@dreb/ai 2.50.0 → 2.52.0

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.
@@ -3152,44 +3152,6 @@ export const MODELS = {
3152
3152
  contextWindow: 1000000,
3153
3153
  maxTokens: 128000,
3154
3154
  },
3155
- "gemini-2.5-pro": {
3156
- id: "gemini-2.5-pro",
3157
- name: "Gemini 2.5 Pro",
3158
- api: "openai-completions",
3159
- provider: "github-copilot",
3160
- baseUrl: "https://api.individual.githubcopilot.com",
3161
- 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" },
3162
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
3163
- reasoning: true,
3164
- input: ["text", "image"],
3165
- cost: {
3166
- input: 1.25,
3167
- output: 10,
3168
- cacheRead: 0.125,
3169
- cacheWrite: 0,
3170
- },
3171
- contextWindow: 128000,
3172
- maxTokens: 64000,
3173
- },
3174
- "gemini-3-flash-preview": {
3175
- id: "gemini-3-flash-preview",
3176
- name: "Gemini 3 Flash Preview",
3177
- api: "openai-completions",
3178
- provider: "github-copilot",
3179
- baseUrl: "https://api.individual.githubcopilot.com",
3180
- 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" },
3181
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
3182
- reasoning: true,
3183
- input: ["text", "image"],
3184
- cost: {
3185
- input: 0.5,
3186
- output: 3,
3187
- cacheRead: 0.05,
3188
- cacheWrite: 0,
3189
- },
3190
- contextWindow: 128000,
3191
- maxTokens: 64000,
3192
- },
3193
3155
  "gemini-3.1-pro-preview": {
3194
3156
  id: "gemini-3.1-pro-preview",
3195
3157
  name: "Gemini 3.1 Pro Preview",
@@ -3228,6 +3190,25 @@ export const MODELS = {
3228
3190
  contextWindow: 200000,
3229
3191
  maxTokens: 64000,
3230
3192
  },
3193
+ "gemini-3.6-flash": {
3194
+ id: "gemini-3.6-flash",
3195
+ name: "Gemini 3.6 Flash",
3196
+ api: "openai-completions",
3197
+ provider: "github-copilot",
3198
+ baseUrl: "https://api.individual.githubcopilot.com",
3199
+ 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" },
3200
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
3201
+ reasoning: true,
3202
+ input: ["text", "image"],
3203
+ cost: {
3204
+ input: 1.5,
3205
+ output: 7.5,
3206
+ cacheRead: 0.15,
3207
+ cacheWrite: 0,
3208
+ },
3209
+ contextWindow: 1000000,
3210
+ maxTokens: 64000,
3211
+ },
3231
3212
  "gpt-4.1": {
3232
3213
  id: "gpt-4.1",
3233
3214
  name: "GPT-4.1",
@@ -3401,10 +3382,10 @@ export const MODELS = {
3401
3382
  reasoning: true,
3402
3383
  input: ["text", "image"],
3403
3384
  cost: {
3404
- input: 1,
3405
- output: 6,
3406
- cacheRead: 0.1,
3407
- cacheWrite: 1.25,
3385
+ input: 0.2,
3386
+ output: 1.2,
3387
+ cacheRead: 0.02,
3388
+ cacheWrite: 0,
3408
3389
  },
3409
3390
  contextWindow: 1050000,
3410
3391
  maxTokens: 128000,
@@ -3437,14 +3418,33 @@ export const MODELS = {
3437
3418
  reasoning: true,
3438
3419
  input: ["text", "image"],
3439
3420
  cost: {
3440
- input: 2.5,
3441
- output: 15,
3442
- cacheRead: 0.25,
3443
- cacheWrite: 3.125,
3421
+ input: 2,
3422
+ output: 12,
3423
+ cacheRead: 0.2,
3424
+ cacheWrite: 0,
3444
3425
  },
3445
3426
  contextWindow: 1050000,
3446
3427
  maxTokens: 128000,
3447
3428
  },
3429
+ "grok-4.5": {
3430
+ id: "grok-4.5",
3431
+ name: "Grok 4.5",
3432
+ api: "openai-completions",
3433
+ provider: "github-copilot",
3434
+ baseUrl: "https://api.individual.githubcopilot.com",
3435
+ 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" },
3436
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
3437
+ reasoning: true,
3438
+ input: ["text", "image"],
3439
+ cost: {
3440
+ input: 2,
3441
+ output: 6,
3442
+ cacheRead: 0.5,
3443
+ cacheWrite: 0,
3444
+ },
3445
+ contextWindow: 500000,
3446
+ maxTokens: 128000,
3447
+ },
3448
3448
  "kimi-k2.7-code": {
3449
3449
  id: "kimi-k2.7-code",
3450
3450
  name: "Kimi K2.7 Code",
@@ -4967,6 +4967,24 @@ export const MODELS = {
4967
4967
  contextWindow: 1048576,
4968
4968
  maxTokens: 384000,
4969
4969
  },
4970
+ "deepseek-ai/DeepSeek-V4-Flash-0731": {
4971
+ id: "deepseek-ai/DeepSeek-V4-Flash-0731",
4972
+ name: "DeepSeek V4 Flash 0731",
4973
+ api: "openai-completions",
4974
+ provider: "huggingface",
4975
+ baseUrl: "https://router.huggingface.co/v1",
4976
+ compat: { "supportsDeveloperRole": false },
4977
+ reasoning: true,
4978
+ input: ["text"],
4979
+ cost: {
4980
+ input: 0.14,
4981
+ output: 0.28,
4982
+ cacheRead: 0,
4983
+ cacheWrite: 0,
4984
+ },
4985
+ contextWindow: 1048576,
4986
+ maxTokens: 384000,
4987
+ },
4970
4988
  "deepseek-ai/DeepSeek-V4-Pro": {
4971
4989
  id: "deepseek-ai/DeepSeek-V4-Pro",
4972
4990
  name: "DeepSeek V4 Pro",
@@ -8381,6 +8399,23 @@ export const MODELS = {
8381
8399
  contextWindow: 1000000,
8382
8400
  maxTokens: 65536,
8383
8401
  },
8402
+ "qwen3.8-max": {
8403
+ id: "qwen3.8-max",
8404
+ name: "Qwen3.8 Max",
8405
+ api: "anthropic-messages",
8406
+ provider: "opencode-go",
8407
+ baseUrl: "https://opencode.ai/zen/go",
8408
+ reasoning: true,
8409
+ input: ["text", "image"],
8410
+ cost: {
8411
+ input: 2,
8412
+ output: 6,
8413
+ cacheRead: 0.25,
8414
+ cacheWrite: 2.5,
8415
+ },
8416
+ contextWindow: 1000000,
8417
+ maxTokens: 131072,
8418
+ },
8384
8419
  },
8385
8420
  "openrouter": {
8386
8421
  "ai21/jamba-large-1.7": {
@@ -9133,7 +9168,7 @@ export const MODELS = {
9133
9168
  },
9134
9169
  "deepseek/deepseek-v4-flash": {
9135
9170
  id: "deepseek/deepseek-v4-flash",
9136
- name: "DeepSeek: DeepSeek V4 Flash",
9171
+ name: "DeepSeek: DeepSeek V4 Flash 0423",
9137
9172
  api: "openai-completions",
9138
9173
  provider: "openrouter",
9139
9174
  baseUrl: "https://openrouter.ai/api/v1",
@@ -9194,7 +9229,7 @@ export const MODELS = {
9194
9229
  input: 0.3,
9195
9230
  output: 2.5,
9196
9231
  cacheRead: 0.03,
9197
- cacheWrite: 0.08333333333333334,
9232
+ cacheWrite: 0.0833333333333333,
9198
9233
  },
9199
9234
  contextWindow: 1048576,
9200
9235
  maxTokens: 65535,
@@ -9211,7 +9246,7 @@ export const MODELS = {
9211
9246
  input: 0.09999999999999999,
9212
9247
  output: 0.39999999999999997,
9213
9248
  cacheRead: 0.01,
9214
- cacheWrite: 0.08333333333333334,
9249
+ cacheWrite: 0.0833333333333333,
9215
9250
  },
9216
9251
  contextWindow: 1048576,
9217
9252
  maxTokens: 65535,
@@ -9279,7 +9314,7 @@ export const MODELS = {
9279
9314
  input: 0.5,
9280
9315
  output: 3,
9281
9316
  cacheRead: 0.049999999999999996,
9282
- cacheWrite: 0.08333333333333334,
9317
+ cacheWrite: 0.0833333333333333,
9283
9318
  },
9284
9319
  contextWindow: 1048576,
9285
9320
  maxTokens: 65535,
@@ -9313,7 +9348,7 @@ export const MODELS = {
9313
9348
  input: 0.25,
9314
9349
  output: 1.5,
9315
9350
  cacheRead: 0.024999999999999998,
9316
- cacheWrite: 0.08333333333333334,
9351
+ cacheWrite: 0.0833333333333333,
9317
9352
  },
9318
9353
  contextWindow: 1048576,
9319
9354
  maxTokens: 65536,
@@ -9330,7 +9365,7 @@ export const MODELS = {
9330
9365
  input: 0.25,
9331
9366
  output: 1.5,
9332
9367
  cacheRead: 0.024999999999999998,
9333
- cacheWrite: 0.08333333333333334,
9368
+ cacheWrite: 0.0833333333333333,
9334
9369
  },
9335
9370
  contextWindow: 1048576,
9336
9371
  maxTokens: 65536,
@@ -9381,7 +9416,7 @@ export const MODELS = {
9381
9416
  input: 1.5,
9382
9417
  output: 9,
9383
9418
  cacheRead: 0.15,
9384
- cacheWrite: 0.08333333333333334,
9419
+ cacheWrite: 0.0833333333333333,
9385
9420
  },
9386
9421
  contextWindow: 1048576,
9387
9422
  maxTokens: 65536,
@@ -9398,7 +9433,7 @@ export const MODELS = {
9398
9433
  input: 0.3,
9399
9434
  output: 2.5,
9400
9435
  cacheRead: 0.03,
9401
- cacheWrite: 0.08333333333333334,
9436
+ cacheWrite: 0.0833333333333333,
9402
9437
  },
9403
9438
  contextWindow: 1048576,
9404
9439
  maxTokens: 65536,
@@ -9415,7 +9450,7 @@ export const MODELS = {
9415
9450
  input: 1.5,
9416
9451
  output: 7.5,
9417
9452
  cacheRead: 0.15,
9418
- cacheWrite: 0.08333333333333334,
9453
+ cacheWrite: 0.0833333333333333,
9419
9454
  },
9420
9455
  contextWindow: 1048576,
9421
9456
  maxTokens: 65536,
@@ -9735,13 +9770,13 @@ export const MODELS = {
9735
9770
  reasoning: false,
9736
9771
  input: ["text"],
9737
9772
  cost: {
9738
- input: 0.13,
9739
- output: 0.39999999999999997,
9773
+ input: 0.09999999999999999,
9774
+ output: 0.32,
9740
9775
  cacheRead: 0,
9741
9776
  cacheWrite: 0,
9742
9777
  },
9743
9778
  contextWindow: 131072,
9744
- maxTokens: 128000,
9779
+ maxTokens: 16384,
9745
9780
  },
9746
9781
  "meta-llama/llama-4-maverick": {
9747
9782
  id: "meta-llama/llama-4-maverick",
@@ -10245,9 +10280,9 @@ export const MODELS = {
10245
10280
  reasoning: true,
10246
10281
  input: ["text", "image"],
10247
10282
  cost: {
10248
- input: 0.6,
10249
- output: 3.41,
10250
- cacheRead: 0.19999999999999998,
10283
+ input: 0.589,
10284
+ output: 2.48,
10285
+ cacheRead: 0.0992,
10251
10286
  cacheWrite: 0,
10252
10287
  },
10253
10288
  contextWindow: 262144,
@@ -11096,9 +11131,9 @@ export const MODELS = {
11096
11131
  input: ["text", "image"],
11097
11132
  cost: {
11098
11133
  input: 0.09999999999999999,
11099
- output: 0.6000000000000001,
11134
+ output: 0.6,
11100
11135
  cacheRead: 0.01,
11101
- cacheWrite: 0.12500000000000003,
11136
+ cacheWrite: 0.125,
11102
11137
  },
11103
11138
  contextWindow: 1050000,
11104
11139
  maxTokens: 128000,
@@ -11146,7 +11181,7 @@ export const MODELS = {
11146
11181
  reasoning: true,
11147
11182
  input: ["text", "image"],
11148
11183
  cost: {
11149
- input: 1.0000000000000002,
11184
+ input: 1,
11150
11185
  output: 6,
11151
11186
  cacheRead: 0.09999999999999999,
11152
11187
  cacheWrite: 1.25,
@@ -11163,7 +11198,7 @@ export const MODELS = {
11163
11198
  reasoning: true,
11164
11199
  input: ["text", "image"],
11165
11200
  cost: {
11166
- input: 1.0000000000000002,
11201
+ input: 1,
11167
11202
  output: 6,
11168
11203
  cacheRead: 0.09999999999999999,
11169
11204
  cacheWrite: 1.25,
@@ -11656,13 +11691,13 @@ export const MODELS = {
11656
11691
  reasoning: false,
11657
11692
  input: ["text"],
11658
11693
  cost: {
11659
- input: 0.09,
11660
- output: 0.55,
11694
+ input: 0.14950000000000002,
11695
+ output: 0.5980000000000001,
11661
11696
  cacheRead: 0,
11662
11697
  cacheWrite: 0,
11663
11698
  },
11664
11699
  contextWindow: 262144,
11665
- maxTokens: 16384,
11700
+ maxTokens: 32768,
11666
11701
  },
11667
11702
  "qwen/qwen3-235b-a22b-thinking-2507": {
11668
11703
  id: "qwen/qwen3-235b-a22b-thinking-2507",
@@ -11793,12 +11828,12 @@ export const MODELS = {
11793
11828
  input: ["text"],
11794
11829
  cost: {
11795
11830
  input: 0.07,
11796
- output: 0.28,
11831
+ output: 0.27,
11797
11832
  cacheRead: 0,
11798
11833
  cacheWrite: 0,
11799
11834
  },
11800
11835
  contextWindow: 262144,
11801
- maxTokens: 262144,
11836
+ maxTokens: 32768,
11802
11837
  },
11803
11838
  "qwen/qwen3-coder-flash": {
11804
11839
  id: "qwen/qwen3-coder-flash",
@@ -11894,13 +11929,13 @@ export const MODELS = {
11894
11929
  reasoning: false,
11895
11930
  input: ["text"],
11896
11931
  cost: {
11897
- input: 0.09999999999999999,
11932
+ input: 0.09,
11898
11933
  output: 1.1,
11899
- cacheRead: 0.07,
11934
+ cacheRead: 0,
11900
11935
  cacheWrite: 0,
11901
11936
  },
11902
11937
  contextWindow: 262144,
11903
- maxTokens: 262144,
11938
+ maxTokens: 16384,
11904
11939
  },
11905
11940
  "qwen/qwen3-next-80b-a3b-thinking": {
11906
11941
  id: "qwen/qwen3-next-80b-a3b-thinking",
@@ -11917,7 +11952,7 @@ export const MODELS = {
11917
11952
  cacheWrite: 0,
11918
11953
  },
11919
11954
  contextWindow: 262144,
11920
- maxTokens: 32768,
11955
+ maxTokens: 4096,
11921
11956
  },
11922
11957
  "qwen/qwen3-vl-235b-a22b-instruct": {
11923
11958
  id: "qwen/qwen3-vl-235b-a22b-instruct",
@@ -11945,8 +11980,8 @@ export const MODELS = {
11945
11980
  reasoning: true,
11946
11981
  input: ["text", "image"],
11947
11982
  cost: {
11948
- input: 0.39999999999999997,
11949
- output: 4,
11983
+ input: 0.98,
11984
+ output: 3.95,
11950
11985
  cacheRead: 0,
11951
11986
  cacheWrite: 0,
11952
11987
  },
@@ -11962,13 +11997,13 @@ export const MODELS = {
11962
11997
  reasoning: false,
11963
11998
  input: ["text", "image"],
11964
11999
  cost: {
11965
- input: 0.13,
11966
- output: 0.52,
12000
+ input: 0.15,
12001
+ output: 0.6,
11967
12002
  cacheRead: 0,
11968
12003
  cacheWrite: 0,
11969
12004
  },
11970
12005
  contextWindow: 262144,
11971
- maxTokens: 32768,
12006
+ maxTokens: 16384,
11972
12007
  },
11973
12008
  "qwen/qwen3-vl-30b-a3b-thinking": {
11974
12009
  id: "qwen/qwen3-vl-30b-a3b-thinking",
@@ -12183,13 +12218,13 @@ export const MODELS = {
12183
12218
  reasoning: true,
12184
12219
  input: ["text", "image"],
12185
12220
  cost: {
12186
- input: 0.3,
12187
- output: 2,
12188
- cacheRead: 0.15,
12221
+ input: 0.28900000000000003,
12222
+ output: 2.4,
12223
+ cacheRead: 0,
12189
12224
  cacheWrite: 0,
12190
12225
  },
12191
12226
  contextWindow: 262144,
12192
- maxTokens: 65536,
12227
+ maxTokens: 131072,
12193
12228
  },
12194
12229
  "qwen/qwen3.6-35b-a3b": {
12195
12230
  id: "qwen/qwen3.6-35b-a3b",
@@ -12310,6 +12345,23 @@ export const MODELS = {
12310
12345
  contextWindow: 1000000,
12311
12346
  maxTokens: 131072,
12312
12347
  },
12348
+ "qwen/qwen3.8-max": {
12349
+ id: "qwen/qwen3.8-max",
12350
+ name: "Qwen: Qwen3.8 Max",
12351
+ api: "openai-completions",
12352
+ provider: "openrouter",
12353
+ baseUrl: "https://openrouter.ai/api/v1",
12354
+ reasoning: true,
12355
+ input: ["text", "image"],
12356
+ cost: {
12357
+ input: 2,
12358
+ output: 6,
12359
+ cacheRead: 0.25,
12360
+ cacheWrite: 2.5,
12361
+ },
12362
+ contextWindow: 1000000,
12363
+ maxTokens: 131072,
12364
+ },
12313
12365
  "rekaai/reka-edge": {
12314
12366
  id: "rekaai/reka-edge",
12315
12367
  name: "Reka Edge",
@@ -12461,7 +12513,7 @@ export const MODELS = {
12461
12513
  cacheWrite: 0,
12462
12514
  },
12463
12515
  contextWindow: 1024000,
12464
- maxTokens: 32768,
12516
+ maxTokens: 1024000,
12465
12517
  },
12466
12518
  "thinkingmachines/inkling": {
12467
12519
  id: "thinkingmachines/inkling",
@@ -12795,13 +12847,13 @@ export const MODELS = {
12795
12847
  reasoning: true,
12796
12848
  input: ["text"],
12797
12849
  cost: {
12798
- input: 0.2842,
12799
- output: 0.8932,
12800
- cacheRead: 0.05278,
12850
+ input: 0.76,
12851
+ output: 2.42,
12852
+ cacheRead: 0.14,
12801
12853
  cacheWrite: 0,
12802
12854
  },
12803
12855
  contextWindow: 1048576,
12804
- maxTokens: 131072,
12856
+ maxTokens: 262144,
12805
12857
  },
12806
12858
  "z-ai/glm-5v-turbo": {
12807
12859
  id: "z-ai/glm-5v-turbo",
@@ -12917,7 +12969,7 @@ export const MODELS = {
12917
12969
  input: 1.5,
12918
12970
  output: 7.5,
12919
12971
  cacheRead: 0.15,
12920
- cacheWrite: 0.08333333333333334,
12972
+ cacheWrite: 0.0833333333333333,
12921
12973
  },
12922
12974
  contextWindow: 1048576,
12923
12975
  maxTokens: 65536,
@@ -13434,6 +13486,23 @@ export const MODELS = {
13434
13486
  contextWindow: 1000000,
13435
13487
  maxTokens: 64000,
13436
13488
  },
13489
+ "alibaba/qwen3.8-max": {
13490
+ id: "alibaba/qwen3.8-max",
13491
+ name: "Qwen 3.8 Max",
13492
+ api: "anthropic-messages",
13493
+ provider: "vercel-ai-gateway",
13494
+ baseUrl: "https://ai-gateway.vercel.sh",
13495
+ reasoning: true,
13496
+ input: ["text", "image"],
13497
+ cost: {
13498
+ input: 2,
13499
+ output: 6,
13500
+ cacheRead: 0.25,
13501
+ cacheWrite: 2.5,
13502
+ },
13503
+ contextWindow: 1000000,
13504
+ maxTokens: 128000,
13505
+ },
13437
13506
  "amazon/nova-2-lite": {
13438
13507
  id: "amazon/nova-2-lite",
13439
13508
  name: "Nova 2 Lite",
@@ -13970,9 +14039,9 @@ export const MODELS = {
13970
14039
  reasoning: true,
13971
14040
  input: ["text"],
13972
14041
  cost: {
13973
- input: 0.14,
13974
- output: 0.28,
13975
- cacheRead: 0.0028,
14042
+ input: 0.19999999999999998,
14043
+ output: 0.39999999999999997,
14044
+ cacheRead: 0.04,
13976
14045
  cacheWrite: 0,
13977
14046
  },
13978
14047
  contextWindow: 1000000,