@dreb/ai 2.61.1 → 2.61.2

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.
@@ -2769,10 +2769,10 @@ export const MODELS = {
2769
2769
  reasoning: true,
2770
2770
  input: ["text", "image"],
2771
2771
  cost: {
2772
- input: 5,
2773
- output: 30,
2774
- cacheRead: 0.5,
2775
- cacheWrite: 6.25,
2772
+ input: 4,
2773
+ output: 20,
2774
+ cacheRead: 0.4,
2775
+ cacheWrite: 5,
2776
2776
  },
2777
2777
  contextWindow: 1050000,
2778
2778
  maxTokens: 128000,
@@ -2803,10 +2803,10 @@ export const MODELS = {
2803
2803
  reasoning: true,
2804
2804
  input: ["text", "image"],
2805
2805
  cost: {
2806
- input: 5,
2807
- output: 30,
2808
- cacheRead: 0.5,
2809
- cacheWrite: 6.25,
2806
+ input: 4,
2807
+ output: 20,
2808
+ cacheRead: 0.4,
2809
+ cacheWrite: 5,
2810
2810
  },
2811
2811
  contextWindow: 1050000,
2812
2812
  maxTokens: 128000,
@@ -7011,10 +7011,10 @@ export const MODELS = {
7011
7011
  reasoning: true,
7012
7012
  input: ["text", "image"],
7013
7013
  cost: {
7014
- input: 5,
7015
- output: 30,
7016
- cacheRead: 0.5,
7017
- cacheWrite: 6.25,
7014
+ input: 4,
7015
+ output: 20,
7016
+ cacheRead: 0.4,
7017
+ cacheWrite: 5,
7018
7018
  },
7019
7019
  contextWindow: 1050000,
7020
7020
  maxTokens: 128000,
@@ -7045,10 +7045,10 @@ export const MODELS = {
7045
7045
  reasoning: true,
7046
7046
  input: ["text", "image"],
7047
7047
  cost: {
7048
- input: 5,
7049
- output: 30,
7050
- cacheRead: 0.5,
7051
- cacheWrite: 6.25,
7048
+ input: 4,
7049
+ output: 20,
7050
+ cacheRead: 0.4,
7051
+ cacheWrite: 5,
7052
7052
  },
7053
7053
  contextWindow: 1050000,
7054
7054
  maxTokens: 128000,
@@ -8069,10 +8069,10 @@ export const MODELS = {
8069
8069
  reasoning: true,
8070
8070
  input: ["text", "image"],
8071
8071
  cost: {
8072
- input: 2.5,
8073
- output: 15,
8074
- cacheRead: 0.25,
8075
- cacheWrite: 3.125,
8072
+ input: 2,
8073
+ output: 10,
8074
+ cacheRead: 0.2,
8075
+ cacheWrite: 2.5,
8076
8076
  },
8077
8077
  contextWindow: 1050000,
8078
8078
  maxTokens: 128000,
@@ -8105,7 +8105,7 @@ export const MODELS = {
8105
8105
  cost: {
8106
8106
  input: 2,
8107
8107
  output: 6,
8108
- cacheRead: 0.5,
8108
+ cacheRead: 0.3,
8109
8109
  cacheWrite: 0,
8110
8110
  },
8111
8111
  contextWindow: 500000,
@@ -8538,9 +8538,9 @@ export const MODELS = {
8538
8538
  contextWindow: 1050000,
8539
8539
  maxTokens: 128000,
8540
8540
  },
8541
- "grok-4.5": {
8542
- id: "grok-4.5",
8543
- name: "Grok 4.5",
8541
+ "grok-4.6": {
8542
+ id: "grok-4.6",
8543
+ name: "Grok 4.6",
8544
8544
  api: "openai-responses",
8545
8545
  provider: "opencode-go",
8546
8546
  baseUrl: "https://opencode.ai/zen/go/v1",
@@ -8623,6 +8623,23 @@ export const MODELS = {
8623
8623
  contextWindow: 1048576,
8624
8624
  maxTokens: 131072,
8625
8625
  },
8626
+ "longcat-2.0": {
8627
+ id: "longcat-2.0",
8628
+ name: "LongCat-2.0",
8629
+ api: "openai-completions",
8630
+ provider: "opencode-go",
8631
+ baseUrl: "https://opencode.ai/zen/go/v1",
8632
+ reasoning: true,
8633
+ input: ["text"],
8634
+ cost: {
8635
+ input: 0.3,
8636
+ output: 1.2,
8637
+ cacheRead: 0.006,
8638
+ cacheWrite: 0,
8639
+ },
8640
+ contextWindow: 1000000,
8641
+ maxTokens: 131072,
8642
+ },
8626
8643
  "mimo-v2.5": {
8627
8644
  id: "mimo-v2.5",
8628
8645
  name: "MiMo V2.5",
@@ -9422,7 +9439,7 @@ export const MODELS = {
9422
9439
  cacheWrite: 0,
9423
9440
  },
9424
9441
  contextWindow: 262144,
9425
- maxTokens: 262144,
9442
+ maxTokens: 235929,
9426
9443
  },
9427
9444
  "arcee-ai/virtuoso-large": {
9428
9445
  id: "arcee-ai/virtuoso-large",
@@ -9507,7 +9524,7 @@ export const MODELS = {
9507
9524
  cacheWrite: 0,
9508
9525
  },
9509
9526
  contextWindow: 262144,
9510
- maxTokens: 262144,
9527
+ maxTokens: 235929,
9511
9528
  },
9512
9529
  "bytedance-seed/seed-2.0-code": {
9513
9530
  id: "bytedance-seed/seed-2.0-code",
@@ -9643,7 +9660,7 @@ export const MODELS = {
9643
9660
  cacheWrite: 0,
9644
9661
  },
9645
9662
  contextWindow: 163840,
9646
- maxTokens: 163840,
9663
+ maxTokens: 147456,
9647
9664
  },
9648
9665
  "deepseek/deepseek-chat-v3.1": {
9649
9666
  id: "deepseek/deepseek-chat-v3.1",
@@ -9654,13 +9671,13 @@ export const MODELS = {
9654
9671
  reasoning: true,
9655
9672
  input: ["text"],
9656
9673
  cost: {
9657
- input: 0.25,
9658
- output: 0.95,
9659
- cacheRead: 0.13,
9674
+ input: 0.55,
9675
+ output: 1.6500000000000001,
9676
+ cacheRead: 0.55,
9660
9677
  cacheWrite: 0,
9661
9678
  },
9662
9679
  contextWindow: 163840,
9663
- maxTokens: 32768,
9680
+ maxTokens: 144900,
9664
9681
  },
9665
9682
  "deepseek/deepseek-r1": {
9666
9683
  id: "deepseek/deepseek-r1",
@@ -9722,13 +9739,13 @@ export const MODELS = {
9722
9739
  reasoning: true,
9723
9740
  input: ["text"],
9724
9741
  cost: {
9725
- input: 0.26899999999999996,
9726
- output: 0.39999999999999997,
9727
- cacheRead: 0.13449999999999998,
9742
+ input: 0.26,
9743
+ output: 0.38,
9744
+ cacheRead: 0.13,
9728
9745
  cacheWrite: 0,
9729
9746
  },
9730
9747
  contextWindow: 163840,
9731
- maxTokens: 65536,
9748
+ maxTokens: 147456,
9732
9749
  },
9733
9750
  "deepseek/deepseek-v3.2-exp": {
9734
9751
  id: "deepseek/deepseek-v3.2-exp",
@@ -9756,9 +9773,9 @@ export const MODELS = {
9756
9773
  reasoning: true,
9757
9774
  input: ["text"],
9758
9775
  cost: {
9759
- input: 0.07966,
9760
- output: 0.15932,
9761
- cacheRead: 0.015932,
9776
+ input: 0.0798,
9777
+ output: 0.1596,
9778
+ cacheRead: 0.01596,
9762
9779
  cacheWrite: 0,
9763
9780
  },
9764
9781
  contextWindow: 1048576,
@@ -9773,13 +9790,13 @@ export const MODELS = {
9773
9790
  reasoning: true,
9774
9791
  input: ["text"],
9775
9792
  cost: {
9776
- input: 0.08,
9777
- output: 0.18,
9778
- cacheRead: 0.016,
9793
+ input: 0.04,
9794
+ output: 0.08,
9795
+ cacheRead: 0.008,
9779
9796
  cacheWrite: 0,
9780
9797
  },
9781
9798
  contextWindow: 1310720,
9782
- maxTokens: 384000,
9799
+ maxTokens: 943718,
9783
9800
  },
9784
9801
  "deepseek/deepseek-v4-flash-vision-exp": {
9785
9802
  id: "deepseek/deepseek-v4-flash-vision-exp",
@@ -9807,13 +9824,13 @@ export const MODELS = {
9807
9824
  reasoning: true,
9808
9825
  input: ["text"],
9809
9826
  cost: {
9810
- input: 1.5999999999999999,
9811
- output: 3.1999999999999997,
9812
- cacheRead: 0.135,
9827
+ input: 0.55593,
9828
+ output: 1.11186,
9829
+ cacheRead: 0.0463275,
9813
9830
  cacheWrite: 0,
9814
9831
  },
9815
9832
  contextWindow: 1048576,
9816
- maxTokens: 393216,
9833
+ maxTokens: 384000,
9817
9834
  },
9818
9835
  "deepseek/deepseek-v4-pro-0813": {
9819
9836
  id: "deepseek/deepseek-v4-pro-0813",
@@ -9824,13 +9841,13 @@ export const MODELS = {
9824
9841
  reasoning: true,
9825
9842
  input: ["text"],
9826
9843
  cost: {
9827
- input: 1.1880000000000002,
9828
- output: 3.564,
9829
- cacheRead: 0.039599999999999996,
9844
+ input: 1.122,
9845
+ output: 3.366,
9846
+ cacheRead: 0.037399999999999996,
9830
9847
  cacheWrite: 0,
9831
9848
  },
9832
9849
  contextWindow: 1048576,
9833
- maxTokens: 4096,
9850
+ maxTokens: 943717,
9834
9851
  },
9835
9852
  "dots-studio/dots-3-note-preview:free": {
9836
9853
  id: "dots-studio/dots-3-note-preview:free",
@@ -9847,7 +9864,7 @@ export const MODELS = {
9847
9864
  cacheWrite: 0,
9848
9865
  },
9849
9866
  contextWindow: 512000,
9850
- maxTokens: 512000,
9867
+ maxTokens: 460800,
9851
9868
  },
9852
9869
  "google/gemini-2.5-flash": {
9853
9870
  id: "google/gemini-2.5-flash",
@@ -10306,7 +10323,7 @@ export const MODELS = {
10306
10323
  cacheWrite: 0,
10307
10324
  },
10308
10325
  contextWindow: 262144,
10309
- maxTokens: 131072,
10326
+ maxTokens: 117964,
10310
10327
  },
10311
10328
  "google/gemma-4-26b-a4b-it": {
10312
10329
  id: "google/gemma-4-26b-a4b-it",
@@ -10357,7 +10374,7 @@ export const MODELS = {
10357
10374
  cacheWrite: 0,
10358
10375
  },
10359
10376
  contextWindow: 262144,
10360
- maxTokens: 262144,
10377
+ maxTokens: 235929,
10361
10378
  },
10362
10379
  "google/gemma-4-31b-it:free": {
10363
10380
  id: "google/gemma-4-31b-it:free",
@@ -10391,7 +10408,7 @@ export const MODELS = {
10391
10408
  cacheWrite: 0,
10392
10409
  },
10393
10410
  contextWindow: 131072,
10394
- maxTokens: 131072,
10411
+ maxTokens: 117964,
10395
10412
  },
10396
10413
  "inception/mercury-2": {
10397
10414
  id: "inception/mercury-2",
@@ -10410,40 +10427,6 @@ export const MODELS = {
10410
10427
  contextWindow: 128000,
10411
10428
  maxTokens: 50000,
10412
10429
  },
10413
- "inclusionai/ling-2.6-1t": {
10414
- id: "inclusionai/ling-2.6-1t",
10415
- name: "inclusionAI: Ling-2.6-1T",
10416
- api: "openai-completions",
10417
- provider: "openrouter",
10418
- baseUrl: "https://openrouter.ai/api/v1",
10419
- reasoning: false,
10420
- input: ["text"],
10421
- cost: {
10422
- input: 0.075,
10423
- output: 0.625,
10424
- cacheRead: 0.015,
10425
- cacheWrite: 0,
10426
- },
10427
- contextWindow: 262144,
10428
- maxTokens: 32768,
10429
- },
10430
- "inclusionai/ling-2.6-flash": {
10431
- id: "inclusionai/ling-2.6-flash",
10432
- name: "inclusionAI: Ling-2.6-flash",
10433
- api: "openai-completions",
10434
- provider: "openrouter",
10435
- baseUrl: "https://openrouter.ai/api/v1",
10436
- reasoning: false,
10437
- input: ["text"],
10438
- cost: {
10439
- input: 0.01,
10440
- output: 0.03,
10441
- cacheRead: 0.002,
10442
- cacheWrite: 0,
10443
- },
10444
- contextWindow: 262144,
10445
- maxTokens: 32768,
10446
- },
10447
10430
  "inclusionai/ling-3.0-flash": {
10448
10431
  id: "inclusionai/ling-3.0-flash",
10449
10432
  name: "Ling-3.0-flash",
@@ -10461,23 +10444,6 @@ export const MODELS = {
10461
10444
  contextWindow: 262144,
10462
10445
  maxTokens: 32768,
10463
10446
  },
10464
- "inclusionai/ring-2.6-1t": {
10465
- id: "inclusionai/ring-2.6-1t",
10466
- name: "inclusionAI: Ring-2.6-1T",
10467
- api: "openai-completions",
10468
- provider: "openrouter",
10469
- baseUrl: "https://openrouter.ai/api/v1",
10470
- reasoning: true,
10471
- input: ["text"],
10472
- cost: {
10473
- input: 0.075,
10474
- output: 0.625,
10475
- cacheRead: 0.015,
10476
- cacheWrite: 0,
10477
- },
10478
- contextWindow: 262144,
10479
- maxTokens: 65536,
10480
- },
10481
10447
  "kwaipilot/kat-coder-air-v2.5": {
10482
10448
  id: "kwaipilot/kat-coder-air-v2.5",
10483
10449
  name: "Kwaipilot: KAT-Coder-Air V2.5",
@@ -10595,7 +10561,7 @@ export const MODELS = {
10595
10561
  cacheWrite: 0,
10596
10562
  },
10597
10563
  contextWindow: 131072,
10598
- maxTokens: 131072,
10564
+ maxTokens: 117964,
10599
10565
  },
10600
10566
  "meta-llama/llama-3.3-70b-instruct": {
10601
10567
  id: "meta-llama/llama-3.3-70b-instruct",
@@ -10657,13 +10623,13 @@ export const MODELS = {
10657
10623
  reasoning: true,
10658
10624
  input: ["text", "image"],
10659
10625
  cost: {
10660
- input: 0.3,
10661
- output: 1.1,
10626
+ input: 0.35,
10627
+ output: 1.5,
10662
10628
  cacheRead: 0.04,
10663
10629
  cacheWrite: 0,
10664
10630
  },
10665
10631
  contextWindow: 131072,
10666
- maxTokens: 131072,
10632
+ maxTokens: 117964,
10667
10633
  },
10668
10634
  "meta/muse-spark-1.1": {
10669
10635
  id: "meta/muse-spark-1.1",
@@ -10680,7 +10646,7 @@ export const MODELS = {
10680
10646
  cacheWrite: 0,
10681
10647
  },
10682
10648
  contextWindow: 1048576,
10683
- maxTokens: 4096,
10649
+ maxTokens: 943718,
10684
10650
  },
10685
10651
  "meta/muse-spark-1.2": {
10686
10652
  id: "meta/muse-spark-1.2",
@@ -10697,7 +10663,24 @@ export const MODELS = {
10697
10663
  cacheWrite: 0,
10698
10664
  },
10699
10665
  contextWindow: 1048576,
10700
- maxTokens: 4096,
10666
+ maxTokens: 943718,
10667
+ },
10668
+ "meta/muse-spark-1.2-contributor": {
10669
+ id: "meta/muse-spark-1.2-contributor",
10670
+ name: "Meta: Muse Spark 1.2 Contributor",
10671
+ api: "openai-completions",
10672
+ provider: "openrouter",
10673
+ baseUrl: "https://openrouter.ai/api/v1",
10674
+ reasoning: true,
10675
+ input: ["text", "image"],
10676
+ cost: {
10677
+ input: 0.09999999999999999,
10678
+ output: 0.19999999999999998,
10679
+ cacheRead: 0.002,
10680
+ cacheWrite: 0,
10681
+ },
10682
+ contextWindow: 1048576,
10683
+ maxTokens: 943718,
10701
10684
  },
10702
10685
  "minimax/minimax-m1": {
10703
10686
  id: "minimax/minimax-m1",
@@ -10760,12 +10743,12 @@ export const MODELS = {
10760
10743
  input: ["text"],
10761
10744
  cost: {
10762
10745
  input: 0.27,
10763
- output: 0.95,
10764
- cacheRead: 0.03,
10746
+ output: 1.08,
10747
+ cacheRead: 0.027,
10765
10748
  cacheWrite: 0,
10766
10749
  },
10767
10750
  contextWindow: 204800,
10768
- maxTokens: 32768,
10751
+ maxTokens: 128000,
10769
10752
  },
10770
10753
  "minimax/minimax-m2.7": {
10771
10754
  id: "minimax/minimax-m2.7",
@@ -10784,6 +10767,23 @@ export const MODELS = {
10784
10767
  contextWindow: 204800,
10785
10768
  maxTokens: 131072,
10786
10769
  },
10770
+ "minimax/minimax-m2.7:free": {
10771
+ id: "minimax/minimax-m2.7:free",
10772
+ name: "MiniMax: MiniMax M2.7 (free)",
10773
+ api: "openai-completions",
10774
+ provider: "openrouter",
10775
+ baseUrl: "https://openrouter.ai/api/v1",
10776
+ reasoning: true,
10777
+ input: ["text"],
10778
+ cost: {
10779
+ input: 0,
10780
+ output: 0,
10781
+ cacheRead: 0,
10782
+ cacheWrite: 0,
10783
+ },
10784
+ contextWindow: 196608,
10785
+ maxTokens: 176947,
10786
+ },
10787
10787
  "minimax/minimax-m3": {
10788
10788
  id: "minimax/minimax-m3",
10789
10789
  name: "MiniMax: MiniMax M3",
@@ -10816,7 +10816,24 @@ export const MODELS = {
10816
10816
  cacheWrite: 0,
10817
10817
  },
10818
10818
  contextWindow: 524288,
10819
- maxTokens: 4096,
10819
+ maxTokens: 471859,
10820
+ },
10821
+ "minimax/minimax-m3:free": {
10822
+ id: "minimax/minimax-m3:free",
10823
+ name: "MiniMax: MiniMax M3 (free)",
10824
+ api: "openai-completions",
10825
+ provider: "openrouter",
10826
+ baseUrl: "https://openrouter.ai/api/v1",
10827
+ reasoning: true,
10828
+ input: ["text", "image"],
10829
+ cost: {
10830
+ input: 0,
10831
+ output: 0,
10832
+ cacheRead: 0,
10833
+ cacheWrite: 0,
10834
+ },
10835
+ contextWindow: 1048576,
10836
+ maxTokens: 943718,
10820
10837
  },
10821
10838
  "mistralai/codestral-2508": {
10822
10839
  id: "mistralai/codestral-2508",
@@ -10833,7 +10850,24 @@ export const MODELS = {
10833
10850
  cacheWrite: 0,
10834
10851
  },
10835
10852
  contextWindow: 256000,
10836
- maxTokens: 4096,
10853
+ maxTokens: 204800,
10854
+ },
10855
+ "mistralai/devstral-2512": {
10856
+ id: "mistralai/devstral-2512",
10857
+ name: "Mistral: Devstral 2 2512",
10858
+ api: "openai-completions",
10859
+ provider: "openrouter",
10860
+ baseUrl: "https://openrouter.ai/api/v1",
10861
+ reasoning: false,
10862
+ input: ["text"],
10863
+ cost: {
10864
+ input: 0.44,
10865
+ output: 2.2,
10866
+ cacheRead: 0.044,
10867
+ cacheWrite: 0,
10868
+ },
10869
+ contextWindow: 262144,
10870
+ maxTokens: 209715,
10837
10871
  },
10838
10872
  "mistralai/ministral-14b-2512": {
10839
10873
  id: "mistralai/ministral-14b-2512",
@@ -10850,7 +10884,7 @@ export const MODELS = {
10850
10884
  cacheWrite: 0,
10851
10885
  },
10852
10886
  contextWindow: 262144,
10853
- maxTokens: 4096,
10887
+ maxTokens: 209715,
10854
10888
  },
10855
10889
  "mistralai/ministral-3b-2512": {
10856
10890
  id: "mistralai/ministral-3b-2512",
@@ -10867,7 +10901,7 @@ export const MODELS = {
10867
10901
  cacheWrite: 0,
10868
10902
  },
10869
10903
  contextWindow: 131072,
10870
- maxTokens: 4096,
10904
+ maxTokens: 104857,
10871
10905
  },
10872
10906
  "mistralai/ministral-8b-2512": {
10873
10907
  id: "mistralai/ministral-8b-2512",
@@ -10884,7 +10918,7 @@ export const MODELS = {
10884
10918
  cacheWrite: 0,
10885
10919
  },
10886
10920
  contextWindow: 262144,
10887
- maxTokens: 4096,
10921
+ maxTokens: 209715,
10888
10922
  },
10889
10923
  "mistralai/mistral-large": {
10890
10924
  id: "mistralai/mistral-large",
@@ -10901,7 +10935,7 @@ export const MODELS = {
10901
10935
  cacheWrite: 0,
10902
10936
  },
10903
10937
  contextWindow: 128000,
10904
- maxTokens: 4096,
10938
+ maxTokens: 102400,
10905
10939
  },
10906
10940
  "mistralai/mistral-large-2407": {
10907
10941
  id: "mistralai/mistral-large-2407",
@@ -10918,7 +10952,7 @@ export const MODELS = {
10918
10952
  cacheWrite: 0,
10919
10953
  },
10920
10954
  contextWindow: 131072,
10921
- maxTokens: 4096,
10955
+ maxTokens: 104857,
10922
10956
  },
10923
10957
  "mistralai/mistral-large-2512": {
10924
10958
  id: "mistralai/mistral-large-2512",
@@ -10935,7 +10969,7 @@ export const MODELS = {
10935
10969
  cacheWrite: 0,
10936
10970
  },
10937
10971
  contextWindow: 262144,
10938
- maxTokens: 4096,
10972
+ maxTokens: 209715,
10939
10973
  },
10940
10974
  "mistralai/mistral-medium-3": {
10941
10975
  id: "mistralai/mistral-medium-3",
@@ -10952,7 +10986,7 @@ export const MODELS = {
10952
10986
  cacheWrite: 0,
10953
10987
  },
10954
10988
  contextWindow: 131072,
10955
- maxTokens: 4096,
10989
+ maxTokens: 104857,
10956
10990
  },
10957
10991
  "mistralai/mistral-medium-3-5": {
10958
10992
  id: "mistralai/mistral-medium-3-5",
@@ -10969,7 +11003,7 @@ export const MODELS = {
10969
11003
  cacheWrite: 0,
10970
11004
  },
10971
11005
  contextWindow: 262144,
10972
- maxTokens: 4096,
11006
+ maxTokens: 209715,
10973
11007
  },
10974
11008
  "mistralai/mistral-medium-3.1": {
10975
11009
  id: "mistralai/mistral-medium-3.1",
@@ -10986,7 +11020,7 @@ export const MODELS = {
10986
11020
  cacheWrite: 0,
10987
11021
  },
10988
11022
  contextWindow: 131072,
10989
- maxTokens: 4096,
11023
+ maxTokens: 104857,
10990
11024
  },
10991
11025
  "mistralai/mistral-nemo": {
10992
11026
  id: "mistralai/mistral-nemo",
@@ -11020,7 +11054,7 @@ export const MODELS = {
11020
11054
  cacheWrite: 0,
11021
11055
  },
11022
11056
  contextWindow: 32768,
11023
- maxTokens: 4096,
11057
+ maxTokens: 26214,
11024
11058
  },
11025
11059
  "mistralai/mistral-small-2603": {
11026
11060
  id: "mistralai/mistral-small-2603",
@@ -11037,7 +11071,7 @@ export const MODELS = {
11037
11071
  cacheWrite: 0,
11038
11072
  },
11039
11073
  contextWindow: 262144,
11040
- maxTokens: 4096,
11074
+ maxTokens: 209715,
11041
11075
  },
11042
11076
  "mistralai/mistral-small-3.2-24b-instruct": {
11043
11077
  id: "mistralai/mistral-small-3.2-24b-instruct",
@@ -11048,12 +11082,12 @@ export const MODELS = {
11048
11082
  reasoning: false,
11049
11083
  input: ["text", "image"],
11050
11084
  cost: {
11051
- input: 0.09375,
11052
- output: 0.25,
11085
+ input: 0.075,
11086
+ output: 0.19999999999999998,
11053
11087
  cacheRead: 0,
11054
11088
  cacheWrite: 0,
11055
11089
  },
11056
- contextWindow: 256000,
11090
+ contextWindow: 131072,
11057
11091
  maxTokens: 16384,
11058
11092
  },
11059
11093
  "mistralai/mixtral-8x22b-instruct": {
@@ -11071,7 +11105,7 @@ export const MODELS = {
11071
11105
  cacheWrite: 0,
11072
11106
  },
11073
11107
  contextWindow: 65536,
11074
- maxTokens: 4096,
11108
+ maxTokens: 52428,
11075
11109
  },
11076
11110
  "mistralai/voxtral-small-24b-2507": {
11077
11111
  id: "mistralai/voxtral-small-24b-2507",
@@ -11088,7 +11122,7 @@ export const MODELS = {
11088
11122
  cacheWrite: 0,
11089
11123
  },
11090
11124
  contextWindow: 32000,
11091
- maxTokens: 4096,
11125
+ maxTokens: 25600,
11092
11126
  },
11093
11127
  "moonshotai/kimi-k2": {
11094
11128
  id: "moonshotai/kimi-k2",
@@ -11167,13 +11201,13 @@ export const MODELS = {
11167
11201
  reasoning: true,
11168
11202
  input: ["text", "image"],
11169
11203
  cost: {
11170
- input: 0.5795,
11171
- output: 2.44,
11172
- cacheRead: 0.0976,
11204
+ input: 0.95,
11205
+ output: 4,
11206
+ cacheRead: 0.16,
11173
11207
  cacheWrite: 0,
11174
11208
  },
11175
11209
  contextWindow: 262144,
11176
- maxTokens: 262144,
11210
+ maxTokens: 235929,
11177
11211
  },
11178
11212
  "moonshotai/kimi-k2.7-code": {
11179
11213
  id: "moonshotai/kimi-k2.7-code",
@@ -11186,11 +11220,11 @@ export const MODELS = {
11186
11220
  cost: {
11187
11221
  input: 0.67,
11188
11222
  output: 3.4,
11189
- cacheRead: 0.16999999999999998,
11223
+ cacheRead: 0.19,
11190
11224
  cacheWrite: 0,
11191
11225
  },
11192
11226
  contextWindow: 262144,
11193
- maxTokens: 262144,
11227
+ maxTokens: 235929,
11194
11228
  },
11195
11229
  "moonshotai/kimi-k2.7-code:batch": {
11196
11230
  id: "moonshotai/kimi-k2.7-code:batch",
@@ -11207,7 +11241,7 @@ export const MODELS = {
11207
11241
  cacheWrite: 0,
11208
11242
  },
11209
11243
  contextWindow: 262144,
11210
- maxTokens: 4096,
11244
+ maxTokens: 235929,
11211
11245
  },
11212
11246
  "moonshotai/kimi-k3": {
11213
11247
  id: "moonshotai/kimi-k3",
@@ -11224,7 +11258,7 @@ export const MODELS = {
11224
11258
  cacheWrite: 0,
11225
11259
  },
11226
11260
  contextWindow: 1048576,
11227
- maxTokens: 4096,
11261
+ maxTokens: 943718,
11228
11262
  },
11229
11263
  "nex-agi/nex-n2-mini": {
11230
11264
  id: "nex-agi/nex-n2-mini",
@@ -11241,7 +11275,7 @@ export const MODELS = {
11241
11275
  cacheWrite: 0,
11242
11276
  },
11243
11277
  contextWindow: 262144,
11244
- maxTokens: 262144,
11278
+ maxTokens: 235929,
11245
11279
  },
11246
11280
  "nex-agi/nex-n2-pro": {
11247
11281
  id: "nex-agi/nex-n2-pro",
@@ -11258,7 +11292,7 @@ export const MODELS = {
11258
11292
  cacheWrite: 0,
11259
11293
  },
11260
11294
  contextWindow: 262144,
11261
- maxTokens: 262144,
11295
+ maxTokens: 235929,
11262
11296
  },
11263
11297
  "nvidia/nemotron-3-nano-30b-a3b": {
11264
11298
  id: "nvidia/nemotron-3-nano-30b-a3b",
@@ -11275,24 +11309,7 @@ export const MODELS = {
11275
11309
  cacheWrite: 0,
11276
11310
  },
11277
11311
  contextWindow: 262144,
11278
- maxTokens: 262144,
11279
- },
11280
- "nvidia/nemotron-3-nano-30b-a3b:free": {
11281
- id: "nvidia/nemotron-3-nano-30b-a3b:free",
11282
- name: "NVIDIA: Nemotron 3 Nano 30B A3B (free)",
11283
- api: "openai-completions",
11284
- provider: "openrouter",
11285
- baseUrl: "https://openrouter.ai/api/v1",
11286
- reasoning: true,
11287
- input: ["text"],
11288
- cost: {
11289
- input: 0,
11290
- output: 0,
11291
- cacheRead: 0,
11292
- cacheWrite: 0,
11293
- },
11294
- contextWindow: 256000,
11295
- maxTokens: 4096,
11312
+ maxTokens: 235929,
11296
11313
  },
11297
11314
  "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free": {
11298
11315
  id: "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
@@ -11343,7 +11360,7 @@ export const MODELS = {
11343
11360
  cacheWrite: 0,
11344
11361
  },
11345
11362
  contextWindow: 262144,
11346
- maxTokens: 262144,
11363
+ maxTokens: 235929,
11347
11364
  },
11348
11365
  "nvidia/nemotron-3-ultra-550b-a55b": {
11349
11366
  id: "nvidia/nemotron-3-ultra-550b-a55b",
@@ -11360,7 +11377,7 @@ export const MODELS = {
11360
11377
  cacheWrite: 0,
11361
11378
  },
11362
11379
  contextWindow: 512288,
11363
- maxTokens: 4096,
11380
+ maxTokens: 461059,
11364
11381
  },
11365
11382
  "nvidia/nemotron-3-ultra-550b-a55b:batch": {
11366
11383
  id: "nvidia/nemotron-3-ultra-550b-a55b:batch",
@@ -11377,7 +11394,7 @@ export const MODELS = {
11377
11394
  cacheWrite: 0,
11378
11395
  },
11379
11396
  contextWindow: 512288,
11380
- maxTokens: 4096,
11397
+ maxTokens: 461059,
11381
11398
  },
11382
11399
  "nvidia/nemotron-3-ultra-550b-a55b:free": {
11383
11400
  id: "nvidia/nemotron-3-ultra-550b-a55b:free",
@@ -11430,56 +11447,22 @@ export const MODELS = {
11430
11447
  contextWindow: 1000000,
11431
11448
  maxTokens: 65536,
11432
11449
  },
11433
- "nvidia/nemotron-nano-12b-v2-vl:free": {
11434
- id: "nvidia/nemotron-nano-12b-v2-vl:free",
11435
- name: "NVIDIA: Nemotron Nano 12B 2 VL (free)",
11450
+ "openai/gpt-3.5-turbo": {
11451
+ id: "openai/gpt-3.5-turbo",
11452
+ name: "OpenAI: GPT-3.5 Turbo",
11436
11453
  api: "openai-completions",
11437
11454
  provider: "openrouter",
11438
11455
  baseUrl: "https://openrouter.ai/api/v1",
11439
- reasoning: true,
11440
- input: ["text", "image"],
11456
+ reasoning: false,
11457
+ input: ["text"],
11441
11458
  cost: {
11442
- input: 0,
11443
- output: 0,
11459
+ input: 0.5,
11460
+ output: 1.5,
11444
11461
  cacheRead: 0,
11445
11462
  cacheWrite: 0,
11446
11463
  },
11447
- contextWindow: 128000,
11448
- maxTokens: 128000,
11449
- },
11450
- "nvidia/nemotron-nano-9b-v2:free": {
11451
- id: "nvidia/nemotron-nano-9b-v2:free",
11452
- name: "NVIDIA: Nemotron Nano 9B V2 (free)",
11453
- api: "openai-completions",
11454
- provider: "openrouter",
11455
- baseUrl: "https://openrouter.ai/api/v1",
11456
- reasoning: true,
11457
- input: ["text"],
11458
- cost: {
11459
- input: 0,
11460
- output: 0,
11461
- cacheRead: 0,
11462
- cacheWrite: 0,
11463
- },
11464
- contextWindow: 128000,
11465
- maxTokens: 4096,
11466
- },
11467
- "openai/gpt-3.5-turbo": {
11468
- id: "openai/gpt-3.5-turbo",
11469
- name: "OpenAI: GPT-3.5 Turbo",
11470
- api: "openai-completions",
11471
- provider: "openrouter",
11472
- baseUrl: "https://openrouter.ai/api/v1",
11473
- reasoning: false,
11474
- input: ["text"],
11475
- cost: {
11476
- input: 0.5,
11477
- output: 1.5,
11478
- cacheRead: 0,
11479
- cacheWrite: 0,
11480
- },
11481
- contextWindow: 16385,
11482
- maxTokens: 4096,
11464
+ contextWindow: 16385,
11465
+ maxTokens: 4096,
11483
11466
  },
11484
11467
  "openai/gpt-3.5-turbo-0613": {
11485
11468
  id: "openai/gpt-3.5-turbo-0613",
@@ -11496,7 +11479,7 @@ export const MODELS = {
11496
11479
  cacheWrite: 0,
11497
11480
  },
11498
11481
  contextWindow: 4095,
11499
- maxTokens: 4096,
11482
+ maxTokens: 3685,
11500
11483
  },
11501
11484
  "openai/gpt-3.5-turbo-16k": {
11502
11485
  id: "openai/gpt-3.5-turbo-16k",
@@ -12459,10 +12442,10 @@ export const MODELS = {
12459
12442
  reasoning: true,
12460
12443
  input: ["text", "image"],
12461
12444
  cost: {
12462
- input: 2.5,
12463
- output: 15,
12464
- cacheRead: 0.25,
12465
- cacheWrite: 3.125,
12445
+ input: 2,
12446
+ output: 10,
12447
+ cacheRead: 0.19999999999999998,
12448
+ cacheWrite: 2.5,
12466
12449
  },
12467
12450
  contextWindow: 1050000,
12468
12451
  maxTokens: 128000,
@@ -12476,10 +12459,10 @@ export const MODELS = {
12476
12459
  reasoning: true,
12477
12460
  input: ["text", "image"],
12478
12461
  cost: {
12479
- input: 2.5,
12480
- output: 15,
12481
- cacheRead: 0.25,
12482
- cacheWrite: 3.125,
12462
+ input: 2,
12463
+ output: 10,
12464
+ cacheRead: 0.19999999999999998,
12465
+ cacheWrite: 2.5,
12483
12466
  },
12484
12467
  contextWindow: 1050000,
12485
12468
  maxTokens: 128000,
@@ -12493,10 +12476,10 @@ export const MODELS = {
12493
12476
  reasoning: true,
12494
12477
  input: ["text", "image"],
12495
12478
  cost: {
12496
- input: 1.25,
12497
- output: 7.5,
12498
- cacheRead: 0.125,
12499
- cacheWrite: 0,
12479
+ input: 1,
12480
+ output: 5,
12481
+ cacheRead: 0.09999999999999999,
12482
+ cacheWrite: 1.25,
12500
12483
  },
12501
12484
  contextWindow: 1050000,
12502
12485
  maxTokens: 128000,
@@ -12510,10 +12493,10 @@ export const MODELS = {
12510
12493
  reasoning: true,
12511
12494
  input: ["text", "image"],
12512
12495
  cost: {
12513
- input: 1.25,
12514
- output: 7.5,
12515
- cacheRead: 0.125,
12516
- cacheWrite: 0,
12496
+ input: 1,
12497
+ output: 5,
12498
+ cacheRead: 0.09999999999999999,
12499
+ cacheWrite: 1.25,
12517
12500
  },
12518
12501
  contextWindow: 1050000,
12519
12502
  maxTokens: 128000,
@@ -12663,13 +12646,13 @@ export const MODELS = {
12663
12646
  reasoning: true,
12664
12647
  input: ["text"],
12665
12648
  cost: {
12666
- input: 0.03,
12649
+ input: 0.037,
12667
12650
  output: 0.16999999999999998,
12668
- cacheRead: 0.03,
12651
+ cacheRead: 0,
12669
12652
  cacheWrite: 0,
12670
12653
  },
12671
12654
  contextWindow: 131072,
12672
- maxTokens: 131072,
12655
+ maxTokens: 117964,
12673
12656
  },
12674
12657
  "openai/gpt-oss-20b": {
12675
12658
  id: "openai/gpt-oss-20b",
@@ -12686,24 +12669,7 @@ export const MODELS = {
12686
12669
  cacheWrite: 0,
12687
12670
  },
12688
12671
  contextWindow: 131072,
12689
- maxTokens: 131072,
12690
- },
12691
- "openai/gpt-oss-20b:free": {
12692
- id: "openai/gpt-oss-20b:free",
12693
- name: "OpenAI: gpt-oss-20b (free)",
12694
- api: "openai-completions",
12695
- provider: "openrouter",
12696
- baseUrl: "https://openrouter.ai/api/v1",
12697
- reasoning: true,
12698
- input: ["text"],
12699
- cost: {
12700
- input: 0,
12701
- output: 0,
12702
- cacheRead: 0,
12703
- cacheWrite: 0,
12704
- },
12705
- contextWindow: 131072,
12706
- maxTokens: 32768,
12672
+ maxTokens: 117964,
12707
12673
  },
12708
12674
  "openai/gpt-oss-safeguard-20b": {
12709
12675
  id: "openai/gpt-oss-safeguard-20b",
@@ -13111,7 +13077,7 @@ export const MODELS = {
13111
13077
  cacheWrite: 0,
13112
13078
  },
13113
13079
  contextWindow: 32768,
13114
- maxTokens: 32768,
13080
+ maxTokens: 29491,
13115
13081
  },
13116
13082
  "qwen/qwen-plus": {
13117
13083
  id: "qwen/qwen-plus",
@@ -13147,23 +13113,6 @@ export const MODELS = {
13147
13113
  contextWindow: 1000000,
13148
13114
  maxTokens: 32768,
13149
13115
  },
13150
- "qwen/qwen-plus-2025-07-28:thinking": {
13151
- id: "qwen/qwen-plus-2025-07-28:thinking",
13152
- name: "Qwen: Qwen Plus 0728 (thinking)",
13153
- api: "openai-completions",
13154
- provider: "openrouter",
13155
- baseUrl: "https://openrouter.ai/api/v1",
13156
- reasoning: true,
13157
- input: ["text"],
13158
- cost: {
13159
- input: 0.26,
13160
- output: 0.78,
13161
- cacheRead: 0,
13162
- cacheWrite: 0,
13163
- },
13164
- contextWindow: 1000000,
13165
- maxTokens: 32768,
13166
- },
13167
13116
  "qwen/qwen3-14b": {
13168
13117
  id: "qwen/qwen3-14b",
13169
13118
  name: "Qwen: Qwen3 14B",
@@ -13229,8 +13178,8 @@ export const MODELS = {
13229
13178
  cacheRead: 0,
13230
13179
  cacheWrite: 0,
13231
13180
  },
13232
- contextWindow: 262144,
13233
- maxTokens: 4096,
13181
+ contextWindow: 131072,
13182
+ maxTokens: 117964,
13234
13183
  },
13235
13184
  "qwen/qwen3-30b-a3b": {
13236
13185
  id: "qwen/qwen3-30b-a3b",
@@ -13241,13 +13190,13 @@ export const MODELS = {
13241
13190
  reasoning: true,
13242
13191
  input: ["text"],
13243
13192
  cost: {
13244
- input: 0.13,
13245
- output: 0.52,
13193
+ input: 0.12,
13194
+ output: 0.5,
13246
13195
  cacheRead: 0,
13247
13196
  cacheWrite: 0,
13248
13197
  },
13249
13198
  contextWindow: 131072,
13250
- maxTokens: 8192,
13199
+ maxTokens: 16384,
13251
13200
  },
13252
13201
  "qwen/qwen3-30b-a3b-instruct-2507": {
13253
13202
  id: "qwen/qwen3-30b-a3b-instruct-2507",
@@ -13349,7 +13298,7 @@ export const MODELS = {
13349
13298
  cacheWrite: 0,
13350
13299
  },
13351
13300
  contextWindow: 262144,
13352
- maxTokens: 262144,
13301
+ maxTokens: 235929,
13353
13302
  },
13354
13303
  "qwen/qwen3-coder-flash": {
13355
13304
  id: "qwen/qwen3-coder-flash",
@@ -13383,7 +13332,7 @@ export const MODELS = {
13383
13332
  cacheWrite: 0,
13384
13333
  },
13385
13334
  contextWindow: 262144,
13386
- maxTokens: 262144,
13335
+ maxTokens: 235929,
13387
13336
  },
13388
13337
  "qwen/qwen3-coder-plus": {
13389
13338
  id: "qwen/qwen3-coder-plus",
@@ -13445,13 +13394,13 @@ export const MODELS = {
13445
13394
  reasoning: false,
13446
13395
  input: ["text"],
13447
13396
  cost: {
13448
- input: 0.09,
13397
+ input: 0.09999999999999999,
13449
13398
  output: 1.1,
13450
- cacheRead: 0,
13399
+ cacheRead: 0.07,
13451
13400
  cacheWrite: 0,
13452
13401
  },
13453
13402
  contextWindow: 262144,
13454
- maxTokens: 16384,
13403
+ maxTokens: 235929,
13455
13404
  },
13456
13405
  "qwen/qwen3-next-80b-a3b-thinking": {
13457
13406
  id: "qwen/qwen3-next-80b-a3b-thinking",
@@ -13604,7 +13553,7 @@ export const MODELS = {
13604
13553
  cacheWrite: 0,
13605
13554
  },
13606
13555
  contextWindow: 262144,
13607
- maxTokens: 65536,
13556
+ maxTokens: 235929,
13608
13557
  },
13609
13558
  "qwen/qwen3.5-27b": {
13610
13559
  id: "qwen/qwen3.5-27b",
@@ -13638,7 +13587,7 @@ export const MODELS = {
13638
13587
  cacheWrite: 0,
13639
13588
  },
13640
13589
  contextWindow: 262144,
13641
- maxTokens: 262144,
13590
+ maxTokens: 235929,
13642
13591
  },
13643
13592
  "qwen/qwen3.5-397b-a17b": {
13644
13593
  id: "qwen/qwen3.5-397b-a17b",
@@ -13649,13 +13598,13 @@ export const MODELS = {
13649
13598
  reasoning: true,
13650
13599
  input: ["text", "image"],
13651
13600
  cost: {
13652
- input: 0.39,
13653
- output: 2.34,
13654
- cacheRead: 0,
13601
+ input: 0.5,
13602
+ output: 3.5999999999999996,
13603
+ cacheRead: 0.3,
13655
13604
  cacheWrite: 0,
13656
13605
  },
13657
13606
  contextWindow: 262144,
13658
- maxTokens: 65536,
13607
+ maxTokens: 235929,
13659
13608
  },
13660
13609
  "qwen/qwen3.5-9b": {
13661
13610
  id: "qwen/qwen3.5-9b",
@@ -13672,7 +13621,7 @@ export const MODELS = {
13672
13621
  cacheWrite: 0,
13673
13622
  },
13674
13623
  contextWindow: 262144,
13675
- maxTokens: 262144,
13624
+ maxTokens: 235929,
13676
13625
  },
13677
13626
  "qwen/qwen3.5-flash-02-23": {
13678
13627
  id: "qwen/qwen3.5-flash-02-23",
@@ -13734,13 +13683,13 @@ export const MODELS = {
13734
13683
  reasoning: true,
13735
13684
  input: ["text", "image"],
13736
13685
  cost: {
13737
- input: 0.6,
13738
- output: 3.5999999999999996,
13739
- cacheRead: 0.12,
13686
+ input: 0.32,
13687
+ output: 3.1999999999999997,
13688
+ cacheRead: 0,
13740
13689
  cacheWrite: 0,
13741
13690
  },
13742
13691
  contextWindow: 262144,
13743
- maxTokens: 262144,
13692
+ maxTokens: 81920,
13744
13693
  },
13745
13694
  "qwen/qwen3.6-35b-a3b": {
13746
13695
  id: "qwen/qwen3.6-35b-a3b",
@@ -13757,7 +13706,7 @@ export const MODELS = {
13757
13706
  cacheWrite: 0,
13758
13707
  },
13759
13708
  contextWindow: 262144,
13760
- maxTokens: 262144,
13709
+ maxTokens: 235929,
13761
13710
  },
13762
13711
  "qwen/qwen3.6-flash": {
13763
13712
  id: "qwen/qwen3.6-flash",
@@ -13876,7 +13825,7 @@ export const MODELS = {
13876
13825
  cacheWrite: 0,
13877
13826
  },
13878
13827
  contextWindow: 1048576,
13879
- maxTokens: 262144,
13828
+ maxTokens: 131072,
13880
13829
  },
13881
13830
  "qwen/qwen3.8-27b": {
13882
13831
  id: "qwen/qwen3.8-27b",
@@ -13887,10 +13836,10 @@ export const MODELS = {
13887
13836
  reasoning: true,
13888
13837
  input: ["text", "image"],
13889
13838
  cost: {
13890
- input: 0.44999999999999996,
13891
- output: 3.1999999999999997,
13892
- cacheRead: 0.049999999999999996,
13893
- cacheWrite: 0,
13839
+ input: 0.425,
13840
+ output: 2.5500000000000003,
13841
+ cacheRead: 0.08499999999999999,
13842
+ cacheWrite: 0.53125,
13894
13843
  },
13895
13844
  contextWindow: 1000000,
13896
13845
  maxTokens: 131072,
@@ -13927,7 +13876,7 @@ export const MODELS = {
13927
13876
  cacheWrite: 0,
13928
13877
  },
13929
13878
  contextWindow: 16384,
13930
- maxTokens: 16384,
13879
+ maxTokens: 14745,
13931
13880
  },
13932
13881
  "relace/relace-search": {
13933
13882
  id: "relace/relace-search",
@@ -14046,7 +13995,7 @@ export const MODELS = {
14046
13995
  cacheWrite: 0,
14047
13996
  },
14048
13997
  contextWindow: 262144,
14049
- maxTokens: 256000,
13998
+ maxTokens: 230400,
14050
13999
  },
14051
14000
  "tencent/hy3": {
14052
14001
  id: "tencent/hy3",
@@ -14080,7 +14029,7 @@ export const MODELS = {
14080
14029
  cacheWrite: 0,
14081
14030
  },
14082
14031
  contextWindow: 262144,
14083
- maxTokens: 4096,
14032
+ maxTokens: 235929,
14084
14033
  },
14085
14034
  "thedrummer/unslopnemo-12b": {
14086
14035
  id: "thedrummer/unslopnemo-12b",
@@ -14097,7 +14046,7 @@ export const MODELS = {
14097
14046
  cacheWrite: 0,
14098
14047
  },
14099
14048
  contextWindow: 1024000,
14100
- maxTokens: 1024000,
14049
+ maxTokens: 26214,
14101
14050
  },
14102
14051
  "thinkingmachines/inkling": {
14103
14052
  id: "thinkingmachines/inkling",
@@ -14133,6 +14082,23 @@ export const MODELS = {
14133
14082
  contextWindow: 1048576,
14134
14083
  maxTokens: 262144,
14135
14084
  },
14085
+ "thinkingmachines/inkling-small:free": {
14086
+ id: "thinkingmachines/inkling-small:free",
14087
+ name: "Thinking Machines: Inkling Small (free)",
14088
+ api: "openai-completions",
14089
+ provider: "openrouter",
14090
+ baseUrl: "https://openrouter.ai/api/v1",
14091
+ reasoning: true,
14092
+ input: ["text", "image"],
14093
+ cost: {
14094
+ input: 0,
14095
+ output: 0,
14096
+ cacheRead: 0,
14097
+ cacheWrite: 0,
14098
+ },
14099
+ contextWindow: 1048576,
14100
+ maxTokens: 262144,
14101
+ },
14136
14102
  "thinkingmachines/inkling:batch": {
14137
14103
  id: "thinkingmachines/inkling:batch",
14138
14104
  name: "Thinking Machines: Inkling (batch)",
@@ -14148,7 +14114,24 @@ export const MODELS = {
14148
14114
  cacheWrite: 0,
14149
14115
  },
14150
14116
  contextWindow: 524288,
14151
- maxTokens: 4096,
14117
+ maxTokens: 471859,
14118
+ },
14119
+ "thinkingmachines/inkling:free": {
14120
+ id: "thinkingmachines/inkling:free",
14121
+ name: "Thinking Machines: Inkling (free)",
14122
+ api: "openai-completions",
14123
+ provider: "openrouter",
14124
+ baseUrl: "https://openrouter.ai/api/v1",
14125
+ reasoning: true,
14126
+ input: ["text", "image"],
14127
+ cost: {
14128
+ input: 0,
14129
+ output: 0,
14130
+ cacheRead: 0,
14131
+ cacheWrite: 0,
14132
+ },
14133
+ contextWindow: 1048576,
14134
+ maxTokens: 262144,
14152
14135
  },
14153
14136
  "upstage/solar-pro-3": {
14154
14137
  id: "upstage/solar-pro-3",
@@ -14165,7 +14148,7 @@ export const MODELS = {
14165
14148
  cacheWrite: 0,
14166
14149
  },
14167
14150
  contextWindow: 131072,
14168
- maxTokens: 131072,
14151
+ maxTokens: 117964,
14169
14152
  },
14170
14153
  "upstage/solar-pro4": {
14171
14154
  id: "upstage/solar-pro4",
@@ -14199,7 +14182,7 @@ export const MODELS = {
14199
14182
  cacheWrite: 0,
14200
14183
  },
14201
14184
  contextWindow: 2000000,
14202
- maxTokens: 4096,
14185
+ maxTokens: 1800000,
14203
14186
  },
14204
14187
  "x-ai/grok-4.3": {
14205
14188
  id: "x-ai/grok-4.3",
@@ -14216,7 +14199,7 @@ export const MODELS = {
14216
14199
  cacheWrite: 0,
14217
14200
  },
14218
14201
  contextWindow: 1000000,
14219
- maxTokens: 4096,
14202
+ maxTokens: 900000,
14220
14203
  },
14221
14204
  "x-ai/grok-4.5": {
14222
14205
  id: "x-ai/grok-4.5",
@@ -14233,7 +14216,7 @@ export const MODELS = {
14233
14216
  cacheWrite: 0,
14234
14217
  },
14235
14218
  contextWindow: 500000,
14236
- maxTokens: 4096,
14219
+ maxTokens: 450000,
14237
14220
  },
14238
14221
  "x-ai/grok-4.6": {
14239
14222
  id: "x-ai/grok-4.6",
@@ -14250,7 +14233,7 @@ export const MODELS = {
14250
14233
  cacheWrite: 0,
14251
14234
  },
14252
14235
  contextWindow: 500000,
14253
- maxTokens: 4096,
14236
+ maxTokens: 450000,
14254
14237
  },
14255
14238
  "x-ai/grok-build-0.1": {
14256
14239
  id: "x-ai/grok-build-0.1",
@@ -14267,7 +14250,7 @@ export const MODELS = {
14267
14250
  cacheWrite: 0,
14268
14251
  },
14269
14252
  contextWindow: 256000,
14270
- maxTokens: 4096,
14253
+ maxTokens: 230400,
14271
14254
  },
14272
14255
  "xiaomi/mimo-v2.5": {
14273
14256
  id: "xiaomi/mimo-v2.5",
@@ -14465,13 +14448,13 @@ export const MODELS = {
14465
14448
  reasoning: true,
14466
14449
  input: ["text"],
14467
14450
  cost: {
14468
- input: 0.966,
14469
- output: 3.036,
14470
- cacheRead: 0.1794,
14451
+ input: 1.26,
14452
+ output: 3.9600000000000004,
14453
+ cacheRead: 0.234,
14471
14454
  cacheWrite: 0,
14472
14455
  },
14473
14456
  contextWindow: 204800,
14474
- maxTokens: 128000,
14457
+ maxTokens: 182476,
14475
14458
  },
14476
14459
  "z-ai/glm-5.2": {
14477
14460
  id: "z-ai/glm-5.2",
@@ -14482,13 +14465,13 @@ export const MODELS = {
14482
14465
  reasoning: true,
14483
14466
  input: ["text"],
14484
14467
  cost: {
14485
- input: 0.966,
14486
- output: 3.036,
14487
- cacheRead: 0.1932,
14468
+ input: 1.19,
14469
+ output: 3.74,
14470
+ cacheRead: 0.221,
14488
14471
  cacheWrite: 0,
14489
14472
  },
14490
14473
  contextWindow: 1048576,
14491
- maxTokens: 131072,
14474
+ maxTokens: 262144,
14492
14475
  },
14493
14476
  "z-ai/glm-5.2:batch": {
14494
14477
  id: "z-ai/glm-5.2:batch",
@@ -14505,7 +14488,7 @@ export const MODELS = {
14505
14488
  cacheWrite: 0,
14506
14489
  },
14507
14490
  contextWindow: 1048575,
14508
- maxTokens: 4096,
14491
+ maxTokens: 943717,
14509
14492
  },
14510
14493
  "z-ai/glm-5.2:free": {
14511
14494
  id: "z-ai/glm-5.2:free",
@@ -14522,7 +14505,7 @@ export const MODELS = {
14522
14505
  cacheWrite: 0,
14523
14506
  },
14524
14507
  contextWindow: 256000,
14525
- maxTokens: 256000,
14508
+ maxTokens: 230400,
14526
14509
  },
14527
14510
  "z-ai/glm-5.3": {
14528
14511
  id: "z-ai/glm-5.3",
@@ -14635,13 +14618,13 @@ export const MODELS = {
14635
14618
  reasoning: true,
14636
14619
  input: ["text"],
14637
14620
  cost: {
14638
- input: 0.065,
14639
- output: 0.18,
14640
- cacheRead: 0.02,
14621
+ input: 0.035,
14622
+ output: 0.09999999999999999,
14623
+ cacheRead: 0.008,
14641
14624
  cacheWrite: 0,
14642
14625
  },
14643
14626
  contextWindow: 1310720,
14644
- maxTokens: 1048576,
14627
+ maxTokens: 943718,
14645
14628
  },
14646
14629
  "~google/gemini-flash-latest": {
14647
14630
  id: "~google/gemini-flash-latest",
@@ -14692,7 +14675,7 @@ export const MODELS = {
14692
14675
  cacheWrite: 0,
14693
14676
  },
14694
14677
  contextWindow: 1048576,
14695
- maxTokens: 974842,
14678
+ maxTokens: 877357,
14696
14679
  },
14697
14680
  "~openai/gpt-latest": {
14698
14681
  id: "~openai/gpt-latest",
@@ -14703,10 +14686,10 @@ export const MODELS = {
14703
14686
  reasoning: true,
14704
14687
  input: ["text", "image"],
14705
14688
  cost: {
14706
- input: 2.5,
14707
- output: 15,
14708
- cacheRead: 0.25,
14709
- cacheWrite: 3.125,
14689
+ input: 2,
14690
+ output: 10,
14691
+ cacheRead: 0.19999999999999998,
14692
+ cacheWrite: 2.5,
14710
14693
  },
14711
14694
  contextWindow: 1050000,
14712
14695
  maxTokens: 128000,
@@ -14743,7 +14726,7 @@ export const MODELS = {
14743
14726
  cacheWrite: 0,
14744
14727
  },
14745
14728
  contextWindow: 500000,
14746
- maxTokens: 4096,
14729
+ maxTokens: 450000,
14747
14730
  },
14748
14731
  "~z-ai/glm-latest": {
14749
14732
  id: "~z-ai/glm-latest",
@@ -15580,23 +15563,6 @@ export const MODELS = {
15580
15563
  contextWindow: 262100,
15581
15564
  maxTokens: 80000,
15582
15565
  },
15583
- "arcee-ai/trinity-mini": {
15584
- id: "arcee-ai/trinity-mini",
15585
- name: "Trinity Mini",
15586
- api: "anthropic-messages",
15587
- provider: "vercel-ai-gateway",
15588
- baseUrl: "https://ai-gateway.vercel.sh",
15589
- reasoning: false,
15590
- input: ["text"],
15591
- cost: {
15592
- input: 0.045,
15593
- output: 0.15,
15594
- cacheRead: 0,
15595
- cacheWrite: 0,
15596
- },
15597
- contextWindow: 131072,
15598
- maxTokens: 131072,
15599
- },
15600
15566
  "bytedance/seed-1.6": {
15601
15567
  id: "bytedance/seed-1.6",
15602
15568
  name: "Seed 1.6",
@@ -15776,9 +15742,9 @@ export const MODELS = {
15776
15742
  reasoning: true,
15777
15743
  input: ["text"],
15778
15744
  cost: {
15779
- input: 0.13,
15780
- output: 0.26,
15781
- cacheRead: 0.028,
15745
+ input: 0.07600000000000001,
15746
+ output: 0.153,
15747
+ cacheRead: 0.014,
15782
15748
  cacheWrite: 0,
15783
15749
  },
15784
15750
  contextWindow: 1000000,
@@ -15827,9 +15793,9 @@ export const MODELS = {
15827
15793
  reasoning: true,
15828
15794
  input: ["text"],
15829
15795
  cost: {
15830
- input: 1.32,
15831
- output: 3.9600000000000004,
15832
- cacheRead: 0.13199999999999998,
15796
+ input: 0.66,
15797
+ output: 1.9800000000000002,
15798
+ cacheRead: 0.06599999999999999,
15833
15799
  cacheWrite: 0,
15834
15800
  },
15835
15801
  contextWindow: 1000000,
@@ -16430,6 +16396,23 @@ export const MODELS = {
16430
16396
  contextWindow: 204800,
16431
16397
  maxTokens: 131000,
16432
16398
  },
16399
+ "minimax/minimax-m2.7-free": {
16400
+ id: "minimax/minimax-m2.7-free",
16401
+ name: "Minimax M2.7 (Free)",
16402
+ api: "anthropic-messages",
16403
+ provider: "vercel-ai-gateway",
16404
+ baseUrl: "https://ai-gateway.vercel.sh",
16405
+ reasoning: true,
16406
+ input: ["text"],
16407
+ cost: {
16408
+ input: 0,
16409
+ output: 0,
16410
+ cacheRead: 0,
16411
+ cacheWrite: 0,
16412
+ },
16413
+ contextWindow: 196608,
16414
+ maxTokens: 196608,
16415
+ },
16433
16416
  "minimax/minimax-m2.7-highspeed": {
16434
16417
  id: "minimax/minimax-m2.7-highspeed",
16435
16418
  name: "MiniMax M2.7 High Speed",
@@ -16464,6 +16447,23 @@ export const MODELS = {
16464
16447
  contextWindow: 1000000,
16465
16448
  maxTokens: 1000000,
16466
16449
  },
16450
+ "minimax/minimax-m3-free": {
16451
+ id: "minimax/minimax-m3-free",
16452
+ name: "MiniMax M3 (Free)",
16453
+ api: "anthropic-messages",
16454
+ provider: "vercel-ai-gateway",
16455
+ baseUrl: "https://ai-gateway.vercel.sh",
16456
+ reasoning: true,
16457
+ input: ["text", "image"],
16458
+ cost: {
16459
+ input: 0,
16460
+ output: 0,
16461
+ cacheRead: 0,
16462
+ cacheWrite: 0,
16463
+ },
16464
+ contextWindow: 1048576,
16465
+ maxTokens: 1048576,
16466
+ },
16467
16467
  "mistral/codestral": {
16468
16468
  id: "mistral/codestral",
16469
16469
  name: "Mistral Codestral",
@@ -16515,40 +16515,6 @@ export const MODELS = {
16515
16515
  contextWindow: 256000,
16516
16516
  maxTokens: 256000,
16517
16517
  },
16518
- "mistral/magistral-medium": {
16519
- id: "mistral/magistral-medium",
16520
- name: "Magistral Medium 2509",
16521
- api: "anthropic-messages",
16522
- provider: "vercel-ai-gateway",
16523
- baseUrl: "https://ai-gateway.vercel.sh",
16524
- reasoning: true,
16525
- input: ["text", "image"],
16526
- cost: {
16527
- input: 2,
16528
- output: 5,
16529
- cacheRead: 0,
16530
- cacheWrite: 0,
16531
- },
16532
- contextWindow: 128000,
16533
- maxTokens: 64000,
16534
- },
16535
- "mistral/magistral-small": {
16536
- id: "mistral/magistral-small",
16537
- name: "Magistral Small 2509",
16538
- api: "anthropic-messages",
16539
- provider: "vercel-ai-gateway",
16540
- baseUrl: "https://ai-gateway.vercel.sh",
16541
- reasoning: true,
16542
- input: ["text", "image"],
16543
- cost: {
16544
- input: 0.5,
16545
- output: 1.5,
16546
- cacheRead: 0,
16547
- cacheWrite: 0,
16548
- },
16549
- contextWindow: 128000,
16550
- maxTokens: 64000,
16551
- },
16552
16518
  "mistral/ministral-14b": {
16553
16519
  id: "mistral/ministral-14b",
16554
16520
  name: "Ministral 14B",
@@ -17646,10 +17612,10 @@ export const MODELS = {
17646
17612
  reasoning: true,
17647
17613
  input: ["text", "image"],
17648
17614
  cost: {
17649
- input: 2.5,
17650
- output: 15,
17651
- cacheRead: 0.25,
17652
- cacheWrite: 3.125,
17615
+ input: 2,
17616
+ output: 10,
17617
+ cacheRead: 0.19999999999999998,
17618
+ cacheWrite: 2.5,
17653
17619
  },
17654
17620
  contextWindow: 1050000,
17655
17621
  maxTokens: 128000,
@@ -17663,10 +17629,10 @@ export const MODELS = {
17663
17629
  reasoning: true,
17664
17630
  input: ["text", "image"],
17665
17631
  cost: {
17666
- input: 5,
17667
- output: 30,
17668
- cacheRead: 0.5,
17669
- cacheWrite: 3.125,
17632
+ input: 4,
17633
+ output: 20,
17634
+ cacheRead: 0.39999999999999997,
17635
+ cacheWrite: 2.5,
17670
17636
  },
17671
17637
  contextWindow: 1050000,
17672
17638
  maxTokens: 128000,
@@ -17739,6 +17705,23 @@ export const MODELS = {
17739
17705
  contextWindow: 131072,
17740
17706
  maxTokens: 8192,
17741
17707
  },
17708
+ "openai/gpt-oss-safeguard-120b": {
17709
+ id: "openai/gpt-oss-safeguard-120b",
17710
+ name: "GPT OSS Safeguard 120B",
17711
+ api: "anthropic-messages",
17712
+ provider: "vercel-ai-gateway",
17713
+ baseUrl: "https://ai-gateway.vercel.sh",
17714
+ reasoning: true,
17715
+ input: ["text"],
17716
+ cost: {
17717
+ input: 0.15,
17718
+ output: 0.6,
17719
+ cacheRead: 0,
17720
+ cacheWrite: 0,
17721
+ },
17722
+ contextWindow: 128000,
17723
+ maxTokens: 16000,
17724
+ },
17742
17725
  "openai/gpt-oss-safeguard-20b": {
17743
17726
  id: "openai/gpt-oss-safeguard-20b",
17744
17727
  name: "GPT OSS Safeguard 20B",
@@ -17748,13 +17731,13 @@ export const MODELS = {
17748
17731
  reasoning: true,
17749
17732
  input: ["text"],
17750
17733
  cost: {
17751
- input: 0.075,
17752
- output: 0.3,
17753
- cacheRead: 0.037,
17734
+ input: 0.07,
17735
+ output: 0.19999999999999998,
17736
+ cacheRead: 0,
17754
17737
  cacheWrite: 0,
17755
17738
  },
17756
- contextWindow: 131072,
17757
- maxTokens: 65536,
17739
+ contextWindow: 128000,
17740
+ maxTokens: 16000,
17758
17741
  },
17759
17742
  "openai/o1": {
17760
17743
  id: "openai/o1",
@@ -17790,23 +17773,6 @@ export const MODELS = {
17790
17773
  contextWindow: 200000,
17791
17774
  maxTokens: 100000,
17792
17775
  },
17793
- "openai/o3-deep-research": {
17794
- id: "openai/o3-deep-research",
17795
- name: "o3-deep-research",
17796
- api: "anthropic-messages",
17797
- provider: "vercel-ai-gateway",
17798
- baseUrl: "https://ai-gateway.vercel.sh",
17799
- reasoning: true,
17800
- input: ["text", "image"],
17801
- cost: {
17802
- input: 10,
17803
- output: 40,
17804
- cacheRead: 2.5,
17805
- cacheWrite: 0,
17806
- },
17807
- contextWindow: 200000,
17808
- maxTokens: 100000,
17809
- },
17810
17776
  "openai/o3-fast": {
17811
17777
  id: "openai/o3-fast",
17812
17778
  name: "o3 (Fast)",