@kolisachint/hoocode-ai 0.5.61 → 0.5.63

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",
@@ -7469,6 +7486,23 @@ export const MODELS = {
7469
7486
  },
7470
7487
  },
7471
7488
  "opencode-go": {
7489
+ "deepseek-flash": {
7490
+ id: "deepseek-flash",
7491
+ name: "DeepSeek V4.1 Flash",
7492
+ api: "openai-completions",
7493
+ provider: "opencode-go",
7494
+ baseUrl: "https://opencode.ai/zen/go/v1",
7495
+ reasoning: true,
7496
+ input: ["text", "image"],
7497
+ cost: {
7498
+ input: 0.15,
7499
+ output: 0.6,
7500
+ cacheRead: 0.003,
7501
+ cacheWrite: 0,
7502
+ },
7503
+ contextWindow: 1000000,
7504
+ maxTokens: 384000,
7505
+ },
7472
7506
  "deepseek-v4-flash": {
7473
7507
  id: "deepseek-v4-flash",
7474
7508
  name: "DeepSeek V4 Flash",
@@ -7480,9 +7514,9 @@ export const MODELS = {
7480
7514
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
7481
7515
  input: ["text"],
7482
7516
  cost: {
7483
- input: 0.22,
7484
- output: 0.66,
7485
- cacheRead: 0.007,
7517
+ input: 0.15,
7518
+ output: 0.6,
7519
+ cacheRead: 0.003,
7486
7520
  cacheWrite: 0,
7487
7521
  },
7488
7522
  contextWindow: 1000000,
@@ -7499,9 +7533,9 @@ export const MODELS = {
7499
7533
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
7500
7534
  input: ["text", "image"],
7501
7535
  cost: {
7502
- input: 0.22,
7503
- output: 0.66,
7504
- cacheRead: 0.007,
7536
+ input: 0.15,
7537
+ output: 0.6,
7538
+ cacheRead: 0.003,
7505
7539
  cacheWrite: 0,
7506
7540
  },
7507
7541
  contextWindow: 1000000,
@@ -7579,16 +7613,16 @@ export const MODELS = {
7579
7613
  },
7580
7614
  "glm-5.3-flash": {
7581
7615
  id: "glm-5.3-flash",
7582
- name: "GLM-5.3-Flash (2x usage)",
7616
+ name: "GLM-5.3-Flash",
7583
7617
  api: "openai-completions",
7584
7618
  provider: "opencode-go",
7585
7619
  baseUrl: "https://opencode.ai/zen/go/v1",
7586
7620
  reasoning: true,
7587
7621
  input: ["text", "image"],
7588
7622
  cost: {
7589
- input: 0.075,
7590
- output: 0.25,
7591
- cacheRead: 0.015,
7623
+ input: 0.15,
7624
+ output: 0.5,
7625
+ cacheRead: 0.03,
7592
7626
  cacheWrite: 0,
7593
7627
  },
7594
7628
  contextWindow: 1000000,
@@ -7834,23 +7868,6 @@ export const MODELS = {
7834
7868
  contextWindow: 1048576,
7835
7869
  maxTokens: 131072,
7836
7870
  },
7837
- "omen-alpha": {
7838
- id: "omen-alpha",
7839
- name: "Omen Alpha",
7840
- api: "openai-completions",
7841
- provider: "opencode-go",
7842
- baseUrl: "https://opencode.ai/zen/go/v1",
7843
- reasoning: true,
7844
- input: ["text", "image"],
7845
- cost: {
7846
- input: 0.2,
7847
- output: 0.66,
7848
- cacheRead: 0.04,
7849
- cacheWrite: 0,
7850
- },
7851
- contextWindow: 500000,
7852
- maxTokens: 128000,
7853
- },
7854
7871
  "qwen3.6-plus": {
7855
7872
  id: "qwen3.6-plus",
7856
7873
  name: "Qwen3.6 Plus",
@@ -8743,13 +8760,13 @@ export const MODELS = {
8743
8760
  reasoning: false,
8744
8761
  input: ["text"],
8745
8762
  cost: {
8746
- input: 0.32,
8747
- output: 0.8899999999999999,
8763
+ input: 0.2574,
8764
+ output: 1.0287,
8748
8765
  cacheRead: 0,
8749
8766
  cacheWrite: 0,
8750
8767
  },
8751
8768
  contextWindow: 163840,
8752
- maxTokens: 16384,
8769
+ maxTokens: 16000,
8753
8770
  },
8754
8771
  "deepseek/deepseek-chat-v3-0324": {
8755
8772
  id: "deepseek/deepseek-chat-v3-0324",
@@ -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,
@@ -8995,14 +9031,33 @@ 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,
9004
9040
  maxTokens: 943718,
9005
9041
  },
9042
+ "deepseek/deepseek-v4.1-flash": {
9043
+ id: "deepseek/deepseek-v4.1-flash",
9044
+ name: "DeepSeek: DeepSeek V4.1 Flash",
9045
+ api: "openai-completions",
9046
+ provider: "openrouter",
9047
+ baseUrl: "https://openrouter.ai/api/v1",
9048
+ compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
9049
+ reasoning: true,
9050
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
9051
+ input: ["text", "image"],
9052
+ cost: {
9053
+ input: 0.3,
9054
+ output: 1.2,
9055
+ cacheRead: 0.006,
9056
+ cacheWrite: 0,
9057
+ },
9058
+ contextWindow: 1048576,
9059
+ maxTokens: 384000,
9060
+ },
9006
9061
  "dots-studio/dots-3-note-preview:free": {
9007
9062
  id: "dots-studio/dots-3-note-preview:free",
9008
9063
  name: "Dots Studio: Dots3-Note Preview (free)",
@@ -9607,9 +9662,9 @@ export const MODELS = {
9607
9662
  reasoning: true,
9608
9663
  input: ["text"],
9609
9664
  cost: {
9610
- input: 0.09999999999999999,
9611
- output: 0.15,
9612
- cacheRead: 0.049999999999999996,
9665
+ input: 0.06,
9666
+ output: 0.25,
9667
+ cacheRead: 0.015,
9613
9668
  cacheWrite: 0,
9614
9669
  },
9615
9670
  contextWindow: 131072,
@@ -9632,9 +9687,9 @@ export const MODELS = {
9632
9687
  contextWindow: 128000,
9633
9688
  maxTokens: 50000,
9634
9689
  },
9635
- "inception/mercury-2.5-preview": {
9636
- id: "inception/mercury-2.5-preview",
9637
- name: "Inception: Mercury 2.5 Preview",
9690
+ "inception/mercury-2.5": {
9691
+ id: "inception/mercury-2.5",
9692
+ name: "Inception: Mercury 2.5",
9638
9693
  api: "openai-completions",
9639
9694
  provider: "openrouter",
9640
9695
  baseUrl: "https://openrouter.ai/api/v1",
@@ -9896,9 +9951,9 @@ export const MODELS = {
9896
9951
  reasoning: true,
9897
9952
  input: ["text", "image"],
9898
9953
  cost: {
9899
- input: 0.35,
9900
- output: 1.5,
9901
- cacheRead: 0.04,
9954
+ input: 0.175,
9955
+ output: 0.75,
9956
+ cacheRead: 0.02,
9902
9957
  cacheWrite: 0,
9903
9958
  },
9904
9959
  contextWindow: 131072,
@@ -10049,13 +10104,13 @@ export const MODELS = {
10049
10104
  reasoning: true,
10050
10105
  input: ["text"],
10051
10106
  cost: {
10052
- input: 0.27,
10053
- output: 1.08,
10054
- cacheRead: 0.027,
10107
+ input: 0.3,
10108
+ output: 1.2,
10109
+ cacheRead: 0.03,
10055
10110
  cacheWrite: 0,
10056
10111
  },
10057
10112
  contextWindow: 204800,
10058
- maxTokens: 128000,
10113
+ maxTokens: 131072,
10059
10114
  },
10060
10115
  "minimax/minimax-m2.7": {
10061
10116
  id: "minimax/minimax-m2.7",
@@ -10074,23 +10129,6 @@ export const MODELS = {
10074
10129
  contextWindow: 204800,
10075
10130
  maxTokens: 131072,
10076
10131
  },
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
10132
  "minimax/minimax-m3": {
10095
10133
  id: "minimax/minimax-m3",
10096
10134
  name: "MiniMax: MiniMax M3",
@@ -10125,35 +10163,35 @@ export const MODELS = {
10125
10163
  contextWindow: 524288,
10126
10164
  maxTokens: 471859,
10127
10165
  },
10128
- "minimax/minimax-m3:free": {
10129
- id: "minimax/minimax-m3:free",
10130
- name: "MiniMax: MiniMax M3 (free)",
10166
+ "mistralai/codestral-2508": {
10167
+ id: "mistralai/codestral-2508",
10168
+ name: "Mistral: Codestral 2508",
10131
10169
  api: "openai-completions",
10132
10170
  provider: "openrouter",
10133
10171
  baseUrl: "https://openrouter.ai/api/v1",
10134
- reasoning: true,
10135
- input: ["text", "image"],
10172
+ reasoning: false,
10173
+ input: ["text"],
10136
10174
  cost: {
10137
- input: 0,
10138
- output: 0,
10139
- cacheRead: 0,
10175
+ input: 0.3,
10176
+ output: 0.8999999999999999,
10177
+ cacheRead: 0.03,
10140
10178
  cacheWrite: 0,
10141
10179
  },
10142
- contextWindow: 1048576,
10143
- maxTokens: 943718,
10180
+ contextWindow: 256000,
10181
+ maxTokens: 204800,
10144
10182
  },
10145
- "mistralai/codestral-2508": {
10146
- id: "mistralai/codestral-2508",
10147
- name: "Mistral: Codestral 2508",
10183
+ "mistralai/codestral-2508:batch": {
10184
+ id: "mistralai/codestral-2508:batch",
10185
+ name: "Mistral: Codestral 2508 (batch)",
10148
10186
  api: "openai-completions",
10149
10187
  provider: "openrouter",
10150
10188
  baseUrl: "https://openrouter.ai/api/v1",
10151
10189
  reasoning: false,
10152
10190
  input: ["text"],
10153
10191
  cost: {
10154
- input: 0.3,
10155
- output: 0.8999999999999999,
10156
- cacheRead: 0.03,
10192
+ input: 0.15,
10193
+ output: 0.44999999999999996,
10194
+ cacheRead: 0.015,
10157
10195
  cacheWrite: 0,
10158
10196
  },
10159
10197
  contextWindow: 256000,
@@ -10227,6 +10265,23 @@ export const MODELS = {
10227
10265
  contextWindow: 262144,
10228
10266
  maxTokens: 209715,
10229
10267
  },
10268
+ "mistralai/ministral-8b-2512:batch": {
10269
+ id: "mistralai/ministral-8b-2512:batch",
10270
+ name: "Mistral: Ministral 3 8B 2512 (batch)",
10271
+ api: "openai-completions",
10272
+ provider: "openrouter",
10273
+ baseUrl: "https://openrouter.ai/api/v1",
10274
+ reasoning: false,
10275
+ input: ["text", "image"],
10276
+ cost: {
10277
+ input: 0.075,
10278
+ output: 0.075,
10279
+ cacheRead: 0.0075,
10280
+ cacheWrite: 0,
10281
+ },
10282
+ contextWindow: 262144,
10283
+ maxTokens: 209715,
10284
+ },
10230
10285
  "mistralai/mistral-large": {
10231
10286
  id: "mistralai/mistral-large",
10232
10287
  name: "Mistral Large",
@@ -10278,6 +10333,23 @@ export const MODELS = {
10278
10333
  contextWindow: 262144,
10279
10334
  maxTokens: 209715,
10280
10335
  },
10336
+ "mistralai/mistral-large-2512:batch": {
10337
+ id: "mistralai/mistral-large-2512:batch",
10338
+ name: "Mistral: Mistral Large 3 2512 (batch)",
10339
+ api: "openai-completions",
10340
+ provider: "openrouter",
10341
+ baseUrl: "https://openrouter.ai/api/v1",
10342
+ reasoning: false,
10343
+ input: ["text", "image"],
10344
+ cost: {
10345
+ input: 0.25,
10346
+ output: 0.75,
10347
+ cacheRead: 0.024999999999999998,
10348
+ cacheWrite: 0,
10349
+ },
10350
+ contextWindow: 262144,
10351
+ maxTokens: 209715,
10352
+ },
10281
10353
  "mistralai/mistral-medium-3": {
10282
10354
  id: "mistralai/mistral-medium-3",
10283
10355
  name: "Mistral: Mistral Medium 3",
@@ -10326,8 +10398,8 @@ export const MODELS = {
10326
10398
  cacheRead: 0,
10327
10399
  cacheWrite: 0,
10328
10400
  },
10329
- contextWindow: 32768,
10330
- maxTokens: 26214,
10401
+ contextWindow: 262144,
10402
+ maxTokens: 209715,
10331
10403
  },
10332
10404
  "mistralai/mistral-medium-3.1": {
10333
10405
  id: "mistralai/mistral-medium-3.1",
@@ -10346,6 +10418,23 @@ export const MODELS = {
10346
10418
  contextWindow: 131072,
10347
10419
  maxTokens: 104857,
10348
10420
  },
10421
+ "mistralai/mistral-medium-3.1:batch": {
10422
+ id: "mistralai/mistral-medium-3.1:batch",
10423
+ name: "Mistral: Mistral Medium 3.1 (batch)",
10424
+ api: "openai-completions",
10425
+ provider: "openrouter",
10426
+ baseUrl: "https://openrouter.ai/api/v1",
10427
+ reasoning: false,
10428
+ input: ["text", "image"],
10429
+ cost: {
10430
+ input: 0.19999999999999998,
10431
+ output: 1,
10432
+ cacheRead: 0.02,
10433
+ cacheWrite: 0,
10434
+ },
10435
+ contextWindow: 131072,
10436
+ maxTokens: 104857,
10437
+ },
10349
10438
  "mistralai/mistral-nemo": {
10350
10439
  id: "mistralai/mistral-nemo",
10351
10440
  name: "Mistral: Mistral Nemo",
@@ -10397,6 +10486,23 @@ export const MODELS = {
10397
10486
  contextWindow: 262144,
10398
10487
  maxTokens: 209715,
10399
10488
  },
10489
+ "mistralai/mistral-small-2603:batch": {
10490
+ id: "mistralai/mistral-small-2603:batch",
10491
+ name: "Mistral: Mistral Small 4 (batch)",
10492
+ api: "openai-completions",
10493
+ provider: "openrouter",
10494
+ baseUrl: "https://openrouter.ai/api/v1",
10495
+ reasoning: true,
10496
+ input: ["text", "image"],
10497
+ cost: {
10498
+ input: 0.075,
10499
+ output: 0.3,
10500
+ cacheRead: 0.0075,
10501
+ cacheWrite: 0,
10502
+ },
10503
+ contextWindow: 262144,
10504
+ maxTokens: 209715,
10505
+ },
10400
10506
  "mistralai/mistral-small-3.2-24b-instruct": {
10401
10507
  id: "mistralai/mistral-small-3.2-24b-instruct",
10402
10508
  name: "Mistral: Mistral Small 3.2 24B",
@@ -10542,9 +10648,9 @@ export const MODELS = {
10542
10648
  reasoning: true,
10543
10649
  input: ["text", "image"],
10544
10650
  cost: {
10545
- input: 0.66,
10546
- output: 3.4,
10547
- cacheRead: 0.18,
10651
+ input: 0.71,
10652
+ output: 3.5,
10653
+ cacheRead: 0.15,
10548
10654
  cacheWrite: 0,
10549
10655
  },
10550
10656
  contextWindow: 262144,
@@ -10584,35 +10690,35 @@ export const MODELS = {
10584
10690
  contextWindow: 1048576,
10585
10691
  maxTokens: 943718,
10586
10692
  },
10587
- "nex-agi/nex-n2-mini": {
10588
- id: "nex-agi/nex-n2-mini",
10589
- name: "Nex AGI: Nex-N2-Mini",
10693
+ "nex-agi/nex-n2.5-mini:free": {
10694
+ id: "nex-agi/nex-n2.5-mini:free",
10695
+ name: "Nex AGI: Nex-N2.5-Mini (free)",
10590
10696
  api: "openai-completions",
10591
10697
  provider: "openrouter",
10592
10698
  baseUrl: "https://openrouter.ai/api/v1",
10593
10699
  reasoning: true,
10594
10700
  input: ["text", "image"],
10595
10701
  cost: {
10596
- input: 0.024999999999999998,
10597
- output: 0.09999999999999999,
10598
- cacheRead: 0.0025,
10702
+ input: 0,
10703
+ output: 0,
10704
+ cacheRead: 0,
10599
10705
  cacheWrite: 0,
10600
10706
  },
10601
10707
  contextWindow: 262144,
10602
10708
  maxTokens: 235929,
10603
10709
  },
10604
- "nex-agi/nex-n2-pro": {
10605
- id: "nex-agi/nex-n2-pro",
10606
- name: "Nex AGI: Nex-N2-Pro",
10710
+ "nex-agi/nex-n2.5-pro:free": {
10711
+ id: "nex-agi/nex-n2.5-pro:free",
10712
+ name: "Nex AGI: Nex-N2.5-Pro (free)",
10607
10713
  api: "openai-completions",
10608
10714
  provider: "openrouter",
10609
10715
  baseUrl: "https://openrouter.ai/api/v1",
10610
10716
  reasoning: true,
10611
10717
  input: ["text", "image"],
10612
10718
  cost: {
10613
- input: 0.25,
10614
- output: 1,
10615
- cacheRead: 0.024999999999999998,
10719
+ input: 0,
10720
+ output: 0,
10721
+ cacheRead: 0,
10616
10722
  cacheWrite: 0,
10617
10723
  },
10618
10724
  contextWindow: 262144,
@@ -10666,7 +10772,7 @@ export const MODELS = {
10666
10772
  cacheRead: 0,
10667
10773
  cacheWrite: 0,
10668
10774
  },
10669
- contextWindow: 1000000,
10775
+ contextWindow: 262144,
10670
10776
  maxTokens: 16384,
10671
10777
  },
10672
10778
  "nvidia/nemotron-3-super-120b-a12b:free": {
@@ -12448,13 +12554,13 @@ export const MODELS = {
12448
12554
  reasoning: true,
12449
12555
  input: ["text"],
12450
12556
  cost: {
12451
- input: 0.12,
12452
- output: 0.24,
12557
+ input: 0.22749999999999998,
12558
+ output: 0.9099999999999999,
12453
12559
  cacheRead: 0,
12454
12560
  cacheWrite: 0,
12455
12561
  },
12456
12562
  contextWindow: 131072,
12457
- maxTokens: 16384,
12563
+ maxTokens: 8192,
12458
12564
  },
12459
12565
  "qwen/qwen3-235b-a22b": {
12460
12566
  id: "qwen/qwen3-235b-a22b",
@@ -12482,8 +12588,8 @@ export const MODELS = {
12482
12588
  reasoning: false,
12483
12589
  input: ["text"],
12484
12590
  cost: {
12485
- input: 0.09,
12486
- output: 0.55,
12591
+ input: 0.22,
12592
+ output: 0.88,
12487
12593
  cacheRead: 0,
12488
12594
  cacheWrite: 0,
12489
12595
  },
@@ -12533,13 +12639,13 @@ export const MODELS = {
12533
12639
  reasoning: false,
12534
12640
  input: ["text"],
12535
12641
  cost: {
12536
- input: 0.04815,
12537
- output: 0.19305,
12642
+ input: 0.09,
12643
+ output: 0.3,
12538
12644
  cacheRead: 0,
12539
12645
  cacheWrite: 0,
12540
12646
  },
12541
12647
  contextWindow: 262144,
12542
- maxTokens: 32000,
12648
+ maxTokens: 235929,
12543
12649
  },
12544
12650
  "qwen/qwen3-30b-a3b-thinking-2507": {
12545
12651
  id: "qwen/qwen3-30b-a3b-thinking-2507",
@@ -12720,13 +12826,13 @@ export const MODELS = {
12720
12826
  reasoning: false,
12721
12827
  input: ["text"],
12722
12828
  cost: {
12723
- input: 0.09999999999999999,
12829
+ input: 0.09,
12724
12830
  output: 1.1,
12725
- cacheRead: 0.07,
12831
+ cacheRead: 0,
12726
12832
  cacheWrite: 0,
12727
12833
  },
12728
12834
  contextWindow: 262144,
12729
- maxTokens: 235929,
12835
+ maxTokens: 16384,
12730
12836
  },
12731
12837
  "qwen/qwen3-next-80b-a3b-thinking": {
12732
12838
  id: "qwen/qwen3-next-80b-a3b-thinking",
@@ -12743,7 +12849,7 @@ export const MODELS = {
12743
12849
  cacheWrite: 0,
12744
12850
  },
12745
12851
  contextWindow: 262144,
12746
- maxTokens: 32768,
12852
+ maxTokens: 235929,
12747
12853
  },
12748
12854
  "qwen/qwen3-vl-235b-a22b-instruct": {
12749
12855
  id: "qwen/qwen3-vl-235b-a22b-instruct",
@@ -12873,13 +12979,13 @@ export const MODELS = {
12873
12979
  reasoning: true,
12874
12980
  input: ["text", "image"],
12875
12981
  cost: {
12876
- input: 0.29,
12877
- output: 2.4,
12982
+ input: 0.26,
12983
+ output: 2.08,
12878
12984
  cacheRead: 0,
12879
12985
  cacheWrite: 0,
12880
12986
  },
12881
12987
  contextWindow: 262144,
12882
- maxTokens: 81920,
12988
+ maxTokens: 65536,
12883
12989
  },
12884
12990
  "qwen/qwen3.5-27b": {
12885
12991
  id: "qwen/qwen3.5-27b",
@@ -13168,7 +13274,7 @@ export const MODELS = {
13168
13274
  cacheWrite: 0,
13169
13275
  },
13170
13276
  contextWindow: 1048576,
13171
- maxTokens: 262144,
13277
+ maxTokens: 131072,
13172
13278
  },
13173
13279
  "qwen/qwen3.8-2.4t-a95b:batch": {
13174
13280
  id: "qwen/qwen3.8-2.4t-a95b:batch",
@@ -13366,9 +13472,9 @@ export const MODELS = {
13366
13472
  reasoning: true,
13367
13473
  input: ["text"],
13368
13474
  cost: {
13369
- input: 0.0825,
13370
- output: 0.33,
13371
- cacheRead: 0.020625,
13475
+ input: 0.13199999999999998,
13476
+ output: 0.5279999999999999,
13477
+ cacheRead: 0.032999999999999995,
13372
13478
  cacheWrite: 0,
13373
13479
  },
13374
13480
  contextWindow: 262144,
@@ -13440,7 +13546,7 @@ export const MODELS = {
13440
13546
  cacheWrite: 0,
13441
13547
  },
13442
13548
  contextWindow: 1048576,
13443
- maxTokens: 471859,
13549
+ maxTokens: 32768,
13444
13550
  },
13445
13551
  "thinkingmachines/inkling-small": {
13446
13552
  id: "thinkingmachines/inkling-small",
@@ -13757,13 +13863,13 @@ export const MODELS = {
13757
13863
  reasoning: true,
13758
13864
  input: ["text"],
13759
13865
  cost: {
13760
- input: 0.55,
13761
- output: 2.2,
13762
- cacheRead: 0.11,
13866
+ input: 0.43,
13867
+ output: 1.75,
13868
+ cacheRead: 0.08,
13763
13869
  cacheWrite: 0,
13764
13870
  },
13765
13871
  contextWindow: 204800,
13766
- maxTokens: 131072,
13872
+ maxTokens: 16384,
13767
13873
  },
13768
13874
  "z-ai/glm-4.6v": {
13769
13875
  id: "z-ai/glm-4.6v",
@@ -13808,13 +13914,13 @@ export const MODELS = {
13808
13914
  reasoning: true,
13809
13915
  input: ["text"],
13810
13916
  cost: {
13811
- input: 0.06,
13917
+ input: 0.060500000000000005,
13812
13918
  output: 0.39999999999999997,
13813
- cacheRead: 0.01,
13919
+ cacheRead: 0,
13814
13920
  cacheWrite: 0,
13815
13921
  },
13816
13922
  contextWindow: 202752,
13817
- maxTokens: 16384,
13923
+ maxTokens: 117964,
13818
13924
  },
13819
13925
  "z-ai/glm-5": {
13820
13926
  id: "z-ai/glm-5",
@@ -13884,6 +13990,23 @@ export const MODELS = {
13884
13990
  contextWindow: 1048576,
13885
13991
  maxTokens: 131072,
13886
13992
  },
13993
+ "z-ai/glm-5.2:batch": {
13994
+ id: "z-ai/glm-5.2:batch",
13995
+ name: "Z.ai: GLM 5.2 (batch)",
13996
+ api: "openai-completions",
13997
+ provider: "openrouter",
13998
+ baseUrl: "https://openrouter.ai/api/v1",
13999
+ reasoning: true,
14000
+ input: ["text"],
14001
+ cost: {
14002
+ input: 0.7,
14003
+ output: 2.2,
14004
+ cacheRead: 0.07,
14005
+ cacheWrite: 0,
14006
+ },
14007
+ contextWindow: 1048576,
14008
+ maxTokens: 943718,
14009
+ },
13887
14010
  "z-ai/glm-5.3": {
13888
14011
  id: "z-ai/glm-5.3",
13889
14012
  name: "Z.ai: GLM 5.3",
@@ -13895,11 +14018,11 @@ export const MODELS = {
13895
14018
  cost: {
13896
14019
  input: 1.4,
13897
14020
  output: 4.4,
13898
- cacheRead: 0.14,
14021
+ cacheRead: 0.26,
13899
14022
  cacheWrite: 0,
13900
14023
  },
13901
14024
  contextWindow: 1310720,
13902
- maxTokens: 262144,
14025
+ maxTokens: 943718,
13903
14026
  },
13904
14027
  "z-ai/glm-5.3-flash": {
13905
14028
  id: "z-ai/glm-5.3-flash",
@@ -13927,13 +14050,30 @@ export const MODELS = {
13927
14050
  reasoning: true,
13928
14051
  input: ["text", "image"],
13929
14052
  cost: {
13930
- input: 0.15,
13931
- output: 0.5,
13932
- cacheRead: 0.03,
14053
+ input: 0.075,
14054
+ output: 0.25,
14055
+ cacheRead: 0.015,
13933
14056
  cacheWrite: 0,
13934
14057
  },
13935
- contextWindow: 1048575,
13936
- maxTokens: 943717,
14058
+ contextWindow: 1048576,
14059
+ maxTokens: 943718,
14060
+ },
14061
+ "z-ai/glm-5.3:batch": {
14062
+ id: "z-ai/glm-5.3:batch",
14063
+ name: "Z.ai: GLM 5.3 (batch)",
14064
+ api: "openai-completions",
14065
+ provider: "openrouter",
14066
+ baseUrl: "https://openrouter.ai/api/v1",
14067
+ reasoning: true,
14068
+ input: ["text"],
14069
+ cost: {
14070
+ input: 0.7,
14071
+ output: 2.2,
14072
+ cacheRead: 0.13,
14073
+ cacheWrite: 0,
14074
+ },
14075
+ contextWindow: 1048576,
14076
+ maxTokens: 943718,
13937
14077
  },
13938
14078
  "z-ai/glm-5v-turbo": {
13939
14079
  id: "z-ai/glm-5v-turbo",
@@ -14034,13 +14174,13 @@ export const MODELS = {
14034
14174
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
14035
14175
  input: ["text"],
14036
14176
  cost: {
14037
- input: 0.045,
14038
- output: 0.09,
14039
- cacheRead: 0.009,
14177
+ input: 0.049999999999999996,
14178
+ output: 0.16,
14179
+ cacheRead: 0.013000000000000001,
14040
14180
  cacheWrite: 0,
14041
14181
  },
14042
14182
  contextWindow: 1310720,
14043
- maxTokens: 943718,
14183
+ maxTokens: 393216,
14044
14184
  },
14045
14185
  "~google/gemini-flash-latest": {
14046
14186
  id: "~google/gemini-flash-latest",
@@ -14085,9 +14225,9 @@ export const MODELS = {
14085
14225
  reasoning: true,
14086
14226
  input: ["text", "image"],
14087
14227
  cost: {
14088
- input: 2.5500000000000003,
14089
- output: 12.75,
14090
- cacheRead: 0.25599998999999996,
14228
+ input: 2.4,
14229
+ output: 12,
14230
+ cacheRead: 0.24,
14091
14231
  cacheWrite: 0,
14092
14232
  },
14093
14233
  contextWindow: 1048576,
@@ -14159,7 +14299,7 @@ export const MODELS = {
14159
14299
  cacheWrite: 0,
14160
14300
  },
14161
14301
  contextWindow: 1310720,
14162
- maxTokens: 943718,
14302
+ maxTokens: 131072,
14163
14303
  },
14164
14304
  "~z-ai/glm-latest": {
14165
14305
  id: "~z-ai/glm-latest",
@@ -14170,13 +14310,13 @@ export const MODELS = {
14170
14310
  reasoning: true,
14171
14311
  input: ["text"],
14172
14312
  cost: {
14173
- input: 1.17,
14174
- output: 3.9600000000000004,
14175
- cacheRead: 0.234,
14313
+ input: 1.085,
14314
+ output: 3.41,
14315
+ cacheRead: 0.20149999999999998,
14176
14316
  cacheWrite: 0,
14177
14317
  },
14178
14318
  contextWindow: 1310720,
14179
- maxTokens: 235929,
14319
+ maxTokens: 128000,
14180
14320
  },
14181
14321
  },
14182
14322
  "together": {
@@ -15582,9 +15722,9 @@ export const MODELS = {
15582
15722
  reasoning: false,
15583
15723
  input: ["text"],
15584
15724
  cost: {
15585
- input: 0.28,
15586
- output: 0.42,
15587
- cacheRead: 0.028,
15725
+ input: 0.62,
15726
+ output: 1.85,
15727
+ cacheRead: 0,
15588
15728
  cacheWrite: 0,
15589
15729
  },
15590
15730
  contextWindow: 128000,
@@ -15692,6 +15832,23 @@ export const MODELS = {
15692
15832
  contextWindow: 1000000,
15693
15833
  maxTokens: 384000,
15694
15834
  },
15835
+ "deepseek/deepseek-v4.1-flash": {
15836
+ id: "deepseek/deepseek-v4.1-flash",
15837
+ name: "DeepSeek V4.1 Flash",
15838
+ api: "anthropic-messages",
15839
+ provider: "vercel-ai-gateway",
15840
+ baseUrl: "https://ai-gateway.vercel.sh",
15841
+ reasoning: true,
15842
+ input: ["text", "image"],
15843
+ cost: {
15844
+ input: 0.15,
15845
+ output: 0.6,
15846
+ cacheRead: 0.003,
15847
+ cacheWrite: 0,
15848
+ },
15849
+ contextWindow: 1000000,
15850
+ maxTokens: 384000,
15851
+ },
15695
15852
  "google/gemini-2.5-flash": {
15696
15853
  id: "google/gemini-2.5-flash",
15697
15854
  name: "Gemini 2.5 Flash",
@@ -15930,6 +16087,23 @@ export const MODELS = {
15930
16087
  contextWindow: 128000,
15931
16088
  maxTokens: 128000,
15932
16089
  },
16090
+ "inception/mercury-2.5": {
16091
+ id: "inception/mercury-2.5",
16092
+ name: "Mercury 2.5",
16093
+ api: "anthropic-messages",
16094
+ provider: "vercel-ai-gateway",
16095
+ baseUrl: "https://ai-gateway.vercel.sh",
16096
+ reasoning: true,
16097
+ input: ["text"],
16098
+ cost: {
16099
+ input: 0.04,
16100
+ output: 0.15,
16101
+ cacheRead: 0.004,
16102
+ cacheWrite: 0,
16103
+ },
16104
+ contextWindow: 260000,
16105
+ maxTokens: 65536,
16106
+ },
15933
16107
  "inception/mercury-coder-small": {
15934
16108
  id: "inception/mercury-coder-small",
15935
16109
  name: "Mercury Coder Small Beta",
@@ -16406,23 +16580,6 @@ export const MODELS = {
16406
16580
  contextWindow: 204800,
16407
16581
  maxTokens: 131000,
16408
16582
  },
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
16583
  "minimax/minimax-m2.7-highspeed": {
16427
16584
  id: "minimax/minimax-m2.7-highspeed",
16428
16585
  name: "MiniMax M2.7 High Speed",
@@ -16457,23 +16614,6 @@ export const MODELS = {
16457
16614
  contextWindow: 512000,
16458
16615
  maxTokens: 512000,
16459
16616
  },
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
16617
  "mistral/codestral": {
16478
16618
  id: "mistral/codestral",
16479
16619
  name: "Mistral Codestral",
@@ -18325,23 +18465,6 @@ export const MODELS = {
18325
18465
  contextWindow: 1050000,
18326
18466
  maxTokens: 131000,
18327
18467
  },
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
18468
  "zai/glm-4.5": {
18346
18469
  id: "zai/glm-4.5",
18347
18470
  name: "GLM 4.5",
@@ -18555,9 +18678,9 @@ export const MODELS = {
18555
18678
  reasoning: true,
18556
18679
  input: ["text"],
18557
18680
  cost: {
18558
- input: 0.7,
18559
- output: 2.2,
18560
- cacheRead: 0.13,
18681
+ input: 1.4,
18682
+ output: 4.4,
18683
+ cacheRead: 0.14,
18561
18684
  cacheWrite: 0,
18562
18685
  },
18563
18686
  contextWindow: 1000000,
@@ -18597,23 +18720,6 @@ export const MODELS = {
18597
18720
  contextWindow: 1000000,
18598
18721
  maxTokens: 131000,
18599
18722
  },
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
18723
  "zai/glm-5v-turbo": {
18618
18724
  id: "zai/glm-5v-turbo",
18619
18725
  name: "GLM 5V Turbo",