@dreb/ai 2.51.0 → 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",
@@ -9150,7 +9168,7 @@ export const MODELS = {
9150
9168
  },
9151
9169
  "deepseek/deepseek-v4-flash": {
9152
9170
  id: "deepseek/deepseek-v4-flash",
9153
- name: "DeepSeek: DeepSeek V4 Flash",
9171
+ name: "DeepSeek: DeepSeek V4 Flash 0423",
9154
9172
  api: "openai-completions",
9155
9173
  provider: "openrouter",
9156
9174
  baseUrl: "https://openrouter.ai/api/v1",
@@ -9211,7 +9229,7 @@ export const MODELS = {
9211
9229
  input: 0.3,
9212
9230
  output: 2.5,
9213
9231
  cacheRead: 0.03,
9214
- cacheWrite: 0.08333333333333334,
9232
+ cacheWrite: 0.0833333333333333,
9215
9233
  },
9216
9234
  contextWindow: 1048576,
9217
9235
  maxTokens: 65535,
@@ -9228,7 +9246,7 @@ export const MODELS = {
9228
9246
  input: 0.09999999999999999,
9229
9247
  output: 0.39999999999999997,
9230
9248
  cacheRead: 0.01,
9231
- cacheWrite: 0.08333333333333334,
9249
+ cacheWrite: 0.0833333333333333,
9232
9250
  },
9233
9251
  contextWindow: 1048576,
9234
9252
  maxTokens: 65535,
@@ -9296,7 +9314,7 @@ export const MODELS = {
9296
9314
  input: 0.5,
9297
9315
  output: 3,
9298
9316
  cacheRead: 0.049999999999999996,
9299
- cacheWrite: 0.08333333333333334,
9317
+ cacheWrite: 0.0833333333333333,
9300
9318
  },
9301
9319
  contextWindow: 1048576,
9302
9320
  maxTokens: 65535,
@@ -9330,7 +9348,7 @@ export const MODELS = {
9330
9348
  input: 0.25,
9331
9349
  output: 1.5,
9332
9350
  cacheRead: 0.024999999999999998,
9333
- cacheWrite: 0.08333333333333334,
9351
+ cacheWrite: 0.0833333333333333,
9334
9352
  },
9335
9353
  contextWindow: 1048576,
9336
9354
  maxTokens: 65536,
@@ -9347,7 +9365,7 @@ export const MODELS = {
9347
9365
  input: 0.25,
9348
9366
  output: 1.5,
9349
9367
  cacheRead: 0.024999999999999998,
9350
- cacheWrite: 0.08333333333333334,
9368
+ cacheWrite: 0.0833333333333333,
9351
9369
  },
9352
9370
  contextWindow: 1048576,
9353
9371
  maxTokens: 65536,
@@ -9398,7 +9416,7 @@ export const MODELS = {
9398
9416
  input: 1.5,
9399
9417
  output: 9,
9400
9418
  cacheRead: 0.15,
9401
- cacheWrite: 0.08333333333333334,
9419
+ cacheWrite: 0.0833333333333333,
9402
9420
  },
9403
9421
  contextWindow: 1048576,
9404
9422
  maxTokens: 65536,
@@ -9415,7 +9433,7 @@ export const MODELS = {
9415
9433
  input: 0.3,
9416
9434
  output: 2.5,
9417
9435
  cacheRead: 0.03,
9418
- cacheWrite: 0.08333333333333334,
9436
+ cacheWrite: 0.0833333333333333,
9419
9437
  },
9420
9438
  contextWindow: 1048576,
9421
9439
  maxTokens: 65536,
@@ -9432,7 +9450,7 @@ export const MODELS = {
9432
9450
  input: 1.5,
9433
9451
  output: 7.5,
9434
9452
  cacheRead: 0.15,
9435
- cacheWrite: 0.08333333333333334,
9453
+ cacheWrite: 0.0833333333333333,
9436
9454
  },
9437
9455
  contextWindow: 1048576,
9438
9456
  maxTokens: 65536,
@@ -9752,13 +9770,13 @@ export const MODELS = {
9752
9770
  reasoning: false,
9753
9771
  input: ["text"],
9754
9772
  cost: {
9755
- input: 0.13,
9756
- output: 0.39999999999999997,
9773
+ input: 0.09999999999999999,
9774
+ output: 0.32,
9757
9775
  cacheRead: 0,
9758
9776
  cacheWrite: 0,
9759
9777
  },
9760
9778
  contextWindow: 131072,
9761
- maxTokens: 128000,
9779
+ maxTokens: 16384,
9762
9780
  },
9763
9781
  "meta-llama/llama-4-maverick": {
9764
9782
  id: "meta-llama/llama-4-maverick",
@@ -10262,9 +10280,9 @@ export const MODELS = {
10262
10280
  reasoning: true,
10263
10281
  input: ["text", "image"],
10264
10282
  cost: {
10265
- input: 0.6,
10266
- output: 3.41,
10267
- cacheRead: 0.19999999999999998,
10283
+ input: 0.589,
10284
+ output: 2.48,
10285
+ cacheRead: 0.0992,
10268
10286
  cacheWrite: 0,
10269
10287
  },
10270
10288
  contextWindow: 262144,
@@ -11810,12 +11828,12 @@ export const MODELS = {
11810
11828
  input: ["text"],
11811
11829
  cost: {
11812
11830
  input: 0.07,
11813
- output: 0.28,
11831
+ output: 0.27,
11814
11832
  cacheRead: 0,
11815
11833
  cacheWrite: 0,
11816
11834
  },
11817
11835
  contextWindow: 262144,
11818
- maxTokens: 262144,
11836
+ maxTokens: 32768,
11819
11837
  },
11820
11838
  "qwen/qwen3-coder-flash": {
11821
11839
  id: "qwen/qwen3-coder-flash",
@@ -11911,13 +11929,13 @@ export const MODELS = {
11911
11929
  reasoning: false,
11912
11930
  input: ["text"],
11913
11931
  cost: {
11914
- input: 0.09999999999999999,
11932
+ input: 0.09,
11915
11933
  output: 1.1,
11916
- cacheRead: 0.07,
11934
+ cacheRead: 0,
11917
11935
  cacheWrite: 0,
11918
11936
  },
11919
11937
  contextWindow: 262144,
11920
- maxTokens: 262144,
11938
+ maxTokens: 16384,
11921
11939
  },
11922
11940
  "qwen/qwen3-next-80b-a3b-thinking": {
11923
11941
  id: "qwen/qwen3-next-80b-a3b-thinking",
@@ -11934,7 +11952,7 @@ export const MODELS = {
11934
11952
  cacheWrite: 0,
11935
11953
  },
11936
11954
  contextWindow: 262144,
11937
- maxTokens: 32768,
11955
+ maxTokens: 4096,
11938
11956
  },
11939
11957
  "qwen/qwen3-vl-235b-a22b-instruct": {
11940
11958
  id: "qwen/qwen3-vl-235b-a22b-instruct",
@@ -11979,13 +11997,13 @@ export const MODELS = {
11979
11997
  reasoning: false,
11980
11998
  input: ["text", "image"],
11981
11999
  cost: {
11982
- input: 0.13,
11983
- output: 0.52,
12000
+ input: 0.15,
12001
+ output: 0.6,
11984
12002
  cacheRead: 0,
11985
12003
  cacheWrite: 0,
11986
12004
  },
11987
12005
  contextWindow: 262144,
11988
- maxTokens: 32768,
12006
+ maxTokens: 16384,
11989
12007
  },
11990
12008
  "qwen/qwen3-vl-30b-a3b-thinking": {
11991
12009
  id: "qwen/qwen3-vl-30b-a3b-thinking",
@@ -12064,8 +12082,8 @@ export const MODELS = {
12064
12082
  reasoning: true,
12065
12083
  input: ["text", "image"],
12066
12084
  cost: {
12067
- input: 0.39999999999999997,
12068
- output: 3.1999999999999997,
12085
+ input: 0.26,
12086
+ output: 2.08,
12069
12087
  cacheRead: 0,
12070
12088
  cacheWrite: 0,
12071
12089
  },
@@ -12200,13 +12218,13 @@ export const MODELS = {
12200
12218
  reasoning: true,
12201
12219
  input: ["text", "image"],
12202
12220
  cost: {
12203
- input: 0.3,
12204
- output: 2,
12205
- cacheRead: 0.15,
12221
+ input: 0.28900000000000003,
12222
+ output: 2.4,
12223
+ cacheRead: 0,
12206
12224
  cacheWrite: 0,
12207
12225
  },
12208
12226
  contextWindow: 262144,
12209
- maxTokens: 65536,
12227
+ maxTokens: 131072,
12210
12228
  },
12211
12229
  "qwen/qwen3.6-35b-a3b": {
12212
12230
  id: "qwen/qwen3.6-35b-a3b",
@@ -12327,6 +12345,23 @@ export const MODELS = {
12327
12345
  contextWindow: 1000000,
12328
12346
  maxTokens: 131072,
12329
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
+ },
12330
12365
  "rekaai/reka-edge": {
12331
12366
  id: "rekaai/reka-edge",
12332
12367
  name: "Reka Edge",
@@ -12812,13 +12847,13 @@ export const MODELS = {
12812
12847
  reasoning: true,
12813
12848
  input: ["text"],
12814
12849
  cost: {
12815
- input: 0.7153999999999999,
12816
- output: 2.2483999999999997,
12817
- cacheRead: 0.13286,
12850
+ input: 0.76,
12851
+ output: 2.42,
12852
+ cacheRead: 0.14,
12818
12853
  cacheWrite: 0,
12819
12854
  },
12820
12855
  contextWindow: 1048576,
12821
- maxTokens: 131072,
12856
+ maxTokens: 262144,
12822
12857
  },
12823
12858
  "z-ai/glm-5v-turbo": {
12824
12859
  id: "z-ai/glm-5v-turbo",
@@ -12934,7 +12969,7 @@ export const MODELS = {
12934
12969
  input: 1.5,
12935
12970
  output: 7.5,
12936
12971
  cacheRead: 0.15,
12937
- cacheWrite: 0.08333333333333334,
12972
+ cacheWrite: 0.0833333333333333,
12938
12973
  },
12939
12974
  contextWindow: 1048576,
12940
12975
  maxTokens: 65536,