@elyracode/ai 0.9.42 → 0.9.44

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -1155,6 +1155,23 @@ export const MODELS = {
1155
1155
  contextWindow: 1000000,
1156
1156
  maxTokens: 128000,
1157
1157
  },
1158
+ "global.moonshotai.kimi-k3": {
1159
+ id: "global.moonshotai.kimi-k3",
1160
+ name: "Kimi K3 (Global)",
1161
+ api: "bedrock-converse-stream",
1162
+ provider: "amazon-bedrock",
1163
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1164
+ reasoning: true,
1165
+ input: ["text", "image"],
1166
+ cost: {
1167
+ input: 3,
1168
+ output: 15,
1169
+ cacheRead: 0.3,
1170
+ cacheWrite: 3.75,
1171
+ },
1172
+ contextWindow: 1048576,
1173
+ maxTokens: 128000,
1174
+ },
1158
1175
  "global.openai.gpt-5.6-luna": {
1159
1176
  id: "global.openai.gpt-5.6-luna",
1160
1177
  name: "GPT-5.6 Luna (Global)",
@@ -1223,6 +1240,40 @@ export const MODELS = {
1223
1240
  contextWindow: 1050000,
1224
1241
  maxTokens: 128000,
1225
1242
  },
1243
+ "global.openai.gpt-6-luna": {
1244
+ id: "global.openai.gpt-6-luna",
1245
+ name: "GPT-6 Luna (Global)",
1246
+ api: "bedrock-converse-stream",
1247
+ provider: "amazon-bedrock",
1248
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1249
+ reasoning: true,
1250
+ input: ["text", "image"],
1251
+ cost: {
1252
+ input: 0.1,
1253
+ output: 0.5,
1254
+ cacheRead: 0.01,
1255
+ cacheWrite: 0.125,
1256
+ },
1257
+ contextWindow: 1050000,
1258
+ maxTokens: 128000,
1259
+ },
1260
+ "global.openai.gpt-6-sol": {
1261
+ id: "global.openai.gpt-6-sol",
1262
+ name: "GPT-6 Sol (Global)",
1263
+ api: "bedrock-converse-stream",
1264
+ provider: "amazon-bedrock",
1265
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1266
+ reasoning: true,
1267
+ input: ["text", "image"],
1268
+ cost: {
1269
+ input: 2,
1270
+ output: 10,
1271
+ cacheRead: 0.2,
1272
+ cacheWrite: 2.5,
1273
+ },
1274
+ contextWindow: 1050000,
1275
+ maxTokens: 128000,
1276
+ },
1226
1277
  "global.xai.grok-4.6": {
1227
1278
  id: "global.xai.grok-4.6",
1228
1279
  name: "Grok 4.6 (Global)",
@@ -1604,7 +1655,7 @@ export const MODELS = {
1604
1655
  cacheRead: 0,
1605
1656
  cacheWrite: 0,
1606
1657
  },
1607
- contextWindow: 204800,
1658
+ contextWindow: 196608,
1608
1659
  maxTokens: 131072,
1609
1660
  },
1610
1661
  "minimax.minimax-m2.5": {
@@ -1638,7 +1689,7 @@ export const MODELS = {
1638
1689
  cacheRead: 0,
1639
1690
  cacheWrite: 0,
1640
1691
  },
1641
- contextWindow: 256000,
1692
+ contextWindow: 262144,
1642
1693
  maxTokens: 8192,
1643
1694
  },
1644
1695
  "mistral.magistral-small-2509": {
@@ -1723,7 +1774,7 @@ export const MODELS = {
1723
1774
  cacheRead: 0,
1724
1775
  cacheWrite: 0,
1725
1776
  },
1726
- contextWindow: 256000,
1777
+ contextWindow: 262144,
1727
1778
  maxTokens: 8192,
1728
1779
  },
1729
1780
  "mistral.pixtral-large-2502-v1:0": {
@@ -1791,7 +1842,7 @@ export const MODELS = {
1791
1842
  cacheRead: 0,
1792
1843
  cacheWrite: 0,
1793
1844
  },
1794
- contextWindow: 262143,
1845
+ contextWindow: 262144,
1795
1846
  maxTokens: 16000,
1796
1847
  },
1797
1848
  "moonshotai.kimi-k2.5": {
@@ -1808,7 +1859,7 @@ export const MODELS = {
1808
1859
  cacheRead: 0,
1809
1860
  cacheWrite: 0,
1810
1861
  },
1811
- contextWindow: 262143,
1862
+ contextWindow: 262144,
1812
1863
  maxTokens: 16384,
1813
1864
  },
1814
1865
  "nvidia.nemotron-nano-12b-v2": {
@@ -1825,7 +1876,7 @@ export const MODELS = {
1825
1876
  cacheRead: 0,
1826
1877
  cacheWrite: 0,
1827
1878
  },
1828
- contextWindow: 128000,
1879
+ contextWindow: 131072,
1829
1880
  maxTokens: 8192,
1830
1881
  },
1831
1882
  "nvidia.nemotron-nano-3-30b": {
@@ -1894,7 +1945,7 @@ export const MODELS = {
1894
1945
  cacheRead: 0.275,
1895
1946
  cacheWrite: 0,
1896
1947
  },
1897
- contextWindow: 272000,
1948
+ contextWindow: 1000000,
1898
1949
  maxTokens: 128000,
1899
1950
  },
1900
1951
  "openai.gpt-5.5": {
@@ -1912,7 +1963,7 @@ export const MODELS = {
1912
1963
  cacheRead: 0.55,
1913
1964
  cacheWrite: 0,
1914
1965
  },
1915
- contextWindow: 272000,
1966
+ contextWindow: 1000000,
1916
1967
  maxTokens: 128000,
1917
1968
  },
1918
1969
  "openai.gpt-5.6-luna": {
@@ -1983,6 +2034,40 @@ export const MODELS = {
1983
2034
  contextWindow: 1050000,
1984
2035
  maxTokens: 128000,
1985
2036
  },
2037
+ "openai.gpt-6-luna": {
2038
+ id: "openai.gpt-6-luna",
2039
+ name: "GPT-6 Luna",
2040
+ api: "bedrock-converse-stream",
2041
+ provider: "amazon-bedrock",
2042
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2043
+ reasoning: true,
2044
+ input: ["text", "image"],
2045
+ cost: {
2046
+ input: 0.11,
2047
+ output: 0.55,
2048
+ cacheRead: 0.011,
2049
+ cacheWrite: 0.1375,
2050
+ },
2051
+ contextWindow: 1050000,
2052
+ maxTokens: 128000,
2053
+ },
2054
+ "openai.gpt-6-sol": {
2055
+ id: "openai.gpt-6-sol",
2056
+ name: "GPT-6 Sol",
2057
+ api: "bedrock-converse-stream",
2058
+ provider: "amazon-bedrock",
2059
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2060
+ reasoning: true,
2061
+ input: ["text", "image"],
2062
+ cost: {
2063
+ input: 2.2,
2064
+ output: 11,
2065
+ cacheRead: 0.22,
2066
+ cacheWrite: 2.75,
2067
+ },
2068
+ contextWindow: 1050000,
2069
+ maxTokens: 128000,
2070
+ },
1986
2071
  "openai.gpt-oss-120b": {
1987
2072
  id: "openai.gpt-oss-120b",
1988
2073
  name: "gpt-oss-120b",
@@ -1997,8 +2082,8 @@ export const MODELS = {
1997
2082
  cacheRead: 0,
1998
2083
  cacheWrite: 0,
1999
2084
  },
2000
- contextWindow: 128000,
2001
- maxTokens: 16384,
2085
+ contextWindow: 131072,
2086
+ maxTokens: 131072,
2002
2087
  },
2003
2088
  "openai.gpt-oss-120b-1:0": {
2004
2089
  id: "openai.gpt-oss-120b-1:0",
@@ -2014,8 +2099,8 @@ export const MODELS = {
2014
2099
  cacheRead: 0,
2015
2100
  cacheWrite: 0,
2016
2101
  },
2017
- contextWindow: 128000,
2018
- maxTokens: 16384,
2102
+ contextWindow: 131072,
2103
+ maxTokens: 128000,
2019
2104
  },
2020
2105
  "openai.gpt-oss-20b": {
2021
2106
  id: "openai.gpt-oss-20b",
@@ -2031,8 +2116,8 @@ export const MODELS = {
2031
2116
  cacheRead: 0,
2032
2117
  cacheWrite: 0,
2033
2118
  },
2034
- contextWindow: 128000,
2035
- maxTokens: 16384,
2119
+ contextWindow: 131072,
2120
+ maxTokens: 131072,
2036
2121
  },
2037
2122
  "openai.gpt-oss-20b-1:0": {
2038
2123
  id: "openai.gpt-oss-20b-1:0",
@@ -2048,8 +2133,8 @@ export const MODELS = {
2048
2133
  cacheRead: 0,
2049
2134
  cacheWrite: 0,
2050
2135
  },
2051
- contextWindow: 128000,
2052
- maxTokens: 16384,
2136
+ contextWindow: 131072,
2137
+ maxTokens: 128000,
2053
2138
  },
2054
2139
  "openai.gpt-oss-safeguard-120b": {
2055
2140
  id: "openai.gpt-oss-safeguard-120b",
@@ -2682,6 +2767,23 @@ export const MODELS = {
2682
2767
  contextWindow: 128000,
2683
2768
  maxTokens: 8192,
2684
2769
  },
2770
+ "us.moonshotai.kimi-k3": {
2771
+ id: "us.moonshotai.kimi-k3",
2772
+ name: "Kimi K3 (US)",
2773
+ api: "bedrock-converse-stream",
2774
+ provider: "amazon-bedrock",
2775
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2776
+ reasoning: true,
2777
+ input: ["text", "image"],
2778
+ cost: {
2779
+ input: 3.3,
2780
+ output: 16.5,
2781
+ cacheRead: 0.33,
2782
+ cacheWrite: 4.125,
2783
+ },
2784
+ contextWindow: 1048576,
2785
+ maxTokens: 128000,
2786
+ },
2685
2787
  "us.openai.gpt-5.6-luna": {
2686
2788
  id: "us.openai.gpt-5.6-luna",
2687
2789
  name: "GPT-5.6 Luna (US)",
@@ -2750,6 +2852,40 @@ export const MODELS = {
2750
2852
  contextWindow: 1050000,
2751
2853
  maxTokens: 128000,
2752
2854
  },
2855
+ "us.openai.gpt-6-luna": {
2856
+ id: "us.openai.gpt-6-luna",
2857
+ name: "GPT-6 Luna (US)",
2858
+ api: "bedrock-converse-stream",
2859
+ provider: "amazon-bedrock",
2860
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2861
+ reasoning: true,
2862
+ input: ["text", "image"],
2863
+ cost: {
2864
+ input: 0.11,
2865
+ output: 0.55,
2866
+ cacheRead: 0.011,
2867
+ cacheWrite: 0.1375,
2868
+ },
2869
+ contextWindow: 1050000,
2870
+ maxTokens: 128000,
2871
+ },
2872
+ "us.openai.gpt-6-sol": {
2873
+ id: "us.openai.gpt-6-sol",
2874
+ name: "GPT-6 Sol (US)",
2875
+ api: "bedrock-converse-stream",
2876
+ provider: "amazon-bedrock",
2877
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2878
+ reasoning: true,
2879
+ input: ["text", "image"],
2880
+ cost: {
2881
+ input: 2.2,
2882
+ output: 11,
2883
+ cacheRead: 0.22,
2884
+ cacheWrite: 2.75,
2885
+ },
2886
+ contextWindow: 1050000,
2887
+ maxTokens: 128000,
2888
+ },
2753
2889
  "us.writer.palmyra-x4-v1:0": {
2754
2890
  id: "us.writer.palmyra-x4-v1:0",
2755
2891
  name: "Palmyra X4 (US)",
@@ -2883,7 +3019,7 @@ export const MODELS = {
2883
3019
  cacheRead: 0,
2884
3020
  cacheWrite: 0,
2885
3021
  },
2886
- contextWindow: 204800,
3022
+ contextWindow: 202752,
2887
3023
  maxTokens: 131072,
2888
3024
  },
2889
3025
  "zai.glm-4.7-flash": {
@@ -2900,7 +3036,7 @@ export const MODELS = {
2900
3036
  cacheRead: 0,
2901
3037
  cacheWrite: 0,
2902
3038
  },
2903
- contextWindow: 200000,
3039
+ contextWindow: 202752,
2904
3040
  maxTokens: 131072,
2905
3041
  },
2906
3042
  "zai.glm-5": {
@@ -3197,6 +3333,24 @@ export const MODELS = {
3197
3333
  contextWindow: 1000000,
3198
3334
  maxTokens: 128000,
3199
3335
  },
3336
+ "claude-sonnet-5-5": {
3337
+ id: "claude-sonnet-5-5",
3338
+ name: "Claude Sonnet 5.5",
3339
+ api: "anthropic-messages",
3340
+ provider: "anthropic",
3341
+ baseUrl: "https://api.anthropic.com",
3342
+ reasoning: true,
3343
+ thinkingType: "adaptive",
3344
+ input: ["text", "image"],
3345
+ cost: {
3346
+ input: 2,
3347
+ output: 10,
3348
+ cacheRead: 0.2,
3349
+ cacheWrite: 2.5,
3350
+ },
3351
+ contextWindow: 1000000,
3352
+ maxTokens: 128000,
3353
+ },
3200
3354
  },
3201
3355
  "azure-openai-responses": {
3202
3356
  "gpt-4": {
@@ -3750,6 +3904,74 @@ export const MODELS = {
3750
3904
  contextWindow: 1050000,
3751
3905
  maxTokens: 128000,
3752
3906
  },
3907
+ "gpt-6-luna": {
3908
+ id: "gpt-6-luna",
3909
+ name: "GPT-6 Luna",
3910
+ api: "azure-openai-responses",
3911
+ provider: "azure-openai-responses",
3912
+ baseUrl: "",
3913
+ reasoning: true,
3914
+ input: ["text", "image"],
3915
+ cost: {
3916
+ input: 0.1,
3917
+ output: 0.5,
3918
+ cacheRead: 0.01,
3919
+ cacheWrite: 0.125,
3920
+ },
3921
+ contextWindow: 1050000,
3922
+ maxTokens: 128000,
3923
+ },
3924
+ "gpt-6-sol": {
3925
+ id: "gpt-6-sol",
3926
+ name: "GPT-6 Sol",
3927
+ api: "azure-openai-responses",
3928
+ provider: "azure-openai-responses",
3929
+ baseUrl: "",
3930
+ reasoning: true,
3931
+ input: ["text", "image"],
3932
+ cost: {
3933
+ input: 2,
3934
+ output: 10,
3935
+ cacheRead: 0.2,
3936
+ cacheWrite: 2.5,
3937
+ },
3938
+ contextWindow: 1050000,
3939
+ maxTokens: 128000,
3940
+ },
3941
+ "gpt-daybreak-blue-latest": {
3942
+ id: "gpt-daybreak-blue-latest",
3943
+ name: "Daybreak Blue",
3944
+ api: "azure-openai-responses",
3945
+ provider: "azure-openai-responses",
3946
+ baseUrl: "",
3947
+ reasoning: true,
3948
+ input: ["text", "image"],
3949
+ cost: {
3950
+ input: 4,
3951
+ output: 20,
3952
+ cacheRead: 0.4,
3953
+ cacheWrite: 5,
3954
+ },
3955
+ contextWindow: 1050000,
3956
+ maxTokens: 128000,
3957
+ },
3958
+ "gpt-daybreak-red-latest": {
3959
+ id: "gpt-daybreak-red-latest",
3960
+ name: "Daybreak Red",
3961
+ api: "azure-openai-responses",
3962
+ provider: "azure-openai-responses",
3963
+ baseUrl: "",
3964
+ reasoning: true,
3965
+ input: ["text", "image"],
3966
+ cost: {
3967
+ input: 12.5,
3968
+ output: 75,
3969
+ cacheRead: 1.25,
3970
+ cacheWrite: 15.625,
3971
+ },
3972
+ contextWindow: 400000,
3973
+ maxTokens: 128000,
3974
+ },
3753
3975
  "gpt-realtime-2.1": {
3754
3976
  id: "gpt-realtime-2.1",
3755
3977
  name: "GPT-Realtime-2.1",
@@ -3902,8 +4124,8 @@ export const MODELS = {
3902
4124
  cacheRead: 0,
3903
4125
  cacheWrite: 0,
3904
4126
  },
3905
- contextWindow: 65536,
3906
- maxTokens: 32768,
4127
+ contextWindow: 131072,
4128
+ maxTokens: 40960,
3907
4129
  },
3908
4130
  },
3909
4131
  "cloudflare-ai-gateway": {
@@ -4048,6 +4270,23 @@ export const MODELS = {
4048
4270
  contextWindow: 1000000,
4049
4271
  maxTokens: 128000,
4050
4272
  },
4273
+ "claude-opus-5.5": {
4274
+ id: "claude-opus-5.5",
4275
+ name: "Claude Opus 5.5",
4276
+ api: "anthropic-messages",
4277
+ provider: "cloudflare-ai-gateway",
4278
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
4279
+ reasoning: true,
4280
+ input: ["text", "image"],
4281
+ cost: {
4282
+ input: 4,
4283
+ output: 20,
4284
+ cacheRead: 0.2,
4285
+ cacheWrite: 5,
4286
+ },
4287
+ contextWindow: 1000000,
4288
+ maxTokens: 128000,
4289
+ },
4051
4290
  "claude-sonnet-4.5": {
4052
4291
  id: "claude-sonnet-4.5",
4053
4292
  name: "Claude Sonnet 4.5 (latest)",
@@ -4435,6 +4674,40 @@ export const MODELS = {
4435
4674
  contextWindow: 1050000,
4436
4675
  maxTokens: 128000,
4437
4676
  },
4677
+ "gpt-6-luna": {
4678
+ id: "gpt-6-luna",
4679
+ name: "GPT-6 Luna",
4680
+ api: "openai-responses",
4681
+ provider: "cloudflare-ai-gateway",
4682
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
4683
+ reasoning: true,
4684
+ input: ["text", "image"],
4685
+ cost: {
4686
+ input: 0.1,
4687
+ output: 0.5,
4688
+ cacheRead: 0.01,
4689
+ cacheWrite: 0.125,
4690
+ },
4691
+ contextWindow: 1050000,
4692
+ maxTokens: 128000,
4693
+ },
4694
+ "gpt-6-sol": {
4695
+ id: "gpt-6-sol",
4696
+ name: "GPT-6 Sol",
4697
+ api: "openai-responses",
4698
+ provider: "cloudflare-ai-gateway",
4699
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
4700
+ reasoning: true,
4701
+ input: ["text", "image"],
4702
+ cost: {
4703
+ input: 2,
4704
+ output: 10,
4705
+ cacheRead: 0.2,
4706
+ cacheWrite: 2.5,
4707
+ },
4708
+ contextWindow: 1050000,
4709
+ maxTokens: 128000,
4710
+ },
4438
4711
  "o3": {
4439
4712
  id: "o3",
4440
4713
  name: "o3",
@@ -4856,74 +5129,6 @@ export const MODELS = {
4856
5129
  },
4857
5130
  },
4858
5131
  "fireworks": {
4859
- "accounts/fireworks/models/deepseek-v4-flash-0731": {
4860
- id: "accounts/fireworks/models/deepseek-v4-flash-0731",
4861
- name: "DeepSeek V4 Flash 0731",
4862
- api: "anthropic-messages",
4863
- provider: "fireworks",
4864
- baseUrl: "https://api.fireworks.ai/inference",
4865
- reasoning: true,
4866
- input: ["text"],
4867
- cost: {
4868
- input: 0.22,
4869
- output: 0.66,
4870
- cacheRead: 0.007,
4871
- cacheWrite: 0,
4872
- },
4873
- contextWindow: 1000000,
4874
- maxTokens: 384000,
4875
- },
4876
- "accounts/fireworks/models/deepseek-v4-flash-vision-exp": {
4877
- id: "accounts/fireworks/models/deepseek-v4-flash-vision-exp",
4878
- name: "DeepSeek V4 Flash Vision Exp",
4879
- api: "anthropic-messages",
4880
- provider: "fireworks",
4881
- baseUrl: "https://api.fireworks.ai/inference",
4882
- reasoning: true,
4883
- input: ["text", "image"],
4884
- cost: {
4885
- input: 0.22,
4886
- output: 0.66,
4887
- cacheRead: 0.007,
4888
- cacheWrite: 0,
4889
- },
4890
- contextWindow: 1000000,
4891
- maxTokens: 384000,
4892
- },
4893
- "accounts/fireworks/models/deepseek-v4-pro": {
4894
- id: "accounts/fireworks/models/deepseek-v4-pro",
4895
- name: "DeepSeek V4 Pro",
4896
- api: "anthropic-messages",
4897
- provider: "fireworks",
4898
- baseUrl: "https://api.fireworks.ai/inference",
4899
- reasoning: true,
4900
- input: ["text"],
4901
- cost: {
4902
- input: 1.2,
4903
- output: 1.2,
4904
- cacheRead: 0.6,
4905
- cacheWrite: 0,
4906
- },
4907
- contextWindow: 1000000,
4908
- maxTokens: 384000,
4909
- },
4910
- "accounts/fireworks/models/deepseek-v4-pro-0813": {
4911
- id: "accounts/fireworks/models/deepseek-v4-pro-0813",
4912
- name: "DeepSeek V4 Pro 0813",
4913
- api: "anthropic-messages",
4914
- provider: "fireworks",
4915
- baseUrl: "https://api.fireworks.ai/inference",
4916
- reasoning: true,
4917
- input: ["text"],
4918
- cost: {
4919
- input: 1.32,
4920
- output: 3.96,
4921
- cacheRead: 0.044,
4922
- cacheWrite: 0,
4923
- },
4924
- contextWindow: 1000000,
4925
- maxTokens: 384000,
4926
- },
4927
5132
  "accounts/fireworks/models/deepseek-v4p1-flash": {
4928
5133
  id: "accounts/fireworks/models/deepseek-v4p1-flash",
4929
5134
  name: "DeepSeek V4.1 Flash",
@@ -4941,21 +5146,21 @@ export const MODELS = {
4941
5146
  contextWindow: 1000000,
4942
5147
  maxTokens: 384000,
4943
5148
  },
4944
- "accounts/fireworks/models/glm-5p2": {
4945
- id: "accounts/fireworks/models/glm-5p2",
4946
- name: "GLM 5.2",
5149
+ "accounts/fireworks/models/ember-1": {
5150
+ id: "accounts/fireworks/models/ember-1",
5151
+ name: "Ember-1",
4947
5152
  api: "anthropic-messages",
4948
5153
  provider: "fireworks",
4949
5154
  baseUrl: "https://api.fireworks.ai/inference",
4950
5155
  reasoning: true,
4951
- input: ["text"],
5156
+ input: ["text", "image"],
4952
5157
  cost: {
4953
- input: 1.4,
4954
- output: 4.4,
4955
- cacheRead: 0.14,
5158
+ input: 3,
5159
+ output: 15,
5160
+ cacheRead: 0.3,
4956
5161
  cacheWrite: 0,
4957
5162
  },
4958
- contextWindow: 1048575,
5163
+ contextWindow: 1048576,
4959
5164
  maxTokens: 131072,
4960
5165
  },
4961
5166
  "accounts/fireworks/models/glm-5p3": {
@@ -5026,40 +5231,6 @@ export const MODELS = {
5026
5231
  contextWindow: 1048576,
5027
5232
  maxTokens: 1048576,
5028
5233
  },
5029
- "accounts/fireworks/models/kimi-k2p6": {
5030
- id: "accounts/fireworks/models/kimi-k2p6",
5031
- name: "Kimi K2.6",
5032
- api: "anthropic-messages",
5033
- provider: "fireworks",
5034
- baseUrl: "https://api.fireworks.ai/inference",
5035
- reasoning: true,
5036
- input: ["text", "image"],
5037
- cost: {
5038
- input: 0.95,
5039
- output: 4,
5040
- cacheRead: 0.16,
5041
- cacheWrite: 0,
5042
- },
5043
- contextWindow: 262000,
5044
- maxTokens: 262000,
5045
- },
5046
- "accounts/fireworks/models/kimi-k2p7-code": {
5047
- id: "accounts/fireworks/models/kimi-k2p7-code",
5048
- name: "Kimi K2.7 Code",
5049
- api: "anthropic-messages",
5050
- provider: "fireworks",
5051
- baseUrl: "https://api.fireworks.ai/inference",
5052
- reasoning: true,
5053
- input: ["text", "image"],
5054
- cost: {
5055
- input: 0.95,
5056
- output: 4,
5057
- cacheRead: 0.19,
5058
- cacheWrite: 0,
5059
- },
5060
- contextWindow: 262000,
5061
- maxTokens: 262000,
5062
- },
5063
5234
  "accounts/fireworks/models/kimi-k3": {
5064
5235
  id: "accounts/fireworks/models/kimi-k3",
5065
5236
  name: "Kimi K3",
@@ -5077,23 +5248,6 @@ export const MODELS = {
5077
5248
  contextWindow: 1048576,
5078
5249
  maxTokens: 131072,
5079
5250
  },
5080
- "accounts/fireworks/models/minimax-m2p7": {
5081
- id: "accounts/fireworks/models/minimax-m2p7",
5082
- name: "MiniMax-M2.7",
5083
- api: "anthropic-messages",
5084
- provider: "fireworks",
5085
- baseUrl: "https://api.fireworks.ai/inference",
5086
- reasoning: true,
5087
- input: ["text"],
5088
- cost: {
5089
- input: 1.2,
5090
- output: 1.2,
5091
- cacheRead: 0.6,
5092
- cacheWrite: 0,
5093
- },
5094
- contextWindow: 196608,
5095
- maxTokens: 131072,
5096
- },
5097
5251
  "accounts/fireworks/models/minimax-m3": {
5098
5252
  id: "accounts/fireworks/models/minimax-m3",
5099
5253
  name: "MiniMax-M3",
@@ -5111,23 +5265,6 @@ export const MODELS = {
5111
5265
  contextWindow: 512000,
5112
5266
  maxTokens: 512000,
5113
5267
  },
5114
- "accounts/fireworks/models/muse-glimmer-30b": {
5115
- id: "accounts/fireworks/models/muse-glimmer-30b",
5116
- name: "Muse Glimmer 30B",
5117
- api: "anthropic-messages",
5118
- provider: "fireworks",
5119
- baseUrl: "https://api.fireworks.ai/inference",
5120
- reasoning: true,
5121
- input: ["text", "image"],
5122
- cost: {
5123
- input: 0.35,
5124
- output: 1.5,
5125
- cacheRead: 0.04,
5126
- cacheWrite: 0,
5127
- },
5128
- contextWindow: 131072,
5129
- maxTokens: 131072,
5130
- },
5131
5268
  "accounts/fireworks/models/nemotron-3-ultra-nvfp4": {
5132
5269
  id: "accounts/fireworks/models/nemotron-3-ultra-nvfp4",
5133
5270
  name: "Nemotron 3 Ultra 550B A55B",
@@ -5162,23 +5299,6 @@ export const MODELS = {
5162
5299
  contextWindow: 262144,
5163
5300
  maxTokens: 262144,
5164
5301
  },
5165
- "accounts/fireworks/models/qwen3p7-plus": {
5166
- id: "accounts/fireworks/models/qwen3p7-plus",
5167
- name: "Qwen 3.7 Plus",
5168
- api: "anthropic-messages",
5169
- provider: "fireworks",
5170
- baseUrl: "https://api.fireworks.ai/inference",
5171
- reasoning: true,
5172
- input: ["text", "image"],
5173
- cost: {
5174
- input: 0.4,
5175
- output: 1.6,
5176
- cacheRead: 0.08,
5177
- cacheWrite: 0,
5178
- },
5179
- contextWindow: 262144,
5180
- maxTokens: 65536,
5181
- },
5182
5302
  "accounts/fireworks/models/qwen3p8-2p4t-a95b": {
5183
5303
  id: "accounts/fireworks/models/qwen3p8-2p4t-a95b",
5184
5304
  name: "Qwen3.8 2.4T A95B",
@@ -5230,40 +5350,6 @@ export const MODELS = {
5230
5350
  contextWindow: 1000000,
5231
5351
  maxTokens: 384000,
5232
5352
  },
5233
- "accounts/fireworks/routers/deepseek-pro-latest": {
5234
- id: "accounts/fireworks/routers/deepseek-pro-latest",
5235
- name: "DeepSeek Pro Latest",
5236
- api: "anthropic-messages",
5237
- provider: "fireworks",
5238
- baseUrl: "https://api.fireworks.ai/inference",
5239
- reasoning: true,
5240
- input: ["text"],
5241
- cost: {
5242
- input: 1.32,
5243
- output: 3.96,
5244
- cacheRead: 0.044,
5245
- cacheWrite: 0,
5246
- },
5247
- contextWindow: 1000000,
5248
- maxTokens: 384000,
5249
- },
5250
- "accounts/fireworks/routers/glm-5p2-fast": {
5251
- id: "accounts/fireworks/routers/glm-5p2-fast",
5252
- name: "GLM 5.2 Fast",
5253
- api: "anthropic-messages",
5254
- provider: "fireworks",
5255
- baseUrl: "https://api.fireworks.ai/inference",
5256
- reasoning: true,
5257
- input: ["text"],
5258
- cost: {
5259
- input: 2.1,
5260
- output: 6.6,
5261
- cacheRead: 0.21,
5262
- cacheWrite: 0,
5263
- },
5264
- contextWindow: 1048575,
5265
- maxTokens: 131072,
5266
- },
5267
5353
  "accounts/fireworks/routers/glm-5p3-fast": {
5268
5354
  id: "accounts/fireworks/routers/glm-5p3-fast",
5269
5355
  name: "GLM 5.3 Fast",
@@ -5535,6 +5621,25 @@ export const MODELS = {
5535
5621
  contextWindow: 1000000,
5536
5622
  maxTokens: 64000,
5537
5623
  },
5624
+ "claude-opus-5.5": {
5625
+ id: "claude-opus-5.5",
5626
+ name: "Claude Opus 5.5",
5627
+ api: "openai-completions",
5628
+ provider: "github-copilot",
5629
+ baseUrl: "https://api.individual.githubcopilot.com",
5630
+ headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
5631
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
5632
+ reasoning: true,
5633
+ input: ["text", "image"],
5634
+ cost: {
5635
+ input: 4,
5636
+ output: 20,
5637
+ cacheRead: 0.2,
5638
+ cacheWrite: 5,
5639
+ },
5640
+ contextWindow: 1000000,
5641
+ maxTokens: 128000,
5642
+ },
5538
5643
  "claude-sonnet-4.6": {
5539
5644
  id: "claude-sonnet-4.6",
5540
5645
  name: "Claude Sonnet 4.6",
@@ -5838,6 +5943,44 @@ export const MODELS = {
5838
5943
  contextWindow: 1050000,
5839
5944
  maxTokens: 128000,
5840
5945
  },
5946
+ "gpt-6-luna": {
5947
+ id: "gpt-6-luna",
5948
+ name: "GPT-6 Luna",
5949
+ api: "openai-completions",
5950
+ provider: "github-copilot",
5951
+ baseUrl: "https://api.individual.githubcopilot.com",
5952
+ headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
5953
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
5954
+ reasoning: true,
5955
+ input: ["text", "image"],
5956
+ cost: {
5957
+ input: 0.1,
5958
+ output: 0.5,
5959
+ cacheRead: 0.01,
5960
+ cacheWrite: 0.125,
5961
+ },
5962
+ contextWindow: 1050000,
5963
+ maxTokens: 128000,
5964
+ },
5965
+ "gpt-6-sol": {
5966
+ id: "gpt-6-sol",
5967
+ name: "GPT-6 Sol",
5968
+ api: "openai-completions",
5969
+ provider: "github-copilot",
5970
+ baseUrl: "https://api.individual.githubcopilot.com",
5971
+ headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
5972
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
5973
+ reasoning: true,
5974
+ input: ["text", "image"],
5975
+ cost: {
5976
+ input: 2,
5977
+ output: 10,
5978
+ cacheRead: 0.2,
5979
+ cacheWrite: 2.5,
5980
+ },
5981
+ contextWindow: 1050000,
5982
+ maxTokens: 128000,
5983
+ },
5841
5984
  "grok-4.5": {
5842
5985
  id: "grok-4.5",
5843
5986
  name: "Grok 4.5",
@@ -6021,8 +6164,8 @@ export const MODELS = {
6021
6164
  cacheRead: 0,
6022
6165
  cacheWrite: 0,
6023
6166
  },
6024
- contextWindow: 131072,
6025
- maxTokens: 65536,
6167
+ contextWindow: 128000,
6168
+ maxTokens: 64000,
6026
6169
  },
6027
6170
  "gemini-2.5-flash": {
6028
6171
  id: "gemini-2.5-flash",
@@ -6127,7 +6270,7 @@ export const MODELS = {
6127
6270
  cacheWrite: 0,
6128
6271
  },
6129
6272
  contextWindow: 65536,
6130
- maxTokens: 65536,
6273
+ maxTokens: 4096,
6131
6274
  },
6132
6275
  "gemini-3.1-flash-lite-preview": {
6133
6276
  id: "gemini-3.1-flash-lite-preview",
@@ -8185,7 +8328,7 @@ export const MODELS = {
8185
8328
  cacheRead: 0.06,
8186
8329
  cacheWrite: 0,
8187
8330
  },
8188
- contextWindow: 1048576,
8331
+ contextWindow: 1000000,
8189
8332
  maxTokens: 512000,
8190
8333
  },
8191
8334
  },
@@ -8238,7 +8381,7 @@ export const MODELS = {
8238
8381
  cacheRead: 0.06,
8239
8382
  cacheWrite: 0,
8240
8383
  },
8241
- contextWindow: 1048576,
8384
+ contextWindow: 1000000,
8242
8385
  maxTokens: 512000,
8243
8386
  },
8244
8387
  },
@@ -8876,7 +9019,7 @@ export const MODELS = {
8876
9019
  cacheWrite: 0,
8877
9020
  },
8878
9021
  contextWindow: 1048576,
8879
- maxTokens: 131072,
9022
+ maxTokens: 1048576,
8880
9023
  },
8881
9024
  },
8882
9025
  "moonshotai-cn": {
@@ -8950,7 +9093,7 @@ export const MODELS = {
8950
9093
  cacheWrite: 0,
8951
9094
  },
8952
9095
  contextWindow: 1048576,
8953
- maxTokens: 131072,
9096
+ maxTokens: 1048576,
8954
9097
  },
8955
9098
  },
8956
9099
  "openai": {
@@ -9505,33 +9648,101 @@ export const MODELS = {
9505
9648
  contextWindow: 1050000,
9506
9649
  maxTokens: 128000,
9507
9650
  },
9508
- "gpt-realtime-2.1": {
9509
- id: "gpt-realtime-2.1",
9510
- name: "GPT-Realtime-2.1",
9651
+ "gpt-6-luna": {
9652
+ id: "gpt-6-luna",
9653
+ name: "GPT-6 Luna",
9511
9654
  api: "openai-responses",
9512
9655
  provider: "openai",
9513
9656
  baseUrl: "https://api.openai.com/v1",
9514
9657
  reasoning: true,
9515
9658
  input: ["text", "image"],
9516
9659
  cost: {
9517
- input: 4,
9518
- output: 24,
9519
- cacheRead: 0.4,
9520
- cacheWrite: 0,
9660
+ input: 0.1,
9661
+ output: 0.5,
9662
+ cacheRead: 0.01,
9663
+ cacheWrite: 0.125,
9521
9664
  },
9522
- contextWindow: 128000,
9523
- maxTokens: 32000,
9665
+ contextWindow: 1050000,
9666
+ maxTokens: 128000,
9524
9667
  },
9525
- "o1": {
9526
- id: "o1",
9527
- name: "o1",
9668
+ "gpt-6-sol": {
9669
+ id: "gpt-6-sol",
9670
+ name: "GPT-6 Sol",
9528
9671
  api: "openai-responses",
9529
9672
  provider: "openai",
9530
9673
  baseUrl: "https://api.openai.com/v1",
9531
9674
  reasoning: true,
9532
9675
  input: ["text", "image"],
9533
9676
  cost: {
9534
- input: 15,
9677
+ input: 2,
9678
+ output: 10,
9679
+ cacheRead: 0.2,
9680
+ cacheWrite: 2.5,
9681
+ },
9682
+ contextWindow: 1050000,
9683
+ maxTokens: 128000,
9684
+ },
9685
+ "gpt-daybreak-blue-latest": {
9686
+ id: "gpt-daybreak-blue-latest",
9687
+ name: "Daybreak Blue",
9688
+ api: "openai-responses",
9689
+ provider: "openai",
9690
+ baseUrl: "https://api.openai.com/v1",
9691
+ reasoning: true,
9692
+ input: ["text", "image"],
9693
+ cost: {
9694
+ input: 4,
9695
+ output: 20,
9696
+ cacheRead: 0.4,
9697
+ cacheWrite: 5,
9698
+ },
9699
+ contextWindow: 1050000,
9700
+ maxTokens: 128000,
9701
+ },
9702
+ "gpt-daybreak-red-latest": {
9703
+ id: "gpt-daybreak-red-latest",
9704
+ name: "Daybreak Red",
9705
+ api: "openai-responses",
9706
+ provider: "openai",
9707
+ baseUrl: "https://api.openai.com/v1",
9708
+ reasoning: true,
9709
+ input: ["text", "image"],
9710
+ cost: {
9711
+ input: 12.5,
9712
+ output: 75,
9713
+ cacheRead: 1.25,
9714
+ cacheWrite: 15.625,
9715
+ },
9716
+ contextWindow: 400000,
9717
+ maxTokens: 128000,
9718
+ },
9719
+ "gpt-realtime-2.1": {
9720
+ id: "gpt-realtime-2.1",
9721
+ name: "GPT-Realtime-2.1",
9722
+ api: "openai-responses",
9723
+ provider: "openai",
9724
+ baseUrl: "https://api.openai.com/v1",
9725
+ reasoning: true,
9726
+ input: ["text", "image"],
9727
+ cost: {
9728
+ input: 4,
9729
+ output: 24,
9730
+ cacheRead: 0.4,
9731
+ cacheWrite: 0,
9732
+ },
9733
+ contextWindow: 128000,
9734
+ maxTokens: 32000,
9735
+ },
9736
+ "o1": {
9737
+ id: "o1",
9738
+ name: "o1",
9739
+ api: "openai-responses",
9740
+ provider: "openai",
9741
+ baseUrl: "https://api.openai.com/v1",
9742
+ reasoning: true,
9743
+ input: ["text", "image"],
9744
+ cost: {
9745
+ input: 15,
9535
9746
  output: 60,
9536
9747
  cacheRead: 7.5,
9537
9748
  cacheWrite: 0,
@@ -9964,6 +10175,23 @@ export const MODELS = {
9964
10175
  contextWindow: 1000000,
9965
10176
  maxTokens: 128000,
9966
10177
  },
10178
+ "claude-opus-5-5": {
10179
+ id: "claude-opus-5-5",
10180
+ name: "Claude Opus 5.5",
10181
+ api: "anthropic-messages",
10182
+ provider: "opencode",
10183
+ baseUrl: "https://opencode.ai/zen",
10184
+ reasoning: true,
10185
+ input: ["text", "image"],
10186
+ cost: {
10187
+ input: 4,
10188
+ output: 20,
10189
+ cacheRead: 0.2,
10190
+ cacheWrite: 5,
10191
+ },
10192
+ contextWindow: 1000000,
10193
+ maxTokens: 128000,
10194
+ },
9967
10195
  "claude-sonnet-4": {
9968
10196
  id: "claude-sonnet-4",
9969
10197
  name: "Claude Sonnet 4",
@@ -10678,6 +10906,40 @@ export const MODELS = {
10678
10906
  contextWindow: 1050000,
10679
10907
  maxTokens: 128000,
10680
10908
  },
10909
+ "gpt-6-luna": {
10910
+ id: "gpt-6-luna",
10911
+ name: "GPT-6 Luna",
10912
+ api: "openai-responses",
10913
+ provider: "opencode",
10914
+ baseUrl: "https://opencode.ai/zen/v1",
10915
+ reasoning: true,
10916
+ input: ["text", "image"],
10917
+ cost: {
10918
+ input: 0.1,
10919
+ output: 0.5,
10920
+ cacheRead: 0.01,
10921
+ cacheWrite: 0.125,
10922
+ },
10923
+ contextWindow: 1050000,
10924
+ maxTokens: 128000,
10925
+ },
10926
+ "gpt-6-sol": {
10927
+ id: "gpt-6-sol",
10928
+ name: "GPT-6 Sol",
10929
+ api: "openai-responses",
10930
+ provider: "opencode",
10931
+ baseUrl: "https://opencode.ai/zen/v1",
10932
+ reasoning: true,
10933
+ input: ["text", "image"],
10934
+ cost: {
10935
+ input: 2,
10936
+ output: 10,
10937
+ cacheRead: 0.2,
10938
+ cacheWrite: 2.5,
10939
+ },
10940
+ contextWindow: 1050000,
10941
+ maxTokens: 128000,
10942
+ },
10681
10943
  "grok-4.5": {
10682
10944
  id: "grok-4.5",
10683
10945
  name: "Grok 4.5",
@@ -10712,6 +10974,23 @@ export const MODELS = {
10712
10974
  contextWindow: 500000,
10713
10975
  maxTokens: 500000,
10714
10976
  },
10977
+ "grok-4.7": {
10978
+ id: "grok-4.7",
10979
+ name: "Grok 4.7",
10980
+ api: "openai-responses",
10981
+ provider: "opencode",
10982
+ baseUrl: "https://opencode.ai/zen/v1",
10983
+ reasoning: true,
10984
+ input: ["text", "image"],
10985
+ cost: {
10986
+ input: 2,
10987
+ output: 6,
10988
+ cacheRead: 0.5,
10989
+ cacheWrite: 0,
10990
+ },
10991
+ contextWindow: 500000,
10992
+ maxTokens: 500000,
10993
+ },
10715
10994
  "grok-build-0.1": {
10716
10995
  id: "grok-build-0.1",
10717
10996
  name: "Grok Build 0.1",
@@ -10814,6 +11093,23 @@ export const MODELS = {
10814
11093
  contextWindow: 262144,
10815
11094
  maxTokens: 32768,
10816
11095
  },
11096
+ "longcat-2.5-preview-free": {
11097
+ id: "longcat-2.5-preview-free",
11098
+ name: "LongCat 2.5 Preview Free",
11099
+ api: "openai-completions",
11100
+ provider: "opencode",
11101
+ baseUrl: "https://opencode.ai/zen/v1",
11102
+ reasoning: true,
11103
+ input: ["text", "image"],
11104
+ cost: {
11105
+ input: 0,
11106
+ output: 0,
11107
+ cacheRead: 0,
11108
+ cacheWrite: 0,
11109
+ },
11110
+ contextWindow: 1000000,
11111
+ maxTokens: 131072,
11112
+ },
10817
11113
  "mimo-v2.6-flash-free": {
10818
11114
  id: "mimo-v2.6-flash-free",
10819
11115
  name: "MiMo-V2.6-Flash Free",
@@ -10899,23 +11195,6 @@ export const MODELS = {
10899
11195
  contextWindow: 1048576,
10900
11196
  maxTokens: 131072,
10901
11197
  },
10902
- "muse-spark-1.2-contributor-free": {
10903
- id: "muse-spark-1.2-contributor-free",
10904
- name: "Muse Spark 1.2 Free",
10905
- api: "openai-responses",
10906
- provider: "opencode",
10907
- baseUrl: "https://opencode.ai/zen/v1",
10908
- reasoning: true,
10909
- input: ["text", "image"],
10910
- cost: {
10911
- input: 0,
10912
- output: 0,
10913
- cacheRead: 0,
10914
- cacheWrite: 0,
10915
- },
10916
- contextWindow: 1048576,
10917
- maxTokens: 131072,
10918
- },
10919
11198
  "muse-spark-1.3": {
10920
11199
  id: "muse-spark-1.3",
10921
11200
  name: "Muse Spark 1.3",
@@ -11035,6 +11314,40 @@ export const MODELS = {
11035
11314
  contextWindow: 1000000,
11036
11315
  maxTokens: 131072,
11037
11316
  },
11317
+ "qwen3.8-max": {
11318
+ id: "qwen3.8-max",
11319
+ name: "Qwen3.8 Max",
11320
+ api: "openai-completions",
11321
+ provider: "opencode",
11322
+ baseUrl: "https://opencode.ai/zen/v1",
11323
+ reasoning: true,
11324
+ input: ["text", "image"],
11325
+ cost: {
11326
+ input: 2,
11327
+ output: 6,
11328
+ cacheRead: 0.25,
11329
+ cacheWrite: 2.5,
11330
+ },
11331
+ contextWindow: 262144,
11332
+ maxTokens: 131072,
11333
+ },
11334
+ "space-bunny-free": {
11335
+ id: "space-bunny-free",
11336
+ name: "Space Bunny Free",
11337
+ api: "openai-completions",
11338
+ provider: "opencode",
11339
+ baseUrl: "https://opencode.ai/zen/v1",
11340
+ reasoning: true,
11341
+ input: ["text", "image"],
11342
+ cost: {
11343
+ input: 0,
11344
+ output: 0,
11345
+ cacheRead: 0,
11346
+ cacheWrite: 0,
11347
+ },
11348
+ contextWindow: 1048576,
11349
+ maxTokens: 524288,
11350
+ },
11038
11351
  },
11039
11352
  "opencode-go": {
11040
11353
  "deepseek-v4-flash": {
@@ -11113,23 +11426,6 @@ export const MODELS = {
11113
11426
  contextWindow: 1000000,
11114
11427
  maxTokens: 384000,
11115
11428
  },
11116
- "glm-5.1": {
11117
- id: "glm-5.1",
11118
- name: "GLM-5.1",
11119
- api: "openai-completions",
11120
- provider: "opencode-go",
11121
- baseUrl: "https://opencode.ai/zen/go/v1",
11122
- reasoning: true,
11123
- input: ["text"],
11124
- cost: {
11125
- input: 1.4,
11126
- output: 4.4,
11127
- cacheRead: 0.26,
11128
- cacheWrite: 0,
11129
- },
11130
- contextWindow: 202752,
11131
- maxTokens: 32768,
11132
- },
11133
11429
  "glm-5.2": {
11134
11430
  id: "glm-5.2",
11135
11431
  name: "GLM-5.2",
@@ -11199,6 +11495,23 @@ export const MODELS = {
11199
11495
  contextWindow: 1050000,
11200
11496
  maxTokens: 128000,
11201
11497
  },
11498
+ "gpt-6-luna": {
11499
+ id: "gpt-6-luna",
11500
+ name: "GPT-6 Luna",
11501
+ api: "openai-responses",
11502
+ provider: "opencode-go",
11503
+ baseUrl: "https://opencode.ai/zen/go/v1",
11504
+ reasoning: true,
11505
+ input: ["text", "image"],
11506
+ cost: {
11507
+ input: 0.1,
11508
+ output: 0.5,
11509
+ cacheRead: 0.01,
11510
+ cacheWrite: 0.125,
11511
+ },
11512
+ contextWindow: 1050000,
11513
+ maxTokens: 128000,
11514
+ },
11202
11515
  "grok-4.6": {
11203
11516
  id: "grok-4.6",
11204
11517
  name: "Grok 4.6",
@@ -11267,23 +11580,6 @@ export const MODELS = {
11267
11580
  contextWindow: 1024000,
11268
11581
  maxTokens: 64000,
11269
11582
  },
11270
- "kimi-k2.6": {
11271
- id: "kimi-k2.6",
11272
- name: "Kimi K2.6",
11273
- api: "openai-completions",
11274
- provider: "opencode-go",
11275
- baseUrl: "https://opencode.ai/zen/go/v1",
11276
- reasoning: true,
11277
- input: ["text", "image"],
11278
- cost: {
11279
- input: 0.95,
11280
- output: 4,
11281
- cacheRead: 0.16,
11282
- cacheWrite: 0,
11283
- },
11284
- contextWindow: 262144,
11285
- maxTokens: 65536,
11286
- },
11287
11583
  "kimi-k2.7-code": {
11288
11584
  id: "kimi-k2.7-code",
11289
11585
  name: "Kimi K2.7 Code",
@@ -11335,6 +11631,23 @@ export const MODELS = {
11335
11631
  contextWindow: 1000000,
11336
11632
  maxTokens: 131072,
11337
11633
  },
11634
+ "longcat-2.5-preview-free": {
11635
+ id: "longcat-2.5-preview-free",
11636
+ name: "LongCat 2.5 Preview Free",
11637
+ api: "openai-completions",
11638
+ provider: "opencode-go",
11639
+ baseUrl: "https://opencode.ai/zen/go/v1",
11640
+ reasoning: true,
11641
+ input: ["text", "image"],
11642
+ cost: {
11643
+ input: 0,
11644
+ output: 0,
11645
+ cacheRead: 0,
11646
+ cacheWrite: 0,
11647
+ },
11648
+ contextWindow: 1000000,
11649
+ maxTokens: 131072,
11650
+ },
11338
11651
  "mimo-v2.5": {
11339
11652
  id: "mimo-v2.5",
11340
11653
  name: "MiMo V2.5",
@@ -11471,41 +11784,6 @@ export const MODELS = {
11471
11784
  contextWindow: 1048576,
11472
11785
  maxTokens: 131072,
11473
11786
  },
11474
- "qwen3.6-plus": {
11475
- id: "qwen3.6-plus",
11476
- name: "Qwen3.6 Plus",
11477
- api: "openai-completions",
11478
- provider: "opencode-go",
11479
- baseUrl: "https://opencode.ai/zen/go/v1",
11480
- compat: { "thinkingFormat": "qwen" },
11481
- reasoning: true,
11482
- input: ["text", "image"],
11483
- cost: {
11484
- input: 0.5,
11485
- output: 3,
11486
- cacheRead: 0.05,
11487
- cacheWrite: 0.625,
11488
- },
11489
- contextWindow: 1000000,
11490
- maxTokens: 65536,
11491
- },
11492
- "qwen3.7-max": {
11493
- id: "qwen3.7-max",
11494
- name: "Qwen3.7 Max",
11495
- api: "openai-completions",
11496
- provider: "opencode-go",
11497
- baseUrl: "https://opencode.ai/zen/go/v1",
11498
- reasoning: true,
11499
- input: ["text"],
11500
- cost: {
11501
- input: 2.5,
11502
- output: 7.5,
11503
- cacheRead: 0.5,
11504
- cacheWrite: 3.125,
11505
- },
11506
- contextWindow: 1000000,
11507
- maxTokens: 65536,
11508
- },
11509
11787
  "qwen3.7-plus": {
11510
11788
  id: "qwen3.7-plus",
11511
11789
  name: "Qwen3.7 Plus",
@@ -11557,6 +11835,23 @@ export const MODELS = {
11557
11835
  contextWindow: 1000000,
11558
11836
  maxTokens: 131072,
11559
11837
  },
11838
+ "space-bunny-free": {
11839
+ id: "space-bunny-free",
11840
+ name: "Space Bunny Free",
11841
+ api: "openai-completions",
11842
+ provider: "opencode-go",
11843
+ baseUrl: "https://opencode.ai/zen/go/v1",
11844
+ reasoning: true,
11845
+ input: ["text", "image"],
11846
+ cost: {
11847
+ input: 0,
11848
+ output: 0,
11849
+ cacheRead: 0,
11850
+ cacheWrite: 0,
11851
+ },
11852
+ contextWindow: 1048576,
11853
+ maxTokens: 524288,
11854
+ },
11560
11855
  },
11561
11856
  "openrouter": {
11562
11857
  "aion-labs/aion-2.0": {
@@ -11573,7 +11868,7 @@ export const MODELS = {
11573
11868
  cacheRead: 0.19999999999999998,
11574
11869
  cacheWrite: 0,
11575
11870
  },
11576
- contextWindow: 1048576,
11871
+ contextWindow: 131072,
11577
11872
  maxTokens: 32768,
11578
11873
  },
11579
11874
  "aion-labs/aion-3.0": {
@@ -11590,7 +11885,7 @@ export const MODELS = {
11590
11885
  cacheRead: 0.75,
11591
11886
  cacheWrite: 0,
11592
11887
  },
11593
- contextWindow: 1048576,
11888
+ contextWindow: 131072,
11594
11889
  maxTokens: 32768,
11595
11890
  },
11596
11891
  "aion-labs/aion-3.0-mini": {
@@ -11607,7 +11902,41 @@ export const MODELS = {
11607
11902
  cacheRead: 0.18,
11608
11903
  cacheWrite: 0,
11609
11904
  },
11610
- contextWindow: 1048576,
11905
+ contextWindow: 131072,
11906
+ maxTokens: 32768,
11907
+ },
11908
+ "aion-labs/aion-3.5": {
11909
+ id: "aion-labs/aion-3.5",
11910
+ name: "AionLabs: Aion 3.5",
11911
+ api: "openai-completions",
11912
+ provider: "openrouter",
11913
+ baseUrl: "https://openrouter.ai/api/v1",
11914
+ reasoning: true,
11915
+ input: ["text"],
11916
+ cost: {
11917
+ input: 3,
11918
+ output: 6,
11919
+ cacheRead: 0.75,
11920
+ cacheWrite: 0,
11921
+ },
11922
+ contextWindow: 262144,
11923
+ maxTokens: 32768,
11924
+ },
11925
+ "aion-labs/aion-3.5-mini": {
11926
+ id: "aion-labs/aion-3.5-mini",
11927
+ name: "AionLabs: Aion 3.5 Mini",
11928
+ api: "openai-completions",
11929
+ provider: "openrouter",
11930
+ baseUrl: "https://openrouter.ai/api/v1",
11931
+ reasoning: true,
11932
+ input: ["text"],
11933
+ cost: {
11934
+ input: 0.7,
11935
+ output: 1.4,
11936
+ cacheRead: 0.18,
11937
+ cacheWrite: 0,
11938
+ },
11939
+ contextWindow: 262144,
11611
11940
  maxTokens: 32768,
11612
11941
  },
11613
11942
  "amazon/nova-2-lite-v1": {
@@ -11695,23 +12024,6 @@ export const MODELS = {
11695
12024
  contextWindow: 300000,
11696
12025
  maxTokens: 5120,
11697
12026
  },
11698
- "anthropic/claude-3-haiku": {
11699
- id: "anthropic/claude-3-haiku",
11700
- name: "Anthropic: Claude 3 Haiku",
11701
- api: "openai-completions",
11702
- provider: "openrouter",
11703
- baseUrl: "https://openrouter.ai/api/v1",
11704
- reasoning: false,
11705
- input: ["text", "image"],
11706
- cost: {
11707
- input: 0.25,
11708
- output: 1.25,
11709
- cacheRead: 0.03,
11710
- cacheWrite: 0.3,
11711
- },
11712
- contextWindow: 200000,
11713
- maxTokens: 4096,
11714
- },
11715
12027
  "anthropic/claude-fable-5": {
11716
12028
  id: "anthropic/claude-fable-5",
11717
12029
  name: "Anthropic: Claude Fable 5",
@@ -12164,6 +12476,23 @@ export const MODELS = {
12164
12476
  contextWindow: 1000000,
12165
12477
  maxTokens: 128000,
12166
12478
  },
12479
+ "anthropic/claude-sonnet-5.5": {
12480
+ id: "anthropic/claude-sonnet-5.5",
12481
+ name: "Anthropic: Claude Sonnet 5.5",
12482
+ api: "openai-completions",
12483
+ provider: "openrouter",
12484
+ baseUrl: "https://openrouter.ai/api/v1",
12485
+ reasoning: true,
12486
+ input: ["text", "image"],
12487
+ cost: {
12488
+ input: 2,
12489
+ output: 10,
12490
+ cacheRead: 0.19999999999999998,
12491
+ cacheWrite: 2.5,
12492
+ },
12493
+ contextWindow: 1000000,
12494
+ maxTokens: 128000,
12495
+ },
12167
12496
  "anthropic/claude-sonnet-5:batch": {
12168
12497
  id: "anthropic/claude-sonnet-5:batch",
12169
12498
  name: "Anthropic: Claude Sonnet 5 (batch)",
@@ -12317,6 +12646,23 @@ export const MODELS = {
12317
12646
  contextWindow: 262144,
12318
12647
  maxTokens: 131072,
12319
12648
  },
12649
+ "cohere/command-a-plus": {
12650
+ id: "cohere/command-a-plus",
12651
+ name: "Cohere: Command A+",
12652
+ api: "openai-completions",
12653
+ provider: "openrouter",
12654
+ baseUrl: "https://openrouter.ai/api/v1",
12655
+ reasoning: true,
12656
+ input: ["text", "image"],
12657
+ cost: {
12658
+ input: 0.3,
12659
+ output: 1.5,
12660
+ cacheRead: 0.15,
12661
+ cacheWrite: 0,
12662
+ },
12663
+ contextWindow: 192000,
12664
+ maxTokens: 64000,
12665
+ },
12320
12666
  "cohere/command-r-08-2024": {
12321
12667
  id: "cohere/command-r-08-2024",
12322
12668
  name: "Cohere: Command R (08-2024)",
@@ -12377,13 +12723,13 @@ export const MODELS = {
12377
12723
  reasoning: false,
12378
12724
  input: ["text"],
12379
12725
  cost: {
12380
- input: 0.32,
12381
- output: 0.8899999999999999,
12726
+ input: 0.2574,
12727
+ output: 1.0287,
12382
12728
  cacheRead: 0,
12383
12729
  cacheWrite: 0,
12384
12730
  },
12385
12731
  contextWindow: 163840,
12386
- maxTokens: 16384,
12732
+ maxTokens: 16000,
12387
12733
  },
12388
12734
  "deepseek/deepseek-chat-v3-0324": {
12389
12735
  id: "deepseek/deepseek-chat-v3-0324",
@@ -12394,9 +12740,9 @@ export const MODELS = {
12394
12740
  reasoning: false,
12395
12741
  input: ["text"],
12396
12742
  cost: {
12397
- input: 0.25,
12398
- output: 1,
12399
- cacheRead: 0,
12743
+ input: 0.29,
12744
+ output: 1.1400000000000001,
12745
+ cacheRead: 0.11,
12400
12746
  cacheWrite: 0,
12401
12747
  },
12402
12748
  contextWindow: 163840,
@@ -12464,11 +12810,11 @@ export const MODELS = {
12464
12810
  cost: {
12465
12811
  input: 0.27,
12466
12812
  output: 1,
12467
- cacheRead: 0.135,
12813
+ cacheRead: 0,
12468
12814
  cacheWrite: 0,
12469
12815
  },
12470
12816
  contextWindow: 163840,
12471
- maxTokens: 32768,
12817
+ maxTokens: 147456,
12472
12818
  },
12473
12819
  "deepseek/deepseek-v3.2": {
12474
12820
  id: "deepseek/deepseek-v3.2",
@@ -12479,9 +12825,9 @@ export const MODELS = {
12479
12825
  reasoning: true,
12480
12826
  input: ["text"],
12481
12827
  cost: {
12482
- input: 0.26899999999999996,
12483
- output: 0.39999999999999997,
12484
- cacheRead: 0.13449999999999998,
12828
+ input: 0.28,
12829
+ output: 0.42,
12830
+ cacheRead: 0.028,
12485
12831
  cacheWrite: 0,
12486
12832
  },
12487
12833
  contextWindow: 163840,
@@ -12496,13 +12842,13 @@ export const MODELS = {
12496
12842
  reasoning: true,
12497
12843
  input: ["text"],
12498
12844
  cost: {
12499
- input: 0.27,
12500
- output: 0.41,
12501
- cacheRead: 0,
12845
+ input: 0.13440000000000002,
12846
+ output: 0.2016,
12847
+ cacheRead: 0.06720000000000001,
12502
12848
  cacheWrite: 0,
12503
12849
  },
12504
12850
  contextWindow: 163840,
12505
- maxTokens: 65536,
12851
+ maxTokens: 147456,
12506
12852
  },
12507
12853
  "deepseek/deepseek-v4-flash": {
12508
12854
  id: "deepseek/deepseek-v4-flash",
@@ -12515,13 +12861,13 @@ export const MODELS = {
12515
12861
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12516
12862
  input: ["text"],
12517
12863
  cost: {
12518
- input: 0.049,
12519
- output: 0.098,
12520
- cacheRead: 0.0098,
12864
+ input: 0.06538,
12865
+ output: 0.13076,
12866
+ cacheRead: 0.013076,
12521
12867
  cacheWrite: 0,
12522
12868
  },
12523
12869
  contextWindow: 1048576,
12524
- maxTokens: 384000,
12870
+ maxTokens: 131072,
12525
12871
  },
12526
12872
  "deepseek/deepseek-v4-flash-0731": {
12527
12873
  id: "deepseek/deepseek-v4-flash-0731",
@@ -12534,8 +12880,8 @@ export const MODELS = {
12534
12880
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12535
12881
  input: ["text"],
12536
12882
  cost: {
12537
- input: 0.04,
12538
- output: 0.64,
12883
+ input: 0.020999999999999998,
12884
+ output: 0.32,
12539
12885
  cacheRead: 0.016,
12540
12886
  cacheWrite: 0,
12541
12887
  },
@@ -12553,13 +12899,13 @@ export const MODELS = {
12553
12899
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12554
12900
  input: ["text", "image"],
12555
12901
  cost: {
12556
- input: 0.22,
12557
- output: 0.66,
12558
- cacheRead: 0.007,
12902
+ input: 0.44,
12903
+ output: 1.32,
12904
+ cacheRead: 0.014,
12559
12905
  cacheWrite: 0,
12560
12906
  },
12561
12907
  contextWindow: 1048576,
12562
- maxTokens: 943718,
12908
+ maxTokens: 943717,
12563
12909
  },
12564
12910
  "deepseek/deepseek-v4-pro": {
12565
12911
  id: "deepseek/deepseek-v4-pro",
@@ -12572,9 +12918,9 @@ export const MODELS = {
12572
12918
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12573
12919
  input: ["text"],
12574
12920
  cost: {
12575
- input: 0.90741,
12576
- output: 1.81482,
12577
- cacheRead: 0.07561749999999999,
12921
+ input: 0.7829999999999999,
12922
+ output: 1.5659999999999998,
12923
+ cacheRead: 0.06525,
12578
12924
  cacheWrite: 0,
12579
12925
  },
12580
12926
  contextWindow: 1048576,
@@ -12591,13 +12937,13 @@ export const MODELS = {
12591
12937
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12592
12938
  input: ["text"],
12593
12939
  cost: {
12594
- input: 0.66,
12595
- output: 1.9800000000000002,
12596
- cacheRead: 0.022,
12940
+ input: 0.3995,
12941
+ output: 4.199999999999999,
12942
+ cacheRead: 0.399,
12597
12943
  cacheWrite: 0,
12598
12944
  },
12599
12945
  contextWindow: 1048576,
12600
- maxTokens: 384000,
12946
+ maxTokens: 943718,
12601
12947
  },
12602
12948
  "deepseek/deepseek-v4.1-flash": {
12603
12949
  id: "deepseek/deepseek-v4.1-flash",
@@ -12610,13 +12956,13 @@ export const MODELS = {
12610
12956
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12611
12957
  input: ["text", "image"],
12612
12958
  cost: {
12613
- input: 0.15,
12614
- output: 0.6,
12615
- cacheRead: 0.003,
12959
+ input: 0.3,
12960
+ output: 1.2,
12961
+ cacheRead: 0.006,
12616
12962
  cacheWrite: 0,
12617
12963
  },
12618
12964
  contextWindow: 1048576,
12619
- maxTokens: 384000,
12965
+ maxTokens: 943718,
12620
12966
  },
12621
12967
  "deepseek/deepseek-v4.1-flash:batch": {
12622
12968
  id: "deepseek/deepseek-v4.1-flash:batch",
@@ -12654,6 +13000,23 @@ export const MODELS = {
12654
13000
  contextWindow: 512000,
12655
13001
  maxTokens: 460800,
12656
13002
  },
13003
+ "fireworks/ember-1": {
13004
+ id: "fireworks/ember-1",
13005
+ name: "Fireworks: Ember-1",
13006
+ api: "openai-completions",
13007
+ provider: "openrouter",
13008
+ baseUrl: "https://openrouter.ai/api/v1",
13009
+ reasoning: true,
13010
+ input: ["text", "image"],
13011
+ cost: {
13012
+ input: 3,
13013
+ output: 15,
13014
+ cacheRead: 0.3,
13015
+ cacheWrite: 0,
13016
+ },
13017
+ contextWindow: 1048576,
13018
+ maxTokens: 943718,
13019
+ },
12657
13020
  "google/gemini-2.5-flash": {
12658
13021
  id: "google/gemini-2.5-flash",
12659
13022
  name: "Google: Gemini 2.5 Flash",
@@ -13283,23 +13646,6 @@ export const MODELS = {
13283
13646
  contextWindow: 262144,
13284
13647
  maxTokens: 235929,
13285
13648
  },
13286
- "inclusionai/ling-3.0-flash-fin:free": {
13287
- id: "inclusionai/ling-3.0-flash-fin:free",
13288
- name: "inclusionAI: Ling 3.0 Flash Fin (free)",
13289
- api: "openai-completions",
13290
- provider: "openrouter",
13291
- baseUrl: "https://openrouter.ai/api/v1",
13292
- reasoning: true,
13293
- input: ["text"],
13294
- cost: {
13295
- input: 0,
13296
- output: 0,
13297
- cacheRead: 0,
13298
- cacheWrite: 0,
13299
- },
13300
- contextWindow: 262144,
13301
- maxTokens: 32768,
13302
- },
13303
13649
  "inclusionai/ling-3.0-flash-sante:free": {
13304
13650
  id: "inclusionai/ling-3.0-flash-sante:free",
13305
13651
  name: "inclusionAI: Ling 3.0 Flash Sante (free)",
@@ -13308,44 +13654,27 @@ export const MODELS = {
13308
13654
  baseUrl: "https://openrouter.ai/api/v1",
13309
13655
  reasoning: true,
13310
13656
  input: ["text"],
13311
- cost: {
13312
- input: 0,
13313
- output: 0,
13314
- cacheRead: 0,
13315
- cacheWrite: 0,
13316
- },
13317
- contextWindow: 262144,
13318
- maxTokens: 32768,
13319
- },
13320
- "inclusionai/ling-3.0-flash-vl": {
13321
- id: "inclusionai/ling-3.0-flash-vl",
13322
- name: "inclusionAI: Ling 3.0 Flash VL",
13323
- api: "openai-completions",
13324
- provider: "openrouter",
13325
- baseUrl: "https://openrouter.ai/api/v1",
13326
- reasoning: true,
13327
- input: ["text", "image"],
13328
- cost: {
13329
- input: 0.06,
13330
- output: 0.18,
13331
- cacheRead: 0.012,
13657
+ cost: {
13658
+ input: 0,
13659
+ output: 0,
13660
+ cacheRead: 0,
13332
13661
  cacheWrite: 0,
13333
13662
  },
13334
- contextWindow: 131072,
13663
+ contextWindow: 262144,
13335
13664
  maxTokens: 32768,
13336
13665
  },
13337
- "inclusionai/ling-3.0-flash-vl:free": {
13338
- id: "inclusionai/ling-3.0-flash-vl:free",
13339
- name: "inclusionAI: Ling 3.0 Flash VL (free)",
13666
+ "inclusionai/ling-3.0-flash-vl": {
13667
+ id: "inclusionai/ling-3.0-flash-vl",
13668
+ name: "inclusionAI: Ling 3.0 Flash VL",
13340
13669
  api: "openai-completions",
13341
13670
  provider: "openrouter",
13342
13671
  baseUrl: "https://openrouter.ai/api/v1",
13343
13672
  reasoning: true,
13344
13673
  input: ["text", "image"],
13345
13674
  cost: {
13346
- input: 0,
13347
- output: 0,
13348
- cacheRead: 0,
13675
+ input: 0.020999999999999998,
13676
+ output: 0.061599999999999995,
13677
+ cacheRead: 0.004200000000000001,
13349
13678
  cacheWrite: 0,
13350
13679
  },
13351
13680
  contextWindow: 262144,
@@ -13615,13 +13944,13 @@ export const MODELS = {
13615
13944
  reasoning: true,
13616
13945
  input: ["text"],
13617
13946
  cost: {
13618
- input: 0.255,
13619
- output: 1.02,
13947
+ input: 0.3,
13948
+ output: 1.2,
13620
13949
  cacheRead: 0,
13621
13950
  cacheWrite: 0,
13622
13951
  },
13623
13952
  contextWindow: 204800,
13624
- maxTokens: 131072,
13953
+ maxTokens: 176947,
13625
13954
  },
13626
13955
  "minimax/minimax-m2.1": {
13627
13956
  id: "minimax/minimax-m2.1",
@@ -13844,6 +14173,23 @@ export const MODELS = {
13844
14173
  contextWindow: 131072,
13845
14174
  maxTokens: 104857,
13846
14175
  },
14176
+ "mistralai/mistral-large-2512": {
14177
+ id: "mistralai/mistral-large-2512",
14178
+ name: "Mistral: Mistral Large 3 2512",
14179
+ api: "openai-completions",
14180
+ provider: "openrouter",
14181
+ baseUrl: "https://openrouter.ai/api/v1",
14182
+ reasoning: false,
14183
+ input: ["text", "image"],
14184
+ cost: {
14185
+ input: 0.5,
14186
+ output: 1.5,
14187
+ cacheRead: 0.049999999999999996,
14188
+ cacheWrite: 0,
14189
+ },
14190
+ contextWindow: 262144,
14191
+ maxTokens: 209715,
14192
+ },
13847
14193
  "mistralai/mistral-large-2512:batch": {
13848
14194
  id: "mistralai/mistral-large-2512:batch",
13849
14195
  name: "Mistral: Mistral Large 3 2512 (batch)",
@@ -14159,9 +14505,9 @@ export const MODELS = {
14159
14505
  reasoning: true,
14160
14506
  input: ["text", "image"],
14161
14507
  cost: {
14162
- input: 0.95,
14163
- output: 4,
14164
- cacheRead: 0.16,
14508
+ input: 0.65,
14509
+ output: 3.41,
14510
+ cacheRead: 0.15,
14165
14511
  cacheWrite: 0,
14166
14512
  },
14167
14513
  contextWindow: 262144,
@@ -14176,7 +14522,7 @@ export const MODELS = {
14176
14522
  reasoning: true,
14177
14523
  input: ["text", "image"],
14178
14524
  cost: {
14179
- input: 0.7062,
14525
+ input: 0.6562,
14180
14526
  output: 3.3000000000000003,
14181
14527
  cacheRead: 0.18,
14182
14528
  cacheWrite: 0,
@@ -14218,23 +14564,6 @@ export const MODELS = {
14218
14564
  contextWindow: 1048576,
14219
14565
  maxTokens: 16384,
14220
14566
  },
14221
- "nex-agi/nex-n2.5-mini:free": {
14222
- id: "nex-agi/nex-n2.5-mini:free",
14223
- name: "Nex AGI: Nex-N2.5-Mini (free)",
14224
- api: "openai-completions",
14225
- provider: "openrouter",
14226
- baseUrl: "https://openrouter.ai/api/v1",
14227
- reasoning: true,
14228
- input: ["text", "image"],
14229
- cost: {
14230
- input: 0,
14231
- output: 0,
14232
- cacheRead: 0,
14233
- cacheWrite: 0,
14234
- },
14235
- contextWindow: 262144,
14236
- maxTokens: 235929,
14237
- },
14238
14567
  "nex-agi/nex-n2.5-pro": {
14239
14568
  id: "nex-agi/nex-n2.5-pro",
14240
14569
  name: "Nex AGI: Nex-N2.5-Pro",
@@ -14252,23 +14581,6 @@ export const MODELS = {
14252
14581
  contextWindow: 262144,
14253
14582
  maxTokens: 235929,
14254
14583
  },
14255
- "nex-agi/nex-n2.5-pro:free": {
14256
- id: "nex-agi/nex-n2.5-pro:free",
14257
- name: "Nex AGI: Nex-N2.5-Pro (free)",
14258
- api: "openai-completions",
14259
- provider: "openrouter",
14260
- baseUrl: "https://openrouter.ai/api/v1",
14261
- reasoning: true,
14262
- input: ["text", "image"],
14263
- cost: {
14264
- input: 0,
14265
- output: 0,
14266
- cacheRead: 0,
14267
- cacheWrite: 0,
14268
- },
14269
- contextWindow: 262144,
14270
- maxTokens: 235929,
14271
- },
14272
14584
  "nvidia/nemotron-3-nano-30b-a3b": {
14273
14585
  id: "nvidia/nemotron-3-nano-30b-a3b",
14274
14586
  name: "NVIDIA: Nemotron 3 Nano 30B A3B",
@@ -14380,13 +14692,13 @@ export const MODELS = {
14380
14692
  reasoning: true,
14381
14693
  input: ["text"],
14382
14694
  cost: {
14383
- input: 0.07,
14695
+ input: 0.08,
14384
14696
  output: 0.19999999999999998,
14385
14697
  cacheRead: 0.04,
14386
14698
  cacheWrite: 0,
14387
14699
  },
14388
- contextWindow: 262144,
14389
- maxTokens: 235929,
14700
+ contextWindow: 1000000,
14701
+ maxTokens: 32768,
14390
14702
  },
14391
14703
  "nvidia/nemotron-3.5-lightning:free": {
14392
14704
  id: "nvidia/nemotron-3.5-lightning:free",
@@ -15317,10 +15629,10 @@ export const MODELS = {
15317
15629
  reasoning: true,
15318
15630
  input: ["text", "image"],
15319
15631
  cost: {
15320
- input: 2,
15321
- output: 10,
15322
- cacheRead: 0.19999999999999998,
15323
- cacheWrite: 2.5,
15632
+ input: 4,
15633
+ output: 20,
15634
+ cacheRead: 0.39999999999999997,
15635
+ cacheWrite: 5,
15324
15636
  },
15325
15637
  contextWindow: 1050000,
15326
15638
  maxTokens: 128000,
@@ -15512,6 +15824,74 @@ export const MODELS = {
15512
15824
  contextWindow: 1050000,
15513
15825
  maxTokens: 128000,
15514
15826
  },
15827
+ "openai/gpt-6-luna": {
15828
+ id: "openai/gpt-6-luna",
15829
+ name: "OpenAI: GPT-6 Luna",
15830
+ api: "openai-completions",
15831
+ provider: "openrouter",
15832
+ baseUrl: "https://openrouter.ai/api/v1",
15833
+ reasoning: true,
15834
+ input: ["text", "image"],
15835
+ cost: {
15836
+ input: 0.09999999999999999,
15837
+ output: 0.5,
15838
+ cacheRead: 0.01,
15839
+ cacheWrite: 0.125,
15840
+ },
15841
+ contextWindow: 1050000,
15842
+ maxTokens: 128000,
15843
+ },
15844
+ "openai/gpt-6-luna-pro": {
15845
+ id: "openai/gpt-6-luna-pro",
15846
+ name: "OpenAI: GPT-6 Luna Pro",
15847
+ api: "openai-completions",
15848
+ provider: "openrouter",
15849
+ baseUrl: "https://openrouter.ai/api/v1",
15850
+ reasoning: true,
15851
+ input: ["text", "image"],
15852
+ cost: {
15853
+ input: 0.09999999999999999,
15854
+ output: 0.5,
15855
+ cacheRead: 0.01,
15856
+ cacheWrite: 0.125,
15857
+ },
15858
+ contextWindow: 1050000,
15859
+ maxTokens: 128000,
15860
+ },
15861
+ "openai/gpt-6-luna-pro:batch": {
15862
+ id: "openai/gpt-6-luna-pro:batch",
15863
+ name: "OpenAI: GPT-6 Luna Pro (batch)",
15864
+ api: "openai-completions",
15865
+ provider: "openrouter",
15866
+ baseUrl: "https://openrouter.ai/api/v1",
15867
+ reasoning: true,
15868
+ input: ["text", "image"],
15869
+ cost: {
15870
+ input: 0.049999999999999996,
15871
+ output: 0.25,
15872
+ cacheRead: 0.005,
15873
+ cacheWrite: 0.0625,
15874
+ },
15875
+ contextWindow: 1050000,
15876
+ maxTokens: 128000,
15877
+ },
15878
+ "openai/gpt-6-luna:batch": {
15879
+ id: "openai/gpt-6-luna:batch",
15880
+ name: "OpenAI: GPT-6 Luna (batch)",
15881
+ api: "openai-completions",
15882
+ provider: "openrouter",
15883
+ baseUrl: "https://openrouter.ai/api/v1",
15884
+ reasoning: true,
15885
+ input: ["text", "image"],
15886
+ cost: {
15887
+ input: 0.049999999999999996,
15888
+ output: 0.25,
15889
+ cacheRead: 0.005,
15890
+ cacheWrite: 0.0625,
15891
+ },
15892
+ contextWindow: 1050000,
15893
+ maxTokens: 128000,
15894
+ },
15515
15895
  "openai/gpt-6-sol": {
15516
15896
  id: "openai/gpt-6-sol",
15517
15897
  name: "OpenAI: GPT-6 Sol",
@@ -15546,6 +15926,23 @@ export const MODELS = {
15546
15926
  contextWindow: 1050000,
15547
15927
  maxTokens: 128000,
15548
15928
  },
15929
+ "openai/gpt-6-sol-pro:batch": {
15930
+ id: "openai/gpt-6-sol-pro:batch",
15931
+ name: "OpenAI: GPT-6 Sol Pro (batch)",
15932
+ api: "openai-completions",
15933
+ provider: "openrouter",
15934
+ baseUrl: "https://openrouter.ai/api/v1",
15935
+ reasoning: true,
15936
+ input: ["text", "image"],
15937
+ cost: {
15938
+ input: 1,
15939
+ output: 5,
15940
+ cacheRead: 0.09999999999999999,
15941
+ cacheWrite: 1.25,
15942
+ },
15943
+ contextWindow: 1050000,
15944
+ maxTokens: 128000,
15945
+ },
15549
15946
  "openai/gpt-6-sol:batch": {
15550
15947
  id: "openai/gpt-6-sol:batch",
15551
15948
  name: "OpenAI: GPT-6 Sol (batch)",
@@ -15631,6 +16028,23 @@ export const MODELS = {
15631
16028
  contextWindow: 131072,
15632
16029
  maxTokens: 65536,
15633
16030
  },
16031
+ "openai/gpt-oss-120b:batch": {
16032
+ id: "openai/gpt-oss-120b:batch",
16033
+ name: "OpenAI: gpt-oss-120b (batch)",
16034
+ api: "openai-completions",
16035
+ provider: "openrouter",
16036
+ baseUrl: "https://openrouter.ai/api/v1",
16037
+ reasoning: true,
16038
+ input: ["text"],
16039
+ cost: {
16040
+ input: 0.0296,
16041
+ output: 0.136,
16042
+ cacheRead: 0,
16043
+ cacheWrite: 0,
16044
+ },
16045
+ contextWindow: 131072,
16046
+ maxTokens: 117964,
16047
+ },
15634
16048
  "openai/gpt-oss-20b": {
15635
16049
  id: "openai/gpt-oss-20b",
15636
16050
  name: "OpenAI: gpt-oss-20b",
@@ -15903,6 +16317,23 @@ export const MODELS = {
15903
16317
  contextWindow: 200000,
15904
16318
  maxTokens: 4096,
15905
16319
  },
16320
+ "perceptron/perceptron-mk1.5": {
16321
+ id: "perceptron/perceptron-mk1.5",
16322
+ name: "Perceptron: Perceptron Mk1.5",
16323
+ api: "openai-completions",
16324
+ provider: "openrouter",
16325
+ baseUrl: "https://openrouter.ai/api/v1",
16326
+ reasoning: true,
16327
+ input: ["text", "image"],
16328
+ cost: {
16329
+ input: 0.15,
16330
+ output: 1.5,
16331
+ cacheRead: 0,
16332
+ cacheWrite: 0,
16333
+ },
16334
+ contextWindow: 36864,
16335
+ maxTokens: 8192,
16336
+ },
15906
16337
  "poolside/laguna-s-2.1": {
15907
16338
  id: "poolside/laguna-s-2.1",
15908
16339
  name: "Poolside: Laguna S 2.1",
@@ -16150,13 +16581,13 @@ export const MODELS = {
16150
16581
  reasoning: false,
16151
16582
  input: ["text"],
16152
16583
  cost: {
16153
- input: 0.04815,
16154
- output: 0.19305,
16584
+ input: 0.09999999999999999,
16585
+ output: 0.3,
16155
16586
  cacheRead: 0,
16156
16587
  cacheWrite: 0,
16157
16588
  },
16158
16589
  contextWindow: 262144,
16159
- maxTokens: 32000,
16590
+ maxTokens: 235929,
16160
16591
  },
16161
16592
  "qwen/qwen3-30b-a3b-thinking-2507": {
16162
16593
  id: "qwen/qwen3-30b-a3b-thinking-2507",
@@ -16337,13 +16768,13 @@ export const MODELS = {
16337
16768
  reasoning: false,
16338
16769
  input: ["text"],
16339
16770
  cost: {
16340
- input: 0.09,
16771
+ input: 0.09999999999999999,
16341
16772
  output: 1.1,
16342
- cacheRead: 0,
16773
+ cacheRead: 0.07,
16343
16774
  cacheWrite: 0,
16344
16775
  },
16345
16776
  contextWindow: 262144,
16346
- maxTokens: 16384,
16777
+ maxTokens: 235929,
16347
16778
  },
16348
16779
  "qwen/qwen3-next-80b-a3b-thinking": {
16349
16780
  id: "qwen/qwen3-next-80b-a3b-thinking",
@@ -16405,13 +16836,13 @@ export const MODELS = {
16405
16836
  reasoning: false,
16406
16837
  input: ["text", "image"],
16407
16838
  cost: {
16408
- input: 0.13,
16409
- output: 0.52,
16839
+ input: 0.15,
16840
+ output: 0.6,
16410
16841
  cacheRead: 0,
16411
16842
  cacheWrite: 0,
16412
16843
  },
16413
16844
  contextWindow: 262144,
16414
- maxTokens: 32768,
16845
+ maxTokens: 16384,
16415
16846
  },
16416
16847
  "qwen/qwen3-vl-30b-a3b-thinking": {
16417
16848
  id: "qwen/qwen3-vl-30b-a3b-thinking",
@@ -16496,7 +16927,7 @@ export const MODELS = {
16496
16927
  cacheWrite: 0,
16497
16928
  },
16498
16929
  contextWindow: 262144,
16499
- maxTokens: 65536,
16930
+ maxTokens: 235929,
16500
16931
  },
16501
16932
  "qwen/qwen3.5-27b": {
16502
16933
  id: "qwen/qwen3.5-27b",
@@ -16524,13 +16955,13 @@ export const MODELS = {
16524
16955
  reasoning: true,
16525
16956
  input: ["text", "image"],
16526
16957
  cost: {
16527
- input: 0.3125,
16528
- output: 1.25,
16529
- cacheRead: 0.15625,
16958
+ input: 0.1625,
16959
+ output: 1.3,
16960
+ cacheRead: 0,
16530
16961
  cacheWrite: 0,
16531
16962
  },
16532
16963
  contextWindow: 262144,
16533
- maxTokens: 16384,
16964
+ maxTokens: 65536,
16534
16965
  },
16535
16966
  "qwen/qwen3.5-397b-a17b": {
16536
16967
  id: "qwen/qwen3.5-397b-a17b",
@@ -16627,12 +17058,12 @@ export const MODELS = {
16627
17058
  input: ["text", "image"],
16628
17059
  cost: {
16629
17060
  input: 0.32,
16630
- output: 2.7,
16631
- cacheRead: 0.15,
17061
+ output: 3.1999999999999997,
17062
+ cacheRead: 0,
16632
17063
  cacheWrite: 0,
16633
17064
  },
16634
17065
  contextWindow: 262144,
16635
- maxTokens: 262140,
17066
+ maxTokens: 81920,
16636
17067
  },
16637
17068
  "qwen/qwen3.6-35b-a3b": {
16638
17069
  id: "qwen/qwen3.6-35b-a3b",
@@ -16838,6 +17269,40 @@ export const MODELS = {
16838
17269
  contextWindow: 1000000,
16839
17270
  maxTokens: 131072,
16840
17271
  },
17272
+ "qwen/qwen3.8-max-prime": {
17273
+ id: "qwen/qwen3.8-max-prime",
17274
+ name: "Qwen: Qwen3.8 Max Prime",
17275
+ api: "openai-completions",
17276
+ provider: "openrouter",
17277
+ baseUrl: "https://openrouter.ai/api/v1",
17278
+ reasoning: true,
17279
+ input: ["text", "image"],
17280
+ cost: {
17281
+ input: 4,
17282
+ output: 12,
17283
+ cacheRead: 0.5,
17284
+ cacheWrite: 0,
17285
+ },
17286
+ contextWindow: 1000000,
17287
+ maxTokens: 131072,
17288
+ },
17289
+ "qwen/qwen3.8-omni-flash": {
17290
+ id: "qwen/qwen3.8-omni-flash",
17291
+ name: "Qwen: Qwen3.8 Omni Flash",
17292
+ api: "openai-completions",
17293
+ provider: "openrouter",
17294
+ baseUrl: "https://openrouter.ai/api/v1",
17295
+ reasoning: true,
17296
+ input: ["text", "image"],
17297
+ cost: {
17298
+ input: 0.15,
17299
+ output: 0.47,
17300
+ cacheRead: 0.016,
17301
+ cacheWrite: 0,
17302
+ },
17303
+ contextWindow: 1000000,
17304
+ maxTokens: 131072,
17305
+ },
16841
17306
  "rekaai/reka-edge": {
16842
17307
  id: "rekaai/reka-edge",
16843
17308
  name: "Reka Edge",
@@ -16957,6 +17422,23 @@ export const MODELS = {
16957
17422
  contextWindow: 131072,
16958
17423
  maxTokens: 16384,
16959
17424
  },
17425
+ "stealth/space-bunny-alpha": {
17426
+ id: "stealth/space-bunny-alpha",
17427
+ name: "Space Bunny Alpha",
17428
+ api: "openai-completions",
17429
+ provider: "openrouter",
17430
+ baseUrl: "https://openrouter.ai/api/v1",
17431
+ reasoning: true,
17432
+ input: ["text", "image"],
17433
+ cost: {
17434
+ input: 0,
17435
+ output: 0,
17436
+ cacheRead: 0,
17437
+ cacheWrite: 0,
17438
+ },
17439
+ contextWindow: 1000000,
17440
+ maxTokens: 524288,
17441
+ },
16960
17442
  "stepfun/step-3.5-flash": {
16961
17443
  id: "stepfun/step-3.5-flash",
16962
17444
  name: "StepFun: Step 3.5 Flash",
@@ -17039,7 +17521,7 @@ export const MODELS = {
17039
17521
  cacheRead: 0.16999999999999998,
17040
17522
  cacheWrite: 0,
17041
17523
  },
17042
- contextWindow: 1048576,
17524
+ contextWindow: 524288,
17043
17525
  maxTokens: 471859,
17044
17526
  },
17045
17527
  "thinkingmachines/inkling-small": {
@@ -17056,7 +17538,7 @@ export const MODELS = {
17056
17538
  cacheRead: 0.09999999999999999,
17057
17539
  cacheWrite: 0,
17058
17540
  },
17059
- contextWindow: 1048576,
17541
+ contextWindow: 524288,
17060
17542
  maxTokens: 262144,
17061
17543
  },
17062
17544
  "thinkingmachines/inkling-small:free": {
@@ -17110,6 +17592,23 @@ export const MODELS = {
17110
17592
  contextWindow: 262144,
17111
17593
  maxTokens: 131072,
17112
17594
  },
17595
+ "upstage/solar-mini4": {
17596
+ id: "upstage/solar-mini4",
17597
+ name: "Upstage: Solar Mini 4",
17598
+ api: "openai-completions",
17599
+ provider: "openrouter",
17600
+ baseUrl: "https://openrouter.ai/api/v1",
17601
+ reasoning: true,
17602
+ input: ["text"],
17603
+ cost: {
17604
+ input: 0.049999999999999996,
17605
+ output: 0.19999999999999998,
17606
+ cacheRead: 0.005,
17607
+ cacheWrite: 0,
17608
+ },
17609
+ contextWindow: 524288,
17610
+ maxTokens: 131072,
17611
+ },
17113
17612
  "upstage/solar-pro-3": {
17114
17613
  id: "upstage/solar-pro-3",
17115
17614
  name: "Upstage: Solar Pro 3",
@@ -17328,7 +17827,7 @@ export const MODELS = {
17328
17827
  cacheRead: 0.0036,
17329
17828
  cacheWrite: 0,
17330
17829
  },
17331
- contextWindow: 1048576,
17830
+ contextWindow: 1050000,
17332
17831
  maxTokens: 131072,
17333
17832
  },
17334
17833
  "xiaomi/mimo-v2.6-pro-ultraspeed": {
@@ -17442,9 +17941,9 @@ export const MODELS = {
17442
17941
  reasoning: true,
17443
17942
  input: ["text"],
17444
17943
  cost: {
17445
- input: 0.39999999999999997,
17446
- output: 1.75,
17447
- cacheRead: 0.08,
17944
+ input: 0.6,
17945
+ output: 2.2,
17946
+ cacheRead: 0.11,
17448
17947
  cacheWrite: 0,
17449
17948
  },
17450
17949
  contextWindow: 204800,
@@ -17510,13 +18009,13 @@ export const MODELS = {
17510
18009
  reasoning: true,
17511
18010
  input: ["text"],
17512
18011
  cost: {
17513
- input: 0.966,
17514
- output: 3.036,
17515
- cacheRead: 0.1794,
18012
+ input: 0.9646,
18013
+ output: 3.0316,
18014
+ cacheRead: 0.17914,
17516
18015
  cacheWrite: 0,
17517
18016
  },
17518
18017
  contextWindow: 204800,
17519
- maxTokens: 128000,
18018
+ maxTokens: 131072,
17520
18019
  },
17521
18020
  "z-ai/glm-5.2": {
17522
18021
  id: "z-ai/glm-5.2",
@@ -17544,13 +18043,13 @@ export const MODELS = {
17544
18043
  reasoning: true,
17545
18044
  input: ["text"],
17546
18045
  cost: {
17547
- input: 0.6537999999999999,
17548
- output: 2.0547999999999997,
17549
- cacheRead: 0.12142000000000001,
18046
+ input: 0.1785,
18047
+ output: 2.8049999999999997,
18048
+ cacheRead: 0.146625,
17550
18049
  cacheWrite: 0,
17551
18050
  },
17552
18051
  contextWindow: 1310720,
17553
- maxTokens: 131072,
18052
+ maxTokens: 943718,
17554
18053
  },
17555
18054
  "z-ai/glm-5.3-flash": {
17556
18055
  id: "z-ai/glm-5.3-flash",
@@ -17563,11 +18062,11 @@ export const MODELS = {
17563
18062
  cost: {
17564
18063
  input: 0.15,
17565
18064
  output: 0.5,
17566
- cacheRead: 0.049999999999999996,
18065
+ cacheRead: 0.03,
17567
18066
  cacheWrite: 0,
17568
18067
  },
17569
18068
  contextWindow: 1310720,
17570
- maxTokens: 943718,
18069
+ maxTokens: 943717,
17571
18070
  },
17572
18071
  "z-ai/glm-5.3-flash:batch": {
17573
18072
  id: "z-ai/glm-5.3-flash:batch",
@@ -17597,12 +18096,29 @@ export const MODELS = {
17597
18096
  cost: {
17598
18097
  input: 0.37,
17599
18098
  output: 1.25,
17600
- cacheRead: 0.075,
18099
+ cacheRead: 0.09,
17601
18100
  cacheWrite: 0,
17602
18101
  },
17603
18102
  contextWindow: 1048576,
17604
18103
  maxTokens: 131072,
17605
18104
  },
18105
+ "z-ai/glm-5.3-prime": {
18106
+ id: "z-ai/glm-5.3-prime",
18107
+ name: "Z.ai: GLM 5.3 Prime",
18108
+ api: "openai-completions",
18109
+ provider: "openrouter",
18110
+ baseUrl: "https://openrouter.ai/api/v1",
18111
+ reasoning: true,
18112
+ input: ["text"],
18113
+ cost: {
18114
+ input: 2.8,
18115
+ output: 8.8,
18116
+ cacheRead: 0.56,
18117
+ cacheWrite: 0,
18118
+ },
18119
+ contextWindow: 1000000,
18120
+ maxTokens: 131072,
18121
+ },
17606
18122
  "z-ai/glm-5.3:batch": {
17607
18123
  id: "z-ai/glm-5.3:batch",
17608
18124
  name: "Z.ai: GLM 5.3 (batch)",
@@ -17612,9 +18128,9 @@ export const MODELS = {
17612
18128
  reasoning: true,
17613
18129
  input: ["text"],
17614
18130
  cost: {
17615
- input: 0.72,
17616
- output: 2.4,
17617
- cacheRead: 0.12,
18131
+ input: 0.44999999999999996,
18132
+ output: 2,
18133
+ cacheRead: 0.09999999999999999,
17618
18134
  cacheWrite: 0,
17619
18135
  },
17620
18136
  contextWindow: 1048576,
@@ -17715,9 +18231,9 @@ export const MODELS = {
17715
18231
  reasoning: true,
17716
18232
  input: ["text", "image"],
17717
18233
  cost: {
17718
- input: 0.12,
17719
- output: 0.48,
17720
- cacheRead: 0.0036,
18234
+ input: 0.03,
18235
+ output: 0.6,
18236
+ cacheRead: 0.01,
17721
18237
  cacheWrite: 0,
17722
18238
  },
17723
18239
  contextWindow: 1048576,
@@ -17732,13 +18248,13 @@ export const MODELS = {
17732
18248
  reasoning: true,
17733
18249
  input: ["text"],
17734
18250
  cost: {
17735
- input: 0.54648,
17736
- output: 1.63944,
17737
- cacheRead: 0.017388,
18251
+ input: 0.22592,
18252
+ output: 1.9584000000000001,
18253
+ cacheRead: 0.08832,
17738
18254
  cacheWrite: 0,
17739
18255
  },
17740
18256
  contextWindow: 1048576,
17741
- maxTokens: 393216,
18257
+ maxTokens: 943718,
17742
18258
  },
17743
18259
  "~deepseek/deepseek-v4-flash-latest": {
17744
18260
  id: "~deepseek/deepseek-v4-flash-latest",
@@ -17751,9 +18267,9 @@ export const MODELS = {
17751
18267
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
17752
18268
  input: ["text"],
17753
18269
  cost: {
17754
- input: 0.03,
17755
- output: 1,
17756
- cacheRead: 0.008,
18270
+ input: 0.020999999999999998,
18271
+ output: 0.32,
18272
+ cacheRead: 0.016,
17757
18273
  cacheWrite: 0,
17758
18274
  },
17759
18275
  contextWindow: 1310720,
@@ -17802,9 +18318,9 @@ export const MODELS = {
17802
18318
  reasoning: true,
17803
18319
  input: ["text", "image"],
17804
18320
  cost: {
17805
- input: 1.5,
17806
- output: 7.5,
17807
- cacheRead: 0.15,
18321
+ input: 0.875,
18322
+ output: 11.2,
18323
+ cacheRead: 0.29,
17808
18324
  cacheWrite: 0,
17809
18325
  },
17810
18326
  contextWindow: 1048576,
@@ -17836,10 +18352,10 @@ export const MODELS = {
17836
18352
  reasoning: true,
17837
18353
  input: ["text", "image"],
17838
18354
  cost: {
17839
- input: 0.19999999999999998,
17840
- output: 1.2,
17841
- cacheRead: 0.02,
17842
- cacheWrite: 0.25,
18355
+ input: 0.09999999999999999,
18356
+ output: 0.5,
18357
+ cacheRead: 0.01,
18358
+ cacheWrite: 0.125,
17843
18359
  },
17844
18360
  contextWindow: 1050000,
17845
18361
  maxTokens: 128000,
@@ -17921,13 +18437,13 @@ export const MODELS = {
17921
18437
  reasoning: true,
17922
18438
  input: ["text", "image"],
17923
18439
  cost: {
17924
- input: 0.075,
17925
- output: 0.25,
17926
- cacheRead: 0.015,
18440
+ input: 0.045,
18441
+ output: 0.14,
18442
+ cacheRead: 0.01,
17927
18443
  cacheWrite: 0,
17928
18444
  },
17929
18445
  contextWindow: 1310720,
17930
- maxTokens: 943718,
18446
+ maxTokens: 128000,
17931
18447
  },
17932
18448
  "~z-ai/glm-latest": {
17933
18449
  id: "~z-ai/glm-latest",
@@ -17938,13 +18454,13 @@ export const MODELS = {
17938
18454
  reasoning: true,
17939
18455
  input: ["text"],
17940
18456
  cost: {
17941
- input: 0.6537999999999999,
17942
- output: 2.0547999999999997,
17943
- cacheRead: 0.12142000000000001,
18457
+ input: 0.1785,
18458
+ output: 2.8049999999999997,
18459
+ cacheRead: 0.146625,
17944
18460
  cacheWrite: 0,
17945
18461
  },
17946
18462
  contextWindow: 1310720,
17947
- maxTokens: 131072,
18463
+ maxTokens: 943718,
17948
18464
  },
17949
18465
  },
17950
18466
  "together": {
@@ -17964,7 +18480,7 @@ export const MODELS = {
17964
18480
  cacheRead: 0.06,
17965
18481
  cacheWrite: 0,
17966
18482
  },
17967
- contextWindow: 202752,
18483
+ contextWindow: 196608,
17968
18484
  maxTokens: 131072,
17969
18485
  },
17970
18486
  "MiniMaxAI/MiniMax-M3": {
@@ -18076,7 +18592,7 @@ export const MODELS = {
18076
18592
  cacheRead: 0.03,
18077
18593
  cacheWrite: 0,
18078
18594
  },
18079
- contextWindow: 1000000,
18595
+ contextWindow: 1048576,
18080
18596
  maxTokens: 384000,
18081
18597
  },
18082
18598
  "deepseek-ai/DeepSeek-V4-Pro": {
@@ -18322,7 +18838,7 @@ export const MODELS = {
18322
18838
  cacheRead: 0.26,
18323
18839
  cacheWrite: 0,
18324
18840
  },
18325
- contextWindow: 512000,
18841
+ contextWindow: 1048575,
18326
18842
  maxTokens: 164000,
18327
18843
  },
18328
18844
  "zai-org/GLM-5.3": {
@@ -18698,7 +19214,7 @@ export const MODELS = {
18698
19214
  input: ["text", "image"],
18699
19215
  cost: {
18700
19216
  input: 0.39999999999999997,
18701
- output: 2.5,
19217
+ output: 2.4,
18702
19218
  cacheRead: 0.04,
18703
19219
  cacheWrite: 0.5,
18704
19220
  },
@@ -18875,6 +19391,23 @@ export const MODELS = {
18875
19391
  contextWindow: 991000,
18876
19392
  maxTokens: 128000,
18877
19393
  },
19394
+ "alibaba/qwen3.8-max-prime": {
19395
+ id: "alibaba/qwen3.8-max-prime",
19396
+ name: "Qwen 3.8 Max Prime",
19397
+ api: "anthropic-messages",
19398
+ provider: "vercel-ai-gateway",
19399
+ baseUrl: "https://ai-gateway.vercel.sh",
19400
+ reasoning: true,
19401
+ input: ["text", "image"],
19402
+ cost: {
19403
+ input: 4,
19404
+ output: 12,
19405
+ cacheRead: 0.5,
19406
+ cacheWrite: 5,
19407
+ },
19408
+ contextWindow: 1000000,
19409
+ maxTokens: 131072,
19410
+ },
18878
19411
  "alibaba/qwen3.8-omni-flash": {
18879
19412
  id: "alibaba/qwen3.8-omni-flash",
18880
19413
  name: "Qwen 3.8 Omni Flash",
@@ -19045,7 +19578,7 @@ export const MODELS = {
19045
19578
  cacheWrite: 18.75,
19046
19579
  },
19047
19580
  contextWindow: 200000,
19048
- maxTokens: 8192,
19581
+ maxTokens: 32000,
19049
19582
  },
19050
19583
  "anthropic/claude-opus-4.5": {
19051
19584
  id: "anthropic/claude-opus-4.5",
@@ -19219,7 +19752,7 @@ export const MODELS = {
19219
19752
  cacheWrite: 3.75,
19220
19753
  },
19221
19754
  contextWindow: 1000000,
19222
- maxTokens: 8192,
19755
+ maxTokens: 64000,
19223
19756
  },
19224
19757
  "anthropic/claude-sonnet-4.5": {
19225
19758
  id: "anthropic/claude-sonnet-4.5",
@@ -19272,6 +19805,23 @@ export const MODELS = {
19272
19805
  contextWindow: 1000000,
19273
19806
  maxTokens: 128000,
19274
19807
  },
19808
+ "anthropic/claude-sonnet-5.5": {
19809
+ id: "anthropic/claude-sonnet-5.5",
19810
+ name: "Claude Sonnet 5.5",
19811
+ api: "anthropic-messages",
19812
+ provider: "vercel-ai-gateway",
19813
+ baseUrl: "https://ai-gateway.vercel.sh",
19814
+ reasoning: true,
19815
+ input: ["text", "image"],
19816
+ cost: {
19817
+ input: 2,
19818
+ output: 10,
19819
+ cacheRead: 0.19999999999999998,
19820
+ cacheWrite: 2.5,
19821
+ },
19822
+ contextWindow: 1000000,
19823
+ maxTokens: 128000,
19824
+ },
19275
19825
  "arcee-ai/trinity-large-thinking": {
19276
19826
  id: "arcee-ai/trinity-large-thinking",
19277
19827
  name: "Trinity Large Thinking",
@@ -19485,9 +20035,9 @@ export const MODELS = {
19485
20035
  reasoning: true,
19486
20036
  input: ["text", "image"],
19487
20037
  cost: {
19488
- input: 0.22,
19489
- output: 0.66,
19490
- cacheRead: 0.007,
20038
+ input: 0.21559999999999999,
20039
+ output: 0.6468,
20040
+ cacheRead: 0.0068,
19491
20041
  cacheWrite: 0,
19492
20042
  },
19493
20043
  contextWindow: 1048576,
@@ -19544,6 +20094,23 @@ export const MODELS = {
19544
20094
  contextWindow: 1048576,
19545
20095
  maxTokens: 32768,
19546
20096
  },
20097
+ "fireworks/ember-1": {
20098
+ id: "fireworks/ember-1",
20099
+ name: "Ember-1",
20100
+ api: "anthropic-messages",
20101
+ provider: "vercel-ai-gateway",
20102
+ baseUrl: "https://ai-gateway.vercel.sh",
20103
+ reasoning: true,
20104
+ input: ["text", "image"],
20105
+ cost: {
20106
+ input: 3,
20107
+ output: 15,
20108
+ cacheRead: 0.3,
20109
+ cacheWrite: 0,
20110
+ },
20111
+ contextWindow: 1048576,
20112
+ maxTokens: 1048576,
20113
+ },
19547
20114
  "google/gemini-2.5-flash": {
19548
20115
  id: "google/gemini-2.5-flash",
19549
20116
  name: "Gemini 2.5 Flash",
@@ -19559,7 +20126,7 @@ export const MODELS = {
19559
20126
  cacheWrite: 0,
19560
20127
  },
19561
20128
  contextWindow: 1000000,
19562
- maxTokens: 65536,
20129
+ maxTokens: 65535,
19563
20130
  },
19564
20131
  "google/gemini-2.5-flash-lite": {
19565
20132
  id: "google/gemini-2.5-flash-lite",
@@ -19576,7 +20143,7 @@ export const MODELS = {
19576
20143
  cacheWrite: 0,
19577
20144
  },
19578
20145
  contextWindow: 1048576,
19579
- maxTokens: 65536,
20146
+ maxTokens: 65535,
19580
20147
  },
19581
20148
  "google/gemini-2.5-pro": {
19582
20149
  id: "google/gemini-2.5-pro",
@@ -19593,7 +20160,7 @@ export const MODELS = {
19593
20160
  cacheWrite: 0,
19594
20161
  },
19595
20162
  contextWindow: 1048576,
19596
- maxTokens: 65536,
20163
+ maxTokens: 65535,
19597
20164
  },
19598
20165
  "google/gemini-3-flash": {
19599
20166
  id: "google/gemini-3-flash",
@@ -19712,7 +20279,7 @@ export const MODELS = {
19712
20279
  cacheWrite: 0,
19713
20280
  },
19714
20281
  contextWindow: 1000000,
19715
- maxTokens: 65536,
20282
+ maxTokens: 65535,
19716
20283
  },
19717
20284
  "google/gemini-3.8-flash": {
19718
20285
  id: "google/gemini-3.8-flash",
@@ -19729,7 +20296,7 @@ export const MODELS = {
19729
20296
  cacheWrite: 0,
19730
20297
  },
19731
20298
  contextWindow: 1000000,
19732
- maxTokens: 65536,
20299
+ maxTokens: 65535,
19733
20300
  },
19734
20301
  "google/gemma-4-26b-a4b-it": {
19735
20302
  id: "google/gemma-4-26b-a4b-it",
@@ -19842,26 +20409,9 @@ export const MODELS = {
19842
20409
  reasoning: true,
19843
20410
  input: ["text"],
19844
20411
  cost: {
19845
- input: 0,
19846
- output: 0,
19847
- cacheRead: 0,
19848
- cacheWrite: 0,
19849
- },
19850
- contextWindow: 256000,
19851
- maxTokens: 32000,
19852
- },
19853
- "inclusionai/ling-3.0-flash-fin-free": {
19854
- id: "inclusionai/ling-3.0-flash-fin-free",
19855
- name: "Ling 3.0 Flash Fin (Free)",
19856
- api: "anthropic-messages",
19857
- provider: "vercel-ai-gateway",
19858
- baseUrl: "https://ai-gateway.vercel.sh",
19859
- reasoning: true,
19860
- input: ["text"],
19861
- cost: {
19862
- input: 0,
19863
- output: 0,
19864
- cacheRead: 0,
20412
+ input: 0.06,
20413
+ output: 0.18,
20414
+ cacheRead: 0.012,
19865
20415
  cacheWrite: 0,
19866
20416
  },
19867
20417
  contextWindow: 256000,
@@ -19910,47 +20460,47 @@ export const MODELS = {
19910
20460
  reasoning: true,
19911
20461
  input: ["text", "image"],
19912
20462
  cost: {
19913
- input: 0,
19914
- output: 0,
19915
- cacheRead: 0,
20463
+ input: 0.075,
20464
+ output: 0.22,
20465
+ cacheRead: 0.015,
19916
20466
  cacheWrite: 0,
19917
20467
  },
19918
20468
  contextWindow: 256000,
19919
20469
  maxTokens: 32000,
19920
20470
  },
19921
- "inclusionai/ling-3.0-flash-vl-free": {
19922
- id: "inclusionai/ling-3.0-flash-vl-free",
19923
- name: "Ling 3.0 Flash VL (Free)",
20471
+ "interfaze/interfaze-beta": {
20472
+ id: "interfaze/interfaze-beta",
20473
+ name: "Interfaze Beta",
19924
20474
  api: "anthropic-messages",
19925
20475
  provider: "vercel-ai-gateway",
19926
20476
  baseUrl: "https://ai-gateway.vercel.sh",
19927
20477
  reasoning: true,
19928
20478
  input: ["text", "image"],
19929
20479
  cost: {
19930
- input: 0,
19931
- output: 0,
20480
+ input: 1.5,
20481
+ output: 3.5,
19932
20482
  cacheRead: 0,
19933
20483
  cacheWrite: 0,
19934
20484
  },
19935
- contextWindow: 256000,
20485
+ contextWindow: 1000000,
19936
20486
  maxTokens: 32000,
19937
20487
  },
19938
- "interfaze/interfaze-beta": {
19939
- id: "interfaze/interfaze-beta",
19940
- name: "Interfaze Beta",
20488
+ "meituan/longcat-2.5-preview": {
20489
+ id: "meituan/longcat-2.5-preview",
20490
+ name: "LongCat 2.5 Preview",
19941
20491
  api: "anthropic-messages",
19942
20492
  provider: "vercel-ai-gateway",
19943
20493
  baseUrl: "https://ai-gateway.vercel.sh",
19944
20494
  reasoning: true,
19945
20495
  input: ["text", "image"],
19946
20496
  cost: {
19947
- input: 1.5,
19948
- output: 3.5,
19949
- cacheRead: 0,
20497
+ input: 0.3,
20498
+ output: 1.2,
20499
+ cacheRead: 0.006,
19950
20500
  cacheWrite: 0,
19951
20501
  },
19952
- contextWindow: 1000000,
19953
- maxTokens: 32000,
20502
+ contextWindow: 1048576,
20503
+ maxTokens: 131072,
19954
20504
  },
19955
20505
  "meta/llama-3.1-70b": {
19956
20506
  id: "meta/llama-3.1-70b",
@@ -20507,7 +21057,7 @@ export const MODELS = {
20507
21057
  cost: {
20508
21058
  input: 0.95,
20509
21059
  output: 4,
20510
- cacheRead: 0.16,
21060
+ cacheRead: 0.19,
20511
21061
  cacheWrite: 0,
20512
21062
  },
20513
21063
  contextWindow: 256000,
@@ -21463,6 +22013,74 @@ export const MODELS = {
21463
22013
  contextWindow: 1050000,
21464
22014
  maxTokens: 128000,
21465
22015
  },
22016
+ "openai/gpt-6-luna": {
22017
+ id: "openai/gpt-6-luna",
22018
+ name: "GPT-6 Luna",
22019
+ api: "anthropic-messages",
22020
+ provider: "vercel-ai-gateway",
22021
+ baseUrl: "https://ai-gateway.vercel.sh",
22022
+ reasoning: true,
22023
+ input: ["text", "image"],
22024
+ cost: {
22025
+ input: 0.09999999999999999,
22026
+ output: 0.5,
22027
+ cacheRead: 0.01,
22028
+ cacheWrite: 0.125,
22029
+ },
22030
+ contextWindow: 1050000,
22031
+ maxTokens: 128000,
22032
+ },
22033
+ "openai/gpt-6-luna-fast": {
22034
+ id: "openai/gpt-6-luna-fast",
22035
+ name: "GPT-6 Luna (Fast)",
22036
+ api: "anthropic-messages",
22037
+ provider: "vercel-ai-gateway",
22038
+ baseUrl: "https://ai-gateway.vercel.sh",
22039
+ reasoning: true,
22040
+ input: ["text", "image"],
22041
+ cost: {
22042
+ input: 0.19999999999999998,
22043
+ output: 1,
22044
+ cacheRead: 0.02,
22045
+ cacheWrite: 0.25,
22046
+ },
22047
+ contextWindow: 1050000,
22048
+ maxTokens: 128000,
22049
+ },
22050
+ "openai/gpt-6-sol": {
22051
+ id: "openai/gpt-6-sol",
22052
+ name: "GPT-6 Sol",
22053
+ api: "anthropic-messages",
22054
+ provider: "vercel-ai-gateway",
22055
+ baseUrl: "https://ai-gateway.vercel.sh",
22056
+ reasoning: true,
22057
+ input: ["text", "image"],
22058
+ cost: {
22059
+ input: 2,
22060
+ output: 10,
22061
+ cacheRead: 0.19999999999999998,
22062
+ cacheWrite: 2.5,
22063
+ },
22064
+ contextWindow: 1050000,
22065
+ maxTokens: 128000,
22066
+ },
22067
+ "openai/gpt-6-sol-fast": {
22068
+ id: "openai/gpt-6-sol-fast",
22069
+ name: "GPT-6 Sol (Fast)",
22070
+ api: "anthropic-messages",
22071
+ provider: "vercel-ai-gateway",
22072
+ baseUrl: "https://ai-gateway.vercel.sh",
22073
+ reasoning: true,
22074
+ input: ["text", "image"],
22075
+ cost: {
22076
+ input: 4,
22077
+ output: 20,
22078
+ cacheRead: 0.39999999999999997,
22079
+ cacheWrite: 5,
22080
+ },
22081
+ contextWindow: 1050000,
22082
+ maxTokens: 128000,
22083
+ },
21466
22084
  "openai/gpt-oss-120b": {
21467
22085
  id: "openai/gpt-oss-120b",
21468
22086
  name: "GPT OSS 120B",
@@ -21474,7 +22092,7 @@ export const MODELS = {
21474
22092
  cost: {
21475
22093
  input: 0.09999999999999999,
21476
22094
  output: 0.5,
21477
- cacheRead: 0,
22095
+ cacheRead: 0.09999999999999999,
21478
22096
  cacheWrite: 0,
21479
22097
  },
21480
22098
  contextWindow: 131072,
@@ -21982,9 +22600,9 @@ export const MODELS = {
21982
22600
  reasoning: true,
21983
22601
  input: ["text", "image"],
21984
22602
  cost: {
21985
- input: 1.2,
21986
- output: 3.5999999999999996,
21987
- cacheRead: 0.3,
22603
+ input: 2,
22604
+ output: 6,
22605
+ cacheRead: 0.5,
21988
22606
  cacheWrite: 0,
21989
22607
  },
21990
22608
  contextWindow: 500000,
@@ -22101,7 +22719,7 @@ export const MODELS = {
22101
22719
  reasoning: true,
22102
22720
  input: ["text", "image"],
22103
22721
  cost: {
22104
- input: 0.5,
22722
+ input: 0.44999999999999996,
22105
22723
  output: 1.2,
22106
22724
  cacheRead: 0.09999999999999999,
22107
22725
  cacheWrite: 0,
@@ -22273,7 +22891,7 @@ export const MODELS = {
22273
22891
  cost: {
22274
22892
  input: 0.6,
22275
22893
  output: 2.2,
22276
- cacheRead: 0.12,
22894
+ cacheRead: 0,
22277
22895
  cacheWrite: 0,
22278
22896
  },
22279
22897
  contextWindow: 200000,
@@ -22390,9 +23008,9 @@ export const MODELS = {
22390
23008
  reasoning: true,
22391
23009
  input: ["text"],
22392
23010
  cost: {
22393
- input: 2.0999999999999996,
22394
- output: 6.6000000000000005,
22395
- cacheRead: 0.21,
23011
+ input: 2.8,
23012
+ output: 8.8,
23013
+ cacheRead: 0.56,
22396
23014
  cacheWrite: 0,
22397
23015
  },
22398
23016
  contextWindow: 1000000,