@elyracode/ai 0.9.33 → 0.9.35

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.
@@ -89,6 +89,25 @@ export const MODELS = {
89
89
  contextWindow: 1000000,
90
90
  maxTokens: 128000,
91
91
  },
92
+ "anthropic.claude-fable-5-1": {
93
+ id: "anthropic.claude-fable-5-1",
94
+ name: "Claude Fable 5.1",
95
+ api: "bedrock-converse-stream",
96
+ provider: "amazon-bedrock",
97
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
98
+ reasoning: true,
99
+ thinkingType: "adaptive",
100
+ thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
101
+ input: ["text", "image"],
102
+ cost: {
103
+ input: 10,
104
+ output: 50,
105
+ cacheRead: 0.25,
106
+ cacheWrite: 12.5,
107
+ },
108
+ contextWindow: 1000000,
109
+ maxTokens: 128000,
110
+ },
92
111
  "anthropic.claude-haiku-4-5-20251001-v1:0": {
93
112
  id: "anthropic.claude-haiku-4-5-20251001-v1:0",
94
113
  name: "Claude Haiku 4.5",
@@ -654,6 +673,25 @@ export const MODELS = {
654
673
  contextWindow: 1000000,
655
674
  maxTokens: 128000,
656
675
  },
676
+ "global.anthropic.claude-fable-5-1": {
677
+ id: "global.anthropic.claude-fable-5-1",
678
+ name: "Claude Fable 5.1 (Global)",
679
+ api: "bedrock-converse-stream",
680
+ provider: "amazon-bedrock",
681
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
682
+ reasoning: true,
683
+ thinkingType: "adaptive",
684
+ thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
685
+ input: ["text", "image"],
686
+ cost: {
687
+ input: 10,
688
+ output: 50,
689
+ cacheRead: 0.25,
690
+ cacheWrite: 12.5,
691
+ },
692
+ contextWindow: 1000000,
693
+ maxTokens: 128000,
694
+ },
657
695
  "global.anthropic.claude-haiku-4-5-20251001-v1:0": {
658
696
  id: "global.anthropic.claude-haiku-4-5-20251001-v1:0",
659
697
  name: "Claude Haiku 4.5 (Global)",
@@ -1750,6 +1788,25 @@ export const MODELS = {
1750
1788
  contextWindow: 1000000,
1751
1789
  maxTokens: 128000,
1752
1790
  },
1791
+ "us.anthropic.claude-fable-5-1": {
1792
+ id: "us.anthropic.claude-fable-5-1",
1793
+ name: "Claude Fable 5.1 (US)",
1794
+ api: "bedrock-converse-stream",
1795
+ provider: "amazon-bedrock",
1796
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1797
+ reasoning: true,
1798
+ thinkingType: "adaptive",
1799
+ thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
1800
+ input: ["text", "image"],
1801
+ cost: {
1802
+ input: 11,
1803
+ output: 55,
1804
+ cacheRead: 0.275,
1805
+ cacheWrite: 13.75,
1806
+ },
1807
+ contextWindow: 1000000,
1808
+ maxTokens: 128000,
1809
+ },
1753
1810
  "us.anthropic.claude-haiku-4-5-20251001-v1:0": {
1754
1811
  id: "us.anthropic.claude-haiku-4-5-20251001-v1:0",
1755
1812
  name: "Claude Haiku 4.5 (US)",
@@ -2124,6 +2181,25 @@ export const MODELS = {
2124
2181
  contextWindow: 1000000,
2125
2182
  maxTokens: 128000,
2126
2183
  },
2184
+ "claude-fable-5-1": {
2185
+ id: "claude-fable-5-1",
2186
+ name: "Claude Fable 5.1",
2187
+ api: "anthropic-messages",
2188
+ provider: "anthropic",
2189
+ baseUrl: "https://api.anthropic.com",
2190
+ reasoning: true,
2191
+ thinkingType: "adaptive",
2192
+ thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
2193
+ input: ["text", "image"],
2194
+ cost: {
2195
+ input: 10,
2196
+ output: 50,
2197
+ cacheRead: 0.25,
2198
+ cacheWrite: 12.5,
2199
+ },
2200
+ contextWindow: 1000000,
2201
+ maxTokens: 128000,
2202
+ },
2127
2203
  "claude-haiku-4-5": {
2128
2204
  id: "claude-haiku-4-5",
2129
2205
  name: "Claude Haiku 4.5 (latest)",
@@ -3906,7 +3982,7 @@ export const MODELS = {
3906
3982
  cacheWrite: 0,
3907
3983
  },
3908
3984
  contextWindow: 1310720,
3909
- maxTokens: 1310720,
3985
+ maxTokens: 1048576,
3910
3986
  },
3911
3987
  },
3912
3988
  "deepseek": {
@@ -3959,9 +4035,26 @@ export const MODELS = {
3959
4035
  reasoning: true,
3960
4036
  input: ["text"],
3961
4037
  cost: {
3962
- input: 0.14,
3963
- output: 0.28,
3964
- cacheRead: 0.028,
4038
+ input: 0.22,
4039
+ output: 0.66,
4040
+ cacheRead: 0.007,
4041
+ cacheWrite: 0,
4042
+ },
4043
+ contextWindow: 1000000,
4044
+ maxTokens: 384000,
4045
+ },
4046
+ "accounts/fireworks/models/deepseek-v4-flash-vision-exp": {
4047
+ id: "accounts/fireworks/models/deepseek-v4-flash-vision-exp",
4048
+ name: "DeepSeek V4 Flash Vision Exp",
4049
+ api: "anthropic-messages",
4050
+ provider: "fireworks",
4051
+ baseUrl: "https://api.fireworks.ai/inference",
4052
+ reasoning: true,
4053
+ input: ["text", "image"],
4054
+ cost: {
4055
+ input: 0.22,
4056
+ output: 0.66,
4057
+ cacheRead: 0.007,
3965
4058
  cacheWrite: 0,
3966
4059
  },
3967
4060
  contextWindow: 1000000,
@@ -4018,6 +4111,23 @@ export const MODELS = {
4018
4111
  contextWindow: 1000000,
4019
4112
  maxTokens: 131072,
4020
4113
  },
4114
+ "accounts/fireworks/models/glm-5p3-flash": {
4115
+ id: "accounts/fireworks/models/glm-5p3-flash",
4116
+ name: "GLM 5.3 Flash",
4117
+ api: "anthropic-messages",
4118
+ provider: "fireworks",
4119
+ baseUrl: "https://api.fireworks.ai/inference",
4120
+ reasoning: true,
4121
+ input: ["text", "image"],
4122
+ cost: {
4123
+ input: 0.15,
4124
+ output: 0.5,
4125
+ cacheRead: 0.03,
4126
+ cacheWrite: 0,
4127
+ },
4128
+ contextWindow: 1000000,
4129
+ maxTokens: 131072,
4130
+ },
4021
4131
  "accounts/fireworks/models/gpt-oss-120b": {
4022
4132
  id: "accounts/fireworks/models/gpt-oss-120b",
4023
4133
  name: "GPT OSS 120B",
@@ -5169,13 +5279,14 @@ export const MODELS = {
5169
5279
  contextWindow: 1048576,
5170
5280
  maxTokens: 65536,
5171
5281
  },
5172
- "gemini-flash-latest": {
5173
- id: "gemini-flash-latest",
5174
- name: "Gemini Flash Latest",
5282
+ "gemini-3.8-flash": {
5283
+ id: "gemini-3.8-flash",
5284
+ name: "Gemini 3.8 Flash",
5175
5285
  api: "google-generative-ai",
5176
5286
  provider: "google",
5177
5287
  baseUrl: "https://generativelanguage.googleapis.com/v1beta",
5178
5288
  reasoning: true,
5289
+ thinkingLevelMap: { "off": null },
5179
5290
  input: ["text", "image"],
5180
5291
  cost: {
5181
5292
  input: 0.75,
@@ -5186,38 +5297,38 @@ export const MODELS = {
5186
5297
  contextWindow: 1048576,
5187
5298
  maxTokens: 65536,
5188
5299
  },
5189
- "gemini-flash-lite-latest": {
5190
- id: "gemini-flash-lite-latest",
5191
- name: "Gemini Flash-Lite Latest",
5300
+ "gemini-flash-latest": {
5301
+ id: "gemini-flash-latest",
5302
+ name: "Gemini Flash Latest",
5192
5303
  api: "google-generative-ai",
5193
5304
  provider: "google",
5194
5305
  baseUrl: "https://generativelanguage.googleapis.com/v1beta",
5195
5306
  reasoning: true,
5196
5307
  input: ["text", "image"],
5197
5308
  cost: {
5198
- input: 0.3,
5199
- output: 2.5,
5200
- cacheRead: 0.03,
5309
+ input: 0.75,
5310
+ output: 3.75,
5311
+ cacheRead: 0.075,
5201
5312
  cacheWrite: 0,
5202
5313
  },
5203
5314
  contextWindow: 1048576,
5204
5315
  maxTokens: 65536,
5205
5316
  },
5206
- "gemini-robotics-er-1.6-preview": {
5207
- id: "gemini-robotics-er-1.6-preview",
5208
- name: "Gemini Robotics-ER 1.6 Preview",
5317
+ "gemini-flash-lite-latest": {
5318
+ id: "gemini-flash-lite-latest",
5319
+ name: "Gemini Flash-Lite Latest",
5209
5320
  api: "google-generative-ai",
5210
5321
  provider: "google",
5211
5322
  baseUrl: "https://generativelanguage.googleapis.com/v1beta",
5212
5323
  reasoning: true,
5213
5324
  input: ["text", "image"],
5214
5325
  cost: {
5215
- input: 1,
5216
- output: 5,
5217
- cacheRead: 0,
5326
+ input: 0.3,
5327
+ output: 2.5,
5328
+ cacheRead: 0.03,
5218
5329
  cacheWrite: 0,
5219
5330
  },
5220
- contextWindow: 131072,
5331
+ contextWindow: 1048576,
5221
5332
  maxTokens: 65536,
5222
5333
  },
5223
5334
  "gemma-4-26b-a4b-it": {
@@ -5587,6 +5698,23 @@ export const MODELS = {
5587
5698
  contextWindow: 131072,
5588
5699
  maxTokens: 16384,
5589
5700
  },
5701
+ "qwen/qwen3.8-27b": {
5702
+ id: "qwen/qwen3.8-27b",
5703
+ name: "Qwen3.8 27B",
5704
+ api: "openai-completions",
5705
+ provider: "groq",
5706
+ baseUrl: "https://api.groq.com/openai/v1",
5707
+ reasoning: true,
5708
+ input: ["text", "image"],
5709
+ cost: {
5710
+ input: 0.8,
5711
+ output: 4,
5712
+ cacheRead: 0,
5713
+ cacheWrite: 0,
5714
+ },
5715
+ contextWindow: 131042,
5716
+ maxTokens: 16384,
5717
+ },
5590
5718
  },
5591
5719
  "huggingface": {
5592
5720
  "MiniMaxAI/MiniMax-M2": {
@@ -6255,6 +6383,24 @@ export const MODELS = {
6255
6383
  contextWindow: 1048576,
6256
6384
  maxTokens: 384000,
6257
6385
  },
6386
+ "deepseek-ai/DeepSeek-V4-Flash-Vision-Exp": {
6387
+ id: "deepseek-ai/DeepSeek-V4-Flash-Vision-Exp",
6388
+ name: "DeepSeek V4 Flash Vision Exp",
6389
+ api: "openai-completions",
6390
+ provider: "huggingface",
6391
+ baseUrl: "https://router.huggingface.co/v1",
6392
+ compat: { "supportsDeveloperRole": false },
6393
+ reasoning: true,
6394
+ input: ["text", "image"],
6395
+ cost: {
6396
+ input: 0.44,
6397
+ output: 1.32,
6398
+ cacheRead: 0,
6399
+ cacheWrite: 0,
6400
+ },
6401
+ contextWindow: 1048576,
6402
+ maxTokens: 384000,
6403
+ },
6258
6404
  "deepseek-ai/DeepSeek-V4-Pro": {
6259
6405
  id: "deepseek-ai/DeepSeek-V4-Pro",
6260
6406
  name: "DeepSeek V4 Pro",
@@ -6577,7 +6723,7 @@ export const MODELS = {
6577
6723
  cacheWrite: 0,
6578
6724
  },
6579
6725
  contextWindow: 262144,
6580
- maxTokens: 64000,
6726
+ maxTokens: 128000,
6581
6727
  },
6582
6728
  "thinkingmachines/Inkling": {
6583
6729
  id: "thinkingmachines/Inkling",
@@ -8793,6 +8939,24 @@ export const MODELS = {
8793
8939
  contextWindow: 1000000,
8794
8940
  maxTokens: 128000,
8795
8941
  },
8942
+ "claude-fable-5-1": {
8943
+ id: "claude-fable-5-1",
8944
+ name: "Claude Fable 5.1",
8945
+ api: "anthropic-messages",
8946
+ provider: "opencode",
8947
+ baseUrl: "https://opencode.ai/zen",
8948
+ reasoning: true,
8949
+ thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
8950
+ input: ["text", "image"],
8951
+ cost: {
8952
+ input: 10,
8953
+ output: 50,
8954
+ cacheRead: 0.25,
8955
+ cacheWrite: 12.5,
8956
+ },
8957
+ contextWindow: 1000000,
8958
+ maxTokens: 128000,
8959
+ },
8796
8960
  "claude-haiku-4-5": {
8797
8961
  id: "claude-haiku-4-5",
8798
8962
  name: "Claude Haiku 4.5",
@@ -9112,6 +9276,24 @@ export const MODELS = {
9112
9276
  contextWindow: 1048576,
9113
9277
  maxTokens: 65536,
9114
9278
  },
9279
+ "gemini-3.8-flash": {
9280
+ id: "gemini-3.8-flash",
9281
+ name: "Gemini 3.8 Flash",
9282
+ api: "google-generative-ai",
9283
+ provider: "opencode",
9284
+ baseUrl: "https://opencode.ai/zen/v1",
9285
+ reasoning: true,
9286
+ thinkingLevelMap: { "off": null },
9287
+ input: ["text", "image"],
9288
+ cost: {
9289
+ input: 1.5,
9290
+ output: 7.5,
9291
+ cacheRead: 0.15,
9292
+ cacheWrite: 0,
9293
+ },
9294
+ contextWindow: 1048576,
9295
+ maxTokens: 65536,
9296
+ },
9115
9297
  "glm-5": {
9116
9298
  id: "glm-5",
9117
9299
  name: "GLM-5",
@@ -9556,23 +9738,6 @@ export const MODELS = {
9556
9738
  contextWindow: 256000,
9557
9739
  maxTokens: 256000,
9558
9740
  },
9559
- "hy3-free": {
9560
- id: "hy3-free",
9561
- name: "Hy3 Free",
9562
- api: "openai-completions",
9563
- provider: "opencode",
9564
- baseUrl: "https://opencode.ai/zen/v1",
9565
- reasoning: true,
9566
- input: ["text"],
9567
- cost: {
9568
- input: 0,
9569
- output: 0,
9570
- cacheRead: 0,
9571
- cacheWrite: 0,
9572
- },
9573
- contextWindow: 190000,
9574
- maxTokens: 64000,
9575
- },
9576
9741
  "kimi-k2.5": {
9577
9742
  id: "kimi-k2.5",
9578
9743
  name: "Kimi K2.5",
@@ -9760,6 +9925,23 @@ export const MODELS = {
9760
9925
  contextWindow: 1048576,
9761
9926
  maxTokens: 131072,
9762
9927
  },
9928
+ "muse-spark-1.3-contributor-free": {
9929
+ id: "muse-spark-1.3-contributor-free",
9930
+ name: "Muse Spark 1.3 Free",
9931
+ api: "openai-responses",
9932
+ provider: "opencode",
9933
+ baseUrl: "https://opencode.ai/zen/v1",
9934
+ reasoning: true,
9935
+ input: ["text", "image"],
9936
+ cost: {
9937
+ input: 0,
9938
+ output: 0,
9939
+ cacheRead: 0,
9940
+ cacheWrite: 0,
9941
+ },
9942
+ contextWindow: 1048576,
9943
+ maxTokens: 131072,
9944
+ },
9763
9945
  "nemotron-3-ultra-free": {
9764
9946
  id: "nemotron-3-ultra-free",
9765
9947
  name: "Nemotron 3 Ultra Free",
@@ -9992,20 +10174,20 @@ export const MODELS = {
9992
10174
  },
9993
10175
  "hy3": {
9994
10176
  id: "hy3",
9995
- name: "Hy3 (8x usage)",
10177
+ name: "Hy3",
9996
10178
  api: "openai-completions",
9997
10179
  provider: "opencode-go",
9998
10180
  baseUrl: "https://opencode.ai/zen/go/v1",
9999
10181
  reasoning: true,
10000
10182
  input: ["text"],
10001
10183
  cost: {
10002
- input: 0.0175,
10003
- output: 0.0725,
10004
- cacheRead: 0.004375,
10184
+ input: 0.14,
10185
+ output: 0.58,
10186
+ cacheRead: 0.035,
10005
10187
  cacheWrite: 0,
10006
10188
  },
10007
10189
  contextWindow: 256000,
10008
- maxTokens: 64000,
10190
+ maxTokens: 128000,
10009
10191
  },
10010
10192
  "hy4-preview": {
10011
10193
  id: "hy4-preview",
@@ -10177,6 +10359,23 @@ export const MODELS = {
10177
10359
  contextWindow: 1048576,
10178
10360
  maxTokens: 131072,
10179
10361
  },
10362
+ "muse-spark-1.3-contributor": {
10363
+ id: "muse-spark-1.3-contributor",
10364
+ name: "Muse Spark 1.3 Contributor",
10365
+ api: "openai-responses",
10366
+ provider: "opencode-go",
10367
+ baseUrl: "https://opencode.ai/zen/go/v1",
10368
+ reasoning: true,
10369
+ input: ["text", "image"],
10370
+ cost: {
10371
+ input: 0.1,
10372
+ output: 0.2,
10373
+ cacheRead: 0.002,
10374
+ cacheWrite: 0,
10375
+ },
10376
+ contextWindow: 1048576,
10377
+ maxTokens: 131072,
10378
+ },
10180
10379
  "qwen3.6-plus": {
10181
10380
  id: "qwen3.6-plus",
10182
10381
  name: "Qwen3.6 Plus",
@@ -10436,9 +10635,9 @@ export const MODELS = {
10436
10635
  contextWindow: 1000000,
10437
10636
  maxTokens: 128000,
10438
10637
  },
10439
- "anthropic/claude-fable-5:batch": {
10440
- id: "anthropic/claude-fable-5:batch",
10441
- name: "Anthropic: Claude Fable 5 (batch)",
10638
+ "anthropic/claude-fable-5.1": {
10639
+ id: "anthropic/claude-fable-5.1",
10640
+ name: "Anthropic: Claude Fable 5.1",
10442
10641
  api: "openai-completions",
10443
10642
  provider: "openrouter",
10444
10643
  baseUrl: "https://openrouter.ai/api/v1",
@@ -10446,24 +10645,60 @@ export const MODELS = {
10446
10645
  thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
10447
10646
  input: ["text", "image"],
10448
10647
  cost: {
10449
- input: 5,
10450
- output: 25,
10451
- cacheRead: 0.5,
10452
- cacheWrite: 6.25,
10648
+ input: 10,
10649
+ output: 50,
10650
+ cacheRead: 0.25,
10651
+ cacheWrite: 12.5,
10453
10652
  },
10454
10653
  contextWindow: 1000000,
10455
10654
  maxTokens: 128000,
10456
10655
  },
10457
- "anthropic/claude-haiku-4.5": {
10458
- id: "anthropic/claude-haiku-4.5",
10459
- name: "Anthropic: Claude Haiku 4.5",
10656
+ "anthropic/claude-fable-5.1:batch": {
10657
+ id: "anthropic/claude-fable-5.1:batch",
10658
+ name: "Anthropic: Claude Fable 5.1 (batch)",
10460
10659
  api: "openai-completions",
10461
10660
  provider: "openrouter",
10462
10661
  baseUrl: "https://openrouter.ai/api/v1",
10463
10662
  reasoning: true,
10663
+ thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
10464
10664
  input: ["text", "image"],
10465
10665
  cost: {
10466
- input: 1,
10666
+ input: 5,
10667
+ output: 25,
10668
+ cacheRead: 0.125,
10669
+ cacheWrite: 6.25,
10670
+ },
10671
+ contextWindow: 1000000,
10672
+ maxTokens: 128000,
10673
+ },
10674
+ "anthropic/claude-fable-5:batch": {
10675
+ id: "anthropic/claude-fable-5:batch",
10676
+ name: "Anthropic: Claude Fable 5 (batch)",
10677
+ api: "openai-completions",
10678
+ provider: "openrouter",
10679
+ baseUrl: "https://openrouter.ai/api/v1",
10680
+ reasoning: true,
10681
+ thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
10682
+ input: ["text", "image"],
10683
+ cost: {
10684
+ input: 5,
10685
+ output: 25,
10686
+ cacheRead: 0.5,
10687
+ cacheWrite: 6.25,
10688
+ },
10689
+ contextWindow: 1000000,
10690
+ maxTokens: 128000,
10691
+ },
10692
+ "anthropic/claude-haiku-4.5": {
10693
+ id: "anthropic/claude-haiku-4.5",
10694
+ name: "Anthropic: Claude Haiku 4.5",
10695
+ api: "openai-completions",
10696
+ provider: "openrouter",
10697
+ baseUrl: "https://openrouter.ai/api/v1",
10698
+ reasoning: true,
10699
+ input: ["text", "image"],
10700
+ cost: {
10701
+ input: 1,
10467
10702
  output: 5,
10468
10703
  cacheRead: 0.09999999999999999,
10469
10704
  cacheWrite: 1.25,
@@ -10627,24 +10862,6 @@ export const MODELS = {
10627
10862
  contextWindow: 1000000,
10628
10863
  maxTokens: 128000,
10629
10864
  },
10630
- "anthropic/claude-opus-4.7-fast": {
10631
- id: "anthropic/claude-opus-4.7-fast",
10632
- name: "Anthropic: Claude Opus 4.7 (Fast)",
10633
- api: "openai-completions",
10634
- provider: "openrouter",
10635
- baseUrl: "https://openrouter.ai/api/v1",
10636
- reasoning: true,
10637
- thinkingLevelMap: { "xhigh": "xhigh" },
10638
- input: ["text", "image"],
10639
- cost: {
10640
- input: 30,
10641
- output: 150,
10642
- cacheRead: 3,
10643
- cacheWrite: 37.5,
10644
- },
10645
- contextWindow: 1000000,
10646
- maxTokens: 128000,
10647
- },
10648
10865
  "anthropic/claude-opus-4.7:batch": {
10649
10866
  id: "anthropic/claude-opus-4.7:batch",
10650
10867
  name: "Anthropic: Claude Opus 4.7 (batch)",
@@ -10681,24 +10898,6 @@ export const MODELS = {
10681
10898
  contextWindow: 1000000,
10682
10899
  maxTokens: 128000,
10683
10900
  },
10684
- "anthropic/claude-opus-4.8-fast": {
10685
- id: "anthropic/claude-opus-4.8-fast",
10686
- name: "Anthropic: Claude Opus 4.8 (Fast)",
10687
- api: "openai-completions",
10688
- provider: "openrouter",
10689
- baseUrl: "https://openrouter.ai/api/v1",
10690
- reasoning: true,
10691
- thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "max", "xhigh": "ultracode" },
10692
- input: ["text", "image"],
10693
- cost: {
10694
- input: 10,
10695
- output: 50,
10696
- cacheRead: 1,
10697
- cacheWrite: 12.5,
10698
- },
10699
- contextWindow: 1000000,
10700
- maxTokens: 128000,
10701
- },
10702
10901
  "anthropic/claude-opus-4.8:batch": {
10703
10902
  id: "anthropic/claude-opus-4.8:batch",
10704
10903
  name: "Anthropic: Claude Opus 4.8 (batch)",
@@ -10734,23 +10933,6 @@ export const MODELS = {
10734
10933
  contextWindow: 1000000,
10735
10934
  maxTokens: 128000,
10736
10935
  },
10737
- "anthropic/claude-opus-5-fast": {
10738
- id: "anthropic/claude-opus-5-fast",
10739
- name: "Claude Opus 5 (Fast)",
10740
- api: "openai-completions",
10741
- provider: "openrouter",
10742
- baseUrl: "https://openrouter.ai/api/v1",
10743
- reasoning: true,
10744
- input: ["text", "image"],
10745
- cost: {
10746
- input: 10,
10747
- output: 50,
10748
- cacheRead: 1,
10749
- cacheWrite: 12.5,
10750
- },
10751
- contextWindow: 1000000,
10752
- maxTokens: 128000,
10753
- },
10754
10936
  "anthropic/claude-opus-5:batch": {
10755
10937
  id: "anthropic/claude-opus-5:batch",
10756
10938
  name: "Claude Opus 5 (batch)",
@@ -10896,13 +11078,13 @@ export const MODELS = {
10896
11078
  reasoning: true,
10897
11079
  input: ["text"],
10898
11080
  cost: {
10899
- input: 0.22,
10900
- output: 0.85,
11081
+ input: 0.25,
11082
+ output: 0.7999999999999999,
10901
11083
  cacheRead: 0.06,
10902
11084
  cacheWrite: 0,
10903
11085
  },
10904
11086
  contextWindow: 262144,
10905
- maxTokens: 235929,
11087
+ maxTokens: 80000,
10906
11088
  },
10907
11089
  "auto": {
10908
11090
  id: "auto",
@@ -11083,13 +11265,13 @@ export const MODELS = {
11083
11265
  reasoning: false,
11084
11266
  input: ["text"],
11085
11267
  cost: {
11086
- input: 0.2574,
11087
- output: 1.0287,
11268
+ input: 0.32,
11269
+ output: 0.8899999999999999,
11088
11270
  cacheRead: 0,
11089
11271
  cacheWrite: 0,
11090
11272
  },
11091
11273
  contextWindow: 163840,
11092
- maxTokens: 16000,
11274
+ maxTokens: 16384,
11093
11275
  },
11094
11276
  "deepseek/deepseek-chat-v3-0324": {
11095
11277
  id: "deepseek/deepseek-chat-v3-0324",
@@ -11221,9 +11403,9 @@ export const MODELS = {
11221
11403
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
11222
11404
  input: ["text"],
11223
11405
  cost: {
11224
- input: 0.08316,
11225
- output: 0.16632,
11226
- cacheRead: 0.016632,
11406
+ input: 0.07784,
11407
+ output: 0.15568,
11408
+ cacheRead: 0.015568,
11227
11409
  cacheWrite: 0,
11228
11410
  },
11229
11411
  contextWindow: 1048576,
@@ -11240,9 +11422,9 @@ export const MODELS = {
11240
11422
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
11241
11423
  input: ["text"],
11242
11424
  cost: {
11243
- input: 0.045,
11244
- output: 0.09,
11245
- cacheRead: 0.009,
11425
+ input: 0.065,
11426
+ output: 0.18,
11427
+ cacheRead: 0.016,
11246
11428
  cacheWrite: 0,
11247
11429
  },
11248
11430
  contextWindow: 1310720,
@@ -11297,9 +11479,9 @@ export const MODELS = {
11297
11479
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
11298
11480
  input: ["text"],
11299
11481
  cost: {
11300
- input: 0.57942,
11301
- output: 1.15884,
11302
- cacheRead: 0.048285,
11482
+ input: 1.030776,
11483
+ output: 2.061552,
11484
+ cacheRead: 0.085898,
11303
11485
  cacheWrite: 0,
11304
11486
  },
11305
11487
  contextWindow: 1048576,
@@ -11777,10 +11959,44 @@ export const MODELS = {
11777
11959
  reasoning: true,
11778
11960
  input: ["text", "image"],
11779
11961
  cost: {
11780
- input: 0.1875,
11781
- output: 0.9375,
11782
- cacheRead: 0.01875,
11783
- cacheWrite: 0.0208333333333333,
11962
+ input: 0.375,
11963
+ output: 1.875,
11964
+ cacheRead: 0.0375,
11965
+ cacheWrite: 0.0416666666666667,
11966
+ },
11967
+ contextWindow: 1048576,
11968
+ maxTokens: 65536,
11969
+ },
11970
+ "google/gemini-3.8-flash": {
11971
+ id: "google/gemini-3.8-flash",
11972
+ name: "Google: Gemini 3.8 Flash",
11973
+ api: "openai-completions",
11974
+ provider: "openrouter",
11975
+ baseUrl: "https://openrouter.ai/api/v1",
11976
+ reasoning: true,
11977
+ input: ["text", "image"],
11978
+ cost: {
11979
+ input: 0.75,
11980
+ output: 3.75,
11981
+ cacheRead: 0.075,
11982
+ cacheWrite: 0.0416666666666667,
11983
+ },
11984
+ contextWindow: 1048576,
11985
+ maxTokens: 65536,
11986
+ },
11987
+ "google/gemini-3.8-flash:batch": {
11988
+ id: "google/gemini-3.8-flash:batch",
11989
+ name: "Google: Gemini 3.8 Flash (batch)",
11990
+ api: "openai-completions",
11991
+ provider: "openrouter",
11992
+ baseUrl: "https://openrouter.ai/api/v1",
11993
+ reasoning: true,
11994
+ input: ["text", "image"],
11995
+ cost: {
11996
+ input: 0.375,
11997
+ output: 1.875,
11998
+ cacheRead: 0.0375,
11999
+ cacheWrite: 0.0416666666666667,
11784
12000
  },
11785
12001
  contextWindow: 1048576,
11786
12002
  maxTokens: 65536,
@@ -11921,6 +12137,23 @@ export const MODELS = {
11921
12137
  contextWindow: 131072,
11922
12138
  maxTokens: 117964,
11923
12139
  },
12140
+ "ibm-granite/granite-4.2-8b": {
12141
+ id: "ibm-granite/granite-4.2-8b",
12142
+ name: "IBM: Granite 4.2 8B",
12143
+ api: "openai-completions",
12144
+ provider: "openrouter",
12145
+ baseUrl: "https://openrouter.ai/api/v1",
12146
+ reasoning: true,
12147
+ input: ["text"],
12148
+ cost: {
12149
+ input: 0.09999999999999999,
12150
+ output: 0.15,
12151
+ cacheRead: 0.049999999999999996,
12152
+ cacheWrite: 0,
12153
+ },
12154
+ contextWindow: 131072,
12155
+ maxTokens: 117964,
12156
+ },
11924
12157
  "inception/mercury-2": {
11925
12158
  id: "inception/mercury-2",
11926
12159
  name: "Inception: Mercury 2",
@@ -11938,6 +12171,23 @@ export const MODELS = {
11938
12171
  contextWindow: 128000,
11939
12172
  maxTokens: 50000,
11940
12173
  },
12174
+ "inception/mercury-2.5-preview": {
12175
+ id: "inception/mercury-2.5-preview",
12176
+ name: "Inception: Mercury 2.5 Preview",
12177
+ api: "openai-completions",
12178
+ provider: "openrouter",
12179
+ baseUrl: "https://openrouter.ai/api/v1",
12180
+ reasoning: true,
12181
+ input: ["text"],
12182
+ cost: {
12183
+ input: 0.04,
12184
+ output: 0.15,
12185
+ cacheRead: 0.004,
12186
+ cacheWrite: 0,
12187
+ },
12188
+ contextWindow: 260000,
12189
+ maxTokens: 65536,
12190
+ },
11941
12191
  "inclusionai/ling-3.0-flash": {
11942
12192
  id: "inclusionai/ling-3.0-flash",
11943
12193
  name: "Ling-3.0-flash",
@@ -11955,39 +12205,39 @@ export const MODELS = {
11955
12205
  contextWindow: 262144,
11956
12206
  maxTokens: 32768,
11957
12207
  },
11958
- "inclusionai/ling-3.0-flash-fin:free": {
11959
- id: "inclusionai/ling-3.0-flash-fin:free",
11960
- name: "Ling 3.0 Flash Fin (free)",
12208
+ "inclusionai/ling-3.0-flash-fin": {
12209
+ id: "inclusionai/ling-3.0-flash-fin",
12210
+ name: "Ling 3.0 Flash Fin",
11961
12211
  api: "openai-completions",
11962
12212
  provider: "openrouter",
11963
12213
  baseUrl: "https://openrouter.ai/api/v1",
11964
12214
  reasoning: true,
11965
12215
  input: ["text"],
11966
12216
  cost: {
11967
- input: 0,
11968
- output: 0,
11969
- cacheRead: 0,
12217
+ input: 0.06,
12218
+ output: 0.18,
12219
+ cacheRead: 0.012,
11970
12220
  cacheWrite: 0,
11971
12221
  },
11972
12222
  contextWindow: 262144,
11973
- maxTokens: 32768,
12223
+ maxTokens: 235929,
11974
12224
  },
11975
- "kwaipilot/kat-coder-air-v2.5": {
11976
- id: "kwaipilot/kat-coder-air-v2.5",
11977
- name: "Kwaipilot: KAT-Coder-Air V2.5",
12225
+ "inclusionai/ling-3.0-flash-fin:free": {
12226
+ id: "inclusionai/ling-3.0-flash-fin:free",
12227
+ name: "Ling 3.0 Flash Fin (free)",
11978
12228
  api: "openai-completions",
11979
12229
  provider: "openrouter",
11980
12230
  baseUrl: "https://openrouter.ai/api/v1",
11981
- reasoning: false,
12231
+ reasoning: true,
11982
12232
  input: ["text"],
11983
12233
  cost: {
11984
- input: 0.15,
11985
- output: 0.6,
11986
- cacheRead: 0.03,
12234
+ input: 0,
12235
+ output: 0,
12236
+ cacheRead: 0,
11987
12237
  cacheWrite: 0,
11988
12238
  },
11989
- contextWindow: 256000,
11990
- maxTokens: 80000,
12239
+ contextWindow: 262144,
12240
+ maxTokens: 32768,
11991
12241
  },
11992
12242
  "kwaipilot/kat-coder-pro-v2": {
11993
12243
  id: "kwaipilot/kat-coder-pro-v2",
@@ -12004,7 +12254,7 @@ export const MODELS = {
12004
12254
  cacheWrite: 0,
12005
12255
  },
12006
12256
  contextWindow: 262144,
12007
- maxTokens: 80000,
12257
+ maxTokens: 144000,
12008
12258
  },
12009
12259
  "kwaipilot/kat-coder-pro-v2.5": {
12010
12260
  id: "kwaipilot/kat-coder-pro-v2.5",
@@ -12021,7 +12271,7 @@ export const MODELS = {
12021
12271
  cacheWrite: 0,
12022
12272
  },
12023
12273
  contextWindow: 262144,
12024
- maxTokens: 80000,
12274
+ maxTokens: 235929,
12025
12275
  },
12026
12276
  "liquid/lfm-2.5-2.6b:free": {
12027
12277
  id: "liquid/lfm-2.5-2.6b:free",
@@ -12100,13 +12350,13 @@ export const MODELS = {
12100
12350
  reasoning: false,
12101
12351
  input: ["text"],
12102
12352
  cost: {
12103
- input: 0.71,
12104
- output: 0.71,
12105
- cacheRead: 0.71,
12353
+ input: 0.09999999999999999,
12354
+ output: 0.32,
12355
+ cacheRead: 0,
12106
12356
  cacheWrite: 0,
12107
12357
  },
12108
12358
  contextWindow: 131072,
12109
- maxTokens: 115200,
12359
+ maxTokens: 16384,
12110
12360
  },
12111
12361
  "meta-llama/llama-4-maverick": {
12112
12362
  id: "meta-llama/llama-4-maverick",
@@ -12118,12 +12368,12 @@ export const MODELS = {
12118
12368
  input: ["text", "image"],
12119
12369
  cost: {
12120
12370
  input: 0.19999999999999998,
12121
- output: 0.7999999999999999,
12371
+ output: 0.696,
12122
12372
  cacheRead: 0,
12123
12373
  cacheWrite: 0,
12124
12374
  },
12125
12375
  contextWindow: 1048576,
12126
- maxTokens: 16384,
12376
+ maxTokens: 115200,
12127
12377
  },
12128
12378
  "meta-llama/llama-4-scout": {
12129
12379
  id: "meta-llama/llama-4-scout",
@@ -12134,13 +12384,13 @@ export const MODELS = {
12134
12384
  reasoning: false,
12135
12385
  input: ["text", "image"],
12136
12386
  cost: {
12137
- input: 0.11,
12138
- output: 0.33999999999999997,
12139
- cacheRead: 0.055,
12387
+ input: 0.09999999999999999,
12388
+ output: 0.3,
12389
+ cacheRead: 0,
12140
12390
  cacheWrite: 0,
12141
12391
  },
12142
12392
  contextWindow: 1310720,
12143
- maxTokens: 8192,
12393
+ maxTokens: 16384,
12144
12394
  },
12145
12395
  "meta/muse-glimmer-30b": {
12146
12396
  id: "meta/muse-glimmer-30b",
@@ -12152,12 +12402,12 @@ export const MODELS = {
12152
12402
  input: ["text", "image"],
12153
12403
  cost: {
12154
12404
  input: 0.3,
12155
- output: 1.2,
12405
+ output: 1.1,
12156
12406
  cacheRead: 0.04,
12157
12407
  cacheWrite: 0,
12158
12408
  },
12159
12409
  contextWindow: 131072,
12160
- maxTokens: 16384,
12410
+ maxTokens: 117964,
12161
12411
  },
12162
12412
  "meta/muse-glimmer-30b:batch": {
12163
12413
  id: "meta/muse-glimmer-30b:batch",
@@ -12227,6 +12477,40 @@ export const MODELS = {
12227
12477
  contextWindow: 1048576,
12228
12478
  maxTokens: 943718,
12229
12479
  },
12480
+ "meta/muse-spark-1.3": {
12481
+ id: "meta/muse-spark-1.3",
12482
+ name: "Meta: Muse Spark 1.3",
12483
+ api: "openai-completions",
12484
+ provider: "openrouter",
12485
+ baseUrl: "https://openrouter.ai/api/v1",
12486
+ reasoning: true,
12487
+ input: ["text", "image"],
12488
+ cost: {
12489
+ input: 1.25,
12490
+ output: 4.25,
12491
+ cacheRead: 0.15,
12492
+ cacheWrite: 0,
12493
+ },
12494
+ contextWindow: 1048576,
12495
+ maxTokens: 943718,
12496
+ },
12497
+ "meta/muse-spark-1.3-contributor": {
12498
+ id: "meta/muse-spark-1.3-contributor",
12499
+ name: "Meta: Muse Spark 1.3 Contributor",
12500
+ api: "openai-completions",
12501
+ provider: "openrouter",
12502
+ baseUrl: "https://openrouter.ai/api/v1",
12503
+ reasoning: true,
12504
+ input: ["text", "image"],
12505
+ cost: {
12506
+ input: 0.09999999999999999,
12507
+ output: 0.19999999999999998,
12508
+ cacheRead: 0.002,
12509
+ cacheWrite: 0,
12510
+ },
12511
+ contextWindow: 1048576,
12512
+ maxTokens: 943718,
12513
+ },
12230
12514
  "minimax/minimax-m1": {
12231
12515
  id: "minimax/minimax-m1",
12232
12516
  name: "MiniMax: MiniMax M1",
@@ -12397,23 +12681,6 @@ export const MODELS = {
12397
12681
  contextWindow: 256000,
12398
12682
  maxTokens: 204800,
12399
12683
  },
12400
- "mistralai/codestral-2508:batch": {
12401
- id: "mistralai/codestral-2508:batch",
12402
- name: "Mistral: Codestral 2508 (batch)",
12403
- api: "openai-completions",
12404
- provider: "openrouter",
12405
- baseUrl: "https://openrouter.ai/api/v1",
12406
- reasoning: false,
12407
- input: ["text"],
12408
- cost: {
12409
- input: 0.3,
12410
- output: 0.8999999999999999,
12411
- cacheRead: 0.03,
12412
- cacheWrite: 0,
12413
- },
12414
- contextWindow: 256000,
12415
- maxTokens: 204800,
12416
- },
12417
12684
  "mistralai/devstral-2512": {
12418
12685
  id: "mistralai/devstral-2512",
12419
12686
  name: "Mistral: Devstral 2 2512",
@@ -12423,9 +12690,9 @@ export const MODELS = {
12423
12690
  reasoning: false,
12424
12691
  input: ["text"],
12425
12692
  cost: {
12426
- input: 0.44,
12427
- output: 2.2,
12428
- cacheRead: 0.044,
12693
+ input: 0.39999999999999997,
12694
+ output: 2,
12695
+ cacheRead: 0.04,
12429
12696
  cacheWrite: 0,
12430
12697
  },
12431
12698
  contextWindow: 262144,
@@ -12482,23 +12749,6 @@ export const MODELS = {
12482
12749
  contextWindow: 262144,
12483
12750
  maxTokens: 209715,
12484
12751
  },
12485
- "mistralai/ministral-8b-2512:batch": {
12486
- id: "mistralai/ministral-8b-2512:batch",
12487
- name: "Mistral: Ministral 3 8B 2512 (batch)",
12488
- api: "openai-completions",
12489
- provider: "openrouter",
12490
- baseUrl: "https://openrouter.ai/api/v1",
12491
- reasoning: false,
12492
- input: ["text", "image"],
12493
- cost: {
12494
- input: 0.15,
12495
- output: 0.15,
12496
- cacheRead: 0.015,
12497
- cacheWrite: 0,
12498
- },
12499
- contextWindow: 262144,
12500
- maxTokens: 209715,
12501
- },
12502
12752
  "mistralai/mistral-large": {
12503
12753
  id: "mistralai/mistral-large",
12504
12754
  name: "Mistral Large",
@@ -12550,23 +12800,6 @@ export const MODELS = {
12550
12800
  contextWindow: 262144,
12551
12801
  maxTokens: 209715,
12552
12802
  },
12553
- "mistralai/mistral-large-2512:batch": {
12554
- id: "mistralai/mistral-large-2512:batch",
12555
- name: "Mistral: Mistral Large 3 2512 (batch)",
12556
- api: "openai-completions",
12557
- provider: "openrouter",
12558
- baseUrl: "https://openrouter.ai/api/v1",
12559
- reasoning: false,
12560
- input: ["text", "image"],
12561
- cost: {
12562
- input: 0.5,
12563
- output: 1.5,
12564
- cacheRead: 0.049999999999999996,
12565
- cacheWrite: 0,
12566
- },
12567
- contextWindow: 262144,
12568
- maxTokens: 209715,
12569
- },
12570
12803
  "mistralai/mistral-medium-3": {
12571
12804
  id: "mistralai/mistral-medium-3",
12572
12805
  name: "Mistral: Mistral Medium 3",
@@ -12635,23 +12868,6 @@ export const MODELS = {
12635
12868
  contextWindow: 131072,
12636
12869
  maxTokens: 104857,
12637
12870
  },
12638
- "mistralai/mistral-medium-3.1:batch": {
12639
- id: "mistralai/mistral-medium-3.1:batch",
12640
- name: "Mistral: Mistral Medium 3.1 (batch)",
12641
- api: "openai-completions",
12642
- provider: "openrouter",
12643
- baseUrl: "https://openrouter.ai/api/v1",
12644
- reasoning: false,
12645
- input: ["text", "image"],
12646
- cost: {
12647
- input: 0.39999999999999997,
12648
- output: 2,
12649
- cacheRead: 0.04,
12650
- cacheWrite: 0,
12651
- },
12652
- contextWindow: 131072,
12653
- maxTokens: 104857,
12654
- },
12655
12871
  "mistralai/mistral-nemo": {
12656
12872
  id: "mistralai/mistral-nemo",
12657
12873
  name: "Mistral: Mistral Nemo",
@@ -12703,23 +12919,6 @@ export const MODELS = {
12703
12919
  contextWindow: 262144,
12704
12920
  maxTokens: 209715,
12705
12921
  },
12706
- "mistralai/mistral-small-2603:batch": {
12707
- id: "mistralai/mistral-small-2603:batch",
12708
- name: "Mistral: Mistral Small 4 (batch)",
12709
- api: "openai-completions",
12710
- provider: "openrouter",
12711
- baseUrl: "https://openrouter.ai/api/v1",
12712
- reasoning: true,
12713
- input: ["text", "image"],
12714
- cost: {
12715
- input: 0.15,
12716
- output: 0.6,
12717
- cacheRead: 0.015,
12718
- cacheWrite: 0,
12719
- },
12720
- contextWindow: 262144,
12721
- maxTokens: 209715,
12722
- },
12723
12922
  "mistralai/mistral-small-3.2-24b-instruct": {
12724
12923
  id: "mistralai/mistral-small-3.2-24b-instruct",
12725
12924
  name: "Mistral: Mistral Small 3.2 24B",
@@ -12952,11 +13151,11 @@ export const MODELS = {
12952
13151
  cost: {
12953
13152
  input: 0.049999999999999996,
12954
13153
  output: 0.19999999999999998,
12955
- cacheRead: 0.024999999999999998,
13154
+ cacheRead: 0.03,
12956
13155
  cacheWrite: 0,
12957
13156
  },
12958
13157
  contextWindow: 262144,
12959
- maxTokens: 228000,
13158
+ maxTokens: 235929,
12960
13159
  },
12961
13160
  "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free": {
12962
13161
  id: "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
@@ -13017,31 +13216,14 @@ export const MODELS = {
13017
13216
  baseUrl: "https://openrouter.ai/api/v1",
13018
13217
  reasoning: true,
13019
13218
  input: ["text"],
13020
- cost: {
13021
- input: 0.5,
13022
- output: 2.2,
13023
- cacheRead: 0.09999999999999999,
13024
- cacheWrite: 0,
13025
- },
13026
- contextWindow: 262144,
13027
- maxTokens: 16384,
13028
- },
13029
- "nvidia/nemotron-3-ultra-550b-a55b:batch": {
13030
- id: "nvidia/nemotron-3-ultra-550b-a55b:batch",
13031
- name: "NVIDIA: Nemotron 3 Ultra (batch)",
13032
- api: "openai-completions",
13033
- provider: "openrouter",
13034
- baseUrl: "https://openrouter.ai/api/v1",
13035
- reasoning: true,
13036
- input: ["text"],
13037
13219
  cost: {
13038
13220
  input: 0.6,
13039
- output: 3.5999999999999996,
13040
- cacheRead: 0.19999999999999998,
13221
+ output: 2.4,
13222
+ cacheRead: 0.12,
13041
13223
  cacheWrite: 0,
13042
13224
  },
13043
- contextWindow: 512288,
13044
- maxTokens: 461059,
13225
+ contextWindow: 262144,
13226
+ maxTokens: 182520,
13045
13227
  },
13046
13228
  "nvidia/nemotron-3-ultra-550b-a55b:free": {
13047
13229
  id: "nvidia/nemotron-3-ultra-550b-a55b:free",
@@ -13145,6 +13327,23 @@ export const MODELS = {
13145
13327
  contextWindow: 16385,
13146
13328
  maxTokens: 4096,
13147
13329
  },
13330
+ "openai/gpt-3.5-turbo:batch": {
13331
+ id: "openai/gpt-3.5-turbo:batch",
13332
+ name: "OpenAI: GPT-3.5 Turbo (batch)",
13333
+ api: "openai-completions",
13334
+ provider: "openrouter",
13335
+ baseUrl: "https://openrouter.ai/api/v1",
13336
+ reasoning: false,
13337
+ input: ["text"],
13338
+ cost: {
13339
+ input: 0.25,
13340
+ output: 0.75,
13341
+ cacheRead: 0,
13342
+ cacheWrite: 0,
13343
+ },
13344
+ contextWindow: 16385,
13345
+ maxTokens: 4096,
13346
+ },
13148
13347
  "openai/gpt-4": {
13149
13348
  id: "openai/gpt-4",
13150
13349
  name: "OpenAI: GPT-4",
@@ -13162,6 +13361,23 @@ export const MODELS = {
13162
13361
  contextWindow: 8191,
13163
13362
  maxTokens: 4096,
13164
13363
  },
13364
+ "openai/gpt-4-turbo:batch": {
13365
+ id: "openai/gpt-4-turbo:batch",
13366
+ name: "OpenAI: GPT-4 Turbo (batch)",
13367
+ api: "openai-completions",
13368
+ provider: "openrouter",
13369
+ baseUrl: "https://openrouter.ai/api/v1",
13370
+ reasoning: false,
13371
+ input: ["text", "image"],
13372
+ cost: {
13373
+ input: 5,
13374
+ output: 15,
13375
+ cacheRead: 0,
13376
+ cacheWrite: 0,
13377
+ },
13378
+ contextWindow: 128000,
13379
+ maxTokens: 4096,
13380
+ },
13165
13381
  "openai/gpt-4.1": {
13166
13382
  id: "openai/gpt-4.1",
13167
13383
  name: "OpenAI: GPT-4.1",
@@ -13196,6 +13412,23 @@ export const MODELS = {
13196
13412
  contextWindow: 1047576,
13197
13413
  maxTokens: 32768,
13198
13414
  },
13415
+ "openai/gpt-4.1-mini:batch": {
13416
+ id: "openai/gpt-4.1-mini:batch",
13417
+ name: "OpenAI: GPT-4.1 Mini (batch)",
13418
+ api: "openai-completions",
13419
+ provider: "openrouter",
13420
+ baseUrl: "https://openrouter.ai/api/v1",
13421
+ reasoning: false,
13422
+ input: ["text", "image"],
13423
+ cost: {
13424
+ input: 0.19999999999999998,
13425
+ output: 0.7999999999999999,
13426
+ cacheRead: 0.049999999999999996,
13427
+ cacheWrite: 0,
13428
+ },
13429
+ contextWindow: 1047576,
13430
+ maxTokens: 32768,
13431
+ },
13199
13432
  "openai/gpt-4.1-nano": {
13200
13433
  id: "openai/gpt-4.1-nano",
13201
13434
  name: "OpenAI: GPT-4.1 Nano",
@@ -13207,11 +13440,45 @@ export const MODELS = {
13207
13440
  cost: {
13208
13441
  input: 0.09999999999999999,
13209
13442
  output: 0.39999999999999997,
13210
- cacheRead: 0.03,
13443
+ cacheRead: 0.024999999999999998,
13444
+ cacheWrite: 0,
13445
+ },
13446
+ contextWindow: 1047576,
13447
+ maxTokens: 32768,
13448
+ },
13449
+ "openai/gpt-4.1-nano:batch": {
13450
+ id: "openai/gpt-4.1-nano:batch",
13451
+ name: "OpenAI: GPT-4.1 Nano (batch)",
13452
+ api: "openai-completions",
13453
+ provider: "openrouter",
13454
+ baseUrl: "https://openrouter.ai/api/v1",
13455
+ reasoning: false,
13456
+ input: ["text", "image"],
13457
+ cost: {
13458
+ input: 0.049999999999999996,
13459
+ output: 0.19999999999999998,
13460
+ cacheRead: 0.012499999999999999,
13211
13461
  cacheWrite: 0,
13212
13462
  },
13213
13463
  contextWindow: 1047576,
13214
- maxTokens: 942818,
13464
+ maxTokens: 32768,
13465
+ },
13466
+ "openai/gpt-4.1:batch": {
13467
+ id: "openai/gpt-4.1:batch",
13468
+ name: "OpenAI: GPT-4.1 (batch)",
13469
+ api: "openai-completions",
13470
+ provider: "openrouter",
13471
+ baseUrl: "https://openrouter.ai/api/v1",
13472
+ reasoning: false,
13473
+ input: ["text", "image"],
13474
+ cost: {
13475
+ input: 1,
13476
+ output: 4,
13477
+ cacheRead: 0.25,
13478
+ cacheWrite: 0,
13479
+ },
13480
+ contextWindow: 1047576,
13481
+ maxTokens: 32768,
13215
13482
  },
13216
13483
  "openai/gpt-4o": {
13217
13484
  id: "openai/gpt-4o",
@@ -13247,6 +13514,40 @@ export const MODELS = {
13247
13514
  contextWindow: 128000,
13248
13515
  maxTokens: 16384,
13249
13516
  },
13517
+ "openai/gpt-4o-mini:batch": {
13518
+ id: "openai/gpt-4o-mini:batch",
13519
+ name: "OpenAI: GPT-4o-mini (batch)",
13520
+ api: "openai-completions",
13521
+ provider: "openrouter",
13522
+ baseUrl: "https://openrouter.ai/api/v1",
13523
+ reasoning: false,
13524
+ input: ["text", "image"],
13525
+ cost: {
13526
+ input: 0.075,
13527
+ output: 0.3,
13528
+ cacheRead: 0.0375,
13529
+ cacheWrite: 0,
13530
+ },
13531
+ contextWindow: 128000,
13532
+ maxTokens: 16384,
13533
+ },
13534
+ "openai/gpt-4o:batch": {
13535
+ id: "openai/gpt-4o:batch",
13536
+ name: "OpenAI: GPT-4o (batch)",
13537
+ api: "openai-completions",
13538
+ provider: "openrouter",
13539
+ baseUrl: "https://openrouter.ai/api/v1",
13540
+ reasoning: false,
13541
+ input: ["text", "image"],
13542
+ cost: {
13543
+ input: 1.25,
13544
+ output: 5,
13545
+ cacheRead: 0.625,
13546
+ cacheWrite: 0,
13547
+ },
13548
+ contextWindow: 128000,
13549
+ maxTokens: 16384,
13550
+ },
13250
13551
  "openai/gpt-5": {
13251
13552
  id: "openai/gpt-5",
13252
13553
  name: "OpenAI: GPT-5",
@@ -13281,6 +13582,23 @@ export const MODELS = {
13281
13582
  contextWindow: 400000,
13282
13583
  maxTokens: 128000,
13283
13584
  },
13585
+ "openai/gpt-5-mini:batch": {
13586
+ id: "openai/gpt-5-mini:batch",
13587
+ name: "OpenAI: GPT-5 Mini (batch)",
13588
+ api: "openai-completions",
13589
+ provider: "openrouter",
13590
+ baseUrl: "https://openrouter.ai/api/v1",
13591
+ reasoning: true,
13592
+ input: ["text", "image"],
13593
+ cost: {
13594
+ input: 0.125,
13595
+ output: 1,
13596
+ cacheRead: 0.012499999999999999,
13597
+ cacheWrite: 0,
13598
+ },
13599
+ contextWindow: 400000,
13600
+ maxTokens: 128000,
13601
+ },
13284
13602
  "openai/gpt-5-nano": {
13285
13603
  id: "openai/gpt-5-nano",
13286
13604
  name: "OpenAI: GPT-5 Nano",
@@ -13298,6 +13616,23 @@ export const MODELS = {
13298
13616
  contextWindow: 400000,
13299
13617
  maxTokens: 128000,
13300
13618
  },
13619
+ "openai/gpt-5-nano:batch": {
13620
+ id: "openai/gpt-5-nano:batch",
13621
+ name: "OpenAI: GPT-5 Nano (batch)",
13622
+ api: "openai-completions",
13623
+ provider: "openrouter",
13624
+ baseUrl: "https://openrouter.ai/api/v1",
13625
+ reasoning: true,
13626
+ input: ["text", "image"],
13627
+ cost: {
13628
+ input: 0.024999999999999998,
13629
+ output: 0.19999999999999998,
13630
+ cacheRead: 0.0025,
13631
+ cacheWrite: 0,
13632
+ },
13633
+ contextWindow: 400000,
13634
+ maxTokens: 128000,
13635
+ },
13301
13636
  "openai/gpt-5-pro": {
13302
13637
  id: "openai/gpt-5-pro",
13303
13638
  name: "OpenAI: GPT-5 Pro",
@@ -13315,6 +13650,23 @@ export const MODELS = {
13315
13650
  contextWindow: 400000,
13316
13651
  maxTokens: 128000,
13317
13652
  },
13653
+ "openai/gpt-5-pro:batch": {
13654
+ id: "openai/gpt-5-pro:batch",
13655
+ name: "OpenAI: GPT-5 Pro (batch)",
13656
+ api: "openai-completions",
13657
+ provider: "openrouter",
13658
+ baseUrl: "https://openrouter.ai/api/v1",
13659
+ reasoning: true,
13660
+ input: ["text", "image"],
13661
+ cost: {
13662
+ input: 7.5,
13663
+ output: 60,
13664
+ cacheRead: 0,
13665
+ cacheWrite: 0,
13666
+ },
13667
+ contextWindow: 400000,
13668
+ maxTokens: 128000,
13669
+ },
13318
13670
  "openai/gpt-5.1": {
13319
13671
  id: "openai/gpt-5.1",
13320
13672
  name: "OpenAI: GPT-5.1",
@@ -13383,6 +13735,23 @@ export const MODELS = {
13383
13735
  contextWindow: 400000,
13384
13736
  maxTokens: 128000,
13385
13737
  },
13738
+ "openai/gpt-5.1:batch": {
13739
+ id: "openai/gpt-5.1:batch",
13740
+ name: "OpenAI: GPT-5.1 (batch)",
13741
+ api: "openai-completions",
13742
+ provider: "openrouter",
13743
+ baseUrl: "https://openrouter.ai/api/v1",
13744
+ reasoning: true,
13745
+ input: ["text", "image"],
13746
+ cost: {
13747
+ input: 0.625,
13748
+ output: 5,
13749
+ cacheRead: 0.0625,
13750
+ cacheWrite: 0,
13751
+ },
13752
+ contextWindow: 400000,
13753
+ maxTokens: 128000,
13754
+ },
13386
13755
  "openai/gpt-5.2": {
13387
13756
  id: "openai/gpt-5.2",
13388
13757
  name: "OpenAI: GPT-5.2",
@@ -13455,6 +13824,42 @@ export const MODELS = {
13455
13824
  contextWindow: 400000,
13456
13825
  maxTokens: 128000,
13457
13826
  },
13827
+ "openai/gpt-5.2-pro:batch": {
13828
+ id: "openai/gpt-5.2-pro:batch",
13829
+ name: "OpenAI: GPT-5.2 Pro (batch)",
13830
+ api: "openai-completions",
13831
+ provider: "openrouter",
13832
+ baseUrl: "https://openrouter.ai/api/v1",
13833
+ reasoning: true,
13834
+ thinkingLevelMap: { "xhigh": "xhigh" },
13835
+ input: ["text", "image"],
13836
+ cost: {
13837
+ input: 10.5,
13838
+ output: 84,
13839
+ cacheRead: 0,
13840
+ cacheWrite: 0,
13841
+ },
13842
+ contextWindow: 400000,
13843
+ maxTokens: 128000,
13844
+ },
13845
+ "openai/gpt-5.2:batch": {
13846
+ id: "openai/gpt-5.2:batch",
13847
+ name: "OpenAI: GPT-5.2 (batch)",
13848
+ api: "openai-completions",
13849
+ provider: "openrouter",
13850
+ baseUrl: "https://openrouter.ai/api/v1",
13851
+ reasoning: true,
13852
+ thinkingLevelMap: { "xhigh": "xhigh" },
13853
+ input: ["text", "image"],
13854
+ cost: {
13855
+ input: 0.875,
13856
+ output: 7,
13857
+ cacheRead: 0.0875,
13858
+ cacheWrite: 0,
13859
+ },
13860
+ contextWindow: 400000,
13861
+ maxTokens: 128000,
13862
+ },
13458
13863
  "openai/gpt-5.3-codex": {
13459
13864
  id: "openai/gpt-5.3-codex",
13460
13865
  name: "OpenAI: GPT-5.3-Codex",
@@ -13509,6 +13914,24 @@ export const MODELS = {
13509
13914
  contextWindow: 400000,
13510
13915
  maxTokens: 128000,
13511
13916
  },
13917
+ "openai/gpt-5.4-mini:batch": {
13918
+ id: "openai/gpt-5.4-mini:batch",
13919
+ name: "OpenAI: GPT-5.4 Mini (batch)",
13920
+ api: "openai-completions",
13921
+ provider: "openrouter",
13922
+ baseUrl: "https://openrouter.ai/api/v1",
13923
+ reasoning: true,
13924
+ thinkingLevelMap: { "xhigh": "xhigh" },
13925
+ input: ["text", "image"],
13926
+ cost: {
13927
+ input: 0.375,
13928
+ output: 2.25,
13929
+ cacheRead: 0.0375,
13930
+ cacheWrite: 0,
13931
+ },
13932
+ contextWindow: 400000,
13933
+ maxTokens: 128000,
13934
+ },
13512
13935
  "openai/gpt-5.4-nano": {
13513
13936
  id: "openai/gpt-5.4-nano",
13514
13937
  name: "OpenAI: GPT-5.4 Nano",
@@ -13527,6 +13950,24 @@ export const MODELS = {
13527
13950
  contextWindow: 400000,
13528
13951
  maxTokens: 128000,
13529
13952
  },
13953
+ "openai/gpt-5.4-nano:batch": {
13954
+ id: "openai/gpt-5.4-nano:batch",
13955
+ name: "OpenAI: GPT-5.4 Nano (batch)",
13956
+ api: "openai-completions",
13957
+ provider: "openrouter",
13958
+ baseUrl: "https://openrouter.ai/api/v1",
13959
+ reasoning: true,
13960
+ thinkingLevelMap: { "xhigh": "xhigh" },
13961
+ input: ["text", "image"],
13962
+ cost: {
13963
+ input: 0.09999999999999999,
13964
+ output: 0.625,
13965
+ cacheRead: 0.01,
13966
+ cacheWrite: 0,
13967
+ },
13968
+ contextWindow: 400000,
13969
+ maxTokens: 128000,
13970
+ },
13530
13971
  "openai/gpt-5.4-pro": {
13531
13972
  id: "openai/gpt-5.4-pro",
13532
13973
  name: "OpenAI: GPT-5.4 Pro",
@@ -13545,6 +13986,42 @@ export const MODELS = {
13545
13986
  contextWindow: 1050000,
13546
13987
  maxTokens: 128000,
13547
13988
  },
13989
+ "openai/gpt-5.4-pro:batch": {
13990
+ id: "openai/gpt-5.4-pro:batch",
13991
+ name: "OpenAI: GPT-5.4 Pro (batch)",
13992
+ api: "openai-completions",
13993
+ provider: "openrouter",
13994
+ baseUrl: "https://openrouter.ai/api/v1",
13995
+ reasoning: true,
13996
+ thinkingLevelMap: { "xhigh": "xhigh" },
13997
+ input: ["text", "image"],
13998
+ cost: {
13999
+ input: 15,
14000
+ output: 90,
14001
+ cacheRead: 0,
14002
+ cacheWrite: 0,
14003
+ },
14004
+ contextWindow: 1050000,
14005
+ maxTokens: 128000,
14006
+ },
14007
+ "openai/gpt-5.4:batch": {
14008
+ id: "openai/gpt-5.4:batch",
14009
+ name: "OpenAI: GPT-5.4 (batch)",
14010
+ api: "openai-completions",
14011
+ provider: "openrouter",
14012
+ baseUrl: "https://openrouter.ai/api/v1",
14013
+ reasoning: true,
14014
+ thinkingLevelMap: { "xhigh": "xhigh" },
14015
+ input: ["text", "image"],
14016
+ cost: {
14017
+ input: 1.25,
14018
+ output: 7.5,
14019
+ cacheRead: 0.125,
14020
+ cacheWrite: 0,
14021
+ },
14022
+ contextWindow: 1050000,
14023
+ maxTokens: 128000,
14024
+ },
13548
14025
  "openai/gpt-5.5": {
13549
14026
  id: "openai/gpt-5.5",
13550
14027
  name: "OpenAI: GPT-5.5",
@@ -13581,6 +14058,42 @@ export const MODELS = {
13581
14058
  contextWindow: 1050000,
13582
14059
  maxTokens: 128000,
13583
14060
  },
14061
+ "openai/gpt-5.5-pro:batch": {
14062
+ id: "openai/gpt-5.5-pro:batch",
14063
+ name: "OpenAI: GPT-5.5 Pro (batch)",
14064
+ api: "openai-completions",
14065
+ provider: "openrouter",
14066
+ baseUrl: "https://openrouter.ai/api/v1",
14067
+ reasoning: true,
14068
+ thinkingLevelMap: { "xhigh": "xhigh" },
14069
+ input: ["text", "image"],
14070
+ cost: {
14071
+ input: 15,
14072
+ output: 90,
14073
+ cacheRead: 0,
14074
+ cacheWrite: 0,
14075
+ },
14076
+ contextWindow: 1050000,
14077
+ maxTokens: 128000,
14078
+ },
14079
+ "openai/gpt-5.5:batch": {
14080
+ id: "openai/gpt-5.5:batch",
14081
+ name: "OpenAI: GPT-5.5 (batch)",
14082
+ api: "openai-completions",
14083
+ provider: "openrouter",
14084
+ baseUrl: "https://openrouter.ai/api/v1",
14085
+ reasoning: true,
14086
+ thinkingLevelMap: { "xhigh": "xhigh" },
14087
+ input: ["text", "image"],
14088
+ cost: {
14089
+ input: 2.5,
14090
+ output: 15,
14091
+ cacheRead: 0.25,
14092
+ cacheWrite: 0,
14093
+ },
14094
+ contextWindow: 1050000,
14095
+ maxTokens: 128000,
14096
+ },
13584
14097
  "openai/gpt-5.6-luna": {
13585
14098
  id: "openai/gpt-5.6-luna",
13586
14099
  name: "OpenAI: GPT-5.6 Luna",
@@ -13615,6 +14128,40 @@ export const MODELS = {
13615
14128
  contextWindow: 1050000,
13616
14129
  maxTokens: 128000,
13617
14130
  },
14131
+ "openai/gpt-5.6-luna-pro:batch": {
14132
+ id: "openai/gpt-5.6-luna-pro:batch",
14133
+ name: "OpenAI: GPT-5.6 Luna Pro (batch)",
14134
+ api: "openai-completions",
14135
+ provider: "openrouter",
14136
+ baseUrl: "https://openrouter.ai/api/v1",
14137
+ reasoning: true,
14138
+ input: ["text", "image"],
14139
+ cost: {
14140
+ input: 0.09999999999999999,
14141
+ output: 0.6,
14142
+ cacheRead: 0.01,
14143
+ cacheWrite: 0,
14144
+ },
14145
+ contextWindow: 1050000,
14146
+ maxTokens: 128000,
14147
+ },
14148
+ "openai/gpt-5.6-luna:batch": {
14149
+ id: "openai/gpt-5.6-luna:batch",
14150
+ name: "OpenAI: GPT-5.6 Luna (batch)",
14151
+ api: "openai-completions",
14152
+ provider: "openrouter",
14153
+ baseUrl: "https://openrouter.ai/api/v1",
14154
+ reasoning: true,
14155
+ input: ["text", "image"],
14156
+ cost: {
14157
+ input: 0.09999999999999999,
14158
+ output: 0.6,
14159
+ cacheRead: 0.01,
14160
+ cacheWrite: 0,
14161
+ },
14162
+ contextWindow: 1050000,
14163
+ maxTokens: 128000,
14164
+ },
13618
14165
  "openai/gpt-5.6-sol": {
13619
14166
  id: "openai/gpt-5.6-sol",
13620
14167
  name: "OpenAI: GPT-5.6 Sol",
@@ -13649,6 +14196,40 @@ export const MODELS = {
13649
14196
  contextWindow: 1050000,
13650
14197
  maxTokens: 128000,
13651
14198
  },
14199
+ "openai/gpt-5.6-sol-pro:batch": {
14200
+ id: "openai/gpt-5.6-sol-pro:batch",
14201
+ name: "OpenAI: GPT-5.6 Sol Pro (batch)",
14202
+ api: "openai-completions",
14203
+ provider: "openrouter",
14204
+ baseUrl: "https://openrouter.ai/api/v1",
14205
+ reasoning: true,
14206
+ input: ["text", "image"],
14207
+ cost: {
14208
+ input: 1,
14209
+ output: 5,
14210
+ cacheRead: 0.09999999999999999,
14211
+ cacheWrite: 1.25,
14212
+ },
14213
+ contextWindow: 1050000,
14214
+ maxTokens: 128000,
14215
+ },
14216
+ "openai/gpt-5.6-sol:batch": {
14217
+ id: "openai/gpt-5.6-sol:batch",
14218
+ name: "OpenAI: GPT-5.6 Sol (batch)",
14219
+ api: "openai-completions",
14220
+ provider: "openrouter",
14221
+ baseUrl: "https://openrouter.ai/api/v1",
14222
+ reasoning: true,
14223
+ input: ["text", "image"],
14224
+ cost: {
14225
+ input: 1,
14226
+ output: 5,
14227
+ cacheRead: 0.09999999999999999,
14228
+ cacheWrite: 1.25,
14229
+ },
14230
+ contextWindow: 1050000,
14231
+ maxTokens: 128000,
14232
+ },
13652
14233
  "openai/gpt-5.6-terra": {
13653
14234
  id: "openai/gpt-5.6-terra",
13654
14235
  name: "OpenAI: GPT-5.6 Terra",
@@ -13683,6 +14264,57 @@ export const MODELS = {
13683
14264
  contextWindow: 1050000,
13684
14265
  maxTokens: 128000,
13685
14266
  },
14267
+ "openai/gpt-5.6-terra-pro:batch": {
14268
+ id: "openai/gpt-5.6-terra-pro:batch",
14269
+ name: "OpenAI: GPT-5.6 Terra Pro (batch)",
14270
+ api: "openai-completions",
14271
+ provider: "openrouter",
14272
+ baseUrl: "https://openrouter.ai/api/v1",
14273
+ reasoning: true,
14274
+ input: ["text", "image"],
14275
+ cost: {
14276
+ input: 1,
14277
+ output: 6,
14278
+ cacheRead: 0.09999999999999999,
14279
+ cacheWrite: 0,
14280
+ },
14281
+ contextWindow: 1050000,
14282
+ maxTokens: 128000,
14283
+ },
14284
+ "openai/gpt-5.6-terra:batch": {
14285
+ id: "openai/gpt-5.6-terra:batch",
14286
+ name: "OpenAI: GPT-5.6 Terra (batch)",
14287
+ api: "openai-completions",
14288
+ provider: "openrouter",
14289
+ baseUrl: "https://openrouter.ai/api/v1",
14290
+ reasoning: true,
14291
+ input: ["text", "image"],
14292
+ cost: {
14293
+ input: 1,
14294
+ output: 6,
14295
+ cacheRead: 0.09999999999999999,
14296
+ cacheWrite: 0,
14297
+ },
14298
+ contextWindow: 1050000,
14299
+ maxTokens: 128000,
14300
+ },
14301
+ "openai/gpt-5:batch": {
14302
+ id: "openai/gpt-5:batch",
14303
+ name: "OpenAI: GPT-5 (batch)",
14304
+ api: "openai-completions",
14305
+ provider: "openrouter",
14306
+ baseUrl: "https://openrouter.ai/api/v1",
14307
+ reasoning: true,
14308
+ input: ["text", "image"],
14309
+ cost: {
14310
+ input: 0.625,
14311
+ output: 5,
14312
+ cacheRead: 0.0625,
14313
+ cacheWrite: 0,
14314
+ },
14315
+ contextWindow: 400000,
14316
+ maxTokens: 128000,
14317
+ },
13686
14318
  "openai/gpt-audio": {
13687
14319
  id: "openai/gpt-audio",
13688
14320
  name: "OpenAI: GPT Audio",
@@ -13870,18 +14502,52 @@ export const MODELS = {
13870
14502
  contextWindow: 200000,
13871
14503
  maxTokens: 100000,
13872
14504
  },
13873
- "openai/o3-pro": {
13874
- id: "openai/o3-pro",
13875
- name: "OpenAI: o3 Pro",
14505
+ "openai/o3-mini:batch": {
14506
+ id: "openai/o3-mini:batch",
14507
+ name: "OpenAI: o3 Mini (batch)",
14508
+ api: "openai-completions",
14509
+ provider: "openrouter",
14510
+ baseUrl: "https://openrouter.ai/api/v1",
14511
+ reasoning: true,
14512
+ input: ["text"],
14513
+ cost: {
14514
+ input: 0.55,
14515
+ output: 2.2,
14516
+ cacheRead: 0.275,
14517
+ cacheWrite: 0,
14518
+ },
14519
+ contextWindow: 200000,
14520
+ maxTokens: 100000,
14521
+ },
14522
+ "openai/o3-pro": {
14523
+ id: "openai/o3-pro",
14524
+ name: "OpenAI: o3 Pro",
14525
+ api: "openai-completions",
14526
+ provider: "openrouter",
14527
+ baseUrl: "https://openrouter.ai/api/v1",
14528
+ reasoning: true,
14529
+ input: ["text", "image"],
14530
+ cost: {
14531
+ input: 20,
14532
+ output: 80,
14533
+ cacheRead: 0,
14534
+ cacheWrite: 0,
14535
+ },
14536
+ contextWindow: 200000,
14537
+ maxTokens: 100000,
14538
+ },
14539
+ "openai/o3:batch": {
14540
+ id: "openai/o3:batch",
14541
+ name: "OpenAI: o3 (batch)",
13876
14542
  api: "openai-completions",
13877
14543
  provider: "openrouter",
13878
14544
  baseUrl: "https://openrouter.ai/api/v1",
13879
14545
  reasoning: true,
13880
14546
  input: ["text", "image"],
13881
14547
  cost: {
13882
- input: 20,
13883
- output: 80,
13884
- cacheRead: 0,
14548
+ input: 1,
14549
+ output: 4,
14550
+ cacheRead: 0.25,
13885
14551
  cacheWrite: 0,
13886
14552
  },
13887
14553
  contextWindow: 200000,
@@ -13921,6 +14587,23 @@ export const MODELS = {
13921
14587
  contextWindow: 200000,
13922
14588
  maxTokens: 100000,
13923
14589
  },
14590
+ "openai/o4-mini:batch": {
14591
+ id: "openai/o4-mini:batch",
14592
+ name: "OpenAI: o4 Mini (batch)",
14593
+ api: "openai-completions",
14594
+ provider: "openrouter",
14595
+ baseUrl: "https://openrouter.ai/api/v1",
14596
+ reasoning: true,
14597
+ input: ["text", "image"],
14598
+ cost: {
14599
+ input: 0.55,
14600
+ output: 2.2,
14601
+ cacheRead: 0.1375,
14602
+ cacheWrite: 0,
14603
+ },
14604
+ contextWindow: 200000,
14605
+ maxTokens: 100000,
14606
+ },
13924
14607
  "openrouter/auto": {
13925
14608
  id: "openrouter/auto",
13926
14609
  name: "Auto Router",
@@ -14593,13 +15276,13 @@ export const MODELS = {
14593
15276
  reasoning: true,
14594
15277
  input: ["text", "image"],
14595
15278
  cost: {
14596
- input: 0.39,
14597
- output: 2.34,
14598
- cacheRead: 0,
15279
+ input: 0.55,
15280
+ output: 3.5,
15281
+ cacheRead: 0.22499999999999998,
14599
15282
  cacheWrite: 0,
14600
15283
  },
14601
15284
  contextWindow: 262144,
14602
- maxTokens: 65536,
15285
+ maxTokens: 235929,
14603
15286
  },
14604
15287
  "qwen/qwen3.5-9b": {
14605
15288
  id: "qwen/qwen3.5-9b",
@@ -14848,9 +15531,9 @@ export const MODELS = {
14848
15531
  reasoning: true,
14849
15532
  input: ["text"],
14850
15533
  cost: {
14851
- input: 2.5,
14852
- output: 6.25,
14853
- cacheRead: 0.5,
15534
+ input: 2,
15535
+ output: 6,
15536
+ cacheRead: 0.25,
14854
15537
  cacheWrite: 0,
14855
15538
  },
14856
15539
  contextWindow: 1010000,
@@ -14865,10 +15548,10 @@ export const MODELS = {
14865
15548
  reasoning: true,
14866
15549
  input: ["text", "image"],
14867
15550
  cost: {
14868
- input: 0.425,
14869
- output: 2.5500000000000003,
15551
+ input: 0.42,
15552
+ output: 3,
14870
15553
  cacheRead: 0.08499999999999999,
14871
- cacheWrite: 0.53125,
15554
+ cacheWrite: 0,
14872
15555
  },
14873
15556
  contextWindow: 1000000,
14874
15557
  maxTokens: 131072,
@@ -15086,13 +15769,13 @@ export const MODELS = {
15086
15769
  reasoning: true,
15087
15770
  input: ["text", "image"],
15088
15771
  cost: {
15089
- input: 0.95,
15772
+ input: 1,
15090
15773
  output: 4.05,
15091
- cacheRead: 0.16,
15774
+ cacheRead: 0.16999999999999998,
15092
15775
  cacheWrite: 0,
15093
15776
  },
15094
15777
  contextWindow: 1048576,
15095
- maxTokens: 262144,
15778
+ maxTokens: 471859,
15096
15779
  },
15097
15780
  "thinkingmachines/inkling-small": {
15098
15781
  id: "thinkingmachines/inkling-small",
@@ -15392,13 +16075,13 @@ export const MODELS = {
15392
16075
  reasoning: true,
15393
16076
  input: ["text"],
15394
16077
  cost: {
15395
- input: 0.43,
15396
- output: 1.75,
15397
- cacheRead: 0.08,
16078
+ input: 0.55,
16079
+ output: 2.2,
16080
+ cacheRead: 0.11,
15398
16081
  cacheWrite: 0,
15399
16082
  },
15400
16083
  contextWindow: 204800,
15401
- maxTokens: 16384,
16084
+ maxTokens: 131072,
15402
16085
  },
15403
16086
  "z-ai/glm-4.6v": {
15404
16087
  id: "z-ai/glm-4.6v",
@@ -15494,13 +16177,13 @@ export const MODELS = {
15494
16177
  reasoning: true,
15495
16178
  input: ["text"],
15496
16179
  cost: {
15497
- input: 1.26,
15498
- output: 3.9600000000000004,
15499
- cacheRead: 0.234,
16180
+ input: 0.966,
16181
+ output: 3.036,
16182
+ cacheRead: 0.1794,
15500
16183
  cacheWrite: 0,
15501
16184
  },
15502
16185
  contextWindow: 204800,
15503
- maxTokens: 182476,
16186
+ maxTokens: 128000,
15504
16187
  },
15505
16188
  "z-ai/glm-5.2": {
15506
16189
  id: "z-ai/glm-5.2",
@@ -15511,13 +16194,13 @@ export const MODELS = {
15511
16194
  reasoning: true,
15512
16195
  input: ["text"],
15513
16196
  cost: {
15514
- input: 1.19,
15515
- output: 3.74,
15516
- cacheRead: 0.221,
16197
+ input: 0.966,
16198
+ output: 3.036,
16199
+ cacheRead: 0.1932,
15517
16200
  cacheWrite: 0,
15518
16201
  },
15519
16202
  contextWindow: 1048576,
15520
- maxTokens: 262144,
16203
+ maxTokens: 131072,
15521
16204
  },
15522
16205
  "z-ai/glm-5.2:free": {
15523
16206
  id: "z-ai/glm-5.2:free",
@@ -15547,11 +16230,11 @@ export const MODELS = {
15547
16230
  cost: {
15548
16231
  input: 1.4,
15549
16232
  output: 4.4,
15550
- cacheRead: 0.26,
16233
+ cacheRead: 0.14,
15551
16234
  cacheWrite: 0,
15552
16235
  },
15553
16236
  contextWindow: 1310720,
15554
- maxTokens: 131072,
16237
+ maxTokens: 262144,
15555
16238
  },
15556
16239
  "z-ai/glm-5.3-flash": {
15557
16240
  id: "z-ai/glm-5.3-flash",
@@ -15616,7 +16299,7 @@ export const MODELS = {
15616
16299
  cost: {
15617
16300
  input: 10,
15618
16301
  output: 50,
15619
- cacheRead: 1,
16302
+ cacheRead: 0.25,
15620
16303
  cacheWrite: 12.5,
15621
16304
  },
15622
16305
  contextWindow: 1000000,
@@ -15684,13 +16367,13 @@ export const MODELS = {
15684
16367
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
15685
16368
  input: ["text"],
15686
16369
  cost: {
15687
- input: 0.03,
15688
- output: 0.09999999999999999,
15689
- cacheRead: 0.007,
16370
+ input: 0.049999999999999996,
16371
+ output: 0.16,
16372
+ cacheRead: 0.013000000000000001,
15690
16373
  cacheWrite: 0,
15691
16374
  },
15692
16375
  contextWindow: 1310720,
15693
- maxTokens: 131072,
16376
+ maxTokens: 393216,
15694
16377
  },
15695
16378
  "~google/gemini-flash-latest": {
15696
16379
  id: "~google/gemini-flash-latest",
@@ -15735,9 +16418,9 @@ export const MODELS = {
15735
16418
  reasoning: true,
15736
16419
  input: ["text", "image"],
15737
16420
  cost: {
15738
- input: 2.5500000000000003,
15739
- output: 12.75,
15740
- cacheRead: 0.25599998999999996,
16421
+ input: 2.5,
16422
+ output: 14,
16423
+ cacheRead: 0.29,
15741
16424
  cacheWrite: 0,
15742
16425
  },
15743
16426
  contextWindow: 1048576,
@@ -15794,6 +16477,23 @@ export const MODELS = {
15794
16477
  contextWindow: 500000,
15795
16478
  maxTokens: 450000,
15796
16479
  },
16480
+ "~z-ai/glm-flash-latest": {
16481
+ id: "~z-ai/glm-flash-latest",
16482
+ name: "Z.ai: GLM Flash Latest",
16483
+ api: "openai-completions",
16484
+ provider: "openrouter",
16485
+ baseUrl: "https://openrouter.ai/api/v1",
16486
+ reasoning: true,
16487
+ input: ["text", "image"],
16488
+ cost: {
16489
+ input: 0.07125000000000001,
16490
+ output: 0.2375,
16491
+ cacheRead: 0.01425,
16492
+ cacheWrite: 0,
16493
+ },
16494
+ contextWindow: 1310720,
16495
+ maxTokens: 131072,
16496
+ },
15797
16497
  "~z-ai/glm-latest": {
15798
16498
  id: "~z-ai/glm-latest",
15799
16499
  name: "Z.ai: GLM Latest",
@@ -15803,13 +16503,13 @@ export const MODELS = {
15803
16503
  reasoning: true,
15804
16504
  input: ["text"],
15805
16505
  cost: {
15806
- input: 1.1875,
15807
- output: 4.18,
15808
- cacheRead: 0.24699999999999997,
16506
+ input: 1.1480000000000001,
16507
+ output: 3.608,
16508
+ cacheRead: 0.18860000000000002,
15809
16509
  cacheWrite: 0,
15810
16510
  },
15811
16511
  contextWindow: 1310720,
15812
- maxTokens: 131072,
16512
+ maxTokens: 943718,
15813
16513
  },
15814
16514
  },
15815
16515
  "together": {
@@ -16171,6 +16871,25 @@ export const MODELS = {
16171
16871
  contextWindow: 512000,
16172
16872
  maxTokens: 164000,
16173
16873
  },
16874
+ "zai-org/GLM-5.3": {
16875
+ id: "zai-org/GLM-5.3",
16876
+ name: "GLM-5.3",
16877
+ api: "openai-completions",
16878
+ provider: "together",
16879
+ baseUrl: "https://api.together.ai/v1",
16880
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
16881
+ reasoning: true,
16882
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
16883
+ input: ["text"],
16884
+ cost: {
16885
+ input: 1.4,
16886
+ output: 4.4,
16887
+ cacheRead: 0.26,
16888
+ cacheWrite: 0,
16889
+ },
16890
+ contextWindow: 1048576,
16891
+ maxTokens: 262144,
16892
+ },
16174
16893
  "zai-org/GLM-5.3-Flash": {
16175
16894
  id: "zai-org/GLM-5.3-Flash",
16176
16895
  name: "GLM-5.3-Flash",
@@ -16668,6 +17387,23 @@ export const MODELS = {
16668
17387
  contextWindow: 991000,
16669
17388
  maxTokens: 128000,
16670
17389
  },
17390
+ "alibaba/qwen3.8-flash-next": {
17391
+ id: "alibaba/qwen3.8-flash-next",
17392
+ name: "Qwen 3.8 Flash Next",
17393
+ api: "anthropic-messages",
17394
+ provider: "vercel-ai-gateway",
17395
+ baseUrl: "https://ai-gateway.vercel.sh",
17396
+ reasoning: true,
17397
+ input: ["text", "image"],
17398
+ cost: {
17399
+ input: 0.12,
17400
+ output: 0.39999999999999997,
17401
+ cacheRead: 0.01,
17402
+ cacheWrite: 0,
17403
+ },
17404
+ contextWindow: 1048576,
17405
+ maxTokens: 1048576,
17406
+ },
16671
17407
  "alibaba/qwen3.8-max": {
16672
17408
  id: "alibaba/qwen3.8-max",
16673
17409
  name: "Qwen 3.8 Max",
@@ -16685,6 +17421,23 @@ export const MODELS = {
16685
17421
  contextWindow: 1000000,
16686
17422
  maxTokens: 128000,
16687
17423
  },
17424
+ "alibaba/qwen3.8-max-0902": {
17425
+ id: "alibaba/qwen3.8-max-0902",
17426
+ name: "Qwen3.8 Max 0902",
17427
+ api: "anthropic-messages",
17428
+ provider: "vercel-ai-gateway",
17429
+ baseUrl: "https://ai-gateway.vercel.sh",
17430
+ reasoning: true,
17431
+ input: ["text", "image"],
17432
+ cost: {
17433
+ input: 2,
17434
+ output: 6,
17435
+ cacheRead: 0.25,
17436
+ cacheWrite: 2.5,
17437
+ },
17438
+ contextWindow: 991000,
17439
+ maxTokens: 128000,
17440
+ },
16688
17441
  "amazon/nova-2-lite": {
16689
17442
  id: "amazon/nova-2-lite",
16690
17443
  name: "Nova 2 Lite",
@@ -16788,6 +17541,24 @@ export const MODELS = {
16788
17541
  contextWindow: 1000000,
16789
17542
  maxTokens: 128000,
16790
17543
  },
17544
+ "anthropic/claude-fable-5.1": {
17545
+ id: "anthropic/claude-fable-5.1",
17546
+ name: "Claude Fable 5.1",
17547
+ api: "anthropic-messages",
17548
+ provider: "vercel-ai-gateway",
17549
+ baseUrl: "https://ai-gateway.vercel.sh",
17550
+ reasoning: true,
17551
+ thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
17552
+ input: ["text", "image"],
17553
+ cost: {
17554
+ input: 10,
17555
+ output: 50,
17556
+ cacheRead: 0.25,
17557
+ cacheWrite: 12.5,
17558
+ },
17559
+ contextWindow: 1000000,
17560
+ maxTokens: 128000,
17561
+ },
16791
17562
  "anthropic/claude-haiku-4.5": {
16792
17563
  id: "anthropic/claude-haiku-4.5",
16793
17564
  name: "Claude Haiku 4.5",
@@ -17098,23 +17869,6 @@ export const MODELS = {
17098
17869
  contextWindow: 128000,
17099
17870
  maxTokens: 8192,
17100
17871
  },
17101
- "deepseek/deepseek-v3": {
17102
- id: "deepseek/deepseek-v3",
17103
- name: "DeepSeek V3 0324",
17104
- api: "anthropic-messages",
17105
- provider: "vercel-ai-gateway",
17106
- baseUrl: "https://ai-gateway.vercel.sh",
17107
- reasoning: false,
17108
- input: ["text"],
17109
- cost: {
17110
- input: 0.27,
17111
- output: 1.12,
17112
- cacheRead: 0.135,
17113
- cacheWrite: 0,
17114
- },
17115
- contextWindow: 163840,
17116
- maxTokens: 163840,
17117
- },
17118
17872
  "deepseek/deepseek-v3.1": {
17119
17873
  id: "deepseek/deepseek-v3.1",
17120
17874
  name: "DeepSeek V3.1",
@@ -17231,8 +17985,8 @@ export const MODELS = {
17231
17985
  cacheRead: 0.007,
17232
17986
  cacheWrite: 0,
17233
17987
  },
17234
- contextWindow: 1000000,
17235
- maxTokens: 384000,
17988
+ contextWindow: 1048576,
17989
+ maxTokens: 1048576,
17236
17990
  },
17237
17991
  "deepseek/deepseek-v4-pro": {
17238
17992
  id: "deepseek/deepseek-v4-pro",
@@ -17438,6 +18192,23 @@ export const MODELS = {
17438
18192
  contextWindow: 1000000,
17439
18193
  maxTokens: 65536,
17440
18194
  },
18195
+ "google/gemini-3.8-flash": {
18196
+ id: "google/gemini-3.8-flash",
18197
+ name: "Gemini 3.8 Flash",
18198
+ api: "anthropic-messages",
18199
+ provider: "vercel-ai-gateway",
18200
+ baseUrl: "https://ai-gateway.vercel.sh",
18201
+ reasoning: true,
18202
+ input: ["text", "image"],
18203
+ cost: {
18204
+ input: 0.75,
18205
+ output: 3.75,
18206
+ cacheRead: 0.075,
18207
+ cacheWrite: 0,
18208
+ },
18209
+ contextWindow: 1000000,
18210
+ maxTokens: 65536,
18211
+ },
17441
18212
  "google/gemma-4-26b-a4b-it": {
17442
18213
  id: "google/gemma-4-26b-a4b-it",
17443
18214
  name: "Google Gemma 4 26B A4B",
@@ -17795,6 +18566,40 @@ export const MODELS = {
17795
18566
  contextWindow: 1048576,
17796
18567
  maxTokens: 1048576,
17797
18568
  },
18569
+ "meta/muse-spark-1.3": {
18570
+ id: "meta/muse-spark-1.3",
18571
+ name: "Muse Spark 1.3",
18572
+ api: "anthropic-messages",
18573
+ provider: "vercel-ai-gateway",
18574
+ baseUrl: "https://ai-gateway.vercel.sh",
18575
+ reasoning: true,
18576
+ input: ["text", "image"],
18577
+ cost: {
18578
+ input: 1.25,
18579
+ output: 4.25,
18580
+ cacheRead: 0.15,
18581
+ cacheWrite: 0,
18582
+ },
18583
+ contextWindow: 1048576,
18584
+ maxTokens: 1048576,
18585
+ },
18586
+ "meta/muse-spark-1.3-contributor": {
18587
+ id: "meta/muse-spark-1.3-contributor",
18588
+ name: "Muse Spark 1.3 Contributor",
18589
+ api: "anthropic-messages",
18590
+ provider: "vercel-ai-gateway",
18591
+ baseUrl: "https://ai-gateway.vercel.sh",
18592
+ reasoning: true,
18593
+ input: ["text", "image"],
18594
+ cost: {
18595
+ input: 0.09999999999999999,
18596
+ output: 0.19999999999999998,
18597
+ cacheRead: 0.002,
18598
+ cacheWrite: 0,
18599
+ },
18600
+ contextWindow: 1048576,
18601
+ maxTokens: 1048576,
18602
+ },
17798
18603
  "minimax/minimax-m2": {
17799
18604
  id: "minimax/minimax-m2",
17800
18605
  name: "MiniMax M2",
@@ -19765,6 +20570,23 @@ export const MODELS = {
19765
20570
  contextWindow: 1050000,
19766
20571
  maxTokens: 131000,
19767
20572
  },
20573
+ "xiaomi/mimo-v2.5-pro-ultraspeed": {
20574
+ id: "xiaomi/mimo-v2.5-pro-ultraspeed",
20575
+ name: "MiMo V2.5 Pro UltraSpeed",
20576
+ api: "anthropic-messages",
20577
+ provider: "vercel-ai-gateway",
20578
+ baseUrl: "https://ai-gateway.vercel.sh",
20579
+ reasoning: true,
20580
+ input: ["text"],
20581
+ cost: {
20582
+ input: 1.305,
20583
+ output: 2.61,
20584
+ cacheRead: 0.0108,
20585
+ cacheWrite: 0,
20586
+ },
20587
+ contextWindow: 1048576,
20588
+ maxTokens: 131072,
20589
+ },
19768
20590
  "zai/glm-4.5": {
19769
20591
  id: "zai/glm-4.5",
19770
20592
  name: "GLM 4.5",
@@ -19978,14 +20800,31 @@ export const MODELS = {
19978
20800
  reasoning: true,
19979
20801
  input: ["text"],
19980
20802
  cost: {
19981
- input: 1.4,
19982
- output: 4.4,
19983
- cacheRead: 0.14,
20803
+ input: 0.7,
20804
+ output: 2.2,
20805
+ cacheRead: 0.13,
19984
20806
  cacheWrite: 0,
19985
20807
  },
19986
20808
  contextWindow: 1000000,
19987
20809
  maxTokens: 1000000,
19988
20810
  },
20811
+ "zai/glm-5.3-fast": {
20812
+ id: "zai/glm-5.3-fast",
20813
+ name: "GLM 5.3 Fast",
20814
+ api: "anthropic-messages",
20815
+ provider: "vercel-ai-gateway",
20816
+ baseUrl: "https://ai-gateway.vercel.sh",
20817
+ reasoning: true,
20818
+ input: ["text"],
20819
+ cost: {
20820
+ input: 2.0999999999999996,
20821
+ output: 6.6000000000000005,
20822
+ cacheRead: 0.21,
20823
+ cacheWrite: 0,
20824
+ },
20825
+ contextWindow: 1048576,
20826
+ maxTokens: 262144,
20827
+ },
19989
20828
  "zai/glm-5.3-flash": {
19990
20829
  id: "zai/glm-5.3-flash",
19991
20830
  name: "GLM 5.3 Flash",
@@ -20003,6 +20842,23 @@ export const MODELS = {
20003
20842
  contextWindow: 1000000,
20004
20843
  maxTokens: 131000,
20005
20844
  },
20845
+ "zai/glm-5.3-promo-50": {
20846
+ id: "zai/glm-5.3-promo-50",
20847
+ name: "GLM 5.3 (50% off)",
20848
+ api: "anthropic-messages",
20849
+ provider: "vercel-ai-gateway",
20850
+ baseUrl: "https://ai-gateway.vercel.sh",
20851
+ reasoning: true,
20852
+ input: ["text"],
20853
+ cost: {
20854
+ input: 0.7,
20855
+ output: 2.2,
20856
+ cacheRead: 0.13,
20857
+ cacheWrite: 0,
20858
+ },
20859
+ contextWindow: 1048576,
20860
+ maxTokens: 1048576,
20861
+ },
20006
20862
  "zai/glm-5v-turbo": {
20007
20863
  id: "zai/glm-5v-turbo",
20008
20864
  name: "GLM 5V Turbo",