@dreb/ai 2.51.0 → 2.53.0

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",
@@ -4394,23 +4394,6 @@ export const MODELS = {
4394
4394
  contextWindow: 131072,
4395
4395
  maxTokens: 32768,
4396
4396
  },
4397
- "meta-llama/llama-4-scout-17b-16e-instruct": {
4398
- id: "meta-llama/llama-4-scout-17b-16e-instruct",
4399
- name: "Llama 4 Scout 17B 16E",
4400
- api: "openai-completions",
4401
- provider: "groq",
4402
- baseUrl: "https://api.groq.com/openai/v1",
4403
- reasoning: false,
4404
- input: ["text", "image"],
4405
- cost: {
4406
- input: 0.11,
4407
- output: 0.34,
4408
- cacheRead: 0,
4409
- cacheWrite: 0,
4410
- },
4411
- contextWindow: 131072,
4412
- maxTokens: 8192,
4413
- },
4414
4397
  "openai/gpt-oss-120b": {
4415
4398
  id: "openai/gpt-oss-120b",
4416
4399
  name: "GPT OSS 120B",
@@ -4462,22 +4445,22 @@ export const MODELS = {
4462
4445
  contextWindow: 131072,
4463
4446
  maxTokens: 65536,
4464
4447
  },
4465
- "qwen/qwen3-32b": {
4466
- id: "qwen/qwen3-32b",
4467
- name: "Qwen3-32B",
4448
+ "qwen/qwen3.6-27b": {
4449
+ id: "qwen/qwen3.6-27b",
4450
+ name: "Qwen3.6 27B",
4468
4451
  api: "openai-completions",
4469
4452
  provider: "groq",
4470
4453
  baseUrl: "https://api.groq.com/openai/v1",
4471
4454
  reasoning: true,
4472
- input: ["text"],
4455
+ input: ["text", "image"],
4473
4456
  cost: {
4474
- input: 0.29,
4475
- output: 0.59,
4476
- cacheRead: 0,
4457
+ input: 0.6,
4458
+ output: 3,
4459
+ cacheRead: 0.3,
4477
4460
  cacheWrite: 0,
4478
4461
  },
4479
4462
  contextWindow: 131072,
4480
- maxTokens: 40960,
4463
+ maxTokens: 16384,
4481
4464
  },
4482
4465
  },
4483
4466
  "huggingface": {
@@ -4967,6 +4950,24 @@ export const MODELS = {
4967
4950
  contextWindow: 1048576,
4968
4951
  maxTokens: 384000,
4969
4952
  },
4953
+ "deepseek-ai/DeepSeek-V4-Flash-0731": {
4954
+ id: "deepseek-ai/DeepSeek-V4-Flash-0731",
4955
+ name: "DeepSeek V4 Flash 0731",
4956
+ api: "openai-completions",
4957
+ provider: "huggingface",
4958
+ baseUrl: "https://router.huggingface.co/v1",
4959
+ compat: { "supportsDeveloperRole": false },
4960
+ reasoning: true,
4961
+ input: ["text"],
4962
+ cost: {
4963
+ input: 0.14,
4964
+ output: 0.28,
4965
+ cacheRead: 0,
4966
+ cacheWrite: 0,
4967
+ },
4968
+ contextWindow: 1048576,
4969
+ maxTokens: 384000,
4970
+ },
4970
4971
  "deepseek-ai/DeepSeek-V4-Pro": {
4971
4972
  id: "deepseek-ai/DeepSeek-V4-Pro",
4972
4973
  name: "DeepSeek V4 Pro",
@@ -7310,7 +7311,7 @@ export const MODELS = {
7310
7311
  },
7311
7312
  "deepseek-v4-flash": {
7312
7313
  id: "deepseek-v4-flash",
7313
- name: "DeepSeek V4 Flash 0731",
7314
+ name: "DeepSeek V4 Flash (New)",
7314
7315
  api: "openai-completions",
7315
7316
  provider: "opencode",
7316
7317
  baseUrl: "https://opencode.ai/zen/v1",
@@ -9150,7 +9151,7 @@ export const MODELS = {
9150
9151
  },
9151
9152
  "deepseek/deepseek-v4-flash": {
9152
9153
  id: "deepseek/deepseek-v4-flash",
9153
- name: "DeepSeek: DeepSeek V4 Flash",
9154
+ name: "DeepSeek: DeepSeek V4 Flash 0423",
9154
9155
  api: "openai-completions",
9155
9156
  provider: "openrouter",
9156
9157
  baseUrl: "https://openrouter.ai/api/v1",
@@ -9211,7 +9212,7 @@ export const MODELS = {
9211
9212
  input: 0.3,
9212
9213
  output: 2.5,
9213
9214
  cacheRead: 0.03,
9214
- cacheWrite: 0.08333333333333334,
9215
+ cacheWrite: 0.0833333333333333,
9215
9216
  },
9216
9217
  contextWindow: 1048576,
9217
9218
  maxTokens: 65535,
@@ -9228,7 +9229,7 @@ export const MODELS = {
9228
9229
  input: 0.09999999999999999,
9229
9230
  output: 0.39999999999999997,
9230
9231
  cacheRead: 0.01,
9231
- cacheWrite: 0.08333333333333334,
9232
+ cacheWrite: 0.0833333333333333,
9232
9233
  },
9233
9234
  contextWindow: 1048576,
9234
9235
  maxTokens: 65535,
@@ -9296,7 +9297,7 @@ export const MODELS = {
9296
9297
  input: 0.5,
9297
9298
  output: 3,
9298
9299
  cacheRead: 0.049999999999999996,
9299
- cacheWrite: 0.08333333333333334,
9300
+ cacheWrite: 0.0833333333333333,
9300
9301
  },
9301
9302
  contextWindow: 1048576,
9302
9303
  maxTokens: 65535,
@@ -9330,7 +9331,7 @@ export const MODELS = {
9330
9331
  input: 0.25,
9331
9332
  output: 1.5,
9332
9333
  cacheRead: 0.024999999999999998,
9333
- cacheWrite: 0.08333333333333334,
9334
+ cacheWrite: 0.0833333333333333,
9334
9335
  },
9335
9336
  contextWindow: 1048576,
9336
9337
  maxTokens: 65536,
@@ -9347,7 +9348,7 @@ export const MODELS = {
9347
9348
  input: 0.25,
9348
9349
  output: 1.5,
9349
9350
  cacheRead: 0.024999999999999998,
9350
- cacheWrite: 0.08333333333333334,
9351
+ cacheWrite: 0.0833333333333333,
9351
9352
  },
9352
9353
  contextWindow: 1048576,
9353
9354
  maxTokens: 65536,
@@ -9398,7 +9399,7 @@ export const MODELS = {
9398
9399
  input: 1.5,
9399
9400
  output: 9,
9400
9401
  cacheRead: 0.15,
9401
- cacheWrite: 0.08333333333333334,
9402
+ cacheWrite: 0.0833333333333333,
9402
9403
  },
9403
9404
  contextWindow: 1048576,
9404
9405
  maxTokens: 65536,
@@ -9415,7 +9416,7 @@ export const MODELS = {
9415
9416
  input: 0.3,
9416
9417
  output: 2.5,
9417
9418
  cacheRead: 0.03,
9418
- cacheWrite: 0.08333333333333334,
9419
+ cacheWrite: 0.0833333333333333,
9419
9420
  },
9420
9421
  contextWindow: 1048576,
9421
9422
  maxTokens: 65536,
@@ -9432,7 +9433,7 @@ export const MODELS = {
9432
9433
  input: 1.5,
9433
9434
  output: 7.5,
9434
9435
  cacheRead: 0.15,
9435
- cacheWrite: 0.08333333333333334,
9436
+ cacheWrite: 0.0833333333333333,
9436
9437
  },
9437
9438
  contextWindow: 1048576,
9438
9439
  maxTokens: 65536,
@@ -9752,13 +9753,13 @@ export const MODELS = {
9752
9753
  reasoning: false,
9753
9754
  input: ["text"],
9754
9755
  cost: {
9755
- input: 0.13,
9756
- output: 0.39999999999999997,
9756
+ input: 0.09999999999999999,
9757
+ output: 0.32,
9757
9758
  cacheRead: 0,
9758
9759
  cacheWrite: 0,
9759
9760
  },
9760
9761
  contextWindow: 131072,
9761
- maxTokens: 128000,
9762
+ maxTokens: 16384,
9762
9763
  },
9763
9764
  "meta-llama/llama-4-maverick": {
9764
9765
  id: "meta-llama/llama-4-maverick",
@@ -9888,9 +9889,9 @@ export const MODELS = {
9888
9889
  reasoning: true,
9889
9890
  input: ["text"],
9890
9891
  cost: {
9891
- input: 0.25,
9892
- output: 1,
9893
- cacheRead: 0.049999999999999996,
9892
+ input: 0.27,
9893
+ output: 1.08,
9894
+ cacheRead: 0.054,
9894
9895
  cacheWrite: 0,
9895
9896
  },
9896
9897
  contextWindow: 204800,
@@ -10143,8 +10144,8 @@ export const MODELS = {
10143
10144
  reasoning: false,
10144
10145
  input: ["text", "image"],
10145
10146
  cost: {
10146
- input: 0.075,
10147
- output: 0.19999999999999998,
10147
+ input: 0.09375,
10148
+ output: 0.25,
10148
10149
  cacheRead: 0,
10149
10150
  cacheWrite: 0,
10150
10151
  },
@@ -10262,9 +10263,9 @@ export const MODELS = {
10262
10263
  reasoning: true,
10263
10264
  input: ["text", "image"],
10264
10265
  cost: {
10265
- input: 0.6,
10266
- output: 3.41,
10267
- cacheRead: 0.19999999999999998,
10266
+ input: 0.589,
10267
+ output: 2.48,
10268
+ cacheRead: 0.0992,
10268
10269
  cacheWrite: 0,
10269
10270
  },
10270
10271
  contextWindow: 262144,
@@ -11810,12 +11811,12 @@ export const MODELS = {
11810
11811
  input: ["text"],
11811
11812
  cost: {
11812
11813
  input: 0.07,
11813
- output: 0.28,
11814
+ output: 0.27,
11814
11815
  cacheRead: 0,
11815
11816
  cacheWrite: 0,
11816
11817
  },
11817
11818
  contextWindow: 262144,
11818
- maxTokens: 262144,
11819
+ maxTokens: 32768,
11819
11820
  },
11820
11821
  "qwen/qwen3-coder-flash": {
11821
11822
  id: "qwen/qwen3-coder-flash",
@@ -11911,13 +11912,13 @@ export const MODELS = {
11911
11912
  reasoning: false,
11912
11913
  input: ["text"],
11913
11914
  cost: {
11914
- input: 0.09999999999999999,
11915
+ input: 0.09,
11915
11916
  output: 1.1,
11916
- cacheRead: 0.07,
11917
+ cacheRead: 0,
11917
11918
  cacheWrite: 0,
11918
11919
  },
11919
11920
  contextWindow: 262144,
11920
- maxTokens: 262144,
11921
+ maxTokens: 16384,
11921
11922
  },
11922
11923
  "qwen/qwen3-next-80b-a3b-thinking": {
11923
11924
  id: "qwen/qwen3-next-80b-a3b-thinking",
@@ -11934,7 +11935,7 @@ export const MODELS = {
11934
11935
  cacheWrite: 0,
11935
11936
  },
11936
11937
  contextWindow: 262144,
11937
- maxTokens: 32768,
11938
+ maxTokens: 4096,
11938
11939
  },
11939
11940
  "qwen/qwen3-vl-235b-a22b-instruct": {
11940
11941
  id: "qwen/qwen3-vl-235b-a22b-instruct",
@@ -11979,13 +11980,13 @@ export const MODELS = {
11979
11980
  reasoning: false,
11980
11981
  input: ["text", "image"],
11981
11982
  cost: {
11982
- input: 0.13,
11983
- output: 0.52,
11983
+ input: 0.15,
11984
+ output: 0.6,
11984
11985
  cacheRead: 0,
11985
11986
  cacheWrite: 0,
11986
11987
  },
11987
11988
  contextWindow: 262144,
11988
- maxTokens: 32768,
11989
+ maxTokens: 16384,
11989
11990
  },
11990
11991
  "qwen/qwen3-vl-30b-a3b-thinking": {
11991
11992
  id: "qwen/qwen3-vl-30b-a3b-thinking",
@@ -12064,8 +12065,8 @@ export const MODELS = {
12064
12065
  reasoning: true,
12065
12066
  input: ["text", "image"],
12066
12067
  cost: {
12067
- input: 0.39999999999999997,
12068
- output: 3.1999999999999997,
12068
+ input: 0.26,
12069
+ output: 2.08,
12069
12070
  cacheRead: 0,
12070
12071
  cacheWrite: 0,
12071
12072
  },
@@ -12200,13 +12201,13 @@ export const MODELS = {
12200
12201
  reasoning: true,
12201
12202
  input: ["text", "image"],
12202
12203
  cost: {
12203
- input: 0.3,
12204
- output: 2,
12205
- cacheRead: 0.15,
12204
+ input: 0.28900000000000003,
12205
+ output: 2.4,
12206
+ cacheRead: 0,
12206
12207
  cacheWrite: 0,
12207
12208
  },
12208
12209
  contextWindow: 262144,
12209
- maxTokens: 65536,
12210
+ maxTokens: 131072,
12210
12211
  },
12211
12212
  "qwen/qwen3.6-35b-a3b": {
12212
12213
  id: "qwen/qwen3.6-35b-a3b",
@@ -12327,6 +12328,23 @@ export const MODELS = {
12327
12328
  contextWindow: 1000000,
12328
12329
  maxTokens: 131072,
12329
12330
  },
12331
+ "qwen/qwen3.8-max": {
12332
+ id: "qwen/qwen3.8-max",
12333
+ name: "Qwen: Qwen3.8 Max",
12334
+ api: "openai-completions",
12335
+ provider: "openrouter",
12336
+ baseUrl: "https://openrouter.ai/api/v1",
12337
+ reasoning: true,
12338
+ input: ["text", "image"],
12339
+ cost: {
12340
+ input: 2,
12341
+ output: 6,
12342
+ cacheRead: 0.25,
12343
+ cacheWrite: 2.5,
12344
+ },
12345
+ contextWindow: 1000000,
12346
+ maxTokens: 131072,
12347
+ },
12330
12348
  "rekaai/reka-edge": {
12331
12349
  id: "rekaai/reka-edge",
12332
12350
  name: "Reka Edge",
@@ -12533,7 +12551,7 @@ export const MODELS = {
12533
12551
  },
12534
12552
  "x-ai/grok-4.20": {
12535
12553
  id: "x-ai/grok-4.20",
12536
- name: "xAI: Grok 4.20",
12554
+ name: "SpaceXAI: Grok 4.20",
12537
12555
  api: "openai-completions",
12538
12556
  provider: "openrouter",
12539
12557
  baseUrl: "https://openrouter.ai/api/v1",
@@ -12550,7 +12568,7 @@ export const MODELS = {
12550
12568
  },
12551
12569
  "x-ai/grok-4.3": {
12552
12570
  id: "x-ai/grok-4.3",
12553
- name: "xAI: Grok 4.3",
12571
+ name: "SpaceXAI: Grok 4.3",
12554
12572
  api: "openai-completions",
12555
12573
  provider: "openrouter",
12556
12574
  baseUrl: "https://openrouter.ai/api/v1",
@@ -12567,7 +12585,7 @@ export const MODELS = {
12567
12585
  },
12568
12586
  "x-ai/grok-4.5": {
12569
12587
  id: "x-ai/grok-4.5",
12570
- name: "xAI: Grok 4.5",
12588
+ name: "SpaceXAI: Grok 4.5",
12571
12589
  api: "openai-completions",
12572
12590
  provider: "openrouter",
12573
12591
  baseUrl: "https://openrouter.ai/api/v1",
@@ -12584,7 +12602,7 @@ export const MODELS = {
12584
12602
  },
12585
12603
  "x-ai/grok-build-0.1": {
12586
12604
  id: "x-ai/grok-build-0.1",
12587
- name: "xAI: Grok Build 0.1",
12605
+ name: "SpaceXAI: Grok Build 0.1",
12588
12606
  api: "openai-completions",
12589
12607
  provider: "openrouter",
12590
12608
  baseUrl: "https://openrouter.ai/api/v1",
@@ -12812,13 +12830,13 @@ export const MODELS = {
12812
12830
  reasoning: true,
12813
12831
  input: ["text"],
12814
12832
  cost: {
12815
- input: 0.7153999999999999,
12816
- output: 2.2483999999999997,
12817
- cacheRead: 0.13286,
12833
+ input: 0.76,
12834
+ output: 2.42,
12835
+ cacheRead: 0.14,
12818
12836
  cacheWrite: 0,
12819
12837
  },
12820
12838
  contextWindow: 1048576,
12821
- maxTokens: 131072,
12839
+ maxTokens: 262144,
12822
12840
  },
12823
12841
  "z-ai/glm-5v-turbo": {
12824
12842
  id: "z-ai/glm-5v-turbo",
@@ -12934,7 +12952,7 @@ export const MODELS = {
12934
12952
  input: 1.5,
12935
12953
  output: 7.5,
12936
12954
  cacheRead: 0.15,
12937
- cacheWrite: 0.08333333333333334,
12955
+ cacheWrite: 0.0833333333333333,
12938
12956
  },
12939
12957
  contextWindow: 1048576,
12940
12958
  maxTokens: 65536,