@dreb/ai 2.62.0 → 2.64.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -3235,9 +3235,9 @@ export const MODELS = {
3235
3235
  reasoning: true,
3236
3236
  input: ["text", "image"],
3237
3237
  cost: {
3238
- input: 1.5,
3239
- output: 7.5,
3240
- cacheRead: 0.15,
3238
+ input: 0.75,
3239
+ output: 3.75,
3240
+ cacheRead: 0.075,
3241
3241
  cacheWrite: 0,
3242
3242
  },
3243
3243
  contextWindow: 1000000,
@@ -3438,7 +3438,7 @@ export const MODELS = {
3438
3438
  input: 0.2,
3439
3439
  output: 1.2,
3440
3440
  cacheRead: 0.02,
3441
- cacheWrite: 0,
3441
+ cacheWrite: 0.25,
3442
3442
  },
3443
3443
  contextWindow: 1050000,
3444
3444
  maxTokens: 128000,
@@ -3453,10 +3453,10 @@ export const MODELS = {
3453
3453
  reasoning: true,
3454
3454
  input: ["text", "image"],
3455
3455
  cost: {
3456
- input: 2.5,
3457
- output: 15,
3458
- cacheRead: 0.25,
3459
- cacheWrite: 3.125,
3456
+ input: 2,
3457
+ output: 10,
3458
+ cacheRead: 0.2,
3459
+ cacheWrite: 2.5,
3460
3460
  },
3461
3461
  contextWindow: 1050000,
3462
3462
  maxTokens: 128000,
@@ -3474,7 +3474,7 @@ export const MODELS = {
3474
3474
  input: 2,
3475
3475
  output: 12,
3476
3476
  cacheRead: 0.2,
3477
- cacheWrite: 0,
3477
+ cacheWrite: 2.5,
3478
3478
  },
3479
3479
  contextWindow: 1050000,
3480
3480
  maxTokens: 128000,
@@ -5772,7 +5772,7 @@ export const MODELS = {
5772
5772
  baseUrl: "https://router.huggingface.co/v1",
5773
5773
  compat: { "supportsDeveloperRole": false },
5774
5774
  reasoning: true,
5775
- input: ["text"],
5775
+ input: ["text", "image"],
5776
5776
  cost: {
5777
5777
  input: 0.15,
5778
5778
  output: 0.5,
@@ -8283,6 +8283,23 @@ export const MODELS = {
8283
8283
  contextWindow: 1048576,
8284
8284
  maxTokens: 131072,
8285
8285
  },
8286
+ "ling-3.0-flash-fin-free": {
8287
+ id: "ling-3.0-flash-fin-free",
8288
+ name: "Ling 3.0 Flash Fin Free",
8289
+ api: "openai-completions",
8290
+ provider: "opencode",
8291
+ baseUrl: "https://opencode.ai/zen/v1",
8292
+ reasoning: true,
8293
+ input: ["text"],
8294
+ cost: {
8295
+ input: 0,
8296
+ output: 0,
8297
+ cacheRead: 0,
8298
+ cacheWrite: 0,
8299
+ },
8300
+ contextWindow: 262144,
8301
+ maxTokens: 32768,
8302
+ },
8286
8303
  "mimo-v2.5-free": {
8287
8304
  id: "mimo-v2.5-free",
8288
8305
  name: "MiMo V2.5 Free",
@@ -8625,6 +8642,23 @@ export const MODELS = {
8625
8642
  contextWindow: 256000,
8626
8643
  maxTokens: 64000,
8627
8644
  },
8645
+ "hy4-preview": {
8646
+ id: "hy4-preview",
8647
+ name: "Hy4 preview",
8648
+ api: "openai-completions",
8649
+ provider: "opencode-go",
8650
+ baseUrl: "https://opencode.ai/zen/go/v1",
8651
+ reasoning: true,
8652
+ input: ["text"],
8653
+ cost: {
8654
+ input: 0.834,
8655
+ output: 2.501,
8656
+ cacheRead: 0.042,
8657
+ cacheWrite: 0,
8658
+ },
8659
+ contextWindow: 1024000,
8660
+ maxTokens: 64000,
8661
+ },
8628
8662
  "kimi-k2.6": {
8629
8663
  id: "kimi-k2.6",
8630
8664
  name: "Kimi K2.6",
@@ -8829,6 +8863,23 @@ export const MODELS = {
8829
8863
  contextWindow: 1000000,
8830
8864
  maxTokens: 65536,
8831
8865
  },
8866
+ "qwen3.8-flash": {
8867
+ id: "qwen3.8-flash",
8868
+ name: "Qwen3.8 Flash",
8869
+ api: "anthropic-messages",
8870
+ provider: "opencode-go",
8871
+ baseUrl: "https://opencode.ai/zen/go",
8872
+ reasoning: true,
8873
+ input: ["text", "image"],
8874
+ cost: {
8875
+ input: 0.15,
8876
+ output: 0.47,
8877
+ cacheRead: 0.016,
8878
+ cacheWrite: 0.2,
8879
+ },
8880
+ contextWindow: 1000000,
8881
+ maxTokens: 131072,
8882
+ },
8832
8883
  "qwen3.8-max": {
8833
8884
  id: "qwen3.8-max",
8834
8885
  name: "Qwen3.8 Max",
@@ -9775,13 +9826,13 @@ export const MODELS = {
9775
9826
  reasoning: true,
9776
9827
  input: ["text"],
9777
9828
  cost: {
9778
- input: 0.26,
9779
- output: 0.38,
9780
- cacheRead: 0.13,
9829
+ input: 0.26899999999999996,
9830
+ output: 0.39999999999999997,
9831
+ cacheRead: 0.13449999999999998,
9781
9832
  cacheWrite: 0,
9782
9833
  },
9783
9834
  contextWindow: 163840,
9784
- maxTokens: 147456,
9835
+ maxTokens: 65536,
9785
9836
  },
9786
9837
  "deepseek/deepseek-v3.2-exp": {
9787
9838
  id: "deepseek/deepseek-v3.2-exp",
@@ -9809,9 +9860,9 @@ export const MODELS = {
9809
9860
  reasoning: true,
9810
9861
  input: ["text"],
9811
9862
  cost: {
9812
- input: 0.07798000000000001,
9813
- output: 0.15596000000000002,
9814
- cacheRead: 0.015595999999999999,
9863
+ input: 0.0868,
9864
+ output: 0.1736,
9865
+ cacheRead: 0.01736,
9815
9866
  cacheWrite: 0,
9816
9867
  },
9817
9868
  contextWindow: 1048576,
@@ -9834,6 +9885,23 @@ export const MODELS = {
9834
9885
  contextWindow: 1310720,
9835
9886
  maxTokens: 943718,
9836
9887
  },
9888
+ "deepseek/deepseek-v4-flash-0731:batch": {
9889
+ id: "deepseek/deepseek-v4-flash-0731:batch",
9890
+ name: "DeepSeek: DeepSeek V4 Flash 0731 (batch)",
9891
+ api: "openai-completions",
9892
+ provider: "openrouter",
9893
+ baseUrl: "https://openrouter.ai/api/v1",
9894
+ reasoning: true,
9895
+ input: ["text"],
9896
+ cost: {
9897
+ input: 0.14,
9898
+ output: 0.28,
9899
+ cacheRead: 0.03,
9900
+ cacheWrite: 0,
9901
+ },
9902
+ contextWindow: 1048576,
9903
+ maxTokens: 943718,
9904
+ },
9837
9905
  "deepseek/deepseek-v4-flash-vision-exp": {
9838
9906
  id: "deepseek/deepseek-v4-flash-vision-exp",
9839
9907
  name: "DeepSeek: DeepSeek V4 Flash Vision Exp",
@@ -9860,9 +9928,9 @@ export const MODELS = {
9860
9928
  reasoning: true,
9861
9929
  input: ["text"],
9862
9930
  cost: {
9863
- input: 0.87,
9864
- output: 1.74,
9865
- cacheRead: 0.0725,
9931
+ input: 0.741588,
9932
+ output: 1.483176,
9933
+ cacheRead: 0.061799,
9866
9934
  cacheWrite: 0,
9867
9935
  },
9868
9936
  contextWindow: 1048576,
@@ -9877,13 +9945,30 @@ export const MODELS = {
9877
9945
  reasoning: true,
9878
9946
  input: ["text"],
9879
9947
  cost: {
9880
- input: 1.122,
9881
- output: 3.366,
9882
- cacheRead: 0.037399999999999996,
9948
+ input: 0.66,
9949
+ output: 1.9800000000000002,
9950
+ cacheRead: 0.022,
9951
+ cacheWrite: 0,
9952
+ },
9953
+ contextWindow: 1048576,
9954
+ maxTokens: 384000,
9955
+ },
9956
+ "deepseek/deepseek-v4-pro-0813:batch": {
9957
+ id: "deepseek/deepseek-v4-pro-0813:batch",
9958
+ name: "DeepSeek: DeepSeek V4 Pro 0813 (batch)",
9959
+ api: "openai-completions",
9960
+ provider: "openrouter",
9961
+ baseUrl: "https://openrouter.ai/api/v1",
9962
+ reasoning: true,
9963
+ input: ["text"],
9964
+ cost: {
9965
+ input: 1.32,
9966
+ output: 3.9600000000000004,
9967
+ cacheRead: 0.13,
9883
9968
  cacheWrite: 0,
9884
9969
  },
9885
9970
  contextWindow: 1048576,
9886
- maxTokens: 943717,
9971
+ maxTokens: 943718,
9887
9972
  },
9888
9973
  "dots-studio/dots-3-note-preview:free": {
9889
9974
  id: "dots-studio/dots-3-note-preview:free",
@@ -10302,10 +10387,10 @@ export const MODELS = {
10302
10387
  reasoning: true,
10303
10388
  input: ["text", "image"],
10304
10389
  cost: {
10305
- input: 0.375,
10306
- output: 1.875,
10307
- cacheRead: 0.0375,
10308
- cacheWrite: 0.0208333333333333,
10390
+ input: 0.75,
10391
+ output: 3.75,
10392
+ cacheRead: 0.075,
10393
+ cacheWrite: 0.0416666666666667,
10309
10394
  },
10310
10395
  contextWindow: 1048576,
10311
10396
  maxTokens: 65536,
@@ -10358,7 +10443,7 @@ export const MODELS = {
10358
10443
  cacheRead: 0.04,
10359
10444
  cacheWrite: 0,
10360
10445
  },
10361
- contextWindow: 262144,
10446
+ contextWindow: 131072,
10362
10447
  maxTokens: 117964,
10363
10448
  },
10364
10449
  "google/gemma-4-26b-a4b-it": {
@@ -10412,6 +10497,23 @@ export const MODELS = {
10412
10497
  contextWindow: 262144,
10413
10498
  maxTokens: 16384,
10414
10499
  },
10500
+ "google/gemma-4-31b-it:batch": {
10501
+ id: "google/gemma-4-31b-it:batch",
10502
+ name: "Google: Gemma 4 31B (batch)",
10503
+ api: "openai-completions",
10504
+ provider: "openrouter",
10505
+ baseUrl: "https://openrouter.ai/api/v1",
10506
+ reasoning: true,
10507
+ input: ["text", "image"],
10508
+ cost: {
10509
+ input: 0.39,
10510
+ output: 0.9700000000000001,
10511
+ cacheRead: 0,
10512
+ cacheWrite: 0,
10513
+ },
10514
+ contextWindow: 262144,
10515
+ maxTokens: 235929,
10516
+ },
10415
10517
  "google/gemma-4-31b-it:free": {
10416
10518
  id: "google/gemma-4-31b-it:free",
10417
10519
  name: "Google: Gemma 4 31B (free)",
@@ -10545,7 +10647,7 @@ export const MODELS = {
10545
10647
  cacheRead: 0.15,
10546
10648
  cacheWrite: 0,
10547
10649
  },
10548
- contextWindow: 256000,
10650
+ contextWindow: 262144,
10549
10651
  maxTokens: 80000,
10550
10652
  },
10551
10653
  "liquid/lfm-2.5-2.6b:free": {
@@ -10675,6 +10777,23 @@ export const MODELS = {
10675
10777
  baseUrl: "https://openrouter.ai/api/v1",
10676
10778
  reasoning: true,
10677
10779
  input: ["text", "image"],
10780
+ cost: {
10781
+ input: 0.3,
10782
+ output: 1.2,
10783
+ cacheRead: 0.04,
10784
+ cacheWrite: 0,
10785
+ },
10786
+ contextWindow: 131072,
10787
+ maxTokens: 16384,
10788
+ },
10789
+ "meta/muse-glimmer-30b:batch": {
10790
+ id: "meta/muse-glimmer-30b:batch",
10791
+ name: "Meta: Muse Glimmer 30B (batch)",
10792
+ api: "openai-completions",
10793
+ provider: "openrouter",
10794
+ baseUrl: "https://openrouter.ai/api/v1",
10795
+ reasoning: true,
10796
+ input: ["text", "image"],
10678
10797
  cost: {
10679
10798
  input: 0.35,
10680
10799
  output: 1.5,
@@ -10905,6 +11024,23 @@ export const MODELS = {
10905
11024
  contextWindow: 256000,
10906
11025
  maxTokens: 204800,
10907
11026
  },
11027
+ "mistralai/codestral-2508:batch": {
11028
+ id: "mistralai/codestral-2508:batch",
11029
+ name: "Mistral: Codestral 2508 (batch)",
11030
+ api: "openai-completions",
11031
+ provider: "openrouter",
11032
+ baseUrl: "https://openrouter.ai/api/v1",
11033
+ reasoning: false,
11034
+ input: ["text"],
11035
+ cost: {
11036
+ input: 0.3,
11037
+ output: 0.8999999999999999,
11038
+ cacheRead: 0.03,
11039
+ cacheWrite: 0,
11040
+ },
11041
+ contextWindow: 256000,
11042
+ maxTokens: 204800,
11043
+ },
10908
11044
  "mistralai/devstral-2512": {
10909
11045
  id: "mistralai/devstral-2512",
10910
11046
  name: "Mistral: Devstral 2 2512",
@@ -10973,6 +11109,23 @@ export const MODELS = {
10973
11109
  contextWindow: 262144,
10974
11110
  maxTokens: 209715,
10975
11111
  },
11112
+ "mistralai/ministral-8b-2512:batch": {
11113
+ id: "mistralai/ministral-8b-2512:batch",
11114
+ name: "Mistral: Ministral 3 8B 2512 (batch)",
11115
+ api: "openai-completions",
11116
+ provider: "openrouter",
11117
+ baseUrl: "https://openrouter.ai/api/v1",
11118
+ reasoning: false,
11119
+ input: ["text", "image"],
11120
+ cost: {
11121
+ input: 0.15,
11122
+ output: 0.15,
11123
+ cacheRead: 0.015,
11124
+ cacheWrite: 0,
11125
+ },
11126
+ contextWindow: 262144,
11127
+ maxTokens: 209715,
11128
+ },
10976
11129
  "mistralai/mistral-large": {
10977
11130
  id: "mistralai/mistral-large",
10978
11131
  name: "Mistral Large",
@@ -11024,6 +11177,23 @@ export const MODELS = {
11024
11177
  contextWindow: 262144,
11025
11178
  maxTokens: 209715,
11026
11179
  },
11180
+ "mistralai/mistral-large-2512:batch": {
11181
+ id: "mistralai/mistral-large-2512:batch",
11182
+ name: "Mistral: Mistral Large 3 2512 (batch)",
11183
+ api: "openai-completions",
11184
+ provider: "openrouter",
11185
+ baseUrl: "https://openrouter.ai/api/v1",
11186
+ reasoning: false,
11187
+ input: ["text", "image"],
11188
+ cost: {
11189
+ input: 0.5,
11190
+ output: 1.5,
11191
+ cacheRead: 0.049999999999999996,
11192
+ cacheWrite: 0,
11193
+ },
11194
+ contextWindow: 262144,
11195
+ maxTokens: 209715,
11196
+ },
11027
11197
  "mistralai/mistral-medium-3": {
11028
11198
  id: "mistralai/mistral-medium-3",
11029
11199
  name: "Mistral: Mistral Medium 3",
@@ -11058,6 +11228,23 @@ export const MODELS = {
11058
11228
  contextWindow: 262144,
11059
11229
  maxTokens: 209715,
11060
11230
  },
11231
+ "mistralai/mistral-medium-3-5:batch": {
11232
+ id: "mistralai/mistral-medium-3-5:batch",
11233
+ name: "Mistral: Mistral Medium 3.5 (batch)",
11234
+ api: "openai-completions",
11235
+ provider: "openrouter",
11236
+ baseUrl: "https://openrouter.ai/api/v1",
11237
+ reasoning: true,
11238
+ input: ["text", "image"],
11239
+ cost: {
11240
+ input: 0.75,
11241
+ output: 3.75,
11242
+ cacheRead: 0,
11243
+ cacheWrite: 0,
11244
+ },
11245
+ contextWindow: 262144,
11246
+ maxTokens: 209715,
11247
+ },
11061
11248
  "mistralai/mistral-medium-3.1": {
11062
11249
  id: "mistralai/mistral-medium-3.1",
11063
11250
  name: "Mistral: Mistral Medium 3.1",
@@ -11075,6 +11262,23 @@ export const MODELS = {
11075
11262
  contextWindow: 131072,
11076
11263
  maxTokens: 104857,
11077
11264
  },
11265
+ "mistralai/mistral-medium-3.1:batch": {
11266
+ id: "mistralai/mistral-medium-3.1:batch",
11267
+ name: "Mistral: Mistral Medium 3.1 (batch)",
11268
+ api: "openai-completions",
11269
+ provider: "openrouter",
11270
+ baseUrl: "https://openrouter.ai/api/v1",
11271
+ reasoning: false,
11272
+ input: ["text", "image"],
11273
+ cost: {
11274
+ input: 0.39999999999999997,
11275
+ output: 2,
11276
+ cacheRead: 0.04,
11277
+ cacheWrite: 0,
11278
+ },
11279
+ contextWindow: 131072,
11280
+ maxTokens: 104857,
11281
+ },
11078
11282
  "mistralai/mistral-nemo": {
11079
11283
  id: "mistralai/mistral-nemo",
11080
11284
  name: "Mistral: Mistral Nemo",
@@ -11126,6 +11330,23 @@ export const MODELS = {
11126
11330
  contextWindow: 262144,
11127
11331
  maxTokens: 209715,
11128
11332
  },
11333
+ "mistralai/mistral-small-2603:batch": {
11334
+ id: "mistralai/mistral-small-2603:batch",
11335
+ name: "Mistral: Mistral Small 4 (batch)",
11336
+ api: "openai-completions",
11337
+ provider: "openrouter",
11338
+ baseUrl: "https://openrouter.ai/api/v1",
11339
+ reasoning: true,
11340
+ input: ["text", "image"],
11341
+ cost: {
11342
+ input: 0.15,
11343
+ output: 0.6,
11344
+ cacheRead: 0.015,
11345
+ cacheWrite: 0,
11346
+ },
11347
+ contextWindow: 262144,
11348
+ maxTokens: 209715,
11349
+ },
11129
11350
  "mistralai/mistral-small-3.2-24b-instruct": {
11130
11351
  id: "mistralai/mistral-small-3.2-24b-instruct",
11131
11352
  name: "Mistral: Mistral Small 3.2 24B",
@@ -11174,8 +11395,8 @@ export const MODELS = {
11174
11395
  cacheRead: 0.01,
11175
11396
  cacheWrite: 0,
11176
11397
  },
11177
- contextWindow: 32000,
11178
- maxTokens: 25600,
11398
+ contextWindow: 32768,
11399
+ maxTokens: 26214,
11179
11400
  },
11180
11401
  "moonshotai/kimi-k2": {
11181
11402
  id: "moonshotai/kimi-k2",
@@ -11279,26 +11500,26 @@ export const MODELS = {
11279
11500
  contextWindow: 262144,
11280
11501
  maxTokens: 235929,
11281
11502
  },
11282
- "moonshotai/kimi-k2.7-code:batch": {
11283
- id: "moonshotai/kimi-k2.7-code:batch",
11284
- name: "MoonshotAI: Kimi K2.7 Code (batch)",
11503
+ "moonshotai/kimi-k3": {
11504
+ id: "moonshotai/kimi-k3",
11505
+ name: "MoonshotAI: Kimi K3",
11285
11506
  api: "openai-completions",
11286
11507
  provider: "openrouter",
11287
11508
  baseUrl: "https://openrouter.ai/api/v1",
11288
11509
  reasoning: true,
11289
11510
  input: ["text", "image"],
11290
11511
  cost: {
11291
- input: 0.95,
11292
- output: 4,
11293
- cacheRead: 0.19,
11512
+ input: 2.5500000000000003,
11513
+ output: 12.75,
11514
+ cacheRead: 0.25599998999999996,
11294
11515
  cacheWrite: 0,
11295
11516
  },
11296
- contextWindow: 262144,
11297
- maxTokens: 235929,
11517
+ contextWindow: 1048576,
11518
+ maxTokens: 943718,
11298
11519
  },
11299
- "moonshotai/kimi-k3": {
11300
- id: "moonshotai/kimi-k3",
11301
- name: "MoonshotAI: Kimi K3",
11520
+ "moonshotai/kimi-k3:batch": {
11521
+ id: "moonshotai/kimi-k3:batch",
11522
+ name: "MoonshotAI: Kimi K3 (batch)",
11302
11523
  api: "openai-completions",
11303
11524
  provider: "openrouter",
11304
11525
  baseUrl: "https://openrouter.ai/api/v1",
@@ -11424,13 +11645,13 @@ export const MODELS = {
11424
11645
  reasoning: true,
11425
11646
  input: ["text"],
11426
11647
  cost: {
11427
- input: 0.6,
11428
- output: 3.5999999999999996,
11429
- cacheRead: 0.19999999999999998,
11648
+ input: 0.5,
11649
+ output: 2.2,
11650
+ cacheRead: 0.09999999999999999,
11430
11651
  cacheWrite: 0,
11431
11652
  },
11432
- contextWindow: 512288,
11433
- maxTokens: 461059,
11653
+ contextWindow: 262144,
11654
+ maxTokens: 16384,
11434
11655
  },
11435
11656
  "nvidia/nemotron-3-ultra-550b-a55b:batch": {
11436
11657
  id: "nvidia/nemotron-3-ultra-550b-a55b:batch",
@@ -11551,34 +11772,17 @@ export const MODELS = {
11551
11772
  contextWindow: 16385,
11552
11773
  maxTokens: 4096,
11553
11774
  },
11554
- "openai/gpt-3.5-turbo:batch": {
11555
- id: "openai/gpt-3.5-turbo:batch",
11556
- name: "OpenAI: GPT-3.5 Turbo (batch)",
11775
+ "openai/gpt-4": {
11776
+ id: "openai/gpt-4",
11777
+ name: "OpenAI: GPT-4",
11557
11778
  api: "openai-completions",
11558
11779
  provider: "openrouter",
11559
11780
  baseUrl: "https://openrouter.ai/api/v1",
11560
11781
  reasoning: false,
11561
11782
  input: ["text"],
11562
11783
  cost: {
11563
- input: 0.25,
11564
- output: 0.75,
11565
- cacheRead: 0,
11566
- cacheWrite: 0,
11567
- },
11568
- contextWindow: 16385,
11569
- maxTokens: 4096,
11570
- },
11571
- "openai/gpt-4": {
11572
- id: "openai/gpt-4",
11573
- name: "OpenAI: GPT-4",
11574
- api: "openai-completions",
11575
- provider: "openrouter",
11576
- baseUrl: "https://openrouter.ai/api/v1",
11577
- reasoning: false,
11578
- input: ["text"],
11579
- cost: {
11580
- input: 30,
11581
- output: 60,
11784
+ input: 30,
11785
+ output: 60,
11582
11786
  cacheRead: 0,
11583
11787
  cacheWrite: 0,
11584
11788
  },
@@ -11619,23 +11823,6 @@ export const MODELS = {
11619
11823
  contextWindow: 128000,
11620
11824
  maxTokens: 4096,
11621
11825
  },
11622
- "openai/gpt-4-turbo:batch": {
11623
- id: "openai/gpt-4-turbo:batch",
11624
- name: "OpenAI: GPT-4 Turbo (batch)",
11625
- api: "openai-completions",
11626
- provider: "openrouter",
11627
- baseUrl: "https://openrouter.ai/api/v1",
11628
- reasoning: false,
11629
- input: ["text", "image"],
11630
- cost: {
11631
- input: 5,
11632
- output: 15,
11633
- cacheRead: 0,
11634
- cacheWrite: 0,
11635
- },
11636
- contextWindow: 128000,
11637
- maxTokens: 4096,
11638
- },
11639
11826
  "openai/gpt-4.1": {
11640
11827
  id: "openai/gpt-4.1",
11641
11828
  name: "OpenAI: GPT-4.1",
@@ -11670,23 +11857,6 @@ export const MODELS = {
11670
11857
  contextWindow: 1047576,
11671
11858
  maxTokens: 32768,
11672
11859
  },
11673
- "openai/gpt-4.1-mini:batch": {
11674
- id: "openai/gpt-4.1-mini:batch",
11675
- name: "OpenAI: GPT-4.1 Mini (batch)",
11676
- api: "openai-completions",
11677
- provider: "openrouter",
11678
- baseUrl: "https://openrouter.ai/api/v1",
11679
- reasoning: false,
11680
- input: ["text", "image"],
11681
- cost: {
11682
- input: 0.19999999999999998,
11683
- output: 0.7999999999999999,
11684
- cacheRead: 0.049999999999999996,
11685
- cacheWrite: 0,
11686
- },
11687
- contextWindow: 1047576,
11688
- maxTokens: 32768,
11689
- },
11690
11860
  "openai/gpt-4.1-nano": {
11691
11861
  id: "openai/gpt-4.1-nano",
11692
11862
  name: "OpenAI: GPT-4.1 Nano",
@@ -11698,45 +11868,11 @@ export const MODELS = {
11698
11868
  cost: {
11699
11869
  input: 0.09999999999999999,
11700
11870
  output: 0.39999999999999997,
11701
- cacheRead: 0.024999999999999998,
11702
- cacheWrite: 0,
11703
- },
11704
- contextWindow: 1047576,
11705
- maxTokens: 32768,
11706
- },
11707
- "openai/gpt-4.1-nano:batch": {
11708
- id: "openai/gpt-4.1-nano:batch",
11709
- name: "OpenAI: GPT-4.1 Nano (batch)",
11710
- api: "openai-completions",
11711
- provider: "openrouter",
11712
- baseUrl: "https://openrouter.ai/api/v1",
11713
- reasoning: false,
11714
- input: ["text", "image"],
11715
- cost: {
11716
- input: 0.049999999999999996,
11717
- output: 0.19999999999999998,
11718
- cacheRead: 0.012499999999999999,
11719
- cacheWrite: 0,
11720
- },
11721
- contextWindow: 1047576,
11722
- maxTokens: 32768,
11723
- },
11724
- "openai/gpt-4.1:batch": {
11725
- id: "openai/gpt-4.1:batch",
11726
- name: "OpenAI: GPT-4.1 (batch)",
11727
- api: "openai-completions",
11728
- provider: "openrouter",
11729
- baseUrl: "https://openrouter.ai/api/v1",
11730
- reasoning: false,
11731
- input: ["text", "image"],
11732
- cost: {
11733
- input: 1,
11734
- output: 4,
11735
- cacheRead: 0.25,
11871
+ cacheRead: 0.03,
11736
11872
  cacheWrite: 0,
11737
11873
  },
11738
11874
  contextWindow: 1047576,
11739
- maxTokens: 32768,
11875
+ maxTokens: 942818,
11740
11876
  },
11741
11877
  "openai/gpt-4o": {
11742
11878
  id: "openai/gpt-4o",
@@ -11840,40 +11976,6 @@ export const MODELS = {
11840
11976
  contextWindow: 128000,
11841
11977
  maxTokens: 16384,
11842
11978
  },
11843
- "openai/gpt-4o-mini:batch": {
11844
- id: "openai/gpt-4o-mini:batch",
11845
- name: "OpenAI: GPT-4o-mini (batch)",
11846
- api: "openai-completions",
11847
- provider: "openrouter",
11848
- baseUrl: "https://openrouter.ai/api/v1",
11849
- reasoning: false,
11850
- input: ["text", "image"],
11851
- cost: {
11852
- input: 0.075,
11853
- output: 0.3,
11854
- cacheRead: 0.0375,
11855
- cacheWrite: 0,
11856
- },
11857
- contextWindow: 128000,
11858
- maxTokens: 16384,
11859
- },
11860
- "openai/gpt-4o:batch": {
11861
- id: "openai/gpt-4o:batch",
11862
- name: "OpenAI: GPT-4o (batch)",
11863
- api: "openai-completions",
11864
- provider: "openrouter",
11865
- baseUrl: "https://openrouter.ai/api/v1",
11866
- reasoning: false,
11867
- input: ["text", "image"],
11868
- cost: {
11869
- input: 1.25,
11870
- output: 5,
11871
- cacheRead: 0.625,
11872
- cacheWrite: 0,
11873
- },
11874
- contextWindow: 128000,
11875
- maxTokens: 16384,
11876
- },
11877
11979
  "openai/gpt-5": {
11878
11980
  id: "openai/gpt-5",
11879
11981
  name: "OpenAI: GPT-5",
@@ -11891,23 +11993,6 @@ export const MODELS = {
11891
11993
  contextWindow: 400000,
11892
11994
  maxTokens: 128000,
11893
11995
  },
11894
- "openai/gpt-5-codex:batch": {
11895
- id: "openai/gpt-5-codex:batch",
11896
- name: "OpenAI: GPT-5 Codex (batch)",
11897
- api: "openai-completions",
11898
- provider: "openrouter",
11899
- baseUrl: "https://openrouter.ai/api/v1",
11900
- reasoning: true,
11901
- input: ["text", "image"],
11902
- cost: {
11903
- input: 0.625,
11904
- output: 5,
11905
- cacheRead: 0.0625,
11906
- cacheWrite: 0,
11907
- },
11908
- contextWindow: 400000,
11909
- maxTokens: 128000,
11910
- },
11911
11996
  "openai/gpt-5-mini": {
11912
11997
  id: "openai/gpt-5-mini",
11913
11998
  name: "OpenAI: GPT-5 Mini",
@@ -11925,23 +12010,6 @@ export const MODELS = {
11925
12010
  contextWindow: 400000,
11926
12011
  maxTokens: 128000,
11927
12012
  },
11928
- "openai/gpt-5-mini:batch": {
11929
- id: "openai/gpt-5-mini:batch",
11930
- name: "OpenAI: GPT-5 Mini (batch)",
11931
- api: "openai-completions",
11932
- provider: "openrouter",
11933
- baseUrl: "https://openrouter.ai/api/v1",
11934
- reasoning: true,
11935
- input: ["text", "image"],
11936
- cost: {
11937
- input: 0.125,
11938
- output: 1,
11939
- cacheRead: 0.012499999999999999,
11940
- cacheWrite: 0,
11941
- },
11942
- contextWindow: 400000,
11943
- maxTokens: 128000,
11944
- },
11945
12013
  "openai/gpt-5-nano": {
11946
12014
  id: "openai/gpt-5-nano",
11947
12015
  name: "OpenAI: GPT-5 Nano",
@@ -11959,23 +12027,6 @@ export const MODELS = {
11959
12027
  contextWindow: 400000,
11960
12028
  maxTokens: 128000,
11961
12029
  },
11962
- "openai/gpt-5-nano:batch": {
11963
- id: "openai/gpt-5-nano:batch",
11964
- name: "OpenAI: GPT-5 Nano (batch)",
11965
- api: "openai-completions",
11966
- provider: "openrouter",
11967
- baseUrl: "https://openrouter.ai/api/v1",
11968
- reasoning: true,
11969
- input: ["text", "image"],
11970
- cost: {
11971
- input: 0.024999999999999998,
11972
- output: 0.19999999999999998,
11973
- cacheRead: 0.0025,
11974
- cacheWrite: 0,
11975
- },
11976
- contextWindow: 400000,
11977
- maxTokens: 128000,
11978
- },
11979
12030
  "openai/gpt-5-pro": {
11980
12031
  id: "openai/gpt-5-pro",
11981
12032
  name: "OpenAI: GPT-5 Pro",
@@ -11993,23 +12044,6 @@ export const MODELS = {
11993
12044
  contextWindow: 400000,
11994
12045
  maxTokens: 128000,
11995
12046
  },
11996
- "openai/gpt-5-pro:batch": {
11997
- id: "openai/gpt-5-pro:batch",
11998
- name: "OpenAI: GPT-5 Pro (batch)",
11999
- api: "openai-completions",
12000
- provider: "openrouter",
12001
- baseUrl: "https://openrouter.ai/api/v1",
12002
- reasoning: true,
12003
- input: ["text", "image"],
12004
- cost: {
12005
- input: 7.5,
12006
- output: 60,
12007
- cacheRead: 0,
12008
- cacheWrite: 0,
12009
- },
12010
- contextWindow: 400000,
12011
- maxTokens: 128000,
12012
- },
12013
12047
  "openai/gpt-5.1": {
12014
12048
  id: "openai/gpt-5.1",
12015
12049
  name: "OpenAI: GPT-5.1",
@@ -12078,23 +12112,6 @@ export const MODELS = {
12078
12112
  contextWindow: 400000,
12079
12113
  maxTokens: 128000,
12080
12114
  },
12081
- "openai/gpt-5.1:batch": {
12082
- id: "openai/gpt-5.1:batch",
12083
- name: "OpenAI: GPT-5.1 (batch)",
12084
- api: "openai-completions",
12085
- provider: "openrouter",
12086
- baseUrl: "https://openrouter.ai/api/v1",
12087
- reasoning: true,
12088
- input: ["text", "image"],
12089
- cost: {
12090
- input: 0.625,
12091
- output: 5,
12092
- cacheRead: 0.0625,
12093
- cacheWrite: 0,
12094
- },
12095
- contextWindow: 400000,
12096
- maxTokens: 128000,
12097
- },
12098
12115
  "openai/gpt-5.2": {
12099
12116
  id: "openai/gpt-5.2",
12100
12117
  name: "OpenAI: GPT-5.2",
@@ -12163,40 +12180,6 @@ export const MODELS = {
12163
12180
  contextWindow: 400000,
12164
12181
  maxTokens: 128000,
12165
12182
  },
12166
- "openai/gpt-5.2-pro:batch": {
12167
- id: "openai/gpt-5.2-pro:batch",
12168
- name: "OpenAI: GPT-5.2 Pro (batch)",
12169
- api: "openai-completions",
12170
- provider: "openrouter",
12171
- baseUrl: "https://openrouter.ai/api/v1",
12172
- reasoning: true,
12173
- input: ["text", "image"],
12174
- cost: {
12175
- input: 10.5,
12176
- output: 84,
12177
- cacheRead: 0,
12178
- cacheWrite: 0,
12179
- },
12180
- contextWindow: 400000,
12181
- maxTokens: 128000,
12182
- },
12183
- "openai/gpt-5.2:batch": {
12184
- id: "openai/gpt-5.2:batch",
12185
- name: "OpenAI: GPT-5.2 (batch)",
12186
- api: "openai-completions",
12187
- provider: "openrouter",
12188
- baseUrl: "https://openrouter.ai/api/v1",
12189
- reasoning: true,
12190
- input: ["text", "image"],
12191
- cost: {
12192
- input: 0.875,
12193
- output: 7,
12194
- cacheRead: 0.0875,
12195
- cacheWrite: 0,
12196
- },
12197
- contextWindow: 400000,
12198
- maxTokens: 128000,
12199
- },
12200
12183
  "openai/gpt-5.3-codex": {
12201
12184
  id: "openai/gpt-5.3-codex",
12202
12185
  name: "OpenAI: GPT-5.3-Codex",
@@ -12248,23 +12231,6 @@ export const MODELS = {
12248
12231
  contextWindow: 400000,
12249
12232
  maxTokens: 128000,
12250
12233
  },
12251
- "openai/gpt-5.4-mini:batch": {
12252
- id: "openai/gpt-5.4-mini:batch",
12253
- name: "OpenAI: GPT-5.4 Mini (batch)",
12254
- api: "openai-completions",
12255
- provider: "openrouter",
12256
- baseUrl: "https://openrouter.ai/api/v1",
12257
- reasoning: true,
12258
- input: ["text", "image"],
12259
- cost: {
12260
- input: 0.375,
12261
- output: 2.25,
12262
- cacheRead: 0.0375,
12263
- cacheWrite: 0,
12264
- },
12265
- contextWindow: 400000,
12266
- maxTokens: 128000,
12267
- },
12268
12234
  "openai/gpt-5.4-nano": {
12269
12235
  id: "openai/gpt-5.4-nano",
12270
12236
  name: "OpenAI: GPT-5.4 Nano",
@@ -12282,23 +12248,6 @@ export const MODELS = {
12282
12248
  contextWindow: 400000,
12283
12249
  maxTokens: 128000,
12284
12250
  },
12285
- "openai/gpt-5.4-nano:batch": {
12286
- id: "openai/gpt-5.4-nano:batch",
12287
- name: "OpenAI: GPT-5.4 Nano (batch)",
12288
- api: "openai-completions",
12289
- provider: "openrouter",
12290
- baseUrl: "https://openrouter.ai/api/v1",
12291
- reasoning: true,
12292
- input: ["text", "image"],
12293
- cost: {
12294
- input: 0.09999999999999999,
12295
- output: 0.625,
12296
- cacheRead: 0.01,
12297
- cacheWrite: 0,
12298
- },
12299
- contextWindow: 400000,
12300
- maxTokens: 128000,
12301
- },
12302
12251
  "openai/gpt-5.4-pro": {
12303
12252
  id: "openai/gpt-5.4-pro",
12304
12253
  name: "OpenAI: GPT-5.4 Pro",
@@ -12316,40 +12265,6 @@ export const MODELS = {
12316
12265
  contextWindow: 1050000,
12317
12266
  maxTokens: 128000,
12318
12267
  },
12319
- "openai/gpt-5.4-pro:batch": {
12320
- id: "openai/gpt-5.4-pro:batch",
12321
- name: "OpenAI: GPT-5.4 Pro (batch)",
12322
- api: "openai-completions",
12323
- provider: "openrouter",
12324
- baseUrl: "https://openrouter.ai/api/v1",
12325
- reasoning: true,
12326
- input: ["text", "image"],
12327
- cost: {
12328
- input: 15,
12329
- output: 90,
12330
- cacheRead: 0,
12331
- cacheWrite: 0,
12332
- },
12333
- contextWindow: 1050000,
12334
- maxTokens: 128000,
12335
- },
12336
- "openai/gpt-5.4:batch": {
12337
- id: "openai/gpt-5.4:batch",
12338
- name: "OpenAI: GPT-5.4 (batch)",
12339
- api: "openai-completions",
12340
- provider: "openrouter",
12341
- baseUrl: "https://openrouter.ai/api/v1",
12342
- reasoning: true,
12343
- input: ["text", "image"],
12344
- cost: {
12345
- input: 1.25,
12346
- output: 7.5,
12347
- cacheRead: 0.125,
12348
- cacheWrite: 0,
12349
- },
12350
- contextWindow: 1050000,
12351
- maxTokens: 128000,
12352
- },
12353
12268
  "openai/gpt-5.5": {
12354
12269
  id: "openai/gpt-5.5",
12355
12270
  name: "OpenAI: GPT-5.5",
@@ -12384,40 +12299,6 @@ export const MODELS = {
12384
12299
  contextWindow: 1050000,
12385
12300
  maxTokens: 128000,
12386
12301
  },
12387
- "openai/gpt-5.5-pro:batch": {
12388
- id: "openai/gpt-5.5-pro:batch",
12389
- name: "OpenAI: GPT-5.5 Pro (batch)",
12390
- api: "openai-completions",
12391
- provider: "openrouter",
12392
- baseUrl: "https://openrouter.ai/api/v1",
12393
- reasoning: true,
12394
- input: ["text", "image"],
12395
- cost: {
12396
- input: 15,
12397
- output: 90,
12398
- cacheRead: 0,
12399
- cacheWrite: 0,
12400
- },
12401
- contextWindow: 1050000,
12402
- maxTokens: 128000,
12403
- },
12404
- "openai/gpt-5.5:batch": {
12405
- id: "openai/gpt-5.5:batch",
12406
- name: "OpenAI: GPT-5.5 (batch)",
12407
- api: "openai-completions",
12408
- provider: "openrouter",
12409
- baseUrl: "https://openrouter.ai/api/v1",
12410
- reasoning: true,
12411
- input: ["text", "image"],
12412
- cost: {
12413
- input: 2.5,
12414
- output: 15,
12415
- cacheRead: 0.25,
12416
- cacheWrite: 0,
12417
- },
12418
- contextWindow: 1050000,
12419
- maxTokens: 128000,
12420
- },
12421
12302
  "openai/gpt-5.6-luna": {
12422
12303
  id: "openai/gpt-5.6-luna",
12423
12304
  name: "OpenAI: GPT-5.6 Luna",
@@ -12452,40 +12333,6 @@ export const MODELS = {
12452
12333
  contextWindow: 1050000,
12453
12334
  maxTokens: 128000,
12454
12335
  },
12455
- "openai/gpt-5.6-luna-pro:batch": {
12456
- id: "openai/gpt-5.6-luna-pro:batch",
12457
- name: "OpenAI: GPT-5.6 Luna Pro (batch)",
12458
- api: "openai-completions",
12459
- provider: "openrouter",
12460
- baseUrl: "https://openrouter.ai/api/v1",
12461
- reasoning: true,
12462
- input: ["text", "image"],
12463
- cost: {
12464
- input: 0.09999999999999999,
12465
- output: 0.6,
12466
- cacheRead: 0.01,
12467
- cacheWrite: 0,
12468
- },
12469
- contextWindow: 1050000,
12470
- maxTokens: 128000,
12471
- },
12472
- "openai/gpt-5.6-luna:batch": {
12473
- id: "openai/gpt-5.6-luna:batch",
12474
- name: "OpenAI: GPT-5.6 Luna (batch)",
12475
- api: "openai-completions",
12476
- provider: "openrouter",
12477
- baseUrl: "https://openrouter.ai/api/v1",
12478
- reasoning: true,
12479
- input: ["text", "image"],
12480
- cost: {
12481
- input: 0.09999999999999999,
12482
- output: 0.6,
12483
- cacheRead: 0.01,
12484
- cacheWrite: 0,
12485
- },
12486
- contextWindow: 1050000,
12487
- maxTokens: 128000,
12488
- },
12489
12336
  "openai/gpt-5.6-sol": {
12490
12337
  id: "openai/gpt-5.6-sol",
12491
12338
  name: "OpenAI: GPT-5.6 Sol",
@@ -12520,40 +12367,6 @@ export const MODELS = {
12520
12367
  contextWindow: 1050000,
12521
12368
  maxTokens: 128000,
12522
12369
  },
12523
- "openai/gpt-5.6-sol-pro:batch": {
12524
- id: "openai/gpt-5.6-sol-pro:batch",
12525
- name: "OpenAI: GPT-5.6 Sol Pro (batch)",
12526
- api: "openai-completions",
12527
- provider: "openrouter",
12528
- baseUrl: "https://openrouter.ai/api/v1",
12529
- reasoning: true,
12530
- input: ["text", "image"],
12531
- cost: {
12532
- input: 1,
12533
- output: 5,
12534
- cacheRead: 0.09999999999999999,
12535
- cacheWrite: 1.25,
12536
- },
12537
- contextWindow: 1050000,
12538
- maxTokens: 128000,
12539
- },
12540
- "openai/gpt-5.6-sol:batch": {
12541
- id: "openai/gpt-5.6-sol:batch",
12542
- name: "OpenAI: GPT-5.6 Sol (batch)",
12543
- api: "openai-completions",
12544
- provider: "openrouter",
12545
- baseUrl: "https://openrouter.ai/api/v1",
12546
- reasoning: true,
12547
- input: ["text", "image"],
12548
- cost: {
12549
- input: 1,
12550
- output: 5,
12551
- cacheRead: 0.09999999999999999,
12552
- cacheWrite: 1.25,
12553
- },
12554
- contextWindow: 1050000,
12555
- maxTokens: 128000,
12556
- },
12557
12370
  "openai/gpt-5.6-terra": {
12558
12371
  id: "openai/gpt-5.6-terra",
12559
12372
  name: "OpenAI: GPT-5.6 Terra",
@@ -12562,81 +12375,30 @@ export const MODELS = {
12562
12375
  baseUrl: "https://openrouter.ai/api/v1",
12563
12376
  reasoning: true,
12564
12377
  input: ["text", "image"],
12565
- cost: {
12566
- input: 2,
12567
- output: 12,
12568
- cacheRead: 0.19999999999999998,
12569
- cacheWrite: 2.5,
12570
- },
12571
- contextWindow: 1050000,
12572
- maxTokens: 128000,
12573
- },
12574
- "openai/gpt-5.6-terra-pro": {
12575
- id: "openai/gpt-5.6-terra-pro",
12576
- name: "OpenAI: GPT-5.6 Terra Pro",
12577
- api: "openai-completions",
12578
- provider: "openrouter",
12579
- baseUrl: "https://openrouter.ai/api/v1",
12580
- reasoning: true,
12581
- input: ["text", "image"],
12582
- cost: {
12583
- input: 2,
12584
- output: 12,
12585
- cacheRead: 0.19999999999999998,
12586
- cacheWrite: 2.5,
12587
- },
12588
- contextWindow: 1050000,
12589
- maxTokens: 128000,
12590
- },
12591
- "openai/gpt-5.6-terra-pro:batch": {
12592
- id: "openai/gpt-5.6-terra-pro:batch",
12593
- name: "OpenAI: GPT-5.6 Terra Pro (batch)",
12594
- api: "openai-completions",
12595
- provider: "openrouter",
12596
- baseUrl: "https://openrouter.ai/api/v1",
12597
- reasoning: true,
12598
- input: ["text", "image"],
12599
- cost: {
12600
- input: 1,
12601
- output: 6,
12602
- cacheRead: 0.09999999999999999,
12603
- cacheWrite: 0,
12604
- },
12605
- contextWindow: 1050000,
12606
- maxTokens: 128000,
12607
- },
12608
- "openai/gpt-5.6-terra:batch": {
12609
- id: "openai/gpt-5.6-terra:batch",
12610
- name: "OpenAI: GPT-5.6 Terra (batch)",
12611
- api: "openai-completions",
12612
- provider: "openrouter",
12613
- baseUrl: "https://openrouter.ai/api/v1",
12614
- reasoning: true,
12615
- input: ["text", "image"],
12616
- cost: {
12617
- input: 1,
12618
- output: 6,
12619
- cacheRead: 0.09999999999999999,
12620
- cacheWrite: 0,
12378
+ cost: {
12379
+ input: 2,
12380
+ output: 12,
12381
+ cacheRead: 0.19999999999999998,
12382
+ cacheWrite: 2.5,
12621
12383
  },
12622
12384
  contextWindow: 1050000,
12623
12385
  maxTokens: 128000,
12624
12386
  },
12625
- "openai/gpt-5:batch": {
12626
- id: "openai/gpt-5:batch",
12627
- name: "OpenAI: GPT-5 (batch)",
12387
+ "openai/gpt-5.6-terra-pro": {
12388
+ id: "openai/gpt-5.6-terra-pro",
12389
+ name: "OpenAI: GPT-5.6 Terra Pro",
12628
12390
  api: "openai-completions",
12629
12391
  provider: "openrouter",
12630
12392
  baseUrl: "https://openrouter.ai/api/v1",
12631
12393
  reasoning: true,
12632
12394
  input: ["text", "image"],
12633
12395
  cost: {
12634
- input: 0.625,
12635
- output: 5,
12636
- cacheRead: 0.0625,
12637
- cacheWrite: 0,
12396
+ input: 2,
12397
+ output: 12,
12398
+ cacheRead: 0.19999999999999998,
12399
+ cacheWrite: 2.5,
12638
12400
  },
12639
- contextWindow: 400000,
12401
+ contextWindow: 1050000,
12640
12402
  maxTokens: 128000,
12641
12403
  },
12642
12404
  "openai/gpt-audio": {
@@ -12707,6 +12469,23 @@ export const MODELS = {
12707
12469
  contextWindow: 131072,
12708
12470
  maxTokens: 117964,
12709
12471
  },
12472
+ "openai/gpt-oss-120b:batch": {
12473
+ id: "openai/gpt-oss-120b:batch",
12474
+ name: "OpenAI: gpt-oss-120b (batch)",
12475
+ api: "openai-completions",
12476
+ provider: "openrouter",
12477
+ baseUrl: "https://openrouter.ai/api/v1",
12478
+ reasoning: true,
12479
+ input: ["text"],
12480
+ cost: {
12481
+ input: 0.15,
12482
+ output: 0.6,
12483
+ cacheRead: 0,
12484
+ cacheWrite: 0,
12485
+ },
12486
+ contextWindow: 131072,
12487
+ maxTokens: 117964,
12488
+ },
12710
12489
  "openai/gpt-oss-20b": {
12711
12490
  id: "openai/gpt-oss-20b",
12712
12491
  name: "OpenAI: gpt-oss-20b",
@@ -12758,23 +12537,6 @@ export const MODELS = {
12758
12537
  contextWindow: 200000,
12759
12538
  maxTokens: 100000,
12760
12539
  },
12761
- "openai/o1:batch": {
12762
- id: "openai/o1:batch",
12763
- name: "OpenAI: o1 (batch)",
12764
- api: "openai-completions",
12765
- provider: "openrouter",
12766
- baseUrl: "https://openrouter.ai/api/v1",
12767
- reasoning: true,
12768
- input: ["text", "image"],
12769
- cost: {
12770
- input: 7.5,
12771
- output: 30,
12772
- cacheRead: 3.75,
12773
- cacheWrite: 0,
12774
- },
12775
- contextWindow: 200000,
12776
- maxTokens: 100000,
12777
- },
12778
12540
  "openai/o3": {
12779
12541
  id: "openai/o3",
12780
12542
  name: "OpenAI: o3",
@@ -12826,40 +12588,6 @@ export const MODELS = {
12826
12588
  contextWindow: 200000,
12827
12589
  maxTokens: 100000,
12828
12590
  },
12829
- "openai/o3-mini-high:batch": {
12830
- id: "openai/o3-mini-high:batch",
12831
- name: "OpenAI: o3 Mini High (batch)",
12832
- api: "openai-completions",
12833
- provider: "openrouter",
12834
- baseUrl: "https://openrouter.ai/api/v1",
12835
- reasoning: true,
12836
- input: ["text"],
12837
- cost: {
12838
- input: 0.55,
12839
- output: 2.2,
12840
- cacheRead: 0.275,
12841
- cacheWrite: 0,
12842
- },
12843
- contextWindow: 200000,
12844
- maxTokens: 100000,
12845
- },
12846
- "openai/o3-mini:batch": {
12847
- id: "openai/o3-mini:batch",
12848
- name: "OpenAI: o3 Mini (batch)",
12849
- api: "openai-completions",
12850
- provider: "openrouter",
12851
- baseUrl: "https://openrouter.ai/api/v1",
12852
- reasoning: true,
12853
- input: ["text"],
12854
- cost: {
12855
- input: 0.55,
12856
- output: 2.2,
12857
- cacheRead: 0.275,
12858
- cacheWrite: 0,
12859
- },
12860
- contextWindow: 200000,
12861
- maxTokens: 100000,
12862
- },
12863
12591
  "openai/o3-pro": {
12864
12592
  id: "openai/o3-pro",
12865
12593
  name: "OpenAI: o3 Pro",
@@ -12877,40 +12605,6 @@ export const MODELS = {
12877
12605
  contextWindow: 200000,
12878
12606
  maxTokens: 100000,
12879
12607
  },
12880
- "openai/o3-pro:batch": {
12881
- id: "openai/o3-pro:batch",
12882
- name: "OpenAI: o3 Pro (batch)",
12883
- api: "openai-completions",
12884
- provider: "openrouter",
12885
- baseUrl: "https://openrouter.ai/api/v1",
12886
- reasoning: true,
12887
- input: ["text", "image"],
12888
- cost: {
12889
- input: 10,
12890
- output: 40,
12891
- cacheRead: 0,
12892
- cacheWrite: 0,
12893
- },
12894
- contextWindow: 200000,
12895
- maxTokens: 100000,
12896
- },
12897
- "openai/o3:batch": {
12898
- id: "openai/o3:batch",
12899
- name: "OpenAI: o3 (batch)",
12900
- api: "openai-completions",
12901
- provider: "openrouter",
12902
- baseUrl: "https://openrouter.ai/api/v1",
12903
- reasoning: true,
12904
- input: ["text", "image"],
12905
- cost: {
12906
- input: 1,
12907
- output: 4,
12908
- cacheRead: 0.25,
12909
- cacheWrite: 0,
12910
- },
12911
- contextWindow: 200000,
12912
- maxTokens: 100000,
12913
- },
12914
12608
  "openai/o4-mini": {
12915
12609
  id: "openai/o4-mini",
12916
12610
  name: "OpenAI: o4 Mini",
@@ -12945,40 +12639,6 @@ export const MODELS = {
12945
12639
  contextWindow: 200000,
12946
12640
  maxTokens: 100000,
12947
12641
  },
12948
- "openai/o4-mini-high:batch": {
12949
- id: "openai/o4-mini-high:batch",
12950
- name: "OpenAI: o4 Mini High (batch)",
12951
- api: "openai-completions",
12952
- provider: "openrouter",
12953
- baseUrl: "https://openrouter.ai/api/v1",
12954
- reasoning: true,
12955
- input: ["text", "image"],
12956
- cost: {
12957
- input: 0.55,
12958
- output: 2.2,
12959
- cacheRead: 0.1375,
12960
- cacheWrite: 0,
12961
- },
12962
- contextWindow: 200000,
12963
- maxTokens: 100000,
12964
- },
12965
- "openai/o4-mini:batch": {
12966
- id: "openai/o4-mini:batch",
12967
- name: "OpenAI: o4 Mini (batch)",
12968
- api: "openai-completions",
12969
- provider: "openrouter",
12970
- baseUrl: "https://openrouter.ai/api/v1",
12971
- reasoning: true,
12972
- input: ["text", "image"],
12973
- cost: {
12974
- input: 0.55,
12975
- output: 2.2,
12976
- cacheRead: 0.1375,
12977
- cacheWrite: 0,
12978
- },
12979
- contextWindow: 200000,
12980
- maxTokens: 100000,
12981
- },
12982
12642
  "openrouter/auto": {
12983
12643
  id: "openrouter/auto",
12984
12644
  name: "Auto Router",
@@ -13515,13 +13175,13 @@ export const MODELS = {
13515
13175
  reasoning: false,
13516
13176
  input: ["text", "image"],
13517
13177
  cost: {
13518
- input: 0.13,
13519
- output: 0.52,
13178
+ input: 0.15,
13179
+ output: 0.6,
13520
13180
  cacheRead: 0,
13521
13181
  cacheWrite: 0,
13522
13182
  },
13523
13183
  contextWindow: 262144,
13524
- maxTokens: 32768,
13184
+ maxTokens: 16384,
13525
13185
  },
13526
13186
  "qwen/qwen3-vl-30b-a3b-thinking": {
13527
13187
  id: "qwen/qwen3-vl-30b-a3b-thinking",
@@ -13600,13 +13260,13 @@ export const MODELS = {
13600
13260
  reasoning: true,
13601
13261
  input: ["text", "image"],
13602
13262
  cost: {
13603
- input: 0.26,
13604
- output: 2.08,
13263
+ input: 0.29,
13264
+ output: 2.4,
13605
13265
  cacheRead: 0,
13606
13266
  cacheWrite: 0,
13607
13267
  },
13608
13268
  contextWindow: 262144,
13609
- maxTokens: 235929,
13269
+ maxTokens: 81920,
13610
13270
  },
13611
13271
  "qwen/qwen3.5-27b": {
13612
13272
  id: "qwen/qwen3.5-27b",
@@ -13676,6 +13336,23 @@ export const MODELS = {
13676
13336
  contextWindow: 262144,
13677
13337
  maxTokens: 235929,
13678
13338
  },
13339
+ "qwen/qwen3.5-9b:batch": {
13340
+ id: "qwen/qwen3.5-9b:batch",
13341
+ name: "Qwen: Qwen3.5-9B (batch)",
13342
+ api: "openai-completions",
13343
+ provider: "openrouter",
13344
+ baseUrl: "https://openrouter.ai/api/v1",
13345
+ reasoning: true,
13346
+ input: ["text", "image"],
13347
+ cost: {
13348
+ input: 0.16999999999999998,
13349
+ output: 0.25,
13350
+ cacheRead: 0,
13351
+ cacheWrite: 0,
13352
+ },
13353
+ contextWindow: 262144,
13354
+ maxTokens: 235929,
13355
+ },
13679
13356
  "qwen/qwen3.5-flash-02-23": {
13680
13357
  id: "qwen/qwen3.5-flash-02-23",
13681
13358
  name: "Qwen: Qwen3.5-Flash",
@@ -13874,12 +13551,29 @@ export const MODELS = {
13874
13551
  cost: {
13875
13552
  input: 2,
13876
13553
  output: 6,
13877
- cacheRead: 0.25,
13554
+ cacheRead: 0.19999999999999998,
13878
13555
  cacheWrite: 0,
13879
13556
  },
13880
13557
  contextWindow: 1048576,
13881
13558
  maxTokens: 131072,
13882
13559
  },
13560
+ "qwen/qwen3.8-2.4t-a95b:batch": {
13561
+ id: "qwen/qwen3.8-2.4t-a95b:batch",
13562
+ name: "Qwen: Qwen3.8 2.4T A95B (batch)",
13563
+ api: "openai-completions",
13564
+ provider: "openrouter",
13565
+ baseUrl: "https://openrouter.ai/api/v1",
13566
+ reasoning: true,
13567
+ input: ["text"],
13568
+ cost: {
13569
+ input: 2,
13570
+ output: 6,
13571
+ cacheRead: 0.25,
13572
+ cacheWrite: 0,
13573
+ },
13574
+ contextWindow: 1010000,
13575
+ maxTokens: 909000,
13576
+ },
13883
13577
  "qwen/qwen3.8-27b": {
13884
13578
  id: "qwen/qwen3.8-27b",
13885
13579
  name: "Qwen: Qwen3.8 27B",
@@ -14084,6 +13778,23 @@ export const MODELS = {
14084
13778
  contextWindow: 262144,
14085
13779
  maxTokens: 235929,
14086
13780
  },
13781
+ "tencent/hy4-preview": {
13782
+ id: "tencent/hy4-preview",
13783
+ name: "Tencent: Hy4 preview",
13784
+ api: "openai-completions",
13785
+ provider: "openrouter",
13786
+ baseUrl: "https://openrouter.ai/api/v1",
13787
+ reasoning: true,
13788
+ input: ["text"],
13789
+ cost: {
13790
+ input: 0.834,
13791
+ output: 2.501,
13792
+ cacheRead: 0.041999999999999996,
13793
+ cacheWrite: 0,
13794
+ },
13795
+ contextWindow: 1048576,
13796
+ maxTokens: 64000,
13797
+ },
14087
13798
  "thedrummer/unslopnemo-12b": {
14088
13799
  id: "thedrummer/unslopnemo-12b",
14089
13800
  name: "TheDrummer: UnslopNemo 12B",
@@ -14135,6 +13846,23 @@ export const MODELS = {
14135
13846
  contextWindow: 1048576,
14136
13847
  maxTokens: 262144,
14137
13848
  },
13849
+ "thinkingmachines/inkling-small:batch": {
13850
+ id: "thinkingmachines/inkling-small:batch",
13851
+ name: "Thinking Machines: Inkling Small (batch)",
13852
+ api: "openai-completions",
13853
+ provider: "openrouter",
13854
+ baseUrl: "https://openrouter.ai/api/v1",
13855
+ reasoning: true,
13856
+ input: ["text", "image"],
13857
+ cost: {
13858
+ input: 0.5,
13859
+ output: 1.2,
13860
+ cacheRead: 0.09999999999999999,
13861
+ cacheWrite: 0,
13862
+ },
13863
+ contextWindow: 524288,
13864
+ maxTokens: 471859,
13865
+ },
14138
13866
  "thinkingmachines/inkling-small:free": {
14139
13867
  id: "thinkingmachines/inkling-small:free",
14140
13868
  name: "Thinking Machines: Inkling Small (free)",
@@ -14557,7 +14285,7 @@ export const MODELS = {
14557
14285
  cacheRead: 0.26,
14558
14286
  cacheWrite: 0,
14559
14287
  },
14560
- contextWindow: 1048576,
14288
+ contextWindow: 1310720,
14561
14289
  maxTokens: 131072,
14562
14290
  },
14563
14291
  "z-ai/glm-5.3-flash": {
@@ -14577,6 +14305,23 @@ export const MODELS = {
14577
14305
  contextWindow: 1310720,
14578
14306
  maxTokens: 131072,
14579
14307
  },
14308
+ "z-ai/glm-5.3-flash:batch": {
14309
+ id: "z-ai/glm-5.3-flash:batch",
14310
+ name: "Z.ai: GLM 5.3 Flash (batch)",
14311
+ api: "openai-completions",
14312
+ provider: "openrouter",
14313
+ baseUrl: "https://openrouter.ai/api/v1",
14314
+ reasoning: true,
14315
+ input: ["text", "image"],
14316
+ cost: {
14317
+ input: 0.15,
14318
+ output: 0.5,
14319
+ cacheRead: 0.03,
14320
+ cacheWrite: 0,
14321
+ },
14322
+ contextWindow: 1048575,
14323
+ maxTokens: 943717,
14324
+ },
14580
14325
  "z-ai/glm-5v-turbo": {
14581
14326
  id: "z-ai/glm-5v-turbo",
14582
14327
  name: "Z.ai: GLM 5V Turbo",
@@ -14688,10 +14433,10 @@ export const MODELS = {
14688
14433
  reasoning: true,
14689
14434
  input: ["text", "image"],
14690
14435
  cost: {
14691
- input: 0.375,
14692
- output: 1.875,
14693
- cacheRead: 0.0375,
14694
- cacheWrite: 0.0208333333333333,
14436
+ input: 0.75,
14437
+ output: 3.75,
14438
+ cacheRead: 0.075,
14439
+ cacheWrite: 0.0416666666666667,
14695
14440
  },
14696
14441
  contextWindow: 1048576,
14697
14442
  maxTokens: 65536,
@@ -14790,12 +14535,12 @@ export const MODELS = {
14790
14535
  reasoning: true,
14791
14536
  input: ["text"],
14792
14537
  cost: {
14793
- input: 1.4,
14538
+ input: 1.25,
14794
14539
  output: 4.4,
14795
14540
  cacheRead: 0.26,
14796
14541
  cacheWrite: 0,
14797
14542
  },
14798
- contextWindow: 1048576,
14543
+ contextWindow: 1310720,
14799
14544
  maxTokens: 131072,
14800
14545
  },
14801
14546
  },
@@ -15236,11 +14981,11 @@ export const MODELS = {
15236
14981
  cost: {
15237
14982
  input: 2,
15238
14983
  output: 6,
15239
- cacheRead: 0.19999999999999998,
14984
+ cacheRead: 0.25,
15240
14985
  cacheWrite: 0,
15241
14986
  },
15242
14987
  contextWindow: 262144,
15243
- maxTokens: 131072,
14988
+ maxTokens: 128000,
15244
14989
  },
15245
14990
  "alibaba/qwen3.8-27b": {
15246
14991
  id: "alibaba/qwen3.8-27b",
@@ -15846,13 +15591,13 @@ export const MODELS = {
15846
15591
  reasoning: true,
15847
15592
  input: ["text"],
15848
15593
  cost: {
15849
- input: 1.74,
15850
- output: 3.48,
15851
- cacheRead: 0.14,
15594
+ input: 0.66,
15595
+ output: 1.9800000000000002,
15596
+ cacheRead: 0.022,
15852
15597
  cacheWrite: 0,
15853
15598
  },
15854
- contextWindow: 1048600,
15855
- maxTokens: 1048600,
15599
+ contextWindow: 1000000,
15600
+ maxTokens: 384000,
15856
15601
  },
15857
15602
  "deepseek/deepseek-v4-pro-0813": {
15858
15603
  id: "deepseek/deepseek-v4-pro-0813",
@@ -16485,7 +16230,7 @@ export const MODELS = {
16485
16230
  },
16486
16231
  "minimax/minimax-m2.7": {
16487
16232
  id: "minimax/minimax-m2.7",
16488
- name: "Minimax M2.7",
16233
+ name: "MiniMax M2.7",
16489
16234
  api: "anthropic-messages",
16490
16235
  provider: "vercel-ai-gateway",
16491
16236
  baseUrl: "https://ai-gateway.vercel.sh",
@@ -16502,7 +16247,7 @@ export const MODELS = {
16502
16247
  },
16503
16248
  "minimax/minimax-m2.7-free": {
16504
16249
  id: "minimax/minimax-m2.7-free",
16505
- name: "Minimax M2.7 (Free)",
16250
+ name: "MiniMax M2.7 (Free)",
16506
16251
  api: "anthropic-messages",
16507
16252
  provider: "vercel-ai-gateway",
16508
16253
  baseUrl: "https://ai-gateway.vercel.sh",
@@ -16548,8 +16293,8 @@ export const MODELS = {
16548
16293
  cacheRead: 0.06,
16549
16294
  cacheWrite: 0,
16550
16295
  },
16551
- contextWindow: 1000000,
16552
- maxTokens: 1000000,
16296
+ contextWindow: 512000,
16297
+ maxTokens: 512000,
16553
16298
  },
16554
16299
  "minimax/minimax-m3-free": {
16555
16300
  id: "minimax/minimax-m3-free",
@@ -16851,7 +16596,7 @@ export const MODELS = {
16851
16596
  cost: {
16852
16597
  input: 0.95,
16853
16598
  output: 4,
16854
- cacheRead: 0.19,
16599
+ cacheRead: 0.16,
16855
16600
  cacheWrite: 0,
16856
16601
  },
16857
16602
  contextWindow: 256000,
@@ -16969,8 +16714,8 @@ export const MODELS = {
16969
16714
  input: ["text"],
16970
16715
  cost: {
16971
16716
  input: 0.049999999999999996,
16972
- output: 0.15,
16973
- cacheRead: 0.049999999999999996,
16717
+ output: 0.19999999999999998,
16718
+ cacheRead: 0.01,
16974
16719
  cacheWrite: 0,
16975
16720
  },
16976
16721
  contextWindow: 262144,
@@ -18277,13 +18022,30 @@ export const MODELS = {
18277
18022
  reasoning: true,
18278
18023
  input: ["text"],
18279
18024
  cost: {
18280
- input: 0.13199999999999998,
18281
- output: 0.5279999999999999,
18282
- cacheRead: 0.032999999999999995,
18025
+ input: 0.14,
18026
+ output: 0.58,
18027
+ cacheRead: 0.035,
18283
18028
  cacheWrite: 0,
18284
18029
  },
18285
- contextWindow: 256000,
18286
- maxTokens: 128000,
18030
+ contextWindow: 262144,
18031
+ maxTokens: 262144,
18032
+ },
18033
+ "tencent/hy4-preview": {
18034
+ id: "tencent/hy4-preview",
18035
+ name: "Tencent Hy4 Preview",
18036
+ api: "anthropic-messages",
18037
+ provider: "vercel-ai-gateway",
18038
+ baseUrl: "https://ai-gateway.vercel.sh",
18039
+ reasoning: true,
18040
+ input: ["text"],
18041
+ cost: {
18042
+ input: 0.834,
18043
+ output: 2.501,
18044
+ cacheRead: 0.041999999999999996,
18045
+ cacheWrite: 0,
18046
+ },
18047
+ contextWindow: 1024000,
18048
+ maxTokens: 64000,
18287
18049
  },
18288
18050
  "thinkingmachines/inkling": {
18289
18051
  id: "thinkingmachines/inkling",
@@ -18568,11 +18330,11 @@ export const MODELS = {
18568
18330
  cost: {
18569
18331
  input: 1.4,
18570
18332
  output: 4.4,
18571
- cacheRead: 0.26,
18333
+ cacheRead: 0.14,
18572
18334
  cacheWrite: 0,
18573
18335
  },
18574
18336
  contextWindow: 1000000,
18575
- maxTokens: 12800,
18337
+ maxTokens: 1000000,
18576
18338
  },
18577
18339
  "zai/glm-5.3-flash": {
18578
18340
  id: "zai/glm-5.3-flash",