@dreb/ai 2.19.2 → 2.19.3

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.
@@ -900,8 +900,8 @@ export const MODELS = {
900
900
  cacheRead: 0,
901
901
  cacheWrite: 0,
902
902
  },
903
- contextWindow: 256000,
904
- maxTokens: 256000,
903
+ contextWindow: 262143,
904
+ maxTokens: 16000,
905
905
  },
906
906
  "moonshotai.kimi-k2.5": {
907
907
  id: "moonshotai.kimi-k2.5",
@@ -917,8 +917,8 @@ export const MODELS = {
917
917
  cacheRead: 0,
918
918
  cacheWrite: 0,
919
919
  },
920
- contextWindow: 256000,
921
- maxTokens: 256000,
920
+ contextWindow: 262143,
921
+ maxTokens: 16000,
922
922
  },
923
923
  "nvidia.nemotron-nano-12b-v2": {
924
924
  id: "nvidia.nemotron-nano-12b-v2",
@@ -3301,6 +3301,23 @@ export const MODELS = {
3301
3301
  contextWindow: 1048576,
3302
3302
  maxTokens: 65536,
3303
3303
  },
3304
+ "gemini-3.5-flash": {
3305
+ id: "gemini-3.5-flash",
3306
+ name: "Gemini 3.5 Flash",
3307
+ api: "google-generative-ai",
3308
+ provider: "google",
3309
+ baseUrl: "https://generativelanguage.googleapis.com/v1beta",
3310
+ reasoning: true,
3311
+ input: ["text", "image"],
3312
+ cost: {
3313
+ input: 1.5,
3314
+ output: 9,
3315
+ cacheRead: 0.15,
3316
+ cacheWrite: 0,
3317
+ },
3318
+ contextWindow: 1048576,
3319
+ maxTokens: 65536,
3320
+ },
3304
3321
  "gemini-flash-latest": {
3305
3322
  id: "gemini-flash-latest",
3306
3323
  name: "Gemini Flash Latest",
@@ -6220,8 +6237,8 @@ export const MODELS = {
6220
6237
  cacheRead: 0,
6221
6238
  cacheWrite: 0,
6222
6239
  },
6223
- contextWindow: 1000000,
6224
- maxTokens: 384000,
6240
+ contextWindow: 200000,
6241
+ maxTokens: 128000,
6225
6242
  },
6226
6243
  "gemini-3-flash": {
6227
6244
  id: "gemini-3-flash",
@@ -7397,7 +7414,7 @@ export const MODELS = {
7397
7414
  cacheRead: 0,
7398
7415
  cacheWrite: 0,
7399
7416
  },
7400
- contextWindow: 120000,
7417
+ contextWindow: 131072,
7401
7418
  maxTokens: 8000,
7402
7419
  },
7403
7420
  "baidu/ernie-4.5-vl-28b-a3b": {
@@ -7414,7 +7431,7 @@ export const MODELS = {
7414
7431
  cacheRead: 0,
7415
7432
  cacheWrite: 0,
7416
7433
  },
7417
- contextWindow: 30000,
7434
+ contextWindow: 131072,
7418
7435
  maxTokens: 8000,
7419
7436
  },
7420
7437
  "bytedance-seed/seed-1.6": {
@@ -7584,7 +7601,7 @@ export const MODELS = {
7584
7601
  cacheRead: 0,
7585
7602
  cacheWrite: 0,
7586
7603
  },
7587
- contextWindow: 64000,
7604
+ contextWindow: 163840,
7588
7605
  maxTokens: 16000,
7589
7606
  },
7590
7607
  "deepseek/deepseek-r1-0528": {
@@ -7669,7 +7686,7 @@ export const MODELS = {
7669
7686
  cacheRead: 0.022,
7670
7687
  cacheWrite: 0,
7671
7688
  },
7672
- contextWindow: 1048575,
7689
+ contextWindow: 1048576,
7673
7690
  maxTokens: 4096,
7674
7691
  },
7675
7692
  "deepseek/deepseek-v4-flash:free": {
@@ -7941,6 +7958,23 @@ export const MODELS = {
7941
7958
  cacheRead: 0.19999999999999998,
7942
7959
  cacheWrite: 0.375,
7943
7960
  },
7961
+ contextWindow: 1048756,
7962
+ maxTokens: 65536,
7963
+ },
7964
+ "google/gemini-3.5-flash": {
7965
+ id: "google/gemini-3.5-flash",
7966
+ name: "Google: Gemini 3.5 Flash",
7967
+ api: "openai-completions",
7968
+ provider: "openrouter",
7969
+ baseUrl: "https://openrouter.ai/api/v1",
7970
+ reasoning: true,
7971
+ input: ["text", "image"],
7972
+ cost: {
7973
+ input: 1.5,
7974
+ output: 9,
7975
+ cacheRead: 0.15,
7976
+ cacheWrite: 0.08333333333333334,
7977
+ },
7944
7978
  contextWindow: 1048576,
7945
7979
  maxTokens: 65536,
7946
7980
  },
@@ -8179,7 +8213,7 @@ export const MODELS = {
8179
8213
  cacheRead: 0,
8180
8214
  cacheWrite: 0,
8181
8215
  },
8182
- contextWindow: 16384,
8216
+ contextWindow: 131072,
8183
8217
  maxTokens: 16384,
8184
8218
  },
8185
8219
  "meta-llama/llama-3.3-70b-instruct": {
@@ -8213,7 +8247,7 @@ export const MODELS = {
8213
8247
  cacheRead: 0,
8214
8248
  cacheWrite: 0,
8215
8249
  },
8216
- contextWindow: 65536,
8250
+ contextWindow: 131072,
8217
8251
  maxTokens: 4096,
8218
8252
  },
8219
8253
  "meta-llama/llama-4-scout": {
@@ -8230,7 +8264,7 @@ export const MODELS = {
8230
8264
  cacheRead: 0,
8231
8265
  cacheWrite: 0,
8232
8266
  },
8233
- contextWindow: 327680,
8267
+ contextWindow: 10000000,
8234
8268
  maxTokens: 16384,
8235
8269
  },
8236
8270
  "minimax/minimax-m1": {
@@ -8264,7 +8298,7 @@ export const MODELS = {
8264
8298
  cacheRead: 0.03,
8265
8299
  cacheWrite: 0,
8266
8300
  },
8267
- contextWindow: 196608,
8301
+ contextWindow: 204800,
8268
8302
  maxTokens: 196608,
8269
8303
  },
8270
8304
  "minimax/minimax-m2.1": {
@@ -8281,7 +8315,7 @@ export const MODELS = {
8281
8315
  cacheRead: 0.03,
8282
8316
  cacheWrite: 0,
8283
8317
  },
8284
- contextWindow: 196608,
8318
+ contextWindow: 204800,
8285
8319
  maxTokens: 196608,
8286
8320
  },
8287
8321
  "minimax/minimax-m2.5": {
@@ -8298,7 +8332,7 @@ export const MODELS = {
8298
8332
  cacheRead: 0,
8299
8333
  cacheWrite: 0,
8300
8334
  },
8301
- contextWindow: 196608,
8335
+ contextWindow: 204800,
8302
8336
  maxTokens: 196608,
8303
8337
  },
8304
8338
  "minimax/minimax-m2.5:free": {
@@ -8315,7 +8349,7 @@ export const MODELS = {
8315
8349
  cacheRead: 0,
8316
8350
  cacheWrite: 0,
8317
8351
  },
8318
- contextWindow: 196608,
8352
+ contextWindow: 204800,
8319
8353
  maxTokens: 8192,
8320
8354
  },
8321
8355
  "minimax/minimax-m2.7": {
@@ -8332,7 +8366,7 @@ export const MODELS = {
8332
8366
  cacheRead: 0,
8333
8367
  cacheWrite: 0,
8334
8368
  },
8335
- contextWindow: 196608,
8369
+ contextWindow: 204800,
8336
8370
  maxTokens: 131072,
8337
8371
  },
8338
8372
  "mistralai/codestral-2508": {
@@ -8774,7 +8808,7 @@ export const MODELS = {
8774
8808
  cacheRead: 0.25,
8775
8809
  cacheWrite: 0,
8776
8810
  },
8777
- contextWindow: 262142,
8811
+ contextWindow: 262144,
8778
8812
  maxTokens: 262142,
8779
8813
  },
8780
8814
  "nex-agi/deepseek-v3.1-nex-n1": {
@@ -8876,7 +8910,7 @@ export const MODELS = {
8876
8910
  cacheRead: 0,
8877
8911
  cacheWrite: 0,
8878
8912
  },
8879
- contextWindow: 262144,
8913
+ contextWindow: 1000000,
8880
8914
  maxTokens: 4096,
8881
8915
  },
8882
8916
  "nvidia/nemotron-3-super-120b-a12b:free": {
@@ -8893,7 +8927,7 @@ export const MODELS = {
8893
8927
  cacheRead: 0,
8894
8928
  cacheWrite: 0,
8895
8929
  },
8896
- contextWindow: 262144,
8930
+ contextWindow: 1000000,
8897
8931
  maxTokens: 262144,
8898
8932
  },
8899
8933
  "nvidia/nemotron-nano-12b-v2-vl:free": {
@@ -10032,7 +10066,7 @@ export const MODELS = {
10032
10066
  cacheRead: 0,
10033
10067
  cacheWrite: 0,
10034
10068
  },
10035
- contextWindow: 32768,
10069
+ contextWindow: 131072,
10036
10070
  maxTokens: 16384,
10037
10071
  },
10038
10072
  "qwen/qwen-2.5-7b-instruct": {
@@ -10049,7 +10083,7 @@ export const MODELS = {
10049
10083
  cacheRead: 0,
10050
10084
  cacheWrite: 0,
10051
10085
  },
10052
- contextWindow: 32768,
10086
+ contextWindow: 131072,
10053
10087
  maxTokens: 32768,
10054
10088
  },
10055
10089
  "qwen/qwen-plus": {
@@ -10117,7 +10151,7 @@ export const MODELS = {
10117
10151
  cacheRead: 0,
10118
10152
  cacheWrite: 0,
10119
10153
  },
10120
- contextWindow: 40960,
10154
+ contextWindow: 131702,
10121
10155
  maxTokens: 40960,
10122
10156
  },
10123
10157
  "qwen/qwen3-235b-a22b": {
@@ -10168,7 +10202,7 @@ export const MODELS = {
10168
10202
  cacheRead: 0,
10169
10203
  cacheWrite: 0,
10170
10204
  },
10171
- contextWindow: 131072,
10205
+ contextWindow: 262144,
10172
10206
  maxTokens: 4096,
10173
10207
  },
10174
10208
  "qwen/qwen3-30b-a3b": {
@@ -10185,7 +10219,7 @@ export const MODELS = {
10185
10219
  cacheRead: 0,
10186
10220
  cacheWrite: 0,
10187
10221
  },
10188
- contextWindow: 40960,
10222
+ contextWindow: 131072,
10189
10223
  maxTokens: 20000,
10190
10224
  },
10191
10225
  "qwen/qwen3-30b-a3b-instruct-2507": {
@@ -10236,7 +10270,7 @@ export const MODELS = {
10236
10270
  cacheRead: 0,
10237
10271
  cacheWrite: 0,
10238
10272
  },
10239
- contextWindow: 40960,
10273
+ contextWindow: 131072,
10240
10274
  maxTokens: 16384,
10241
10275
  },
10242
10276
  "qwen/qwen3-8b": {
@@ -10253,7 +10287,7 @@ export const MODELS = {
10253
10287
  cacheRead: 0.049999999999999996,
10254
10288
  cacheWrite: 0,
10255
10289
  },
10256
- contextWindow: 40960,
10290
+ contextWindow: 131072,
10257
10291
  maxTokens: 8192,
10258
10292
  },
10259
10293
  "qwen/qwen3-coder": {
@@ -10270,7 +10304,7 @@ export const MODELS = {
10270
10304
  cacheRead: 0,
10271
10305
  cacheWrite: 0,
10272
10306
  },
10273
- contextWindow: 262144,
10307
+ contextWindow: 1048576,
10274
10308
  maxTokens: 65536,
10275
10309
  },
10276
10310
  "qwen/qwen3-coder-30b-a3b-instruct": {
@@ -10355,7 +10389,7 @@ export const MODELS = {
10355
10389
  cacheRead: 0,
10356
10390
  cacheWrite: 0,
10357
10391
  },
10358
- contextWindow: 262000,
10392
+ contextWindow: 1048576,
10359
10393
  maxTokens: 262000,
10360
10394
  },
10361
10395
  "qwen/qwen3-max": {
@@ -10440,7 +10474,7 @@ export const MODELS = {
10440
10474
  cacheRead: 0,
10441
10475
  cacheWrite: 0,
10442
10476
  },
10443
- contextWindow: 131072,
10477
+ contextWindow: 262144,
10444
10478
  maxTokens: 32768,
10445
10479
  },
10446
10480
  "qwen/qwen3-vl-235b-a22b-instruct": {
@@ -10491,7 +10525,7 @@ export const MODELS = {
10491
10525
  cacheRead: 0,
10492
10526
  cacheWrite: 0,
10493
10527
  },
10494
- contextWindow: 131072,
10528
+ contextWindow: 262144,
10495
10529
  maxTokens: 32768,
10496
10530
  },
10497
10531
  "qwen/qwen3-vl-30b-a3b-thinking": {
@@ -10525,7 +10559,7 @@ export const MODELS = {
10525
10559
  cacheRead: 0,
10526
10560
  cacheWrite: 0,
10527
10561
  },
10528
- contextWindow: 131072,
10562
+ contextWindow: 262144,
10529
10563
  maxTokens: 32768,
10530
10564
  },
10531
10565
  "qwen/qwen3-vl-8b-instruct": {
@@ -10542,7 +10576,7 @@ export const MODELS = {
10542
10576
  cacheRead: 0,
10543
10577
  cacheWrite: 0,
10544
10578
  },
10545
- contextWindow: 131072,
10579
+ contextWindow: 256000,
10546
10580
  maxTokens: 32768,
10547
10581
  },
10548
10582
  "qwen/qwen3-vl-8b-thinking": {
@@ -10559,7 +10593,7 @@ export const MODELS = {
10559
10593
  cacheRead: 0,
10560
10594
  cacheWrite: 0,
10561
10595
  },
10562
- contextWindow: 131072,
10596
+ contextWindow: 256000,
10563
10597
  maxTokens: 32768,
10564
10598
  },
10565
10599
  "qwen/qwen3.5-122b-a10b": {
@@ -10605,13 +10639,13 @@ export const MODELS = {
10605
10639
  reasoning: true,
10606
10640
  input: ["text", "image"],
10607
10641
  cost: {
10608
- input: 0.14,
10642
+ input: 0.13899999999999998,
10609
10643
  output: 1,
10610
- cacheRead: 0.049999999999999996,
10644
+ cacheRead: 0,
10611
10645
  cacheWrite: 0,
10612
10646
  },
10613
10647
  contextWindow: 262144,
10614
- maxTokens: 81920,
10648
+ maxTokens: 4096,
10615
10649
  },
10616
10650
  "qwen/qwen3.5-397b-a17b": {
10617
10651
  id: "qwen/qwen3.5-397b-a17b",
@@ -11251,13 +11285,13 @@ export const MODELS = {
11251
11285
  reasoning: true,
11252
11286
  input: ["text"],
11253
11287
  cost: {
11254
- input: 0.98,
11255
- output: 3.08,
11256
- cacheRead: 0.182,
11288
+ input: 0,
11289
+ output: 0,
11290
+ cacheRead: 0,
11257
11291
  cacheWrite: 0,
11258
11292
  },
11259
- contextWindow: 202752,
11260
- maxTokens: 4096,
11293
+ contextWindow: 202800,
11294
+ maxTokens: 202800,
11261
11295
  },
11262
11296
  "z-ai/glm-5v-turbo": {
11263
11297
  id: "z-ai/glm-5v-turbo",
@@ -11336,9 +11370,9 @@ export const MODELS = {
11336
11370
  reasoning: true,
11337
11371
  input: ["text", "image"],
11338
11372
  cost: {
11339
- input: 0.5,
11340
- output: 3,
11341
- cacheRead: 0.049999999999999996,
11373
+ input: 1.5,
11374
+ output: 9,
11375
+ cacheRead: 0.15,
11342
11376
  cacheWrite: 0.08333333333333334,
11343
11377
  },
11344
11378
  contextWindow: 1048576,
@@ -11375,7 +11409,7 @@ export const MODELS = {
11375
11409
  cacheRead: 0.25,
11376
11410
  cacheWrite: 0,
11377
11411
  },
11378
- contextWindow: 262142,
11412
+ contextWindow: 262144,
11379
11413
  maxTokens: 262142,
11380
11414
  },
11381
11415
  "~openai/gpt-latest": {
@@ -12281,6 +12315,23 @@ export const MODELS = {
12281
12315
  contextWindow: 1000000,
12282
12316
  maxTokens: 64000,
12283
12317
  },
12318
+ "google/gemini-3.5-flash": {
12319
+ id: "google/gemini-3.5-flash",
12320
+ name: "Gemini 3.5 Flash",
12321
+ api: "anthropic-messages",
12322
+ provider: "vercel-ai-gateway",
12323
+ baseUrl: "https://ai-gateway.vercel.sh",
12324
+ reasoning: true,
12325
+ input: ["text", "image"],
12326
+ cost: {
12327
+ input: 1.5,
12328
+ output: 9,
12329
+ cacheRead: 0.15,
12330
+ cacheWrite: 0,
12331
+ },
12332
+ contextWindow: 1000000,
12333
+ maxTokens: 64000,
12334
+ },
12284
12335
  "google/gemma-4-26b-a4b-it": {
12285
12336
  id: "google/gemma-4-26b-a4b-it",
12286
12337
  name: "Gemma 4 26B A4B IT",
@@ -13590,125 +13641,6 @@ export const MODELS = {
13590
13641
  contextWindow: 200000,
13591
13642
  maxTokens: 8000,
13592
13643
  },
13593
- "xai/grok-3": {
13594
- id: "xai/grok-3",
13595
- name: "Grok 3 Beta",
13596
- api: "anthropic-messages",
13597
- provider: "vercel-ai-gateway",
13598
- baseUrl: "https://ai-gateway.vercel.sh",
13599
- reasoning: false,
13600
- input: ["text"],
13601
- cost: {
13602
- input: 3,
13603
- output: 15,
13604
- cacheRead: 0.75,
13605
- cacheWrite: 0,
13606
- },
13607
- contextWindow: 131072,
13608
- maxTokens: 131072,
13609
- },
13610
- "xai/grok-3-fast": {
13611
- id: "xai/grok-3-fast",
13612
- name: "Grok 3 Fast Beta",
13613
- api: "anthropic-messages",
13614
- provider: "vercel-ai-gateway",
13615
- baseUrl: "https://ai-gateway.vercel.sh",
13616
- reasoning: false,
13617
- input: ["text"],
13618
- cost: {
13619
- input: 5,
13620
- output: 25,
13621
- cacheRead: 1.25,
13622
- cacheWrite: 0,
13623
- },
13624
- contextWindow: 131072,
13625
- maxTokens: 131072,
13626
- },
13627
- "xai/grok-3-mini": {
13628
- id: "xai/grok-3-mini",
13629
- name: "Grok 3 Mini Beta",
13630
- api: "anthropic-messages",
13631
- provider: "vercel-ai-gateway",
13632
- baseUrl: "https://ai-gateway.vercel.sh",
13633
- reasoning: false,
13634
- input: ["text"],
13635
- cost: {
13636
- input: 0.3,
13637
- output: 0.5,
13638
- cacheRead: 0.075,
13639
- cacheWrite: 0,
13640
- },
13641
- contextWindow: 131072,
13642
- maxTokens: 131072,
13643
- },
13644
- "xai/grok-3-mini-fast": {
13645
- id: "xai/grok-3-mini-fast",
13646
- name: "Grok 3 Mini Fast Beta",
13647
- api: "anthropic-messages",
13648
- provider: "vercel-ai-gateway",
13649
- baseUrl: "https://ai-gateway.vercel.sh",
13650
- reasoning: false,
13651
- input: ["text"],
13652
- cost: {
13653
- input: 0.6,
13654
- output: 4,
13655
- cacheRead: 0,
13656
- cacheWrite: 0,
13657
- },
13658
- contextWindow: 131072,
13659
- maxTokens: 131072,
13660
- },
13661
- "xai/grok-4": {
13662
- id: "xai/grok-4",
13663
- name: "Grok 4",
13664
- api: "anthropic-messages",
13665
- provider: "vercel-ai-gateway",
13666
- baseUrl: "https://ai-gateway.vercel.sh",
13667
- reasoning: true,
13668
- input: ["text", "image"],
13669
- cost: {
13670
- input: 3,
13671
- output: 15,
13672
- cacheRead: 0.75,
13673
- cacheWrite: 0,
13674
- },
13675
- contextWindow: 256000,
13676
- maxTokens: 256000,
13677
- },
13678
- "xai/grok-4-fast-non-reasoning": {
13679
- id: "xai/grok-4-fast-non-reasoning",
13680
- name: "Grok 4 Fast Non-Reasoning",
13681
- api: "anthropic-messages",
13682
- provider: "vercel-ai-gateway",
13683
- baseUrl: "https://ai-gateway.vercel.sh",
13684
- reasoning: false,
13685
- input: ["text", "image"],
13686
- cost: {
13687
- input: 0.19999999999999998,
13688
- output: 0.5,
13689
- cacheRead: 0.049999999999999996,
13690
- cacheWrite: 0,
13691
- },
13692
- contextWindow: 2000000,
13693
- maxTokens: 256000,
13694
- },
13695
- "xai/grok-4-fast-reasoning": {
13696
- id: "xai/grok-4-fast-reasoning",
13697
- name: "Grok 4 Fast Reasoning",
13698
- api: "anthropic-messages",
13699
- provider: "vercel-ai-gateway",
13700
- baseUrl: "https://ai-gateway.vercel.sh",
13701
- reasoning: true,
13702
- input: ["text", "image"],
13703
- cost: {
13704
- input: 0.19999999999999998,
13705
- output: 0.5,
13706
- cacheRead: 0.049999999999999996,
13707
- cacheWrite: 0,
13708
- },
13709
- contextWindow: 2000000,
13710
- maxTokens: 256000,
13711
- },
13712
13644
  "xai/grok-4.1-fast-non-reasoning": {
13713
13645
  id: "xai/grok-4.1-fast-non-reasoning",
13714
13646
  name: "Grok 4.1 Fast Non-Reasoning",
@@ -13723,8 +13655,8 @@ export const MODELS = {
13723
13655
  cacheRead: 0.049999999999999996,
13724
13656
  cacheWrite: 0,
13725
13657
  },
13726
- contextWindow: 2000000,
13727
- maxTokens: 30000,
13658
+ contextWindow: 1000000,
13659
+ maxTokens: 1000000,
13728
13660
  },
13729
13661
  "xai/grok-4.1-fast-reasoning": {
13730
13662
  id: "xai/grok-4.1-fast-reasoning",
@@ -13740,8 +13672,8 @@ export const MODELS = {
13740
13672
  cacheRead: 0.049999999999999996,
13741
13673
  cacheWrite: 0,
13742
13674
  },
13743
- contextWindow: 2000000,
13744
- maxTokens: 30000,
13675
+ contextWindow: 1000000,
13676
+ maxTokens: 1000000,
13745
13677
  },
13746
13678
  "xai/grok-4.20-multi-agent": {
13747
13679
  id: "xai/grok-4.20-multi-agent",
@@ -13862,23 +13794,6 @@ export const MODELS = {
13862
13794
  contextWindow: 1000000,
13863
13795
  maxTokens: 1000000,
13864
13796
  },
13865
- "xai/grok-code-fast-1": {
13866
- id: "xai/grok-code-fast-1",
13867
- name: "Grok Code Fast 1",
13868
- api: "anthropic-messages",
13869
- provider: "vercel-ai-gateway",
13870
- baseUrl: "https://ai-gateway.vercel.sh",
13871
- reasoning: true,
13872
- input: ["text"],
13873
- cost: {
13874
- input: 0.19999999999999998,
13875
- output: 1.5,
13876
- cacheRead: 0.02,
13877
- cacheWrite: 0,
13878
- },
13879
- contextWindow: 256000,
13880
- maxTokens: 256000,
13881
- },
13882
13797
  "xiaomi/mimo-v2-flash": {
13883
13798
  id: "xiaomi/mimo-v2-flash",
13884
13799
  name: "MiMo V2 Flash",
@@ -14272,227 +14187,6 @@ export const MODELS = {
14272
14187
  contextWindow: 8192,
14273
14188
  maxTokens: 4096,
14274
14189
  },
14275
- "grok-3": {
14276
- id: "grok-3",
14277
- name: "Grok 3",
14278
- api: "openai-completions",
14279
- provider: "xai",
14280
- baseUrl: "https://api.x.ai/v1",
14281
- reasoning: false,
14282
- input: ["text"],
14283
- cost: {
14284
- input: 3,
14285
- output: 15,
14286
- cacheRead: 0.75,
14287
- cacheWrite: 0,
14288
- },
14289
- contextWindow: 131072,
14290
- maxTokens: 8192,
14291
- },
14292
- "grok-3-fast": {
14293
- id: "grok-3-fast",
14294
- name: "Grok 3 Fast",
14295
- api: "openai-completions",
14296
- provider: "xai",
14297
- baseUrl: "https://api.x.ai/v1",
14298
- reasoning: false,
14299
- input: ["text"],
14300
- cost: {
14301
- input: 5,
14302
- output: 25,
14303
- cacheRead: 1.25,
14304
- cacheWrite: 0,
14305
- },
14306
- contextWindow: 131072,
14307
- maxTokens: 8192,
14308
- },
14309
- "grok-3-fast-latest": {
14310
- id: "grok-3-fast-latest",
14311
- name: "Grok 3 Fast Latest",
14312
- api: "openai-completions",
14313
- provider: "xai",
14314
- baseUrl: "https://api.x.ai/v1",
14315
- reasoning: false,
14316
- input: ["text"],
14317
- cost: {
14318
- input: 5,
14319
- output: 25,
14320
- cacheRead: 1.25,
14321
- cacheWrite: 0,
14322
- },
14323
- contextWindow: 131072,
14324
- maxTokens: 8192,
14325
- },
14326
- "grok-3-latest": {
14327
- id: "grok-3-latest",
14328
- name: "Grok 3 Latest",
14329
- api: "openai-completions",
14330
- provider: "xai",
14331
- baseUrl: "https://api.x.ai/v1",
14332
- reasoning: false,
14333
- input: ["text"],
14334
- cost: {
14335
- input: 3,
14336
- output: 15,
14337
- cacheRead: 0.75,
14338
- cacheWrite: 0,
14339
- },
14340
- contextWindow: 131072,
14341
- maxTokens: 8192,
14342
- },
14343
- "grok-3-mini": {
14344
- id: "grok-3-mini",
14345
- name: "Grok 3 Mini",
14346
- api: "openai-completions",
14347
- provider: "xai",
14348
- baseUrl: "https://api.x.ai/v1",
14349
- reasoning: true,
14350
- input: ["text"],
14351
- cost: {
14352
- input: 0.3,
14353
- output: 0.5,
14354
- cacheRead: 0.075,
14355
- cacheWrite: 0,
14356
- },
14357
- contextWindow: 131072,
14358
- maxTokens: 8192,
14359
- },
14360
- "grok-3-mini-fast": {
14361
- id: "grok-3-mini-fast",
14362
- name: "Grok 3 Mini Fast",
14363
- api: "openai-completions",
14364
- provider: "xai",
14365
- baseUrl: "https://api.x.ai/v1",
14366
- reasoning: true,
14367
- input: ["text"],
14368
- cost: {
14369
- input: 0.6,
14370
- output: 4,
14371
- cacheRead: 0.15,
14372
- cacheWrite: 0,
14373
- },
14374
- contextWindow: 131072,
14375
- maxTokens: 8192,
14376
- },
14377
- "grok-3-mini-fast-latest": {
14378
- id: "grok-3-mini-fast-latest",
14379
- name: "Grok 3 Mini Fast Latest",
14380
- api: "openai-completions",
14381
- provider: "xai",
14382
- baseUrl: "https://api.x.ai/v1",
14383
- reasoning: true,
14384
- input: ["text"],
14385
- cost: {
14386
- input: 0.6,
14387
- output: 4,
14388
- cacheRead: 0.15,
14389
- cacheWrite: 0,
14390
- },
14391
- contextWindow: 131072,
14392
- maxTokens: 8192,
14393
- },
14394
- "grok-3-mini-latest": {
14395
- id: "grok-3-mini-latest",
14396
- name: "Grok 3 Mini Latest",
14397
- api: "openai-completions",
14398
- provider: "xai",
14399
- baseUrl: "https://api.x.ai/v1",
14400
- reasoning: true,
14401
- input: ["text"],
14402
- cost: {
14403
- input: 0.3,
14404
- output: 0.5,
14405
- cacheRead: 0.075,
14406
- cacheWrite: 0,
14407
- },
14408
- contextWindow: 131072,
14409
- maxTokens: 8192,
14410
- },
14411
- "grok-4": {
14412
- id: "grok-4",
14413
- name: "Grok 4",
14414
- api: "openai-completions",
14415
- provider: "xai",
14416
- baseUrl: "https://api.x.ai/v1",
14417
- reasoning: true,
14418
- input: ["text"],
14419
- cost: {
14420
- input: 3,
14421
- output: 15,
14422
- cacheRead: 0.75,
14423
- cacheWrite: 0,
14424
- },
14425
- contextWindow: 256000,
14426
- maxTokens: 64000,
14427
- },
14428
- "grok-4-1-fast": {
14429
- id: "grok-4-1-fast",
14430
- name: "Grok 4.1 Fast",
14431
- api: "openai-completions",
14432
- provider: "xai",
14433
- baseUrl: "https://api.x.ai/v1",
14434
- reasoning: true,
14435
- input: ["text", "image"],
14436
- cost: {
14437
- input: 0.2,
14438
- output: 0.5,
14439
- cacheRead: 0.05,
14440
- cacheWrite: 0,
14441
- },
14442
- contextWindow: 2000000,
14443
- maxTokens: 30000,
14444
- },
14445
- "grok-4-1-fast-non-reasoning": {
14446
- id: "grok-4-1-fast-non-reasoning",
14447
- name: "Grok 4.1 Fast (Non-Reasoning)",
14448
- api: "openai-completions",
14449
- provider: "xai",
14450
- baseUrl: "https://api.x.ai/v1",
14451
- reasoning: false,
14452
- input: ["text", "image"],
14453
- cost: {
14454
- input: 0.2,
14455
- output: 0.5,
14456
- cacheRead: 0.05,
14457
- cacheWrite: 0,
14458
- },
14459
- contextWindow: 2000000,
14460
- maxTokens: 30000,
14461
- },
14462
- "grok-4-fast": {
14463
- id: "grok-4-fast",
14464
- name: "Grok 4 Fast",
14465
- api: "openai-completions",
14466
- provider: "xai",
14467
- baseUrl: "https://api.x.ai/v1",
14468
- reasoning: true,
14469
- input: ["text", "image"],
14470
- cost: {
14471
- input: 0.2,
14472
- output: 0.5,
14473
- cacheRead: 0.05,
14474
- cacheWrite: 0,
14475
- },
14476
- contextWindow: 2000000,
14477
- maxTokens: 30000,
14478
- },
14479
- "grok-4-fast-non-reasoning": {
14480
- id: "grok-4-fast-non-reasoning",
14481
- name: "Grok 4 Fast (Non-Reasoning)",
14482
- api: "openai-completions",
14483
- provider: "xai",
14484
- baseUrl: "https://api.x.ai/v1",
14485
- reasoning: false,
14486
- input: ["text", "image"],
14487
- cost: {
14488
- input: 0.2,
14489
- output: 0.5,
14490
- cacheRead: 0.05,
14491
- cacheWrite: 0,
14492
- },
14493
- contextWindow: 2000000,
14494
- maxTokens: 30000,
14495
- },
14496
14190
  "grok-4.20-0309-non-reasoning": {
14497
14191
  id: "grok-4.20-0309-non-reasoning",
14498
14192
  name: "Grok 4.20 (Non-Reasoning)",
@@ -14567,7 +14261,7 @@ export const MODELS = {
14567
14261
  api: "openai-completions",
14568
14262
  provider: "xai",
14569
14263
  baseUrl: "https://api.x.ai/v1",
14570
- reasoning: true,
14264
+ reasoning: false,
14571
14265
  input: ["text"],
14572
14266
  cost: {
14573
14267
  input: 0.2,
@@ -14575,8 +14269,8 @@ export const MODELS = {
14575
14269
  cacheRead: 0.02,
14576
14270
  cacheWrite: 0,
14577
14271
  },
14578
- contextWindow: 256000,
14579
- maxTokens: 10000,
14272
+ contextWindow: 32768,
14273
+ maxTokens: 8192,
14580
14274
  },
14581
14275
  "grok-vision-beta": {
14582
14276
  id: "grok-vision-beta",