@elyracode/ai 0.9.21 → 0.9.22

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.
@@ -4979,6 +4979,42 @@ export const MODELS = {
4979
4979
  contextWindow: 1048576,
4980
4980
  maxTokens: 65536,
4981
4981
  },
4982
+ "gemini-3.5-flash-lite": {
4983
+ id: "gemini-3.5-flash-lite",
4984
+ name: "Gemini 3.5 Flash Lite",
4985
+ api: "google-generative-ai",
4986
+ provider: "google",
4987
+ baseUrl: "https://generativelanguage.googleapis.com/v1beta",
4988
+ reasoning: true,
4989
+ thinkingLevelMap: { "off": null },
4990
+ input: ["text", "image"],
4991
+ cost: {
4992
+ input: 0.3,
4993
+ output: 2.5,
4994
+ cacheRead: 0.03,
4995
+ cacheWrite: 0,
4996
+ },
4997
+ contextWindow: 1048576,
4998
+ maxTokens: 65536,
4999
+ },
5000
+ "gemini-3.6-flash": {
5001
+ id: "gemini-3.6-flash",
5002
+ name: "Gemini 3.6 Flash",
5003
+ api: "google-generative-ai",
5004
+ provider: "google",
5005
+ baseUrl: "https://generativelanguage.googleapis.com/v1beta",
5006
+ reasoning: true,
5007
+ thinkingLevelMap: { "off": null },
5008
+ input: ["text", "image"],
5009
+ cost: {
5010
+ input: 1.5,
5011
+ output: 7.5,
5012
+ cacheRead: 0.15,
5013
+ cacheWrite: 0,
5014
+ },
5015
+ contextWindow: 1048576,
5016
+ maxTokens: 65536,
5017
+ },
4982
5018
  "gemini-flash-latest": {
4983
5019
  id: "gemini-flash-latest",
4984
5020
  name: "Gemini Flash Latest",
@@ -5760,6 +5796,24 @@ export const MODELS = {
5760
5796
  contextWindow: 262144,
5761
5797
  maxTokens: 65536,
5762
5798
  },
5799
+ "XiaomiMiMo/MiMo-V2.5": {
5800
+ id: "XiaomiMiMo/MiMo-V2.5",
5801
+ name: "MiMo-V2.5",
5802
+ api: "openai-completions",
5803
+ provider: "huggingface",
5804
+ baseUrl: "https://router.huggingface.co/v1",
5805
+ compat: { "supportsDeveloperRole": false },
5806
+ reasoning: true,
5807
+ input: ["text"],
5808
+ cost: {
5809
+ input: 0.4,
5810
+ output: 2,
5811
+ cacheRead: 0,
5812
+ cacheWrite: 0,
5813
+ },
5814
+ contextWindow: 262144,
5815
+ maxTokens: 131072,
5816
+ },
5763
5817
  "XiaomiMiMo/MiMo-V2.5-Pro": {
5764
5818
  id: "XiaomiMiMo/MiMo-V2.5-Pro",
5765
5819
  name: "MiMo-V2.5-Pro",
@@ -6266,9 +6320,9 @@ export const MODELS = {
6266
6320
  },
6267
6321
  },
6268
6322
  "kimi-coding": {
6269
- "k2p7": {
6270
- id: "k2p7",
6271
- name: "Kimi K2.7 Code",
6323
+ "k3": {
6324
+ id: "k3",
6325
+ name: "Kimi K3",
6272
6326
  api: "anthropic-messages",
6273
6327
  provider: "kimi-coding",
6274
6328
  baseUrl: "https://api.kimi.com/coding",
@@ -6281,12 +6335,12 @@ export const MODELS = {
6281
6335
  cacheRead: 0,
6282
6336
  cacheWrite: 0,
6283
6337
  },
6284
- contextWindow: 262144,
6285
- maxTokens: 32768,
6338
+ contextWindow: 1048576,
6339
+ maxTokens: 131072,
6286
6340
  },
6287
- "k3": {
6288
- id: "k3",
6289
- name: "Kimi K3",
6341
+ "kimi-for-coding": {
6342
+ id: "kimi-for-coding",
6343
+ name: "Kimi K2.7 Code",
6290
6344
  api: "anthropic-messages",
6291
6345
  provider: "kimi-coding",
6292
6346
  baseUrl: "https://api.kimi.com/coding",
@@ -6299,8 +6353,8 @@ export const MODELS = {
6299
6353
  cacheRead: 0,
6300
6354
  cacheWrite: 0,
6301
6355
  },
6302
- contextWindow: 1048576,
6303
- maxTokens: 131072,
6356
+ contextWindow: 262144,
6357
+ maxTokens: 32768,
6304
6358
  },
6305
6359
  "kimi-for-coding-highspeed": {
6306
6360
  id: "kimi-for-coding-highspeed",
@@ -8564,6 +8618,42 @@ export const MODELS = {
8564
8618
  contextWindow: 1048576,
8565
8619
  maxTokens: 65536,
8566
8620
  },
8621
+ "gemini-3.5-flash-lite": {
8622
+ id: "gemini-3.5-flash-lite",
8623
+ name: "Gemini 3.5 Flash Lite",
8624
+ api: "google-generative-ai",
8625
+ provider: "opencode",
8626
+ baseUrl: "https://opencode.ai/zen/v1",
8627
+ reasoning: true,
8628
+ thinkingLevelMap: { "off": null },
8629
+ input: ["text", "image"],
8630
+ cost: {
8631
+ input: 0.3,
8632
+ output: 2.5,
8633
+ cacheRead: 0.03,
8634
+ cacheWrite: 0,
8635
+ },
8636
+ contextWindow: 1048576,
8637
+ maxTokens: 65536,
8638
+ },
8639
+ "gemini-3.6-flash": {
8640
+ id: "gemini-3.6-flash",
8641
+ name: "Gemini 3.6 Flash",
8642
+ api: "google-generative-ai",
8643
+ provider: "opencode",
8644
+ baseUrl: "https://opencode.ai/zen/v1",
8645
+ reasoning: true,
8646
+ thinkingLevelMap: { "off": null },
8647
+ input: ["text", "image"],
8648
+ cost: {
8649
+ input: 1.5,
8650
+ output: 7.5,
8651
+ cacheRead: 0.15,
8652
+ cacheWrite: 0,
8653
+ },
8654
+ contextWindow: 1048576,
8655
+ maxTokens: 65536,
8656
+ },
8567
8657
  "glm-5": {
8568
8658
  id: "glm-5",
8569
8659
  name: "GLM-5",
@@ -8991,23 +9081,6 @@ export const MODELS = {
8991
9081
  contextWindow: 256000,
8992
9082
  maxTokens: 256000,
8993
9083
  },
8994
- "hy3-free": {
8995
- id: "hy3-free",
8996
- name: "Hy3 Free",
8997
- api: "openai-completions",
8998
- provider: "opencode",
8999
- baseUrl: "https://opencode.ai/zen/v1",
9000
- reasoning: true,
9001
- input: ["text"],
9002
- cost: {
9003
- input: 0,
9004
- output: 0,
9005
- cacheRead: 0,
9006
- cacheWrite: 0,
9007
- },
9008
- contextWindow: 190000,
9009
- maxTokens: 64000,
9010
- },
9011
9084
  "kimi-k2.5": {
9012
9085
  id: "kimi-k2.5",
9013
9086
  name: "Kimi K2.5",
@@ -9059,6 +9132,23 @@ export const MODELS = {
9059
9132
  contextWindow: 262144,
9060
9133
  maxTokens: 262144,
9061
9134
  },
9135
+ "laguna-s-2.1-free": {
9136
+ id: "laguna-s-2.1-free",
9137
+ name: "Laguna S 2.1 Free",
9138
+ api: "openai-completions",
9139
+ provider: "opencode",
9140
+ baseUrl: "https://opencode.ai/zen/v1",
9141
+ reasoning: true,
9142
+ input: ["text"],
9143
+ cost: {
9144
+ input: 0,
9145
+ output: 0,
9146
+ cacheRead: 0,
9147
+ cacheWrite: 0,
9148
+ },
9149
+ contextWindow: 256000,
9150
+ maxTokens: 32000,
9151
+ },
9062
9152
  "mimo-v2.5-free": {
9063
9153
  id: "mimo-v2.5-free",
9064
9154
  name: "MiMo V2.5 Free",
@@ -9286,6 +9376,23 @@ export const MODELS = {
9286
9376
  contextWindow: 500000,
9287
9377
  maxTokens: 500000,
9288
9378
  },
9379
+ "hy3": {
9380
+ id: "hy3",
9381
+ name: "Hy3",
9382
+ api: "openai-completions",
9383
+ provider: "opencode-go",
9384
+ baseUrl: "https://opencode.ai/zen/go/v1",
9385
+ reasoning: true,
9386
+ input: ["text"],
9387
+ cost: {
9388
+ input: 0.14,
9389
+ output: 0.58,
9390
+ cacheRead: 0.035,
9391
+ cacheWrite: 0,
9392
+ },
9393
+ contextWindow: 256000,
9394
+ maxTokens: 64000,
9395
+ },
9289
9396
  "kimi-k2.6": {
9290
9397
  id: "kimi-k2.6",
9291
9398
  name: "Kimi K2.6",
@@ -10057,7 +10164,7 @@ export const MODELS = {
10057
10164
  cacheRead: 0,
10058
10165
  cacheWrite: 0,
10059
10166
  },
10060
- contextWindow: 131072,
10167
+ contextWindow: 163840,
10061
10168
  maxTokens: 16000,
10062
10169
  },
10063
10170
  "deepseek/deepseek-chat-v3-0324": {
@@ -10142,7 +10249,7 @@ export const MODELS = {
10142
10249
  cacheRead: 0.135,
10143
10250
  cacheWrite: 0,
10144
10251
  },
10145
- contextWindow: 131072,
10252
+ contextWindow: 163840,
10146
10253
  maxTokens: 32768,
10147
10254
  },
10148
10255
  "deepseek/deepseek-v3.2": {
@@ -10333,7 +10440,7 @@ export const MODELS = {
10333
10440
  cacheRead: 0.19999999999999998,
10334
10441
  cacheWrite: 0.375,
10335
10442
  },
10336
- contextWindow: 65536,
10443
+ contextWindow: 131072,
10337
10444
  maxTokens: 32768,
10338
10445
  },
10339
10446
  "google/gemini-3.1-flash-lite": {
@@ -10401,7 +10508,7 @@ export const MODELS = {
10401
10508
  cacheRead: 0.19999999999999998,
10402
10509
  cacheWrite: 0.375,
10403
10510
  },
10404
- contextWindow: 1048756,
10511
+ contextWindow: 1048576,
10405
10512
  maxTokens: 65536,
10406
10513
  },
10407
10514
  "google/gemini-3.5-flash": {
@@ -10421,6 +10528,40 @@ export const MODELS = {
10421
10528
  contextWindow: 1048576,
10422
10529
  maxTokens: 65536,
10423
10530
  },
10531
+ "google/gemini-3.5-flash-lite": {
10532
+ id: "google/gemini-3.5-flash-lite",
10533
+ name: "Google: Gemini 3.5 Flash Lite",
10534
+ api: "openai-completions",
10535
+ provider: "openrouter",
10536
+ baseUrl: "https://openrouter.ai/api/v1",
10537
+ reasoning: true,
10538
+ input: ["text", "image"],
10539
+ cost: {
10540
+ input: 0.3,
10541
+ output: 2.5,
10542
+ cacheRead: 0.03,
10543
+ cacheWrite: 0.08333333333333334,
10544
+ },
10545
+ contextWindow: 1048576,
10546
+ maxTokens: 65536,
10547
+ },
10548
+ "google/gemini-3.6-flash": {
10549
+ id: "google/gemini-3.6-flash",
10550
+ name: "Google: Gemini 3.6 Flash",
10551
+ api: "openai-completions",
10552
+ provider: "openrouter",
10553
+ baseUrl: "https://openrouter.ai/api/v1",
10554
+ reasoning: true,
10555
+ input: ["text", "image"],
10556
+ cost: {
10557
+ input: 1.5,
10558
+ output: 7.5,
10559
+ cacheRead: 0.15,
10560
+ cacheWrite: 0.08333333333333334,
10561
+ },
10562
+ contextWindow: 1048576,
10563
+ maxTokens: 65536,
10564
+ },
10424
10565
  "google/gemma-3-12b-it": {
10425
10566
  id: "google/gemma-3-12b-it",
10426
10567
  name: "Google: Gemma 3 12B",
@@ -10452,7 +10593,7 @@ export const MODELS = {
10452
10593
  cacheRead: 0,
10453
10594
  cacheWrite: 0,
10454
10595
  },
10455
- contextWindow: 131072,
10596
+ contextWindow: 262144,
10456
10597
  maxTokens: 4096,
10457
10598
  },
10458
10599
  "google/gemma-4-26b-a4b-it": {
@@ -10464,13 +10605,13 @@ export const MODELS = {
10464
10605
  reasoning: true,
10465
10606
  input: ["text", "image"],
10466
10607
  cost: {
10467
- input: 0.07,
10468
- output: 0.33999999999999997,
10469
- cacheRead: 0,
10608
+ input: 0.12,
10609
+ output: 0.35,
10610
+ cacheRead: 0.049999999999999996,
10470
10611
  cacheWrite: 0,
10471
10612
  },
10472
10613
  contextWindow: 262144,
10473
- maxTokens: 16384,
10614
+ maxTokens: 262144,
10474
10615
  },
10475
10616
  "google/gemma-4-26b-a4b-it:free": {
10476
10617
  id: "google/gemma-4-26b-a4b-it:free",
@@ -10498,9 +10639,9 @@ export const MODELS = {
10498
10639
  reasoning: true,
10499
10640
  input: ["text", "image"],
10500
10641
  cost: {
10501
- input: 0.22,
10502
- output: 0.55,
10503
- cacheRead: 0.12,
10642
+ input: 0.12,
10643
+ output: 0.35,
10644
+ cacheRead: 0.09,
10504
10645
  cacheWrite: 0,
10505
10646
  },
10506
10647
  contextWindow: 262144,
@@ -10639,7 +10780,7 @@ export const MODELS = {
10639
10780
  cacheRead: 0.06,
10640
10781
  cacheWrite: 0,
10641
10782
  },
10642
- contextWindow: 256000,
10783
+ contextWindow: 262144,
10643
10784
  maxTokens: 80000,
10644
10785
  },
10645
10786
  "kwaipilot/kat-coder-pro-v2.5": {
@@ -10659,6 +10800,23 @@ export const MODELS = {
10659
10800
  contextWindow: 256000,
10660
10801
  maxTokens: 80000,
10661
10802
  },
10803
+ "meituan/longcat-2.0": {
10804
+ id: "meituan/longcat-2.0",
10805
+ name: "Meituan: LongCat 2.0",
10806
+ api: "openai-completions",
10807
+ provider: "openrouter",
10808
+ baseUrl: "https://openrouter.ai/api/v1",
10809
+ reasoning: true,
10810
+ input: ["text"],
10811
+ cost: {
10812
+ input: 0.3,
10813
+ output: 1.2,
10814
+ cacheRead: 0.006,
10815
+ cacheWrite: 0,
10816
+ },
10817
+ contextWindow: 1048756,
10818
+ maxTokens: 262144,
10819
+ },
10662
10820
  "meta-llama/llama-3.1-70b-instruct": {
10663
10821
  id: "meta-llama/llama-3.1-70b-instruct",
10664
10822
  name: "Meta: Llama 3.1 70B Instruct",
@@ -10710,23 +10868,6 @@ export const MODELS = {
10710
10868
  contextWindow: 131072,
10711
10869
  maxTokens: 128000,
10712
10870
  },
10713
- "meta-llama/llama-3.3-70b-instruct:free": {
10714
- id: "meta-llama/llama-3.3-70b-instruct:free",
10715
- name: "Meta: Llama 3.3 70B Instruct (free)",
10716
- api: "openai-completions",
10717
- provider: "openrouter",
10718
- baseUrl: "https://openrouter.ai/api/v1",
10719
- reasoning: false,
10720
- input: ["text"],
10721
- cost: {
10722
- input: 0,
10723
- output: 0,
10724
- cacheRead: 0,
10725
- cacheWrite: 0,
10726
- },
10727
- contextWindow: 131072,
10728
- maxTokens: 4096,
10729
- },
10730
10871
  "meta-llama/llama-4-maverick": {
10731
10872
  id: "meta-llama/llama-4-maverick",
10732
10873
  name: "Meta: Llama 4 Maverick",
@@ -10758,7 +10899,7 @@ export const MODELS = {
10758
10899
  cacheRead: 0,
10759
10900
  cacheWrite: 0,
10760
10901
  },
10761
- contextWindow: 10000000,
10902
+ contextWindow: 1310720,
10762
10903
  maxTokens: 16384,
10763
10904
  },
10764
10905
  "meta/muse-spark-1.1": {
@@ -11132,7 +11273,7 @@ export const MODELS = {
11132
11273
  cacheRead: 0.01,
11133
11274
  cacheWrite: 0,
11134
11275
  },
11135
- contextWindow: 131072,
11276
+ contextWindow: 256000,
11136
11277
  maxTokens: 4096,
11137
11278
  },
11138
11279
  "mistralai/mixtral-8x22b-instruct": {
@@ -11263,9 +11404,9 @@ export const MODELS = {
11263
11404
  reasoning: true,
11264
11405
  input: ["text", "image"],
11265
11406
  cost: {
11266
- input: 0.85,
11267
- output: 3.8,
11268
- cacheRead: 0.16999999999999998,
11407
+ input: 0.82,
11408
+ output: 3.75,
11409
+ cacheRead: 0.16,
11269
11410
  cacheWrite: 0,
11270
11411
  },
11271
11412
  contextWindow: 262144,
@@ -11382,9 +11523,9 @@ export const MODELS = {
11382
11523
  reasoning: true,
11383
11524
  input: ["text"],
11384
11525
  cost: {
11385
- input: 0.21,
11386
- output: 0.45499999999999996,
11387
- cacheRead: 0.06,
11526
+ input: 0.08,
11527
+ output: 0.44999999999999996,
11528
+ cacheRead: 0,
11388
11529
  cacheWrite: 0,
11389
11530
  },
11390
11531
  contextWindow: 1000000,
@@ -11404,7 +11545,7 @@ export const MODELS = {
11404
11545
  cacheRead: 0,
11405
11546
  cacheWrite: 0,
11406
11547
  },
11407
- contextWindow: 1000000,
11548
+ contextWindow: 262144,
11408
11549
  maxTokens: 262144,
11409
11550
  },
11410
11551
  "nvidia/nemotron-3-ultra-550b-a55b": {
@@ -11416,13 +11557,13 @@ export const MODELS = {
11416
11557
  reasoning: true,
11417
11558
  input: ["text"],
11418
11559
  cost: {
11419
- input: 0.6,
11420
- output: 3.5999999999999996,
11421
- cacheRead: 0.19999999999999998,
11560
+ input: 0.5,
11561
+ output: 2.2,
11562
+ cacheRead: 0.09999999999999999,
11422
11563
  cacheWrite: 0,
11423
11564
  },
11424
- contextWindow: 1000000,
11425
- maxTokens: 4096,
11565
+ contextWindow: 512288,
11566
+ maxTokens: 16384,
11426
11567
  },
11427
11568
  "nvidia/nemotron-3-ultra-550b-a55b:free": {
11428
11569
  id: "nvidia/nemotron-3-ultra-550b-a55b:free",
@@ -12473,6 +12614,40 @@ export const MODELS = {
12473
12614
  contextWindow: 262144,
12474
12615
  maxTokens: 32768,
12475
12616
  },
12617
+ "poolside/laguna-s-2.1": {
12618
+ id: "poolside/laguna-s-2.1",
12619
+ name: "Poolside: Laguna S 2.1",
12620
+ api: "openai-completions",
12621
+ provider: "openrouter",
12622
+ baseUrl: "https://openrouter.ai/api/v1",
12623
+ reasoning: true,
12624
+ input: ["text"],
12625
+ cost: {
12626
+ input: 0.09999999999999999,
12627
+ output: 0.19999999999999998,
12628
+ cacheRead: 0.01,
12629
+ cacheWrite: 0,
12630
+ },
12631
+ contextWindow: 1048576,
12632
+ maxTokens: 131072,
12633
+ },
12634
+ "poolside/laguna-s-2.1:free": {
12635
+ id: "poolside/laguna-s-2.1:free",
12636
+ name: "Poolside: Laguna S 2.1 (free)",
12637
+ api: "openai-completions",
12638
+ provider: "openrouter",
12639
+ baseUrl: "https://openrouter.ai/api/v1",
12640
+ reasoning: true,
12641
+ input: ["text"],
12642
+ cost: {
12643
+ input: 0,
12644
+ output: 0,
12645
+ cacheRead: 0,
12646
+ cacheWrite: 0,
12647
+ },
12648
+ contextWindow: 262144,
12649
+ maxTokens: 32768,
12650
+ },
12476
12651
  "poolside/laguna-xs-2.1": {
12477
12652
  id: "poolside/laguna-xs-2.1",
12478
12653
  name: "Poolside: Laguna XS 2.1",
@@ -12521,7 +12696,7 @@ export const MODELS = {
12521
12696
  cacheRead: 0,
12522
12697
  cacheWrite: 0,
12523
12698
  },
12524
- contextWindow: 131072,
12699
+ contextWindow: 32768,
12525
12700
  maxTokens: 16384,
12526
12701
  },
12527
12702
  "qwen/qwen-2.5-7b-instruct": {
@@ -12538,7 +12713,7 @@ export const MODELS = {
12538
12713
  cacheRead: 0,
12539
12714
  cacheWrite: 0,
12540
12715
  },
12541
- contextWindow: 131072,
12716
+ contextWindow: 32768,
12542
12717
  maxTokens: 32768,
12543
12718
  },
12544
12719
  "qwen/qwen-plus": {
@@ -12606,7 +12781,7 @@ export const MODELS = {
12606
12781
  cacheRead: 0,
12607
12782
  cacheWrite: 0,
12608
12783
  },
12609
- contextWindow: 131702,
12784
+ contextWindow: 131072,
12610
12785
  maxTokens: 8192,
12611
12786
  },
12612
12787
  "qwen/qwen3-235b-a22b": {
@@ -12652,13 +12827,13 @@ export const MODELS = {
12652
12827
  reasoning: true,
12653
12828
  input: ["text"],
12654
12829
  cost: {
12655
- input: 0.14950000000000002,
12656
- output: 1.495,
12830
+ input: 0.3,
12831
+ output: 3,
12657
12832
  cacheRead: 0,
12658
12833
  cacheWrite: 0,
12659
12834
  },
12660
12835
  contextWindow: 262144,
12661
- maxTokens: 4096,
12836
+ maxTokens: 32768,
12662
12837
  },
12663
12838
  "qwen/qwen3-30b-a3b": {
12664
12839
  id: "qwen/qwen3-30b-a3b",
@@ -12708,7 +12883,7 @@ export const MODELS = {
12708
12883
  cacheRead: 0,
12709
12884
  cacheWrite: 0,
12710
12885
  },
12711
- contextWindow: 131072,
12886
+ contextWindow: 81920,
12712
12887
  maxTokens: 32768,
12713
12888
  },
12714
12889
  "qwen/qwen3-32b": {
@@ -12759,7 +12934,7 @@ export const MODELS = {
12759
12934
  cacheRead: 0.09999999999999999,
12760
12935
  cacheWrite: 0,
12761
12936
  },
12762
- contextWindow: 1048576,
12937
+ contextWindow: 262144,
12763
12938
  maxTokens: 65536,
12764
12939
  },
12765
12940
  "qwen/qwen3-coder-30b-a3b-instruct": {
@@ -12776,7 +12951,7 @@ export const MODELS = {
12776
12951
  cacheRead: 0,
12777
12952
  cacheWrite: 0,
12778
12953
  },
12779
- contextWindow: 160000,
12954
+ contextWindow: 262144,
12780
12955
  maxTokens: 32768,
12781
12956
  },
12782
12957
  "qwen/qwen3-coder-flash": {
@@ -12830,23 +13005,6 @@ export const MODELS = {
12830
13005
  contextWindow: 1000000,
12831
13006
  maxTokens: 65536,
12832
13007
  },
12833
- "qwen/qwen3-coder:free": {
12834
- id: "qwen/qwen3-coder:free",
12835
- name: "Qwen: Qwen3 Coder 480B A35B (free)",
12836
- api: "openai-completions",
12837
- provider: "openrouter",
12838
- baseUrl: "https://openrouter.ai/api/v1",
12839
- reasoning: false,
12840
- input: ["text"],
12841
- cost: {
12842
- input: 0,
12843
- output: 0,
12844
- cacheRead: 0,
12845
- cacheWrite: 0,
12846
- },
12847
- contextWindow: 1048576,
12848
- maxTokens: 262000,
12849
- },
12850
13008
  "qwen/qwen3-max": {
12851
13009
  id: "qwen/qwen3-max",
12852
13010
  name: "Qwen: Qwen3 Max",
@@ -12890,30 +13048,13 @@ export const MODELS = {
12890
13048
  reasoning: false,
12891
13049
  input: ["text"],
12892
13050
  cost: {
12893
- input: 0.09999999999999999,
12894
- output: 1.1,
12895
- cacheRead: 0.07,
12896
- cacheWrite: 0,
12897
- },
12898
- contextWindow: 262144,
12899
- maxTokens: 262144,
12900
- },
12901
- "qwen/qwen3-next-80b-a3b-instruct:free": {
12902
- id: "qwen/qwen3-next-80b-a3b-instruct:free",
12903
- name: "Qwen: Qwen3 Next 80B A3B Instruct (free)",
12904
- api: "openai-completions",
12905
- provider: "openrouter",
12906
- baseUrl: "https://openrouter.ai/api/v1",
12907
- reasoning: false,
12908
- input: ["text"],
12909
- cost: {
12910
- input: 0,
12911
- output: 0,
13051
+ input: 0.15,
13052
+ output: 1.2,
12912
13053
  cacheRead: 0,
12913
13054
  cacheWrite: 0,
12914
13055
  },
12915
13056
  contextWindow: 262144,
12916
- maxTokens: 4096,
13057
+ maxTokens: 262144,
12917
13058
  },
12918
13059
  "qwen/qwen3-next-80b-a3b-thinking": {
12919
13060
  id: "qwen/qwen3-next-80b-a3b-thinking",
@@ -12946,7 +13087,7 @@ export const MODELS = {
12946
13087
  cacheRead: 0.09999999999999999,
12947
13088
  cacheWrite: 0,
12948
13089
  },
12949
- contextWindow: 131072,
13090
+ contextWindow: 262144,
12950
13091
  maxTokens: 32768,
12951
13092
  },
12952
13093
  "qwen/qwen3-vl-235b-a22b-thinking": {
@@ -12975,13 +13116,13 @@ export const MODELS = {
12975
13116
  reasoning: false,
12976
13117
  input: ["text", "image"],
12977
13118
  cost: {
12978
- input: 0.13,
12979
- output: 0.52,
13119
+ input: 0.15,
13120
+ output: 0.6,
12980
13121
  cacheRead: 0,
12981
13122
  cacheWrite: 0,
12982
13123
  },
12983
13124
  contextWindow: 262144,
12984
- maxTokens: 32768,
13125
+ maxTokens: 16384,
12985
13126
  },
12986
13127
  "qwen/qwen3-vl-30b-a3b-thinking": {
12987
13128
  id: "qwen/qwen3-vl-30b-a3b-thinking",
@@ -12997,7 +13138,7 @@ export const MODELS = {
12997
13138
  cacheRead: 0,
12998
13139
  cacheWrite: 0,
12999
13140
  },
13000
- contextWindow: 131072,
13141
+ contextWindow: 262144,
13001
13142
  maxTokens: 32768,
13002
13143
  },
13003
13144
  "qwen/qwen3-vl-32b-instruct": {
@@ -13014,7 +13155,7 @@ export const MODELS = {
13014
13155
  cacheRead: 0,
13015
13156
  cacheWrite: 0,
13016
13157
  },
13017
- contextWindow: 262144,
13158
+ contextWindow: 131072,
13018
13159
  maxTokens: 32768,
13019
13160
  },
13020
13161
  "qwen/qwen3-vl-8b-instruct": {
@@ -13031,7 +13172,7 @@ export const MODELS = {
13031
13172
  cacheRead: 0,
13032
13173
  cacheWrite: 0,
13033
13174
  },
13034
- contextWindow: 256000,
13175
+ contextWindow: 262144,
13035
13176
  maxTokens: 32768,
13036
13177
  },
13037
13178
  "qwen/qwen3-vl-8b-thinking": {
@@ -13048,7 +13189,7 @@ export const MODELS = {
13048
13189
  cacheRead: 0,
13049
13190
  cacheWrite: 0,
13050
13191
  },
13051
- contextWindow: 256000,
13192
+ contextWindow: 131072,
13052
13193
  maxTokens: 32768,
13053
13194
  },
13054
13195
  "qwen/qwen3.5-122b-a10b": {
@@ -13196,13 +13337,13 @@ export const MODELS = {
13196
13337
  reasoning: true,
13197
13338
  input: ["text", "image"],
13198
13339
  cost: {
13199
- input: 0.44999999999999996,
13200
- output: 2.7,
13201
- cacheRead: 0,
13340
+ input: 0.6,
13341
+ output: 3.5999999999999996,
13342
+ cacheRead: 0.12,
13202
13343
  cacheWrite: 0,
13203
13344
  },
13204
13345
  contextWindow: 262144,
13205
- maxTokens: 65536,
13346
+ maxTokens: 262144,
13206
13347
  },
13207
13348
  "qwen/qwen3.6-35b-a3b": {
13208
13349
  id: "qwen/qwen3.6-35b-a3b",
@@ -13405,7 +13546,7 @@ export const MODELS = {
13405
13546
  cacheRead: 0.04,
13406
13547
  cacheWrite: 0,
13407
13548
  },
13408
- contextWindow: 256000,
13549
+ contextWindow: 262144,
13409
13550
  maxTokens: 256000,
13410
13551
  },
13411
13552
  "tencent/hy3": {
@@ -13417,26 +13558,9 @@ export const MODELS = {
13417
13558
  reasoning: true,
13418
13559
  input: ["text"],
13419
13560
  cost: {
13420
- input: 0.19999999999999998,
13421
- output: 0.7999999999999999,
13422
- cacheRead: 0.049999999999999996,
13423
- cacheWrite: 0,
13424
- },
13425
- contextWindow: 262144,
13426
- maxTokens: 131072,
13427
- },
13428
- "tencent/hy3:free": {
13429
- id: "tencent/hy3:free",
13430
- name: "Tencent: Hy3 (free)",
13431
- api: "openai-completions",
13432
- provider: "openrouter",
13433
- baseUrl: "https://openrouter.ai/api/v1",
13434
- reasoning: true,
13435
- input: ["text"],
13436
- cost: {
13437
- input: 0,
13438
- output: 0,
13439
- cacheRead: 0,
13561
+ input: 0.14,
13562
+ output: 0.58,
13563
+ cacheRead: 0.035,
13440
13564
  cacheWrite: 0,
13441
13565
  },
13442
13566
  contextWindow: 262144,
@@ -13473,7 +13597,7 @@ export const MODELS = {
13473
13597
  cacheRead: 0.16999999999999998,
13474
13598
  cacheWrite: 0,
13475
13599
  },
13476
- contextWindow: 1048576,
13600
+ contextWindow: 524288,
13477
13601
  maxTokens: 4096,
13478
13602
  },
13479
13603
  "upstage/solar-pro-3": {
@@ -13575,7 +13699,7 @@ export const MODELS = {
13575
13699
  cacheRead: 0.0028,
13576
13700
  cacheWrite: 0,
13577
13701
  },
13578
- contextWindow: 1048576,
13702
+ contextWindow: 1050000,
13579
13703
  maxTokens: 131072,
13580
13704
  },
13581
13705
  "xiaomi/mimo-v2.5-pro": {
@@ -13592,7 +13716,7 @@ export const MODELS = {
13592
13716
  cacheRead: 0.0036,
13593
13717
  cacheWrite: 0,
13594
13718
  },
13595
- contextWindow: 1048576,
13719
+ contextWindow: 1050000,
13596
13720
  maxTokens: 131072,
13597
13721
  },
13598
13722
  "z-ai/glm-4.5": {
@@ -13660,7 +13784,7 @@ export const MODELS = {
13660
13784
  cacheRead: 0.09999999999999999,
13661
13785
  cacheWrite: 0,
13662
13786
  },
13663
- contextWindow: 202752,
13787
+ contextWindow: 204800,
13664
13788
  maxTokens: 131072,
13665
13789
  },
13666
13790
  "z-ai/glm-4.6v": {
@@ -13694,7 +13818,7 @@ export const MODELS = {
13694
13818
  cacheRead: 0.08,
13695
13819
  cacheWrite: 0,
13696
13820
  },
13697
- contextWindow: 202752,
13821
+ contextWindow: 204800,
13698
13822
  maxTokens: 131072,
13699
13823
  },
13700
13824
  "z-ai/glm-4.7-flash": {
@@ -13706,13 +13830,13 @@ export const MODELS = {
13706
13830
  reasoning: true,
13707
13831
  input: ["text"],
13708
13832
  cost: {
13709
- input: 0.060500000000000005,
13833
+ input: 0.06,
13710
13834
  output: 0.39999999999999997,
13711
- cacheRead: 0,
13835
+ cacheRead: 0.01,
13712
13836
  cacheWrite: 0,
13713
13837
  },
13714
- contextWindow: 200000,
13715
- maxTokens: 131072,
13838
+ contextWindow: 202752,
13839
+ maxTokens: 16384,
13716
13840
  },
13717
13841
  "z-ai/glm-5": {
13718
13842
  id: "z-ai/glm-5",
@@ -13728,7 +13852,7 @@ export const MODELS = {
13728
13852
  cacheRead: 0.119,
13729
13853
  cacheWrite: 0,
13730
13854
  },
13731
- contextWindow: 202752,
13855
+ contextWindow: 204800,
13732
13856
  maxTokens: 202752,
13733
13857
  },
13734
13858
  "z-ai/glm-5-turbo": {
@@ -13762,7 +13886,7 @@ export const MODELS = {
13762
13886
  cacheRead: 0.1794,
13763
13887
  cacheWrite: 0,
13764
13888
  },
13765
- contextWindow: 202752,
13889
+ contextWindow: 204800,
13766
13890
  maxTokens: 128000,
13767
13891
  },
13768
13892
  "z-ai/glm-5.2": {
@@ -13774,9 +13898,9 @@ export const MODELS = {
13774
13898
  reasoning: true,
13775
13899
  input: ["text"],
13776
13900
  cost: {
13777
- input: 0.26880000000000004,
13778
- output: 0.8448,
13779
- cacheRead: 0.04992,
13901
+ input: 0.8148,
13902
+ output: 2.5608,
13903
+ cacheRead: 0.15132,
13780
13904
  cacheWrite: 0,
13781
13905
  },
13782
13906
  contextWindow: 1048576,
@@ -13878,7 +14002,7 @@ export const MODELS = {
13878
14002
  input: ["text", "image"],
13879
14003
  cost: {
13880
14004
  input: 1.5,
13881
- output: 9,
14005
+ output: 7.5,
13882
14006
  cacheRead: 0.15,
13883
14007
  cacheWrite: 0.08333333333333334,
13884
14008
  },
@@ -15386,6 +15510,40 @@ export const MODELS = {
15386
15510
  contextWindow: 1000000,
15387
15511
  maxTokens: 64000,
15388
15512
  },
15513
+ "google/gemini-3.5-flash-lite": {
15514
+ id: "google/gemini-3.5-flash-lite",
15515
+ name: "Gemini 3.5 Flash Lite",
15516
+ api: "anthropic-messages",
15517
+ provider: "vercel-ai-gateway",
15518
+ baseUrl: "https://ai-gateway.vercel.sh",
15519
+ reasoning: true,
15520
+ input: ["text", "image"],
15521
+ cost: {
15522
+ input: 0.3,
15523
+ output: 2.5,
15524
+ cacheRead: 0.03,
15525
+ cacheWrite: 0,
15526
+ },
15527
+ contextWindow: 1000000,
15528
+ maxTokens: 65000,
15529
+ },
15530
+ "google/gemini-3.6-flash": {
15531
+ id: "google/gemini-3.6-flash",
15532
+ name: "Gemini 3.6 Flash",
15533
+ api: "anthropic-messages",
15534
+ provider: "vercel-ai-gateway",
15535
+ baseUrl: "https://ai-gateway.vercel.sh",
15536
+ reasoning: true,
15537
+ input: ["text", "image"],
15538
+ cost: {
15539
+ input: 1.5,
15540
+ output: 7.5,
15541
+ cacheRead: 0.15,
15542
+ cacheWrite: 0,
15543
+ },
15544
+ contextWindow: 1000000,
15545
+ maxTokens: 64000,
15546
+ },
15389
15547
  "google/gemma-4-26b-a4b-it": {
15390
15548
  id: "google/gemma-4-26b-a4b-it",
15391
15549
  name: "Gemma 4 26B A4B IT",
@@ -16928,6 +17086,40 @@ export const MODELS = {
16928
17086
  contextWindow: 200000,
16929
17087
  maxTokens: 100000,
16930
17088
  },
17089
+ "poolside/laguna-s-2.1": {
17090
+ id: "poolside/laguna-s-2.1",
17091
+ name: "Laguna S 2.1",
17092
+ api: "anthropic-messages",
17093
+ provider: "vercel-ai-gateway",
17094
+ baseUrl: "https://ai-gateway.vercel.sh",
17095
+ reasoning: true,
17096
+ input: ["text"],
17097
+ cost: {
17098
+ input: 0.09999999999999999,
17099
+ output: 0.19999999999999998,
17100
+ cacheRead: 0.01,
17101
+ cacheWrite: 0,
17102
+ },
17103
+ contextWindow: 1000000,
17104
+ maxTokens: 131072,
17105
+ },
17106
+ "poolside/laguna-s-2.1-free": {
17107
+ id: "poolside/laguna-s-2.1-free",
17108
+ name: "Laguna S 2.1 Free",
17109
+ api: "anthropic-messages",
17110
+ provider: "vercel-ai-gateway",
17111
+ baseUrl: "https://ai-gateway.vercel.sh",
17112
+ reasoning: true,
17113
+ input: ["text"],
17114
+ cost: {
17115
+ input: 0,
17116
+ output: 0,
17117
+ cacheRead: 0,
17118
+ cacheWrite: 0,
17119
+ },
17120
+ contextWindow: 256000,
17121
+ maxTokens: 32768,
17122
+ },
16931
17123
  "sakana/fugu-ultra": {
16932
17124
  id: "sakana/fugu-ultra",
16933
17125
  name: "Fugu Ultra",
@@ -16979,6 +17171,23 @@ export const MODELS = {
16979
17171
  contextWindow: 256000,
16980
17172
  maxTokens: 256000,
16981
17173
  },
17174
+ "tencent/hy3": {
17175
+ id: "tencent/hy3",
17176
+ name: "Hy3",
17177
+ api: "anthropic-messages",
17178
+ provider: "vercel-ai-gateway",
17179
+ baseUrl: "https://ai-gateway.vercel.sh",
17180
+ reasoning: true,
17181
+ input: ["text"],
17182
+ cost: {
17183
+ input: 0.14,
17184
+ output: 0.58,
17185
+ cacheRead: 0.035,
17186
+ cacheWrite: 0,
17187
+ },
17188
+ contextWindow: 262144,
17189
+ maxTokens: 262144,
17190
+ },
16982
17191
  "thinkingmachines/inkling": {
16983
17192
  id: "thinkingmachines/inkling",
16984
17193
  name: "Inkling",
@@ -17160,7 +17369,7 @@ export const MODELS = {
17160
17369
  cost: {
17161
17370
  input: 2,
17162
17371
  output: 6,
17163
- cacheRead: 0.5,
17372
+ cacheRead: 0.3,
17164
17373
  cacheWrite: 0,
17165
17374
  },
17166
17375
  contextWindow: 500000,