9154
+ input: 1.5,
9155
+ output: 7.5,
9156
+ cacheRead: 0.15,
9157
+ cacheWrite: 0.08333333333333334,
9158
+ },
9159
+ contextWindow: 1048576,
9160
+ maxTokens: 65536,
9161
+ },
9025
9162
  "google/gemma-3-12b-it": {
9026
9163
  id: "google/gemma-3-12b-it",
9027
9164
  name: "Google: Gemma 3 12B",
@@ -9053,7 +9190,7 @@ export const MODELS = {
9053
9190
  cacheRead: 0,
9054
9191
  cacheWrite: 0,
9055
9192
  },
9056
- contextWindow: 131072,
9193
+ contextWindow: 262144,
9057
9194
  maxTokens: 4096,
9058
9195
  },
9059
9196
  "google/gemma-4-26b-a4b-it": {
@@ -9065,13 +9202,13 @@ export const MODELS = {
9065
9202
  reasoning: true,
9066
9203
  input: ["text", "image"],
9067
9204
  cost: {
9068
- input: 0.07,
9069
- output: 0.33999999999999997,
9070
- cacheRead: 0,
9205
+ input: 0.12,
9206
+ output: 0.35,
9207
+ cacheRead: 0.049999999999999996,
9071
9208
  cacheWrite: 0,
9072
9209
  },
9073
9210
  contextWindow: 262144,
9074
- maxTokens: 16384,
9211
+ maxTokens: 262144,
9075
9212
  },
9076
9213
  "google/gemma-4-26b-a4b-it:free": {
9077
9214
  id: "google/gemma-4-26b-a4b-it:free",
@@ -9099,9 +9236,9 @@ export const MODELS = {
9099
9236
  reasoning: true,
9100
9237
  input: ["text", "image"],
9101
9238
  cost: {
9102
- input: 0.22,
9103
- output: 0.55,
9104
- cacheRead: 0.12,
9239
+ input: 0.12,
9240
+ output: 0.35,
9241
+ cacheRead: 0.09,
9105
9242
  cacheWrite: 0,
9106
9243
  },
9107
9244
  contextWindow: 262144,
@@ -9240,7 +9377,7 @@ export const MODELS = {
9240
9377
  cacheRead: 0.06,
9241
9378
  cacheWrite: 0,
9242
9379
  },
9243
- contextWindow: 256000,
9380
+ contextWindow: 262144,
9244
9381
  maxTokens: 80000,
9245
9382
  },
9246
9383
  "kwaipilot/kat-coder-pro-v2.5": {
@@ -9260,6 +9397,23 @@ export const MODELS = {
9260
9397
  contextWindow: 256000,
9261
9398
  maxTokens: 80000,
9262
9399
  },
9400
+ "meituan/longcat-2.0": {
9401
+ id: "meituan/longcat-2.0",
9402
+ name: "Meituan: LongCat 2.0",
9403
+ api: "openai-completions",
9404
+ provider: "openrouter",
9405
+ baseUrl: "https://openrouter.ai/api/v1",
9406
+ reasoning: true,
9407
+ input: ["text"],
9408
+ cost: {
9409
+ input: 0.3,
9410
+ output: 1.2,
9411
+ cacheRead: 0.006,
9412
+ cacheWrite: 0,
9413
+ },
9414
+ contextWindow: 1048756,
9415
+ maxTokens: 262144,
9416
+ },
9263
9417
  "meta-llama/llama-3.1-70b-instruct": {
9264
9418
  id: "meta-llama/llama-3.1-70b-instruct",
9265
9419
  name: "Meta: Llama 3.1 70B Instruct",
@@ -9342,7 +9496,7 @@ export const MODELS = {
9342
9496
  cacheRead: 0,
9343
9497
  cacheWrite: 0,
9344
9498
  },
9345
- contextWindow: 10000000,
9499
+ contextWindow: 1310720,
9346
9500
  maxTokens: 16384,
9347
9501
  },
9348
9502
  "meta/muse-spark-1.1": {
@@ -9716,7 +9870,7 @@ export const MODELS = {
9716
9870
  cacheRead: 0.01,
9717
9871
  cacheWrite: 0,
9718
9872
  },
9719
- contextWindow: 131072,
9873
+ contextWindow: 256000,
9720
9874
  maxTokens: 4096,
9721
9875
  },
9722
9876
  "mistralai/mixtral-8x22b-instruct": {
@@ -9847,9 +10001,9 @@ export const MODELS = {
9847
10001
  reasoning: true,
9848
10002
  input: ["text", "image"],
9849
10003
  cost: {
9850
- input: 0.85,
9851
- output: 3.8,
9852
- cacheRead: 0.16999999999999998,
10004
+ input: 0.82,
10005
+ output: 3.75,
10006
+ cacheRead: 0.16,
9853
10007
  cacheWrite: 0,
9854
10008
  },
9855
10009
  contextWindow: 262144,
@@ -9966,13 +10120,13 @@ export const MODELS = {
9966
10120
  reasoning: true,
9967
10121
  input: ["text"],
9968
10122
  cost: {
9969
- input: 0.08499999999999999,
9970
- output: 0.39999999999999997,
10123
+ input: 0.08,
10124
+ output: 0.44999999999999996,
9971
10125
  cacheRead: 0,
9972
10126
  cacheWrite: 0,
9973
10127
  },
9974
10128
  contextWindow: 1000000,
9975
- maxTokens: 16384,
10129
+ maxTokens: 4096,
9976
10130
  },
9977
10131
  "nvidia/nemotron-3-super-120b-a12b:free": {
9978
10132
  id: "nvidia/nemotron-3-super-120b-a12b:free",
@@ -9988,7 +10142,7 @@ export const MODELS = {
9988
10142
  cacheRead: 0,
9989
10143
  cacheWrite: 0,
9990
10144
  },
9991
- contextWindow: 1000000,
10145
+ contextWindow: 262144,
9992
10146
  maxTokens: 262144,
9993
10147
  },
9994
10148
  "nvidia/nemotron-3-ultra-550b-a55b": {
@@ -10000,13 +10154,13 @@ export const MODELS = {
10000
10154
  reasoning: true,
10001
10155
  input: ["text"],
10002
10156
  cost: {
10003
- input: 0.6,
10004
- output: 3.5999999999999996,
10005
- cacheRead: 0.19999999999999998,
10157
+ input: 0.5,
10158
+ output: 2.2,
10159
+ cacheRead: 0.09999999999999999,
10006
10160
  cacheWrite: 0,
10007
10161
  },
10008
- contextWindow: 1000000,
10009
- maxTokens: 4096,
10162
+ contextWindow: 512288,
10163
+ maxTokens: 16384,
10010
10164
  },
10011
10165
  "nvidia/nemotron-3-ultra-550b-a55b:free": {
10012
10166
  id: "nvidia/nemotron-3-ultra-550b-a55b:free",
@@ -11147,6 +11301,40 @@ export const MODELS = {
11147
11301
  contextWindow: 262144,
11148
11302
  maxTokens: 32768,
11149
11303
  },
11304
+ "poolside/laguna-s-2.1": {
11305
+ id: "poolside/laguna-s-2.1",
11306
+ name: "Poolside: Laguna S 2.1",
11307
+ api: "openai-completions",
11308
+ provider: "openrouter",
11309
+ baseUrl: "https://openrouter.ai/api/v1",
11310
+ reasoning: true,
11311
+ input: ["text"],
11312
+ cost: {
11313
+ input: 0.09999999999999999,
11314
+ output: 0.19999999999999998,
11315
+ cacheRead: 0.01,
11316
+ cacheWrite: 0,
11317
+ },
11318
+ contextWindow: 1048576,
11319
+ maxTokens: 131072,
11320
+ },
11321
+ "poolside/laguna-s-2.1:free": {
11322
+ id: "poolside/laguna-s-2.1:free",
11323
+ name: "Poolside: Laguna S 2.1 (free)",
11324
+ api: "openai-completions",
11325
+ provider: "openrouter",
11326
+ baseUrl: "https://openrouter.ai/api/v1",
11327
+ reasoning: true,
11328
+ input: ["text"],
11329
+ cost: {
11330
+ input: 0,
11331
+ output: 0,
11332
+ cacheRead: 0,
11333
+ cacheWrite: 0,
11334
+ },
11335
+ contextWindow: 262144,
11336
+ maxTokens: 32768,
11337
+ },
11150
11338
  "poolside/laguna-xs-2.1": {
11151
11339
  id: "poolside/laguna-xs-2.1",
11152
11340
  name: "Poolside: Laguna XS 2.1",
@@ -11195,7 +11383,7 @@ export const MODELS = {
11195
11383
  cacheRead: 0,
11196
11384
  cacheWrite: 0,
11197
11385
  },
11198
- contextWindow: 131072,
11386
+ contextWindow: 32768,
11199
11387
  maxTokens: 16384,
11200
11388
  },
11201
11389
  "qwen/qwen-2.5-7b-instruct": {
@@ -11212,7 +11400,7 @@ export const MODELS = {
11212
11400
  cacheRead: 0,
11213
11401
  cacheWrite: 0,
11214
11402
  },
11215
- contextWindow: 131072,
11403
+ contextWindow: 32768,
11216
11404
  maxTokens: 32768,
11217
11405
  },
11218
11406
  "qwen/qwen-plus": {
@@ -11275,13 +11463,13 @@ export const MODELS = {
11275
11463
  reasoning: true,
11276
11464
  input: ["text"],
11277
11465
  cost: {
11278
- input: 0.12,
11279
- output: 0.24,
11466
+ input: 0.22749999999999998,
11467
+ output: 0.9099999999999999,
11280
11468
  cacheRead: 0,
11281
11469
  cacheWrite: 0,
11282
11470
  },
11283
- contextWindow: 131702,
11284
- maxTokens: 16384,
11471
+ contextWindow: 131072,
11472
+ maxTokens: 8192,
11285
11473
  },
11286
11474
  "qwen/qwen3-235b-a22b": {
11287
11475
  id: "qwen/qwen3-235b-a22b",
@@ -11326,13 +11514,13 @@ export const MODELS = {
11326
11514
  reasoning: true,
11327
11515
  input: ["text"],
11328
11516
  cost: {
11329
- input: 0.14950000000000002,
11330
- output: 1.495,
11517
+ input: 0.3,
11518
+ output: 3,
11331
11519
  cacheRead: 0,
11332
11520
  cacheWrite: 0,
11333
11521
  },
11334
11522
  contextWindow: 262144,
11335
- maxTokens: 4096,
11523
+ maxTokens: 32768,
11336
11524
  },
11337
11525
  "qwen/qwen3-30b-a3b": {
11338
11526
  id: "qwen/qwen3-30b-a3b",
@@ -11382,7 +11570,7 @@ export const MODELS = {
11382
11570
  cacheRead: 0,
11383
11571
  cacheWrite: 0,
11384
11572
  },
11385
- contextWindow: 131072,
11573
+ contextWindow: 81920,
11386
11574
  maxTokens: 32768,
11387
11575
  },
11388
11576
  "qwen/qwen3-32b": {
@@ -11433,7 +11621,7 @@ export const MODELS = {
11433
11621
  cacheRead: 0.09999999999999999,
11434
11622
  cacheWrite: 0,
11435
11623
  },
11436
- contextWindow: 1048576,
11624
+ contextWindow: 262144,
11437
11625
  maxTokens: 65536,
11438
11626
  },
11439
11627
  "qwen/qwen3-coder-30b-a3b-instruct": {
@@ -11450,7 +11638,7 @@ export const MODELS = {
11450
11638
  cacheRead: 0,
11451
11639
  cacheWrite: 0,
11452
11640
  },
11453
- contextWindow: 160000,
11641
+ contextWindow: 262144,
11454
11642
  maxTokens: 32768,
11455
11643
  },
11456
11644
  "qwen/qwen3-coder-flash": {
@@ -11547,9 +11735,9 @@ export const MODELS = {
11547
11735
  reasoning: false,
11548
11736
  input: ["text"],
11549
11737
  cost: {
11550
- input: 0.09999999999999999,
11551
- output: 1.1,
11552
- cacheRead: 0.07,
11738
+ input: 0.15,
11739
+ output: 1.2,
11740
+ cacheRead: 0,
11553
11741
  cacheWrite: 0,
11554
11742
  },
11555
11743
  contextWindow: 262144,
@@ -11586,7 +11774,7 @@ export const MODELS = {
11586
11774
  cacheRead: 0.09999999999999999,
11587
11775
  cacheWrite: 0,
11588
11776
  },
11589
- contextWindow: 131072,
11777
+ contextWindow: 262144,
11590
11778
  maxTokens: 32768,
11591
11779
  },
11592
11780
  "qwen/qwen3-vl-235b-a22b-thinking": {
@@ -11615,13 +11803,13 @@ export const MODELS = {
11615
11803
  reasoning: false,
11616
11804
  input: ["text", "image"],
11617
11805
  cost: {
11618
- input: 0.13,
11619
- output: 0.52,
11806
+ input: 0.15,
11807
+ output: 0.6,
11620
11808
  cacheRead: 0,
11621
11809
  cacheWrite: 0,
11622
11810
  },
11623
11811
  contextWindow: 262144,
11624
- maxTokens: 32768,
11812
+ maxTokens: 16384,
11625
11813
  },
11626
11814
  "qwen/qwen3-vl-30b-a3b-thinking": {
11627
11815
  id: "qwen/qwen3-vl-30b-a3b-thinking",
@@ -11637,7 +11825,7 @@ export const MODELS = {
11637
11825
  cacheRead: 0,
11638
11826
  cacheWrite: 0,
11639
11827
  },
11640
- contextWindow: 131072,
11828
+ contextWindow: 262144,
11641
11829
  maxTokens: 32768,
11642
11830
  },
11643
11831
  "qwen/qwen3-vl-32b-instruct": {
@@ -11654,7 +11842,7 @@ export const MODELS = {
11654
11842
  cacheRead: 0,
11655
11843
  cacheWrite: 0,
11656
11844
  },
11657
- contextWindow: 262144,
11845
+ contextWindow: 131072,
11658
11846
  maxTokens: 32768,
11659
11847
  },
11660
11848
  "qwen/qwen3-vl-8b-instruct": {
@@ -11671,7 +11859,7 @@ export const MODELS = {
11671
11859
  cacheRead: 0,
11672
11860
  cacheWrite: 0,
11673
11861
  },
11674
- contextWindow: 256000,
11862
+ contextWindow: 262144,
11675
11863
  maxTokens: 32768,
11676
11864
  },
11677
11865
  "qwen/qwen3-vl-8b-thinking": {
@@ -11688,7 +11876,7 @@ export const MODELS = {
11688
11876
  cacheRead: 0,
11689
11877
  cacheWrite: 0,
11690
11878
  },
11691
- contextWindow: 256000,
11879
+ contextWindow: 131072,
11692
11880
  maxTokens: 32768,
11693
11881
  },
11694
11882
  "qwen/qwen3.5-122b-a10b": {
@@ -11836,13 +12024,13 @@ export const MODELS = {
11836
12024
  reasoning: true,
11837
12025
  input: ["text", "image"],
11838
12026
  cost: {
11839
- input: 0.44999999999999996,
11840
- output: 2.7,
11841
- cacheRead: 0,
12027
+ input: 0.6,
12028
+ output: 3.5999999999999996,
12029
+ cacheRead: 0.12,
11842
12030
  cacheWrite: 0,
11843
12031
  },
11844
12032
  contextWindow: 262144,
11845
- maxTokens: 65536,
12033
+ maxTokens: 262144,
11846
12034
  },
11847
12035
  "qwen/qwen3.6-35b-a3b": {
11848
12036
  id: "qwen/qwen3.6-35b-a3b",
@@ -12045,7 +12233,7 @@ export const MODELS = {
12045
12233
  cacheRead: 0.04,
12046
12234
  cacheWrite: 0,
12047
12235
  },
12048
- contextWindow: 256000,
12236
+ contextWindow: 262144,
12049
12237
  maxTokens: 256000,
12050
12238
  },
12051
12239
  "tencent/hy3": {
@@ -12057,13 +12245,13 @@ export const MODELS = {
12057
12245
  reasoning: true,
12058
12246
  input: ["text"],
12059
12247
  cost: {
12060
- input: 0.19999999999999998,
12061
- output: 0.7999999999999999,
12062
- cacheRead: 0.049999999999999996,
12248
+ input: 0.14,
12249
+ output: 0.58,
12250
+ cacheRead: 0.035,
12063
12251
  cacheWrite: 0,
12064
12252
  },
12065
12253
  contextWindow: 262144,
12066
- maxTokens: 131072,
12254
+ maxTokens: 262144,
12067
12255
  },
12068
12256
  "tencent/hy3-preview": {
12069
12257
  id: "tencent/hy3-preview",
@@ -12082,23 +12270,6 @@ export const MODELS = {
12082
12270
  contextWindow: 262144,
12083
12271
  maxTokens: 4096,
12084
12272
  },
12085
- "tencent/hy3:free": {
12086
- id: "tencent/hy3:free",
12087
- name: "Tencent: Hy3 (free)",
12088
- api: "openai-completions",
12089
- provider: "openrouter",
12090
- baseUrl: "https://openrouter.ai/api/v1",
12091
- reasoning: true,
12092
- input: ["text"],
12093
- cost: {
12094
- input: 0,
12095
- output: 0,
12096
- cacheRead: 0,
12097
- cacheWrite: 0,
12098
- },
12099
- contextWindow: 262144,
12100
- maxTokens: 262144,
12101
- },
12102
12273
  "thedrummer/unslopnemo-12b": {
12103
12274
  id: "thedrummer/unslopnemo-12b",
12104
12275
  name: "TheDrummer: UnslopNemo 12B",
@@ -12232,7 +12403,7 @@ export const MODELS = {
12232
12403
  cacheRead: 0.0028,
12233
12404
  cacheWrite: 0,
12234
12405
  },
12235
- contextWindow: 1048576,
12406
+ contextWindow: 1050000,
12236
12407
  maxTokens: 131072,
12237
12408
  },
12238
12409
  "xiaomi/mimo-v2.5-pro": {
@@ -12249,7 +12420,7 @@ export const MODELS = {
12249
12420
  cacheRead: 0.0036,
12250
12421
  cacheWrite: 0,
12251
12422
  },
12252
- contextWindow: 1048576,
12423
+ contextWindow: 1050000,
12253
12424
  maxTokens: 131072,
12254
12425
  },
12255
12426
  "z-ai/glm-4.5": {
@@ -12317,7 +12488,7 @@ export const MODELS = {
12317
12488
  cacheRead: 0.09999999999999999,
12318
12489
  cacheWrite: 0,
12319
12490
  },
12320
- contextWindow: 202752,
12491
+ contextWindow: 204800,
12321
12492
  maxTokens: 131072,
12322
12493
  },
12323
12494
  "z-ai/glm-4.6v": {
@@ -12351,7 +12522,7 @@ export const MODELS = {
12351
12522
  cacheRead: 0.08,
12352
12523
  cacheWrite: 0,
12353
12524
  },
12354
- contextWindow: 202752,
12525
+ contextWindow: 204800,
12355
12526
  maxTokens: 131072,
12356
12527
  },
12357
12528
  "z-ai/glm-4.7-flash": {
@@ -12363,13 +12534,13 @@ export const MODELS = {
12363
12534
  reasoning: true,
12364
12535
  input: ["text"],
12365
12536
  cost: {
12366
- input: 0.060500000000000005,
12537
+ input: 0.06,
12367
12538
  output: 0.39999999999999997,
12368
- cacheRead: 0,
12539
+ cacheRead: 0.01,
12369
12540
  cacheWrite: 0,
12370
12541
  },
12371
- contextWindow: 200000,
12372
- maxTokens: 131072,
12542
+ contextWindow: 202752,
12543
+ maxTokens: 16384,
12373
12544
  },
12374
12545
  "z-ai/glm-5": {
12375
12546
  id: "z-ai/glm-5",
@@ -12381,12 +12552,12 @@ export const MODELS = {
12381
12552
  input: ["text"],
12382
12553
  cost: {
12383
12554
  input: 0.95,
12384
- output: 3.15,
12385
- cacheRead: 0.19,
12555
+ output: 2.5500000000000003,
12556
+ cacheRead: 0.19999999999999998,
12386
12557
  cacheWrite: 0,
12387
12558
  },
12388
- contextWindow: 202752,
12389
- maxTokens: 202752,
12559
+ contextWindow: 204800,
12560
+ maxTokens: 131072,
12390
12561
  },
12391
12562
  "z-ai/glm-5-turbo": {
12392
12563
  id: "z-ai/glm-5-turbo",
@@ -12419,7 +12590,7 @@ export const MODELS = {
12419
12590
  cacheRead: 0.1794,
12420
12591
  cacheWrite: 0,
12421
12592
  },
12422
- contextWindow: 202752,
12593
+ contextWindow: 204800,
12423
12594
  maxTokens: 128000,
12424
12595
  },
12425
12596
  "z-ai/glm-5.2": {
@@ -12431,9 +12602,9 @@ export const MODELS = {
12431
12602
  reasoning: true,
12432
12603
  input: ["text"],
12433
12604
  cost: {
12434
- input: 0.252,
12435
- output: 0.792,
12436
- cacheRead: 0.0468,
12605
+ input: 0.826,
12606
+ output: 2.5959999999999996,
12607
+ cacheRead: 0.1534,
12437
12608
  cacheWrite: 0,
12438
12609
  },
12439
12610
  contextWindow: 1048576,
@@ -12534,7 +12705,7 @@ export const MODELS = {
12534
12705
  input: ["text", "image"],
12535
12706
  cost: {
12536
12707
  input: 1.5,
12537
- output: 9,
12708
+ output: 7.5,
12538
12709
  cacheRead: 0.15,
12539
12710
  cacheWrite: 0.08333333333333334,
12540
12711
  },
@@ -13733,6 +13904,40 @@ export const MODELS = {
13733
13904
  contextWindow: 1000000,
13734
13905
  maxTokens: 64000,
13735
13906
  },
13907
+ "google/gemini-3.5-flash-lite": {
13908
+ id: "google/gemini-3.5-flash-lite",
13909
+ name: "Gemini 3.5 Flash Lite",
13910
+ api: "anthropic-messages",
13911
+ provider: "vercel-ai-gateway",
13912
+ baseUrl: "https://ai-gateway.vercel.sh",
13913
+ reasoning: true,
13914
+ input: ["text", "image"],
13915
+ cost: {
13916
+ input: 0.3,
13917
+ output: 2.5,
13918
+ cacheRead: 0.03,
13919
+ cacheWrite: 0,
13920
+ },
13921
+ contextWindow: 1000000,
13922
+ maxTokens: 65000,
13923
+ },
13924
+ "google/gemini-3.6-flash": {
13925
+ id: "google/gemini-3.6-flash",
13926
+ name: "Gemini 3.6 Flash",
13927
+ api: "anthropic-messages",
13928
+ provider: "vercel-ai-gateway",
13929
+ baseUrl: "https://ai-gateway.vercel.sh",
13930
+ reasoning: true,
13931
+ input: ["text", "image"],
13932
+ cost: {
13933
+ input: 1.5,
13934
+ output: 7.5,
13935
+ cacheRead: 0.15,
13936
+ cacheWrite: 0,
13937
+ },
13938
+ contextWindow: 1000000,
13939
+ maxTokens: 64000,
13940
+ },
13736
13941
  "google/gemma-4-26b-a4b-it": {
13737
13942
  id: "google/gemma-4-26b-a4b-it",
13738
13943
  name: "Gemma 4 26B A4B IT",
@@ -13801,6 +14006,23 @@ export const MODELS = {
13801
14006
  contextWindow: 32000,
13802
14007
  maxTokens: 16384,
13803
14008
  },
14009
+ "inclusionai/ling-3.0-flash-free": {
14010
+ id: "inclusionai/ling-3.0-flash-free",
14011
+ name: "Ling 3.0 Flash",
14012
+ api: "anthropic-messages",
14013
+ provider: "vercel-ai-gateway",
14014
+ baseUrl: "https://ai-gateway.vercel.sh",
14015
+ reasoning: true,
14016
+ input: ["text"],
14017
+ cost: {
14018
+ input: 0,
14019
+ output: 0,
14020
+ cacheRead: 0,
14021
+ cacheWrite: 0,
14022
+ },
14023
+ contextWindow: 256000,
14024
+ maxTokens: 256000,
14025
+ },
13804
14026
  "interfaze/interfaze-beta": {
13805
14027
  id: "interfaze/interfaze-beta",
13806
14028
  name: "Interfaze Beta",
@@ -15280,6 +15502,40 @@ export const MODELS = {
15280
15502
  contextWindow: 200000,
15281
15503
  maxTokens: 100000,
15282
15504
  },
15505
+ "poolside/laguna-s-2.1": {
15506
+ id: "poolside/laguna-s-2.1",
15507
+ name: "Laguna S 2.1",
15508
+ api: "anthropic-messages",
15509
+ provider: "vercel-ai-gateway",
15510
+ baseUrl: "https://ai-gateway.vercel.sh",
15511
+ reasoning: true,
15512
+ input: ["text"],
15513
+ cost: {
15514
+ input: 0.09999999999999999,
15515
+ output: 0.19999999999999998,
15516
+ cacheRead: 0.01,
15517
+ cacheWrite: 0,
15518
+ },
15519
+ contextWindow: 1000000,
15520
+ maxTokens: 131072,
15521
+ },
15522
+ "poolside/laguna-s-2.1-free": {
15523
+ id: "poolside/laguna-s-2.1-free",
15524
+ name: "Laguna S 2.1 Free",
15525
+ api: "anthropic-messages",
15526
+ provider: "vercel-ai-gateway",
15527
+ baseUrl: "https://ai-gateway.vercel.sh",
15528
+ reasoning: true,
15529
+ input: ["text"],
15530
+ cost: {
15531
+ input: 0,
15532
+ output: 0,
15533
+ cacheRead: 0,
15534
+ cacheWrite: 0,
15535
+ },
15536
+ contextWindow: 256000,
15537
+ maxTokens: 32768,
15538
+ },
15283
15539
  "sakana/fugu-ultra": {
15284
15540
  id: "sakana/fugu-ultra",
15285
15541
  name: "Fugu Ultra",
@@ -15331,6 +15587,23 @@ export const MODELS = {
15331
15587
  contextWindow: 256000,
15332
15588
  maxTokens: 256000,
15333
15589
  },
15590
+ "tencent/hy3": {
15591
+ id: "tencent/hy3",
15592
+ name: "Hy3",
15593
+ api: "anthropic-messages",
15594
+ provider: "vercel-ai-gateway",
15595
+ baseUrl: "https://ai-gateway.vercel.sh",
15596
+ reasoning: true,
15597
+ input: ["text"],
15598
+ cost: {
15599
+ input: 0.14,
15600
+ output: 0.58,
15601
+ cacheRead: 0.035,
15602
+ cacheWrite: 0,
15603
+ },
15604
+ contextWindow: 262144,
15605
+ maxTokens: 262144,
15606
+ },
15334
15607
  "thinkingmachines/inkling": {
15335
15608
  id: "thinkingmachines/inkling",
15336
15609
  name: "Inkling",
@@ -15512,7 +15785,7 @@ export const MODELS = {
15512
15785
  cost: {
15513
15786
  input: 2,
15514
15787
  output: 6,
15515
- cacheRead: 0.5,
15788
+ cacheRead: 0.3,
15516
15789
  cacheWrite: 0,
15517
15790
  },
15518
15791
  contextWindow: 500000,