@dreb/ai 2.43.3 → 2.45.0

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",
@@ -9048,13 +9185,13 @@ export const MODELS = {
9048
9185
  reasoning: false,
9049
9186
  input: ["text", "image"],
9050
9187
  cost: {
9051
- input: 0.09999999999999999,
9052
- output: 0.3,
9053
- cacheRead: 0,
9188
+ input: 0.08,
9189
+ output: 0.44999999999999996,
9190
+ cacheRead: 0.04,
9054
9191
  cacheWrite: 0,
9055
9192
  },
9056
- contextWindow: 131072,
9057
- maxTokens: 4096,
9193
+ contextWindow: 262144,
9194
+ maxTokens: 131072,
9058
9195
  },
9059
9196
  "google/gemma-4-26b-a4b-it": {
9060
9197
  id: "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,
@@ -9192,6 +9329,23 @@ export const MODELS = {
9192
9329
  contextWindow: 262144,
9193
9330
  maxTokens: 32768,
9194
9331
  },
9332
+ "inclusionai/ling-3.0-flash:free": {
9333
+ id: "inclusionai/ling-3.0-flash:free",
9334
+ name: "Ling-3.0-flash (free)",
9335
+ api: "openai-completions",
9336
+ provider: "openrouter",
9337
+ baseUrl: "https://openrouter.ai/api/v1",
9338
+ reasoning: true,
9339
+ input: ["text"],
9340
+ cost: {
9341
+ input: 0,
9342
+ output: 0,
9343
+ cacheRead: 0,
9344
+ cacheWrite: 0,
9345
+ },
9346
+ contextWindow: 262144,
9347
+ maxTokens: 32768,
9348
+ },
9195
9349
  "inclusionai/ring-2.6-1t": {
9196
9350
  id: "inclusionai/ring-2.6-1t",
9197
9351
  name: "inclusionAI: Ring-2.6-1T",
@@ -9240,7 +9394,7 @@ export const MODELS = {
9240
9394
  cacheRead: 0.06,
9241
9395
  cacheWrite: 0,
9242
9396
  },
9243
- contextWindow: 256000,
9397
+ contextWindow: 262144,
9244
9398
  maxTokens: 80000,
9245
9399
  },
9246
9400
  "kwaipilot/kat-coder-pro-v2.5": {
@@ -9260,6 +9414,23 @@ export const MODELS = {
9260
9414
  contextWindow: 256000,
9261
9415
  maxTokens: 80000,
9262
9416
  },
9417
+ "meituan/longcat-2.0": {
9418
+ id: "meituan/longcat-2.0",
9419
+ name: "Meituan: LongCat 2.0",
9420
+ api: "openai-completions",
9421
+ provider: "openrouter",
9422
+ baseUrl: "https://openrouter.ai/api/v1",
9423
+ reasoning: true,
9424
+ input: ["text"],
9425
+ cost: {
9426
+ input: 0.3,
9427
+ output: 1.2,
9428
+ cacheRead: 0.006,
9429
+ cacheWrite: 0,
9430
+ },
9431
+ contextWindow: 1048756,
9432
+ maxTokens: 262144,
9433
+ },
9263
9434
  "meta-llama/llama-3.1-70b-instruct": {
9264
9435
  id: "meta-llama/llama-3.1-70b-instruct",
9265
9436
  name: "Meta: Llama 3.1 70B Instruct",
@@ -9342,7 +9513,7 @@ export const MODELS = {
9342
9513
  cacheRead: 0,
9343
9514
  cacheWrite: 0,
9344
9515
  },
9345
- contextWindow: 10000000,
9516
+ contextWindow: 1310720,
9346
9517
  maxTokens: 16384,
9347
9518
  },
9348
9519
  "meta/muse-spark-1.1": {
@@ -9388,9 +9559,9 @@ export const MODELS = {
9388
9559
  reasoning: true,
9389
9560
  input: ["text"],
9390
9561
  cost: {
9391
- input: 0.3,
9392
- output: 1.2,
9393
- cacheRead: 0.03,
9562
+ input: 0.255,
9563
+ output: 1.02,
9564
+ cacheRead: 0,
9394
9565
  cacheWrite: 0,
9395
9566
  },
9396
9567
  contextWindow: 204800,
@@ -9716,7 +9887,7 @@ export const MODELS = {
9716
9887
  cacheRead: 0.01,
9717
9888
  cacheWrite: 0,
9718
9889
  },
9719
- contextWindow: 131072,
9890
+ contextWindow: 256000,
9720
9891
  maxTokens: 4096,
9721
9892
  },
9722
9893
  "mistralai/mixtral-8x22b-instruct": {
@@ -9847,9 +10018,9 @@ export const MODELS = {
9847
10018
  reasoning: true,
9848
10019
  input: ["text", "image"],
9849
10020
  cost: {
9850
- input: 0.85,
9851
- output: 3.8,
9852
- cacheRead: 0.16999999999999998,
10021
+ input: 0.82,
10022
+ output: 3.75,
10023
+ cacheRead: 0.16,
9853
10024
  cacheWrite: 0,
9854
10025
  },
9855
10026
  contextWindow: 262144,
@@ -9966,13 +10137,13 @@ export const MODELS = {
9966
10137
  reasoning: true,
9967
10138
  input: ["text"],
9968
10139
  cost: {
9969
- input: 0.08499999999999999,
9970
- output: 0.39999999999999997,
10140
+ input: 0.08,
10141
+ output: 0.44999999999999996,
9971
10142
  cacheRead: 0,
9972
10143
  cacheWrite: 0,
9973
10144
  },
9974
10145
  contextWindow: 1000000,
9975
- maxTokens: 16384,
10146
+ maxTokens: 4096,
9976
10147
  },
9977
10148
  "nvidia/nemotron-3-super-120b-a12b:free": {
9978
10149
  id: "nvidia/nemotron-3-super-120b-a12b:free",
@@ -9988,7 +10159,7 @@ export const MODELS = {
9988
10159
  cacheRead: 0,
9989
10160
  cacheWrite: 0,
9990
10161
  },
9991
- contextWindow: 1000000,
10162
+ contextWindow: 262144,
9992
10163
  maxTokens: 262144,
9993
10164
  },
9994
10165
  "nvidia/nemotron-3-ultra-550b-a55b": {
@@ -10000,13 +10171,13 @@ export const MODELS = {
10000
10171
  reasoning: true,
10001
10172
  input: ["text"],
10002
10173
  cost: {
10003
- input: 0.6,
10004
- output: 3.5999999999999996,
10005
- cacheRead: 0.19999999999999998,
10174
+ input: 0.5,
10175
+ output: 2.2,
10176
+ cacheRead: 0.09999999999999999,
10006
10177
  cacheWrite: 0,
10007
10178
  },
10008
- contextWindow: 1000000,
10009
- maxTokens: 4096,
10179
+ contextWindow: 512288,
10180
+ maxTokens: 16384,
10010
10181
  },
10011
10182
  "nvidia/nemotron-3-ultra-550b-a55b:free": {
10012
10183
  id: "nvidia/nemotron-3-ultra-550b-a55b:free",
@@ -11147,6 +11318,40 @@ export const MODELS = {
11147
11318
  contextWindow: 262144,
11148
11319
  maxTokens: 32768,
11149
11320
  },
11321
+ "poolside/laguna-s-2.1": {
11322
+ id: "poolside/laguna-s-2.1",
11323
+ name: "Poolside: Laguna S 2.1",
11324
+ api: "openai-completions",
11325
+ provider: "openrouter",
11326
+ baseUrl: "https://openrouter.ai/api/v1",
11327
+ reasoning: true,
11328
+ input: ["text"],
11329
+ cost: {
11330
+ input: 0.09999999999999999,
11331
+ output: 0.19999999999999998,
11332
+ cacheRead: 0.01,
11333
+ cacheWrite: 0,
11334
+ },
11335
+ contextWindow: 1048576,
11336
+ maxTokens: 131072,
11337
+ },
11338
+ "poolside/laguna-s-2.1:free": {
11339
+ id: "poolside/laguna-s-2.1:free",
11340
+ name: "Poolside: Laguna S 2.1 (free)",
11341
+ api: "openai-completions",
11342
+ provider: "openrouter",
11343
+ baseUrl: "https://openrouter.ai/api/v1",
11344
+ reasoning: true,
11345
+ input: ["text"],
11346
+ cost: {
11347
+ input: 0,
11348
+ output: 0,
11349
+ cacheRead: 0,
11350
+ cacheWrite: 0,
11351
+ },
11352
+ contextWindow: 262144,
11353
+ maxTokens: 32768,
11354
+ },
11150
11355
  "poolside/laguna-xs-2.1": {
11151
11356
  id: "poolside/laguna-xs-2.1",
11152
11357
  name: "Poolside: Laguna XS 2.1",
@@ -11195,7 +11400,7 @@ export const MODELS = {
11195
11400
  cacheRead: 0,
11196
11401
  cacheWrite: 0,
11197
11402
  },
11198
- contextWindow: 131072,
11403
+ contextWindow: 32768,
11199
11404
  maxTokens: 16384,
11200
11405
  },
11201
11406
  "qwen/qwen-2.5-7b-instruct": {
@@ -11212,7 +11417,7 @@ export const MODELS = {
11212
11417
  cacheRead: 0,
11213
11418
  cacheWrite: 0,
11214
11419
  },
11215
- contextWindow: 131072,
11420
+ contextWindow: 32768,
11216
11421
  maxTokens: 32768,
11217
11422
  },
11218
11423
  "qwen/qwen-plus": {
@@ -11275,13 +11480,13 @@ export const MODELS = {
11275
11480
  reasoning: true,
11276
11481
  input: ["text"],
11277
11482
  cost: {
11278
- input: 0.12,
11279
- output: 0.24,
11483
+ input: 0.22749999999999998,
11484
+ output: 0.9099999999999999,
11280
11485
  cacheRead: 0,
11281
11486
  cacheWrite: 0,
11282
11487
  },
11283
- contextWindow: 131702,
11284
- maxTokens: 16384,
11488
+ contextWindow: 131072,
11489
+ maxTokens: 8192,
11285
11490
  },
11286
11491
  "qwen/qwen3-235b-a22b": {
11287
11492
  id: "qwen/qwen3-235b-a22b",
@@ -11326,13 +11531,13 @@ export const MODELS = {
11326
11531
  reasoning: true,
11327
11532
  input: ["text"],
11328
11533
  cost: {
11329
- input: 0.14950000000000002,
11330
- output: 1.495,
11534
+ input: 0.3,
11535
+ output: 3,
11331
11536
  cacheRead: 0,
11332
11537
  cacheWrite: 0,
11333
11538
  },
11334
11539
  contextWindow: 262144,
11335
- maxTokens: 4096,
11540
+ maxTokens: 32768,
11336
11541
  },
11337
11542
  "qwen/qwen3-30b-a3b": {
11338
11543
  id: "qwen/qwen3-30b-a3b",
@@ -11382,7 +11587,7 @@ export const MODELS = {
11382
11587
  cacheRead: 0,
11383
11588
  cacheWrite: 0,
11384
11589
  },
11385
- contextWindow: 131072,
11590
+ contextWindow: 81920,
11386
11591
  maxTokens: 32768,
11387
11592
  },
11388
11593
  "qwen/qwen3-32b": {
@@ -11433,7 +11638,7 @@ export const MODELS = {
11433
11638
  cacheRead: 0.09999999999999999,
11434
11639
  cacheWrite: 0,
11435
11640
  },
11436
- contextWindow: 1048576,
11641
+ contextWindow: 262144,
11437
11642
  maxTokens: 65536,
11438
11643
  },
11439
11644
  "qwen/qwen3-coder-30b-a3b-instruct": {
@@ -11450,7 +11655,7 @@ export const MODELS = {
11450
11655
  cacheRead: 0,
11451
11656
  cacheWrite: 0,
11452
11657
  },
11453
- contextWindow: 160000,
11658
+ contextWindow: 262144,
11454
11659
  maxTokens: 32768,
11455
11660
  },
11456
11661
  "qwen/qwen3-coder-flash": {
@@ -11547,9 +11752,9 @@ export const MODELS = {
11547
11752
  reasoning: false,
11548
11753
  input: ["text"],
11549
11754
  cost: {
11550
- input: 0.09999999999999999,
11551
- output: 1.1,
11552
- cacheRead: 0.07,
11755
+ input: 0.15,
11756
+ output: 1.2,
11757
+ cacheRead: 0,
11553
11758
  cacheWrite: 0,
11554
11759
  },
11555
11760
  contextWindow: 262144,
@@ -11586,7 +11791,7 @@ export const MODELS = {
11586
11791
  cacheRead: 0.09999999999999999,
11587
11792
  cacheWrite: 0,
11588
11793
  },
11589
- contextWindow: 131072,
11794
+ contextWindow: 262144,
11590
11795
  maxTokens: 32768,
11591
11796
  },
11592
11797
  "qwen/qwen3-vl-235b-a22b-thinking": {
@@ -11615,13 +11820,13 @@ export const MODELS = {
11615
11820
  reasoning: false,
11616
11821
  input: ["text", "image"],
11617
11822
  cost: {
11618
- input: 0.13,
11619
- output: 0.52,
11823
+ input: 0.15,
11824
+ output: 0.6,
11620
11825
  cacheRead: 0,
11621
11826
  cacheWrite: 0,
11622
11827
  },
11623
11828
  contextWindow: 262144,
11624
- maxTokens: 32768,
11829
+ maxTokens: 16384,
11625
11830
  },
11626
11831
  "qwen/qwen3-vl-30b-a3b-thinking": {
11627
11832
  id: "qwen/qwen3-vl-30b-a3b-thinking",
@@ -11637,7 +11842,7 @@ export const MODELS = {
11637
11842
  cacheRead: 0,
11638
11843
  cacheWrite: 0,
11639
11844
  },
11640
- contextWindow: 131072,
11845
+ contextWindow: 262144,
11641
11846
  maxTokens: 32768,
11642
11847
  },
11643
11848
  "qwen/qwen3-vl-32b-instruct": {
@@ -11654,7 +11859,7 @@ export const MODELS = {
11654
11859
  cacheRead: 0,
11655
11860
  cacheWrite: 0,
11656
11861
  },
11657
- contextWindow: 262144,
11862
+ contextWindow: 131072,
11658
11863
  maxTokens: 32768,
11659
11864
  },
11660
11865
  "qwen/qwen3-vl-8b-instruct": {
@@ -11671,7 +11876,7 @@ export const MODELS = {
11671
11876
  cacheRead: 0,
11672
11877
  cacheWrite: 0,
11673
11878
  },
11674
- contextWindow: 256000,
11879
+ contextWindow: 262144,
11675
11880
  maxTokens: 32768,
11676
11881
  },
11677
11882
  "qwen/qwen3-vl-8b-thinking": {
@@ -11688,7 +11893,7 @@ export const MODELS = {
11688
11893
  cacheRead: 0,
11689
11894
  cacheWrite: 0,
11690
11895
  },
11691
- contextWindow: 256000,
11896
+ contextWindow: 131072,
11692
11897
  maxTokens: 32768,
11693
11898
  },
11694
11899
  "qwen/qwen3.5-122b-a10b": {
@@ -11717,13 +11922,13 @@ export const MODELS = {
11717
11922
  reasoning: true,
11718
11923
  input: ["text", "image"],
11719
11924
  cost: {
11720
- input: 0.26,
11721
- output: 2.6,
11925
+ input: 0.195,
11926
+ output: 1.56,
11722
11927
  cacheRead: 0,
11723
11928
  cacheWrite: 0,
11724
11929
  },
11725
11930
  contextWindow: 262144,
11726
- maxTokens: 81920,
11931
+ maxTokens: 65536,
11727
11932
  },
11728
11933
  "qwen/qwen3.5-35b-a3b": {
11729
11934
  id: "qwen/qwen3.5-35b-a3b",
@@ -11836,13 +12041,13 @@ export const MODELS = {
11836
12041
  reasoning: true,
11837
12042
  input: ["text", "image"],
11838
12043
  cost: {
11839
- input: 0.44999999999999996,
11840
- output: 2.7,
11841
- cacheRead: 0,
12044
+ input: 0.6,
12045
+ output: 3.5999999999999996,
12046
+ cacheRead: 0.12,
11842
12047
  cacheWrite: 0,
11843
12048
  },
11844
12049
  contextWindow: 262144,
11845
- maxTokens: 65536,
12050
+ maxTokens: 262144,
11846
12051
  },
11847
12052
  "qwen/qwen3.6-35b-a3b": {
11848
12053
  id: "qwen/qwen3.6-35b-a3b",
@@ -12045,7 +12250,7 @@ export const MODELS = {
12045
12250
  cacheRead: 0.04,
12046
12251
  cacheWrite: 0,
12047
12252
  },
12048
- contextWindow: 256000,
12253
+ contextWindow: 262144,
12049
12254
  maxTokens: 256000,
12050
12255
  },
12051
12256
  "tencent/hy3": {
@@ -12057,13 +12262,13 @@ export const MODELS = {
12057
12262
  reasoning: true,
12058
12263
  input: ["text"],
12059
12264
  cost: {
12060
- input: 0.19999999999999998,
12061
- output: 0.7999999999999999,
12062
- cacheRead: 0.049999999999999996,
12265
+ input: 0.14,
12266
+ output: 0.58,
12267
+ cacheRead: 0.035,
12063
12268
  cacheWrite: 0,
12064
12269
  },
12065
12270
  contextWindow: 262144,
12066
- maxTokens: 131072,
12271
+ maxTokens: 262144,
12067
12272
  },
12068
12273
  "tencent/hy3-preview": {
12069
12274
  id: "tencent/hy3-preview",
@@ -12082,23 +12287,6 @@ export const MODELS = {
12082
12287
  contextWindow: 262144,
12083
12288
  maxTokens: 4096,
12084
12289
  },
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
12290
  "thedrummer/unslopnemo-12b": {
12103
12291
  id: "thedrummer/unslopnemo-12b",
12104
12292
  name: "TheDrummer: UnslopNemo 12B",
@@ -12232,7 +12420,7 @@ export const MODELS = {
12232
12420
  cacheRead: 0.0028,
12233
12421
  cacheWrite: 0,
12234
12422
  },
12235
- contextWindow: 1048576,
12423
+ contextWindow: 1050000,
12236
12424
  maxTokens: 131072,
12237
12425
  },
12238
12426
  "xiaomi/mimo-v2.5-pro": {
@@ -12249,7 +12437,7 @@ export const MODELS = {
12249
12437
  cacheRead: 0.0036,
12250
12438
  cacheWrite: 0,
12251
12439
  },
12252
- contextWindow: 1048576,
12440
+ contextWindow: 1050000,
12253
12441
  maxTokens: 131072,
12254
12442
  },
12255
12443
  "z-ai/glm-4.5": {
@@ -12317,7 +12505,7 @@ export const MODELS = {
12317
12505
  cacheRead: 0.09999999999999999,
12318
12506
  cacheWrite: 0,
12319
12507
  },
12320
- contextWindow: 202752,
12508
+ contextWindow: 204800,
12321
12509
  maxTokens: 131072,
12322
12510
  },
12323
12511
  "z-ai/glm-4.6v": {
@@ -12351,7 +12539,7 @@ export const MODELS = {
12351
12539
  cacheRead: 0.08,
12352
12540
  cacheWrite: 0,
12353
12541
  },
12354
- contextWindow: 202752,
12542
+ contextWindow: 204800,
12355
12543
  maxTokens: 131072,
12356
12544
  },
12357
12545
  "z-ai/glm-4.7-flash": {
@@ -12363,13 +12551,13 @@ export const MODELS = {
12363
12551
  reasoning: true,
12364
12552
  input: ["text"],
12365
12553
  cost: {
12366
- input: 0.060500000000000005,
12554
+ input: 0.06,
12367
12555
  output: 0.39999999999999997,
12368
- cacheRead: 0,
12556
+ cacheRead: 0.01,
12369
12557
  cacheWrite: 0,
12370
12558
  },
12371
- contextWindow: 200000,
12372
- maxTokens: 131072,
12559
+ contextWindow: 202752,
12560
+ maxTokens: 16384,
12373
12561
  },
12374
12562
  "z-ai/glm-5": {
12375
12563
  id: "z-ai/glm-5",
@@ -12381,12 +12569,12 @@ export const MODELS = {
12381
12569
  input: ["text"],
12382
12570
  cost: {
12383
12571
  input: 0.95,
12384
- output: 3.15,
12385
- cacheRead: 0.19,
12572
+ output: 2.5500000000000003,
12573
+ cacheRead: 0.19999999999999998,
12386
12574
  cacheWrite: 0,
12387
12575
  },
12388
- contextWindow: 202752,
12389
- maxTokens: 202752,
12576
+ contextWindow: 204800,
12577
+ maxTokens: 131072,
12390
12578
  },
12391
12579
  "z-ai/glm-5-turbo": {
12392
12580
  id: "z-ai/glm-5-turbo",
@@ -12419,7 +12607,7 @@ export const MODELS = {
12419
12607
  cacheRead: 0.1794,
12420
12608
  cacheWrite: 0,
12421
12609
  },
12422
- contextWindow: 202752,
12610
+ contextWindow: 204800,
12423
12611
  maxTokens: 128000,
12424
12612
  },
12425
12613
  "z-ai/glm-5.2": {
@@ -12431,9 +12619,9 @@ export const MODELS = {
12431
12619
  reasoning: true,
12432
12620
  input: ["text"],
12433
12621
  cost: {
12434
- input: 0.252,
12435
- output: 0.792,
12436
- cacheRead: 0.0468,
12622
+ input: 0.8078000000000001,
12623
+ output: 2.5388,
12624
+ cacheRead: 0.15002,
12437
12625
  cacheWrite: 0,
12438
12626
  },
12439
12627
  contextWindow: 1048576,
@@ -12534,7 +12722,7 @@ export const MODELS = {
12534
12722
  input: ["text", "image"],
12535
12723
  cost: {
12536
12724
  input: 1.5,
12537
- output: 9,
12725
+ output: 7.5,
12538
12726
  cacheRead: 0.15,
12539
12727
  cacheWrite: 0.08333333333333334,
12540
12728
  },
@@ -13733,6 +13921,40 @@ export const MODELS = {
13733
13921
  contextWindow: 1000000,
13734
13922
  maxTokens: 64000,
13735
13923
  },
13924
+ "google/gemini-3.5-flash-lite": {
13925
+ id: "google/gemini-3.5-flash-lite",
13926
+ name: "Gemini 3.5 Flash Lite",
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: 0.3,
13934
+ output: 2.5,
13935
+ cacheRead: 0.03,
13936
+ cacheWrite: 0,
13937
+ },
13938
+ contextWindow: 1000000,
13939
+ maxTokens: 65000,
13940
+ },
13941
+ "google/gemini-3.6-flash": {
13942
+ id: "google/gemini-3.6-flash",
13943
+ name: "Gemini 3.6 Flash",
13944
+ api: "anthropic-messages",
13945
+ provider: "vercel-ai-gateway",
13946
+ baseUrl: "https://ai-gateway.vercel.sh",
13947
+ reasoning: true,
13948
+ input: ["text", "image"],
13949
+ cost: {
13950
+ input: 1.5,
13951
+ output: 7.5,
13952
+ cacheRead: 0.15,
13953
+ cacheWrite: 0,
13954
+ },
13955
+ contextWindow: 1000000,
13956
+ maxTokens: 64000,
13957
+ },
13736
13958
  "google/gemma-4-26b-a4b-it": {
13737
13959
  id: "google/gemma-4-26b-a4b-it",
13738
13960
  name: "Gemma 4 26B A4B IT",
@@ -13801,6 +14023,23 @@ export const MODELS = {
13801
14023
  contextWindow: 32000,
13802
14024
  maxTokens: 16384,
13803
14025
  },
14026
+ "inclusionai/ling-3.0-flash-free": {
14027
+ id: "inclusionai/ling-3.0-flash-free",
14028
+ name: "Ling 3.0 Flash",
14029
+ api: "anthropic-messages",
14030
+ provider: "vercel-ai-gateway",
14031
+ baseUrl: "https://ai-gateway.vercel.sh",
14032
+ reasoning: true,
14033
+ input: ["text"],
14034
+ cost: {
14035
+ input: 0,
14036
+ output: 0,
14037
+ cacheRead: 0,
14038
+ cacheWrite: 0,
14039
+ },
14040
+ contextWindow: 256000,
14041
+ maxTokens: 256000,
14042
+ },
13804
14043
  "interfaze/interfaze-beta": {
13805
14044
  id: "interfaze/interfaze-beta",
13806
14045
  name: "Interfaze Beta",
@@ -15280,6 +15519,40 @@ export const MODELS = {
15280
15519
  contextWindow: 200000,
15281
15520
  maxTokens: 100000,
15282
15521
  },
15522
+ "poolside/laguna-s-2.1": {
15523
+ id: "poolside/laguna-s-2.1",
15524
+ name: "Laguna S 2.1",
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: 0.09999999999999999,
15532
+ output: 0.19999999999999998,
15533
+ cacheRead: 0.01,
15534
+ cacheWrite: 0,
15535
+ },
15536
+ contextWindow: 1000000,
15537
+ maxTokens: 131072,
15538
+ },
15539
+ "poolside/laguna-s-2.1-free": {
15540
+ id: "poolside/laguna-s-2.1-free",
15541
+ name: "Laguna S 2.1 Free",
15542
+ api: "anthropic-messages",
15543
+ provider: "vercel-ai-gateway",
15544
+ baseUrl: "https://ai-gateway.vercel.sh",
15545
+ reasoning: true,
15546
+ input: ["text"],
15547
+ cost: {
15548
+ input: 0,
15549
+ output: 0,
15550
+ cacheRead: 0,
15551
+ cacheWrite: 0,
15552
+ },
15553
+ contextWindow: 256000,
15554
+ maxTokens: 32768,
15555
+ },
15283
15556
  "sakana/fugu-ultra": {
15284
15557
  id: "sakana/fugu-ultra",
15285
15558
  name: "Fugu Ultra",
@@ -15331,6 +15604,23 @@ export const MODELS = {
15331
15604
  contextWindow: 256000,
15332
15605
  maxTokens: 256000,
15333
15606
  },
15607
+ "tencent/hy3": {
15608
+ id: "tencent/hy3",
15609
+ name: "Hy3",
15610
+ api: "anthropic-messages",
15611
+ provider: "vercel-ai-gateway",
15612
+ baseUrl: "https://ai-gateway.vercel.sh",
15613
+ reasoning: true,
15614
+ input: ["text"],
15615
+ cost: {
15616
+ input: 0.14,
15617
+ output: 0.58,
15618
+ cacheRead: 0.035,
15619
+ cacheWrite: 0,
15620
+ },
15621
+ contextWindow: 262144,
15622
+ maxTokens: 262144,
15623
+ },
15334
15624
  "thinkingmachines/inkling": {
15335
15625
  id: "thinkingmachines/inkling",
15336
15626
  name: "Inkling",
@@ -15512,7 +15802,7 @@ export const MODELS = {
15512
15802
  cost: {
15513
15803
  input: 2,
15514
15804
  output: 6,
15515
- cacheRead: 0.5,
15805
+ cacheRead: 0.3,
15516
15806
  cacheWrite: 0,
15517
15807
  },
15518
15808
  contextWindow: 500000,