@dreb/ai 2.57.0 → 2.57.1

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.
@@ -3175,6 +3175,25 @@ export const MODELS = {
3175
3175
  contextWindow: 1000000,
3176
3176
  maxTokens: 64000,
3177
3177
  },
3178
+ "gemini-3.7-flash": {
3179
+ id: "gemini-3.7-flash",
3180
+ name: "Gemini 3.7 Flash",
3181
+ api: "openai-completions",
3182
+ provider: "github-copilot",
3183
+ baseUrl: "https://api.individual.githubcopilot.com",
3184
+ 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" },
3185
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
3186
+ reasoning: true,
3187
+ input: ["text", "image"],
3188
+ cost: {
3189
+ input: 0.75,
3190
+ output: 3.75,
3191
+ cacheRead: 0.075,
3192
+ cacheWrite: 0,
3193
+ },
3194
+ contextWindow: 1000000,
3195
+ maxTokens: 64000,
3196
+ },
3178
3197
  "gpt-4.1": {
3179
3198
  id: "gpt-4.1",
3180
3199
  name: "GPT-4.1",
@@ -3411,6 +3430,25 @@ export const MODELS = {
3411
3430
  contextWindow: 500000,
3412
3431
  maxTokens: 128000,
3413
3432
  },
3433
+ "grok-4.6": {
3434
+ id: "grok-4.6",
3435
+ name: "Grok 4.6",
3436
+ api: "openai-completions",
3437
+ provider: "github-copilot",
3438
+ baseUrl: "https://api.individual.githubcopilot.com",
3439
+ 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" },
3440
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
3441
+ reasoning: true,
3442
+ input: ["text", "image"],
3443
+ cost: {
3444
+ input: 2,
3445
+ output: 6,
3446
+ cacheRead: 0.5,
3447
+ cacheWrite: 0,
3448
+ },
3449
+ contextWindow: 500000,
3450
+ maxTokens: 128000,
3451
+ },
3414
3452
  "kimi-k2.7-code": {
3415
3453
  id: "kimi-k2.7-code",
3416
3454
  name: "Kimi K2.7 Code",
@@ -4524,6 +4562,24 @@ export const MODELS = {
4524
4562
  contextWindow: 524288,
4525
4563
  maxTokens: 128000,
4526
4564
  },
4565
+ "Qwen/Qwen2.5-Coder-32B-Instruct": {
4566
+ id: "Qwen/Qwen2.5-Coder-32B-Instruct",
4567
+ name: "Qwen2.5-Coder-32B-Instruct",
4568
+ api: "openai-completions",
4569
+ provider: "huggingface",
4570
+ baseUrl: "https://router.huggingface.co/v1",
4571
+ compat: { "supportsDeveloperRole": false },
4572
+ reasoning: false,
4573
+ input: ["text"],
4574
+ cost: {
4575
+ input: 0.06,
4576
+ output: 0.2,
4577
+ cacheRead: 0,
4578
+ cacheWrite: 0,
4579
+ },
4580
+ contextWindow: 131072,
4581
+ maxTokens: 8192,
4582
+ },
4527
4583
  "Qwen/Qwen3-235B-A22B": {
4528
4584
  id: "Qwen/Qwen3-235B-A22B",
4529
4585
  name: "Qwen3 235B-A22B",
@@ -4578,6 +4634,24 @@ export const MODELS = {
4578
4634
  contextWindow: 262144,
4579
4635
  maxTokens: 131072,
4580
4636
  },
4637
+ "Qwen/Qwen3-30B-A3B": {
4638
+ id: "Qwen/Qwen3-30B-A3B",
4639
+ name: "Qwen3 30B A3B",
4640
+ api: "openai-completions",
4641
+ provider: "huggingface",
4642
+ baseUrl: "https://router.huggingface.co/v1",
4643
+ compat: { "supportsDeveloperRole": false },
4644
+ reasoning: true,
4645
+ input: ["text"],
4646
+ cost: {
4647
+ input: 0.12,
4648
+ output: 0.5,
4649
+ cacheRead: 0,
4650
+ cacheWrite: 0,
4651
+ },
4652
+ contextWindow: 40960,
4653
+ maxTokens: 16384,
4654
+ },
4581
4655
  "Qwen/Qwen3-32B": {
4582
4656
  id: "Qwen/Qwen3-32B",
4583
4657
  name: "Qwen3 32B",
@@ -4920,6 +4994,24 @@ export const MODELS = {
4920
4994
  contextWindow: 64000,
4921
4995
  maxTokens: 8192,
4922
4996
  },
4997
+ "deepseek-ai/DeepSeek-V3-0324": {
4998
+ id: "deepseek-ai/DeepSeek-V3-0324",
4999
+ name: "DeepSeek V3 0324",
5000
+ api: "openai-completions",
5001
+ provider: "huggingface",
5002
+ baseUrl: "https://router.huggingface.co/v1",
5003
+ compat: { "supportsDeveloperRole": false },
5004
+ reasoning: false,
5005
+ input: ["text"],
5006
+ cost: {
5007
+ input: 0.27,
5008
+ output: 1.12,
5009
+ cacheRead: 0,
5010
+ cacheWrite: 0,
5011
+ },
5012
+ contextWindow: 163840,
5013
+ maxTokens: 163840,
5014
+ },
4923
5015
  "deepseek-ai/DeepSeek-V3.1": {
4924
5016
  id: "deepseek-ai/DeepSeek-V3.1",
4925
5017
  name: "DeepSeek-V3.1",
@@ -5010,6 +5102,24 @@ export const MODELS = {
5010
5102
  contextWindow: 1048576,
5011
5103
  maxTokens: 393216,
5012
5104
  },
5105
+ "deepseek-ai/DeepSeek-V4-Pro-0813": {
5106
+ id: "deepseek-ai/DeepSeek-V4-Pro-0813",
5107
+ name: "DeepSeek V4 Pro 0813",
5108
+ api: "openai-completions",
5109
+ provider: "huggingface",
5110
+ baseUrl: "https://router.huggingface.co/v1",
5111
+ compat: { "supportsDeveloperRole": false },
5112
+ reasoning: true,
5113
+ input: ["text"],
5114
+ cost: {
5115
+ input: 1.32,
5116
+ output: 3.96,
5117
+ cacheRead: 0,
5118
+ cacheWrite: 0,
5119
+ },
5120
+ contextWindow: 1000000,
5121
+ maxTokens: 384000,
5122
+ },
5013
5123
  "google/gemma-4-26B-A4B-it": {
5014
5124
  id: "google/gemma-4-26B-A4B-it",
5015
5125
  name: "Gemma 4 26B A4B IT",
@@ -5046,6 +5156,24 @@ export const MODELS = {
5046
5156
  contextWindow: 262144,
5047
5157
  maxTokens: 32768,
5048
5158
  },
5159
+ "meta-llama/Llama-3.1-8B-Instruct": {
5160
+ id: "meta-llama/Llama-3.1-8B-Instruct",
5161
+ name: "Llama-3.1-8B-Instruct",
5162
+ api: "openai-completions",
5163
+ provider: "huggingface",
5164
+ baseUrl: "https://router.huggingface.co/v1",
5165
+ compat: { "supportsDeveloperRole": false },
5166
+ reasoning: false,
5167
+ input: ["text"],
5168
+ cost: {
5169
+ input: 0.06,
5170
+ output: 0.06,
5171
+ cacheRead: 0,
5172
+ cacheWrite: 0,
5173
+ },
5174
+ contextWindow: 131072,
5175
+ maxTokens: 4096,
5176
+ },
5049
5177
  "meta-llama/Llama-3.3-70B-Instruct": {
5050
5178
  id: "meta-llama/Llama-3.3-70B-Instruct",
5051
5179
  name: "Llama-3.3-70B-Instruct",
@@ -8064,6 +8192,23 @@ export const MODELS = {
8064
8192
  contextWindow: 512000,
8065
8193
  maxTokens: 128000,
8066
8194
  },
8195
+ "muse-spark-1.2": {
8196
+ id: "muse-spark-1.2",
8197
+ name: "Muse Spark 1.2",
8198
+ api: "openai-responses",
8199
+ provider: "opencode",
8200
+ baseUrl: "https://opencode.ai/zen/v1",
8201
+ reasoning: true,
8202
+ input: ["text", "image"],
8203
+ cost: {
8204
+ input: 1.25,
8205
+ output: 4.25,
8206
+ cacheRead: 0.15,
8207
+ cacheWrite: 0,
8208
+ },
8209
+ contextWindow: 1048576,
8210
+ maxTokens: 131072,
8211
+ },
8067
8212
  "nemotron-3-ultra-free": {
8068
8213
  id: "nemotron-3-ultra-free",
8069
8214
  name: "Nemotron 3 Ultra Free",
@@ -8202,6 +8347,23 @@ export const MODELS = {
8202
8347
  contextWindow: 1000000,
8203
8348
  maxTokens: 131072,
8204
8349
  },
8350
+ "glm-5.3": {
8351
+ id: "glm-5.3",
8352
+ name: "GLM-5.3",
8353
+ api: "openai-completions",
8354
+ provider: "opencode-go",
8355
+ baseUrl: "https://opencode.ai/zen/go/v1",
8356
+ reasoning: true,
8357
+ input: ["text"],
8358
+ cost: {
8359
+ input: 1.4,
8360
+ output: 4.4,
8361
+ cacheRead: 0.26,
8362
+ cacheWrite: 0,
8363
+ },
8364
+ contextWindow: 1000000,
8365
+ maxTokens: 131072,
8366
+ },
8205
8367
  "gpt-5.6-luna": {
8206
8368
  id: "gpt-5.6-luna",
8207
8369
  name: "GPT-5.6 Luna (2x usage)",
@@ -9420,13 +9582,13 @@ export const MODELS = {
9420
9582
  reasoning: true,
9421
9583
  input: ["text"],
9422
9584
  cost: {
9423
- input: 0.14,
9424
- output: 0.28,
9425
- cacheRead: 0.028,
9585
+ input: 0.06426,
9586
+ output: 0.12852,
9587
+ cacheRead: 0.012852,
9426
9588
  cacheWrite: 0,
9427
9589
  },
9428
9590
  contextWindow: 1048576,
9429
- maxTokens: 393216,
9591
+ maxTokens: 384000,
9430
9592
  },
9431
9593
  "deepseek/deepseek-v4-flash-0731": {
9432
9594
  id: "deepseek/deepseek-v4-flash-0731",
@@ -9437,13 +9599,13 @@ export const MODELS = {
9437
9599
  reasoning: true,
9438
9600
  input: ["text"],
9439
9601
  cost: {
9440
- input: 0.08,
9441
- output: 0.18,
9442
- cacheRead: 0.016,
9602
+ input: 0.14,
9603
+ output: 0.28,
9604
+ cacheRead: 0.028,
9443
9605
  cacheWrite: 0,
9444
9606
  },
9445
9607
  contextWindow: 1048576,
9446
- maxTokens: 384000,
9608
+ maxTokens: 393216,
9447
9609
  },
9448
9610
  "deepseek/deepseek-v4-pro": {
9449
9611
  id: "deepseek/deepseek-v4-pro",
@@ -9479,6 +9641,23 @@ export const MODELS = {
9479
9641
  contextWindow: 1048576,
9480
9642
  maxTokens: 384000,
9481
9643
  },
9644
+ "dots-studio/dots-3-note-preview:free": {
9645
+ id: "dots-studio/dots-3-note-preview:free",
9646
+ name: "Dots Studio: Dots3-Note Preview (free)",
9647
+ api: "openai-completions",
9648
+ provider: "openrouter",
9649
+ baseUrl: "https://openrouter.ai/api/v1",
9650
+ reasoning: true,
9651
+ input: ["text", "image"],
9652
+ cost: {
9653
+ input: 0,
9654
+ output: 0,
9655
+ cacheRead: 0,
9656
+ cacheWrite: 0,
9657
+ },
9658
+ contextWindow: 512000,
9659
+ maxTokens: 512000,
9660
+ },
9482
9661
  "google/gemini-2.5-flash": {
9483
9662
  id: "google/gemini-2.5-flash",
9484
9663
  name: "Google: Gemini 2.5 Flash",
@@ -10174,7 +10353,7 @@ export const MODELS = {
10174
10353
  cacheWrite: 0,
10175
10354
  },
10176
10355
  contextWindow: 128000,
10177
- maxTokens: 32768,
10356
+ maxTokens: 8192,
10178
10357
  },
10179
10358
  "meituan/longcat-2.0": {
10180
10359
  id: "meituan/longcat-2.0",
@@ -10254,12 +10433,12 @@ export const MODELS = {
10254
10433
  input: ["text", "image"],
10255
10434
  cost: {
10256
10435
  input: 0.19999999999999998,
10257
- output: 0.696,
10436
+ output: 0.7999999999999999,
10258
10437
  cacheRead: 0,
10259
10438
  cacheWrite: 0,
10260
10439
  },
10261
10440
  contextWindow: 1048576,
10262
- maxTokens: 4096,
10441
+ maxTokens: 16384,
10263
10442
  },
10264
10443
  "meta-llama/llama-4-scout": {
10265
10444
  id: "meta-llama/llama-4-scout",
@@ -10797,9 +10976,9 @@ export const MODELS = {
10797
10976
  reasoning: true,
10798
10977
  input: ["text", "image"],
10799
10978
  cost: {
10800
- input: 0.5605,
10801
- output: 2.36,
10802
- cacheRead: 0.0944,
10979
+ input: 0.5415,
10980
+ output: 2.2800000000000002,
10981
+ cacheRead: 0.09119999999999999,
10803
10982
  cacheWrite: 0,
10804
10983
  },
10805
10984
  contextWindow: 262144,
@@ -10814,8 +10993,8 @@ export const MODELS = {
10814
10993
  reasoning: true,
10815
10994
  input: ["text", "image"],
10816
10995
  cost: {
10817
- input: 0.67,
10818
- output: 3.4,
10996
+ input: 0.71,
10997
+ output: 3.5,
10819
10998
  cacheRead: 0.15,
10820
10999
  cacheWrite: 0,
10821
11000
  },
@@ -12786,10 +12965,10 @@ export const MODELS = {
12786
12965
  reasoning: true,
12787
12966
  input: ["text"],
12788
12967
  cost: {
12789
- input: 0.39999999999999997,
12790
- output: 1.2,
12968
+ input: 0.26,
12969
+ output: 0.78,
12791
12970
  cacheRead: 0,
12792
- cacheWrite: 0.5,
12971
+ cacheWrite: 0,
12793
12972
  },
12794
12973
  contextWindow: 1000000,
12795
12974
  maxTokens: 32768,
@@ -13143,13 +13322,13 @@ export const MODELS = {
13143
13322
  reasoning: false,
13144
13323
  input: ["text", "image"],
13145
13324
  cost: {
13146
- input: 0.15,
13147
- output: 0.6,
13325
+ input: 0.13,
13326
+ output: 0.52,
13148
13327
  cacheRead: 0,
13149
13328
  cacheWrite: 0,
13150
13329
  },
13151
13330
  contextWindow: 262144,
13152
- maxTokens: 16384,
13331
+ maxTokens: 32768,
13153
13332
  },
13154
13333
  "qwen/qwen3-vl-30b-a3b-thinking": {
13155
13334
  id: "qwen/qwen3-vl-30b-a3b-thinking",
@@ -13262,13 +13441,13 @@ export const MODELS = {
13262
13441
  reasoning: true,
13263
13442
  input: ["text", "image"],
13264
13443
  cost: {
13265
- input: 0.25,
13266
- output: 1.25,
13267
- cacheRead: 0.25,
13444
+ input: 0.22499999999999998,
13445
+ output: 1.7999999999999998,
13446
+ cacheRead: 0.22499999999999998,
13268
13447
  cacheWrite: 0,
13269
13448
  },
13270
13449
  contextWindow: 262144,
13271
- maxTokens: 262144,
13450
+ maxTokens: 65536,
13272
13451
  },
13273
13452
  "qwen/qwen3.5-397b-a17b": {
13274
13453
  id: "qwen/qwen3.5-397b-a17b",
@@ -13279,13 +13458,13 @@ export const MODELS = {
13279
13458
  reasoning: true,
13280
13459
  input: ["text", "image"],
13281
13460
  cost: {
13282
- input: 0.5,
13283
- output: 3.5999999999999996,
13284
- cacheRead: 0.3,
13461
+ input: 0.39,
13462
+ output: 2.34,
13463
+ cacheRead: 0,
13285
13464
  cacheWrite: 0,
13286
13465
  },
13287
13466
  contextWindow: 262144,
13288
- maxTokens: 262144,
13467
+ maxTokens: 65536,
13289
13468
  },
13290
13469
  "qwen/qwen3.5-9b": {
13291
13470
  id: "qwen/qwen3.5-9b",
@@ -13505,9 +13684,26 @@ export const MODELS = {
13505
13684
  cacheRead: 0.25,
13506
13685
  cacheWrite: 0,
13507
13686
  },
13508
- contextWindow: 1000000,
13687
+ contextWindow: 1048576,
13509
13688
  maxTokens: 262144,
13510
13689
  },
13690
+ "qwen/qwen3.8-27b": {
13691
+ id: "qwen/qwen3.8-27b",
13692
+ name: "Qwen: Qwen3.8 27B",
13693
+ api: "openai-completions",
13694
+ provider: "openrouter",
13695
+ baseUrl: "https://openrouter.ai/api/v1",
13696
+ reasoning: true,
13697
+ input: ["text", "image"],
13698
+ cost: {
13699
+ input: 0.44999999999999996,
13700
+ output: 3.1999999999999997,
13701
+ cacheRead: 0,
13702
+ cacheWrite: 0,
13703
+ },
13704
+ contextWindow: 262144,
13705
+ maxTokens: 131072,
13706
+ },
13511
13707
  "qwen/qwen3.8-max": {
13512
13708
  id: "qwen/qwen3.8-max",
13513
13709
  name: "Qwen: Qwen3.8 Max",
@@ -13670,9 +13866,9 @@ export const MODELS = {
13670
13866
  reasoning: true,
13671
13867
  input: ["text"],
13672
13868
  cost: {
13673
- input: 0.063,
13674
- output: 0.21,
13675
- cacheRead: 0.020999999999999998,
13869
+ input: 0.18,
13870
+ output: 0.6,
13871
+ cacheRead: 0.06,
13676
13872
  cacheWrite: 0,
13677
13873
  },
13678
13874
  contextWindow: 262144,
@@ -13959,9 +14155,9 @@ export const MODELS = {
13959
14155
  reasoning: true,
13960
14156
  input: ["text"],
13961
14157
  cost: {
13962
- input: 0.5,
13963
- output: 2,
13964
- cacheRead: 0.09999999999999999,
14158
+ input: 0.55,
14159
+ output: 2.2,
14160
+ cacheRead: 0.11,
13965
14161
  cacheWrite: 0,
13966
14162
  },
13967
14163
  contextWindow: 204800,
@@ -14027,13 +14223,13 @@ export const MODELS = {
14027
14223
  reasoning: true,
14028
14224
  input: ["text"],
14029
14225
  cost: {
14030
- input: 0.95,
14031
- output: 2.5500000000000003,
14032
- cacheRead: 0.19999999999999998,
14226
+ input: 0.6,
14227
+ output: 1.92,
14228
+ cacheRead: 0.12,
14033
14229
  cacheWrite: 0,
14034
14230
  },
14035
14231
  contextWindow: 204800,
14036
- maxTokens: 131072,
14232
+ maxTokens: 128000,
14037
14233
  },
14038
14234
  "z-ai/glm-5-turbo": {
14039
14235
  id: "z-ai/glm-5-turbo",
@@ -14061,13 +14257,13 @@ export const MODELS = {
14061
14257
  reasoning: true,
14062
14258
  input: ["text"],
14063
14259
  cost: {
14064
- input: 0.952,
14065
- output: 2.992,
14066
- cacheRead: 0.17679999999999998,
14260
+ input: 0.966,
14261
+ output: 3.036,
14262
+ cacheRead: 0.1794,
14067
14263
  cacheWrite: 0,
14068
14264
  },
14069
14265
  contextWindow: 204800,
14070
- maxTokens: 131072,
14266
+ maxTokens: 128000,
14071
14267
  },
14072
14268
  "z-ai/glm-5.2": {
14073
14269
  id: "z-ai/glm-5.2",
@@ -14078,9 +14274,9 @@ export const MODELS = {
14078
14274
  reasoning: true,
14079
14275
  input: ["text"],
14080
14276
  cost: {
14081
- input: 0.392,
14082
- output: 1.232,
14083
- cacheRead: 0.0728,
14277
+ input: 0.46199999999999997,
14278
+ output: 1.452,
14279
+ cacheRead: 0.0858,
14084
14280
  cacheWrite: 0,
14085
14281
  },
14086
14282
  contextWindow: 1048576,
@@ -14197,9 +14393,9 @@ export const MODELS = {
14197
14393
  reasoning: true,
14198
14394
  input: ["text"],
14199
14395
  cost: {
14200
- input: 0.072,
14201
- output: 0.144,
14202
- cacheRead: 0.016,
14396
+ input: 0.0675,
14397
+ output: 0.135,
14398
+ cacheRead: 0.0135,
14203
14399
  cacheWrite: 0,
14204
14400
  },
14205
14401
  contextWindow: 1048576,
@@ -14248,13 +14444,13 @@ export const MODELS = {
14248
14444
  reasoning: true,
14249
14445
  input: ["text", "image"],
14250
14446
  cost: {
14251
- input: 2.4,
14252
- output: 12,
14253
- cacheRead: 0.24,
14447
+ input: 2.8,
14448
+ output: 14,
14449
+ cacheRead: 0.29,
14254
14450
  cacheWrite: 0,
14255
14451
  },
14256
14452
  contextWindow: 1048576,
14257
- maxTokens: 974842,
14453
+ maxTokens: 1048576,
14258
14454
  },
14259
14455
  "~openai/gpt-latest": {
14260
14456
  id: "~openai/gpt-latest",
@@ -15338,9 +15534,9 @@ export const MODELS = {
15338
15534
  reasoning: true,
15339
15535
  input: ["text"],
15340
15536
  cost: {
15341
- input: 0.435,
15342
- output: 0.87,
15343
- cacheRead: 0.0036,
15537
+ input: 1.32,
15538
+ output: 3.9600000000000004,
15539
+ cacheRead: 0.13199999999999998,
15344
15540
  cacheWrite: 0,
15345
15541
  },
15346
15542
  contextWindow: 1000000,
@@ -15601,23 +15797,6 @@ export const MODELS = {
15601
15797
  contextWindow: 256000,
15602
15798
  maxTokens: 32000,
15603
15799
  },
15604
- "inclusionai/ling-3.0-tiny-free": {
15605
- id: "inclusionai/ling-3.0-tiny-free",
15606
- name: "Ling 3.0 Tiny (Free)",
15607
- api: "anthropic-messages",
15608
- provider: "vercel-ai-gateway",
15609
- baseUrl: "https://ai-gateway.vercel.sh",
15610
- reasoning: true,
15611
- input: ["text"],
15612
- cost: {
15613
- input: 0,
15614
- output: 0,
15615
- cacheRead: 0,
15616
- cacheWrite: 0,
15617
- },
15618
- contextWindow: 256000,
15619
- maxTokens: 32000,
15620
- },
15621
15800
  "interfaze/interfaze-beta": {
15622
15801
  id: "interfaze/interfaze-beta",
15623
15802
  name: "Interfaze Beta",
@@ -17427,7 +17606,7 @@ export const MODELS = {
17427
17606
  provider: "vercel-ai-gateway",
17428
17607
  baseUrl: "https://ai-gateway.vercel.sh",
17429
17608
  reasoning: true,
17430
- input: ["text"],
17609
+ input: ["text", "image"],
17431
17610
  cost: {
17432
17611
  input: 2,
17433
17612
  output: 6,