@dreb/ai 2.55.6 → 2.57.0

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.
Files changed (5) hide show
  1. package/dist/models.generated.d.ts +278 -46
  2. package/dist/models.generated.d.ts.map +1 -1
  3. package/dist/models.generated.js +324 -101
  4. package/dist/models.generated.js.map +1 -1
  5. package/package.json +1 -1
package/dist/models.generated.js CHANGED
@@ -3468,6 +3468,25 @@ export const MODELS = {
3468
3468
  contextWindow: 256000,
3469
3469
  maxTokens: 128000,
3470
3470
  },
3471
+ "mai-code-1.1-flash": {
3472
+ id: "mai-code-1.1-flash",
3473
+ name: "MAI-Code-1.1-Flash",
3474
+ api: "openai-completions",
3475
+ provider: "github-copilot",
3476
+ baseUrl: "https://api.individual.githubcopilot.com",
3477
+ headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
3478
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
3479
+ reasoning: true,
3480
+ input: ["text", "image"],
3481
+ cost: {
3482
+ input: 0.2,
3483
+ output: 1.2,
3484
+ cacheRead: 0.02,
3485
+ cacheWrite: 0,
3486
+ },
3487
+ contextWindow: 256000,
3488
+ maxTokens: 128000,
3489
+ },
3471
3490
  },
3472
3491
  "google": {
3473
3492
  "deep-research-max-preview-04-2026": {
@@ -3742,6 +3761,23 @@ export const MODELS = {
3742
3761
  contextWindow: 1048576,
3743
3762
  maxTokens: 65536,
3744
3763
  },
3764
+ "gemini-3.7-flash": {
3765
+ id: "gemini-3.7-flash",
3766
+ name: "Gemini 3.7 Flash",
3767
+ api: "google-generative-ai",
3768
+ provider: "google",
3769
+ baseUrl: "https://generativelanguage.googleapis.com/v1beta",
3770
+ reasoning: true,
3771
+ input: ["text", "image"],
3772
+ cost: {
3773
+ input: 0.75,
3774
+ output: 3.75,
3775
+ cacheRead: 0.075,
3776
+ cacheWrite: 0,
3777
+ },
3778
+ contextWindow: 1048576,
3779
+ maxTokens: 65536,
3780
+ },
3745
3781
  "gemini-flash-latest": {
3746
3782
  id: "gemini-flash-latest",
3747
3783
  name: "Gemini Flash Latest",
@@ -7416,6 +7452,23 @@ export const MODELS = {
7416
7452
  contextWindow: 1048576,
7417
7453
  maxTokens: 65536,
7418
7454
  },
7455
+ "gemini-3.7-flash": {
7456
+ id: "gemini-3.7-flash",
7457
+ name: "Gemini 3.7 Flash",
7458
+ api: "google-generative-ai",
7459
+ provider: "opencode",
7460
+ baseUrl: "https://opencode.ai/zen/v1",
7461
+ reasoning: true,
7462
+ input: ["text", "image"],
7463
+ cost: {
7464
+ input: 1.5,
7465
+ output: 7.5,
7466
+ cacheRead: 0.15,
7467
+ cacheWrite: 0,
7468
+ },
7469
+ contextWindow: 1048576,
7470
+ maxTokens: 65536,
7471
+ },
7419
7472
  "glm-5": {
7420
7473
  id: "glm-5",
7421
7474
  name: "GLM-5",
@@ -7807,6 +7860,23 @@ export const MODELS = {
7807
7860
  contextWindow: 500000,
7808
7861
  maxTokens: 500000,
7809
7862
  },
7863
+ "grok-4.6": {
7864
+ id: "grok-4.6",
7865
+ name: "Grok 4.6",
7866
+ api: "openai-responses",
7867
+ provider: "opencode",
7868
+ baseUrl: "https://opencode.ai/zen/v1",
7869
+ reasoning: true,
7870
+ input: ["text", "image"],
7871
+ cost: {
7872
+ input: 2,
7873
+ output: 6,
7874
+ cacheRead: 0.5,
7875
+ cacheWrite: 0,
7876
+ },
7877
+ contextWindow: 500000,
7878
+ maxTokens: 500000,
7879
+ },
7810
7880
  "grok-build-0.1": {
7811
7881
  id: "grok-build-0.1",
7812
7882
  name: "Grok Build 0.1",
@@ -7926,40 +7996,6 @@ export const MODELS = {
7926
7996
  contextWindow: 256000,
7927
7997
  maxTokens: 32000,
7928
7998
  },
7929
- "ling-3.0-tiny-free": {
7930
- id: "ling-3.0-tiny-free",
7931
- name: "Ling-3.0-tiny Free",
7932
- api: "openai-completions",
7933
- provider: "opencode",
7934
- baseUrl: "https://opencode.ai/zen/v1",
7935
- reasoning: true,
7936
- input: ["text"],
7937
- cost: {
7938
- input: 0,
7939
- output: 0,
7940
- cacheRead: 0,
7941
- cacheWrite: 0,
7942
- },
7943
- contextWindow: 262144,
7944
- maxTokens: 32768,
7945
- },
7946
- "longcat-2.0-free": {
7947
- id: "longcat-2.0-free",
7948
- name: "LongCat-2.0 Free",
7949
- api: "openai-completions",
7950
- provider: "opencode",
7951
- baseUrl: "https://opencode.ai/zen/v1",
7952
- reasoning: true,
7953
- input: ["text"],
7954
- cost: {
7955
- input: 0,
7956
- output: 0,
7957
- cacheRead: 0,
7958
- cacheWrite: 0,
7959
- },
7960
- contextWindow: 1000000,
7961
- maxTokens: 131072,
7962
- },
7963
7999
  "mimo-v2.5-free": {
7964
8000
  id: "mimo-v2.5-free",
7965
8001
  name: "MiMo V2.5 Free",
@@ -8117,7 +8153,7 @@ export const MODELS = {
8117
8153
  },
8118
8154
  "deepseek-v4-pro": {
8119
8155
  id: "deepseek-v4-pro",
8120
- name: "DeepSeek V4 Pro",
8156
+ name: "DeepSeek V4 Pro (New)",
8121
8157
  api: "openai-completions",
8122
8158
  provider: "opencode-go",
8123
8159
  baseUrl: "https://opencode.ai/zen/go/v1",
@@ -9120,6 +9156,23 @@ export const MODELS = {
9120
9156
  contextWindow: 262144,
9121
9157
  maxTokens: 32768,
9122
9158
  },
9159
+ "bytedance-seed/seed-2-1-turbo": {
9160
+ id: "bytedance-seed/seed-2-1-turbo",
9161
+ name: "ByteDance Seed: Seed 2.1 Turbo",
9162
+ api: "openai-completions",
9163
+ provider: "openrouter",
9164
+ baseUrl: "https://openrouter.ai/api/v1",
9165
+ reasoning: true,
9166
+ input: ["text", "image"],
9167
+ cost: {
9168
+ input: 0.5,
9169
+ output: 2.5,
9170
+ cacheRead: 0,
9171
+ cacheWrite: 0,
9172
+ },
9173
+ contextWindow: 262144,
9174
+ maxTokens: 262144,
9175
+ },
9123
9176
  "bytedance-seed/seed-2.0-code": {
9124
9177
  id: "bytedance-seed/seed-2.0-code",
9125
9178
  name: "ByteDance Seed: Seed-2.0-Code",
@@ -9287,7 +9340,7 @@ export const MODELS = {
9287
9340
  cacheRead: 0,
9288
9341
  cacheWrite: 0,
9289
9342
  },
9290
- contextWindow: 163840,
9343
+ contextWindow: 64000,
9291
9344
  maxTokens: 16000,
9292
9345
  },
9293
9346
  "deepseek/deepseek-r1-0528": {
@@ -9317,8 +9370,8 @@ export const MODELS = {
9317
9370
  input: ["text"],
9318
9371
  cost: {
9319
9372
  input: 0.27,
9320
- output: 1,
9321
- cacheRead: 0.135,
9373
+ output: 0.95,
9374
+ cacheRead: 0.13,
9322
9375
  cacheWrite: 0,
9323
9376
  },
9324
9377
  contextWindow: 163840,
@@ -9401,14 +9454,31 @@ export const MODELS = {
9401
9454
  reasoning: true,
9402
9455
  input: ["text"],
9403
9456
  cost: {
9404
- input: 0.63168,
9405
- output: 1.26336,
9406
- cacheRead: 0.053298,
9457
+ input: 1.1680000000000001,
9458
+ output: 2.3360000000000003,
9459
+ cacheRead: 0.09855000000000001,
9407
9460
  cacheWrite: 0,
9408
9461
  },
9409
9462
  contextWindow: 1048576,
9410
9463
  maxTokens: 393216,
9411
9464
  },
9465
+ "deepseek/deepseek-v4-pro-0813": {
9466
+ id: "deepseek/deepseek-v4-pro-0813",
9467
+ name: "DeepSeek: DeepSeek V4 Pro 0813",
9468
+ api: "openai-completions",
9469
+ provider: "openrouter",
9470
+ baseUrl: "https://openrouter.ai/api/v1",
9471
+ reasoning: true,
9472
+ input: ["text"],
9473
+ cost: {
9474
+ input: 0.435,
9475
+ output: 0.87,
9476
+ cacheRead: 0.003625,
9477
+ cacheWrite: 0,
9478
+ },
9479
+ contextWindow: 1048576,
9480
+ maxTokens: 384000,
9481
+ },
9412
9482
  "google/gemini-2.5-flash": {
9413
9483
  id: "google/gemini-2.5-flash",
9414
9484
  name: "Google: Gemini 2.5 Flash",
@@ -9775,10 +9845,10 @@ export const MODELS = {
9775
9845
  reasoning: true,
9776
9846
  input: ["text", "image"],
9777
9847
  cost: {
9778
- input: 1.5,
9779
- output: 7.5,
9780
- cacheRead: 0.15,
9781
- cacheWrite: 0.0833333333333333,
9848
+ input: 0.75,
9849
+ output: 3.75,
9850
+ cacheRead: 0.075,
9851
+ cacheWrite: 0.0416666666666667,
9782
9852
  },
9783
9853
  contextWindow: 1048576,
9784
9854
  maxTokens: 65536,
@@ -9792,10 +9862,44 @@ export const MODELS = {
9792
9862
  reasoning: true,
9793
9863
  input: ["text", "image"],
9794
9864
  cost: {
9795
- input: 0.75,
9796
- output: 3.75,
9797
- cacheRead: 0.075,
9798
- cacheWrite: 0.0833333333333333,
9865
+ input: 0.375,
9866
+ output: 1.875,
9867
+ cacheRead: 0.0375,
9868
+ cacheWrite: 0.0416666666666667,
9869
+ },
9870
+ contextWindow: 1048576,
9871
+ maxTokens: 65536,
9872
+ },
9873
+ "google/gemini-3.7-flash": {
9874
+ id: "google/gemini-3.7-flash",
9875
+ name: "Google: Gemini 3.7 Flash",
9876
+ api: "openai-completions",
9877
+ provider: "openrouter",
9878
+ baseUrl: "https://openrouter.ai/api/v1",
9879
+ reasoning: true,
9880
+ input: ["text", "image"],
9881
+ cost: {
9882
+ input: 0.375,
9883
+ output: 1.875,
9884
+ cacheRead: 0.0375,
9885
+ cacheWrite: 0.0208333333333333,
9886
+ },
9887
+ contextWindow: 1048576,
9888
+ maxTokens: 65536,
9889
+ },
9890
+ "google/gemini-3.7-flash:batch": {
9891
+ id: "google/gemini-3.7-flash:batch",
9892
+ name: "Google: Gemini 3.7 Flash (batch)",
9893
+ api: "openai-completions",
9894
+ provider: "openrouter",
9895
+ baseUrl: "https://openrouter.ai/api/v1",
9896
+ reasoning: true,
9897
+ input: ["text", "image"],
9898
+ cost: {
9899
+ input: 0.1875,
9900
+ output: 0.9375,
9901
+ cacheRead: 0.01875,
9902
+ cacheWrite: 0.0208333333333333,
9799
9903
  },
9800
9904
  contextWindow: 1048576,
9801
9905
  maxTokens: 65536,
@@ -9987,23 +10091,6 @@ export const MODELS = {
9987
10091
  contextWindow: 262144,
9988
10092
  maxTokens: 32768,
9989
10093
  },
9990
- "inclusionai/ling-3.0-tiny:free": {
9991
- id: "inclusionai/ling-3.0-tiny:free",
9992
- name: "inclusionAI: Ling 3.0 Tiny (free)",
9993
- api: "openai-completions",
9994
- provider: "openrouter",
9995
- baseUrl: "https://openrouter.ai/api/v1",
9996
- reasoning: true,
9997
- input: ["text"],
9998
- cost: {
9999
- input: 0,
10000
- output: 0,
10001
- cacheRead: 0,
10002
- cacheWrite: 0,
10003
- },
10004
- contextWindow: 262144,
10005
- maxTokens: 32768,
10006
- },
10007
10094
  "inclusionai/ring-2.6-1t": {
10008
10095
  id: "inclusionai/ring-2.6-1t",
10009
10096
  name: "inclusionAI: Ring-2.6-1T",
@@ -10710,9 +10797,9 @@ export const MODELS = {
10710
10797
  reasoning: true,
10711
10798
  input: ["text", "image"],
10712
10799
  cost: {
10713
- input: 0.95,
10714
- output: 4,
10715
- cacheRead: 0.16,
10800
+ input: 0.5605,
10801
+ output: 2.36,
10802
+ cacheRead: 0.0944,
10716
10803
  cacheWrite: 0,
10717
10804
  },
10718
10805
  contextWindow: 262144,
@@ -10727,8 +10814,8 @@ export const MODELS = {
10727
10814
  reasoning: true,
10728
10815
  input: ["text", "image"],
10729
10816
  cost: {
10730
- input: 0.7,
10731
- output: 3.5,
10817
+ input: 0.67,
10818
+ output: 3.4,
10732
10819
  cacheRead: 0.15,
10733
10820
  cacheWrite: 0,
10734
10821
  },
@@ -10939,6 +11026,23 @@ export const MODELS = {
10939
11026
  contextWindow: 1000000,
10940
11027
  maxTokens: 65536,
10941
11028
  },
11029
+ "nvidia/nemotron-3.5-lightning": {
11030
+ id: "nvidia/nemotron-3.5-lightning",
11031
+ name: "NVIDIA: Nemotron 3.5 Lightning",
11032
+ api: "openai-completions",
11033
+ provider: "openrouter",
11034
+ baseUrl: "https://openrouter.ai/api/v1",
11035
+ reasoning: true,
11036
+ input: ["text"],
11037
+ cost: {
11038
+ input: 0.09999999999999999,
11039
+ output: 0.25,
11040
+ cacheRead: 0.049999999999999996,
11041
+ cacheWrite: 0,
11042
+ },
11043
+ contextWindow: 1000000,
11044
+ maxTokens: 262144,
11045
+ },
10942
11046
  "nvidia/nemotron-3.5-lightning:free": {
10943
11047
  id: "nvidia/nemotron-3.5-lightning:free",
10944
11048
  name: "NVIDIA: Nemotron 3.5 Lightning (free)",
@@ -12189,9 +12293,9 @@ export const MODELS = {
12189
12293
  reasoning: true,
12190
12294
  input: ["text"],
12191
12295
  cost: {
12192
- input: 0.037,
12296
+ input: 0.03,
12193
12297
  output: 0.16999999999999998,
12194
- cacheRead: 0,
12298
+ cacheRead: 0.03,
12195
12299
  cacheWrite: 0,
12196
12300
  },
12197
12301
  contextWindow: 131072,
@@ -12971,13 +13075,13 @@ export const MODELS = {
12971
13075
  reasoning: false,
12972
13076
  input: ["text"],
12973
13077
  cost: {
12974
- input: 0.09,
13078
+ input: 0.09999999999999999,
12975
13079
  output: 1.1,
12976
- cacheRead: 0,
13080
+ cacheRead: 0.07,
12977
13081
  cacheWrite: 0,
12978
13082
  },
12979
13083
  contextWindow: 262144,
12980
- maxTokens: 16384,
13084
+ maxTokens: 262144,
12981
13085
  },
12982
13086
  "qwen/qwen3-next-80b-a3b-thinking": {
12983
13087
  id: "qwen/qwen3-next-80b-a3b-thinking",
@@ -12994,7 +13098,7 @@ export const MODELS = {
12994
13098
  cacheWrite: 0,
12995
13099
  },
12996
13100
  contextWindow: 262144,
12997
- maxTokens: 262144,
13101
+ maxTokens: 32768,
12998
13102
  },
12999
13103
  "qwen/qwen3-vl-235b-a22b-instruct": {
13000
13104
  id: "qwen/qwen3-vl-235b-a22b-instruct",
@@ -13005,9 +13109,9 @@ export const MODELS = {
13005
13109
  reasoning: false,
13006
13110
  input: ["text", "image"],
13007
13111
  cost: {
13008
- input: 0.21,
13009
- output: 1.9,
13010
- cacheRead: 0.09999999999999999,
13112
+ input: 0.26,
13113
+ output: 1.04,
13114
+ cacheRead: 0,
13011
13115
  cacheWrite: 0,
13012
13116
  },
13013
13117
  contextWindow: 262144,
@@ -13158,9 +13262,9 @@ export const MODELS = {
13158
13262
  reasoning: true,
13159
13263
  input: ["text", "image"],
13160
13264
  cost: {
13161
- input: 0.14,
13162
- output: 1,
13163
- cacheRead: 0,
13265
+ input: 0.25,
13266
+ output: 1.25,
13267
+ cacheRead: 0.25,
13164
13268
  cacheWrite: 0,
13165
13269
  },
13166
13270
  contextWindow: 262144,
@@ -13387,6 +13491,23 @@ export const MODELS = {
13387
13491
  contextWindow: 1000000,
13388
13492
  maxTokens: 131072,
13389
13493
  },
13494
+ "qwen/qwen3.8-2.4t-a95b": {
13495
+ id: "qwen/qwen3.8-2.4t-a95b",
13496
+ name: "Qwen: Qwen3.8 2.4T A95B",
13497
+ api: "openai-completions",
13498
+ provider: "openrouter",
13499
+ baseUrl: "https://openrouter.ai/api/v1",
13500
+ reasoning: true,
13501
+ input: ["text"],
13502
+ cost: {
13503
+ input: 2,
13504
+ output: 6,
13505
+ cacheRead: 0.25,
13506
+ cacheWrite: 0,
13507
+ },
13508
+ contextWindow: 1000000,
13509
+ maxTokens: 262144,
13510
+ },
13390
13511
  "qwen/qwen3.8-max": {
13391
13512
  id: "qwen/qwen3.8-max",
13392
13513
  name: "Qwen: Qwen3.8 Max",
@@ -13710,6 +13831,23 @@ export const MODELS = {
13710
13831
  contextWindow: 500000,
13711
13832
  maxTokens: 4096,
13712
13833
  },
13834
+ "x-ai/grok-4.6": {
13835
+ id: "x-ai/grok-4.6",
13836
+ name: "SpaceXAI: Grok 4.6",
13837
+ api: "openai-completions",
13838
+ provider: "openrouter",
13839
+ baseUrl: "https://openrouter.ai/api/v1",
13840
+ reasoning: true,
13841
+ input: ["text", "image"],
13842
+ cost: {
13843
+ input: 2,
13844
+ output: 6,
13845
+ cacheRead: 0.5,
13846
+ cacheWrite: 0,
13847
+ },
13848
+ contextWindow: 500000,
13849
+ maxTokens: 4096,
13850
+ },
13713
13851
  "x-ai/grok-build-0.1": {
13714
13852
  id: "x-ai/grok-build-0.1",
13715
13853
  name: "SpaceXAI: Grok Build 0.1",
@@ -13923,9 +14061,9 @@ export const MODELS = {
13923
14061
  reasoning: true,
13924
14062
  input: ["text"],
13925
14063
  cost: {
13926
- input: 1.4,
13927
- output: 4.4,
13928
- cacheRead: 0.26,
14064
+ input: 0.952,
14065
+ output: 2.992,
14066
+ cacheRead: 0.17679999999999998,
13929
14067
  cacheWrite: 0,
13930
14068
  },
13931
14069
  contextWindow: 204800,
@@ -13940,13 +14078,13 @@ export const MODELS = {
13940
14078
  reasoning: true,
13941
14079
  input: ["text"],
13942
14080
  cost: {
13943
- input: 0.76,
13944
- output: 2.42,
13945
- cacheRead: 0.14,
14081
+ input: 0.392,
14082
+ output: 1.232,
14083
+ cacheRead: 0.0728,
13946
14084
  cacheWrite: 0,
13947
14085
  },
13948
14086
  contextWindow: 1048576,
13949
- maxTokens: 262144,
14087
+ maxTokens: 131072,
13950
14088
  },
13951
14089
  "z-ai/glm-5.2:batch": {
13952
14090
  id: "z-ai/glm-5.2:batch",
@@ -14061,7 +14199,7 @@ export const MODELS = {
14061
14199
  cost: {
14062
14200
  input: 0.072,
14063
14201
  output: 0.144,
14064
- cacheRead: 0.0144,
14202
+ cacheRead: 0.016,
14065
14203
  cacheWrite: 0,
14066
14204
  },
14067
14205
  contextWindow: 1048576,
@@ -14076,10 +14214,10 @@ export const MODELS = {
14076
14214
  reasoning: true,
14077
14215
  input: ["text", "image"],
14078
14216
  cost: {
14079
- input: 1.5,
14080
- output: 7.5,
14081
- cacheRead: 0.15,
14082
- cacheWrite: 0.0833333333333333,
14217
+ input: 0.375,
14218
+ output: 1.875,
14219
+ cacheRead: 0.0375,
14220
+ cacheWrite: 0.0208333333333333,
14083
14221
  },
14084
14222
  contextWindow: 1048576,
14085
14223
  maxTokens: 65536,
@@ -14110,13 +14248,13 @@ export const MODELS = {
14110
14248
  reasoning: true,
14111
14249
  input: ["text", "image"],
14112
14250
  cost: {
14113
- input: 2.8,
14114
- output: 14,
14115
- cacheRead: 0.29,
14251
+ input: 2.4,
14252
+ output: 12,
14253
+ cacheRead: 0.24,
14116
14254
  cacheWrite: 0,
14117
14255
  },
14118
14256
  contextWindow: 1048576,
14119
- maxTokens: 1048576,
14257
+ maxTokens: 974842,
14120
14258
  },
14121
14259
  "~openai/gpt-latest": {
14122
14260
  id: "~openai/gpt-latest",
@@ -14163,7 +14301,7 @@ export const MODELS = {
14163
14301
  cost: {
14164
14302
  input: 2,
14165
14303
  output: 6,
14166
- cacheRead: 0.3,
14304
+ cacheRead: 0.5,
14167
14305
  cacheWrite: 0,
14168
14306
  },
14169
14307
  contextWindow: 500000,
@@ -14596,6 +14734,23 @@ export const MODELS = {
14596
14734
  contextWindow: 1000000,
14597
14735
  maxTokens: 64000,
14598
14736
  },
14737
+ "alibaba/qwen3.8-2.4t-a95b": {
14738
+ id: "alibaba/qwen3.8-2.4t-a95b",
14739
+ name: "Qwen3.8 2.4T A95B",
14740
+ api: "anthropic-messages",
14741
+ provider: "vercel-ai-gateway",
14742
+ baseUrl: "https://ai-gateway.vercel.sh",
14743
+ reasoning: true,
14744
+ input: ["text"],
14745
+ cost: {
14746
+ input: 2,
14747
+ output: 6,
14748
+ cacheRead: 0.25,
14749
+ cacheWrite: 0,
14750
+ },
14751
+ contextWindow: 262144,
14752
+ maxTokens: 131072,
14753
+ },
14599
14754
  "alibaba/qwen3.8-max": {
14600
14755
  id: "alibaba/qwen3.8-max",
14601
14756
  name: "Qwen 3.8 Max",
@@ -15174,6 +15329,23 @@ export const MODELS = {
15174
15329
  contextWindow: 1048600,
15175
15330
  maxTokens: 1048600,
15176
15331
  },
15332
+ "deepseek/deepseek-v4-pro-0813": {
15333
+ id: "deepseek/deepseek-v4-pro-0813",
15334
+ name: "DeepSeek V4 Pro 0813",
15335
+ api: "anthropic-messages",
15336
+ provider: "vercel-ai-gateway",
15337
+ baseUrl: "https://ai-gateway.vercel.sh",
15338
+ reasoning: true,
15339
+ input: ["text"],
15340
+ cost: {
15341
+ input: 0.435,
15342
+ output: 0.87,
15343
+ cacheRead: 0.0036,
15344
+ cacheWrite: 0,
15345
+ },
15346
+ contextWindow: 1000000,
15347
+ maxTokens: 384000,
15348
+ },
15177
15349
  "google/gemini-2.5-flash": {
15178
15350
  id: "google/gemini-2.5-flash",
15179
15351
  name: "Gemini 2.5 Flash",
@@ -15327,6 +15499,23 @@ export const MODELS = {
15327
15499
  contextWindow: 1000000,
15328
15500
  maxTokens: 64000,
15329
15501
  },
15502
+ "google/gemini-3.7-flash": {
15503
+ id: "google/gemini-3.7-flash",
15504
+ name: "Gemini 3.7 Flash",
15505
+ api: "anthropic-messages",
15506
+ provider: "vercel-ai-gateway",
15507
+ baseUrl: "https://ai-gateway.vercel.sh",
15508
+ reasoning: true,
15509
+ input: ["text", "image"],
15510
+ cost: {
15511
+ input: 0.75,
15512
+ output: 3.75,
15513
+ cacheRead: 0.075,
15514
+ cacheWrite: 0,
15515
+ },
15516
+ contextWindow: 1000000,
15517
+ maxTokens: 65536,
15518
+ },
15330
15519
  "google/gemma-4-26b-a4b-it": {
15331
15520
  id: "google/gemma-4-26b-a4b-it",
15332
15521
  name: "Google Gemma 4 26B A4B",
@@ -15358,7 +15547,7 @@ export const MODELS = {
15358
15547
  cacheRead: 0,
15359
15548
  cacheWrite: 0,
15360
15549
  },
15361
- contextWindow: 256000,
15550
+ contextWindow: 262144,
15362
15551
  maxTokens: 131072,
15363
15552
  },
15364
15553
  "inception/mercury-2": {
@@ -17231,6 +17420,23 @@ export const MODELS = {
17231
17420
  contextWindow: 500000,
17232
17421
  maxTokens: 500000,
17233
17422
  },
17423
+ "xai/grok-4.6": {
17424
+ id: "xai/grok-4.6",
17425
+ name: "Grok 4.6",
17426
+ api: "anthropic-messages",
17427
+ provider: "vercel-ai-gateway",
17428
+ baseUrl: "https://ai-gateway.vercel.sh",
17429
+ reasoning: true,
17430
+ input: ["text"],
17431
+ cost: {
17432
+ input: 2,
17433
+ output: 6,
17434
+ cacheRead: 0.5,
17435
+ cacheWrite: 0,
17436
+ },
17437
+ contextWindow: 500000,
17438
+ maxTokens: 500000,
17439
+ },
17234
17440
  "xai/grok-build-0.1": {
17235
17441
  id: "xai/grok-build-0.1",
17236
17442
  name: "Grok Build 0.1",
@@ -17607,6 +17813,23 @@ export const MODELS = {
17607
17813
  contextWindow: 500000,
17608
17814
  maxTokens: 500000,
17609
17815
  },
17816
+ "grok-4.6": {
17817
+ id: "grok-4.6",
17818
+ name: "Grok 4.6",
17819
+ api: "openai-completions",
17820
+ provider: "xai",
17821
+ baseUrl: "https://api.x.ai/v1",
17822
+ reasoning: true,
17823
+ input: ["text", "image"],
17824
+ cost: {
17825
+ input: 2,
17826
+ output: 6,
17827
+ cacheRead: 0.5,
17828
+ cacheWrite: 0,
17829
+ },
17830
+ contextWindow: 500000,
17831
+ maxTokens: 500000,
17832
+ },
17610
17833
  "grok-build-0.1": {
17611
17834
  id: "grok-build-0.1",
17612
17835
  name: "Grok Build 0.1",