@elyracode/ai 0.9.43 → 0.9.44

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.
@@ -3333,6 +3333,24 @@ export const MODELS = {
3333
3333
  contextWindow: 1000000,
3334
3334
  maxTokens: 128000,
3335
3335
  },
3336
+ "claude-sonnet-5-5": {
3337
+ id: "claude-sonnet-5-5",
3338
+ name: "Claude Sonnet 5.5",
3339
+ api: "anthropic-messages",
3340
+ provider: "anthropic",
3341
+ baseUrl: "https://api.anthropic.com",
3342
+ reasoning: true,
3343
+ thinkingType: "adaptive",
3344
+ input: ["text", "image"],
3345
+ cost: {
3346
+ input: 2,
3347
+ output: 10,
3348
+ cacheRead: 0.2,
3349
+ cacheWrite: 2.5,
3350
+ },
3351
+ contextWindow: 1000000,
3352
+ maxTokens: 128000,
3353
+ },
3336
3354
  },
3337
3355
  "azure-openai-responses": {
3338
3356
  "gpt-4": {
@@ -3920,6 +3938,40 @@ export const MODELS = {
3920
3938
  contextWindow: 1050000,
3921
3939
  maxTokens: 128000,
3922
3940
  },
3941
+ "gpt-daybreak-blue-latest": {
3942
+ id: "gpt-daybreak-blue-latest",
3943
+ name: "Daybreak Blue",
3944
+ api: "azure-openai-responses",
3945
+ provider: "azure-openai-responses",
3946
+ baseUrl: "",
3947
+ reasoning: true,
3948
+ input: ["text", "image"],
3949
+ cost: {
3950
+ input: 4,
3951
+ output: 20,
3952
+ cacheRead: 0.4,
3953
+ cacheWrite: 5,
3954
+ },
3955
+ contextWindow: 1050000,
3956
+ maxTokens: 128000,
3957
+ },
3958
+ "gpt-daybreak-red-latest": {
3959
+ id: "gpt-daybreak-red-latest",
3960
+ name: "Daybreak Red",
3961
+ api: "azure-openai-responses",
3962
+ provider: "azure-openai-responses",
3963
+ baseUrl: "",
3964
+ reasoning: true,
3965
+ input: ["text", "image"],
3966
+ cost: {
3967
+ input: 12.5,
3968
+ output: 75,
3969
+ cacheRead: 1.25,
3970
+ cacheWrite: 15.625,
3971
+ },
3972
+ contextWindow: 400000,
3973
+ maxTokens: 128000,
3974
+ },
3923
3975
  "gpt-realtime-2.1": {
3924
3976
  id: "gpt-realtime-2.1",
3925
3977
  name: "GPT-Realtime-2.1",
@@ -4072,8 +4124,8 @@ export const MODELS = {
4072
4124
  cacheRead: 0,
4073
4125
  cacheWrite: 0,
4074
4126
  },
4075
- contextWindow: 65536,
4076
- maxTokens: 32768,
4127
+ contextWindow: 131072,
4128
+ maxTokens: 40960,
4077
4129
  },
4078
4130
  },
4079
4131
  "cloudflare-ai-gateway": {
@@ -5077,74 +5129,6 @@ export const MODELS = {
5077
5129
  },
5078
5130
  },
5079
5131
  "fireworks": {
5080
- "accounts/fireworks/models/deepseek-v4-flash-0731": {
5081
- id: "accounts/fireworks/models/deepseek-v4-flash-0731",
5082
- name: "DeepSeek V4 Flash 0731",
5083
- api: "anthropic-messages",
5084
- provider: "fireworks",
5085
- baseUrl: "https://api.fireworks.ai/inference",
5086
- reasoning: true,
5087
- input: ["text"],
5088
- cost: {
5089
- input: 0.22,
5090
- output: 0.66,
5091
- cacheRead: 0.007,
5092
- cacheWrite: 0,
5093
- },
5094
- contextWindow: 1000000,
5095
- maxTokens: 384000,
5096
- },
5097
- "accounts/fireworks/models/deepseek-v4-flash-vision-exp": {
5098
- id: "accounts/fireworks/models/deepseek-v4-flash-vision-exp",
5099
- name: "DeepSeek V4 Flash Vision Exp",
5100
- api: "anthropic-messages",
5101
- provider: "fireworks",
5102
- baseUrl: "https://api.fireworks.ai/inference",
5103
- reasoning: true,
5104
- input: ["text", "image"],
5105
- cost: {
5106
- input: 0.22,
5107
- output: 0.66,
5108
- cacheRead: 0.007,
5109
- cacheWrite: 0,
5110
- },
5111
- contextWindow: 1000000,
5112
- maxTokens: 384000,
5113
- },
5114
- "accounts/fireworks/models/deepseek-v4-pro": {
5115
- id: "accounts/fireworks/models/deepseek-v4-pro",
5116
- name: "DeepSeek V4 Pro",
5117
- api: "anthropic-messages",
5118
- provider: "fireworks",
5119
- baseUrl: "https://api.fireworks.ai/inference",
5120
- reasoning: true,
5121
- input: ["text"],
5122
- cost: {
5123
- input: 1.2,
5124
- output: 1.2,
5125
- cacheRead: 0.6,
5126
- cacheWrite: 0,
5127
- },
5128
- contextWindow: 1000000,
5129
- maxTokens: 384000,
5130
- },
5131
- "accounts/fireworks/models/deepseek-v4-pro-0813": {
5132
- id: "accounts/fireworks/models/deepseek-v4-pro-0813",
5133
- name: "DeepSeek V4 Pro 0813",
5134
- api: "anthropic-messages",
5135
- provider: "fireworks",
5136
- baseUrl: "https://api.fireworks.ai/inference",
5137
- reasoning: true,
5138
- input: ["text"],
5139
- cost: {
5140
- input: 1.32,
5141
- output: 3.96,
5142
- cacheRead: 0.044,
5143
- cacheWrite: 0,
5144
- },
5145
- contextWindow: 1000000,
5146
- maxTokens: 384000,
5147
- },
5148
5132
  "accounts/fireworks/models/deepseek-v4p1-flash": {
5149
5133
  id: "accounts/fireworks/models/deepseek-v4p1-flash",
5150
5134
  name: "DeepSeek V4.1 Flash",
@@ -5179,23 +5163,6 @@ export const MODELS = {
5179
5163
  contextWindow: 1048576,
5180
5164
  maxTokens: 131072,
5181
5165
  },
5182
- "accounts/fireworks/models/glm-5p2": {
5183
- id: "accounts/fireworks/models/glm-5p2",
5184
- name: "GLM 5.2",
5185
- api: "anthropic-messages",
5186
- provider: "fireworks",
5187
- baseUrl: "https://api.fireworks.ai/inference",
5188
- reasoning: true,
5189
- input: ["text"],
5190
- cost: {
5191
- input: 1.4,
5192
- output: 4.4,
5193
- cacheRead: 0.14,
5194
- cacheWrite: 0,
5195
- },
5196
- contextWindow: 1048575,
5197
- maxTokens: 131072,
5198
- },
5199
5166
  "accounts/fireworks/models/glm-5p3": {
5200
5167
  id: "accounts/fireworks/models/glm-5p3",
5201
5168
  name: "GLM 5.3",
@@ -5264,40 +5231,6 @@ export const MODELS = {
5264
5231
  contextWindow: 1048576,
5265
5232
  maxTokens: 1048576,
5266
5233
  },
5267
- "accounts/fireworks/models/kimi-k2p6": {
5268
- id: "accounts/fireworks/models/kimi-k2p6",
5269
- name: "Kimi K2.6",
5270
- api: "anthropic-messages",
5271
- provider: "fireworks",
5272
- baseUrl: "https://api.fireworks.ai/inference",
5273
- reasoning: true,
5274
- input: ["text", "image"],
5275
- cost: {
5276
- input: 0.95,
5277
- output: 4,
5278
- cacheRead: 0.16,
5279
- cacheWrite: 0,
5280
- },
5281
- contextWindow: 262000,
5282
- maxTokens: 262000,
5283
- },
5284
- "accounts/fireworks/models/kimi-k2p7-code": {
5285
- id: "accounts/fireworks/models/kimi-k2p7-code",
5286
- name: "Kimi K2.7 Code",
5287
- api: "anthropic-messages",
5288
- provider: "fireworks",
5289
- baseUrl: "https://api.fireworks.ai/inference",
5290
- reasoning: true,
5291
- input: ["text", "image"],
5292
- cost: {
5293
- input: 0.95,
5294
- output: 4,
5295
- cacheRead: 0.19,
5296
- cacheWrite: 0,
5297
- },
5298
- contextWindow: 262000,
5299
- maxTokens: 262000,
5300
- },
5301
5234
  "accounts/fireworks/models/kimi-k3": {
5302
5235
  id: "accounts/fireworks/models/kimi-k3",
5303
5236
  name: "Kimi K3",
@@ -5315,23 +5248,6 @@ export const MODELS = {
5315
5248
  contextWindow: 1048576,
5316
5249
  maxTokens: 131072,
5317
5250
  },
5318
- "accounts/fireworks/models/minimax-m2p7": {
5319
- id: "accounts/fireworks/models/minimax-m2p7",
5320
- name: "MiniMax-M2.7",
5321
- api: "anthropic-messages",
5322
- provider: "fireworks",
5323
- baseUrl: "https://api.fireworks.ai/inference",
5324
- reasoning: true,
5325
- input: ["text"],
5326
- cost: {
5327
- input: 1.2,
5328
- output: 1.2,
5329
- cacheRead: 0.6,
5330
- cacheWrite: 0,
5331
- },
5332
- contextWindow: 196608,
5333
- maxTokens: 131072,
5334
- },
5335
5251
  "accounts/fireworks/models/minimax-m3": {
5336
5252
  id: "accounts/fireworks/models/minimax-m3",
5337
5253
  name: "MiniMax-M3",
@@ -5349,23 +5265,6 @@ export const MODELS = {
5349
5265
  contextWindow: 512000,
5350
5266
  maxTokens: 512000,
5351
5267
  },
5352
- "accounts/fireworks/models/muse-glimmer-30b": {
5353
- id: "accounts/fireworks/models/muse-glimmer-30b",
5354
- name: "Muse Glimmer 30B",
5355
- api: "anthropic-messages",
5356
- provider: "fireworks",
5357
- baseUrl: "https://api.fireworks.ai/inference",
5358
- reasoning: true,
5359
- input: ["text", "image"],
5360
- cost: {
5361
- input: 0.35,
5362
- output: 1.5,
5363
- cacheRead: 0.04,
5364
- cacheWrite: 0,
5365
- },
5366
- contextWindow: 131072,
5367
- maxTokens: 131072,
5368
- },
5369
5268
  "accounts/fireworks/models/nemotron-3-ultra-nvfp4": {
5370
5269
  id: "accounts/fireworks/models/nemotron-3-ultra-nvfp4",
5371
5270
  name: "Nemotron 3 Ultra 550B A55B",
@@ -5400,23 +5299,6 @@ export const MODELS = {
5400
5299
  contextWindow: 262144,
5401
5300
  maxTokens: 262144,
5402
5301
  },
5403
- "accounts/fireworks/models/qwen3p7-plus": {
5404
- id: "accounts/fireworks/models/qwen3p7-plus",
5405
- name: "Qwen 3.7 Plus",
5406
- api: "anthropic-messages",
5407
- provider: "fireworks",
5408
- baseUrl: "https://api.fireworks.ai/inference",
5409
- reasoning: true,
5410
- input: ["text", "image"],
5411
- cost: {
5412
- input: 0.4,
5413
- output: 1.6,
5414
- cacheRead: 0.08,
5415
- cacheWrite: 0,
5416
- },
5417
- contextWindow: 262144,
5418
- maxTokens: 65536,
5419
- },
5420
5302
  "accounts/fireworks/models/qwen3p8-2p4t-a95b": {
5421
5303
  id: "accounts/fireworks/models/qwen3p8-2p4t-a95b",
5422
5304
  name: "Qwen3.8 2.4T A95B",
@@ -5468,40 +5350,6 @@ export const MODELS = {
5468
5350
  contextWindow: 1000000,
5469
5351
  maxTokens: 384000,
5470
5352
  },
5471
- "accounts/fireworks/routers/deepseek-pro-latest": {
5472
- id: "accounts/fireworks/routers/deepseek-pro-latest",
5473
- name: "DeepSeek Pro Latest",
5474
- api: "anthropic-messages",
5475
- provider: "fireworks",
5476
- baseUrl: "https://api.fireworks.ai/inference",
5477
- reasoning: true,
5478
- input: ["text"],
5479
- cost: {
5480
- input: 1.32,
5481
- output: 3.96,
5482
- cacheRead: 0.044,
5483
- cacheWrite: 0,
5484
- },
5485
- contextWindow: 1000000,
5486
- maxTokens: 384000,
5487
- },
5488
- "accounts/fireworks/routers/glm-5p2-fast": {
5489
- id: "accounts/fireworks/routers/glm-5p2-fast",
5490
- name: "GLM 5.2 Fast",
5491
- api: "anthropic-messages",
5492
- provider: "fireworks",
5493
- baseUrl: "https://api.fireworks.ai/inference",
5494
- reasoning: true,
5495
- input: ["text"],
5496
- cost: {
5497
- input: 2.1,
5498
- output: 6.6,
5499
- cacheRead: 0.21,
5500
- cacheWrite: 0,
5501
- },
5502
- contextWindow: 1048575,
5503
- maxTokens: 131072,
5504
- },
5505
5353
  "accounts/fireworks/routers/glm-5p3-fast": {
5506
5354
  id: "accounts/fireworks/routers/glm-5p3-fast",
5507
5355
  name: "GLM 5.3 Fast",
@@ -9834,6 +9682,40 @@ export const MODELS = {
9834
9682
  contextWindow: 1050000,
9835
9683
  maxTokens: 128000,
9836
9684
  },
9685
+ "gpt-daybreak-blue-latest": {
9686
+ id: "gpt-daybreak-blue-latest",
9687
+ name: "Daybreak Blue",
9688
+ api: "openai-responses",
9689
+ provider: "openai",
9690
+ baseUrl: "https://api.openai.com/v1",
9691
+ reasoning: true,
9692
+ input: ["text", "image"],
9693
+ cost: {
9694
+ input: 4,
9695
+ output: 20,
9696
+ cacheRead: 0.4,
9697
+ cacheWrite: 5,
9698
+ },
9699
+ contextWindow: 1050000,
9700
+ maxTokens: 128000,
9701
+ },
9702
+ "gpt-daybreak-red-latest": {
9703
+ id: "gpt-daybreak-red-latest",
9704
+ name: "Daybreak Red",
9705
+ api: "openai-responses",
9706
+ provider: "openai",
9707
+ baseUrl: "https://api.openai.com/v1",
9708
+ reasoning: true,
9709
+ input: ["text", "image"],
9710
+ cost: {
9711
+ input: 12.5,
9712
+ output: 75,
9713
+ cacheRead: 1.25,
9714
+ cacheWrite: 15.625,
9715
+ },
9716
+ contextWindow: 400000,
9717
+ maxTokens: 128000,
9718
+ },
9837
9719
  "gpt-realtime-2.1": {
9838
9720
  id: "gpt-realtime-2.1",
9839
9721
  name: "GPT-Realtime-2.1",
@@ -11094,16 +10976,16 @@ export const MODELS = {
11094
10976
  },
11095
10977
  "grok-4.7": {
11096
10978
  id: "grok-4.7",
11097
- name: "Grok 4.7 (30% Off)",
10979
+ name: "Grok 4.7",
11098
10980
  api: "openai-responses",
11099
10981
  provider: "opencode",
11100
10982
  baseUrl: "https://opencode.ai/zen/v1",
11101
10983
  reasoning: true,
11102
10984
  input: ["text", "image"],
11103
10985
  cost: {
11104
- input: 1.4,
11105
- output: 4.2,
11106
- cacheRead: 0.35,
10986
+ input: 2,
10987
+ output: 6,
10988
+ cacheRead: 0.5,
11107
10989
  cacheWrite: 0,
11108
10990
  },
11109
10991
  contextWindow: 500000,
@@ -11211,6 +11093,23 @@ export const MODELS = {
11211
11093
  contextWindow: 262144,
11212
11094
  maxTokens: 32768,
11213
11095
  },
11096
+ "longcat-2.5-preview-free": {
11097
+ id: "longcat-2.5-preview-free",
11098
+ name: "LongCat 2.5 Preview Free",
11099
+ api: "openai-completions",
11100
+ provider: "opencode",
11101
+ baseUrl: "https://opencode.ai/zen/v1",
11102
+ reasoning: true,
11103
+ input: ["text", "image"],
11104
+ cost: {
11105
+ input: 0,
11106
+ output: 0,
11107
+ cacheRead: 0,
11108
+ cacheWrite: 0,
11109
+ },
11110
+ contextWindow: 1000000,
11111
+ maxTokens: 131072,
11112
+ },
11214
11113
  "mimo-v2.6-flash-free": {
11215
11114
  id: "mimo-v2.6-flash-free",
11216
11115
  name: "MiMo-V2.6-Flash Free",
@@ -11296,23 +11195,6 @@ export const MODELS = {
11296
11195
  contextWindow: 1048576,
11297
11196
  maxTokens: 131072,
11298
11197
  },
11299
- "muse-spark-1.2-contributor-free": {
11300
- id: "muse-spark-1.2-contributor-free",
11301
- name: "Muse Spark 1.2 Free",
11302
- api: "openai-responses",
11303
- provider: "opencode",
11304
- baseUrl: "https://opencode.ai/zen/v1",
11305
- reasoning: true,
11306
- input: ["text", "image"],
11307
- cost: {
11308
- input: 0,
11309
- output: 0,
11310
- cacheRead: 0,
11311
- cacheWrite: 0,
11312
- },
11313
- contextWindow: 1048576,
11314
- maxTokens: 131072,
11315
- },
11316
11198
  "muse-spark-1.3": {
11317
11199
  id: "muse-spark-1.3",
11318
11200
  name: "Muse Spark 1.3",
@@ -11432,6 +11314,23 @@ export const MODELS = {
11432
11314
  contextWindow: 1000000,
11433
11315
  maxTokens: 131072,
11434
11316
  },
11317
+ "qwen3.8-max": {
11318
+ id: "qwen3.8-max",
11319
+ name: "Qwen3.8 Max",
11320
+ api: "openai-completions",
11321
+ provider: "opencode",
11322
+ baseUrl: "https://opencode.ai/zen/v1",
11323
+ reasoning: true,
11324
+ input: ["text", "image"],
11325
+ cost: {
11326
+ input: 2,
11327
+ output: 6,
11328
+ cacheRead: 0.25,
11329
+ cacheWrite: 2.5,
11330
+ },
11331
+ contextWindow: 262144,
11332
+ maxTokens: 131072,
11333
+ },
11435
11334
  "space-bunny-free": {
11436
11335
  id: "space-bunny-free",
11437
11336
  name: "Space Bunny Free",
@@ -11527,23 +11426,6 @@ export const MODELS = {
11527
11426
  contextWindow: 1000000,
11528
11427
  maxTokens: 384000,
11529
11428
  },
11530
- "glm-5.1": {
11531
- id: "glm-5.1",
11532
- name: "GLM-5.1",
11533
- api: "openai-completions",
11534
- provider: "opencode-go",
11535
- baseUrl: "https://opencode.ai/zen/go/v1",
11536
- reasoning: true,
11537
- input: ["text"],
11538
- cost: {
11539
- input: 1.4,
11540
- output: 4.4,
11541
- cacheRead: 0.26,
11542
- cacheWrite: 0,
11543
- },
11544
- contextWindow: 202752,
11545
- maxTokens: 32768,
11546
- },
11547
11429
  "glm-5.2": {
11548
11430
  id: "glm-5.2",
11549
11431
  name: "GLM-5.2",
@@ -11698,23 +11580,6 @@ export const MODELS = {
11698
11580
  contextWindow: 1024000,
11699
11581
  maxTokens: 64000,
11700
11582
  },
11701
- "kimi-k2.6": {
11702
- id: "kimi-k2.6",
11703
- name: "Kimi K2.6",
11704
- api: "openai-completions",
11705
- provider: "opencode-go",
11706
- baseUrl: "https://opencode.ai/zen/go/v1",
11707
- reasoning: true,
11708
- input: ["text", "image"],
11709
- cost: {
11710
- input: 0.95,
11711
- output: 4,
11712
- cacheRead: 0.16,
11713
- cacheWrite: 0,
11714
- },
11715
- contextWindow: 262144,
11716
- maxTokens: 65536,
11717
- },
11718
11583
  "kimi-k2.7-code": {
11719
11584
  id: "kimi-k2.7-code",
11720
11585
  name: "Kimi K2.7 Code",
@@ -11766,6 +11631,23 @@ export const MODELS = {
11766
11631
  contextWindow: 1000000,
11767
11632
  maxTokens: 131072,
11768
11633
  },
11634
+ "longcat-2.5-preview-free": {
11635
+ id: "longcat-2.5-preview-free",
11636
+ name: "LongCat 2.5 Preview Free",
11637
+ api: "openai-completions",
11638
+ provider: "opencode-go",
11639
+ baseUrl: "https://opencode.ai/zen/go/v1",
11640
+ reasoning: true,
11641
+ input: ["text", "image"],
11642
+ cost: {
11643
+ input: 0,
11644
+ output: 0,
11645
+ cacheRead: 0,
11646
+ cacheWrite: 0,
11647
+ },
11648
+ contextWindow: 1000000,
11649
+ maxTokens: 131072,
11650
+ },
11769
11651
  "mimo-v2.5": {
11770
11652
  id: "mimo-v2.5",
11771
11653
  name: "MiMo V2.5",
@@ -11902,41 +11784,6 @@ export const MODELS = {
11902
11784
  contextWindow: 1048576,
11903
11785
  maxTokens: 131072,
11904
11786
  },
11905
- "qwen3.6-plus": {
11906
- id: "qwen3.6-plus",
11907
- name: "Qwen3.6 Plus",
11908
- api: "openai-completions",
11909
- provider: "opencode-go",
11910
- baseUrl: "https://opencode.ai/zen/go/v1",
11911
- compat: { "thinkingFormat": "qwen" },
11912
- reasoning: true,
11913
- input: ["text", "image"],
11914
- cost: {
11915
- input: 0.5,
11916
- output: 3,
11917
- cacheRead: 0.05,
11918
- cacheWrite: 0.625,
11919
- },
11920
- contextWindow: 1000000,
11921
- maxTokens: 65536,
11922
- },
11923
- "qwen3.7-max": {
11924
- id: "qwen3.7-max",
11925
- name: "Qwen3.7 Max",
11926
- api: "openai-completions",
11927
- provider: "opencode-go",
11928
- baseUrl: "https://opencode.ai/zen/go/v1",
11929
- reasoning: true,
11930
- input: ["text"],
11931
- cost: {
11932
- input: 2.5,
11933
- output: 7.5,
11934
- cacheRead: 0.5,
11935
- cacheWrite: 3.125,
11936
- },
11937
- contextWindow: 1000000,
11938
- maxTokens: 65536,
11939
- },
11940
11787
  "qwen3.7-plus": {
11941
11788
  id: "qwen3.7-plus",
11942
11789
  name: "Qwen3.7 Plus",
@@ -12177,23 +12024,6 @@ export const MODELS = {
12177
12024
  contextWindow: 300000,
12178
12025
  maxTokens: 5120,
12179
12026
  },
12180
- "anthropic/claude-3-haiku": {
12181
- id: "anthropic/claude-3-haiku",
12182
- name: "Anthropic: Claude 3 Haiku",
12183
- api: "openai-completions",
12184
- provider: "openrouter",
12185
- baseUrl: "https://openrouter.ai/api/v1",
12186
- reasoning: false,
12187
- input: ["text", "image"],
12188
- cost: {
12189
- input: 0.25,
12190
- output: 1.25,
12191
- cacheRead: 0.03,
12192
- cacheWrite: 0.3,
12193
- },
12194
- contextWindow: 200000,
12195
- maxTokens: 4096,
12196
- },
12197
12027
  "anthropic/claude-fable-5": {
12198
12028
  id: "anthropic/claude-fable-5",
12199
12029
  name: "Anthropic: Claude Fable 5",
@@ -12646,6 +12476,23 @@ export const MODELS = {
12646
12476
  contextWindow: 1000000,
12647
12477
  maxTokens: 128000,
12648
12478
  },
12479
+ "anthropic/claude-sonnet-5.5": {
12480
+ id: "anthropic/claude-sonnet-5.5",
12481
+ name: "Anthropic: Claude Sonnet 5.5",
12482
+ api: "openai-completions",
12483
+ provider: "openrouter",
12484
+ baseUrl: "https://openrouter.ai/api/v1",
12485
+ reasoning: true,
12486
+ input: ["text", "image"],
12487
+ cost: {
12488
+ input: 2,
12489
+ output: 10,
12490
+ cacheRead: 0.19999999999999998,
12491
+ cacheWrite: 2.5,
12492
+ },
12493
+ contextWindow: 1000000,
12494
+ maxTokens: 128000,
12495
+ },
12649
12496
  "anthropic/claude-sonnet-5:batch": {
12650
12497
  id: "anthropic/claude-sonnet-5:batch",
12651
12498
  name: "Anthropic: Claude Sonnet 5 (batch)",
@@ -12876,13 +12723,13 @@ export const MODELS = {
12876
12723
  reasoning: false,
12877
12724
  input: ["text"],
12878
12725
  cost: {
12879
- input: 0.32,
12880
- output: 0.8899999999999999,
12726
+ input: 0.2574,
12727
+ output: 1.0287,
12881
12728
  cacheRead: 0,
12882
12729
  cacheWrite: 0,
12883
12730
  },
12884
12731
  contextWindow: 163840,
12885
- maxTokens: 16384,
12732
+ maxTokens: 16000,
12886
12733
  },
12887
12734
  "deepseek/deepseek-chat-v3-0324": {
12888
12735
  id: "deepseek/deepseek-chat-v3-0324",
@@ -12893,9 +12740,9 @@ export const MODELS = {
12893
12740
  reasoning: false,
12894
12741
  input: ["text"],
12895
12742
  cost: {
12896
- input: 0.25,
12897
- output: 1,
12898
- cacheRead: 0,
12743
+ input: 0.29,
12744
+ output: 1.1400000000000001,
12745
+ cacheRead: 0.11,
12899
12746
  cacheWrite: 0,
12900
12747
  },
12901
12748
  contextWindow: 163840,
@@ -12963,11 +12810,11 @@ export const MODELS = {
12963
12810
  cost: {
12964
12811
  input: 0.27,
12965
12812
  output: 1,
12966
- cacheRead: 0.135,
12813
+ cacheRead: 0,
12967
12814
  cacheWrite: 0,
12968
12815
  },
12969
12816
  contextWindow: 163840,
12970
- maxTokens: 32768,
12817
+ maxTokens: 147456,
12971
12818
  },
12972
12819
  "deepseek/deepseek-v3.2": {
12973
12820
  id: "deepseek/deepseek-v3.2",
@@ -12978,9 +12825,9 @@ export const MODELS = {
12978
12825
  reasoning: true,
12979
12826
  input: ["text"],
12980
12827
  cost: {
12981
- input: 0.26899999999999996,
12982
- output: 0.39999999999999997,
12983
- cacheRead: 0.13449999999999998,
12828
+ input: 0.28,
12829
+ output: 0.42,
12830
+ cacheRead: 0.028,
12984
12831
  cacheWrite: 0,
12985
12832
  },
12986
12833
  contextWindow: 163840,
@@ -12995,13 +12842,13 @@ export const MODELS = {
12995
12842
  reasoning: true,
12996
12843
  input: ["text"],
12997
12844
  cost: {
12998
- input: 0.27,
12999
- output: 0.41,
13000
- cacheRead: 0,
12845
+ input: 0.13440000000000002,
12846
+ output: 0.2016,
12847
+ cacheRead: 0.06720000000000001,
13001
12848
  cacheWrite: 0,
13002
12849
  },
13003
12850
  contextWindow: 163840,
13004
- maxTokens: 65536,
12851
+ maxTokens: 147456,
13005
12852
  },
13006
12853
  "deepseek/deepseek-v4-flash": {
13007
12854
  id: "deepseek/deepseek-v4-flash",
@@ -13014,13 +12861,13 @@ export const MODELS = {
13014
12861
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13015
12862
  input: ["text"],
13016
12863
  cost: {
13017
- input: 0.088606,
13018
- output: 0.177212,
13019
- cacheRead: 0.017721200000000003,
12864
+ input: 0.06538,
12865
+ output: 0.13076,
12866
+ cacheRead: 0.013076,
13020
12867
  cacheWrite: 0,
13021
12868
  },
13022
12869
  contextWindow: 1048576,
13023
- maxTokens: 384000,
12870
+ maxTokens: 131072,
13024
12871
  },
13025
12872
  "deepseek/deepseek-v4-flash-0731": {
13026
12873
  id: "deepseek/deepseek-v4-flash-0731",
@@ -13033,7 +12880,7 @@ export const MODELS = {
13033
12880
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13034
12881
  input: ["text"],
13035
12882
  cost: {
13036
- input: 0.03,
12883
+ input: 0.020999999999999998,
13037
12884
  output: 0.32,
13038
12885
  cacheRead: 0.016,
13039
12886
  cacheWrite: 0,
@@ -13052,13 +12899,13 @@ export const MODELS = {
13052
12899
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13053
12900
  input: ["text", "image"],
13054
12901
  cost: {
13055
- input: 0.22,
13056
- output: 0.66,
13057
- cacheRead: 0.007,
12902
+ input: 0.44,
12903
+ output: 1.32,
12904
+ cacheRead: 0.014,
13058
12905
  cacheWrite: 0,
13059
12906
  },
13060
12907
  contextWindow: 1048576,
13061
- maxTokens: 943718,
12908
+ maxTokens: 943717,
13062
12909
  },
13063
12910
  "deepseek/deepseek-v4-pro": {
13064
12911
  id: "deepseek/deepseek-v4-pro",
@@ -13071,9 +12918,9 @@ export const MODELS = {
13071
12918
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13072
12919
  input: ["text"],
13073
12920
  cost: {
13074
- input: 0.9396,
13075
- output: 1.8792,
13076
- cacheRead: 0.07830000000000001,
12921
+ input: 0.7829999999999999,
12922
+ output: 1.5659999999999998,
12923
+ cacheRead: 0.06525,
13077
12924
  cacheWrite: 0,
13078
12925
  },
13079
12926
  contextWindow: 1048576,
@@ -13090,13 +12937,13 @@ export const MODELS = {
13090
12937
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13091
12938
  input: ["text"],
13092
12939
  cost: {
13093
- input: 0.46199999999999997,
13094
- output: 1.386,
13095
- cacheRead: 0.015399999999999999,
12940
+ input: 0.3995,
12941
+ output: 4.199999999999999,
12942
+ cacheRead: 0.399,
13096
12943
  cacheWrite: 0,
13097
12944
  },
13098
12945
  contextWindow: 1048576,
13099
- maxTokens: 384000,
12946
+ maxTokens: 943718,
13100
12947
  },
13101
12948
  "deepseek/deepseek-v4.1-flash": {
13102
12949
  id: "deepseek/deepseek-v4.1-flash",
@@ -13109,13 +12956,13 @@ export const MODELS = {
13109
12956
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13110
12957
  input: ["text", "image"],
13111
12958
  cost: {
13112
- input: 0.14,
13113
- output: 0.42,
13114
- cacheRead: 0.004200000000000001,
12959
+ input: 0.3,
12960
+ output: 1.2,
12961
+ cacheRead: 0.006,
13115
12962
  cacheWrite: 0,
13116
12963
  },
13117
12964
  contextWindow: 1048576,
13118
- maxTokens: 131072,
12965
+ maxTokens: 943718,
13119
12966
  },
13120
12967
  "deepseek/deepseek-v4.1-flash:batch": {
13121
12968
  id: "deepseek/deepseek-v4.1-flash:batch",
@@ -13799,23 +13646,6 @@ export const MODELS = {
13799
13646
  contextWindow: 262144,
13800
13647
  maxTokens: 235929,
13801
13648
  },
13802
- "inclusionai/ling-3.0-flash-fin:free": {
13803
- id: "inclusionai/ling-3.0-flash-fin:free",
13804
- name: "inclusionAI: Ling 3.0 Flash Fin (free)",
13805
- api: "openai-completions",
13806
- provider: "openrouter",
13807
- baseUrl: "https://openrouter.ai/api/v1",
13808
- reasoning: true,
13809
- input: ["text"],
13810
- cost: {
13811
- input: 0,
13812
- output: 0,
13813
- cacheRead: 0,
13814
- cacheWrite: 0,
13815
- },
13816
- contextWindow: 262144,
13817
- maxTokens: 32768,
13818
- },
13819
13649
  "inclusionai/ling-3.0-flash-sante:free": {
13820
13650
  id: "inclusionai/ling-3.0-flash-sante:free",
13821
13651
  name: "inclusionAI: Ling 3.0 Flash Sante (free)",
@@ -13842,9 +13672,9 @@ export const MODELS = {
13842
13672
  reasoning: true,
13843
13673
  input: ["text", "image"],
13844
13674
  cost: {
13845
- input: 0.06,
13846
- output: 0.18,
13847
- cacheRead: 0.012,
13675
+ input: 0.020999999999999998,
13676
+ output: 0.061599999999999995,
13677
+ cacheRead: 0.004200000000000001,
13848
13678
  cacheWrite: 0,
13849
13679
  },
13850
13680
  contextWindow: 262144,
@@ -14224,6 +14054,23 @@ export const MODELS = {
14224
14054
  contextWindow: 256000,
14225
14055
  maxTokens: 204800,
14226
14056
  },
14057
+ "mistralai/devstral-2512": {
14058
+ id: "mistralai/devstral-2512",
14059
+ name: "Mistral: Devstral 2 2512",
14060
+ api: "openai-completions",
14061
+ provider: "openrouter",
14062
+ baseUrl: "https://openrouter.ai/api/v1",
14063
+ reasoning: false,
14064
+ input: ["text"],
14065
+ cost: {
14066
+ input: 0.39999999999999997,
14067
+ output: 2,
14068
+ cacheRead: 0.04,
14069
+ cacheWrite: 0,
14070
+ },
14071
+ contextWindow: 262144,
14072
+ maxTokens: 209715,
14073
+ },
14227
14074
  "mistralai/ministral-14b-2512": {
14228
14075
  id: "mistralai/ministral-14b-2512",
14229
14076
  name: "Mistral: Ministral 3 14B 2512",
@@ -14326,6 +14173,23 @@ export const MODELS = {
14326
14173
  contextWindow: 131072,
14327
14174
  maxTokens: 104857,
14328
14175
  },
14176
+ "mistralai/mistral-large-2512": {
14177
+ id: "mistralai/mistral-large-2512",
14178
+ name: "Mistral: Mistral Large 3 2512",
14179
+ api: "openai-completions",
14180
+ provider: "openrouter",
14181
+ baseUrl: "https://openrouter.ai/api/v1",
14182
+ reasoning: false,
14183
+ input: ["text", "image"],
14184
+ cost: {
14185
+ input: 0.5,
14186
+ output: 1.5,
14187
+ cacheRead: 0.049999999999999996,
14188
+ cacheWrite: 0,
14189
+ },
14190
+ contextWindow: 262144,
14191
+ maxTokens: 209715,
14192
+ },
14329
14193
  "mistralai/mistral-large-2512:batch": {
14330
14194
  id: "mistralai/mistral-large-2512:batch",
14331
14195
  name: "Mistral: Mistral Large 3 2512 (batch)",
@@ -14641,9 +14505,9 @@ export const MODELS = {
14641
14505
  reasoning: true,
14642
14506
  input: ["text", "image"],
14643
14507
  cost: {
14644
- input: 0.95,
14645
- output: 4,
14646
- cacheRead: 0.16,
14508
+ input: 0.65,
14509
+ output: 3.41,
14510
+ cacheRead: 0.15,
14647
14511
  cacheWrite: 0,
14648
14512
  },
14649
14513
  contextWindow: 262144,
@@ -14700,35 +14564,18 @@ export const MODELS = {
14700
14564
  contextWindow: 1048576,
14701
14565
  maxTokens: 16384,
14702
14566
  },
14703
- "nex-agi/nex-n2.5-mini:free": {
14704
- id: "nex-agi/nex-n2.5-mini:free",
14705
- name: "Nex AGI: Nex-N2.5-Mini (free)",
14706
- api: "openai-completions",
14707
- provider: "openrouter",
14708
- baseUrl: "https://openrouter.ai/api/v1",
14709
- reasoning: true,
14710
- input: ["text", "image"],
14711
- cost: {
14712
- input: 0,
14713
- output: 0,
14714
- cacheRead: 0,
14715
- cacheWrite: 0,
14716
- },
14717
- contextWindow: 262144,
14718
- maxTokens: 235929,
14719
- },
14720
- "nex-agi/nex-n2.5-pro:free": {
14721
- id: "nex-agi/nex-n2.5-pro:free",
14722
- name: "Nex AGI: Nex-N2.5-Pro (free)",
14567
+ "nex-agi/nex-n2.5-pro": {
14568
+ id: "nex-agi/nex-n2.5-pro",
14569
+ name: "Nex AGI: Nex-N2.5-Pro",
14723
14570
  api: "openai-completions",
14724
14571
  provider: "openrouter",
14725
14572
  baseUrl: "https://openrouter.ai/api/v1",
14726
14573
  reasoning: true,
14727
14574
  input: ["text", "image"],
14728
14575
  cost: {
14729
- input: 0,
14730
- output: 0,
14731
- cacheRead: 0,
14576
+ input: 0.075,
14577
+ output: 0.25,
14578
+ cacheRead: 0.015,
14732
14579
  cacheWrite: 0,
14733
14580
  },
14734
14581
  contextWindow: 262144,
@@ -14850,8 +14697,8 @@ export const MODELS = {
14850
14697
  cacheRead: 0.04,
14851
14698
  cacheWrite: 0,
14852
14699
  },
14853
- contextWindow: 262144,
14854
- maxTokens: 131072,
14700
+ contextWindow: 1000000,
14701
+ maxTokens: 32768,
14855
14702
  },
14856
14703
  "nvidia/nemotron-3.5-lightning:free": {
14857
14704
  id: "nvidia/nemotron-3.5-lightning:free",
@@ -15782,10 +15629,10 @@ export const MODELS = {
15782
15629
  reasoning: true,
15783
15630
  input: ["text", "image"],
15784
15631
  cost: {
15785
- input: 2,
15786
- output: 10,
15787
- cacheRead: 0.19999999999999998,
15788
- cacheWrite: 2.5,
15632
+ input: 4,
15633
+ output: 20,
15634
+ cacheRead: 0.39999999999999997,
15635
+ cacheWrite: 5,
15789
15636
  },
15790
15637
  contextWindow: 1050000,
15791
15638
  maxTokens: 128000,
@@ -16470,6 +16317,23 @@ export const MODELS = {
16470
16317
  contextWindow: 200000,
16471
16318
  maxTokens: 4096,
16472
16319
  },
16320
+ "perceptron/perceptron-mk1.5": {
16321
+ id: "perceptron/perceptron-mk1.5",
16322
+ name: "Perceptron: Perceptron Mk1.5",
16323
+ api: "openai-completions",
16324
+ provider: "openrouter",
16325
+ baseUrl: "https://openrouter.ai/api/v1",
16326
+ reasoning: true,
16327
+ input: ["text", "image"],
16328
+ cost: {
16329
+ input: 0.15,
16330
+ output: 1.5,
16331
+ cacheRead: 0,
16332
+ cacheWrite: 0,
16333
+ },
16334
+ contextWindow: 36864,
16335
+ maxTokens: 8192,
16336
+ },
16473
16337
  "poolside/laguna-s-2.1": {
16474
16338
  id: "poolside/laguna-s-2.1",
16475
16339
  name: "Poolside: Laguna S 2.1",
@@ -16972,13 +16836,13 @@ export const MODELS = {
16972
16836
  reasoning: false,
16973
16837
  input: ["text", "image"],
16974
16838
  cost: {
16975
- input: 0.13,
16976
- output: 0.52,
16839
+ input: 0.15,
16840
+ output: 0.6,
16977
16841
  cacheRead: 0,
16978
16842
  cacheWrite: 0,
16979
16843
  },
16980
16844
  contextWindow: 262144,
16981
- maxTokens: 32768,
16845
+ maxTokens: 16384,
16982
16846
  },
16983
16847
  "qwen/qwen3-vl-30b-a3b-thinking": {
16984
16848
  id: "qwen/qwen3-vl-30b-a3b-thinking",
@@ -17063,7 +16927,7 @@ export const MODELS = {
17063
16927
  cacheWrite: 0,
17064
16928
  },
17065
16929
  contextWindow: 262144,
17066
- maxTokens: 65536,
16930
+ maxTokens: 235929,
17067
16931
  },
17068
16932
  "qwen/qwen3.5-27b": {
17069
16933
  id: "qwen/qwen3.5-27b",
@@ -17091,13 +16955,13 @@ export const MODELS = {
17091
16955
  reasoning: true,
17092
16956
  input: ["text", "image"],
17093
16957
  cost: {
17094
- input: 0.3125,
17095
- output: 1.25,
17096
- cacheRead: 0.15625,
16958
+ input: 0.1625,
16959
+ output: 1.3,
16960
+ cacheRead: 0,
17097
16961
  cacheWrite: 0,
17098
16962
  },
17099
16963
  contextWindow: 262144,
17100
- maxTokens: 16384,
16964
+ maxTokens: 65536,
17101
16965
  },
17102
16966
  "qwen/qwen3.5-397b-a17b": {
17103
16967
  id: "qwen/qwen3.5-397b-a17b",
@@ -17194,12 +17058,12 @@ export const MODELS = {
17194
17058
  input: ["text", "image"],
17195
17059
  cost: {
17196
17060
  input: 0.32,
17197
- output: 2.7,
17198
- cacheRead: 0.15,
17061
+ output: 3.1999999999999997,
17062
+ cacheRead: 0,
17199
17063
  cacheWrite: 0,
17200
17064
  },
17201
17065
  contextWindow: 262144,
17202
- maxTokens: 262140,
17066
+ maxTokens: 81920,
17203
17067
  },
17204
17068
  "qwen/qwen3.6-35b-a3b": {
17205
17069
  id: "qwen/qwen3.6-35b-a3b",
@@ -17618,9 +17482,9 @@ export const MODELS = {
17618
17482
  reasoning: true,
17619
17483
  input: ["text"],
17620
17484
  cost: {
17621
- input: 0.13199999999999998,
17622
- output: 0.5279999999999999,
17623
- cacheRead: 0.032999999999999995,
17485
+ input: 0.0825,
17486
+ output: 0.33,
17487
+ cacheRead: 0.020625,
17624
17488
  cacheWrite: 0,
17625
17489
  },
17626
17490
  contextWindow: 262144,
@@ -17657,7 +17521,7 @@ export const MODELS = {
17657
17521
  cacheRead: 0.16999999999999998,
17658
17522
  cacheWrite: 0,
17659
17523
  },
17660
- contextWindow: 1048576,
17524
+ contextWindow: 524288,
17661
17525
  maxTokens: 471859,
17662
17526
  },
17663
17527
  "thinkingmachines/inkling-small": {
@@ -17674,7 +17538,7 @@ export const MODELS = {
17674
17538
  cacheRead: 0.09999999999999999,
17675
17539
  cacheWrite: 0,
17676
17540
  },
17677
- contextWindow: 1048576,
17541
+ contextWindow: 524288,
17678
17542
  maxTokens: 262144,
17679
17543
  },
17680
17544
  "thinkingmachines/inkling-small:free": {
@@ -17963,7 +17827,7 @@ export const MODELS = {
17963
17827
  cacheRead: 0.0036,
17964
17828
  cacheWrite: 0,
17965
17829
  },
17966
- contextWindow: 1048576,
17830
+ contextWindow: 1050000,
17967
17831
  maxTokens: 131072,
17968
17832
  },
17969
17833
  "xiaomi/mimo-v2.6-pro-ultraspeed": {
@@ -18077,9 +17941,9 @@ export const MODELS = {
18077
17941
  reasoning: true,
18078
17942
  input: ["text"],
18079
17943
  cost: {
18080
- input: 0.39999999999999997,
18081
- output: 1.75,
18082
- cacheRead: 0.08,
17944
+ input: 0.6,
17945
+ output: 2.2,
17946
+ cacheRead: 0.11,
18083
17947
  cacheWrite: 0,
18084
17948
  },
18085
17949
  contextWindow: 204800,
@@ -18145,13 +18009,13 @@ export const MODELS = {
18145
18009
  reasoning: true,
18146
18010
  input: ["text"],
18147
18011
  cost: {
18148
- input: 0.966,
18149
- output: 3.036,
18150
- cacheRead: 0.1794,
18012
+ input: 0.9646,
18013
+ output: 3.0316,
18014
+ cacheRead: 0.17914,
18151
18015
  cacheWrite: 0,
18152
18016
  },
18153
18017
  contextWindow: 204800,
18154
- maxTokens: 128000,
18018
+ maxTokens: 131072,
18155
18019
  },
18156
18020
  "z-ai/glm-5.2": {
18157
18021
  id: "z-ai/glm-5.2",
@@ -18179,13 +18043,13 @@ export const MODELS = {
18179
18043
  reasoning: true,
18180
18044
  input: ["text"],
18181
18045
  cost: {
18182
- input: 0.84,
18183
- output: 2.64,
18184
- cacheRead: 0.156,
18046
+ input: 0.1785,
18047
+ output: 2.8049999999999997,
18048
+ cacheRead: 0.146625,
18185
18049
  cacheWrite: 0,
18186
18050
  },
18187
18051
  contextWindow: 1310720,
18188
- maxTokens: 131072,
18052
+ maxTokens: 943718,
18189
18053
  },
18190
18054
  "z-ai/glm-5.3-flash": {
18191
18055
  id: "z-ai/glm-5.3-flash",
@@ -18198,11 +18062,11 @@ export const MODELS = {
18198
18062
  cost: {
18199
18063
  input: 0.15,
18200
18064
  output: 0.5,
18201
- cacheRead: 0.049999999999999996,
18065
+ cacheRead: 0.03,
18202
18066
  cacheWrite: 0,
18203
18067
  },
18204
18068
  contextWindow: 1310720,
18205
- maxTokens: 943718,
18069
+ maxTokens: 943717,
18206
18070
  },
18207
18071
  "z-ai/glm-5.3-flash:batch": {
18208
18072
  id: "z-ai/glm-5.3-flash:batch",
@@ -18367,8 +18231,8 @@ export const MODELS = {
18367
18231
  reasoning: true,
18368
18232
  input: ["text", "image"],
18369
18233
  cost: {
18370
- input: 0.04,
18371
- output: 1,
18234
+ input: 0.03,
18235
+ output: 0.6,
18372
18236
  cacheRead: 0.01,
18373
18237
  cacheWrite: 0,
18374
18238
  },
@@ -18384,9 +18248,9 @@ export const MODELS = {
18384
18248
  reasoning: true,
18385
18249
  input: ["text"],
18386
18250
  cost: {
18387
- input: 0.39,
18388
- output: 2.9000000000000004,
18389
- cacheRead: 0.25,
18251
+ input: 0.22592,
18252
+ output: 1.9584000000000001,
18253
+ cacheRead: 0.08832,
18390
18254
  cacheWrite: 0,
18391
18255
  },
18392
18256
  contextWindow: 1048576,
@@ -18403,7 +18267,7 @@ export const MODELS = {
18403
18267
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
18404
18268
  input: ["text"],
18405
18269
  cost: {
18406
- input: 0.03,
18270
+ input: 0.020999999999999998,
18407
18271
  output: 0.32,
18408
18272
  cacheRead: 0.016,
18409
18273
  cacheWrite: 0,
@@ -18454,9 +18318,9 @@ export const MODELS = {
18454
18318
  reasoning: true,
18455
18319
  input: ["text", "image"],
18456
18320
  cost: {
18457
- input: 1.4,
18458
- output: 10.75,
18459
- cacheRead: 0.3,
18321
+ input: 0.875,
18322
+ output: 11.2,
18323
+ cacheRead: 0.29,
18460
18324
  cacheWrite: 0,
18461
18325
  },
18462
18326
  contextWindow: 1048576,
@@ -18590,13 +18454,13 @@ export const MODELS = {
18590
18454
  reasoning: true,
18591
18455
  input: ["text"],
18592
18456
  cost: {
18593
- input: 0.5625,
18594
- output: 2.5,
18595
- cacheRead: 0.125,
18457
+ input: 0.1785,
18458
+ output: 2.8049999999999997,
18459
+ cacheRead: 0.146625,
18596
18460
  cacheWrite: 0,
18597
18461
  },
18598
18462
  contextWindow: 1310720,
18599
- maxTokens: 131072,
18463
+ maxTokens: 943718,
18600
18464
  },
18601
18465
  },
18602
18466
  "together": {
@@ -19350,7 +19214,7 @@ export const MODELS = {
19350
19214
  input: ["text", "image"],
19351
19215
  cost: {
19352
19216
  input: 0.39999999999999997,
19353
- output: 2.5,
19217
+ output: 2.4,
19354
19218
  cacheRead: 0.04,
19355
19219
  cacheWrite: 0.5,
19356
19220
  },
@@ -19539,7 +19403,7 @@ export const MODELS = {
19539
19403
  input: 4,
19540
19404
  output: 12,
19541
19405
  cacheRead: 0.5,
19542
- cacheWrite: 0,
19406
+ cacheWrite: 5,
19543
19407
  },
19544
19408
  contextWindow: 1000000,
19545
19409
  maxTokens: 131072,
@@ -19941,6 +19805,23 @@ export const MODELS = {
19941
19805
  contextWindow: 1000000,
19942
19806
  maxTokens: 128000,
19943
19807
  },
19808
+ "anthropic/claude-sonnet-5.5": {
19809
+ id: "anthropic/claude-sonnet-5.5",
19810
+ name: "Claude Sonnet 5.5",
19811
+ api: "anthropic-messages",
19812
+ provider: "vercel-ai-gateway",
19813
+ baseUrl: "https://ai-gateway.vercel.sh",
19814
+ reasoning: true,
19815
+ input: ["text", "image"],
19816
+ cost: {
19817
+ input: 2,
19818
+ output: 10,
19819
+ cacheRead: 0.19999999999999998,
19820
+ cacheWrite: 2.5,
19821
+ },
19822
+ contextWindow: 1000000,
19823
+ maxTokens: 128000,
19824
+ },
19944
19825
  "arcee-ai/trinity-large-thinking": {
19945
19826
  id: "arcee-ai/trinity-large-thinking",
19946
19827
  name: "Trinity Large Thinking",
@@ -20154,9 +20035,9 @@ export const MODELS = {
20154
20035
  reasoning: true,
20155
20036
  input: ["text", "image"],
20156
20037
  cost: {
20157
- input: 0.22,
20158
- output: 0.66,
20159
- cacheRead: 0.007,
20038
+ input: 0.21559999999999999,
20039
+ output: 0.6468,
20040
+ cacheRead: 0.0068,
20160
20041
  cacheWrite: 0,
20161
20042
  },
20162
20043
  contextWindow: 1048576,
@@ -20213,6 +20094,23 @@ export const MODELS = {
20213
20094
  contextWindow: 1048576,
20214
20095
  maxTokens: 32768,
20215
20096
  },
20097
+ "fireworks/ember-1": {
20098
+ id: "fireworks/ember-1",
20099
+ name: "Ember-1",
20100
+ api: "anthropic-messages",
20101
+ provider: "vercel-ai-gateway",
20102
+ baseUrl: "https://ai-gateway.vercel.sh",
20103
+ reasoning: true,
20104
+ input: ["text", "image"],
20105
+ cost: {
20106
+ input: 3,
20107
+ output: 15,
20108
+ cacheRead: 0.3,
20109
+ cacheWrite: 0,
20110
+ },
20111
+ contextWindow: 1048576,
20112
+ maxTokens: 1048576,
20113
+ },
20216
20114
  "google/gemini-2.5-flash": {
20217
20115
  id: "google/gemini-2.5-flash",
20218
20116
  name: "Gemini 2.5 Flash",
@@ -20511,26 +20409,9 @@ export const MODELS = {
20511
20409
  reasoning: true,
20512
20410
  input: ["text"],
20513
20411
  cost: {
20514
- input: 0,
20515
- output: 0,
20516
- cacheRead: 0,
20517
- cacheWrite: 0,
20518
- },
20519
- contextWindow: 256000,
20520
- maxTokens: 32000,
20521
- },
20522
- "inclusionai/ling-3.0-flash-fin-free": {
20523
- id: "inclusionai/ling-3.0-flash-fin-free",
20524
- name: "Ling 3.0 Flash Fin (Free)",
20525
- api: "anthropic-messages",
20526
- provider: "vercel-ai-gateway",
20527
- baseUrl: "https://ai-gateway.vercel.sh",
20528
- reasoning: true,
20529
- input: ["text"],
20530
- cost: {
20531
- input: 0,
20532
- output: 0,
20533
- cacheRead: 0,
20412
+ input: 0.06,
20413
+ output: 0.18,
20414
+ cacheRead: 0.012,
20534
20415
  cacheWrite: 0,
20535
20416
  },
20536
20417
  contextWindow: 256000,
@@ -20604,6 +20485,23 @@ export const MODELS = {
20604
20485
  contextWindow: 1000000,
20605
20486
  maxTokens: 32000,
20606
20487
  },
20488
+ "meituan/longcat-2.5-preview": {
20489
+ id: "meituan/longcat-2.5-preview",
20490
+ name: "LongCat 2.5 Preview",
20491
+ api: "anthropic-messages",
20492
+ provider: "vercel-ai-gateway",
20493
+ baseUrl: "https://ai-gateway.vercel.sh",
20494
+ reasoning: true,
20495
+ input: ["text", "image"],
20496
+ cost: {
20497
+ input: 0.3,
20498
+ output: 1.2,
20499
+ cacheRead: 0.006,
20500
+ cacheWrite: 0,
20501
+ },
20502
+ contextWindow: 1048576,
20503
+ maxTokens: 131072,
20504
+ },
20607
20505
  "meta/llama-3.1-70b": {
20608
20506
  id: "meta/llama-3.1-70b",
20609
20507
  name: "Llama 3.1 70B Instruct",
@@ -21159,7 +21057,7 @@ export const MODELS = {
21159
21057
  cost: {
21160
21058
  input: 0.95,
21161
21059
  output: 4,
21162
- cacheRead: 0.16,
21060
+ cacheRead: 0.19,
21163
21061
  cacheWrite: 0,
21164
21062
  },
21165
21063
  contextWindow: 256000,
@@ -22702,9 +22600,9 @@ export const MODELS = {
22702
22600
  reasoning: true,
22703
22601
  input: ["text", "image"],
22704
22602
  cost: {
22705
- input: 1.2,
22706
- output: 3.5999999999999996,
22707
- cacheRead: 0.3,
22603
+ input: 2,
22604
+ output: 6,
22605
+ cacheRead: 0.5,
22708
22606
  cacheWrite: 0,
22709
22607
  },
22710
22608
  contextWindow: 500000,
@@ -22821,7 +22719,7 @@ export const MODELS = {
22821
22719
  reasoning: true,
22822
22720
  input: ["text", "image"],
22823
22721
  cost: {
22824
- input: 0.5,
22722
+ input: 0.44999999999999996,
22825
22723
  output: 1.2,
22826
22724
  cacheRead: 0.09999999999999999,
22827
22725
  cacheWrite: 0,
@@ -22993,7 +22891,7 @@ export const MODELS = {
22993
22891
  cost: {
22994
22892
  input: 0.6,
22995
22893
  output: 2.2,
22996
- cacheRead: 0.12,
22894
+ cacheRead: 0,
22997
22895
  cacheWrite: 0,
22998
22896
  },
22999
22897
  contextWindow: 200000,
@@ -23110,9 +23008,9 @@ export const MODELS = {
23110
23008
  reasoning: true,
23111
23009
  input: ["text"],
23112
23010
  cost: {
23113
- input: 2.0999999999999996,
23114
- output: 6.6000000000000005,
23115
- cacheRead: 0.21,
23011
+ input: 2.8,
23012
+ output: 8.8,
23013
+ cacheRead: 0.56,
23116
23014
  cacheWrite: 0,
23117
23015
  },
23118
23016
  contextWindow: 1000000,