@elyracode/ai 0.9.32 → 0.9.34

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)",
@@ -828,10 +866,10 @@ export const MODELS = {
828
866
  reasoning: true,
829
867
  input: ["text", "image"],
830
868
  cost: {
831
- input: 0.22,
832
- output: 1.32,
833
- cacheRead: 0.022,
834
- cacheWrite: 0.275,
869
+ input: 0.2,
870
+ output: 1.2,
871
+ cacheRead: 0.02,
872
+ cacheWrite: 0.25,
835
873
  },
836
874
  contextWindow: 1050000,
837
875
  maxTokens: 128000,
@@ -845,10 +883,10 @@ export const MODELS = {
845
883
  reasoning: true,
846
884
  input: ["text", "image"],
847
885
  cost: {
848
- input: 5.5,
849
- output: 33,
850
- cacheRead: 0.55,
851
- cacheWrite: 6.875,
886
+ input: 4,
887
+ output: 20,
888
+ cacheRead: 0.4,
889
+ cacheWrite: 5,
852
890
  },
853
891
  contextWindow: 1050000,
854
892
  maxTokens: 128000,
@@ -862,10 +900,10 @@ export const MODELS = {
862
900
  reasoning: true,
863
901
  input: ["text", "image"],
864
902
  cost: {
865
- input: 2.2,
866
- output: 13.2,
867
- cacheRead: 0.22,
868
- cacheWrite: 2.75,
903
+ input: 2,
904
+ output: 12,
905
+ cacheRead: 0.2,
906
+ cacheWrite: 2.5,
869
907
  },
870
908
  contextWindow: 1050000,
871
909
  maxTokens: 128000,
@@ -1485,10 +1523,10 @@ export const MODELS = {
1485
1523
  reasoning: true,
1486
1524
  input: ["text", "image"],
1487
1525
  cost: {
1488
- input: 5.5,
1489
- output: 33,
1490
- cacheRead: 0.55,
1491
- cacheWrite: 6.875,
1526
+ input: 4.4,
1527
+ output: 22,
1528
+ cacheRead: 0.44,
1529
+ cacheWrite: 5.5,
1492
1530
  },
1493
1531
  contextWindow: 1050000,
1494
1532
  maxTokens: 128000,
@@ -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)",
@@ -3872,6 +3948,42 @@ export const MODELS = {
3872
3948
  contextWindow: 262144,
3873
3949
  maxTokens: 256000,
3874
3950
  },
3951
+ "@cf/zai-org/glm-5.3": {
3952
+ id: "@cf/zai-org/glm-5.3",
3953
+ name: "Glm 5.3",
3954
+ api: "openai-completions",
3955
+ provider: "cloudflare-workers-ai",
3956
+ baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
3957
+ compat: { "sendSessionAffinityHeaders": true },
3958
+ reasoning: true,
3959
+ input: ["text"],
3960
+ cost: {
3961
+ input: 1.4,
3962
+ output: 4.4,
3963
+ cacheRead: 0.26,
3964
+ cacheWrite: 0,
3965
+ },
3966
+ contextWindow: 1310720,
3967
+ maxTokens: 1310720,
3968
+ },
3969
+ "@cf/zai-org/glm-5.3-flash": {
3970
+ id: "@cf/zai-org/glm-5.3-flash",
3971
+ name: "Glm 5.3 Flash",
3972
+ api: "openai-completions",
3973
+ provider: "cloudflare-workers-ai",
3974
+ baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
3975
+ compat: { "sendSessionAffinityHeaders": true },
3976
+ reasoning: true,
3977
+ input: ["text", "image"],
3978
+ cost: {
3979
+ input: 0.15,
3980
+ output: 0.5,
3981
+ cacheRead: 0.03,
3982
+ cacheWrite: 0,
3983
+ },
3984
+ contextWindow: 1310720,
3985
+ maxTokens: 1048576,
3986
+ },
3875
3987
  },
3876
3988
  "deepseek": {
3877
3989
  "deepseek-v4-flash": {
@@ -3914,23 +4026,6 @@ export const MODELS = {
3914
4026
  },
3915
4027
  },
3916
4028
  "fireworks": {
3917
- "accounts/fireworks/models/deepseek-v4-flash": {
3918
- id: "accounts/fireworks/models/deepseek-v4-flash",
3919
- name: "DeepSeek V4 Flash",
3920
- api: "anthropic-messages",
3921
- provider: "fireworks",
3922
- baseUrl: "https://api.fireworks.ai/inference",
3923
- reasoning: true,
3924
- input: ["text"],
3925
- cost: {
3926
- input: 0.14,
3927
- output: 0.28,
3928
- cacheRead: 0.028,
3929
- cacheWrite: 0,
3930
- },
3931
- contextWindow: 1000000,
3932
- maxTokens: 384000,
3933
- },
3934
4029
  "accounts/fireworks/models/deepseek-v4-flash-0731": {
3935
4030
  id: "accounts/fireworks/models/deepseek-v4-flash-0731",
3936
4031
  name: "DeepSeek V4 Flash 0731",
@@ -3948,23 +4043,6 @@ export const MODELS = {
3948
4043
  contextWindow: 1000000,
3949
4044
  maxTokens: 384000,
3950
4045
  },
3951
- "accounts/fireworks/models/deepseek-v4-pro": {
3952
- id: "accounts/fireworks/models/deepseek-v4-pro",
3953
- name: "DeepSeek V4 Pro",
3954
- api: "anthropic-messages",
3955
- provider: "fireworks",
3956
- baseUrl: "https://api.fireworks.ai/inference",
3957
- reasoning: true,
3958
- input: ["text"],
3959
- cost: {
3960
- input: 1.74,
3961
- output: 3.48,
3962
- cacheRead: 0.145,
3963
- cacheWrite: 0,
3964
- },
3965
- contextWindow: 1000000,
3966
- maxTokens: 384000,
3967
- },
3968
4046
  "accounts/fireworks/models/deepseek-v4-pro-0813": {
3969
4047
  id: "accounts/fireworks/models/deepseek-v4-pro-0813",
3970
4048
  name: "DeepSeek V4 Pro 0813",
@@ -3999,35 +4077,52 @@ export const MODELS = {
3999
4077
  contextWindow: 1048575,
4000
4078
  maxTokens: 131072,
4001
4079
  },
4002
- "accounts/fireworks/models/gpt-oss-120b": {
4003
- id: "accounts/fireworks/models/gpt-oss-120b",
4004
- name: "GPT OSS 120B",
4080
+ "accounts/fireworks/models/glm-5p3": {
4081
+ id: "accounts/fireworks/models/glm-5p3",
4082
+ name: "GLM 5.3",
4005
4083
  api: "anthropic-messages",
4006
4084
  provider: "fireworks",
4007
4085
  baseUrl: "https://api.fireworks.ai/inference",
4008
4086
  reasoning: true,
4009
4087
  input: ["text"],
4088
+ cost: {
4089
+ input: 1.4,
4090
+ output: 4.4,
4091
+ cacheRead: 0.26,
4092
+ cacheWrite: 0,
4093
+ },
4094
+ contextWindow: 1000000,
4095
+ maxTokens: 131072,
4096
+ },
4097
+ "accounts/fireworks/models/glm-5p3-flash": {
4098
+ id: "accounts/fireworks/models/glm-5p3-flash",
4099
+ name: "GLM 5.3 Flash",
4100
+ api: "anthropic-messages",
4101
+ provider: "fireworks",
4102
+ baseUrl: "https://api.fireworks.ai/inference",
4103
+ reasoning: true,
4104
+ input: ["text", "image"],
4010
4105
  cost: {
4011
4106
  input: 0.15,
4012
- output: 0.6,
4013
- cacheRead: 0.015,
4107
+ output: 0.5,
4108
+ cacheRead: 0.029,
4014
4109
  cacheWrite: 0,
4015
4110
  },
4016
- contextWindow: 131072,
4017
- maxTokens: 32768,
4111
+ contextWindow: 1000000,
4112
+ maxTokens: 131072,
4018
4113
  },
4019
- "accounts/fireworks/models/gpt-oss-20b": {
4020
- id: "accounts/fireworks/models/gpt-oss-20b",
4021
- name: "GPT OSS 20B",
4114
+ "accounts/fireworks/models/gpt-oss-120b": {
4115
+ id: "accounts/fireworks/models/gpt-oss-120b",
4116
+ name: "GPT OSS 120B",
4022
4117
  api: "anthropic-messages",
4023
4118
  provider: "fireworks",
4024
4119
  baseUrl: "https://api.fireworks.ai/inference",
4025
4120
  reasoning: true,
4026
4121
  input: ["text"],
4027
4122
  cost: {
4028
- input: 0.07,
4029
- output: 0.3,
4030
- cacheRead: 0.035,
4123
+ input: 0.15,
4124
+ output: 0.6,
4125
+ cacheRead: 0.015,
4031
4126
  cacheWrite: 0,
4032
4127
  },
4033
4128
  contextWindow: 131072,
@@ -4101,23 +4196,6 @@ export const MODELS = {
4101
4196
  contextWindow: 1048576,
4102
4197
  maxTokens: 131072,
4103
4198
  },
4104
- "accounts/fireworks/models/minimax-m2p7": {
4105
- id: "accounts/fireworks/models/minimax-m2p7",
4106
- name: "MiniMax-M2.7",
4107
- api: "anthropic-messages",
4108
- provider: "fireworks",
4109
- baseUrl: "https://api.fireworks.ai/inference",
4110
- reasoning: true,
4111
- input: ["text"],
4112
- cost: {
4113
- input: 0.3,
4114
- output: 1.2,
4115
- cacheRead: 0.06,
4116
- cacheWrite: 0,
4117
- },
4118
- contextWindow: 196608,
4119
- maxTokens: 196608,
4120
- },
4121
4199
  "accounts/fireworks/models/minimax-m3": {
4122
4200
  id: "accounts/fireworks/models/minimax-m3",
4123
4201
  name: "MiniMax-M3",
@@ -4237,57 +4315,6 @@ export const MODELS = {
4237
4315
  contextWindow: 1048575,
4238
4316
  maxTokens: 131072,
4239
4317
  },
4240
- "accounts/fireworks/routers/kimi-k2p6-fast": {
4241
- id: "accounts/fireworks/routers/kimi-k2p6-fast",
4242
- name: "Kimi K2.6 Fast",
4243
- api: "anthropic-messages",
4244
- provider: "fireworks",
4245
- baseUrl: "https://api.fireworks.ai/inference",
4246
- reasoning: true,
4247
- input: ["text", "image"],
4248
- cost: {
4249
- input: 2,
4250
- output: 8,
4251
- cacheRead: 0.3,
4252
- cacheWrite: 0,
4253
- },
4254
- contextWindow: 262000,
4255
- maxTokens: 262000,
4256
- },
4257
- "accounts/fireworks/routers/kimi-k2p6-turbo": {
4258
- id: "accounts/fireworks/routers/kimi-k2p6-turbo",
4259
- name: "Kimi K2.6 Turbo",
4260
- api: "anthropic-messages",
4261
- provider: "fireworks",
4262
- baseUrl: "https://api.fireworks.ai/inference",
4263
- reasoning: true,
4264
- input: ["text", "image"],
4265
- cost: {
4266
- input: 2,
4267
- output: 8,
4268
- cacheRead: 0.3,
4269
- cacheWrite: 0,
4270
- },
4271
- contextWindow: 262000,
4272
- maxTokens: 262000,
4273
- },
4274
- "accounts/fireworks/routers/kimi-k2p7-code-fast": {
4275
- id: "accounts/fireworks/routers/kimi-k2p7-code-fast",
4276
- name: "Kimi K2.7 Code Fast",
4277
- api: "anthropic-messages",
4278
- provider: "fireworks",
4279
- baseUrl: "https://api.fireworks.ai/inference",
4280
- reasoning: true,
4281
- input: ["text", "image"],
4282
- cost: {
4283
- input: 1.9,
4284
- output: 8,
4285
- cacheRead: 0.38,
4286
- cacheWrite: 0,
4287
- },
4288
- contextWindow: 262000,
4289
- maxTokens: 262000,
4290
- },
4291
4318
  "accounts/fireworks/routers/kimi-k3-fast": {
4292
4319
  id: "accounts/fireworks/routers/kimi-k3-fast",
4293
4320
  name: "Kimi K3 Fast",
@@ -4564,9 +4591,9 @@ export const MODELS = {
4564
4591
  reasoning: true,
4565
4592
  input: ["text", "image"],
4566
4593
  cost: {
4567
- input: 1.5,
4568
- output: 7.5,
4569
- cacheRead: 0.15,
4594
+ input: 0.75,
4595
+ output: 3.75,
4596
+ cacheRead: 0.075,
4570
4597
  cacheWrite: 0,
4571
4598
  },
4572
4599
  contextWindow: 1000000,
@@ -4776,7 +4803,7 @@ export const MODELS = {
4776
4803
  input: 0.2,
4777
4804
  output: 1.2,
4778
4805
  cacheRead: 0.02,
4779
- cacheWrite: 0,
4806
+ cacheWrite: 0.25,
4780
4807
  },
4781
4808
  contextWindow: 1050000,
4782
4809
  maxTokens: 128000,
@@ -4792,11 +4819,11 @@ export const MODELS = {
4792
4819
  thinkingLevelMap: { "off": null },
4793
4820
  input: ["text", "image"],
4794
4821
  cost: {
4795
- input: 2.5,
4796
- output: 15,
4797
- cacheRead: 0.25,
4798
- cacheWrite: 3.125,
4799
- },
4822
+ input: 2,
4823
+ output: 10,
4824
+ cacheRead: 0.2,
4825
+ cacheWrite: 2.5,
4826
+ },
4800
4827
  contextWindow: 1050000,
4801
4828
  maxTokens: 128000,
4802
4829
  },
@@ -4814,7 +4841,7 @@ export const MODELS = {
4814
4841
  input: 2,
4815
4842
  output: 12,
4816
4843
  cacheRead: 0.2,
4817
- cacheWrite: 0,
4844
+ cacheWrite: 2.5,
4818
4845
  },
4819
4846
  contextWindow: 1050000,
4820
4847
  maxTokens: 128000,
@@ -5269,23 +5296,6 @@ export const MODELS = {
5269
5296
  contextWindow: 1048576,
5270
5297
  maxTokens: 65536,
5271
5298
  },
5272
- "gemini-robotics-er-1.6-preview": {
5273
- id: "gemini-robotics-er-1.6-preview",
5274
- name: "Gemini Robotics-ER 1.6 Preview",
5275
- api: "google-generative-ai",
5276
- provider: "google",
5277
- baseUrl: "https://generativelanguage.googleapis.com/v1beta",
5278
- reasoning: true,
5279
- input: ["text", "image"],
5280
- cost: {
5281
- input: 1,
5282
- output: 5,
5283
- cacheRead: 0,
5284
- cacheWrite: 0,
5285
- },
5286
- contextWindow: 131072,
5287
- maxTokens: 65536,
5288
- },
5289
5299
  "gemma-4-26b-a4b-it": {
5290
5300
  id: "gemma-4-26b-a4b-it",
5291
5301
  name: "Gemma 4 26B A4B IT",
@@ -5653,6 +5663,23 @@ export const MODELS = {
5653
5663
  contextWindow: 131072,
5654
5664
  maxTokens: 16384,
5655
5665
  },
5666
+ "qwen/qwen3.8-27b": {
5667
+ id: "qwen/qwen3.8-27b",
5668
+ name: "Qwen3.8 27B",
5669
+ api: "openai-completions",
5670
+ provider: "groq",
5671
+ baseUrl: "https://api.groq.com/openai/v1",
5672
+ reasoning: true,
5673
+ input: ["text", "image"],
5674
+ cost: {
5675
+ input: 0.8,
5676
+ output: 4,
5677
+ cacheRead: 0,
5678
+ cacheWrite: 0,
5679
+ },
5680
+ contextWindow: 131042,
5681
+ maxTokens: 16384,
5682
+ },
5656
5683
  },
5657
5684
  "huggingface": {
5658
5685
  "MiniMaxAI/MiniMax-M2": {
@@ -5671,7 +5698,7 @@ export const MODELS = {
5671
5698
  cacheWrite: 0,
5672
5699
  },
5673
5700
  contextWindow: 204800,
5674
- maxTokens: 128000,
5701
+ maxTokens: 131072,
5675
5702
  },
5676
5703
  "MiniMaxAI/MiniMax-M2.1": {
5677
5704
  id: "MiniMaxAI/MiniMax-M2.1",
@@ -5743,7 +5770,7 @@ export const MODELS = {
5743
5770
  cacheWrite: 0,
5744
5771
  },
5745
5772
  contextWindow: 524288,
5746
- maxTokens: 128000,
5773
+ maxTokens: 512000,
5747
5774
  },
5748
5775
  "Qwen/Qwen2.5-Coder-32B-Instruct": {
5749
5776
  id: "Qwen/Qwen2.5-Coder-32B-Instruct",
@@ -6123,6 +6150,24 @@ export const MODELS = {
6123
6150
  contextWindow: 262144,
6124
6151
  maxTokens: 131072,
6125
6152
  },
6153
+ "Qwen/Qwen3.8-27B": {
6154
+ id: "Qwen/Qwen3.8-27B",
6155
+ name: "Qwen3.8 27B",
6156
+ api: "openai-completions",
6157
+ provider: "huggingface",
6158
+ baseUrl: "https://router.huggingface.co/v1",
6159
+ compat: { "supportsDeveloperRole": false },
6160
+ reasoning: true,
6161
+ input: ["text", "image"],
6162
+ cost: {
6163
+ input: 0.4,
6164
+ output: 3,
6165
+ cacheRead: 0,
6166
+ cacheWrite: 0,
6167
+ },
6168
+ contextWindow: 262144,
6169
+ maxTokens: 32768,
6170
+ },
6126
6171
  "XiaomiMiMo/MiMo-V2.5": {
6127
6172
  id: "XiaomiMiMo/MiMo-V2.5",
6128
6173
  name: "MiMo-V2.5",
@@ -6843,6 +6888,42 @@ export const MODELS = {
6843
6888
  contextWindow: 262144,
6844
6889
  maxTokens: 131072,
6845
6890
  },
6891
+ "zai-org/GLM-5.3": {
6892
+ id: "zai-org/GLM-5.3",
6893
+ name: "GLM-5.3",
6894
+ api: "openai-completions",
6895
+ provider: "huggingface",
6896
+ baseUrl: "https://router.huggingface.co/v1",
6897
+ compat: { "supportsDeveloperRole": false },
6898
+ reasoning: true,
6899
+ input: ["text"],
6900
+ cost: {
6901
+ input: 1.4,
6902
+ output: 4.4,
6903
+ cacheRead: 0,
6904
+ cacheWrite: 0,
6905
+ },
6906
+ contextWindow: 1048576,
6907
+ maxTokens: 131072,
6908
+ },
6909
+ "zai-org/GLM-5.3-Flash": {
6910
+ id: "zai-org/GLM-5.3-Flash",
6911
+ name: "GLM-5.3-Flash",
6912
+ api: "openai-completions",
6913
+ provider: "huggingface",
6914
+ baseUrl: "https://router.huggingface.co/v1",
6915
+ compat: { "supportsDeveloperRole": false },
6916
+ reasoning: true,
6917
+ input: ["text", "image"],
6918
+ cost: {
6919
+ input: 0.15,
6920
+ output: 0.5,
6921
+ cacheRead: 0,
6922
+ cacheWrite: 0,
6923
+ },
6924
+ contextWindow: 1048576,
6925
+ maxTokens: 131072,
6926
+ },
6846
6927
  },
6847
6928
  "kimi-coding": {
6848
6929
  "k3": {
@@ -6967,8 +7048,8 @@ export const MODELS = {
6967
7048
  cacheRead: 0.06,
6968
7049
  cacheWrite: 0,
6969
7050
  },
6970
- contextWindow: 1000000,
6971
- maxTokens: 128000,
7051
+ contextWindow: 1048576,
7052
+ maxTokens: 512000,
6972
7053
  },
6973
7054
  },
6974
7055
  "minimax-cn": {
@@ -7020,8 +7101,8 @@ export const MODELS = {
7020
7101
  cacheRead: 0.06,
7021
7102
  cacheWrite: 0,
7022
7103
  },
7023
- contextWindow: 1000000,
7024
- maxTokens: 128000,
7104
+ contextWindow: 1048576,
7105
+ maxTokens: 512000,
7025
7106
  },
7026
7107
  },
7027
7108
  "mistral": {
@@ -7552,6 +7633,23 @@ export const MODELS = {
7552
7633
  contextWindow: 32000,
7553
7634
  maxTokens: 32000,
7554
7635
  },
7636
+ "zai-glm-5-2": {
7637
+ id: "zai-glm-5-2",
7638
+ name: "GLM-5.2",
7639
+ api: "mistral-conversations",
7640
+ provider: "mistral",
7641
+ baseUrl: "https://api.mistral.ai",
7642
+ reasoning: true,
7643
+ input: ["text"],
7644
+ cost: {
7645
+ input: 1.4,
7646
+ output: 4.4,
7647
+ cacheRead: 0.14,
7648
+ cacheWrite: 0,
7649
+ },
7650
+ contextWindow: 1000000,
7651
+ maxTokens: 131072,
7652
+ },
7555
7653
  },
7556
7654
  "moonshotai": {
7557
7655
  "kimi-k2-0711-preview": {
@@ -8788,6 +8886,24 @@ export const MODELS = {
8788
8886
  contextWindow: 1000000,
8789
8887
  maxTokens: 128000,
8790
8888
  },
8889
+ "claude-fable-5-1": {
8890
+ id: "claude-fable-5-1",
8891
+ name: "Claude Fable 5.1",
8892
+ api: "anthropic-messages",
8893
+ provider: "opencode",
8894
+ baseUrl: "https://opencode.ai/zen",
8895
+ reasoning: true,
8896
+ thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
8897
+ input: ["text", "image"],
8898
+ cost: {
8899
+ input: 10,
8900
+ output: 50,
8901
+ cacheRead: 0.25,
8902
+ cacheWrite: 12.5,
8903
+ },
8904
+ contextWindow: 1000000,
8905
+ maxTokens: 128000,
8906
+ },
8791
8907
  "claude-haiku-4-5": {
8792
8908
  id: "claude-haiku-4-5",
8793
8909
  name: "Claude Haiku 4.5",
@@ -9511,7 +9627,7 @@ export const MODELS = {
9511
9627
  cost: {
9512
9628
  input: 2,
9513
9629
  output: 6,
9514
- cacheRead: 0.5,
9630
+ cacheRead: 0.3,
9515
9631
  cacheWrite: 0,
9516
9632
  },
9517
9633
  contextWindow: 500000,
@@ -9551,23 +9667,6 @@ export const MODELS = {
9551
9667
  contextWindow: 256000,
9552
9668
  maxTokens: 256000,
9553
9669
  },
9554
- "hy3-free": {
9555
- id: "hy3-free",
9556
- name: "Hy3 Free",
9557
- api: "openai-completions",
9558
- provider: "opencode",
9559
- baseUrl: "https://opencode.ai/zen/v1",
9560
- reasoning: true,
9561
- input: ["text"],
9562
- cost: {
9563
- input: 0,
9564
- output: 0,
9565
- cacheRead: 0,
9566
- cacheWrite: 0,
9567
- },
9568
- contextWindow: 190000,
9569
- maxTokens: 64000,
9570
- },
9571
9670
  "kimi-k2.5": {
9572
9671
  id: "kimi-k2.5",
9573
9672
  name: "Kimi K2.5",
@@ -9636,6 +9735,23 @@ export const MODELS = {
9636
9735
  contextWindow: 1048576,
9637
9736
  maxTokens: 131072,
9638
9737
  },
9738
+ "ling-3.0-flash-fin-free": {
9739
+ id: "ling-3.0-flash-fin-free",
9740
+ name: "Ling 3.0 Flash Fin Free",
9741
+ api: "openai-completions",
9742
+ provider: "opencode",
9743
+ baseUrl: "https://opencode.ai/zen/v1",
9744
+ reasoning: true,
9745
+ input: ["text"],
9746
+ cost: {
9747
+ input: 0,
9748
+ output: 0,
9749
+ cacheRead: 0,
9750
+ cacheWrite: 0,
9751
+ },
9752
+ contextWindow: 262144,
9753
+ maxTokens: 32768,
9754
+ },
9639
9755
  "mimo-v2.5-free": {
9640
9756
  id: "mimo-v2.5-free",
9641
9757
  name: "MiMo V2.5 Free",
@@ -9806,23 +9922,6 @@ export const MODELS = {
9806
9922
  contextWindow: 262144,
9807
9923
  maxTokens: 65536,
9808
9924
  },
9809
- "x-preview-f-free": {
9810
- id: "x-preview-f-free",
9811
- name: "Ox Alpha Free (Unlimited)",
9812
- api: "openai-completions",
9813
- provider: "opencode",
9814
- baseUrl: "https://opencode.ai/zen/v1",
9815
- reasoning: true,
9816
- input: ["text", "image"],
9817
- cost: {
9818
- input: 0,
9819
- output: 0,
9820
- cacheRead: 0,
9821
- cacheWrite: 0,
9822
- },
9823
- contextWindow: 1000000,
9824
- maxTokens: 131072,
9825
- },
9826
9925
  },
9827
9926
  "opencode-go": {
9828
9927
  "deepseek-v4-flash": {
@@ -9933,6 +10032,23 @@ export const MODELS = {
9933
10032
  contextWindow: 1000000,
9934
10033
  maxTokens: 131072,
9935
10034
  },
10035
+ "glm-5.3-flash": {
10036
+ id: "glm-5.3-flash",
10037
+ name: "GLM-5.3-Flash (2x usage)",
10038
+ api: "openai-completions",
10039
+ provider: "opencode-go",
10040
+ baseUrl: "https://opencode.ai/zen/go/v1",
10041
+ reasoning: true,
10042
+ input: ["text", "image"],
10043
+ cost: {
10044
+ input: 0.075,
10045
+ output: 0.25,
10046
+ cacheRead: 0.015,
10047
+ cacheWrite: 0,
10048
+ },
10049
+ contextWindow: 1000000,
10050
+ maxTokens: 131072,
10051
+ },
9936
10052
  "gpt-5.6-luna": {
9937
10053
  id: "gpt-5.6-luna",
9938
10054
  name: "GPT-5.6 Luna",
@@ -9951,9 +10067,9 @@ export const MODELS = {
9951
10067
  contextWindow: 1050000,
9952
10068
  maxTokens: 128000,
9953
10069
  },
9954
- "grok-4.5": {
9955
- id: "grok-4.5",
9956
- name: "Grok 4.5",
10070
+ "grok-4.6": {
10071
+ id: "grok-4.6",
10072
+ name: "Grok 4.6",
9957
10073
  api: "openai-responses",
9958
10074
  provider: "opencode-go",
9959
10075
  baseUrl: "https://opencode.ai/zen/go/v1",
@@ -9970,21 +10086,38 @@ export const MODELS = {
9970
10086
  },
9971
10087
  "hy3": {
9972
10088
  id: "hy3",
9973
- name: "Hy3 (8x usage)",
10089
+ name: "Hy3",
9974
10090
  api: "openai-completions",
9975
10091
  provider: "opencode-go",
9976
10092
  baseUrl: "https://opencode.ai/zen/go/v1",
9977
10093
  reasoning: true,
9978
10094
  input: ["text"],
9979
10095
  cost: {
9980
- input: 0.0175,
9981
- output: 0.0725,
9982
- cacheRead: 0.004375,
10096
+ input: 0.14,
10097
+ output: 0.58,
10098
+ cacheRead: 0.035,
9983
10099
  cacheWrite: 0,
9984
10100
  },
9985
10101
  contextWindow: 256000,
9986
10102
  maxTokens: 64000,
9987
10103
  },
10104
+ "hy4-preview": {
10105
+ id: "hy4-preview",
10106
+ name: "Hy4 preview",
10107
+ api: "openai-completions",
10108
+ provider: "opencode-go",
10109
+ baseUrl: "https://opencode.ai/zen/go/v1",
10110
+ reasoning: true,
10111
+ input: ["text"],
10112
+ cost: {
10113
+ input: 0.834,
10114
+ output: 2.501,
10115
+ cacheRead: 0.042,
10116
+ cacheWrite: 0,
10117
+ },
10118
+ contextWindow: 1024000,
10119
+ maxTokens: 64000,
10120
+ },
9988
10121
  "kimi-k2.6": {
9989
10122
  id: "kimi-k2.6",
9990
10123
  name: "Kimi K2.6",
@@ -10138,23 +10271,6 @@ export const MODELS = {
10138
10271
  contextWindow: 1048576,
10139
10272
  maxTokens: 131072,
10140
10273
  },
10141
- "ox-alpha-free": {
10142
- id: "ox-alpha-free",
10143
- name: "Ox Alpha Free (Unlimited)",
10144
- api: "openai-completions",
10145
- provider: "opencode-go",
10146
- baseUrl: "https://opencode.ai/zen/go/v1",
10147
- reasoning: true,
10148
- input: ["text", "image"],
10149
- cost: {
10150
- input: 0,
10151
- output: 0,
10152
- cacheRead: 0,
10153
- cacheWrite: 0,
10154
- },
10155
- contextWindow: 1000000,
10156
- maxTokens: 131072,
10157
- },
10158
10274
  "qwen3.6-plus": {
10159
10275
  id: "qwen3.6-plus",
10160
10276
  name: "Qwen3.6 Plus",
@@ -10207,6 +10323,23 @@ export const MODELS = {
10207
10323
  contextWindow: 1000000,
10208
10324
  maxTokens: 65536,
10209
10325
  },
10326
+ "qwen3.8-flash": {
10327
+ id: "qwen3.8-flash",
10328
+ name: "Qwen3.8 Flash",
10329
+ api: "anthropic-messages",
10330
+ provider: "opencode-go",
10331
+ baseUrl: "https://opencode.ai/zen/go",
10332
+ reasoning: true,
10333
+ input: ["text", "image"],
10334
+ cost: {
10335
+ input: 0.15,
10336
+ output: 0.47,
10337
+ cacheRead: 0.016,
10338
+ cacheWrite: 0.2,
10339
+ },
10340
+ contextWindow: 1000000,
10341
+ maxTokens: 131072,
10342
+ },
10210
10343
  "qwen3.8-max": {
10211
10344
  id: "qwen3.8-max",
10212
10345
  name: "Qwen3.8 Max",
@@ -10397,6 +10530,24 @@ export const MODELS = {
10397
10530
  contextWindow: 1000000,
10398
10531
  maxTokens: 128000,
10399
10532
  },
10533
+ "anthropic/claude-fable-5.1": {
10534
+ id: "anthropic/claude-fable-5.1",
10535
+ name: "Anthropic: Claude Fable 5.1",
10536
+ api: "openai-completions",
10537
+ provider: "openrouter",
10538
+ baseUrl: "https://openrouter.ai/api/v1",
10539
+ reasoning: true,
10540
+ thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
10541
+ input: ["text", "image"],
10542
+ cost: {
10543
+ input: 10,
10544
+ output: 50,
10545
+ cacheRead: 0.25,
10546
+ cacheWrite: 12.5,
10547
+ },
10548
+ contextWindow: 1000000,
10549
+ maxTokens: 128000,
10550
+ },
10400
10551
  "anthropic/claude-fable-5:batch": {
10401
10552
  id: "anthropic/claude-fable-5:batch",
10402
10553
  name: "Anthropic: Claude Fable 5 (batch)",
@@ -10588,24 +10739,6 @@ export const MODELS = {
10588
10739
  contextWindow: 1000000,
10589
10740
  maxTokens: 128000,
10590
10741
  },
10591
- "anthropic/claude-opus-4.7-fast": {
10592
- id: "anthropic/claude-opus-4.7-fast",
10593
- name: "Anthropic: Claude Opus 4.7 (Fast)",
10594
- api: "openai-completions",
10595
- provider: "openrouter",
10596
- baseUrl: "https://openrouter.ai/api/v1",
10597
- reasoning: true,
10598
- thinkingLevelMap: { "xhigh": "xhigh" },
10599
- input: ["text", "image"],
10600
- cost: {
10601
- input: 30,
10602
- output: 150,
10603
- cacheRead: 3,
10604
- cacheWrite: 37.5,
10605
- },
10606
- contextWindow: 1000000,
10607
- maxTokens: 128000,
10608
- },
10609
10742
  "anthropic/claude-opus-4.7:batch": {
10610
10743
  id: "anthropic/claude-opus-4.7:batch",
10611
10744
  name: "Anthropic: Claude Opus 4.7 (batch)",
@@ -10642,24 +10775,6 @@ export const MODELS = {
10642
10775
  contextWindow: 1000000,
10643
10776
  maxTokens: 128000,
10644
10777
  },
10645
- "anthropic/claude-opus-4.8-fast": {
10646
- id: "anthropic/claude-opus-4.8-fast",
10647
- name: "Anthropic: Claude Opus 4.8 (Fast)",
10648
- api: "openai-completions",
10649
- provider: "openrouter",
10650
- baseUrl: "https://openrouter.ai/api/v1",
10651
- reasoning: true,
10652
- thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "max", "xhigh": "ultracode" },
10653
- input: ["text", "image"],
10654
- cost: {
10655
- input: 10,
10656
- output: 50,
10657
- cacheRead: 1,
10658
- cacheWrite: 12.5,
10659
- },
10660
- contextWindow: 1000000,
10661
- maxTokens: 128000,
10662
- },
10663
10778
  "anthropic/claude-opus-4.8:batch": {
10664
10779
  id: "anthropic/claude-opus-4.8:batch",
10665
10780
  name: "Anthropic: Claude Opus 4.8 (batch)",
@@ -10695,23 +10810,6 @@ export const MODELS = {
10695
10810
  contextWindow: 1000000,
10696
10811
  maxTokens: 128000,
10697
10812
  },
10698
- "anthropic/claude-opus-5-fast": {
10699
- id: "anthropic/claude-opus-5-fast",
10700
- name: "Claude Opus 5 (Fast)",
10701
- api: "openai-completions",
10702
- provider: "openrouter",
10703
- baseUrl: "https://openrouter.ai/api/v1",
10704
- reasoning: true,
10705
- input: ["text", "image"],
10706
- cost: {
10707
- input: 10,
10708
- output: 50,
10709
- cacheRead: 1,
10710
- cacheWrite: 12.5,
10711
- },
10712
- contextWindow: 1000000,
10713
- maxTokens: 128000,
10714
- },
10715
10813
  "anthropic/claude-opus-5:batch": {
10716
10814
  id: "anthropic/claude-opus-5:batch",
10717
10815
  name: "Claude Opus 5 (batch)",
@@ -10857,30 +10955,13 @@ export const MODELS = {
10857
10955
  reasoning: true,
10858
10956
  input: ["text"],
10859
10957
  cost: {
10860
- input: 0.22,
10861
- output: 0.85,
10958
+ input: 0.25,
10959
+ output: 0.7999999999999999,
10862
10960
  cacheRead: 0.06,
10863
10961
  cacheWrite: 0,
10864
10962
  },
10865
10963
  contextWindow: 262144,
10866
- maxTokens: 262144,
10867
- },
10868
- "arcee-ai/virtuoso-large": {
10869
- id: "arcee-ai/virtuoso-large",
10870
- name: "Arcee AI: Virtuoso Large",
10871
- api: "openai-completions",
10872
- provider: "openrouter",
10873
- baseUrl: "https://openrouter.ai/api/v1",
10874
- reasoning: false,
10875
- input: ["text"],
10876
- cost: {
10877
- input: 0.75,
10878
- output: 1.2,
10879
- cacheRead: 0,
10880
- cacheWrite: 0,
10881
- },
10882
- contextWindow: 131072,
10883
- maxTokens: 64000,
10964
+ maxTokens: 80000,
10884
10965
  },
10885
10966
  "auto": {
10886
10967
  id: "auto",
@@ -10948,7 +11029,7 @@ export const MODELS = {
10948
11029
  cacheWrite: 0,
10949
11030
  },
10950
11031
  contextWindow: 262144,
10951
- maxTokens: 262144,
11032
+ maxTokens: 235929,
10952
11033
  },
10953
11034
  "bytedance-seed/seed-2.0-code": {
10954
11035
  id: "bytedance-seed/seed-2.0-code",
@@ -11084,7 +11165,7 @@ export const MODELS = {
11084
11165
  cacheWrite: 0,
11085
11166
  },
11086
11167
  contextWindow: 163840,
11087
- maxTokens: 163840,
11168
+ maxTokens: 147456,
11088
11169
  },
11089
11170
  "deepseek/deepseek-chat-v3.1": {
11090
11171
  id: "deepseek/deepseek-chat-v3.1",
@@ -11101,7 +11182,7 @@ export const MODELS = {
11101
11182
  cacheWrite: 0,
11102
11183
  },
11103
11184
  contextWindow: 163840,
11104
- maxTokens: 161000,
11185
+ maxTokens: 144900,
11105
11186
  },
11106
11187
  "deepseek/deepseek-r1": {
11107
11188
  id: "deepseek/deepseek-r1",
@@ -11163,13 +11244,13 @@ export const MODELS = {
11163
11244
  reasoning: true,
11164
11245
  input: ["text"],
11165
11246
  cost: {
11166
- input: 0.26,
11167
- output: 0.38,
11168
- cacheRead: 0.13,
11247
+ input: 0.26899999999999996,
11248
+ output: 0.39999999999999997,
11249
+ cacheRead: 0.13449999999999998,
11169
11250
  cacheWrite: 0,
11170
11251
  },
11171
11252
  contextWindow: 163840,
11172
- maxTokens: 163840,
11253
+ maxTokens: 65536,
11173
11254
  },
11174
11255
  "deepseek/deepseek-v3.2-exp": {
11175
11256
  id: "deepseek/deepseek-v3.2-exp",
@@ -11199,9 +11280,9 @@ export const MODELS = {
11199
11280
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
11200
11281
  input: ["text"],
11201
11282
  cost: {
11202
- input: 0.0854,
11203
- output: 0.1708,
11204
- cacheRead: 0.01708,
11283
+ input: 0.07322000000000001,
11284
+ output: 0.14644000000000001,
11285
+ cacheRead: 0.014644,
11205
11286
  cacheWrite: 0,
11206
11287
  },
11207
11288
  contextWindow: 1048576,
@@ -11217,14 +11298,33 @@ export const MODELS = {
11217
11298
  reasoning: true,
11218
11299
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
11219
11300
  input: ["text"],
11301
+ cost: {
11302
+ input: 0.065,
11303
+ output: 0.18,
11304
+ cacheRead: 0.016,
11305
+ cacheWrite: 0,
11306
+ },
11307
+ contextWindow: 1310720,
11308
+ maxTokens: 943718,
11309
+ },
11310
+ "deepseek/deepseek-v4-flash-0731:batch": {
11311
+ id: "deepseek/deepseek-v4-flash-0731:batch",
11312
+ name: "DeepSeek: DeepSeek V4 Flash 0731 (batch)",
11313
+ api: "openai-completions",
11314
+ provider: "openrouter",
11315
+ baseUrl: "https://openrouter.ai/api/v1",
11316
+ compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
11317
+ reasoning: true,
11318
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
11319
+ input: ["text"],
11220
11320
  cost: {
11221
11321
  input: 0.14,
11222
11322
  output: 0.28,
11223
- cacheRead: 0.028,
11323
+ cacheRead: 0.03,
11224
11324
  cacheWrite: 0,
11225
11325
  },
11226
- contextWindow: 1310720,
11227
- maxTokens: 131072,
11326
+ contextWindow: 1048576,
11327
+ maxTokens: 943718,
11228
11328
  },
11229
11329
  "deepseek/deepseek-v4-flash-vision-exp": {
11230
11330
  id: "deepseek/deepseek-v4-flash-vision-exp",
@@ -11256,13 +11356,13 @@ export const MODELS = {
11256
11356
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
11257
11357
  input: ["text"],
11258
11358
  cost: {
11259
- input: 0.5790719999999999,
11260
- output: 1.1581439999999998,
11261
- cacheRead: 0.048256,
11359
+ input: 1.5999999999999999,
11360
+ output: 3.1999999999999997,
11361
+ cacheRead: 0.135,
11262
11362
  cacheWrite: 0,
11263
11363
  },
11264
11364
  contextWindow: 1048576,
11265
- maxTokens: 384000,
11365
+ maxTokens: 393216,
11266
11366
  },
11267
11367
  "deepseek/deepseek-v4-pro-0813": {
11268
11368
  id: "deepseek/deepseek-v4-pro-0813",
@@ -11275,13 +11375,32 @@ export const MODELS = {
11275
11375
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
11276
11376
  input: ["text"],
11277
11377
  cost: {
11278
- input: 1.122,
11279
- output: 3.366,
11280
- cacheRead: 0.037399999999999996,
11378
+ input: 0.66,
11379
+ output: 1.9800000000000002,
11380
+ cacheRead: 0.022,
11281
11381
  cacheWrite: 0,
11282
11382
  },
11283
11383
  contextWindow: 1048576,
11284
- maxTokens: 4096,
11384
+ maxTokens: 384000,
11385
+ },
11386
+ "deepseek/deepseek-v4-pro-0813:batch": {
11387
+ id: "deepseek/deepseek-v4-pro-0813:batch",
11388
+ name: "DeepSeek: DeepSeek V4 Pro 0813 (batch)",
11389
+ api: "openai-completions",
11390
+ provider: "openrouter",
11391
+ baseUrl: "https://openrouter.ai/api/v1",
11392
+ compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
11393
+ reasoning: true,
11394
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
11395
+ input: ["text"],
11396
+ cost: {
11397
+ input: 1.32,
11398
+ output: 3.9600000000000004,
11399
+ cacheRead: 0.13,
11400
+ cacheWrite: 0,
11401
+ },
11402
+ contextWindow: 1048576,
11403
+ maxTokens: 943718,
11285
11404
  },
11286
11405
  "dots-studio/dots-3-note-preview:free": {
11287
11406
  id: "dots-studio/dots-3-note-preview:free",
@@ -11298,7 +11417,7 @@ export const MODELS = {
11298
11417
  cacheWrite: 0,
11299
11418
  },
11300
11419
  contextWindow: 512000,
11301
- maxTokens: 512000,
11420
+ maxTokens: 460800,
11302
11421
  },
11303
11422
  "google/gemini-2.5-flash": {
11304
11423
  id: "google/gemini-2.5-flash",
@@ -11700,10 +11819,10 @@ export const MODELS = {
11700
11819
  reasoning: true,
11701
11820
  input: ["text", "image"],
11702
11821
  cost: {
11703
- input: 0.375,
11704
- output: 1.875,
11705
- cacheRead: 0.0375,
11706
- cacheWrite: 0.0208333333333333,
11822
+ input: 0.75,
11823
+ output: 3.75,
11824
+ cacheRead: 0.075,
11825
+ cacheWrite: 0.0416666666666667,
11707
11826
  },
11708
11827
  contextWindow: 1048576,
11709
11828
  maxTokens: 65536,
@@ -11756,8 +11875,8 @@ export const MODELS = {
11756
11875
  cacheRead: 0.04,
11757
11876
  cacheWrite: 0,
11758
11877
  },
11759
- contextWindow: 262144,
11760
- maxTokens: 131072,
11878
+ contextWindow: 131072,
11879
+ maxTokens: 117964,
11761
11880
  },
11762
11881
  "google/gemma-4-26b-a4b-it": {
11763
11882
  id: "google/gemma-4-26b-a4b-it",
@@ -11802,13 +11921,30 @@ export const MODELS = {
11802
11921
  reasoning: true,
11803
11922
  input: ["text", "image"],
11804
11923
  cost: {
11805
- input: 0.09999999999999999,
11924
+ input: 0.09,
11806
11925
  output: 0.33999999999999997,
11807
- cacheRead: 0.09999999999999999,
11926
+ cacheRead: 0.049999999999999996,
11808
11927
  cacheWrite: 0,
11809
11928
  },
11810
11929
  contextWindow: 262144,
11811
- maxTokens: 262144,
11930
+ maxTokens: 16384,
11931
+ },
11932
+ "google/gemma-4-31b-it:batch": {
11933
+ id: "google/gemma-4-31b-it:batch",
11934
+ name: "Google: Gemma 4 31B (batch)",
11935
+ api: "openai-completions",
11936
+ provider: "openrouter",
11937
+ baseUrl: "https://openrouter.ai/api/v1",
11938
+ reasoning: true,
11939
+ input: ["text", "image"],
11940
+ cost: {
11941
+ input: 0.39,
11942
+ output: 0.9700000000000001,
11943
+ cacheRead: 0,
11944
+ cacheWrite: 0,
11945
+ },
11946
+ contextWindow: 262144,
11947
+ maxTokens: 235929,
11812
11948
  },
11813
11949
  "google/gemma-4-31b-it:free": {
11814
11950
  id: "google/gemma-4-31b-it:free",
@@ -11842,7 +11978,24 @@ export const MODELS = {
11842
11978
  cacheWrite: 0,
11843
11979
  },
11844
11980
  contextWindow: 131072,
11845
- maxTokens: 131072,
11981
+ maxTokens: 117964,
11982
+ },
11983
+ "ibm-granite/granite-4.2-8b": {
11984
+ id: "ibm-granite/granite-4.2-8b",
11985
+ name: "IBM: Granite 4.2 8B",
11986
+ api: "openai-completions",
11987
+ provider: "openrouter",
11988
+ baseUrl: "https://openrouter.ai/api/v1",
11989
+ reasoning: true,
11990
+ input: ["text"],
11991
+ cost: {
11992
+ input: 0.09999999999999999,
11993
+ output: 0.15,
11994
+ cacheRead: 0.049999999999999996,
11995
+ cacheWrite: 0,
11996
+ },
11997
+ contextWindow: 131072,
11998
+ maxTokens: 117964,
11846
11999
  },
11847
12000
  "inception/mercury-2": {
11848
12001
  id: "inception/mercury-2",
@@ -11861,6 +12014,23 @@ export const MODELS = {
11861
12014
  contextWindow: 128000,
11862
12015
  maxTokens: 50000,
11863
12016
  },
12017
+ "inception/mercury-2.5-preview": {
12018
+ id: "inception/mercury-2.5-preview",
12019
+ name: "Inception: Mercury 2.5 Preview",
12020
+ api: "openai-completions",
12021
+ provider: "openrouter",
12022
+ baseUrl: "https://openrouter.ai/api/v1",
12023
+ reasoning: true,
12024
+ input: ["text"],
12025
+ cost: {
12026
+ input: 0.04,
12027
+ output: 0.15,
12028
+ cacheRead: 0.004,
12029
+ cacheWrite: 0,
12030
+ },
12031
+ contextWindow: 260000,
12032
+ maxTokens: 65536,
12033
+ },
11864
12034
  "inclusionai/ling-3.0-flash": {
11865
12035
  id: "inclusionai/ling-3.0-flash",
11866
12036
  name: "Ling-3.0-flash",
@@ -11878,22 +12048,22 @@ export const MODELS = {
11878
12048
  contextWindow: 262144,
11879
12049
  maxTokens: 32768,
11880
12050
  },
11881
- "kwaipilot/kat-coder-air-v2.5": {
11882
- id: "kwaipilot/kat-coder-air-v2.5",
11883
- name: "Kwaipilot: KAT-Coder-Air V2.5",
12051
+ "inclusionai/ling-3.0-flash-fin:free": {
12052
+ id: "inclusionai/ling-3.0-flash-fin:free",
12053
+ name: "Ling 3.0 Flash Fin (free)",
11884
12054
  api: "openai-completions",
11885
12055
  provider: "openrouter",
11886
12056
  baseUrl: "https://openrouter.ai/api/v1",
11887
- reasoning: false,
12057
+ reasoning: true,
11888
12058
  input: ["text"],
11889
12059
  cost: {
11890
- input: 0.15,
11891
- output: 0.6,
11892
- cacheRead: 0.03,
12060
+ input: 0,
12061
+ output: 0,
12062
+ cacheRead: 0,
11893
12063
  cacheWrite: 0,
11894
12064
  },
11895
- contextWindow: 256000,
11896
- maxTokens: 80000,
12065
+ contextWindow: 262144,
12066
+ maxTokens: 32768,
11897
12067
  },
11898
12068
  "kwaipilot/kat-coder-pro-v2": {
11899
12069
  id: "kwaipilot/kat-coder-pro-v2",
@@ -11910,7 +12080,7 @@ export const MODELS = {
11910
12080
  cacheWrite: 0,
11911
12081
  },
11912
12082
  contextWindow: 262144,
11913
- maxTokens: 80000,
12083
+ maxTokens: 144000,
11914
12084
  },
11915
12085
  "kwaipilot/kat-coder-pro-v2.5": {
11916
12086
  id: "kwaipilot/kat-coder-pro-v2.5",
@@ -11926,8 +12096,8 @@ export const MODELS = {
11926
12096
  cacheRead: 0.15,
11927
12097
  cacheWrite: 0,
11928
12098
  },
11929
- contextWindow: 256000,
11930
- maxTokens: 80000,
12099
+ contextWindow: 262144,
12100
+ maxTokens: 235929,
11931
12101
  },
11932
12102
  "liquid/lfm-2.5-2.6b:free": {
11933
12103
  id: "liquid/lfm-2.5-2.6b:free",
@@ -11995,7 +12165,7 @@ export const MODELS = {
11995
12165
  cacheWrite: 0,
11996
12166
  },
11997
12167
  contextWindow: 131072,
11998
- maxTokens: 131072,
12168
+ maxTokens: 117964,
11999
12169
  },
12000
12170
  "meta-llama/llama-3.3-70b-instruct": {
12001
12171
  id: "meta-llama/llama-3.3-70b-instruct",
@@ -12006,13 +12176,13 @@ export const MODELS = {
12006
12176
  reasoning: false,
12007
12177
  input: ["text"],
12008
12178
  cost: {
12009
- input: 0.09999999999999999,
12010
- output: 0.32,
12011
- cacheRead: 0,
12179
+ input: 0.71,
12180
+ output: 0.71,
12181
+ cacheRead: 0.71,
12012
12182
  cacheWrite: 0,
12013
12183
  },
12014
12184
  contextWindow: 131072,
12015
- maxTokens: 16384,
12185
+ maxTokens: 115200,
12016
12186
  },
12017
12187
  "meta-llama/llama-4-maverick": {
12018
12188
  id: "meta-llama/llama-4-maverick",
@@ -12024,12 +12194,12 @@ export const MODELS = {
12024
12194
  input: ["text", "image"],
12025
12195
  cost: {
12026
12196
  input: 0.19999999999999998,
12027
- output: 0.7999999999999999,
12197
+ output: 0.696,
12028
12198
  cacheRead: 0,
12029
12199
  cacheWrite: 0,
12030
12200
  },
12031
12201
  contextWindow: 1048576,
12032
- maxTokens: 16384,
12202
+ maxTokens: 115200,
12033
12203
  },
12034
12204
  "meta-llama/llama-4-scout": {
12035
12205
  id: "meta-llama/llama-4-scout",
@@ -12056,6 +12226,23 @@ export const MODELS = {
12056
12226
  baseUrl: "https://openrouter.ai/api/v1",
12057
12227
  reasoning: true,
12058
12228
  input: ["text", "image"],
12229
+ cost: {
12230
+ input: 0.3,
12231
+ output: 1.2,
12232
+ cacheRead: 0.04,
12233
+ cacheWrite: 0,
12234
+ },
12235
+ contextWindow: 131072,
12236
+ maxTokens: 16384,
12237
+ },
12238
+ "meta/muse-glimmer-30b:batch": {
12239
+ id: "meta/muse-glimmer-30b:batch",
12240
+ name: "Meta: Muse Glimmer 30B (batch)",
12241
+ api: "openai-completions",
12242
+ provider: "openrouter",
12243
+ baseUrl: "https://openrouter.ai/api/v1",
12244
+ reasoning: true,
12245
+ input: ["text", "image"],
12059
12246
  cost: {
12060
12247
  input: 0.35,
12061
12248
  output: 1.5,
@@ -12063,7 +12250,7 @@ export const MODELS = {
12063
12250
  cacheWrite: 0,
12064
12251
  },
12065
12252
  contextWindow: 131072,
12066
- maxTokens: 4096,
12253
+ maxTokens: 117964,
12067
12254
  },
12068
12255
  "meta/muse-spark-1.1": {
12069
12256
  id: "meta/muse-spark-1.1",
@@ -12080,7 +12267,7 @@ export const MODELS = {
12080
12267
  cacheWrite: 0,
12081
12268
  },
12082
12269
  contextWindow: 1048576,
12083
- maxTokens: 4096,
12270
+ maxTokens: 943718,
12084
12271
  },
12085
12272
  "meta/muse-spark-1.2": {
12086
12273
  id: "meta/muse-spark-1.2",
@@ -12097,7 +12284,7 @@ export const MODELS = {
12097
12284
  cacheWrite: 0,
12098
12285
  },
12099
12286
  contextWindow: 1048576,
12100
- maxTokens: 4096,
12287
+ maxTokens: 943718,
12101
12288
  },
12102
12289
  "meta/muse-spark-1.2-contributor": {
12103
12290
  id: "meta/muse-spark-1.2-contributor",
@@ -12114,7 +12301,7 @@ export const MODELS = {
12114
12301
  cacheWrite: 0,
12115
12302
  },
12116
12303
  contextWindow: 1048576,
12117
- maxTokens: 4096,
12304
+ maxTokens: 943718,
12118
12305
  },
12119
12306
  "minimax/minimax-m1": {
12120
12307
  id: "minimax/minimax-m1",
@@ -12199,7 +12386,7 @@ export const MODELS = {
12199
12386
  cacheWrite: 0,
12200
12387
  },
12201
12388
  contextWindow: 204800,
12202
- maxTokens: 4096,
12389
+ maxTokens: 131072,
12203
12390
  },
12204
12391
  "minimax/minimax-m2.7:free": {
12205
12392
  id: "minimax/minimax-m2.7:free",
@@ -12216,7 +12403,7 @@ export const MODELS = {
12216
12403
  cacheWrite: 0,
12217
12404
  },
12218
12405
  contextWindow: 196608,
12219
- maxTokens: 4096,
12406
+ maxTokens: 176947,
12220
12407
  },
12221
12408
  "minimax/minimax-m3": {
12222
12409
  id: "minimax/minimax-m3",
@@ -12250,7 +12437,7 @@ export const MODELS = {
12250
12437
  cacheWrite: 0,
12251
12438
  },
12252
12439
  contextWindow: 524288,
12253
- maxTokens: 4096,
12440
+ maxTokens: 471859,
12254
12441
  },
12255
12442
  "minimax/minimax-m3:free": {
12256
12443
  id: "minimax/minimax-m3:free",
@@ -12267,7 +12454,7 @@ export const MODELS = {
12267
12454
  cacheWrite: 0,
12268
12455
  },
12269
12456
  contextWindow: 1048576,
12270
- maxTokens: 4096,
12457
+ maxTokens: 943718,
12271
12458
  },
12272
12459
  "mistralai/codestral-2508": {
12273
12460
  id: "mistralai/codestral-2508",
@@ -12284,7 +12471,7 @@ export const MODELS = {
12284
12471
  cacheWrite: 0,
12285
12472
  },
12286
12473
  contextWindow: 256000,
12287
- maxTokens: 4096,
12474
+ maxTokens: 204800,
12288
12475
  },
12289
12476
  "mistralai/devstral-2512": {
12290
12477
  id: "mistralai/devstral-2512",
@@ -12295,13 +12482,13 @@ export const MODELS = {
12295
12482
  reasoning: false,
12296
12483
  input: ["text"],
12297
12484
  cost: {
12298
- input: 0.44,
12299
- output: 2.2,
12300
- cacheRead: 0.044,
12485
+ input: 0.39999999999999997,
12486
+ output: 2,
12487
+ cacheRead: 0.04,
12301
12488
  cacheWrite: 0,
12302
12489
  },
12303
12490
  contextWindow: 262144,
12304
- maxTokens: 4096,
12491
+ maxTokens: 209715,
12305
12492
  },
12306
12493
  "mistralai/ministral-14b-2512": {
12307
12494
  id: "mistralai/ministral-14b-2512",
@@ -12318,7 +12505,7 @@ export const MODELS = {
12318
12505
  cacheWrite: 0,
12319
12506
  },
12320
12507
  contextWindow: 262144,
12321
- maxTokens: 4096,
12508
+ maxTokens: 209715,
12322
12509
  },
12323
12510
  "mistralai/ministral-3b-2512": {
12324
12511
  id: "mistralai/ministral-3b-2512",
@@ -12335,7 +12522,7 @@ export const MODELS = {
12335
12522
  cacheWrite: 0,
12336
12523
  },
12337
12524
  contextWindow: 131072,
12338
- maxTokens: 4096,
12525
+ maxTokens: 104857,
12339
12526
  },
12340
12527
  "mistralai/ministral-8b-2512": {
12341
12528
  id: "mistralai/ministral-8b-2512",
@@ -12352,7 +12539,7 @@ export const MODELS = {
12352
12539
  cacheWrite: 0,
12353
12540
  },
12354
12541
  contextWindow: 262144,
12355
- maxTokens: 4096,
12542
+ maxTokens: 209715,
12356
12543
  },
12357
12544
  "mistralai/mistral-large": {
12358
12545
  id: "mistralai/mistral-large",
@@ -12369,7 +12556,7 @@ export const MODELS = {
12369
12556
  cacheWrite: 0,
12370
12557
  },
12371
12558
  contextWindow: 128000,
12372
- maxTokens: 4096,
12559
+ maxTokens: 102400,
12373
12560
  },
12374
12561
  "mistralai/mistral-large-2407": {
12375
12562
  id: "mistralai/mistral-large-2407",
@@ -12386,7 +12573,7 @@ export const MODELS = {
12386
12573
  cacheWrite: 0,
12387
12574
  },
12388
12575
  contextWindow: 131072,
12389
- maxTokens: 4096,
12576
+ maxTokens: 104857,
12390
12577
  },
12391
12578
  "mistralai/mistral-large-2512": {
12392
12579
  id: "mistralai/mistral-large-2512",
@@ -12403,7 +12590,7 @@ export const MODELS = {
12403
12590
  cacheWrite: 0,
12404
12591
  },
12405
12592
  contextWindow: 262144,
12406
- maxTokens: 4096,
12593
+ maxTokens: 209715,
12407
12594
  },
12408
12595
  "mistralai/mistral-medium-3": {
12409
12596
  id: "mistralai/mistral-medium-3",
@@ -12420,7 +12607,7 @@ export const MODELS = {
12420
12607
  cacheWrite: 0,
12421
12608
  },
12422
12609
  contextWindow: 131072,
12423
- maxTokens: 4096,
12610
+ maxTokens: 104857,
12424
12611
  },
12425
12612
  "mistralai/mistral-medium-3-5": {
12426
12613
  id: "mistralai/mistral-medium-3-5",
@@ -12437,7 +12624,24 @@ export const MODELS = {
12437
12624
  cacheWrite: 0,
12438
12625
  },
12439
12626
  contextWindow: 262144,
12440
- maxTokens: 4096,
12627
+ maxTokens: 209715,
12628
+ },
12629
+ "mistralai/mistral-medium-3-5:batch": {
12630
+ id: "mistralai/mistral-medium-3-5:batch",
12631
+ name: "Mistral: Mistral Medium 3.5 (batch)",
12632
+ api: "openai-completions",
12633
+ provider: "openrouter",
12634
+ baseUrl: "https://openrouter.ai/api/v1",
12635
+ reasoning: true,
12636
+ input: ["text", "image"],
12637
+ cost: {
12638
+ input: 0.75,
12639
+ output: 3.75,
12640
+ cacheRead: 0,
12641
+ cacheWrite: 0,
12642
+ },
12643
+ contextWindow: 262144,
12644
+ maxTokens: 209715,
12441
12645
  },
12442
12646
  "mistralai/mistral-medium-3.1": {
12443
12647
  id: "mistralai/mistral-medium-3.1",
@@ -12454,7 +12658,7 @@ export const MODELS = {
12454
12658
  cacheWrite: 0,
12455
12659
  },
12456
12660
  contextWindow: 131072,
12457
- maxTokens: 4096,
12661
+ maxTokens: 104857,
12458
12662
  },
12459
12663
  "mistralai/mistral-nemo": {
12460
12664
  id: "mistralai/mistral-nemo",
@@ -12488,7 +12692,7 @@ export const MODELS = {
12488
12692
  cacheWrite: 0,
12489
12693
  },
12490
12694
  contextWindow: 32768,
12491
- maxTokens: 4096,
12695
+ maxTokens: 26214,
12492
12696
  },
12493
12697
  "mistralai/mistral-small-2603": {
12494
12698
  id: "mistralai/mistral-small-2603",
@@ -12505,7 +12709,7 @@ export const MODELS = {
12505
12709
  cacheWrite: 0,
12506
12710
  },
12507
12711
  contextWindow: 262144,
12508
- maxTokens: 4096,
12712
+ maxTokens: 209715,
12509
12713
  },
12510
12714
  "mistralai/mistral-small-3.2-24b-instruct": {
12511
12715
  id: "mistralai/mistral-small-3.2-24b-instruct",
@@ -12539,7 +12743,7 @@ export const MODELS = {
12539
12743
  cacheWrite: 0,
12540
12744
  },
12541
12745
  contextWindow: 65536,
12542
- maxTokens: 4096,
12746
+ maxTokens: 52428,
12543
12747
  },
12544
12748
  "mistralai/voxtral-small-24b-2507": {
12545
12749
  id: "mistralai/voxtral-small-24b-2507",
@@ -12555,8 +12759,8 @@ export const MODELS = {
12555
12759
  cacheRead: 0.01,
12556
12760
  cacheWrite: 0,
12557
12761
  },
12558
- contextWindow: 32000,
12559
- maxTokens: 4096,
12762
+ contextWindow: 32768,
12763
+ maxTokens: 26214,
12560
12764
  },
12561
12765
  "moonshotai/kimi-k2": {
12562
12766
  id: "moonshotai/kimi-k2",
@@ -12641,7 +12845,7 @@ export const MODELS = {
12641
12845
  cacheWrite: 0,
12642
12846
  },
12643
12847
  contextWindow: 262144,
12644
- maxTokens: 4096,
12848
+ maxTokens: 235929,
12645
12849
  },
12646
12850
  "moonshotai/kimi-k2.7-code": {
12647
12851
  id: "moonshotai/kimi-k2.7-code",
@@ -12652,34 +12856,34 @@ export const MODELS = {
12652
12856
  reasoning: true,
12653
12857
  input: ["text", "image"],
12654
12858
  cost: {
12655
- input: 0.67,
12859
+ input: 0.66,
12656
12860
  output: 3.4,
12657
- cacheRead: 0.19,
12861
+ cacheRead: 0.18,
12658
12862
  cacheWrite: 0,
12659
12863
  },
12660
12864
  contextWindow: 262144,
12661
- maxTokens: 262144,
12865
+ maxTokens: 235929,
12662
12866
  },
12663
- "moonshotai/kimi-k2.7-code:batch": {
12664
- id: "moonshotai/kimi-k2.7-code:batch",
12665
- name: "MoonshotAI: Kimi K2.7 Code (batch)",
12867
+ "moonshotai/kimi-k3": {
12868
+ id: "moonshotai/kimi-k3",
12869
+ name: "MoonshotAI: Kimi K3",
12666
12870
  api: "openai-completions",
12667
12871
  provider: "openrouter",
12668
12872
  baseUrl: "https://openrouter.ai/api/v1",
12669
12873
  reasoning: true,
12670
12874
  input: ["text", "image"],
12671
12875
  cost: {
12672
- input: 0.95,
12673
- output: 4,
12674
- cacheRead: 0.19,
12876
+ input: 3,
12877
+ output: 15,
12878
+ cacheRead: 0.3,
12675
12879
  cacheWrite: 0,
12676
12880
  },
12677
- contextWindow: 262144,
12678
- maxTokens: 4096,
12881
+ contextWindow: 1048576,
12882
+ maxTokens: 943718,
12679
12883
  },
12680
- "moonshotai/kimi-k3": {
12681
- id: "moonshotai/kimi-k3",
12682
- name: "MoonshotAI: Kimi K3",
12884
+ "moonshotai/kimi-k3:batch": {
12885
+ id: "moonshotai/kimi-k3:batch",
12886
+ name: "MoonshotAI: Kimi K3 (batch)",
12683
12887
  api: "openai-completions",
12684
12888
  provider: "openrouter",
12685
12889
  baseUrl: "https://openrouter.ai/api/v1",
@@ -12692,7 +12896,7 @@ export const MODELS = {
12692
12896
  cacheWrite: 0,
12693
12897
  },
12694
12898
  contextWindow: 1048576,
12695
- maxTokens: 1048576,
12899
+ maxTokens: 943718,
12696
12900
  },
12697
12901
  "nex-agi/nex-n2-mini": {
12698
12902
  id: "nex-agi/nex-n2-mini",
@@ -12709,7 +12913,7 @@ export const MODELS = {
12709
12913
  cacheWrite: 0,
12710
12914
  },
12711
12915
  contextWindow: 262144,
12712
- maxTokens: 262144,
12916
+ maxTokens: 235929,
12713
12917
  },
12714
12918
  "nex-agi/nex-n2-pro": {
12715
12919
  id: "nex-agi/nex-n2-pro",
@@ -12726,7 +12930,7 @@ export const MODELS = {
12726
12930
  cacheWrite: 0,
12727
12931
  },
12728
12932
  contextWindow: 262144,
12729
- maxTokens: 262144,
12933
+ maxTokens: 235929,
12730
12934
  },
12731
12935
  "nvidia/nemotron-3-nano-30b-a3b": {
12732
12936
  id: "nvidia/nemotron-3-nano-30b-a3b",
@@ -12739,11 +12943,11 @@ export const MODELS = {
12739
12943
  cost: {
12740
12944
  input: 0.049999999999999996,
12741
12945
  output: 0.19999999999999998,
12742
- cacheRead: 0.03,
12946
+ cacheRead: 0.024999999999999998,
12743
12947
  cacheWrite: 0,
12744
12948
  },
12745
12949
  contextWindow: 262144,
12746
- maxTokens: 262144,
12950
+ maxTokens: 228000,
12747
12951
  },
12748
12952
  "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free": {
12749
12953
  id: "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
@@ -12794,7 +12998,7 @@ export const MODELS = {
12794
12998
  cacheWrite: 0,
12795
12999
  },
12796
13000
  contextWindow: 262144,
12797
- maxTokens: 262144,
13001
+ maxTokens: 235929,
12798
13002
  },
12799
13003
  "nvidia/nemotron-3-ultra-550b-a55b": {
12800
13004
  id: "nvidia/nemotron-3-ultra-550b-a55b",
@@ -12805,13 +13009,13 @@ export const MODELS = {
12805
13009
  reasoning: true,
12806
13010
  input: ["text"],
12807
13011
  cost: {
12808
- input: 0.6,
12809
- output: 3.5999999999999996,
12810
- cacheRead: 0.19999999999999998,
13012
+ input: 0.5,
13013
+ output: 2.2,
13014
+ cacheRead: 0.09999999999999999,
12811
13015
  cacheWrite: 0,
12812
13016
  },
12813
- contextWindow: 512288,
12814
- maxTokens: 4096,
13017
+ contextWindow: 262144,
13018
+ maxTokens: 16384,
12815
13019
  },
12816
13020
  "nvidia/nemotron-3-ultra-550b-a55b:batch": {
12817
13021
  id: "nvidia/nemotron-3-ultra-550b-a55b:batch",
@@ -12828,7 +13032,7 @@ export const MODELS = {
12828
13032
  cacheWrite: 0,
12829
13033
  },
12830
13034
  contextWindow: 512288,
12831
- maxTokens: 4096,
13035
+ maxTokens: 461059,
12832
13036
  },
12833
13037
  "nvidia/nemotron-3-ultra-550b-a55b:free": {
12834
13038
  id: "nvidia/nemotron-3-ultra-550b-a55b:free",
@@ -12913,7 +13117,7 @@ export const MODELS = {
12913
13117
  cacheWrite: 0,
12914
13118
  },
12915
13119
  contextWindow: 4095,
12916
- maxTokens: 4096,
13120
+ maxTokens: 3685,
12917
13121
  },
12918
13122
  "openai/gpt-3.5-turbo-16k": {
12919
13123
  id: "openai/gpt-3.5-turbo-16k",
@@ -13164,24 +13368,7 @@ export const MODELS = {
13164
13368
  cost: {
13165
13369
  input: 1.25,
13166
13370
  output: 10,
13167
- cacheRead: 0.125,
13168
- cacheWrite: 0,
13169
- },
13170
- contextWindow: 400000,
13171
- maxTokens: 128000,
13172
- },
13173
- "openai/gpt-5-codex:batch": {
13174
- id: "openai/gpt-5-codex:batch",
13175
- name: "OpenAI: GPT-5 Codex (batch)",
13176
- api: "openai-completions",
13177
- provider: "openrouter",
13178
- baseUrl: "https://openrouter.ai/api/v1",
13179
- reasoning: true,
13180
- input: ["text", "image"],
13181
- cost: {
13182
- input: 0.625,
13183
- output: 5,
13184
- cacheRead: 0.0625,
13371
+ cacheRead: 0.125,
13185
13372
  cacheWrite: 0,
13186
13373
  },
13187
13374
  contextWindow: 400000,
@@ -14003,7 +14190,24 @@ export const MODELS = {
14003
14190
  cacheWrite: 0,
14004
14191
  },
14005
14192
  contextWindow: 131072,
14006
- maxTokens: 131072,
14193
+ maxTokens: 117964,
14194
+ },
14195
+ "openai/gpt-oss-120b:batch": {
14196
+ id: "openai/gpt-oss-120b:batch",
14197
+ name: "OpenAI: gpt-oss-120b (batch)",
14198
+ api: "openai-completions",
14199
+ provider: "openrouter",
14200
+ baseUrl: "https://openrouter.ai/api/v1",
14201
+ reasoning: true,
14202
+ input: ["text"],
14203
+ cost: {
14204
+ input: 0.15,
14205
+ output: 0.6,
14206
+ cacheRead: 0,
14207
+ cacheWrite: 0,
14208
+ },
14209
+ contextWindow: 131072,
14210
+ maxTokens: 117964,
14007
14211
  },
14008
14212
  "openai/gpt-oss-20b": {
14009
14213
  id: "openai/gpt-oss-20b",
@@ -14020,7 +14224,7 @@ export const MODELS = {
14020
14224
  cacheWrite: 0,
14021
14225
  },
14022
14226
  contextWindow: 131072,
14023
- maxTokens: 131072,
14227
+ maxTokens: 117964,
14024
14228
  },
14025
14229
  "openai/gpt-oss-safeguard-20b": {
14026
14230
  id: "openai/gpt-oss-safeguard-20b",
@@ -14056,23 +14260,6 @@ export const MODELS = {
14056
14260
  contextWindow: 200000,
14057
14261
  maxTokens: 100000,
14058
14262
  },
14059
- "openai/o1:batch": {
14060
- id: "openai/o1:batch",
14061
- name: "OpenAI: o1 (batch)",
14062
- api: "openai-completions",
14063
- provider: "openrouter",
14064
- baseUrl: "https://openrouter.ai/api/v1",
14065
- reasoning: true,
14066
- input: ["text", "image"],
14067
- cost: {
14068
- input: 7.5,
14069
- output: 30,
14070
- cacheRead: 3.75,
14071
- cacheWrite: 0,
14072
- },
14073
- contextWindow: 200000,
14074
- maxTokens: 100000,
14075
- },
14076
14263
  "openai/o3": {
14077
14264
  id: "openai/o3",
14078
14265
  name: "OpenAI: o3",
@@ -14124,23 +14311,6 @@ export const MODELS = {
14124
14311
  contextWindow: 200000,
14125
14312
  maxTokens: 100000,
14126
14313
  },
14127
- "openai/o3-mini-high:batch": {
14128
- id: "openai/o3-mini-high:batch",
14129
- name: "OpenAI: o3 Mini High (batch)",
14130
- api: "openai-completions",
14131
- provider: "openrouter",
14132
- baseUrl: "https://openrouter.ai/api/v1",
14133
- reasoning: true,
14134
- input: ["text"],
14135
- cost: {
14136
- input: 0.55,
14137
- output: 2.2,
14138
- cacheRead: 0.275,
14139
- cacheWrite: 0,
14140
- },
14141
- contextWindow: 200000,
14142
- maxTokens: 100000,
14143
- },
14144
14314
  "openai/o3-mini:batch": {
14145
14315
  id: "openai/o3-mini:batch",
14146
14316
  name: "OpenAI: o3 Mini (batch)",
@@ -14175,23 +14345,6 @@ export const MODELS = {
14175
14345
  contextWindow: 200000,
14176
14346
  maxTokens: 100000,
14177
14347
  },
14178
- "openai/o3-pro:batch": {
14179
- id: "openai/o3-pro:batch",
14180
- name: "OpenAI: o3 Pro (batch)",
14181
- api: "openai-completions",
14182
- provider: "openrouter",
14183
- baseUrl: "https://openrouter.ai/api/v1",
14184
- reasoning: true,
14185
- input: ["text", "image"],
14186
- cost: {
14187
- input: 10,
14188
- output: 40,
14189
- cacheRead: 0,
14190
- cacheWrite: 0,
14191
- },
14192
- contextWindow: 200000,
14193
- maxTokens: 100000,
14194
- },
14195
14348
  "openai/o3:batch": {
14196
14349
  id: "openai/o3:batch",
14197
14350
  name: "OpenAI: o3 (batch)",
@@ -14243,23 +14396,6 @@ export const MODELS = {
14243
14396
  contextWindow: 200000,
14244
14397
  maxTokens: 100000,
14245
14398
  },
14246
- "openai/o4-mini-high:batch": {
14247
- id: "openai/o4-mini-high:batch",
14248
- name: "OpenAI: o4 Mini High (batch)",
14249
- api: "openai-completions",
14250
- provider: "openrouter",
14251
- baseUrl: "https://openrouter.ai/api/v1",
14252
- reasoning: true,
14253
- input: ["text", "image"],
14254
- cost: {
14255
- input: 0.55,
14256
- output: 2.2,
14257
- cacheRead: 0.1375,
14258
- cacheWrite: 0,
14259
- },
14260
- contextWindow: 200000,
14261
- maxTokens: 100000,
14262
- },
14263
14399
  "openai/o4-mini:batch": {
14264
14400
  id: "openai/o4-mini:batch",
14265
14401
  name: "OpenAI: o4 Mini (batch)",
@@ -14428,7 +14564,7 @@ export const MODELS = {
14428
14564
  cacheWrite: 0,
14429
14565
  },
14430
14566
  contextWindow: 32768,
14431
- maxTokens: 32768,
14567
+ maxTokens: 29491,
14432
14568
  },
14433
14569
  "qwen/qwen-plus": {
14434
14570
  id: "qwen/qwen-plus",
@@ -14464,23 +14600,6 @@ export const MODELS = {
14464
14600
  contextWindow: 1000000,
14465
14601
  maxTokens: 32768,
14466
14602
  },
14467
- "qwen/qwen-plus-2025-07-28:thinking": {
14468
- id: "qwen/qwen-plus-2025-07-28:thinking",
14469
- name: "Qwen: Qwen Plus 0728 (thinking)",
14470
- api: "openai-completions",
14471
- provider: "openrouter",
14472
- baseUrl: "https://openrouter.ai/api/v1",
14473
- reasoning: true,
14474
- input: ["text"],
14475
- cost: {
14476
- input: 0.26,
14477
- output: 0.78,
14478
- cacheRead: 0,
14479
- cacheWrite: 0,
14480
- },
14481
- contextWindow: 1000000,
14482
- maxTokens: 32768,
14483
- },
14484
14603
  "qwen/qwen3-14b": {
14485
14604
  id: "qwen/qwen3-14b",
14486
14605
  name: "Qwen: Qwen3 14B",
@@ -14524,13 +14643,13 @@ export const MODELS = {
14524
14643
  reasoning: false,
14525
14644
  input: ["text"],
14526
14645
  cost: {
14527
- input: 0.09,
14528
- output: 0.55,
14529
- cacheRead: 0,
14646
+ input: 0.0875,
14647
+ output: 0.35,
14648
+ cacheRead: 0.0175,
14530
14649
  cacheWrite: 0,
14531
14650
  },
14532
14651
  contextWindow: 262144,
14533
- maxTokens: 16384,
14652
+ maxTokens: 235929,
14534
14653
  },
14535
14654
  "qwen/qwen3-235b-a22b-thinking-2507": {
14536
14655
  id: "qwen/qwen3-235b-a22b-thinking-2507",
@@ -14547,7 +14666,7 @@ export const MODELS = {
14547
14666
  cacheWrite: 0,
14548
14667
  },
14549
14668
  contextWindow: 131072,
14550
- maxTokens: 4096,
14669
+ maxTokens: 117964,
14551
14670
  },
14552
14671
  "qwen/qwen3-30b-a3b": {
14553
14672
  id: "qwen/qwen3-30b-a3b",
@@ -14666,7 +14785,7 @@ export const MODELS = {
14666
14785
  cacheWrite: 0,
14667
14786
  },
14668
14787
  contextWindow: 262144,
14669
- maxTokens: 262144,
14788
+ maxTokens: 235929,
14670
14789
  },
14671
14790
  "qwen/qwen3-coder-flash": {
14672
14791
  id: "qwen/qwen3-coder-flash",
@@ -14700,7 +14819,7 @@ export const MODELS = {
14700
14819
  cacheWrite: 0,
14701
14820
  },
14702
14821
  contextWindow: 262144,
14703
- maxTokens: 262144,
14822
+ maxTokens: 235929,
14704
14823
  },
14705
14824
  "qwen/qwen3-coder-plus": {
14706
14825
  id: "qwen/qwen3-coder-plus",
@@ -14768,7 +14887,7 @@ export const MODELS = {
14768
14887
  cacheWrite: 0,
14769
14888
  },
14770
14889
  contextWindow: 262144,
14771
- maxTokens: 262144,
14890
+ maxTokens: 235929,
14772
14891
  },
14773
14892
  "qwen/qwen3-next-80b-a3b-thinking": {
14774
14893
  id: "qwen/qwen3-next-80b-a3b-thinking",
@@ -14830,13 +14949,13 @@ export const MODELS = {
14830
14949
  reasoning: false,
14831
14950
  input: ["text", "image"],
14832
14951
  cost: {
14833
- input: 0.13,
14834
- output: 0.52,
14952
+ input: 0.15,
14953
+ output: 0.6,
14835
14954
  cacheRead: 0,
14836
14955
  cacheWrite: 0,
14837
14956
  },
14838
14957
  contextWindow: 262144,
14839
- maxTokens: 32768,
14958
+ maxTokens: 16384,
14840
14959
  },
14841
14960
  "qwen/qwen3-vl-30b-a3b-thinking": {
14842
14961
  id: "qwen/qwen3-vl-30b-a3b-thinking",
@@ -14915,13 +15034,13 @@ export const MODELS = {
14915
15034
  reasoning: true,
14916
15035
  input: ["text", "image"],
14917
15036
  cost: {
14918
- input: 0.26,
14919
- output: 2.08,
15037
+ input: 0.29,
15038
+ output: 2.4,
14920
15039
  cacheRead: 0,
14921
15040
  cacheWrite: 0,
14922
15041
  },
14923
15042
  contextWindow: 262144,
14924
- maxTokens: 262144,
15043
+ maxTokens: 81920,
14925
15044
  },
14926
15045
  "qwen/qwen3.5-27b": {
14927
15046
  id: "qwen/qwen3.5-27b",
@@ -14955,7 +15074,7 @@ export const MODELS = {
14955
15074
  cacheWrite: 0,
14956
15075
  },
14957
15076
  contextWindow: 262144,
14958
- maxTokens: 262144,
15077
+ maxTokens: 235929,
14959
15078
  },
14960
15079
  "qwen/qwen3.5-397b-a17b": {
14961
15080
  id: "qwen/qwen3.5-397b-a17b",
@@ -14966,13 +15085,13 @@ export const MODELS = {
14966
15085
  reasoning: true,
14967
15086
  input: ["text", "image"],
14968
15087
  cost: {
14969
- input: 0.5,
14970
- output: 3.5999999999999996,
14971
- cacheRead: 0.3,
15088
+ input: 0.39,
15089
+ output: 2.34,
15090
+ cacheRead: 0,
14972
15091
  cacheWrite: 0,
14973
15092
  },
14974
15093
  contextWindow: 262144,
14975
- maxTokens: 262144,
15094
+ maxTokens: 65536,
14976
15095
  },
14977
15096
  "qwen/qwen3.5-9b": {
14978
15097
  id: "qwen/qwen3.5-9b",
@@ -14989,7 +15108,24 @@ export const MODELS = {
14989
15108
  cacheWrite: 0,
14990
15109
  },
14991
15110
  contextWindow: 262144,
14992
- maxTokens: 262144,
15111
+ maxTokens: 235929,
15112
+ },
15113
+ "qwen/qwen3.5-9b:batch": {
15114
+ id: "qwen/qwen3.5-9b:batch",
15115
+ name: "Qwen: Qwen3.5-9B (batch)",
15116
+ api: "openai-completions",
15117
+ provider: "openrouter",
15118
+ baseUrl: "https://openrouter.ai/api/v1",
15119
+ reasoning: true,
15120
+ input: ["text", "image"],
15121
+ cost: {
15122
+ input: 0.16999999999999998,
15123
+ output: 0.25,
15124
+ cacheRead: 0,
15125
+ cacheWrite: 0,
15126
+ },
15127
+ contextWindow: 262144,
15128
+ maxTokens: 235929,
14993
15129
  },
14994
15130
  "qwen/qwen3.5-flash-02-23": {
14995
15131
  id: "qwen/qwen3.5-flash-02-23",
@@ -15051,13 +15187,13 @@ export const MODELS = {
15051
15187
  reasoning: true,
15052
15188
  input: ["text", "image"],
15053
15189
  cost: {
15054
- input: 0.32,
15055
- output: 3.1999999999999997,
15056
- cacheRead: 0,
15190
+ input: 0.6,
15191
+ output: 3.5999999999999996,
15192
+ cacheRead: 0.12,
15057
15193
  cacheWrite: 0,
15058
15194
  },
15059
15195
  contextWindow: 262144,
15060
- maxTokens: 81920,
15196
+ maxTokens: 235929,
15061
15197
  },
15062
15198
  "qwen/qwen3.6-35b-a3b": {
15063
15199
  id: "qwen/qwen3.6-35b-a3b",
@@ -15068,13 +15204,13 @@ export const MODELS = {
15068
15204
  reasoning: true,
15069
15205
  input: ["text", "image"],
15070
15206
  cost: {
15071
- input: 0.14,
15072
- output: 1,
15207
+ input: 0.09999999999999999,
15208
+ output: 0.8999999999999999,
15073
15209
  cacheRead: 0.049999999999999996,
15074
15210
  cacheWrite: 0,
15075
15211
  },
15076
15212
  contextWindow: 262144,
15077
- maxTokens: 262144,
15213
+ maxTokens: 235929,
15078
15214
  },
15079
15215
  "qwen/qwen3.6-flash": {
15080
15216
  id: "qwen/qwen3.6-flash",
@@ -15193,7 +15329,24 @@ export const MODELS = {
15193
15329
  cacheWrite: 0,
15194
15330
  },
15195
15331
  contextWindow: 1048576,
15196
- maxTokens: 131072,
15332
+ maxTokens: 262144,
15333
+ },
15334
+ "qwen/qwen3.8-2.4t-a95b:batch": {
15335
+ id: "qwen/qwen3.8-2.4t-a95b:batch",
15336
+ name: "Qwen: Qwen3.8 2.4T A95B (batch)",
15337
+ api: "openai-completions",
15338
+ provider: "openrouter",
15339
+ baseUrl: "https://openrouter.ai/api/v1",
15340
+ reasoning: true,
15341
+ input: ["text"],
15342
+ cost: {
15343
+ input: 2.5,
15344
+ output: 6.25,
15345
+ cacheRead: 0.5,
15346
+ cacheWrite: 0,
15347
+ },
15348
+ contextWindow: 1010000,
15349
+ maxTokens: 909000,
15197
15350
  },
15198
15351
  "qwen/qwen3.8-27b": {
15199
15352
  id: "qwen/qwen3.8-27b",
@@ -15212,6 +15365,23 @@ export const MODELS = {
15212
15365
  contextWindow: 1000000,
15213
15366
  maxTokens: 131072,
15214
15367
  },
15368
+ "qwen/qwen3.8-flash": {
15369
+ id: "qwen/qwen3.8-flash",
15370
+ name: "Qwen: Qwen3.8 Flash",
15371
+ api: "openai-completions",
15372
+ provider: "openrouter",
15373
+ baseUrl: "https://openrouter.ai/api/v1",
15374
+ reasoning: true,
15375
+ input: ["text", "image"],
15376
+ cost: {
15377
+ input: 0.15,
15378
+ output: 0.47,
15379
+ cacheRead: 0.016,
15380
+ cacheWrite: 0.19999999999999998,
15381
+ },
15382
+ contextWindow: 1000000,
15383
+ maxTokens: 131072,
15384
+ },
15215
15385
  "qwen/qwen3.8-max": {
15216
15386
  id: "qwen/qwen3.8-max",
15217
15387
  name: "Qwen: Qwen3.8 Max",
@@ -15244,7 +15414,7 @@ export const MODELS = {
15244
15414
  cacheWrite: 0,
15245
15415
  },
15246
15416
  contextWindow: 16384,
15247
- maxTokens: 16384,
15417
+ maxTokens: 14745,
15248
15418
  },
15249
15419
  "relace/relace-search": {
15250
15420
  id: "relace/relace-search",
@@ -15314,23 +15484,6 @@ export const MODELS = {
15314
15484
  contextWindow: 131072,
15315
15485
  maxTokens: 16384,
15316
15486
  },
15317
- "stealth/ox-alpha": {
15318
- id: "stealth/ox-alpha",
15319
- name: "Ox Alpha",
15320
- api: "openai-completions",
15321
- provider: "openrouter",
15322
- baseUrl: "https://openrouter.ai/api/v1",
15323
- reasoning: true,
15324
- input: ["text", "image"],
15325
- cost: {
15326
- input: 0,
15327
- output: 0,
15328
- cacheRead: 0,
15329
- cacheWrite: 0,
15330
- },
15331
- contextWindow: 1048576,
15332
- maxTokens: 131072,
15333
- },
15334
15487
  "stepfun/step-3.5-flash": {
15335
15488
  id: "stepfun/step-3.5-flash",
15336
15489
  name: "StepFun: Step 3.5 Flash",
@@ -15363,7 +15516,7 @@ export const MODELS = {
15363
15516
  cacheWrite: 0,
15364
15517
  },
15365
15518
  contextWindow: 262144,
15366
- maxTokens: 256000,
15519
+ maxTokens: 230400,
15367
15520
  },
15368
15521
  "tencent/hy3": {
15369
15522
  id: "tencent/hy3",
@@ -15374,14 +15527,31 @@ export const MODELS = {
15374
15527
  reasoning: true,
15375
15528
  input: ["text"],
15376
15529
  cost: {
15377
- input: 0.13199999999999998,
15378
- output: 0.5279999999999999,
15379
- cacheRead: 0.032999999999999995,
15530
+ input: 0.0825,
15531
+ output: 0.33,
15532
+ cacheRead: 0.020625,
15380
15533
  cacheWrite: 0,
15381
15534
  },
15382
15535
  contextWindow: 262144,
15383
15536
  maxTokens: 128000,
15384
15537
  },
15538
+ "tencent/hy4-preview": {
15539
+ id: "tencent/hy4-preview",
15540
+ name: "Tencent: Hy4 preview",
15541
+ api: "openai-completions",
15542
+ provider: "openrouter",
15543
+ baseUrl: "https://openrouter.ai/api/v1",
15544
+ reasoning: true,
15545
+ input: ["text"],
15546
+ cost: {
15547
+ input: 0.834,
15548
+ output: 2.501,
15549
+ cacheRead: 0.041999999999999996,
15550
+ cacheWrite: 0,
15551
+ },
15552
+ contextWindow: 1048576,
15553
+ maxTokens: 64000,
15554
+ },
15385
15555
  "thedrummer/unslopnemo-12b": {
15386
15556
  id: "thedrummer/unslopnemo-12b",
15387
15557
  name: "TheDrummer: UnslopNemo 12B",
@@ -15397,7 +15567,7 @@ export const MODELS = {
15397
15567
  cacheWrite: 0,
15398
15568
  },
15399
15569
  contextWindow: 1024000,
15400
- maxTokens: 32768,
15570
+ maxTokens: 26214,
15401
15571
  },
15402
15572
  "thinkingmachines/inkling": {
15403
15573
  id: "thinkingmachines/inkling",
@@ -15408,13 +15578,13 @@ export const MODELS = {
15408
15578
  reasoning: true,
15409
15579
  input: ["text", "image"],
15410
15580
  cost: {
15411
- input: 0.95,
15581
+ input: 1,
15412
15582
  output: 4.05,
15413
- cacheRead: 0.16,
15583
+ cacheRead: 0.16999999999999998,
15414
15584
  cacheWrite: 0,
15415
15585
  },
15416
15586
  contextWindow: 1048576,
15417
- maxTokens: 262144,
15587
+ maxTokens: 471859,
15418
15588
  },
15419
15589
  "thinkingmachines/inkling-small": {
15420
15590
  id: "thinkingmachines/inkling-small",
@@ -15433,6 +15603,23 @@ export const MODELS = {
15433
15603
  contextWindow: 1048576,
15434
15604
  maxTokens: 262144,
15435
15605
  },
15606
+ "thinkingmachines/inkling-small:batch": {
15607
+ id: "thinkingmachines/inkling-small:batch",
15608
+ name: "Thinking Machines: Inkling Small (batch)",
15609
+ api: "openai-completions",
15610
+ provider: "openrouter",
15611
+ baseUrl: "https://openrouter.ai/api/v1",
15612
+ reasoning: true,
15613
+ input: ["text", "image"],
15614
+ cost: {
15615
+ input: 0.5,
15616
+ output: 1.2,
15617
+ cacheRead: 0.09999999999999999,
15618
+ cacheWrite: 0,
15619
+ },
15620
+ contextWindow: 524288,
15621
+ maxTokens: 471859,
15622
+ },
15436
15623
  "thinkingmachines/inkling-small:free": {
15437
15624
  id: "thinkingmachines/inkling-small:free",
15438
15625
  name: "Thinking Machines: Inkling Small (free)",
@@ -15465,7 +15652,7 @@ export const MODELS = {
15465
15652
  cacheWrite: 0,
15466
15653
  },
15467
15654
  contextWindow: 524288,
15468
- maxTokens: 4096,
15655
+ maxTokens: 471859,
15469
15656
  },
15470
15657
  "thinkingmachines/inkling:free": {
15471
15658
  id: "thinkingmachines/inkling:free",
@@ -15499,7 +15686,7 @@ export const MODELS = {
15499
15686
  cacheWrite: 0,
15500
15687
  },
15501
15688
  contextWindow: 131072,
15502
- maxTokens: 131072,
15689
+ maxTokens: 117964,
15503
15690
  },
15504
15691
  "upstage/solar-pro4": {
15505
15692
  id: "upstage/solar-pro4",
@@ -15533,7 +15720,7 @@ export const MODELS = {
15533
15720
  cacheWrite: 0,
15534
15721
  },
15535
15722
  contextWindow: 2000000,
15536
- maxTokens: 4096,
15723
+ maxTokens: 1800000,
15537
15724
  },
15538
15725
  "x-ai/grok-4.3": {
15539
15726
  id: "x-ai/grok-4.3",
@@ -15550,7 +15737,7 @@ export const MODELS = {
15550
15737
  cacheWrite: 0,
15551
15738
  },
15552
15739
  contextWindow: 1000000,
15553
- maxTokens: 4096,
15740
+ maxTokens: 900000,
15554
15741
  },
15555
15742
  "x-ai/grok-4.5": {
15556
15743
  id: "x-ai/grok-4.5",
@@ -15567,7 +15754,7 @@ export const MODELS = {
15567
15754
  cacheWrite: 0,
15568
15755
  },
15569
15756
  contextWindow: 500000,
15570
- maxTokens: 4096,
15757
+ maxTokens: 450000,
15571
15758
  },
15572
15759
  "x-ai/grok-4.6": {
15573
15760
  id: "x-ai/grok-4.6",
@@ -15584,7 +15771,7 @@ export const MODELS = {
15584
15771
  cacheWrite: 0,
15585
15772
  },
15586
15773
  contextWindow: 500000,
15587
- maxTokens: 4096,
15774
+ maxTokens: 450000,
15588
15775
  },
15589
15776
  "x-ai/grok-build-0.1": {
15590
15777
  id: "x-ai/grok-build-0.1",
@@ -15601,7 +15788,7 @@ export const MODELS = {
15601
15788
  cacheWrite: 0,
15602
15789
  },
15603
15790
  contextWindow: 256000,
15604
- maxTokens: 4096,
15791
+ maxTokens: 230400,
15605
15792
  },
15606
15793
  "xiaomi/mimo-v2.5": {
15607
15794
  id: "xiaomi/mimo-v2.5",
@@ -15697,13 +15884,13 @@ export const MODELS = {
15697
15884
  reasoning: true,
15698
15885
  input: ["text"],
15699
15886
  cost: {
15700
- input: 0.5,
15701
- output: 2,
15702
- cacheRead: 0.09999999999999999,
15887
+ input: 0.43,
15888
+ output: 1.75,
15889
+ cacheRead: 0.08,
15703
15890
  cacheWrite: 0,
15704
15891
  },
15705
15892
  contextWindow: 204800,
15706
- maxTokens: 131072,
15893
+ maxTokens: 16384,
15707
15894
  },
15708
15895
  "z-ai/glm-4.6v": {
15709
15896
  id: "z-ai/glm-4.6v",
@@ -15799,13 +15986,13 @@ export const MODELS = {
15799
15986
  reasoning: true,
15800
15987
  input: ["text"],
15801
15988
  cost: {
15802
- input: 1.26,
15803
- output: 3.9600000000000004,
15804
- cacheRead: 0.234,
15989
+ input: 0.966,
15990
+ output: 3.036,
15991
+ cacheRead: 0.1794,
15805
15992
  cacheWrite: 0,
15806
15993
  },
15807
15994
  contextWindow: 204800,
15808
- maxTokens: 202752,
15995
+ maxTokens: 128000,
15809
15996
  },
15810
15997
  "z-ai/glm-5.2": {
15811
15998
  id: "z-ai/glm-5.2",
@@ -15824,9 +16011,26 @@ export const MODELS = {
15824
16011
  contextWindow: 1048576,
15825
16012
  maxTokens: 262144,
15826
16013
  },
15827
- "z-ai/glm-5.2:batch": {
15828
- id: "z-ai/glm-5.2:batch",
15829
- name: "Z.ai: GLM 5.2 (batch)",
16014
+ "z-ai/glm-5.2:free": {
16015
+ id: "z-ai/glm-5.2:free",
16016
+ name: "Z.ai: GLM 5.2 (free)",
16017
+ api: "openai-completions",
16018
+ provider: "openrouter",
16019
+ baseUrl: "https://openrouter.ai/api/v1",
16020
+ reasoning: true,
16021
+ input: ["text"],
16022
+ cost: {
16023
+ input: 0,
16024
+ output: 0,
16025
+ cacheRead: 0,
16026
+ cacheWrite: 0,
16027
+ },
16028
+ contextWindow: 256000,
16029
+ maxTokens: 230400,
16030
+ },
16031
+ "z-ai/glm-5.3": {
16032
+ id: "z-ai/glm-5.3",
16033
+ name: "Z.ai: GLM 5.3",
15830
16034
  api: "openai-completions",
15831
16035
  provider: "openrouter",
15832
16036
  baseUrl: "https://openrouter.ai/api/v1",
@@ -15838,42 +16042,42 @@ export const MODELS = {
15838
16042
  cacheRead: 0.26,
15839
16043
  cacheWrite: 0,
15840
16044
  },
15841
- contextWindow: 1048575,
15842
- maxTokens: 4096,
16045
+ contextWindow: 1310720,
16046
+ maxTokens: 131072,
15843
16047
  },
15844
- "z-ai/glm-5.2:free": {
15845
- id: "z-ai/glm-5.2:free",
15846
- name: "Z.ai: GLM 5.2 (free)",
16048
+ "z-ai/glm-5.3-flash": {
16049
+ id: "z-ai/glm-5.3-flash",
16050
+ name: "Z.ai: GLM 5.3 Flash",
15847
16051
  api: "openai-completions",
15848
16052
  provider: "openrouter",
15849
16053
  baseUrl: "https://openrouter.ai/api/v1",
15850
16054
  reasoning: true,
15851
- input: ["text"],
15852
- cost: {
15853
- input: 0,
15854
- output: 0,
15855
- cacheRead: 0,
16055
+ input: ["text", "image"],
16056
+ cost: {
16057
+ input: 0.075,
16058
+ output: 0.25,
16059
+ cacheRead: 0.015,
15856
16060
  cacheWrite: 0,
15857
16061
  },
15858
- contextWindow: 256000,
15859
- maxTokens: 256000,
16062
+ contextWindow: 1310720,
16063
+ maxTokens: 131072,
15860
16064
  },
15861
- "z-ai/glm-5.3": {
15862
- id: "z-ai/glm-5.3",
15863
- name: "Z.ai: GLM 5.3",
16065
+ "z-ai/glm-5.3-flash:batch": {
16066
+ id: "z-ai/glm-5.3-flash:batch",
16067
+ name: "Z.ai: GLM 5.3 Flash (batch)",
15864
16068
  api: "openai-completions",
15865
16069
  provider: "openrouter",
15866
16070
  baseUrl: "https://openrouter.ai/api/v1",
15867
16071
  reasoning: true,
15868
- input: ["text"],
16072
+ input: ["text", "image"],
15869
16073
  cost: {
15870
- input: 1.4,
15871
- output: 4.4,
15872
- cacheRead: 0.26,
16074
+ input: 0.15,
16075
+ output: 0.5,
16076
+ cacheRead: 0.03,
15873
16077
  cacheWrite: 0,
15874
16078
  },
15875
- contextWindow: 1048576,
15876
- maxTokens: 131072,
16079
+ contextWindow: 1048575,
16080
+ maxTokens: 943717,
15877
16081
  },
15878
16082
  "z-ai/glm-5v-turbo": {
15879
16083
  id: "z-ai/glm-5v-turbo",
@@ -15904,7 +16108,7 @@ export const MODELS = {
15904
16108
  cost: {
15905
16109
  input: 10,
15906
16110
  output: 50,
15907
- cacheRead: 1,
16111
+ cacheRead: 0.25,
15908
16112
  cacheWrite: 12.5,
15909
16113
  },
15910
16114
  contextWindow: 1000000,
@@ -15972,13 +16176,13 @@ export const MODELS = {
15972
16176
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
15973
16177
  input: ["text"],
15974
16178
  cost: {
15975
- input: 0.035,
15976
- output: 0.09999999999999999,
15977
- cacheRead: 0.008,
16179
+ input: 0.049980000000000004,
16180
+ output: 0.09996000000000001,
16181
+ cacheRead: 0.009996000000000001,
15978
16182
  cacheWrite: 0,
15979
16183
  },
15980
16184
  contextWindow: 1310720,
15981
- maxTokens: 1048576,
16185
+ maxTokens: 131072,
15982
16186
  },
15983
16187
  "~google/gemini-flash-latest": {
15984
16188
  id: "~google/gemini-flash-latest",
@@ -15989,10 +16193,10 @@ export const MODELS = {
15989
16193
  reasoning: true,
15990
16194
  input: ["text", "image"],
15991
16195
  cost: {
15992
- input: 0.375,
15993
- output: 1.875,
15994
- cacheRead: 0.0375,
15995
- cacheWrite: 0.0208333333333333,
16196
+ input: 0.75,
16197
+ output: 3.75,
16198
+ cacheRead: 0.075,
16199
+ cacheWrite: 0.0416666666666667,
15996
16200
  },
15997
16201
  contextWindow: 1048576,
15998
16202
  maxTokens: 65536,
@@ -16023,13 +16227,13 @@ export const MODELS = {
16023
16227
  reasoning: true,
16024
16228
  input: ["text", "image"],
16025
16229
  cost: {
16026
- input: 2.8,
16027
- output: 14,
16028
- cacheRead: 0.29,
16230
+ input: 2.5500000000000003,
16231
+ output: 12.75,
16232
+ cacheRead: 0.25599998999999996,
16029
16233
  cacheWrite: 0,
16030
16234
  },
16031
16235
  contextWindow: 1048576,
16032
- maxTokens: 1048576,
16236
+ maxTokens: 943718,
16033
16237
  },
16034
16238
  "~openai/gpt-latest": {
16035
16239
  id: "~openai/gpt-latest",
@@ -16080,7 +16284,7 @@ export const MODELS = {
16080
16284
  cacheWrite: 0,
16081
16285
  },
16082
16286
  contextWindow: 500000,
16083
- maxTokens: 4096,
16287
+ maxTokens: 450000,
16084
16288
  },
16085
16289
  "~z-ai/glm-latest": {
16086
16290
  id: "~z-ai/glm-latest",
@@ -16091,13 +16295,13 @@ export const MODELS = {
16091
16295
  reasoning: true,
16092
16296
  input: ["text"],
16093
16297
  cost: {
16094
- input: 1.4,
16095
- output: 4.4,
16096
- cacheRead: 0.26,
16298
+ input: 1.17,
16299
+ output: 3.9600000000000004,
16300
+ cacheRead: 0.234,
16097
16301
  cacheWrite: 0,
16098
16302
  },
16099
- contextWindow: 1048576,
16100
- maxTokens: 131072,
16303
+ contextWindow: 1310720,
16304
+ maxTokens: 943718,
16101
16305
  },
16102
16306
  },
16103
16307
  "together": {
@@ -16459,6 +16663,44 @@ export const MODELS = {
16459
16663
  contextWindow: 512000,
16460
16664
  maxTokens: 164000,
16461
16665
  },
16666
+ "zai-org/GLM-5.3": {
16667
+ id: "zai-org/GLM-5.3",
16668
+ name: "GLM-5.3",
16669
+ api: "openai-completions",
16670
+ provider: "together",
16671
+ baseUrl: "https://api.together.ai/v1",
16672
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
16673
+ reasoning: true,
16674
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
16675
+ input: ["text"],
16676
+ cost: {
16677
+ input: 1.4,
16678
+ output: 4.4,
16679
+ cacheRead: 0.26,
16680
+ cacheWrite: 0,
16681
+ },
16682
+ contextWindow: 1048576,
16683
+ maxTokens: 262144,
16684
+ },
16685
+ "zai-org/GLM-5.3-Flash": {
16686
+ id: "zai-org/GLM-5.3-Flash",
16687
+ name: "GLM-5.3-Flash",
16688
+ api: "openai-completions",
16689
+ provider: "together",
16690
+ baseUrl: "https://api.together.ai/v1",
16691
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
16692
+ reasoning: true,
16693
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
16694
+ input: ["text", "image"],
16695
+ cost: {
16696
+ input: 0.15,
16697
+ output: 0.5,
16698
+ cacheRead: 0.03,
16699
+ cacheWrite: 0,
16700
+ },
16701
+ contextWindow: 1048575,
16702
+ maxTokens: 400000,
16703
+ },
16462
16704
  },
16463
16705
  "vercel-ai-gateway": {
16464
16706
  "alibaba/qwen-3-14b": {
@@ -16897,11 +17139,11 @@ export const MODELS = {
16897
17139
  cost: {
16898
17140
  input: 2,
16899
17141
  output: 6,
16900
- cacheRead: 0.19999999999999998,
17142
+ cacheRead: 0.25,
16901
17143
  cacheWrite: 0,
16902
17144
  },
16903
17145
  contextWindow: 262144,
16904
- maxTokens: 131072,
17146
+ maxTokens: 128000,
16905
17147
  },
16906
17148
  "alibaba/qwen3.8-27b": {
16907
17149
  id: "alibaba/qwen3.8-27b",
@@ -16912,14 +17154,48 @@ export const MODELS = {
16912
17154
  reasoning: true,
16913
17155
  input: ["text", "image"],
16914
17156
  cost: {
16915
- input: 0.55,
16916
- output: 3.3000000000000003,
16917
- cacheRead: 0.11,
16918
- cacheWrite: 0,
17157
+ input: 0.5,
17158
+ output: 3,
17159
+ cacheRead: 0.09999999999999999,
17160
+ cacheWrite: 0.625,
16919
17161
  },
16920
17162
  contextWindow: 1000000,
16921
17163
  maxTokens: 131072,
16922
17164
  },
17165
+ "alibaba/qwen3.8-flash": {
17166
+ id: "alibaba/qwen3.8-flash",
17167
+ name: "Qwen 3.8 Flash",
17168
+ api: "anthropic-messages",
17169
+ provider: "vercel-ai-gateway",
17170
+ baseUrl: "https://ai-gateway.vercel.sh",
17171
+ reasoning: true,
17172
+ input: ["text", "image"],
17173
+ cost: {
17174
+ input: 0.16,
17175
+ output: 0.47,
17176
+ cacheRead: 0.016,
17177
+ cacheWrite: 0.19999999999999998,
17178
+ },
17179
+ contextWindow: 991000,
17180
+ maxTokens: 128000,
17181
+ },
17182
+ "alibaba/qwen3.8-flash-next": {
17183
+ id: "alibaba/qwen3.8-flash-next",
17184
+ name: "Qwen 3.8 Flash Next",
17185
+ api: "anthropic-messages",
17186
+ provider: "vercel-ai-gateway",
17187
+ baseUrl: "https://ai-gateway.vercel.sh",
17188
+ reasoning: true,
17189
+ input: ["text", "image"],
17190
+ cost: {
17191
+ input: 0.12,
17192
+ output: 0.39999999999999997,
17193
+ cacheRead: 0.01,
17194
+ cacheWrite: 0,
17195
+ },
17196
+ contextWindow: 1048576,
17197
+ maxTokens: 1048576,
17198
+ },
16923
17199
  "alibaba/qwen3.8-max": {
16924
17200
  id: "alibaba/qwen3.8-max",
16925
17201
  name: "Qwen 3.8 Max",
@@ -17040,6 +17316,24 @@ export const MODELS = {
17040
17316
  contextWindow: 1000000,
17041
17317
  maxTokens: 128000,
17042
17318
  },
17319
+ "anthropic/claude-fable-5.1": {
17320
+ id: "anthropic/claude-fable-5.1",
17321
+ name: "Claude Fable 5.1",
17322
+ api: "anthropic-messages",
17323
+ provider: "vercel-ai-gateway",
17324
+ baseUrl: "https://ai-gateway.vercel.sh",
17325
+ reasoning: true,
17326
+ thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
17327
+ input: ["text", "image"],
17328
+ cost: {
17329
+ input: 10,
17330
+ output: 50,
17331
+ cacheRead: 0.25,
17332
+ cacheWrite: 12.5,
17333
+ },
17334
+ contextWindow: 1000000,
17335
+ maxTokens: 128000,
17336
+ },
17043
17337
  "anthropic/claude-haiku-4.5": {
17044
17338
  id: "anthropic/claude-haiku-4.5",
17045
17339
  name: "Claude Haiku 4.5",
@@ -17483,8 +17777,8 @@ export const MODELS = {
17483
17777
  cacheRead: 0.007,
17484
17778
  cacheWrite: 0,
17485
17779
  },
17486
- contextWindow: 1000000,
17487
- maxTokens: 384000,
17780
+ contextWindow: 1048576,
17781
+ maxTokens: 1048576,
17488
17782
  },
17489
17783
  "deepseek/deepseek-v4-pro": {
17490
17784
  id: "deepseek/deepseek-v4-pro",
@@ -17495,13 +17789,13 @@ export const MODELS = {
17495
17789
  reasoning: true,
17496
17790
  input: ["text"],
17497
17791
  cost: {
17498
- input: 1.74,
17499
- output: 3.48,
17500
- cacheRead: 0.14,
17792
+ input: 0.66,
17793
+ output: 1.9800000000000002,
17794
+ cacheRead: 0.022,
17501
17795
  cacheWrite: 0,
17502
17796
  },
17503
- contextWindow: 1048600,
17504
- maxTokens: 1048600,
17797
+ contextWindow: 1000000,
17798
+ maxTokens: 384000,
17505
17799
  },
17506
17800
  "deepseek/deepseek-v4-pro-0813": {
17507
17801
  id: "deepseek/deepseek-v4-pro-0813",
@@ -17775,6 +18069,40 @@ export const MODELS = {
17775
18069
  contextWindow: 256000,
17776
18070
  maxTokens: 32000,
17777
18071
  },
18072
+ "inclusionai/ling-3.0-flash-fin": {
18073
+ id: "inclusionai/ling-3.0-flash-fin",
18074
+ name: "Ling 3.0 Flash Fin",
18075
+ api: "anthropic-messages",
18076
+ provider: "vercel-ai-gateway",
18077
+ baseUrl: "https://ai-gateway.vercel.sh",
18078
+ reasoning: true,
18079
+ input: ["text"],
18080
+ cost: {
18081
+ input: 0,
18082
+ output: 0,
18083
+ cacheRead: 0,
18084
+ cacheWrite: 0,
18085
+ },
18086
+ contextWindow: 256000,
18087
+ maxTokens: 32000,
18088
+ },
18089
+ "inclusionai/ling-3.0-flash-fin-free": {
18090
+ id: "inclusionai/ling-3.0-flash-fin-free",
18091
+ name: "Ling 3.0 Flash Fin (Free)",
18092
+ api: "anthropic-messages",
18093
+ provider: "vercel-ai-gateway",
18094
+ baseUrl: "https://ai-gateway.vercel.sh",
18095
+ reasoning: true,
18096
+ input: ["text"],
18097
+ cost: {
18098
+ input: 0,
18099
+ output: 0,
18100
+ cacheRead: 0,
18101
+ cacheWrite: 0,
18102
+ },
18103
+ contextWindow: 256000,
18104
+ maxTokens: 32000,
18105
+ },
17778
18106
  "interfaze/interfaze-beta": {
17779
18107
  id: "interfaze/interfaze-beta",
17780
18108
  name: "Interfaze Beta",
@@ -18100,7 +18428,7 @@ export const MODELS = {
18100
18428
  },
18101
18429
  "minimax/minimax-m2.7": {
18102
18430
  id: "minimax/minimax-m2.7",
18103
- name: "Minimax M2.7",
18431
+ name: "MiniMax M2.7",
18104
18432
  api: "anthropic-messages",
18105
18433
  provider: "vercel-ai-gateway",
18106
18434
  baseUrl: "https://ai-gateway.vercel.sh",
@@ -18117,7 +18445,7 @@ export const MODELS = {
18117
18445
  },
18118
18446
  "minimax/minimax-m2.7-free": {
18119
18447
  id: "minimax/minimax-m2.7-free",
18120
- name: "Minimax M2.7 (Free)",
18448
+ name: "MiniMax M2.7 (Free)",
18121
18449
  api: "anthropic-messages",
18122
18450
  provider: "vercel-ai-gateway",
18123
18451
  baseUrl: "https://ai-gateway.vercel.sh",
@@ -18163,8 +18491,8 @@ export const MODELS = {
18163
18491
  cacheRead: 0.06,
18164
18492
  cacheWrite: 0,
18165
18493
  },
18166
- contextWindow: 1000000,
18167
- maxTokens: 1000000,
18494
+ contextWindow: 512000,
18495
+ maxTokens: 512000,
18168
18496
  },
18169
18497
  "minimax/minimax-m3-free": {
18170
18498
  id: "minimax/minimax-m3-free",
@@ -18466,7 +18794,7 @@ export const MODELS = {
18466
18794
  cost: {
18467
18795
  input: 0.95,
18468
18796
  output: 4,
18469
- cacheRead: 0.19,
18797
+ cacheRead: 0.16,
18470
18798
  cacheWrite: 0,
18471
18799
  },
18472
18800
  contextWindow: 256000,
@@ -19890,13 +20218,30 @@ export const MODELS = {
19890
20218
  reasoning: true,
19891
20219
  input: ["text"],
19892
20220
  cost: {
19893
- input: 0.13199999999999998,
19894
- output: 0.5279999999999999,
19895
- cacheRead: 0.032999999999999995,
20221
+ input: 0.14,
20222
+ output: 0.58,
20223
+ cacheRead: 0.035,
19896
20224
  cacheWrite: 0,
19897
20225
  },
19898
- contextWindow: 256000,
19899
- maxTokens: 128000,
20226
+ contextWindow: 262144,
20227
+ maxTokens: 262144,
20228
+ },
20229
+ "tencent/hy4-preview": {
20230
+ id: "tencent/hy4-preview",
20231
+ name: "Tencent Hy4 Preview",
20232
+ api: "anthropic-messages",
20233
+ provider: "vercel-ai-gateway",
20234
+ baseUrl: "https://ai-gateway.vercel.sh",
20235
+ reasoning: true,
20236
+ input: ["text"],
20237
+ cost: {
20238
+ input: 0.834,
20239
+ output: 2.501,
20240
+ cacheRead: 0.041999999999999996,
20241
+ cacheWrite: 0,
20242
+ },
20243
+ contextWindow: 1024000,
20244
+ maxTokens: 64000,
19900
20245
  },
19901
20246
  "thinkingmachines/inkling": {
19902
20247
  id: "thinkingmachines/inkling",
@@ -19966,6 +20311,23 @@ export const MODELS = {
19966
20311
  contextWindow: 1050000,
19967
20312
  maxTokens: 131000,
19968
20313
  },
20314
+ "xiaomi/mimo-v2.5-pro-ultraspeed": {
20315
+ id: "xiaomi/mimo-v2.5-pro-ultraspeed",
20316
+ name: "MiMo V2.5 Pro UltraSpeed",
20317
+ api: "anthropic-messages",
20318
+ provider: "vercel-ai-gateway",
20319
+ baseUrl: "https://ai-gateway.vercel.sh",
20320
+ reasoning: true,
20321
+ input: ["text"],
20322
+ cost: {
20323
+ input: 1.305,
20324
+ output: 2.61,
20325
+ cacheRead: 0.0108,
20326
+ cacheWrite: 0,
20327
+ },
20328
+ contextWindow: 1048576,
20329
+ maxTokens: 131072,
20330
+ },
19969
20331
  "zai/glm-4.5": {
19970
20332
  id: "zai/glm-4.5",
19971
20333
  name: "GLM 4.5",
@@ -20181,11 +20543,28 @@ export const MODELS = {
20181
20543
  cost: {
20182
20544
  input: 1.4,
20183
20545
  output: 4.4,
20184
- cacheRead: 0.26,
20546
+ cacheRead: 0.14,
20547
+ cacheWrite: 0,
20548
+ },
20549
+ contextWindow: 1000000,
20550
+ maxTokens: 1000000,
20551
+ },
20552
+ "zai/glm-5.3-flash": {
20553
+ id: "zai/glm-5.3-flash",
20554
+ name: "GLM 5.3 Flash",
20555
+ api: "anthropic-messages",
20556
+ provider: "vercel-ai-gateway",
20557
+ baseUrl: "https://ai-gateway.vercel.sh",
20558
+ reasoning: true,
20559
+ input: ["text", "image"],
20560
+ cost: {
20561
+ input: 0.15,
20562
+ output: 0.5,
20563
+ cacheRead: 0.03,
20185
20564
  cacheWrite: 0,
20186
20565
  },
20187
20566
  contextWindow: 1000000,
20188
- maxTokens: 12800,
20567
+ maxTokens: 131000,
20189
20568
  },
20190
20569
  "zai/glm-5v-turbo": {
20191
20570
  id: "zai/glm-5v-turbo",
@@ -20629,6 +21008,42 @@ export const MODELS = {
20629
21008
  contextWindow: 1000000,
20630
21009
  maxTokens: 131072,
20631
21010
  },
21011
+ "glm-5.3-flash": {
21012
+ id: "glm-5.3-flash",
21013
+ name: "GLM-5.3-Flash",
21014
+ api: "openai-completions",
21015
+ provider: "zai",
21016
+ baseUrl: "https://api.z.ai/api/coding/paas/v4",
21017
+ compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
21018
+ reasoning: true,
21019
+ input: ["text", "image"],
21020
+ cost: {
21021
+ input: 0,
21022
+ output: 0,
21023
+ cacheRead: 0,
21024
+ cacheWrite: 0,
21025
+ },
21026
+ contextWindow: 1000000,
21027
+ maxTokens: 131072,
21028
+ },
21029
+ "glm-5.3-highspeed": {
21030
+ id: "glm-5.3-highspeed",
21031
+ name: "GLM-5.3 Highspeed",
21032
+ api: "openai-completions",
21033
+ provider: "zai",
21034
+ baseUrl: "https://api.z.ai/api/coding/paas/v4",
21035
+ compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
21036
+ reasoning: true,
21037
+ input: ["text"],
21038
+ cost: {
21039
+ input: 0,
21040
+ output: 0,
21041
+ cacheRead: 0,
21042
+ cacheWrite: 0,
21043
+ },
21044
+ contextWindow: 1000000,
21045
+ maxTokens: 131072,
21046
+ },
20632
21047
  },
20633
21048
  };
20634
21049
  //# sourceMappingURL=models.generated.js.map