@kolisachint/hoocode-ai 0.5.61 → 0.5.62

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.
@@ -1147,8 +1147,8 @@ export const MODELS = {
1147
1147
  cacheRead: 0.26,
1148
1148
  cacheWrite: 0,
1149
1149
  },
1150
- contextWindow: 1000000,
1151
- maxTokens: 131072,
1150
+ contextWindow: 1048573,
1151
+ maxTokens: 262144,
1152
1152
  },
1153
1153
  "accounts/fireworks/models/glm-5p3-flash": {
1154
1154
  id: "accounts/fireworks/models/glm-5p3-flash",
@@ -1164,7 +1164,7 @@ export const MODELS = {
1164
1164
  cacheRead: 0.03,
1165
1165
  cacheWrite: 0,
1166
1166
  },
1167
- contextWindow: 1000000,
1167
+ contextWindow: 1048573,
1168
1168
  maxTokens: 131072,
1169
1169
  },
1170
1170
  "accounts/fireworks/models/gpt-oss-120b": {
@@ -1388,6 +1388,23 @@ export const MODELS = {
1388
1388
  contextWindow: 1048575,
1389
1389
  maxTokens: 131072,
1390
1390
  },
1391
+ "accounts/fireworks/routers/glm-5p3-fast": {
1392
+ id: "accounts/fireworks/routers/glm-5p3-fast",
1393
+ name: "GLM 5.3 Fast",
1394
+ api: "anthropic-messages",
1395
+ provider: "fireworks",
1396
+ baseUrl: "https://api.fireworks.ai/inference",
1397
+ reasoning: true,
1398
+ input: ["text"],
1399
+ cost: {
1400
+ input: 2.1,
1401
+ output: 6.6,
1402
+ cacheRead: 0.39,
1403
+ cacheWrite: 0,
1404
+ },
1405
+ contextWindow: 1048572,
1406
+ maxTokens: 262144,
1407
+ },
1391
1408
  "accounts/fireworks/routers/kimi-k3-fast": {
1392
1409
  id: "accounts/fireworks/routers/kimi-k3-fast",
1393
1410
  name: "Kimi K3 Fast",
@@ -8760,9 +8777,9 @@ export const MODELS = {
8760
8777
  reasoning: false,
8761
8778
  input: ["text"],
8762
8779
  cost: {
8763
- input: 0.25,
8764
- output: 1,
8765
- cacheRead: 0,
8780
+ input: 0.29,
8781
+ output: 1.1400000000000001,
8782
+ cacheRead: 0.11,
8766
8783
  cacheWrite: 0,
8767
8784
  },
8768
8785
  contextWindow: 163840,
@@ -8777,13 +8794,13 @@ export const MODELS = {
8777
8794
  reasoning: true,
8778
8795
  input: ["text"],
8779
8796
  cost: {
8780
- input: 0.55,
8781
- output: 1.6500000000000001,
8782
- cacheRead: 0.55,
8797
+ input: 0.25,
8798
+ output: 0.95,
8799
+ cacheRead: 0.13,
8783
8800
  cacheWrite: 0,
8784
8801
  },
8785
8802
  contextWindow: 163840,
8786
- maxTokens: 144900,
8803
+ maxTokens: 32768,
8787
8804
  },
8788
8805
  "deepseek/deepseek-r1": {
8789
8806
  id: "deepseek/deepseek-r1",
@@ -8881,9 +8898,9 @@ export const MODELS = {
8881
8898
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
8882
8899
  input: ["text"],
8883
8900
  cost: {
8884
- input: 0.07994,
8885
- output: 0.15988,
8886
- cacheRead: 0.015988000000000002,
8901
+ input: 0.088606,
8902
+ output: 0.177212,
8903
+ cacheRead: 0.017721200000000003,
8887
8904
  cacheWrite: 0,
8888
8905
  },
8889
8906
  contextWindow: 1048576,
@@ -8900,13 +8917,13 @@ export const MODELS = {
8900
8917
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
8901
8918
  input: ["text"],
8902
8919
  cost: {
8903
- input: 0.049980000000000004,
8904
- output: 0.09996000000000001,
8905
- cacheRead: 0.009996000000000001,
8920
+ input: 0.065,
8921
+ output: 0.18,
8922
+ cacheRead: 0.016,
8906
8923
  cacheWrite: 0,
8907
8924
  },
8908
8925
  contextWindow: 1310720,
8909
- maxTokens: 131072,
8926
+ maxTokens: 943718,
8910
8927
  },
8911
8928
  "deepseek/deepseek-v4-flash-0731:batch": {
8912
8929
  id: "deepseek/deepseek-v4-flash-0731:batch",
@@ -8919,9 +8936,9 @@ export const MODELS = {
8919
8936
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
8920
8937
  input: ["text"],
8921
8938
  cost: {
8922
- input: 0.14,
8923
- output: 0.28,
8924
- cacheRead: 0.03,
8939
+ input: 0.11,
8940
+ output: 0.33,
8941
+ cacheRead: 0.0035,
8925
8942
  cacheWrite: 0,
8926
8943
  },
8927
8944
  contextWindow: 1048576,
@@ -8944,7 +8961,26 @@ export const MODELS = {
8944
8961
  cacheWrite: 0,
8945
8962
  },
8946
8963
  contextWindow: 1048576,
8947
- maxTokens: 384000,
8964
+ maxTokens: 943718,
8965
+ },
8966
+ "deepseek/deepseek-v4-flash-vision-exp:batch": {
8967
+ id: "deepseek/deepseek-v4-flash-vision-exp:batch",
8968
+ name: "DeepSeek: DeepSeek V4 Flash Vision Exp (batch)",
8969
+ api: "openai-completions",
8970
+ provider: "openrouter",
8971
+ baseUrl: "https://openrouter.ai/api/v1",
8972
+ compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
8973
+ reasoning: true,
8974
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
8975
+ input: ["text", "image"],
8976
+ cost: {
8977
+ input: 0.11,
8978
+ output: 0.33,
8979
+ cacheRead: 0.0035,
8980
+ cacheWrite: 0,
8981
+ },
8982
+ contextWindow: 1048576,
8983
+ maxTokens: 943718,
8948
8984
  },
8949
8985
  "deepseek/deepseek-v4-pro": {
8950
8986
  id: "deepseek/deepseek-v4-pro",
@@ -8957,9 +8993,9 @@ export const MODELS = {
8957
8993
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
8958
8994
  input: ["text"],
8959
8995
  cost: {
8960
- input: 0.657198,
8961
- output: 1.314396,
8962
- cacheRead: 0.0547665,
8996
+ input: 0.9552599999999999,
8997
+ output: 1.9105199999999998,
8998
+ cacheRead: 0.07960500000000001,
8963
8999
  cacheWrite: 0,
8964
9000
  },
8965
9001
  contextWindow: 1048576,
@@ -8976,9 +9012,9 @@ export const MODELS = {
8976
9012
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
8977
9013
  input: ["text"],
8978
9014
  cost: {
8979
- input: 0.57948,
8980
- output: 1.73844,
8981
- cacheRead: 0.019316,
9015
+ input: 1.0494,
9016
+ output: 3.1482,
9017
+ cacheRead: 0.03498,
8982
9018
  cacheWrite: 0,
8983
9019
  },
8984
9020
  contextWindow: 1048576,
@@ -8995,9 +9031,9 @@ export const MODELS = {
8995
9031
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
8996
9032
  input: ["text"],
8997
9033
  cost: {
8998
- input: 1.32,
8999
- output: 3.9600000000000004,
9000
- cacheRead: 0.13,
9034
+ input: 0.66,
9035
+ output: 1.9800000000000002,
9036
+ cacheRead: 0.022,
9001
9037
  cacheWrite: 0,
9002
9038
  },
9003
9039
  contextWindow: 1048576,
@@ -9607,9 +9643,9 @@ export const MODELS = {
9607
9643
  reasoning: true,
9608
9644
  input: ["text"],
9609
9645
  cost: {
9610
- input: 0.09999999999999999,
9611
- output: 0.15,
9612
- cacheRead: 0.049999999999999996,
9646
+ input: 0.06,
9647
+ output: 0.25,
9648
+ cacheRead: 0.015,
9613
9649
  cacheWrite: 0,
9614
9650
  },
9615
9651
  contextWindow: 131072,
@@ -9632,9 +9668,9 @@ export const MODELS = {
9632
9668
  contextWindow: 128000,
9633
9669
  maxTokens: 50000,
9634
9670
  },
9635
- "inception/mercury-2.5-preview": {
9636
- id: "inception/mercury-2.5-preview",
9637
- name: "Inception: Mercury 2.5 Preview",
9671
+ "inception/mercury-2.5": {
9672
+ id: "inception/mercury-2.5",
9673
+ name: "Inception: Mercury 2.5",
9638
9674
  api: "openai-completions",
9639
9675
  provider: "openrouter",
9640
9676
  baseUrl: "https://openrouter.ai/api/v1",
@@ -9896,9 +9932,9 @@ export const MODELS = {
9896
9932
  reasoning: true,
9897
9933
  input: ["text", "image"],
9898
9934
  cost: {
9899
- input: 0.35,
9900
- output: 1.5,
9901
- cacheRead: 0.04,
9935
+ input: 0.175,
9936
+ output: 0.75,
9937
+ cacheRead: 0.02,
9902
9938
  cacheWrite: 0,
9903
9939
  },
9904
9940
  contextWindow: 131072,
@@ -10074,23 +10110,6 @@ export const MODELS = {
10074
10110
  contextWindow: 204800,
10075
10111
  maxTokens: 131072,
10076
10112
  },
10077
- "minimax/minimax-m2.7:free": {
10078
- id: "minimax/minimax-m2.7:free",
10079
- name: "MiniMax: MiniMax M2.7 (free)",
10080
- api: "openai-completions",
10081
- provider: "openrouter",
10082
- baseUrl: "https://openrouter.ai/api/v1",
10083
- reasoning: true,
10084
- input: ["text"],
10085
- cost: {
10086
- input: 0,
10087
- output: 0,
10088
- cacheRead: 0,
10089
- cacheWrite: 0,
10090
- },
10091
- contextWindow: 196608,
10092
- maxTokens: 176947,
10093
- },
10094
10113
  "minimax/minimax-m3": {
10095
10114
  id: "minimax/minimax-m3",
10096
10115
  name: "MiniMax: MiniMax M3",
@@ -10125,23 +10144,6 @@ export const MODELS = {
10125
10144
  contextWindow: 524288,
10126
10145
  maxTokens: 471859,
10127
10146
  },
10128
- "minimax/minimax-m3:free": {
10129
- id: "minimax/minimax-m3:free",
10130
- name: "MiniMax: MiniMax M3 (free)",
10131
- api: "openai-completions",
10132
- provider: "openrouter",
10133
- baseUrl: "https://openrouter.ai/api/v1",
10134
- reasoning: true,
10135
- input: ["text", "image"],
10136
- cost: {
10137
- input: 0,
10138
- output: 0,
10139
- cacheRead: 0,
10140
- cacheWrite: 0,
10141
- },
10142
- contextWindow: 1048576,
10143
- maxTokens: 943718,
10144
- },
10145
10147
  "mistralai/codestral-2508": {
10146
10148
  id: "mistralai/codestral-2508",
10147
10149
  name: "Mistral: Codestral 2508",
@@ -10326,8 +10328,8 @@ export const MODELS = {
10326
10328
  cacheRead: 0,
10327
10329
  cacheWrite: 0,
10328
10330
  },
10329
- contextWindow: 32768,
10330
- maxTokens: 26214,
10331
+ contextWindow: 262144,
10332
+ maxTokens: 209715,
10331
10333
  },
10332
10334
  "mistralai/mistral-medium-3.1": {
10333
10335
  id: "mistralai/mistral-medium-3.1",
@@ -10493,11 +10495,11 @@ export const MODELS = {
10493
10495
  cost: {
10494
10496
  input: 0.6,
10495
10497
  output: 2.5,
10496
- cacheRead: 0.15,
10498
+ cacheRead: 0,
10497
10499
  cacheWrite: 0,
10498
10500
  },
10499
10501
  contextWindow: 262144,
10500
- maxTokens: 100352,
10502
+ maxTokens: 235929,
10501
10503
  },
10502
10504
  "moonshotai/kimi-k2.5": {
10503
10505
  id: "moonshotai/kimi-k2.5",
@@ -10542,9 +10544,9 @@ export const MODELS = {
10542
10544
  reasoning: true,
10543
10545
  input: ["text", "image"],
10544
10546
  cost: {
10545
- input: 0.66,
10546
- output: 3.4,
10547
- cacheRead: 0.18,
10547
+ input: 0.71,
10548
+ output: 3.5,
10549
+ cacheRead: 0.15,
10548
10550
  cacheWrite: 0,
10549
10551
  },
10550
10552
  contextWindow: 262144,
@@ -10584,35 +10586,35 @@ export const MODELS = {
10584
10586
  contextWindow: 1048576,
10585
10587
  maxTokens: 943718,
10586
10588
  },
10587
- "nex-agi/nex-n2-mini": {
10588
- id: "nex-agi/nex-n2-mini",
10589
- name: "Nex AGI: Nex-N2-Mini",
10589
+ "nex-agi/nex-n2.5-mini:free": {
10590
+ id: "nex-agi/nex-n2.5-mini:free",
10591
+ name: "Nex AGI: Nex-N2.5-Mini (free)",
10590
10592
  api: "openai-completions",
10591
10593
  provider: "openrouter",
10592
10594
  baseUrl: "https://openrouter.ai/api/v1",
10593
10595
  reasoning: true,
10594
- input: ["text", "image"],
10596
+ input: ["text"],
10595
10597
  cost: {
10596
- input: 0.024999999999999998,
10597
- output: 0.09999999999999999,
10598
- cacheRead: 0.0025,
10598
+ input: 0,
10599
+ output: 0,
10600
+ cacheRead: 0,
10599
10601
  cacheWrite: 0,
10600
10602
  },
10601
10603
  contextWindow: 262144,
10602
10604
  maxTokens: 235929,
10603
10605
  },
10604
- "nex-agi/nex-n2-pro": {
10605
- id: "nex-agi/nex-n2-pro",
10606
- name: "Nex AGI: Nex-N2-Pro",
10606
+ "nex-agi/nex-n2.5-pro:free": {
10607
+ id: "nex-agi/nex-n2.5-pro:free",
10608
+ name: "Nex AGI: Nex-N2.5-Pro (free)",
10607
10609
  api: "openai-completions",
10608
10610
  provider: "openrouter",
10609
10611
  baseUrl: "https://openrouter.ai/api/v1",
10610
10612
  reasoning: true,
10611
10613
  input: ["text", "image"],
10612
10614
  cost: {
10613
- input: 0.25,
10614
- output: 1,
10615
- cacheRead: 0.024999999999999998,
10615
+ input: 0,
10616
+ output: 0,
10617
+ cacheRead: 0,
10616
10618
  cacheWrite: 0,
10617
10619
  },
10618
10620
  contextWindow: 262144,
@@ -10666,7 +10668,7 @@ export const MODELS = {
10666
10668
  cacheRead: 0,
10667
10669
  cacheWrite: 0,
10668
10670
  },
10669
- contextWindow: 1000000,
10671
+ contextWindow: 262144,
10670
10672
  maxTokens: 16384,
10671
10673
  },
10672
10674
  "nvidia/nemotron-3-super-120b-a12b:free": {
@@ -12448,13 +12450,13 @@ export const MODELS = {
12448
12450
  reasoning: true,
12449
12451
  input: ["text"],
12450
12452
  cost: {
12451
- input: 0.12,
12452
- output: 0.24,
12453
+ input: 0.22749999999999998,
12454
+ output: 0.9099999999999999,
12453
12455
  cacheRead: 0,
12454
12456
  cacheWrite: 0,
12455
12457
  },
12456
12458
  contextWindow: 131072,
12457
- maxTokens: 16384,
12459
+ maxTokens: 8192,
12458
12460
  },
12459
12461
  "qwen/qwen3-235b-a22b": {
12460
12462
  id: "qwen/qwen3-235b-a22b",
@@ -12482,8 +12484,8 @@ export const MODELS = {
12482
12484
  reasoning: false,
12483
12485
  input: ["text"],
12484
12486
  cost: {
12485
- input: 0.09,
12486
- output: 0.55,
12487
+ input: 0.22,
12488
+ output: 0.88,
12487
12489
  cacheRead: 0,
12488
12490
  cacheWrite: 0,
12489
12491
  },
@@ -12720,13 +12722,13 @@ export const MODELS = {
12720
12722
  reasoning: false,
12721
12723
  input: ["text"],
12722
12724
  cost: {
12723
- input: 0.09999999999999999,
12725
+ input: 0.09,
12724
12726
  output: 1.1,
12725
- cacheRead: 0.07,
12727
+ cacheRead: 0,
12726
12728
  cacheWrite: 0,
12727
12729
  },
12728
12730
  contextWindow: 262144,
12729
- maxTokens: 235929,
12731
+ maxTokens: 16384,
12730
12732
  },
12731
12733
  "qwen/qwen3-next-80b-a3b-thinking": {
12732
12734
  id: "qwen/qwen3-next-80b-a3b-thinking",
@@ -12743,7 +12745,7 @@ export const MODELS = {
12743
12745
  cacheWrite: 0,
12744
12746
  },
12745
12747
  contextWindow: 262144,
12746
- maxTokens: 32768,
12748
+ maxTokens: 235929,
12747
12749
  },
12748
12750
  "qwen/qwen3-vl-235b-a22b-instruct": {
12749
12751
  id: "qwen/qwen3-vl-235b-a22b-instruct",
@@ -13168,7 +13170,7 @@ export const MODELS = {
13168
13170
  cacheWrite: 0,
13169
13171
  },
13170
13172
  contextWindow: 1048576,
13171
- maxTokens: 262144,
13173
+ maxTokens: 131072,
13172
13174
  },
13173
13175
  "qwen/qwen3.8-2.4t-a95b:batch": {
13174
13176
  id: "qwen/qwen3.8-2.4t-a95b:batch",
@@ -13366,9 +13368,9 @@ export const MODELS = {
13366
13368
  reasoning: true,
13367
13369
  input: ["text"],
13368
13370
  cost: {
13369
- input: 0.0825,
13370
- output: 0.33,
13371
- cacheRead: 0.020625,
13371
+ input: 0.13199999999999998,
13372
+ output: 0.5279999999999999,
13373
+ cacheRead: 0.032999999999999995,
13372
13374
  cacheWrite: 0,
13373
13375
  },
13374
13376
  contextWindow: 262144,
@@ -13757,13 +13759,13 @@ export const MODELS = {
13757
13759
  reasoning: true,
13758
13760
  input: ["text"],
13759
13761
  cost: {
13760
- input: 0.55,
13761
- output: 2.2,
13762
- cacheRead: 0.11,
13762
+ input: 0.43,
13763
+ output: 1.75,
13764
+ cacheRead: 0.08,
13763
13765
  cacheWrite: 0,
13764
13766
  },
13765
13767
  contextWindow: 204800,
13766
- maxTokens: 131072,
13768
+ maxTokens: 16384,
13767
13769
  },
13768
13770
  "z-ai/glm-4.6v": {
13769
13771
  id: "z-ai/glm-4.6v",
@@ -13808,13 +13810,13 @@ export const MODELS = {
13808
13810
  reasoning: true,
13809
13811
  input: ["text"],
13810
13812
  cost: {
13811
- input: 0.06,
13813
+ input: 0.060500000000000005,
13812
13814
  output: 0.39999999999999997,
13813
- cacheRead: 0.01,
13815
+ cacheRead: 0,
13814
13816
  cacheWrite: 0,
13815
13817
  },
13816
13818
  contextWindow: 202752,
13817
- maxTokens: 16384,
13819
+ maxTokens: 117964,
13818
13820
  },
13819
13821
  "z-ai/glm-5": {
13820
13822
  id: "z-ai/glm-5",
@@ -13884,6 +13886,23 @@ export const MODELS = {
13884
13886
  contextWindow: 1048576,
13885
13887
  maxTokens: 131072,
13886
13888
  },
13889
+ "z-ai/glm-5.2:batch": {
13890
+ id: "z-ai/glm-5.2:batch",
13891
+ name: "Z.ai: GLM 5.2 (batch)",
13892
+ api: "openai-completions",
13893
+ provider: "openrouter",
13894
+ baseUrl: "https://openrouter.ai/api/v1",
13895
+ reasoning: true,
13896
+ input: ["text"],
13897
+ cost: {
13898
+ input: 0.7,
13899
+ output: 2.2,
13900
+ cacheRead: 0.07,
13901
+ cacheWrite: 0,
13902
+ },
13903
+ contextWindow: 1048576,
13904
+ maxTokens: 943718,
13905
+ },
13887
13906
  "z-ai/glm-5.3": {
13888
13907
  id: "z-ai/glm-5.3",
13889
13908
  name: "Z.ai: GLM 5.3",
@@ -13895,11 +13914,11 @@ export const MODELS = {
13895
13914
  cost: {
13896
13915
  input: 1.4,
13897
13916
  output: 4.4,
13898
- cacheRead: 0.14,
13917
+ cacheRead: 0.26,
13899
13918
  cacheWrite: 0,
13900
13919
  },
13901
13920
  contextWindow: 1310720,
13902
- maxTokens: 262144,
13921
+ maxTokens: 943718,
13903
13922
  },
13904
13923
  "z-ai/glm-5.3-flash": {
13905
13924
  id: "z-ai/glm-5.3-flash",
@@ -13927,13 +13946,30 @@ export const MODELS = {
13927
13946
  reasoning: true,
13928
13947
  input: ["text", "image"],
13929
13948
  cost: {
13930
- input: 0.15,
13931
- output: 0.5,
13932
- cacheRead: 0.03,
13949
+ input: 0.075,
13950
+ output: 0.25,
13951
+ cacheRead: 0.015,
13933
13952
  cacheWrite: 0,
13934
13953
  },
13935
- contextWindow: 1048575,
13936
- maxTokens: 943717,
13954
+ contextWindow: 1048576,
13955
+ maxTokens: 943718,
13956
+ },
13957
+ "z-ai/glm-5.3:batch": {
13958
+ id: "z-ai/glm-5.3:batch",
13959
+ name: "Z.ai: GLM 5.3 (batch)",
13960
+ api: "openai-completions",
13961
+ provider: "openrouter",
13962
+ baseUrl: "https://openrouter.ai/api/v1",
13963
+ reasoning: true,
13964
+ input: ["text"],
13965
+ cost: {
13966
+ input: 0.7,
13967
+ output: 2.2,
13968
+ cacheRead: 0.13,
13969
+ cacheWrite: 0,
13970
+ },
13971
+ contextWindow: 1048576,
13972
+ maxTokens: 943718,
13937
13973
  },
13938
13974
  "z-ai/glm-5v-turbo": {
13939
13975
  id: "z-ai/glm-5v-turbo",
@@ -14034,13 +14070,13 @@ export const MODELS = {
14034
14070
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
14035
14071
  input: ["text"],
14036
14072
  cost: {
14037
- input: 0.045,
14038
- output: 0.09,
14039
- cacheRead: 0.009,
14073
+ input: 0.049999999999999996,
14074
+ output: 0.16,
14075
+ cacheRead: 0.013000000000000001,
14040
14076
  cacheWrite: 0,
14041
14077
  },
14042
14078
  contextWindow: 1310720,
14043
- maxTokens: 943718,
14079
+ maxTokens: 393216,
14044
14080
  },
14045
14081
  "~google/gemini-flash-latest": {
14046
14082
  id: "~google/gemini-flash-latest",
@@ -14085,9 +14121,9 @@ export const MODELS = {
14085
14121
  reasoning: true,
14086
14122
  input: ["text", "image"],
14087
14123
  cost: {
14088
- input: 2.5500000000000003,
14089
- output: 12.75,
14090
- cacheRead: 0.25599998999999996,
14124
+ input: 2.4,
14125
+ output: 12,
14126
+ cacheRead: 0.24,
14091
14127
  cacheWrite: 0,
14092
14128
  },
14093
14129
  contextWindow: 1048576,
@@ -14170,13 +14206,13 @@ export const MODELS = {
14170
14206
  reasoning: true,
14171
14207
  input: ["text"],
14172
14208
  cost: {
14173
- input: 1.17,
14174
- output: 3.9600000000000004,
14175
- cacheRead: 0.234,
14209
+ input: 1.113,
14210
+ output: 3.4979999999999998,
14211
+ cacheRead: 0.2067,
14176
14212
  cacheWrite: 0,
14177
14213
  },
14178
14214
  contextWindow: 1310720,
14179
- maxTokens: 235929,
14215
+ maxTokens: 128000,
14180
14216
  },
14181
14217
  },
14182
14218
  "together": {
@@ -15692,6 +15728,23 @@ export const MODELS = {
15692
15728
  contextWindow: 1000000,
15693
15729
  maxTokens: 384000,
15694
15730
  },
15731
+ "deepseek/deepseek-v4.1-flash-beta": {
15732
+ id: "deepseek/deepseek-v4.1-flash-beta",
15733
+ name: "DeepSeek V4.1 Flash Beta",
15734
+ api: "anthropic-messages",
15735
+ provider: "vercel-ai-gateway",
15736
+ baseUrl: "https://ai-gateway.vercel.sh",
15737
+ reasoning: true,
15738
+ input: ["text", "image"],
15739
+ cost: {
15740
+ input: 0.22,
15741
+ output: 0.66,
15742
+ cacheRead: 0.007,
15743
+ cacheWrite: 0,
15744
+ },
15745
+ contextWindow: 1000000,
15746
+ maxTokens: 384000,
15747
+ },
15695
15748
  "google/gemini-2.5-flash": {
15696
15749
  id: "google/gemini-2.5-flash",
15697
15750
  name: "Gemini 2.5 Flash",
@@ -15930,6 +15983,23 @@ export const MODELS = {
15930
15983
  contextWindow: 128000,
15931
15984
  maxTokens: 128000,
15932
15985
  },
15986
+ "inception/mercury-2.5": {
15987
+ id: "inception/mercury-2.5",
15988
+ name: "Mercury 2.5",
15989
+ api: "anthropic-messages",
15990
+ provider: "vercel-ai-gateway",
15991
+ baseUrl: "https://ai-gateway.vercel.sh",
15992
+ reasoning: true,
15993
+ input: ["text"],
15994
+ cost: {
15995
+ input: 0.04,
15996
+ output: 0.15,
15997
+ cacheRead: 0.004,
15998
+ cacheWrite: 0,
15999
+ },
16000
+ contextWindow: 260000,
16001
+ maxTokens: 65536,
16002
+ },
15933
16003
  "inception/mercury-coder-small": {
15934
16004
  id: "inception/mercury-coder-small",
15935
16005
  name: "Mercury Coder Small Beta",
@@ -16406,23 +16476,6 @@ export const MODELS = {
16406
16476
  contextWindow: 204800,
16407
16477
  maxTokens: 131000,
16408
16478
  },
16409
- "minimax/minimax-m2.7-free": {
16410
- id: "minimax/minimax-m2.7-free",
16411
- name: "MiniMax M2.7 (Free)",
16412
- api: "anthropic-messages",
16413
- provider: "vercel-ai-gateway",
16414
- baseUrl: "https://ai-gateway.vercel.sh",
16415
- reasoning: true,
16416
- input: ["text"],
16417
- cost: {
16418
- input: 0,
16419
- output: 0,
16420
- cacheRead: 0,
16421
- cacheWrite: 0,
16422
- },
16423
- contextWindow: 196608,
16424
- maxTokens: 196608,
16425
- },
16426
16479
  "minimax/minimax-m2.7-highspeed": {
16427
16480
  id: "minimax/minimax-m2.7-highspeed",
16428
16481
  name: "MiniMax M2.7 High Speed",
@@ -16457,23 +16510,6 @@ export const MODELS = {
16457
16510
  contextWindow: 512000,
16458
16511
  maxTokens: 512000,
16459
16512
  },
16460
- "minimax/minimax-m3-free": {
16461
- id: "minimax/minimax-m3-free",
16462
- name: "MiniMax M3 (Free)",
16463
- api: "anthropic-messages",
16464
- provider: "vercel-ai-gateway",
16465
- baseUrl: "https://ai-gateway.vercel.sh",
16466
- reasoning: true,
16467
- input: ["text", "image"],
16468
- cost: {
16469
- input: 0,
16470
- output: 0,
16471
- cacheRead: 0,
16472
- cacheWrite: 0,
16473
- },
16474
- contextWindow: 1048576,
16475
- maxTokens: 1048576,
16476
- },
16477
16513
  "mistral/codestral": {
16478
16514
  id: "mistral/codestral",
16479
16515
  name: "Mistral Codestral",
@@ -18325,23 +18361,6 @@ export const MODELS = {
18325
18361
  contextWindow: 1050000,
18326
18362
  maxTokens: 131000,
18327
18363
  },
18328
- "xiaomi/mimo-v2.5-pro-ultraspeed": {
18329
- id: "xiaomi/mimo-v2.5-pro-ultraspeed",
18330
- name: "MiMo V2.5 Pro UltraSpeed",
18331
- api: "anthropic-messages",
18332
- provider: "vercel-ai-gateway",
18333
- baseUrl: "https://ai-gateway.vercel.sh",
18334
- reasoning: true,
18335
- input: ["text"],
18336
- cost: {
18337
- input: 1.305,
18338
- output: 2.61,
18339
- cacheRead: 0.0108,
18340
- cacheWrite: 0,
18341
- },
18342
- contextWindow: 1048576,
18343
- maxTokens: 131072,
18344
- },
18345
18364
  "zai/glm-4.5": {
18346
18365
  id: "zai/glm-4.5",
18347
18366
  name: "GLM 4.5",
@@ -18555,9 +18574,9 @@ export const MODELS = {
18555
18574
  reasoning: true,
18556
18575
  input: ["text"],
18557
18576
  cost: {
18558
- input: 0.7,
18559
- output: 2.2,
18560
- cacheRead: 0.13,
18577
+ input: 1.4,
18578
+ output: 4.4,
18579
+ cacheRead: 0.14,
18561
18580
  cacheWrite: 0,
18562
18581
  },
18563
18582
  contextWindow: 1000000,
@@ -18597,23 +18616,6 @@ export const MODELS = {
18597
18616
  contextWindow: 1000000,
18598
18617
  maxTokens: 131000,
18599
18618
  },
18600
- "zai/glm-5.3-promo-50": {
18601
- id: "zai/glm-5.3-promo-50",
18602
- name: "GLM 5.3 (50% off)",
18603
- api: "anthropic-messages",
18604
- provider: "vercel-ai-gateway",
18605
- baseUrl: "https://ai-gateway.vercel.sh",
18606
- reasoning: true,
18607
- input: ["text"],
18608
- cost: {
18609
- input: 0.7,
18610
- output: 2.2,
18611
- cacheRead: 0.13,
18612
- cacheWrite: 0,
18613
- },
18614
- contextWindow: 1048576,
18615
- maxTokens: 1048576,
18616
- },
18617
18619
  "zai/glm-5v-turbo": {
18618
18620
  id: "zai/glm-5v-turbo",
18619
18621
  name: "GLM 5V Turbo",