@dreb/ai 2.61.2 → 2.62.0

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.
@@ -776,10 +776,10 @@ export const MODELS = {
776
776
  reasoning: true,
777
777
  input: ["text", "image"],
778
778
  cost: {
779
- input: 0.22,
780
- output: 1.32,
781
- cacheRead: 0.022,
782
- cacheWrite: 0.275,
779
+ input: 0.2,
780
+ output: 1.2,
781
+ cacheRead: 0.02,
782
+ cacheWrite: 0.25,
783
783
  },
784
784
  contextWindow: 1050000,
785
785
  maxTokens: 128000,
@@ -793,10 +793,10 @@ export const MODELS = {
793
793
  reasoning: true,
794
794
  input: ["text", "image"],
795
795
  cost: {
796
- input: 5.5,
797
- output: 33,
798
- cacheRead: 0.55,
799
- cacheWrite: 6.875,
796
+ input: 4,
797
+ output: 20,
798
+ cacheRead: 0.4,
799
+ cacheWrite: 5,
800
800
  },
801
801
  contextWindow: 1050000,
802
802
  maxTokens: 128000,
@@ -810,10 +810,10 @@ export const MODELS = {
810
810
  reasoning: true,
811
811
  input: ["text", "image"],
812
812
  cost: {
813
- input: 2.2,
814
- output: 13.2,
815
- cacheRead: 0.22,
816
- cacheWrite: 2.75,
813
+ input: 2,
814
+ output: 12,
815
+ cacheRead: 0.2,
816
+ cacheWrite: 2.5,
817
817
  },
818
818
  contextWindow: 1050000,
819
819
  maxTokens: 128000,
@@ -1422,10 +1422,10 @@ export const MODELS = {
1422
1422
  reasoning: true,
1423
1423
  input: ["text", "image"],
1424
1424
  cost: {
1425
- input: 5.5,
1426
- output: 33,
1427
- cacheRead: 0.55,
1428
- cacheWrite: 6.875,
1425
+ input: 4.4,
1426
+ output: 22,
1427
+ cacheRead: 0.44,
1428
+ cacheWrite: 5.5,
1429
1429
  },
1430
1430
  contextWindow: 1050000,
1431
1431
  maxTokens: 128000,
@@ -4556,7 +4556,7 @@ export const MODELS = {
4556
4556
  cacheWrite: 0,
4557
4557
  },
4558
4558
  contextWindow: 204800,
4559
- maxTokens: 128000,
4559
+ maxTokens: 131072,
4560
4560
  },
4561
4561
  "MiniMaxAI/MiniMax-M2.1": {
4562
4562
  id: "MiniMaxAI/MiniMax-M2.1",
@@ -4628,7 +4628,7 @@ export const MODELS = {
4628
4628
  cacheWrite: 0,
4629
4629
  },
4630
4630
  contextWindow: 524288,
4631
- maxTokens: 128000,
4631
+ maxTokens: 512000,
4632
4632
  },
4633
4633
  "Qwen/Qwen2.5-Coder-32B-Instruct": {
4634
4634
  id: "Qwen/Qwen2.5-Coder-32B-Instruct",
@@ -5008,6 +5008,24 @@ export const MODELS = {
5008
5008
  contextWindow: 262144,
5009
5009
  maxTokens: 131072,
5010
5010
  },
5011
+ "Qwen/Qwen3.8-27B": {
5012
+ id: "Qwen/Qwen3.8-27B",
5013
+ name: "Qwen3.8 27B",
5014
+ api: "openai-completions",
5015
+ provider: "huggingface",
5016
+ baseUrl: "https://router.huggingface.co/v1",
5017
+ compat: { "supportsDeveloperRole": false },
5018
+ reasoning: true,
5019
+ input: ["text", "image"],
5020
+ cost: {
5021
+ input: 0.4,
5022
+ output: 3,
5023
+ cacheRead: 0,
5024
+ cacheWrite: 0,
5025
+ },
5026
+ contextWindow: 262144,
5027
+ maxTokens: 32768,
5028
+ },
5011
5029
  "XiaomiMiMo/MiMo-V2-Flash": {
5012
5030
  id: "XiaomiMiMo/MiMo-V2-Flash",
5013
5031
  name: "MiMo-V2-Flash",
@@ -5746,6 +5764,24 @@ export const MODELS = {
5746
5764
  contextWindow: 262144,
5747
5765
  maxTokens: 131072,
5748
5766
  },
5767
+ "zai-org/GLM-5.3-Flash": {
5768
+ id: "zai-org/GLM-5.3-Flash",
5769
+ name: "GLM-5.3-Flash",
5770
+ api: "openai-completions",
5771
+ provider: "huggingface",
5772
+ baseUrl: "https://router.huggingface.co/v1",
5773
+ compat: { "supportsDeveloperRole": false },
5774
+ reasoning: true,
5775
+ input: ["text"],
5776
+ cost: {
5777
+ input: 0.15,
5778
+ output: 0.5,
5779
+ cacheRead: 0,
5780
+ cacheWrite: 0,
5781
+ },
5782
+ contextWindow: 1048576,
5783
+ maxTokens: 131072,
5784
+ },
5749
5785
  },
5750
5786
  "kimi-coding": {
5751
5787
  "k2p5": {
@@ -6490,6 +6526,23 @@ export const MODELS = {
6490
6526
  contextWindow: 32000,
6491
6527
  maxTokens: 32000,
6492
6528
  },
6529
+ "zai-glm-5-2": {
6530
+ id: "zai-glm-5-2",
6531
+ name: "GLM-5.2",
6532
+ api: "mistral-conversations",
6533
+ provider: "mistral",
6534
+ baseUrl: "https://api.mistral.ai",
6535
+ reasoning: true,
6536
+ input: ["text"],
6537
+ cost: {
6538
+ input: 1.4,
6539
+ output: 4.4,
6540
+ cacheRead: 0.14,
6541
+ cacheWrite: 0,
6542
+ },
6543
+ contextWindow: 1000000,
6544
+ maxTokens: 131072,
6545
+ },
6493
6546
  },
6494
6547
  "openai": {
6495
6548
  "gpt-4": {
@@ -8400,23 +8453,6 @@ export const MODELS = {
8400
8453
  contextWindow: 262144,
8401
8454
  maxTokens: 65536,
8402
8455
  },
8403
- "x-preview-f-free": {
8404
- id: "x-preview-f-free",
8405
- name: "Ox Alpha Free (Unlimited)",
8406
- api: "openai-completions",
8407
- provider: "opencode",
8408
- baseUrl: "https://opencode.ai/zen/v1",
8409
- reasoning: true,
8410
- input: ["text", "image"],
8411
- cost: {
8412
- input: 0,
8413
- output: 0,
8414
- cacheRead: 0,
8415
- cacheWrite: 0,
8416
- },
8417
- contextWindow: 1000000,
8418
- maxTokens: 131072,
8419
- },
8420
8456
  },
8421
8457
  "opencode-go": {
8422
8458
  "deepseek-v4-flash": {
@@ -8521,6 +8557,23 @@ export const MODELS = {
8521
8557
  contextWindow: 1000000,
8522
8558
  maxTokens: 131072,
8523
8559
  },
8560
+ "glm-5.3-flash": {
8561
+ id: "glm-5.3-flash",
8562
+ name: "GLM-5.3-Flash (2x usage)",
8563
+ api: "openai-completions",
8564
+ provider: "opencode-go",
8565
+ baseUrl: "https://opencode.ai/zen/go/v1",
8566
+ reasoning: true,
8567
+ input: ["text", "image"],
8568
+ cost: {
8569
+ input: 0.075,
8570
+ output: 0.25,
8571
+ cacheRead: 0.015,
8572
+ cacheWrite: 0,
8573
+ },
8574
+ contextWindow: 1000000,
8575
+ maxTokens: 131072,
8576
+ },
8524
8577
  "gpt-5.6-luna": {
8525
8578
  id: "gpt-5.6-luna",
8526
8579
  name: "GPT-5.6 Luna",
@@ -8725,23 +8778,6 @@ export const MODELS = {
8725
8778
  contextWindow: 1048576,
8726
8779
  maxTokens: 131072,
8727
8780
  },
8728
- "ox-alpha-free": {
8729
- id: "ox-alpha-free",
8730
- name: "Ox Alpha Free (Unlimited)",
8731
- api: "openai-completions",
8732
- provider: "opencode-go",
8733
- baseUrl: "https://opencode.ai/zen/go/v1",
8734
- reasoning: true,
8735
- input: ["text", "image"],
8736
- cost: {
8737
- input: 0,
8738
- output: 0,
8739
- cacheRead: 0,
8740
- cacheWrite: 0,
8741
- },
8742
- contextWindow: 1000000,
8743
- maxTokens: 131072,
8744
- },
8745
8781
  "qwen3.6-plus": {
8746
8782
  id: "qwen3.6-plus",
8747
8783
  name: "Qwen3.6 Plus",
@@ -9773,9 +9809,9 @@ export const MODELS = {
9773
9809
  reasoning: true,
9774
9810
  input: ["text"],
9775
9811
  cost: {
9776
- input: 0.0798,
9777
- output: 0.1596,
9778
- cacheRead: 0.01596,
9812
+ input: 0.07798000000000001,
9813
+ output: 0.15596000000000002,
9814
+ cacheRead: 0.015595999999999999,
9779
9815
  cacheWrite: 0,
9780
9816
  },
9781
9817
  contextWindow: 1048576,
@@ -9790,9 +9826,9 @@ export const MODELS = {
9790
9826
  reasoning: true,
9791
9827
  input: ["text"],
9792
9828
  cost: {
9793
- input: 0.04,
9794
- output: 0.08,
9795
- cacheRead: 0.008,
9829
+ input: 0.049999999999999996,
9830
+ output: 0.09999999999999999,
9831
+ cacheRead: 0.01,
9796
9832
  cacheWrite: 0,
9797
9833
  },
9798
9834
  contextWindow: 1310720,
@@ -9824,9 +9860,9 @@ export const MODELS = {
9824
9860
  reasoning: true,
9825
9861
  input: ["text"],
9826
9862
  cost: {
9827
- input: 0.55593,
9828
- output: 1.11186,
9829
- cacheRead: 0.0463275,
9863
+ input: 0.87,
9864
+ output: 1.74,
9865
+ cacheRead: 0.0725,
9830
9866
  cacheWrite: 0,
9831
9867
  },
9832
9868
  contextWindow: 1048576,
@@ -10368,13 +10404,13 @@ export const MODELS = {
10368
10404
  reasoning: true,
10369
10405
  input: ["text", "image"],
10370
10406
  cost: {
10371
- input: 0.09999999999999999,
10407
+ input: 0.09,
10372
10408
  output: 0.33999999999999997,
10373
- cacheRead: 0.09999999999999999,
10409
+ cacheRead: 0.049999999999999996,
10374
10410
  cacheWrite: 0,
10375
10411
  },
10376
10412
  contextWindow: 262144,
10377
- maxTokens: 235929,
10413
+ maxTokens: 16384,
10378
10414
  },
10379
10415
  "google/gemma-4-31b-it:free": {
10380
10416
  id: "google/gemma-4-31b-it:free",
@@ -10444,6 +10480,23 @@ export const MODELS = {
10444
10480
  contextWindow: 262144,
10445
10481
  maxTokens: 32768,
10446
10482
  },
10483
+ "inclusionai/ling-3.0-flash-fin:free": {
10484
+ id: "inclusionai/ling-3.0-flash-fin:free",
10485
+ name: "Ling 3.0 Flash Fin (free)",
10486
+ api: "openai-completions",
10487
+ provider: "openrouter",
10488
+ baseUrl: "https://openrouter.ai/api/v1",
10489
+ reasoning: true,
10490
+ input: ["text"],
10491
+ cost: {
10492
+ input: 0,
10493
+ output: 0,
10494
+ cacheRead: 0,
10495
+ cacheWrite: 0,
10496
+ },
10497
+ contextWindow: 262144,
10498
+ maxTokens: 32768,
10499
+ },
10447
10500
  "kwaipilot/kat-coder-air-v2.5": {
10448
10501
  id: "kwaipilot/kat-coder-air-v2.5",
10449
10502
  name: "Kwaipilot: KAT-Coder-Air V2.5",
@@ -10572,13 +10625,13 @@ export const MODELS = {
10572
10625
  reasoning: false,
10573
10626
  input: ["text"],
10574
10627
  cost: {
10575
- input: 0.09999999999999999,
10576
- output: 0.32,
10577
- cacheRead: 0,
10628
+ input: 0.71,
10629
+ output: 0.71,
10630
+ cacheRead: 0.71,
10578
10631
  cacheWrite: 0,
10579
10632
  },
10580
10633
  contextWindow: 131072,
10581
- maxTokens: 16384,
10634
+ maxTokens: 115200,
10582
10635
  },
10583
10636
  "meta-llama/llama-4-maverick": {
10584
10637
  id: "meta-llama/llama-4-maverick",
@@ -10606,13 +10659,13 @@ export const MODELS = {
10606
10659
  reasoning: false,
10607
10660
  input: ["text", "image"],
10608
10661
  cost: {
10609
- input: 0.09999999999999999,
10610
- output: 0.3,
10611
- cacheRead: 0,
10662
+ input: 0.11,
10663
+ output: 0.33999999999999997,
10664
+ cacheRead: 0.055,
10612
10665
  cacheWrite: 0,
10613
10666
  },
10614
10667
  contextWindow: 1310720,
10615
- maxTokens: 16384,
10668
+ maxTokens: 8192,
10616
10669
  },
10617
10670
  "meta/muse-glimmer-30b": {
10618
10671
  id: "meta/muse-glimmer-30b",
@@ -11218,9 +11271,9 @@ export const MODELS = {
11218
11271
  reasoning: true,
11219
11272
  input: ["text", "image"],
11220
11273
  cost: {
11221
- input: 0.67,
11274
+ input: 0.66,
11222
11275
  output: 3.4,
11223
- cacheRead: 0.19,
11276
+ cacheRead: 0.18,
11224
11277
  cacheWrite: 0,
11225
11278
  },
11226
11279
  contextWindow: 262144,
@@ -11305,11 +11358,11 @@ export const MODELS = {
11305
11358
  cost: {
11306
11359
  input: 0.049999999999999996,
11307
11360
  output: 0.19999999999999998,
11308
- cacheRead: 0.03,
11361
+ cacheRead: 0.024999999999999998,
11309
11362
  cacheWrite: 0,
11310
11363
  },
11311
11364
  contextWindow: 262144,
11312
- maxTokens: 235929,
11365
+ maxTokens: 228000,
11313
11366
  },
11314
11367
  "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free": {
11315
11368
  id: "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
@@ -13156,13 +13209,13 @@ export const MODELS = {
13156
13209
  reasoning: false,
13157
13210
  input: ["text"],
13158
13211
  cost: {
13159
- input: 0.09,
13160
- output: 0.55,
13161
- cacheRead: 0,
13212
+ input: 0.0875,
13213
+ output: 0.35,
13214
+ cacheRead: 0.0175,
13162
13215
  cacheWrite: 0,
13163
13216
  },
13164
13217
  contextWindow: 262144,
13165
- maxTokens: 16384,
13218
+ maxTokens: 235929,
13166
13219
  },
13167
13220
  "qwen/qwen3-235b-a22b-thinking-2507": {
13168
13221
  id: "qwen/qwen3-235b-a22b-thinking-2507",
@@ -13598,13 +13651,13 @@ export const MODELS = {
13598
13651
  reasoning: true,
13599
13652
  input: ["text", "image"],
13600
13653
  cost: {
13601
- input: 0.5,
13602
- output: 3.5999999999999996,
13603
- cacheRead: 0.3,
13654
+ input: 0.39,
13655
+ output: 2.34,
13656
+ cacheRead: 0,
13604
13657
  cacheWrite: 0,
13605
13658
  },
13606
13659
  contextWindow: 262144,
13607
- maxTokens: 235929,
13660
+ maxTokens: 65536,
13608
13661
  },
13609
13662
  "qwen/qwen3.5-9b": {
13610
13663
  id: "qwen/qwen3.5-9b",
@@ -13683,13 +13736,13 @@ export const MODELS = {
13683
13736
  reasoning: true,
13684
13737
  input: ["text", "image"],
13685
13738
  cost: {
13686
- input: 0.32,
13687
- output: 3.1999999999999997,
13688
- cacheRead: 0,
13739
+ input: 0.6,
13740
+ output: 3.5999999999999996,
13741
+ cacheRead: 0.12,
13689
13742
  cacheWrite: 0,
13690
13743
  },
13691
13744
  contextWindow: 262144,
13692
- maxTokens: 81920,
13745
+ maxTokens: 235929,
13693
13746
  },
13694
13747
  "qwen/qwen3.6-35b-a3b": {
13695
13748
  id: "qwen/qwen3.6-35b-a3b",
@@ -13700,8 +13753,8 @@ export const MODELS = {
13700
13753
  reasoning: true,
13701
13754
  input: ["text", "image"],
13702
13755
  cost: {
13703
- input: 0.14,
13704
- output: 1,
13756
+ input: 0.09999999999999999,
13757
+ output: 0.8999999999999999,
13705
13758
  cacheRead: 0.049999999999999996,
13706
13759
  cacheWrite: 0,
13707
13760
  },
@@ -13844,6 +13897,23 @@ export const MODELS = {
13844
13897
  contextWindow: 1000000,
13845
13898
  maxTokens: 131072,
13846
13899
  },
13900
+ "qwen/qwen3.8-flash": {
13901
+ id: "qwen/qwen3.8-flash",
13902
+ name: "Qwen: Qwen3.8 Flash",
13903
+ api: "openai-completions",
13904
+ provider: "openrouter",
13905
+ baseUrl: "https://openrouter.ai/api/v1",
13906
+ reasoning: true,
13907
+ input: ["text", "image"],
13908
+ cost: {
13909
+ input: 0.15,
13910
+ output: 0.47,
13911
+ cacheRead: 0.016,
13912
+ cacheWrite: 0.19999999999999998,
13913
+ },
13914
+ contextWindow: 1000000,
13915
+ maxTokens: 131072,
13916
+ },
13847
13917
  "qwen/qwen3.8-max": {
13848
13918
  id: "qwen/qwen3.8-max",
13849
13919
  name: "Qwen: Qwen3.8 Max",
@@ -13946,23 +14016,6 @@ export const MODELS = {
13946
14016
  contextWindow: 131072,
13947
14017
  maxTokens: 16384,
13948
14018
  },
13949
- "stealth/ox-alpha": {
13950
- id: "stealth/ox-alpha",
13951
- name: "Ox Alpha",
13952
- api: "openai-completions",
13953
- provider: "openrouter",
13954
- baseUrl: "https://openrouter.ai/api/v1",
13955
- reasoning: true,
13956
- input: ["text", "image"],
13957
- cost: {
13958
- input: 0,
13959
- output: 0,
13960
- cacheRead: 0,
13961
- cacheWrite: 0,
13962
- },
13963
- contextWindow: 1048576,
13964
- maxTokens: 131072,
13965
- },
13966
14019
  "stepfun/step-3.5-flash": {
13967
14020
  id: "stepfun/step-3.5-flash",
13968
14021
  name: "StepFun: Step 3.5 Flash",
@@ -14006,9 +14059,9 @@ export const MODELS = {
14006
14059
  reasoning: true,
14007
14060
  input: ["text"],
14008
14061
  cost: {
14009
- input: 0.13199999999999998,
14010
- output: 0.5279999999999999,
14011
- cacheRead: 0.032999999999999995,
14062
+ input: 0.0825,
14063
+ output: 0.33,
14064
+ cacheRead: 0.020625,
14012
14065
  cacheWrite: 0,
14013
14066
  },
14014
14067
  contextWindow: 262144,
@@ -14346,13 +14399,13 @@ export const MODELS = {
14346
14399
  reasoning: true,
14347
14400
  input: ["text"],
14348
14401
  cost: {
14349
- input: 0.5,
14350
- output: 2,
14351
- cacheRead: 0.09999999999999999,
14402
+ input: 0.43,
14403
+ output: 1.75,
14404
+ cacheRead: 0.08,
14352
14405
  cacheWrite: 0,
14353
14406
  },
14354
14407
  contextWindow: 204800,
14355
- maxTokens: 131072,
14408
+ maxTokens: 16384,
14356
14409
  },
14357
14410
  "z-ai/glm-4.6v": {
14358
14411
  id: "z-ai/glm-4.6v",
@@ -14473,23 +14526,6 @@ export const MODELS = {
14473
14526
  contextWindow: 1048576,
14474
14527
  maxTokens: 262144,
14475
14528
  },
14476
- "z-ai/glm-5.2:batch": {
14477
- id: "z-ai/glm-5.2:batch",
14478
- name: "Z.ai: GLM 5.2 (batch)",
14479
- api: "openai-completions",
14480
- provider: "openrouter",
14481
- baseUrl: "https://openrouter.ai/api/v1",
14482
- reasoning: true,
14483
- input: ["text"],
14484
- cost: {
14485
- input: 1.4,
14486
- output: 4.4,
14487
- cacheRead: 0.26,
14488
- cacheWrite: 0,
14489
- },
14490
- contextWindow: 1048575,
14491
- maxTokens: 943717,
14492
- },
14493
14529
  "z-ai/glm-5.2:free": {
14494
14530
  id: "z-ai/glm-5.2:free",
14495
14531
  name: "Z.ai: GLM 5.2 (free)",
@@ -14524,6 +14560,23 @@ export const MODELS = {
14524
14560
  contextWindow: 1048576,
14525
14561
  maxTokens: 131072,
14526
14562
  },
14563
+ "z-ai/glm-5.3-flash": {
14564
+ id: "z-ai/glm-5.3-flash",
14565
+ name: "Z.ai: GLM 5.3 Flash",
14566
+ api: "openai-completions",
14567
+ provider: "openrouter",
14568
+ baseUrl: "https://openrouter.ai/api/v1",
14569
+ reasoning: true,
14570
+ input: ["text", "image"],
14571
+ cost: {
14572
+ input: 0.075,
14573
+ output: 0.25,
14574
+ cacheRead: 0.015,
14575
+ cacheWrite: 0,
14576
+ },
14577
+ contextWindow: 1310720,
14578
+ maxTokens: 131072,
14579
+ },
14527
14580
  "z-ai/glm-5v-turbo": {
14528
14581
  id: "z-ai/glm-5v-turbo",
14529
14582
  name: "Z.ai: GLM 5V Turbo",
@@ -14618,13 +14671,13 @@ export const MODELS = {
14618
14671
  reasoning: true,
14619
14672
  input: ["text"],
14620
14673
  cost: {
14621
- input: 0.035,
14674
+ input: 0.03,
14622
14675
  output: 0.09999999999999999,
14623
- cacheRead: 0.008,
14676
+ cacheRead: 0.007,
14624
14677
  cacheWrite: 0,
14625
14678
  },
14626
14679
  contextWindow: 1310720,
14627
- maxTokens: 943718,
14680
+ maxTokens: 131072,
14628
14681
  },
14629
14682
  "~google/gemini-flash-latest": {
14630
14683
  id: "~google/gemini-flash-latest",
@@ -14669,13 +14722,13 @@ export const MODELS = {
14669
14722
  reasoning: true,
14670
14723
  input: ["text", "image"],
14671
14724
  cost: {
14672
- input: 2.6,
14673
- output: 13,
14674
- cacheRead: 0.29,
14725
+ input: 2.5500000000000003,
14726
+ output: 12.75,
14727
+ cacheRead: 0.25599998999999996,
14675
14728
  cacheWrite: 0,
14676
14729
  },
14677
14730
  contextWindow: 1048576,
14678
- maxTokens: 877357,
14731
+ maxTokens: 943718,
14679
14732
  },
14680
14733
  "~openai/gpt-latest": {
14681
14734
  id: "~openai/gpt-latest",
@@ -15206,6 +15259,23 @@ export const MODELS = {
15206
15259
  contextWindow: 1000000,
15207
15260
  maxTokens: 131072,
15208
15261
  },
15262
+ "alibaba/qwen3.8-flash": {
15263
+ id: "alibaba/qwen3.8-flash",
15264
+ name: "Qwen 3.8 Flash",
15265
+ api: "anthropic-messages",
15266
+ provider: "vercel-ai-gateway",
15267
+ baseUrl: "https://ai-gateway.vercel.sh",
15268
+ reasoning: true,
15269
+ input: ["text", "image"],
15270
+ cost: {
15271
+ input: 0.16,
15272
+ output: 0.47,
15273
+ cacheRead: 0.016,
15274
+ cacheWrite: 0.19999999999999998,
15275
+ },
15276
+ contextWindow: 991000,
15277
+ maxTokens: 128000,
15278
+ },
15209
15279
  "alibaba/qwen3.8-max": {
15210
15280
  id: "alibaba/qwen3.8-max",
15211
15281
  name: "Qwen 3.8 Max",
@@ -16056,6 +16126,40 @@ export const MODELS = {
16056
16126
  contextWindow: 256000,
16057
16127
  maxTokens: 32000,
16058
16128
  },
16129
+ "inclusionai/ling-3.0-flash-fin": {
16130
+ id: "inclusionai/ling-3.0-flash-fin",
16131
+ name: "Ling 3.0 Flash Fin",
16132
+ api: "anthropic-messages",
16133
+ provider: "vercel-ai-gateway",
16134
+ baseUrl: "https://ai-gateway.vercel.sh",
16135
+ reasoning: true,
16136
+ input: ["text"],
16137
+ cost: {
16138
+ input: 0,
16139
+ output: 0,
16140
+ cacheRead: 0,
16141
+ cacheWrite: 0,
16142
+ },
16143
+ contextWindow: 256000,
16144
+ maxTokens: 32000,
16145
+ },
16146
+ "inclusionai/ling-3.0-flash-fin-free": {
16147
+ id: "inclusionai/ling-3.0-flash-fin-free",
16148
+ name: "Ling 3.0 Flash Fin (Free)",
16149
+ api: "anthropic-messages",
16150
+ provider: "vercel-ai-gateway",
16151
+ baseUrl: "https://ai-gateway.vercel.sh",
16152
+ reasoning: true,
16153
+ input: ["text"],
16154
+ cost: {
16155
+ input: 0,
16156
+ output: 0,
16157
+ cacheRead: 0,
16158
+ cacheWrite: 0,
16159
+ },
16160
+ contextWindow: 256000,
16161
+ maxTokens: 32000,
16162
+ },
16059
16163
  "interfaze/interfaze-beta": {
16060
16164
  id: "interfaze/interfaze-beta",
16061
16165
  name: "Interfaze Beta",
@@ -16865,8 +16969,8 @@ export const MODELS = {
16865
16969
  input: ["text"],
16866
16970
  cost: {
16867
16971
  input: 0.049999999999999996,
16868
- output: 0.19999999999999998,
16869
- cacheRead: 0.01,
16972
+ output: 0.15,
16973
+ cacheRead: 0.049999999999999996,
16870
16974
  cacheWrite: 0,
16871
16975
  },
16872
16976
  contextWindow: 262144,
@@ -18470,6 +18574,23 @@ export const MODELS = {
18470
18574
  contextWindow: 1000000,
18471
18575
  maxTokens: 12800,
18472
18576
  },
18577
+ "zai/glm-5.3-flash": {
18578
+ id: "zai/glm-5.3-flash",
18579
+ name: "GLM 5.3 Flash",
18580
+ api: "anthropic-messages",
18581
+ provider: "vercel-ai-gateway",
18582
+ baseUrl: "https://ai-gateway.vercel.sh",
18583
+ reasoning: true,
18584
+ input: ["text", "image"],
18585
+ cost: {
18586
+ input: 0.15,
18587
+ output: 0.5,
18588
+ cacheRead: 0.03,
18589
+ cacheWrite: 0,
18590
+ },
18591
+ contextWindow: 1000000,
18592
+ maxTokens: 131000,
18593
+ },
18473
18594
  "zai/glm-5v-turbo": {
18474
18595
  id: "zai/glm-5v-turbo",
18475
18596
  name: "GLM 5V Turbo",