@dreb/ai 2.68.0 → 2.69.0

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.
Files changed (8) hide show
  1. package/dist/models.generated.d.ts +788 -176
  2. package/dist/models.generated.d.ts.map +1 -1
  3. package/dist/models.generated.js +1002 -404
  4. package/dist/models.generated.js.map +1 -1
  5. package/dist/utils/overflow.d.ts.map +1 -1
  6. package/dist/utils/overflow.js +3 -1
  7. package/dist/utils/overflow.js.map +1 -1
  8. package/package.json +1 -1
package/dist/models.generated.js CHANGED
@@ -291,6 +291,23 @@ export const MODELS = {
291
291
  contextWindow: 1000000,
292
292
  maxTokens: 128000,
293
293
  },
294
+ "anthropic.claude-sonnet-5-5": {
295
+ id: "anthropic.claude-sonnet-5-5",
296
+ name: "Claude Sonnet 5.5",
297
+ api: "bedrock-converse-stream",
298
+ provider: "amazon-bedrock",
299
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
300
+ reasoning: true,
301
+ input: ["text", "image"],
302
+ cost: {
303
+ input: 2,
304
+ output: 10,
305
+ cacheRead: 0.2,
306
+ cacheWrite: 2.5,
307
+ },
308
+ contextWindow: 1000000,
309
+ maxTokens: 128000,
310
+ },
294
311
  "apac.amazon.nova-lite-v1:0": {
295
312
  id: "apac.amazon.nova-lite-v1:0",
296
313
  name: "Nova Lite (APAC)",
@@ -1090,6 +1107,23 @@ export const MODELS = {
1090
1107
  contextWindow: 1000000,
1091
1108
  maxTokens: 128000,
1092
1109
  },
1110
+ "global.anthropic.claude-sonnet-5-5": {
1111
+ id: "global.anthropic.claude-sonnet-5-5",
1112
+ name: "Claude Sonnet 5.5 (Global)",
1113
+ api: "bedrock-converse-stream",
1114
+ provider: "amazon-bedrock",
1115
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1116
+ reasoning: true,
1117
+ input: ["text", "image"],
1118
+ cost: {
1119
+ input: 2,
1120
+ output: 10,
1121
+ cacheRead: 0.2,
1122
+ cacheWrite: 2.5,
1123
+ },
1124
+ contextWindow: 1000000,
1125
+ maxTokens: 128000,
1126
+ },
1093
1127
  "global.moonshotai.kimi-k3": {
1094
1128
  id: "global.moonshotai.kimi-k3",
1095
1129
  name: "Kimi K3 (Global)",
@@ -1105,7 +1139,7 @@ export const MODELS = {
1105
1139
  cacheWrite: 3.75,
1106
1140
  },
1107
1141
  contextWindow: 1048576,
1108
- maxTokens: 131072,
1142
+ maxTokens: 128000,
1109
1143
  },
1110
1144
  "global.openai.gpt-5.6-luna": {
1111
1145
  id: "global.openai.gpt-5.6-luna",
@@ -1226,6 +1260,23 @@ export const MODELS = {
1226
1260
  contextWindow: 500000,
1227
1261
  maxTokens: 500000,
1228
1262
  },
1263
+ "global.xai.grok-4.7": {
1264
+ id: "global.xai.grok-4.7",
1265
+ name: "Grok 4.7 (Global)",
1266
+ api: "bedrock-converse-stream",
1267
+ provider: "amazon-bedrock",
1268
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1269
+ reasoning: true,
1270
+ input: ["text", "image"],
1271
+ cost: {
1272
+ input: 2,
1273
+ output: 6,
1274
+ cacheRead: 0.5,
1275
+ cacheWrite: 0,
1276
+ },
1277
+ contextWindow: 500000,
1278
+ maxTokens: 500000,
1279
+ },
1229
1280
  "google.gemma-4-26b-a4b": {
1230
1281
  id: "google.gemma-4-26b-a4b",
1231
1282
  name: "Gemma 4 26B A4B IT",
@@ -1580,7 +1631,7 @@ export const MODELS = {
1580
1631
  cacheRead: 0,
1581
1632
  cacheWrite: 0,
1582
1633
  },
1583
- contextWindow: 204800,
1634
+ contextWindow: 196608,
1584
1635
  maxTokens: 131072,
1585
1636
  },
1586
1637
  "minimax.minimax-m2.5": {
@@ -1614,7 +1665,7 @@ export const MODELS = {
1614
1665
  cacheRead: 0,
1615
1666
  cacheWrite: 0,
1616
1667
  },
1617
- contextWindow: 256000,
1668
+ contextWindow: 262144,
1618
1669
  maxTokens: 8192,
1619
1670
  },
1620
1671
  "mistral.magistral-small-2509": {
@@ -1699,7 +1750,7 @@ export const MODELS = {
1699
1750
  cacheRead: 0,
1700
1751
  cacheWrite: 0,
1701
1752
  },
1702
- contextWindow: 256000,
1753
+ contextWindow: 262144,
1703
1754
  maxTokens: 8192,
1704
1755
  },
1705
1756
  "mistral.pixtral-large-2502-v1:0": {
@@ -1767,7 +1818,7 @@ export const MODELS = {
1767
1818
  cacheRead: 0,
1768
1819
  cacheWrite: 0,
1769
1820
  },
1770
- contextWindow: 262143,
1821
+ contextWindow: 262144,
1771
1822
  maxTokens: 16000,
1772
1823
  },
1773
1824
  "moonshotai.kimi-k2.5": {
@@ -1784,7 +1835,7 @@ export const MODELS = {
1784
1835
  cacheRead: 0,
1785
1836
  cacheWrite: 0,
1786
1837
  },
1787
- contextWindow: 262143,
1838
+ contextWindow: 262144,
1788
1839
  maxTokens: 16384,
1789
1840
  },
1790
1841
  "nvidia.nemotron-nano-12b-v2": {
@@ -1801,7 +1852,7 @@ export const MODELS = {
1801
1852
  cacheRead: 0,
1802
1853
  cacheWrite: 0,
1803
1854
  },
1804
- contextWindow: 128000,
1855
+ contextWindow: 131072,
1805
1856
  maxTokens: 8192,
1806
1857
  },
1807
1858
  "nvidia.nemotron-nano-3-30b": {
@@ -1869,7 +1920,7 @@ export const MODELS = {
1869
1920
  cacheRead: 0.275,
1870
1921
  cacheWrite: 0,
1871
1922
  },
1872
- contextWindow: 272000,
1923
+ contextWindow: 1000000,
1873
1924
  maxTokens: 128000,
1874
1925
  },
1875
1926
  "openai.gpt-5.5": {
@@ -1886,7 +1937,7 @@ export const MODELS = {
1886
1937
  cacheRead: 0.55,
1887
1938
  cacheWrite: 0,
1888
1939
  },
1889
- contextWindow: 272000,
1940
+ contextWindow: 1000000,
1890
1941
  maxTokens: 128000,
1891
1942
  },
1892
1943
  "openai.gpt-5.6-luna": {
@@ -1957,6 +2008,40 @@ export const MODELS = {
1957
2008
  contextWindow: 1050000,
1958
2009
  maxTokens: 128000,
1959
2010
  },
2011
+ "openai.gpt-6-luna": {
2012
+ id: "openai.gpt-6-luna",
2013
+ name: "GPT-6 Luna",
2014
+ api: "bedrock-converse-stream",
2015
+ provider: "amazon-bedrock",
2016
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2017
+ reasoning: true,
2018
+ input: ["text", "image"],
2019
+ cost: {
2020
+ input: 0.11,
2021
+ output: 0.55,
2022
+ cacheRead: 0.011,
2023
+ cacheWrite: 0.1375,
2024
+ },
2025
+ contextWindow: 1050000,
2026
+ maxTokens: 128000,
2027
+ },
2028
+ "openai.gpt-6-sol": {
2029
+ id: "openai.gpt-6-sol",
2030
+ name: "GPT-6 Sol",
2031
+ api: "bedrock-converse-stream",
2032
+ provider: "amazon-bedrock",
2033
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2034
+ reasoning: true,
2035
+ input: ["text", "image"],
2036
+ cost: {
2037
+ input: 2.2,
2038
+ output: 11,
2039
+ cacheRead: 0.22,
2040
+ cacheWrite: 2.75,
2041
+ },
2042
+ contextWindow: 1050000,
2043
+ maxTokens: 128000,
2044
+ },
1960
2045
  "openai.gpt-oss-120b": {
1961
2046
  id: "openai.gpt-oss-120b",
1962
2047
  name: "gpt-oss-120b",
@@ -1971,8 +2056,8 @@ export const MODELS = {
1971
2056
  cacheRead: 0,
1972
2057
  cacheWrite: 0,
1973
2058
  },
1974
- contextWindow: 128000,
1975
- maxTokens: 16384,
2059
+ contextWindow: 131072,
2060
+ maxTokens: 131072,
1976
2061
  },
1977
2062
  "openai.gpt-oss-120b-1:0": {
1978
2063
  id: "openai.gpt-oss-120b-1:0",
@@ -1988,8 +2073,8 @@ export const MODELS = {
1988
2073
  cacheRead: 0,
1989
2074
  cacheWrite: 0,
1990
2075
  },
1991
- contextWindow: 128000,
1992
- maxTokens: 16384,
2076
+ contextWindow: 131072,
2077
+ maxTokens: 128000,
1993
2078
  },
1994
2079
  "openai.gpt-oss-20b": {
1995
2080
  id: "openai.gpt-oss-20b",
@@ -2005,8 +2090,8 @@ export const MODELS = {
2005
2090
  cacheRead: 0,
2006
2091
  cacheWrite: 0,
2007
2092
  },
2008
- contextWindow: 128000,
2009
- maxTokens: 16384,
2093
+ contextWindow: 131072,
2094
+ maxTokens: 131072,
2010
2095
  },
2011
2096
  "openai.gpt-oss-20b-1:0": {
2012
2097
  id: "openai.gpt-oss-20b-1:0",
@@ -2022,8 +2107,8 @@ export const MODELS = {
2022
2107
  cacheRead: 0,
2023
2108
  cacheWrite: 0,
2024
2109
  },
2025
- contextWindow: 128000,
2026
- maxTokens: 16384,
2110
+ contextWindow: 131072,
2111
+ maxTokens: 128000,
2027
2112
  },
2028
2113
  "openai.gpt-oss-safeguard-120b": {
2029
2114
  id: "openai.gpt-oss-safeguard-120b",
@@ -2652,7 +2737,7 @@ export const MODELS = {
2652
2737
  cacheWrite: 4.125,
2653
2738
  },
2654
2739
  contextWindow: 1048576,
2655
- maxTokens: 131072,
2740
+ maxTokens: 128000,
2656
2741
  },
2657
2742
  "us.openai.gpt-5.6-luna": {
2658
2743
  id: "us.openai.gpt-5.6-luna",
@@ -2807,6 +2892,23 @@ export const MODELS = {
2807
2892
  contextWindow: 500000,
2808
2893
  maxTokens: 500000,
2809
2894
  },
2895
+ "us.xai.grok-4.7": {
2896
+ id: "us.xai.grok-4.7",
2897
+ name: "Grok 4.7 (US)",
2898
+ api: "bedrock-converse-stream",
2899
+ provider: "amazon-bedrock",
2900
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2901
+ reasoning: true,
2902
+ input: ["text", "image"],
2903
+ cost: {
2904
+ input: 2.2,
2905
+ output: 6.6,
2906
+ cacheRead: 0.55,
2907
+ cacheWrite: 0,
2908
+ },
2909
+ contextWindow: 500000,
2910
+ maxTokens: 500000,
2911
+ },
2810
2912
  "writer.palmyra-x4-v1:0": {
2811
2913
  id: "writer.palmyra-x4-v1:0",
2812
2914
  name: "Palmyra X4",
@@ -2889,7 +2991,7 @@ export const MODELS = {
2889
2991
  cacheRead: 0,
2890
2992
  cacheWrite: 0,
2891
2993
  },
2892
- contextWindow: 204800,
2994
+ contextWindow: 202752,
2893
2995
  maxTokens: 131072,
2894
2996
  },
2895
2997
  "zai.glm-4.7-flash": {
@@ -2906,7 +3008,7 @@ export const MODELS = {
2906
3008
  cacheRead: 0,
2907
3009
  cacheWrite: 0,
2908
3010
  },
2909
- contextWindow: 200000,
3011
+ contextWindow: 202752,
2910
3012
  maxTokens: 131072,
2911
3013
  },
2912
3014
  "zai.glm-5": {
@@ -3183,6 +3285,23 @@ export const MODELS = {
3183
3285
  contextWindow: 1000000,
3184
3286
  maxTokens: 128000,
3185
3287
  },
3288
+ "claude-sonnet-5-5": {
3289
+ id: "claude-sonnet-5-5",
3290
+ name: "Claude Sonnet 5.5",
3291
+ api: "anthropic-messages",
3292
+ provider: "anthropic",
3293
+ baseUrl: "https://api.anthropic.com",
3294
+ reasoning: true,
3295
+ input: ["text", "image"],
3296
+ cost: {
3297
+ input: 2,
3298
+ output: 10,
3299
+ cacheRead: 0.2,
3300
+ cacheWrite: 2.5,
3301
+ },
3302
+ contextWindow: 1000000,
3303
+ maxTokens: 128000,
3304
+ },
3186
3305
  },
3187
3306
  "azure-openai-responses": {
3188
3307
  "gpt-4": {
@@ -3814,6 +3933,57 @@ export const MODELS = {
3814
3933
  contextWindow: 1050000,
3815
3934
  maxTokens: 128000,
3816
3935
  },
3936
+ "gpt-6.1-sol": {
3937
+ id: "gpt-6.1-sol",
3938
+ name: "GPT-6.1 Sol",
3939
+ api: "azure-openai-responses",
3940
+ provider: "azure-openai-responses",
3941
+ baseUrl: "",
3942
+ reasoning: true,
3943
+ input: ["text", "image"],
3944
+ cost: {
3945
+ input: 2,
3946
+ output: 10,
3947
+ cacheRead: 0.1,
3948
+ cacheWrite: 2.5,
3949
+ },
3950
+ contextWindow: 1050000,
3951
+ maxTokens: 128000,
3952
+ },
3953
+ "gpt-daybreak-blue-latest": {
3954
+ id: "gpt-daybreak-blue-latest",
3955
+ name: "Daybreak Blue",
3956
+ api: "azure-openai-responses",
3957
+ provider: "azure-openai-responses",
3958
+ baseUrl: "",
3959
+ reasoning: true,
3960
+ input: ["text", "image"],
3961
+ cost: {
3962
+ input: 4,
3963
+ output: 20,
3964
+ cacheRead: 0.4,
3965
+ cacheWrite: 5,
3966
+ },
3967
+ contextWindow: 1050000,
3968
+ maxTokens: 128000,
3969
+ },
3970
+ "gpt-daybreak-red-latest": {
3971
+ id: "gpt-daybreak-red-latest",
3972
+ name: "Daybreak Red",
3973
+ api: "azure-openai-responses",
3974
+ provider: "azure-openai-responses",
3975
+ baseUrl: "",
3976
+ reasoning: true,
3977
+ input: ["text", "image"],
3978
+ cost: {
3979
+ input: 12.5,
3980
+ output: 75,
3981
+ cacheRead: 1.25,
3982
+ cacheWrite: 15.625,
3983
+ },
3984
+ contextWindow: 400000,
3985
+ maxTokens: 128000,
3986
+ },
3817
3987
  "gpt-realtime-2.1": {
3818
3988
  id: "gpt-realtime-2.1",
3819
3989
  name: "GPT-Realtime-2.1",
@@ -3963,11 +4133,11 @@ export const MODELS = {
3963
4133
  cost: {
3964
4134
  input: 0.99,
3965
4135
  output: 1.49,
3966
- cacheRead: 0,
4136
+ cacheRead: 0.99,
3967
4137
  cacheWrite: 0,
3968
4138
  },
3969
- contextWindow: 65536,
3970
- maxTokens: 32768,
4139
+ contextWindow: 131072,
4140
+ maxTokens: 40960,
3971
4141
  },
3972
4142
  },
3973
4143
  "github-copilot": {
@@ -4138,6 +4308,25 @@ export const MODELS = {
4138
4308
  contextWindow: 1000000,
4139
4309
  maxTokens: 128000,
4140
4310
  },
4311
+ "claude-sonnet-5.5": {
4312
+ id: "claude-sonnet-5.5",
4313
+ name: "Claude Sonnet 5.5",
4314
+ api: "openai-completions",
4315
+ provider: "github-copilot",
4316
+ baseUrl: "https://api.individual.githubcopilot.com",
4317
+ 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" },
4318
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
4319
+ reasoning: true,
4320
+ input: ["text", "image"],
4321
+ cost: {
4322
+ input: 2,
4323
+ output: 10,
4324
+ cacheRead: 0.2,
4325
+ cacheWrite: 2.5,
4326
+ },
4327
+ contextWindow: 1000000,
4328
+ maxTokens: 128000,
4329
+ },
4141
4330
  "gemini-3.5-flash": {
4142
4331
  id: "gemini-3.5-flash",
4143
4332
  name: "Gemini 3.5 Flash",
@@ -4430,6 +4619,24 @@ export const MODELS = {
4430
4619
  contextWindow: 1050000,
4431
4620
  maxTokens: 128000,
4432
4621
  },
4622
+ "gpt-6.1-sol": {
4623
+ id: "gpt-6.1-sol",
4624
+ name: "GPT-6.1 Sol",
4625
+ api: "openai-responses",
4626
+ provider: "github-copilot",
4627
+ baseUrl: "https://api.individual.githubcopilot.com",
4628
+ 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" },
4629
+ reasoning: true,
4630
+ input: ["text", "image"],
4631
+ cost: {
4632
+ input: 2,
4633
+ output: 10,
4634
+ cacheRead: 0.1,
4635
+ cacheWrite: 2.5,
4636
+ },
4637
+ contextWindow: 1050000,
4638
+ maxTokens: 128000,
4639
+ },
4433
4640
  "grok-4.5": {
4434
4641
  id: "grok-4.5",
4435
4642
  name: "Grok 4.5",
@@ -4613,8 +4820,8 @@ export const MODELS = {
4613
4820
  cacheRead: 0,
4614
4821
  cacheWrite: 0,
4615
4822
  },
4616
- contextWindow: 131072,
4617
- maxTokens: 65536,
4823
+ contextWindow: 128000,
4824
+ maxTokens: 64000,
4618
4825
  },
4619
4826
  "gemini-2.5-flash": {
4620
4827
  id: "gemini-2.5-flash",
@@ -4716,7 +4923,7 @@ export const MODELS = {
4716
4923
  cacheWrite: 0,
4717
4924
  },
4718
4925
  contextWindow: 65536,
4719
- maxTokens: 65536,
4926
+ maxTokens: 4096,
4720
4927
  },
4721
4928
  "gemini-3.1-flash-lite-preview": {
4722
4929
  id: "gemini-3.1-flash-lite-preview",
@@ -7072,7 +7279,7 @@ export const MODELS = {
7072
7279
  cost: {
7073
7280
  input: 0.3,
7074
7281
  output: 0.9,
7075
- cacheRead: 0,
7282
+ cacheRead: 0.03,
7076
7283
  cacheWrite: 0,
7077
7284
  },
7078
7285
  contextWindow: 256000,
@@ -7214,23 +7421,6 @@ export const MODELS = {
7214
7421
  contextWindow: 128000,
7215
7422
  maxTokens: 16384,
7216
7423
  },
7217
- "magistral-small": {
7218
- id: "magistral-small",
7219
- name: "Magistral Small",
7220
- api: "mistral-conversations",
7221
- provider: "mistral",
7222
- baseUrl: "https://api.mistral.ai",
7223
- reasoning: true,
7224
- input: ["text"],
7225
- cost: {
7226
- input: 0.5,
7227
- output: 1.5,
7228
- cacheRead: 0,
7229
- cacheWrite: 0,
7230
- },
7231
- contextWindow: 128000,
7232
- maxTokens: 128000,
7233
- },
7234
7424
  "ministral-3b-latest": {
7235
7425
  id: "ministral-3b-latest",
7236
7426
  name: "Ministral 3B (latest)",
@@ -7293,7 +7483,7 @@ export const MODELS = {
7293
7483
  cost: {
7294
7484
  input: 0.5,
7295
7485
  output: 1.5,
7296
- cacheRead: 0,
7486
+ cacheRead: 0.05,
7297
7487
  cacheWrite: 0,
7298
7488
  },
7299
7489
  contextWindow: 262144,
@@ -7310,7 +7500,7 @@ export const MODELS = {
7310
7500
  cost: {
7311
7501
  input: 0.5,
7312
7502
  output: 1.5,
7313
- cacheRead: 0,
7503
+ cacheRead: 0.05,
7314
7504
  cacheWrite: 0,
7315
7505
  },
7316
7506
  contextWindow: 262144,
@@ -7361,7 +7551,7 @@ export const MODELS = {
7361
7551
  cost: {
7362
7552
  input: 1.5,
7363
7553
  output: 7.5,
7364
- cacheRead: 0,
7554
+ cacheRead: 0.15,
7365
7555
  cacheWrite: 0,
7366
7556
  },
7367
7557
  contextWindow: 262144,
@@ -7378,7 +7568,7 @@ export const MODELS = {
7378
7568
  cost: {
7379
7569
  input: 1.5,
7380
7570
  output: 7.5,
7381
- cacheRead: 0,
7571
+ cacheRead: 0.15,
7382
7572
  cacheWrite: 0,
7383
7573
  },
7384
7574
  contextWindow: 262144,
@@ -7429,7 +7619,7 @@ export const MODELS = {
7429
7619
  cost: {
7430
7620
  input: 0.15,
7431
7621
  output: 0.6,
7432
- cacheRead: 0,
7622
+ cacheRead: 0.015,
7433
7623
  cacheWrite: 0,
7434
7624
  },
7435
7625
  contextWindow: 256000,
@@ -7446,7 +7636,7 @@ export const MODELS = {
7446
7636
  cost: {
7447
7637
  input: 0.15,
7448
7638
  output: 0.6,
7449
- cacheRead: 0,
7639
+ cacheRead: 0.015,
7450
7640
  cacheWrite: 0,
7451
7641
  },
7452
7642
  contextWindow: 256000,
@@ -8236,19 +8426,70 @@ export const MODELS = {
8236
8426
  contextWindow: 1050000,
8237
8427
  maxTokens: 128000,
8238
8428
  },
8239
- "gpt-realtime-2.1": {
8240
- id: "gpt-realtime-2.1",
8241
- name: "GPT-Realtime-2.1",
8429
+ "gpt-6.1-sol": {
8430
+ id: "gpt-6.1-sol",
8431
+ name: "GPT-6.1 Sol",
8242
8432
  api: "openai-responses",
8243
8433
  provider: "openai",
8244
8434
  baseUrl: "https://api.openai.com/v1",
8245
8435
  reasoning: true,
8246
8436
  input: ["text", "image"],
8247
8437
  cost: {
8248
- input: 4,
8249
- output: 24,
8250
- cacheRead: 0.4,
8251
- cacheWrite: 0,
8438
+ input: 2,
8439
+ output: 10,
8440
+ cacheRead: 0.1,
8441
+ cacheWrite: 2.5,
8442
+ },
8443
+ contextWindow: 1050000,
8444
+ maxTokens: 128000,
8445
+ },
8446
+ "gpt-daybreak-blue-latest": {
8447
+ id: "gpt-daybreak-blue-latest",
8448
+ name: "Daybreak Blue",
8449
+ api: "openai-responses",
8450
+ provider: "openai",
8451
+ baseUrl: "https://api.openai.com/v1",
8452
+ reasoning: true,
8453
+ input: ["text", "image"],
8454
+ cost: {
8455
+ input: 4,
8456
+ output: 20,
8457
+ cacheRead: 0.4,
8458
+ cacheWrite: 5,
8459
+ },
8460
+ contextWindow: 1050000,
8461
+ maxTokens: 128000,
8462
+ },
8463
+ "gpt-daybreak-red-latest": {
8464
+ id: "gpt-daybreak-red-latest",
8465
+ name: "Daybreak Red",
8466
+ api: "openai-responses",
8467
+ provider: "openai",
8468
+ baseUrl: "https://api.openai.com/v1",
8469
+ reasoning: true,
8470
+ input: ["text", "image"],
8471
+ cost: {
8472
+ input: 12.5,
8473
+ output: 75,
8474
+ cacheRead: 1.25,
8475
+ cacheWrite: 15.625,
8476
+ },
8477
+ contextWindow: 400000,
8478
+ maxTokens: 128000,
8479
+ },
8480
+ "gpt-realtime-2.1": {
8481
+ id: "gpt-realtime-2.1",
8482
+ name: "GPT-Realtime-2.1",
8483
+ api: "openai-responses",
8484
+ provider: "openai",
8485
+ baseUrl: "https://api.openai.com/v1",
8486
+ reasoning: true,
8487
+ input: ["text", "image"],
8488
+ cost: {
8489
+ input: 4,
8490
+ output: 24,
8491
+ cacheRead: 0.4,
8492
+ cacheWrite: 0,
8252
8493
  },
8253
8494
  contextWindow: 128000,
8254
8495
  maxTokens: 32000,
@@ -8359,7 +8600,7 @@ export const MODELS = {
8359
8600
  "openai-codex": {
8360
8601
  "gpt-5.4-mini": {
8361
8602
  id: "gpt-5.4-mini",
8362
- name: "GPT-5.4 Mini",
8603
+ name: "GPT-5.4 mini",
8363
8604
  api: "openai-codex-responses",
8364
8605
  provider: "openai-codex",
8365
8606
  baseUrl: "https://chatgpt.com/backend-api",
@@ -8388,7 +8629,7 @@ export const MODELS = {
8388
8629
  cacheRead: 0.5,
8389
8630
  cacheWrite: 0,
8390
8631
  },
8391
- contextWindow: 400000,
8632
+ contextWindow: 272000,
8392
8633
  maxTokens: 128000,
8393
8634
  },
8394
8635
  "gpt-5.6-luna": {
@@ -8400,12 +8641,12 @@ export const MODELS = {
8400
8641
  reasoning: true,
8401
8642
  input: ["text", "image"],
8402
8643
  cost: {
8403
- input: 1,
8404
- output: 6,
8405
- cacheRead: 0.1,
8406
- cacheWrite: 1.25,
8644
+ input: 0.2,
8645
+ output: 1.2,
8646
+ cacheRead: 0.02,
8647
+ cacheWrite: 0.25,
8407
8648
  },
8408
- contextWindow: 372000,
8649
+ contextWindow: 272000,
8409
8650
  maxTokens: 128000,
8410
8651
  },
8411
8652
  "gpt-5.6-sol": {
@@ -8417,12 +8658,12 @@ export const MODELS = {
8417
8658
  reasoning: true,
8418
8659
  input: ["text", "image"],
8419
8660
  cost: {
8420
- input: 5,
8421
- output: 30,
8422
- cacheRead: 0.5,
8423
- cacheWrite: 6.25,
8661
+ input: 4,
8662
+ output: 20,
8663
+ cacheRead: 0.4,
8664
+ cacheWrite: 5,
8424
8665
  },
8425
- contextWindow: 372000,
8666
+ contextWindow: 272000,
8426
8667
  maxTokens: 128000,
8427
8668
  },
8428
8669
  "gpt-5.6-terra": {
@@ -8434,12 +8675,12 @@ export const MODELS = {
8434
8675
  reasoning: true,
8435
8676
  input: ["text", "image"],
8436
8677
  cost: {
8437
- input: 2.5,
8438
- output: 15,
8439
- cacheRead: 0.25,
8440
- cacheWrite: 3.125,
8678
+ input: 2,
8679
+ output: 12,
8680
+ cacheRead: 0.2,
8681
+ cacheWrite: 2.5,
8441
8682
  },
8442
- contextWindow: 372000,
8683
+ contextWindow: 272000,
8443
8684
  maxTokens: 128000,
8444
8685
  },
8445
8686
  "gpt-6-astra": {
@@ -8459,6 +8700,91 @@ export const MODELS = {
8459
8700
  contextWindow: 272000,
8460
8701
  maxTokens: 128000,
8461
8702
  },
8703
+ "gpt-6-luna": {
8704
+ id: "gpt-6-luna",
8705
+ name: "GPT-6 Luna",
8706
+ api: "openai-codex-responses",
8707
+ provider: "openai-codex",
8708
+ baseUrl: "https://chatgpt.com/backend-api",
8709
+ reasoning: true,
8710
+ input: ["text", "image"],
8711
+ cost: {
8712
+ input: 0.1,
8713
+ output: 0.5,
8714
+ cacheRead: 0.01,
8715
+ cacheWrite: 0.125,
8716
+ },
8717
+ contextWindow: 272000,
8718
+ maxTokens: 128000,
8719
+ },
8720
+ "gpt-6-sol": {
8721
+ id: "gpt-6-sol",
8722
+ name: "GPT-6 Sol",
8723
+ api: "openai-codex-responses",
8724
+ provider: "openai-codex",
8725
+ baseUrl: "https://chatgpt.com/backend-api",
8726
+ reasoning: true,
8727
+ input: ["text", "image"],
8728
+ cost: {
8729
+ input: 2,
8730
+ output: 10,
8731
+ cacheRead: 0.2,
8732
+ cacheWrite: 2.5,
8733
+ },
8734
+ contextWindow: 272000,
8735
+ maxTokens: 128000,
8736
+ },
8737
+ "gpt-6.1-sol": {
8738
+ id: "gpt-6.1-sol",
8739
+ name: "GPT-6.1 Sol",
8740
+ api: "openai-codex-responses",
8741
+ provider: "openai-codex",
8742
+ baseUrl: "https://chatgpt.com/backend-api",
8743
+ reasoning: true,
8744
+ input: ["text", "image"],
8745
+ cost: {
8746
+ input: 2,
8747
+ output: 10,
8748
+ cacheRead: 0.1,
8749
+ cacheWrite: 2.5,
8750
+ },
8751
+ contextWindow: 272000,
8752
+ maxTokens: 128000,
8753
+ },
8754
+ "gpt-daybreak-blue-latest": {
8755
+ id: "gpt-daybreak-blue-latest",
8756
+ name: "Daybreak Blue",
8757
+ api: "openai-codex-responses",
8758
+ provider: "openai-codex",
8759
+ baseUrl: "https://chatgpt.com/backend-api",
8760
+ reasoning: true,
8761
+ input: ["text", "image"],
8762
+ cost: {
8763
+ input: 4,
8764
+ output: 20,
8765
+ cacheRead: 0.4,
8766
+ cacheWrite: 5,
8767
+ },
8768
+ contextWindow: 272000,
8769
+ maxTokens: 128000,
8770
+ },
8771
+ "gpt-daybreak-red-latest": {
8772
+ id: "gpt-daybreak-red-latest",
8773
+ name: "Daybreak Red",
8774
+ api: "openai-codex-responses",
8775
+ provider: "openai-codex",
8776
+ baseUrl: "https://chatgpt.com/backend-api",
8777
+ reasoning: true,
8778
+ input: ["text", "image"],
8779
+ cost: {
8780
+ input: 12.5,
8781
+ output: 75,
8782
+ cacheRead: 1.25,
8783
+ cacheWrite: 15.625,
8784
+ },
8785
+ contextWindow: 272000,
8786
+ maxTokens: 128000,
8787
+ },
8462
8788
  },
8463
8789
  "opencode": {
8464
8790
  "big-pickle": {
@@ -8699,6 +9025,23 @@ export const MODELS = {
8699
9025
  contextWindow: 1000000,
8700
9026
  maxTokens: 128000,
8701
9027
  },
9028
+ "claude-sonnet-5-5": {
9029
+ id: "claude-sonnet-5-5",
9030
+ name: "Claude Sonnet 5.5",
9031
+ api: "anthropic-messages",
9032
+ provider: "opencode",
9033
+ baseUrl: "https://opencode.ai/zen",
9034
+ reasoning: true,
9035
+ input: ["text", "image"],
9036
+ cost: {
9037
+ input: 2,
9038
+ output: 10,
9039
+ cacheRead: 0.2,
9040
+ cacheWrite: 2.5,
9041
+ },
9042
+ contextWindow: 1000000,
9043
+ maxTokens: 128000,
9044
+ },
8702
9045
  "deepseek-v4-flash": {
8703
9046
  id: "deepseek-v4-flash",
8704
9047
  name: "DeepSeek V4 Flash",
@@ -9345,6 +9688,23 @@ export const MODELS = {
9345
9688
  contextWindow: 1050000,
9346
9689
  maxTokens: 128000,
9347
9690
  },
9691
+ "gpt-6.1-sol": {
9692
+ id: "gpt-6.1-sol",
9693
+ name: "GPT-6.1 Sol",
9694
+ api: "openai-responses",
9695
+ provider: "opencode",
9696
+ baseUrl: "https://opencode.ai/zen/v1",
9697
+ reasoning: true,
9698
+ input: ["text", "image"],
9699
+ cost: {
9700
+ input: 2,
9701
+ output: 10,
9702
+ cacheRead: 0.1,
9703
+ cacheWrite: 2.5,
9704
+ },
9705
+ contextWindow: 1050000,
9706
+ maxTokens: 128000,
9707
+ },
9348
9708
  "grok-4.5": {
9349
9709
  id: "grok-4.5",
9350
9710
  name: "Grok 4.5",
@@ -9381,16 +9741,16 @@ export const MODELS = {
9381
9741
  },
9382
9742
  "grok-4.7": {
9383
9743
  id: "grok-4.7",
9384
- name: "Grok 4.7 (30% Off)",
9744
+ name: "Grok 4.7",
9385
9745
  api: "openai-responses",
9386
9746
  provider: "opencode",
9387
9747
  baseUrl: "https://opencode.ai/zen/v1",
9388
9748
  reasoning: true,
9389
9749
  input: ["text", "image"],
9390
9750
  cost: {
9391
- input: 1.4,
9392
- output: 4.2,
9393
- cacheRead: 0.35,
9751
+ input: 2,
9752
+ output: 6,
9753
+ cacheRead: 0.5,
9394
9754
  cacheWrite: 0,
9395
9755
  },
9396
9756
  contextWindow: 500000,
@@ -9498,6 +9858,23 @@ export const MODELS = {
9498
9858
  contextWindow: 262144,
9499
9859
  maxTokens: 32768,
9500
9860
  },
9861
+ "longcat-2.5-preview-free": {
9862
+ id: "longcat-2.5-preview-free",
9863
+ name: "LongCat 2.5 Preview Free",
9864
+ api: "openai-completions",
9865
+ provider: "opencode",
9866
+ baseUrl: "https://opencode.ai/zen/v1",
9867
+ reasoning: true,
9868
+ input: ["text", "image"],
9869
+ cost: {
9870
+ input: 0,
9871
+ output: 0,
9872
+ cacheRead: 0,
9873
+ cacheWrite: 0,
9874
+ },
9875
+ contextWindow: 1000000,
9876
+ maxTokens: 131072,
9877
+ },
9501
9878
  "mimo-v2.6-flash-free": {
9502
9879
  id: "mimo-v2.6-flash-free",
9503
9880
  name: "MiMo-V2.6-Flash Free",
@@ -9583,23 +9960,6 @@ export const MODELS = {
9583
9960
  contextWindow: 1048576,
9584
9961
  maxTokens: 131072,
9585
9962
  },
9586
- "muse-spark-1.2-contributor-free": {
9587
- id: "muse-spark-1.2-contributor-free",
9588
- name: "Muse Spark 1.2 Free",
9589
- api: "openai-responses",
9590
- provider: "opencode",
9591
- baseUrl: "https://opencode.ai/zen/v1",
9592
- reasoning: true,
9593
- input: ["text", "image"],
9594
- cost: {
9595
- input: 0,
9596
- output: 0,
9597
- cacheRead: 0,
9598
- cacheWrite: 0,
9599
- },
9600
- contextWindow: 1048576,
9601
- maxTokens: 131072,
9602
- },
9603
9963
  "muse-spark-1.3": {
9604
9964
  id: "muse-spark-1.3",
9605
9965
  name: "Muse Spark 1.3",
@@ -9719,6 +10079,23 @@ export const MODELS = {
9719
10079
  contextWindow: 1000000,
9720
10080
  maxTokens: 131072,
9721
10081
  },
10082
+ "qwen3.8-max": {
10083
+ id: "qwen3.8-max",
10084
+ name: "Qwen3.8 Max",
10085
+ api: "openai-completions",
10086
+ provider: "opencode",
10087
+ baseUrl: "https://opencode.ai/zen/v1",
10088
+ reasoning: true,
10089
+ input: ["text", "image"],
10090
+ cost: {
10091
+ input: 2,
10092
+ output: 6,
10093
+ cacheRead: 0.25,
10094
+ cacheWrite: 2.5,
10095
+ },
10096
+ contextWindow: 262144,
10097
+ maxTokens: 131072,
10098
+ },
9722
10099
  "space-bunny-free": {
9723
10100
  id: "space-bunny-free",
9724
10101
  name: "Space Bunny Free",
@@ -9806,23 +10183,6 @@ export const MODELS = {
9806
10183
  contextWindow: 1000000,
9807
10184
  maxTokens: 384000,
9808
10185
  },
9809
- "glm-5.1": {
9810
- id: "glm-5.1",
9811
- name: "GLM-5.1",
9812
- api: "openai-completions",
9813
- provider: "opencode-go",
9814
- baseUrl: "https://opencode.ai/zen/go/v1",
9815
- reasoning: true,
9816
- input: ["text"],
9817
- cost: {
9818
- input: 1.4,
9819
- output: 4.4,
9820
- cacheRead: 0.26,
9821
- cacheWrite: 0,
9822
- },
9823
- contextWindow: 202752,
9824
- maxTokens: 32768,
9825
- },
9826
10186
  "glm-5.2": {
9827
10187
  id: "glm-5.2",
9828
10188
  name: "GLM-5.2",
@@ -9976,23 +10336,6 @@ export const MODELS = {
9976
10336
  contextWindow: 1024000,
9977
10337
  maxTokens: 64000,
9978
10338
  },
9979
- "kimi-k2.6": {
9980
- id: "kimi-k2.6",
9981
- name: "Kimi K2.6",
9982
- api: "openai-completions",
9983
- provider: "opencode-go",
9984
- baseUrl: "https://opencode.ai/zen/go/v1",
9985
- reasoning: true,
9986
- input: ["text", "image"],
9987
- cost: {
9988
- input: 0.95,
9989
- output: 4,
9990
- cacheRead: 0.16,
9991
- cacheWrite: 0,
9992
- },
9993
- contextWindow: 262144,
9994
- maxTokens: 65536,
9995
- },
9996
10339
  "kimi-k2.7-code": {
9997
10340
  id: "kimi-k2.7-code",
9998
10341
  name: "Kimi K2.7 Code",
@@ -10044,6 +10387,23 @@ export const MODELS = {
10044
10387
  contextWindow: 1000000,
10045
10388
  maxTokens: 131072,
10046
10389
  },
10390
+ "longcat-2.5-preview-free": {
10391
+ id: "longcat-2.5-preview-free",
10392
+ name: "LongCat 2.5 Preview Free",
10393
+ api: "openai-completions",
10394
+ provider: "opencode-go",
10395
+ baseUrl: "https://opencode.ai/zen/go/v1",
10396
+ reasoning: true,
10397
+ input: ["text", "image"],
10398
+ cost: {
10399
+ input: 0,
10400
+ output: 0,
10401
+ cacheRead: 0,
10402
+ cacheWrite: 0,
10403
+ },
10404
+ contextWindow: 1000000,
10405
+ maxTokens: 131072,
10406
+ },
10047
10407
  "mimo-v2.5": {
10048
10408
  id: "mimo-v2.5",
10049
10409
  name: "MiMo V2.5",
@@ -10180,40 +10540,6 @@ export const MODELS = {
10180
10540
  contextWindow: 1048576,
10181
10541
  maxTokens: 131072,
10182
10542
  },
10183
- "qwen3.6-plus": {
10184
- id: "qwen3.6-plus",
10185
- name: "Qwen3.6 Plus",
10186
- api: "openai-completions",
10187
- provider: "opencode-go",
10188
- baseUrl: "https://opencode.ai/zen/go/v1",
10189
- reasoning: true,
10190
- input: ["text", "image"],
10191
- cost: {
10192
- input: 0.5,
10193
- output: 3,
10194
- cacheRead: 0.05,
10195
- cacheWrite: 0.625,
10196
- },
10197
- contextWindow: 1000000,
10198
- maxTokens: 65536,
10199
- },
10200
- "qwen3.7-max": {
10201
- id: "qwen3.7-max",
10202
- name: "Qwen3.7 Max",
10203
- api: "openai-completions",
10204
- provider: "opencode-go",
10205
- baseUrl: "https://opencode.ai/zen/go/v1",
10206
- reasoning: true,
10207
- input: ["text"],
10208
- cost: {
10209
- input: 2.5,
10210
- output: 7.5,
10211
- cacheRead: 0.5,
10212
- cacheWrite: 3.125,
10213
- },
10214
- contextWindow: 1000000,
10215
- maxTokens: 65536,
10216
- },
10217
10543
  "qwen3.7-plus": {
10218
10544
  id: "qwen3.7-plus",
10219
10545
  name: "Qwen3.7 Plus",
@@ -10454,23 +10780,6 @@ export const MODELS = {
10454
10780
  contextWindow: 300000,
10455
10781
  maxTokens: 5120,
10456
10782
  },
10457
- "anthropic/claude-3-haiku": {
10458
- id: "anthropic/claude-3-haiku",
10459
- name: "Anthropic: Claude 3 Haiku",
10460
- api: "openai-completions",
10461
- provider: "openrouter",
10462
- baseUrl: "https://openrouter.ai/api/v1",
10463
- reasoning: false,
10464
- input: ["text", "image"],
10465
- cost: {
10466
- input: 0.25,
10467
- output: 1.25,
10468
- cacheRead: 0.03,
10469
- cacheWrite: 0.3,
10470
- },
10471
- contextWindow: 200000,
10472
- maxTokens: 4096,
10473
- },
10474
10783
  "anthropic/claude-fable-5": {
10475
10784
  id: "anthropic/claude-fable-5",
10476
10785
  name: "Anthropic: Claude Fable 5",
@@ -10913,6 +11222,40 @@ export const MODELS = {
10913
11222
  contextWindow: 1000000,
10914
11223
  maxTokens: 128000,
10915
11224
  },
11225
+ "anthropic/claude-sonnet-5.5": {
11226
+ id: "anthropic/claude-sonnet-5.5",
11227
+ name: "Anthropic: Claude Sonnet 5.5",
11228
+ api: "openai-completions",
11229
+ provider: "openrouter",
11230
+ baseUrl: "https://openrouter.ai/api/v1",
11231
+ reasoning: true,
11232
+ input: ["text", "image"],
11233
+ cost: {
11234
+ input: 2,
11235
+ output: 10,
11236
+ cacheRead: 0.19999999999999998,
11237
+ cacheWrite: 2.5,
11238
+ },
11239
+ contextWindow: 1000000,
11240
+ maxTokens: 128000,
11241
+ },
11242
+ "anthropic/claude-sonnet-5.5:batch": {
11243
+ id: "anthropic/claude-sonnet-5.5:batch",
11244
+ name: "Anthropic: Claude Sonnet 5.5 (batch)",
11245
+ api: "openai-completions",
11246
+ provider: "openrouter",
11247
+ baseUrl: "https://openrouter.ai/api/v1",
11248
+ reasoning: true,
11249
+ input: ["text", "image"],
11250
+ cost: {
11251
+ input: 1,
11252
+ output: 5,
11253
+ cacheRead: 0.09999999999999999,
11254
+ cacheWrite: 1.25,
11255
+ },
11256
+ contextWindow: 1000000,
11257
+ maxTokens: 128000,
11258
+ },
10916
11259
  "anthropic/claude-sonnet-5:batch": {
10917
11260
  id: "anthropic/claude-sonnet-5:batch",
10918
11261
  name: "Anthropic: Claude Sonnet 5 (batch)",
@@ -11143,13 +11486,13 @@ export const MODELS = {
11143
11486
  reasoning: false,
11144
11487
  input: ["text"],
11145
11488
  cost: {
11146
- input: 0.32,
11147
- output: 0.8899999999999999,
11489
+ input: 0.2574,
11490
+ output: 1.0287,
11148
11491
  cacheRead: 0,
11149
11492
  cacheWrite: 0,
11150
11493
  },
11151
11494
  contextWindow: 163840,
11152
- maxTokens: 16384,
11495
+ maxTokens: 16000,
11153
11496
  },
11154
11497
  "deepseek/deepseek-chat-v3-0324": {
11155
11498
  id: "deepseek/deepseek-chat-v3-0324",
@@ -11160,9 +11503,9 @@ export const MODELS = {
11160
11503
  reasoning: false,
11161
11504
  input: ["text"],
11162
11505
  cost: {
11163
- input: 0.25,
11164
- output: 1,
11165
- cacheRead: 0,
11506
+ input: 0.29,
11507
+ output: 1.1400000000000001,
11508
+ cacheRead: 0.11,
11166
11509
  cacheWrite: 0,
11167
11510
  },
11168
11511
  contextWindow: 163840,
@@ -11228,13 +11571,13 @@ export const MODELS = {
11228
11571
  reasoning: true,
11229
11572
  input: ["text"],
11230
11573
  cost: {
11231
- input: 0.27,
11574
+ input: 0.3,
11232
11575
  output: 1,
11233
11576
  cacheRead: 0.135,
11234
11577
  cacheWrite: 0,
11235
11578
  },
11236
11579
  contextWindow: 163840,
11237
- maxTokens: 32768,
11580
+ maxTokens: 65536,
11238
11581
  },
11239
11582
  "deepseek/deepseek-v3.2": {
11240
11583
  id: "deepseek/deepseek-v3.2",
@@ -11245,9 +11588,9 @@ export const MODELS = {
11245
11588
  reasoning: true,
11246
11589
  input: ["text"],
11247
11590
  cost: {
11248
- input: 0.26899999999999996,
11249
- output: 0.39999999999999997,
11250
- cacheRead: 0.13449999999999998,
11591
+ input: 0.28,
11592
+ output: 0.42,
11593
+ cacheRead: 0.028,
11251
11594
  cacheWrite: 0,
11252
11595
  },
11253
11596
  contextWindow: 163840,
@@ -11268,7 +11611,7 @@ export const MODELS = {
11268
11611
  cacheWrite: 0,
11269
11612
  },
11270
11613
  contextWindow: 163840,
11271
- maxTokens: 65536,
11614
+ maxTokens: 147456,
11272
11615
  },
11273
11616
  "deepseek/deepseek-v4-flash": {
11274
11617
  id: "deepseek/deepseek-v4-flash",
@@ -11279,9 +11622,9 @@ export const MODELS = {
11279
11622
  reasoning: true,
11280
11623
  input: ["text"],
11281
11624
  cost: {
11282
- input: 0.08245999999999999,
11283
- output: 0.16491999999999998,
11284
- cacheRead: 0.016492,
11625
+ input: 0.07854,
11626
+ output: 0.15708,
11627
+ cacheRead: 0.015708,
11285
11628
  cacheWrite: 0,
11286
11629
  },
11287
11630
  contextWindow: 1048576,
@@ -11296,12 +11639,12 @@ export const MODELS = {
11296
11639
  reasoning: true,
11297
11640
  input: ["text"],
11298
11641
  cost: {
11299
- input: 0.04,
11300
- output: 0.64,
11301
- cacheRead: 0.016,
11642
+ input: 0.01,
11643
+ output: 1.28,
11644
+ cacheRead: 0.01,
11302
11645
  cacheWrite: 0,
11303
11646
  },
11304
- contextWindow: 1310720,
11647
+ contextWindow: 1048576,
11305
11648
  maxTokens: 943718,
11306
11649
  },
11307
11650
  "deepseek/deepseek-v4-flash-vision-exp": {
@@ -11313,13 +11656,13 @@ export const MODELS = {
11313
11656
  reasoning: true,
11314
11657
  input: ["text", "image"],
11315
11658
  cost: {
11316
- input: 0.22,
11317
- output: 0.66,
11318
- cacheRead: 0.007,
11659
+ input: 0.21559999999999999,
11660
+ output: 0.6468,
11661
+ cacheRead: 0.00686,
11319
11662
  cacheWrite: 0,
11320
11663
  },
11321
11664
  contextWindow: 1048576,
11322
- maxTokens: 943718,
11665
+ maxTokens: 262144,
11323
11666
  },
11324
11667
  "deepseek/deepseek-v4-pro": {
11325
11668
  id: "deepseek/deepseek-v4-pro",
@@ -11330,9 +11673,9 @@ export const MODELS = {
11330
11673
  reasoning: true,
11331
11674
  input: ["text"],
11332
11675
  cost: {
11333
- input: 0.946386,
11334
- output: 1.892772,
11335
- cacheRead: 0.0788655,
11676
+ input: 0.7829999999999999,
11677
+ output: 1.5659999999999998,
11678
+ cacheRead: 0.06525,
11336
11679
  cacheWrite: 0,
11337
11680
  },
11338
11681
  contextWindow: 1048576,
@@ -11347,13 +11690,13 @@ export const MODELS = {
11347
11690
  reasoning: true,
11348
11691
  input: ["text"],
11349
11692
  cost: {
11350
- input: 0.46199999999999997,
11351
- output: 1.386,
11352
- cacheRead: 0.015399999999999999,
11693
+ input: 0.66,
11694
+ output: 1.9800000000000002,
11695
+ cacheRead: 0.022,
11353
11696
  cacheWrite: 0,
11354
11697
  },
11355
11698
  contextWindow: 1048576,
11356
- maxTokens: 384000,
11699
+ maxTokens: 393216,
11357
11700
  },
11358
11701
  "deepseek/deepseek-v4.1-flash": {
11359
11702
  id: "deepseek/deepseek-v4.1-flash",
@@ -11364,9 +11707,9 @@ export const MODELS = {
11364
11707
  reasoning: true,
11365
11708
  input: ["text", "image"],
11366
11709
  cost: {
11367
- input: 0.09999999999999999,
11368
- output: 0.5,
11369
- cacheRead: 0.01,
11710
+ input: 0.019799999999999998,
11711
+ output: 0.396,
11712
+ cacheRead: 0.0029100000000000003,
11370
11713
  cacheWrite: 0,
11371
11714
  },
11372
11715
  contextWindow: 1048576,
@@ -11406,6 +11749,23 @@ export const MODELS = {
11406
11749
  contextWindow: 512000,
11407
11750
  maxTokens: 460800,
11408
11751
  },
11752
+ "fireworks/ember-1": {
11753
+ id: "fireworks/ember-1",
11754
+ name: "Fireworks: Ember-1",
11755
+ api: "openai-completions",
11756
+ provider: "openrouter",
11757
+ baseUrl: "https://openrouter.ai/api/v1",
11758
+ reasoning: true,
11759
+ input: ["text", "image"],
11760
+ cost: {
11761
+ input: 3,
11762
+ output: 15,
11763
+ cacheRead: 0.3,
11764
+ cacheWrite: 0,
11765
+ },
11766
+ contextWindow: 1048576,
11767
+ maxTokens: 943718,
11768
+ },
11409
11769
  "google/gemini-2.5-flash": {
11410
11770
  id: "google/gemini-2.5-flash",
11411
11771
  name: "Google: Gemini 2.5 Flash",
@@ -12035,23 +12395,6 @@ export const MODELS = {
12035
12395
  contextWindow: 262144,
12036
12396
  maxTokens: 235929,
12037
12397
  },
12038
- "inclusionai/ling-3.0-flash-fin:free": {
12039
- id: "inclusionai/ling-3.0-flash-fin:free",
12040
- name: "inclusionAI: Ling 3.0 Flash Fin (free)",
12041
- api: "openai-completions",
12042
- provider: "openrouter",
12043
- baseUrl: "https://openrouter.ai/api/v1",
12044
- reasoning: true,
12045
- input: ["text"],
12046
- cost: {
12047
- input: 0,
12048
- output: 0,
12049
- cacheRead: 0,
12050
- cacheWrite: 0,
12051
- },
12052
- contextWindow: 262144,
12053
- maxTokens: 32768,
12054
- },
12055
12398
  "inclusionai/ling-3.0-flash-sante:free": {
12056
12399
  id: "inclusionai/ling-3.0-flash-sante:free",
12057
12400
  name: "inclusionAI: Ling 3.0 Flash Sante (free)",
@@ -12078,9 +12421,9 @@ export const MODELS = {
12078
12421
  reasoning: true,
12079
12422
  input: ["text", "image"],
12080
12423
  cost: {
12081
- input: 0.06,
12082
- output: 0.18,
12083
- cacheRead: 0.012,
12424
+ input: 0.020999999999999998,
12425
+ output: 0.061599999999999995,
12426
+ cacheRead: 0.004200000000000001,
12084
12427
  cacheWrite: 0,
12085
12428
  },
12086
12429
  contextWindow: 262144,
@@ -12231,13 +12574,13 @@ export const MODELS = {
12231
12574
  reasoning: true,
12232
12575
  input: ["text", "image"],
12233
12576
  cost: {
12234
- input: 0.3,
12235
- output: 1.2,
12577
+ input: 0.35,
12578
+ output: 1.5,
12236
12579
  cacheRead: 0.04,
12237
12580
  cacheWrite: 0,
12238
12581
  },
12239
12582
  contextWindow: 131072,
12240
- maxTokens: 16384,
12583
+ maxTokens: 117964,
12241
12584
  },
12242
12585
  "meta/muse-spark-1.1": {
12243
12586
  id: "meta/muse-spark-1.1",
@@ -12350,13 +12693,13 @@ export const MODELS = {
12350
12693
  reasoning: true,
12351
12694
  input: ["text"],
12352
12695
  cost: {
12353
- input: 0.255,
12354
- output: 1.02,
12696
+ input: 0.3,
12697
+ output: 1.2,
12355
12698
  cacheRead: 0,
12356
12699
  cacheWrite: 0,
12357
12700
  },
12358
12701
  contextWindow: 204800,
12359
- maxTokens: 131072,
12702
+ maxTokens: 176947,
12360
12703
  },
12361
12704
  "minimax/minimax-m2.1": {
12362
12705
  id: "minimax/minimax-m2.1",
@@ -12401,13 +12744,13 @@ export const MODELS = {
12401
12744
  reasoning: true,
12402
12745
  input: ["text"],
12403
12746
  cost: {
12404
- input: 0.3,
12405
- output: 1.2,
12406
- cacheRead: 0.06,
12747
+ input: 0.21,
12748
+ output: 0.84,
12749
+ cacheRead: 0.041999999999999996,
12407
12750
  cacheWrite: 0,
12408
12751
  },
12409
12752
  contextWindow: 204800,
12410
- maxTokens: 131072,
12753
+ maxTokens: 176947,
12411
12754
  },
12412
12755
  "minimax/minimax-m3": {
12413
12756
  id: "minimax/minimax-m3",
@@ -12460,6 +12803,23 @@ export const MODELS = {
12460
12803
  contextWindow: 256000,
12461
12804
  maxTokens: 204800,
12462
12805
  },
12806
+ "mistralai/devstral-2512": {
12807
+ id: "mistralai/devstral-2512",
12808
+ name: "Mistral: Devstral 2 2512",
12809
+ api: "openai-completions",
12810
+ provider: "openrouter",
12811
+ baseUrl: "https://openrouter.ai/api/v1",
12812
+ reasoning: false,
12813
+ input: ["text"],
12814
+ cost: {
12815
+ input: 0.39999999999999997,
12816
+ output: 2,
12817
+ cacheRead: 0.04,
12818
+ cacheWrite: 0,
12819
+ },
12820
+ contextWindow: 262144,
12821
+ maxTokens: 209715,
12822
+ },
12463
12823
  "mistralai/ministral-14b-2512": {
12464
12824
  id: "mistralai/ministral-14b-2512",
12465
12825
  name: "Mistral: Ministral 3 14B 2512",
@@ -12562,6 +12922,23 @@ export const MODELS = {
12562
12922
  contextWindow: 131072,
12563
12923
  maxTokens: 104857,
12564
12924
  },
12925
+ "mistralai/mistral-large-2512": {
12926
+ id: "mistralai/mistral-large-2512",
12927
+ name: "Mistral: Mistral Large 3 2512",
12928
+ api: "openai-completions",
12929
+ provider: "openrouter",
12930
+ baseUrl: "https://openrouter.ai/api/v1",
12931
+ reasoning: false,
12932
+ input: ["text", "image"],
12933
+ cost: {
12934
+ input: 0.5,
12935
+ output: 1.5,
12936
+ cacheRead: 0.049999999999999996,
12937
+ cacheWrite: 0,
12938
+ },
12939
+ contextWindow: 262144,
12940
+ maxTokens: 209715,
12941
+ },
12565
12942
  "mistralai/mistral-large-2512:batch": {
12566
12943
  id: "mistralai/mistral-large-2512:batch",
12567
12944
  name: "Mistral: Mistral Large 3 2512 (batch)",
@@ -12877,9 +13254,9 @@ export const MODELS = {
12877
13254
  reasoning: true,
12878
13255
  input: ["text", "image"],
12879
13256
  cost: {
12880
- input: 0.95,
12881
- output: 4,
12882
- cacheRead: 0.16,
13257
+ input: 0.65,
13258
+ output: 3.41,
13259
+ cacheRead: 0.15,
12883
13260
  cacheWrite: 0,
12884
13261
  },
12885
13262
  contextWindow: 262144,
@@ -12894,8 +13271,8 @@ export const MODELS = {
12894
13271
  reasoning: true,
12895
13272
  input: ["text", "image"],
12896
13273
  cost: {
12897
- input: 0.7062,
12898
- output: 3.3000000000000003,
13274
+ input: 0.6712,
13275
+ output: 3.35,
12899
13276
  cacheRead: 0.18,
12900
13277
  cacheWrite: 0,
12901
13278
  },
@@ -12936,23 +13313,6 @@ export const MODELS = {
12936
13313
  contextWindow: 1048576,
12937
13314
  maxTokens: 16384,
12938
13315
  },
12939
- "nex-agi/nex-n2.5-mini:free": {
12940
- id: "nex-agi/nex-n2.5-mini:free",
12941
- name: "Nex AGI: Nex-N2.5-Mini (free)",
12942
- api: "openai-completions",
12943
- provider: "openrouter",
12944
- baseUrl: "https://openrouter.ai/api/v1",
12945
- reasoning: true,
12946
- input: ["text", "image"],
12947
- cost: {
12948
- input: 0,
12949
- output: 0,
12950
- cacheRead: 0,
12951
- cacheWrite: 0,
12952
- },
12953
- contextWindow: 262144,
12954
- maxTokens: 235929,
12955
- },
12956
13316
  "nex-agi/nex-n2.5-pro": {
12957
13317
  id: "nex-agi/nex-n2.5-pro",
12958
13318
  name: "Nex AGI: Nex-N2.5-Pro",
@@ -12970,23 +13330,6 @@ export const MODELS = {
12970
13330
  contextWindow: 262144,
12971
13331
  maxTokens: 235929,
12972
13332
  },
12973
- "nex-agi/nex-n2.5-pro:free": {
12974
- id: "nex-agi/nex-n2.5-pro:free",
12975
- name: "Nex AGI: Nex-N2.5-Pro (free)",
12976
- api: "openai-completions",
12977
- provider: "openrouter",
12978
- baseUrl: "https://openrouter.ai/api/v1",
12979
- reasoning: true,
12980
- input: ["text", "image"],
12981
- cost: {
12982
- input: 0,
12983
- output: 0,
12984
- cacheRead: 0,
12985
- cacheWrite: 0,
12986
- },
12987
- contextWindow: 262144,
12988
- maxTokens: 235929,
12989
- },
12990
13333
  "nvidia/nemotron-3-nano-30b-a3b": {
12991
13334
  id: "nvidia/nemotron-3-nano-30b-a3b",
12992
13335
  name: "NVIDIA: Nemotron 3 Nano 30B A3B",
@@ -13098,13 +13441,13 @@ export const MODELS = {
13098
13441
  reasoning: true,
13099
13442
  input: ["text"],
13100
13443
  cost: {
13101
- input: 0.08,
13102
- output: 0.19999999999999998,
13103
- cacheRead: 0.04,
13444
+ input: 0.06,
13445
+ output: 0.16,
13446
+ cacheRead: 0.03,
13104
13447
  cacheWrite: 0,
13105
13448
  },
13106
13449
  contextWindow: 262144,
13107
- maxTokens: 131072,
13450
+ maxTokens: 32768,
13108
13451
  },
13109
13452
  "nvidia/nemotron-3.5-lightning:free": {
13110
13453
  id: "nvidia/nemotron-3.5-lightning:free",
@@ -14101,10 +14444,10 @@ export const MODELS = {
14101
14444
  reasoning: true,
14102
14445
  input: ["text", "image"],
14103
14446
  cost: {
14104
- input: 2,
14105
- output: 10,
14106
- cacheRead: 0.19999999999999998,
14107
- cacheWrite: 2.5,
14447
+ input: 4,
14448
+ output: 20,
14449
+ cacheRead: 0.39999999999999997,
14450
+ cacheWrite: 5,
14108
14451
  },
14109
14452
  contextWindow: 1050000,
14110
14453
  maxTokens: 128000,
@@ -14432,6 +14775,74 @@ export const MODELS = {
14432
14775
  contextWindow: 1050000,
14433
14776
  maxTokens: 128000,
14434
14777
  },
14778
+ "openai/gpt-6.1-sol": {
14779
+ id: "openai/gpt-6.1-sol",
14780
+ name: "OpenAI: GPT-6.1 Sol",
14781
+ api: "openai-completions",
14782
+ provider: "openrouter",
14783
+ baseUrl: "https://openrouter.ai/api/v1",
14784
+ reasoning: true,
14785
+ input: ["text", "image"],
14786
+ cost: {
14787
+ input: 2,
14788
+ output: 10,
14789
+ cacheRead: 0.09999999999999999,
14790
+ cacheWrite: 2.5,
14791
+ },
14792
+ contextWindow: 1050000,
14793
+ maxTokens: 128000,
14794
+ },
14795
+ "openai/gpt-6.1-sol-pro": {
14796
+ id: "openai/gpt-6.1-sol-pro",
14797
+ name: "OpenAI: GPT-6.1 Sol Pro",
14798
+ api: "openai-completions",
14799
+ provider: "openrouter",
14800
+ baseUrl: "https://openrouter.ai/api/v1",
14801
+ reasoning: true,
14802
+ input: ["text", "image"],
14803
+ cost: {
14804
+ input: 2,
14805
+ output: 10,
14806
+ cacheRead: 0.09999999999999999,
14807
+ cacheWrite: 2.5,
14808
+ },
14809
+ contextWindow: 1050000,
14810
+ maxTokens: 128000,
14811
+ },
14812
+ "openai/gpt-6.1-sol-pro:batch": {
14813
+ id: "openai/gpt-6.1-sol-pro:batch",
14814
+ name: "OpenAI: GPT-6.1 Sol Pro (batch)",
14815
+ api: "openai-completions",
14816
+ provider: "openrouter",
14817
+ baseUrl: "https://openrouter.ai/api/v1",
14818
+ reasoning: true,
14819
+ input: ["text", "image"],
14820
+ cost: {
14821
+ input: 1,
14822
+ output: 5,
14823
+ cacheRead: 0.049999999999999996,
14824
+ cacheWrite: 1.25,
14825
+ },
14826
+ contextWindow: 1050000,
14827
+ maxTokens: 128000,
14828
+ },
14829
+ "openai/gpt-6.1-sol:batch": {
14830
+ id: "openai/gpt-6.1-sol:batch",
14831
+ name: "OpenAI: GPT-6.1 Sol (batch)",
14832
+ api: "openai-completions",
14833
+ provider: "openrouter",
14834
+ baseUrl: "https://openrouter.ai/api/v1",
14835
+ reasoning: true,
14836
+ input: ["text", "image"],
14837
+ cost: {
14838
+ input: 1,
14839
+ output: 5,
14840
+ cacheRead: 0.049999999999999996,
14841
+ cacheWrite: 1.25,
14842
+ },
14843
+ contextWindow: 1050000,
14844
+ maxTokens: 128000,
14845
+ },
14435
14846
  "openai/gpt-audio": {
14436
14847
  id: "openai/gpt-audio",
14437
14848
  name: "OpenAI: GPT Audio",
@@ -14492,13 +14903,30 @@ export const MODELS = {
14492
14903
  reasoning: true,
14493
14904
  input: ["text"],
14494
14905
  cost: {
14495
- input: 0.15,
14496
- output: 0.6,
14497
- cacheRead: 0.075,
14906
+ input: 0.037,
14907
+ output: 0.16999999999999998,
14908
+ cacheRead: 0,
14498
14909
  cacheWrite: 0,
14499
14910
  },
14500
14911
  contextWindow: 131072,
14501
- maxTokens: 65536,
14912
+ maxTokens: 117964,
14913
+ },
14914
+ "openai/gpt-oss-120b:batch": {
14915
+ id: "openai/gpt-oss-120b:batch",
14916
+ name: "OpenAI: gpt-oss-120b (batch)",
14917
+ api: "openai-completions",
14918
+ provider: "openrouter",
14919
+ baseUrl: "https://openrouter.ai/api/v1",
14920
+ reasoning: true,
14921
+ input: ["text"],
14922
+ cost: {
14923
+ input: 0.0296,
14924
+ output: 0.136,
14925
+ cacheRead: 0,
14926
+ cacheWrite: 0,
14927
+ },
14928
+ contextWindow: 131072,
14929
+ maxTokens: 117964,
14502
14930
  },
14503
14931
  "openai/gpt-oss-20b": {
14504
14932
  id: "openai/gpt-oss-20b",
@@ -14511,7 +14939,7 @@ export const MODELS = {
14511
14939
  cost: {
14512
14940
  input: 0.018,
14513
14941
  output: 0.09,
14514
- cacheRead: 0,
14942
+ cacheRead: 0.009,
14515
14943
  cacheWrite: 0,
14516
14944
  },
14517
14945
  contextWindow: 131072,
@@ -14772,6 +15200,23 @@ export const MODELS = {
14772
15200
  contextWindow: 200000,
14773
15201
  maxTokens: 4096,
14774
15202
  },
15203
+ "perceptron/perceptron-mk1.5": {
15204
+ id: "perceptron/perceptron-mk1.5",
15205
+ name: "Perceptron: Perceptron Mk1.5",
15206
+ api: "openai-completions",
15207
+ provider: "openrouter",
15208
+ baseUrl: "https://openrouter.ai/api/v1",
15209
+ reasoning: true,
15210
+ input: ["text", "image"],
15211
+ cost: {
15212
+ input: 0.15,
15213
+ output: 1.5,
15214
+ cacheRead: 0,
15215
+ cacheWrite: 0,
15216
+ },
15217
+ contextWindow: 36864,
15218
+ maxTokens: 8192,
15219
+ },
14775
15220
  "poolside/laguna-s-2.1": {
14776
15221
  id: "poolside/laguna-s-2.1",
14777
15222
  name: "Poolside: Laguna S 2.1",
@@ -14851,7 +15296,7 @@ export const MODELS = {
14851
15296
  cost: {
14852
15297
  input: 0.075,
14853
15298
  output: 0.5,
14854
- cacheRead: 0,
15299
+ cacheRead: 0.0375,
14855
15300
  cacheWrite: 0,
14856
15301
  },
14857
15302
  contextWindow: 262144,
@@ -15206,13 +15651,13 @@ export const MODELS = {
15206
15651
  reasoning: false,
15207
15652
  input: ["text"],
15208
15653
  cost: {
15209
- input: 0.09,
15654
+ input: 0.09999999999999999,
15210
15655
  output: 1.1,
15211
- cacheRead: 0,
15656
+ cacheRead: 0.07,
15212
15657
  cacheWrite: 0,
15213
15658
  },
15214
15659
  contextWindow: 262144,
15215
- maxTokens: 16384,
15660
+ maxTokens: 235929,
15216
15661
  },
15217
15662
  "qwen/qwen3-next-80b-a3b-thinking": {
15218
15663
  id: "qwen/qwen3-next-80b-a3b-thinking",
@@ -15274,13 +15719,13 @@ export const MODELS = {
15274
15719
  reasoning: false,
15275
15720
  input: ["text", "image"],
15276
15721
  cost: {
15277
- input: 0.13,
15278
- output: 0.52,
15722
+ input: 0.15,
15723
+ output: 0.6,
15279
15724
  cacheRead: 0,
15280
15725
  cacheWrite: 0,
15281
15726
  },
15282
15727
  contextWindow: 262144,
15283
- maxTokens: 32768,
15728
+ maxTokens: 16384,
15284
15729
  },
15285
15730
  "qwen/qwen3-vl-30b-a3b-thinking": {
15286
15731
  id: "qwen/qwen3-vl-30b-a3b-thinking",
@@ -15393,13 +15838,13 @@ export const MODELS = {
15393
15838
  reasoning: true,
15394
15839
  input: ["text", "image"],
15395
15840
  cost: {
15396
- input: 0.3125,
15397
- output: 1.25,
15398
- cacheRead: 0.15625,
15841
+ input: 0.1625,
15842
+ output: 1.3,
15843
+ cacheRead: 0,
15399
15844
  cacheWrite: 0,
15400
15845
  },
15401
15846
  contextWindow: 262144,
15402
- maxTokens: 16384,
15847
+ maxTokens: 65536,
15403
15848
  },
15404
15849
  "qwen/qwen3.5-397b-a17b": {
15405
15850
  id: "qwen/qwen3.5-397b-a17b",
@@ -15496,12 +15941,12 @@ export const MODELS = {
15496
15941
  input: ["text", "image"],
15497
15942
  cost: {
15498
15943
  input: 0.32,
15499
- output: 2.7,
15500
- cacheRead: 0.15,
15944
+ output: 3.1999999999999997,
15945
+ cacheRead: 0,
15501
15946
  cacheWrite: 0,
15502
15947
  },
15503
15948
  contextWindow: 262144,
15504
- maxTokens: 262140,
15949
+ maxTokens: 81920,
15505
15950
  },
15506
15951
  "qwen/qwen3.6-35b-a3b": {
15507
15952
  id: "qwen/qwen3.6-35b-a3b",
@@ -15648,13 +16093,13 @@ export const MODELS = {
15648
16093
  reasoning: true,
15649
16094
  input: ["text", "image"],
15650
16095
  cost: {
15651
- input: 0.42,
15652
- output: 3,
15653
- cacheRead: 0.08499999999999999,
16096
+ input: 0.024900000000000002,
16097
+ output: 4.35,
16098
+ cacheRead: 0.0199,
15654
16099
  cacheWrite: 0,
15655
16100
  },
15656
16101
  contextWindow: 1000000,
15657
- maxTokens: 131072,
16102
+ maxTokens: 235929,
15658
16103
  },
15659
16104
  "qwen/qwen3.8-27b:free": {
15660
16105
  id: "qwen/qwen3.8-27b:free",
@@ -15707,6 +16152,23 @@ export const MODELS = {
15707
16152
  contextWindow: 1000000,
15708
16153
  maxTokens: 131072,
15709
16154
  },
16155
+ "qwen/qwen3.8-max-prime": {
16156
+ id: "qwen/qwen3.8-max-prime",
16157
+ name: "Qwen: Qwen3.8 Max Prime",
16158
+ api: "openai-completions",
16159
+ provider: "openrouter",
16160
+ baseUrl: "https://openrouter.ai/api/v1",
16161
+ reasoning: true,
16162
+ input: ["text", "image"],
16163
+ cost: {
16164
+ input: 4,
16165
+ output: 12,
16166
+ cacheRead: 0.5,
16167
+ cacheWrite: 0,
16168
+ },
16169
+ contextWindow: 1000000,
16170
+ maxTokens: 131072,
16171
+ },
15710
16172
  "qwen/qwen3.8-omni-flash": {
15711
16173
  id: "qwen/qwen3.8-omni-flash",
15712
16174
  name: "Qwen: Qwen3.8 Omni Flash",
@@ -15937,9 +16399,9 @@ export const MODELS = {
15937
16399
  reasoning: true,
15938
16400
  input: ["text"],
15939
16401
  cost: {
15940
- input: 0.834,
15941
- output: 2.501,
15942
- cacheRead: 0.041999999999999996,
16402
+ input: 0.7505999999999999,
16403
+ output: 2.2509,
16404
+ cacheRead: 0.0378,
15943
16405
  cacheWrite: 0,
15944
16406
  },
15945
16407
  contextWindow: 1048576,
@@ -15959,7 +16421,7 @@ export const MODELS = {
15959
16421
  cacheRead: 0.16999999999999998,
15960
16422
  cacheWrite: 0,
15961
16423
  },
15962
- contextWindow: 1048576,
16424
+ contextWindow: 524288,
15963
16425
  maxTokens: 471859,
15964
16426
  },
15965
16427
  "thinkingmachines/inkling-small": {
@@ -15976,7 +16438,7 @@ export const MODELS = {
15976
16438
  cacheRead: 0.09999999999999999,
15977
16439
  cacheWrite: 0,
15978
16440
  },
15979
- contextWindow: 1048576,
16441
+ contextWindow: 524288,
15980
16442
  maxTokens: 262144,
15981
16443
  },
15982
16444
  "thinkingmachines/inkling-small:free": {
@@ -16175,9 +16637,9 @@ export const MODELS = {
16175
16637
  reasoning: true,
16176
16638
  input: ["text", "image"],
16177
16639
  cost: {
16178
- input: 1.5999999999999999,
16179
- output: 4.8,
16180
- cacheRead: 0.39999999999999997,
16640
+ input: 2,
16641
+ output: 6,
16642
+ cacheRead: 0.5,
16181
16643
  cacheWrite: 0,
16182
16644
  },
16183
16645
  contextWindow: 500000,
@@ -16248,7 +16710,7 @@ export const MODELS = {
16248
16710
  cacheRead: 0.0028,
16249
16711
  cacheWrite: 0,
16250
16712
  },
16251
- contextWindow: 1048576,
16713
+ contextWindow: 1050000,
16252
16714
  maxTokens: 131072,
16253
16715
  },
16254
16716
  "xiaomi/mimo-v2.6-pro": {
@@ -16265,7 +16727,7 @@ export const MODELS = {
16265
16727
  cacheRead: 0.0036,
16266
16728
  cacheWrite: 0,
16267
16729
  },
16268
- contextWindow: 1048576,
16730
+ contextWindow: 1050000,
16269
16731
  maxTokens: 131072,
16270
16732
  },
16271
16733
  "xiaomi/mimo-v2.6-pro-ultraspeed": {
@@ -16379,9 +16841,9 @@ export const MODELS = {
16379
16841
  reasoning: true,
16380
16842
  input: ["text"],
16381
16843
  cost: {
16382
- input: 0.39999999999999997,
16383
- output: 1.75,
16384
- cacheRead: 0.08,
16844
+ input: 0.6,
16845
+ output: 2.2,
16846
+ cacheRead: 0.11,
16385
16847
  cacheWrite: 0,
16386
16848
  },
16387
16849
  contextWindow: 204800,
@@ -16447,13 +16909,13 @@ export const MODELS = {
16447
16909
  reasoning: true,
16448
16910
  input: ["text"],
16449
16911
  cost: {
16450
- input: 0.966,
16451
- output: 3.036,
16452
- cacheRead: 0.1794,
16912
+ input: 0.9646,
16913
+ output: 3.0316,
16914
+ cacheRead: 0.17914,
16453
16915
  cacheWrite: 0,
16454
16916
  },
16455
16917
  contextWindow: 204800,
16456
- maxTokens: 128000,
16918
+ maxTokens: 131072,
16457
16919
  },
16458
16920
  "z-ai/glm-5.2": {
16459
16921
  id: "z-ai/glm-5.2",
@@ -16464,13 +16926,13 @@ export const MODELS = {
16464
16926
  reasoning: true,
16465
16927
  input: ["text"],
16466
16928
  cost: {
16467
- input: 0.6496,
16468
- output: 2.0416,
16469
- cacheRead: 0.12064,
16929
+ input: 0.432,
16930
+ output: 3.9899999999999998,
16931
+ cacheRead: 0.26,
16470
16932
  cacheWrite: 0,
16471
16933
  },
16472
16934
  contextWindow: 1048576,
16473
- maxTokens: 131072,
16935
+ maxTokens: 943718,
16474
16936
  },
16475
16937
  "z-ai/glm-5.3": {
16476
16938
  id: "z-ai/glm-5.3",
@@ -16481,13 +16943,13 @@ export const MODELS = {
16481
16943
  reasoning: true,
16482
16944
  input: ["text"],
16483
16945
  cost: {
16484
- input: 0.84,
16485
- output: 2.64,
16486
- cacheRead: 0.156,
16946
+ input: 1.4,
16947
+ output: 4.4,
16948
+ cacheRead: 0.26,
16487
16949
  cacheWrite: 0,
16488
16950
  },
16489
- contextWindow: 1310720,
16490
- maxTokens: 131072,
16951
+ contextWindow: 1048576,
16952
+ maxTokens: 943717,
16491
16953
  },
16492
16954
  "z-ai/glm-5.3-flash": {
16493
16955
  id: "z-ai/glm-5.3-flash",
@@ -16500,11 +16962,11 @@ export const MODELS = {
16500
16962
  cost: {
16501
16963
  input: 0.15,
16502
16964
  output: 0.5,
16503
- cacheRead: 0.049999999999999996,
16965
+ cacheRead: 0.03,
16504
16966
  cacheWrite: 0,
16505
16967
  },
16506
- contextWindow: 1310720,
16507
- maxTokens: 943718,
16968
+ contextWindow: 1048576,
16969
+ maxTokens: 943717,
16508
16970
  },
16509
16971
  "z-ai/glm-5.3-flash:batch": {
16510
16972
  id: "z-ai/glm-5.3-flash:batch",
@@ -16540,6 +17002,23 @@ export const MODELS = {
16540
17002
  contextWindow: 1048576,
16541
17003
  maxTokens: 131072,
16542
17004
  },
17005
+ "z-ai/glm-5.3-prime": {
17006
+ id: "z-ai/glm-5.3-prime",
17007
+ name: "Z.ai: GLM 5.3 Prime",
17008
+ api: "openai-completions",
17009
+ provider: "openrouter",
17010
+ baseUrl: "https://openrouter.ai/api/v1",
17011
+ reasoning: true,
17012
+ input: ["text"],
17013
+ cost: {
17014
+ input: 2.8,
17015
+ output: 8.8,
17016
+ cacheRead: 0.56,
17017
+ cacheWrite: 0,
17018
+ },
17019
+ contextWindow: 1000000,
17020
+ maxTokens: 131072,
17021
+ },
16543
17022
  "z-ai/glm-5.3:batch": {
16544
17023
  id: "z-ai/glm-5.3:batch",
16545
17024
  name: "Z.ai: GLM 5.3 (batch)",
@@ -16651,9 +17130,9 @@ export const MODELS = {
16651
17130
  reasoning: true,
16652
17131
  input: ["text", "image"],
16653
17132
  cost: {
16654
- input: 0.09999999999999999,
16655
- output: 0.5,
16656
- cacheRead: 0.01,
17133
+ input: 0.019799999999999998,
17134
+ output: 0.396,
17135
+ cacheRead: 0.0029100000000000003,
16657
17136
  cacheWrite: 0,
16658
17137
  },
16659
17138
  contextWindow: 1048576,
@@ -16668,13 +17147,13 @@ export const MODELS = {
16668
17147
  reasoning: true,
16669
17148
  input: ["text"],
16670
17149
  cost: {
16671
- input: 0.39499999999999996,
16672
- output: 2.9000000000000004,
16673
- cacheRead: 0.25,
17150
+ input: 0.123,
17151
+ output: 3.5,
17152
+ cacheRead: 0.123,
16674
17153
  cacheWrite: 0,
16675
17154
  },
16676
17155
  contextWindow: 1048576,
16677
- maxTokens: 943718,
17156
+ maxTokens: 393216,
16678
17157
  },
16679
17158
  "~deepseek/deepseek-v4-flash-latest": {
16680
17159
  id: "~deepseek/deepseek-v4-flash-latest",
@@ -16685,12 +17164,12 @@ export const MODELS = {
16685
17164
  reasoning: true,
16686
17165
  input: ["text"],
16687
17166
  cost: {
16688
- input: 0.038000000000000006,
16689
- output: 0.55,
16690
- cacheRead: 0.022799999999999997,
17167
+ input: 0.009899999999999999,
17168
+ output: 0.13068,
17169
+ cacheRead: 0.0013859999999999999,
16691
17170
  cacheWrite: 0,
16692
17171
  },
16693
- contextWindow: 1310720,
17172
+ contextWindow: 1048576,
16694
17173
  maxTokens: 943718,
16695
17174
  },
16696
17175
  "~google/gemini-flash-latest": {
@@ -16736,9 +17215,9 @@ export const MODELS = {
16736
17215
  reasoning: true,
16737
17216
  input: ["text", "image"],
16738
17217
  cost: {
16739
- input: 1.4989,
16740
- output: 10.758,
16741
- cacheRead: 0.3,
17218
+ input: 0.29,
17219
+ output: 11,
17220
+ cacheRead: 0.28,
16742
17221
  cacheWrite: 0,
16743
17222
  },
16744
17223
  contextWindow: 1048576,
@@ -16806,7 +17285,7 @@ export const MODELS = {
16806
17285
  cost: {
16807
17286
  input: 2,
16808
17287
  output: 10,
16809
- cacheRead: 0.19999999999999998,
17288
+ cacheRead: 0.09999999999999999,
16810
17289
  cacheWrite: 2.5,
16811
17290
  },
16812
17291
  contextWindow: 1050000,
@@ -16838,9 +17317,9 @@ export const MODELS = {
16838
17317
  reasoning: true,
16839
17318
  input: ["text", "image"],
16840
17319
  cost: {
16841
- input: 1.5999999999999999,
16842
- output: 4.8,
16843
- cacheRead: 0.39999999999999997,
17320
+ input: 2,
17321
+ output: 6,
17322
+ cacheRead: 0.5,
16844
17323
  cacheWrite: 0,
16845
17324
  },
16846
17325
  contextWindow: 500000,
@@ -16855,13 +17334,13 @@ export const MODELS = {
16855
17334
  reasoning: true,
16856
17335
  input: ["text", "image"],
16857
17336
  cost: {
16858
- input: 0.075,
16859
- output: 0.25,
16860
- cacheRead: 0.015,
17337
+ input: 0.02,
17338
+ output: 0.24750000000000003,
17339
+ cacheRead: 0.01,
16861
17340
  cacheWrite: 0,
16862
17341
  },
16863
- contextWindow: 1310720,
16864
- maxTokens: 131072,
17342
+ contextWindow: 1048576,
17343
+ maxTokens: 943718,
16865
17344
  },
16866
17345
  "~z-ai/glm-latest": {
16867
17346
  id: "~z-ai/glm-latest",
@@ -16872,12 +17351,12 @@ export const MODELS = {
16872
17351
  reasoning: true,
16873
17352
  input: ["text"],
16874
17353
  cost: {
16875
- input: 0.5614,
16876
- output: 1.7644,
16877
- cacheRead: 0.10425999999999999,
17354
+ input: 0.13,
17355
+ output: 4,
17356
+ cacheRead: 0.13,
16878
17357
  cacheWrite: 0,
16879
17358
  },
16880
- contextWindow: 1310720,
17359
+ contextWindow: 1048576,
16881
17360
  maxTokens: 131072,
16882
17361
  },
16883
17362
  },
@@ -17215,7 +17694,7 @@ export const MODELS = {
17215
17694
  input: ["text", "image"],
17216
17695
  cost: {
17217
17696
  input: 0.39999999999999997,
17218
- output: 2.5,
17697
+ output: 2.4,
17219
17698
  cacheRead: 0.04,
17220
17699
  cacheWrite: 0.5,
17221
17700
  },
@@ -17392,6 +17871,23 @@ export const MODELS = {
17392
17871
  contextWindow: 991000,
17393
17872
  maxTokens: 128000,
17394
17873
  },
17874
+ "alibaba/qwen3.8-max-prime": {
17875
+ id: "alibaba/qwen3.8-max-prime",
17876
+ name: "Qwen 3.8 Max Prime",
17877
+ api: "anthropic-messages",
17878
+ provider: "vercel-ai-gateway",
17879
+ baseUrl: "https://ai-gateway.vercel.sh",
17880
+ reasoning: true,
17881
+ input: ["text", "image"],
17882
+ cost: {
17883
+ input: 4,
17884
+ output: 12,
17885
+ cacheRead: 0.5,
17886
+ cacheWrite: 5,
17887
+ },
17888
+ contextWindow: 1000000,
17889
+ maxTokens: 131072,
17890
+ },
17395
17891
  "alibaba/qwen3.8-omni-flash": {
17396
17892
  id: "alibaba/qwen3.8-omni-flash",
17397
17893
  name: "Qwen 3.8 Omni Flash",
@@ -17783,6 +18279,23 @@ export const MODELS = {
17783
18279
  contextWindow: 1000000,
17784
18280
  maxTokens: 128000,
17785
18281
  },
18282
+ "anthropic/claude-sonnet-5.5": {
18283
+ id: "anthropic/claude-sonnet-5.5",
18284
+ name: "Claude Sonnet 5.5",
18285
+ api: "anthropic-messages",
18286
+ provider: "vercel-ai-gateway",
18287
+ baseUrl: "https://ai-gateway.vercel.sh",
18288
+ reasoning: true,
18289
+ input: ["text", "image"],
18290
+ cost: {
18291
+ input: 2,
18292
+ output: 10,
18293
+ cacheRead: 0.19999999999999998,
18294
+ cacheWrite: 2.5,
18295
+ },
18296
+ contextWindow: 1000000,
18297
+ maxTokens: 128000,
18298
+ },
17786
18299
  "arcee-ai/trinity-large-thinking": {
17787
18300
  id: "arcee-ai/trinity-large-thinking",
17788
18301
  name: "Trinity Large Thinking",
@@ -17996,9 +18509,9 @@ export const MODELS = {
17996
18509
  reasoning: true,
17997
18510
  input: ["text", "image"],
17998
18511
  cost: {
17999
- input: 0.22,
18000
- output: 0.66,
18001
- cacheRead: 0.007,
18512
+ input: 0.21559999999999999,
18513
+ output: 0.6468,
18514
+ cacheRead: 0.0068,
18002
18515
  cacheWrite: 0,
18003
18516
  },
18004
18517
  contextWindow: 1048576,
@@ -18055,6 +18568,23 @@ export const MODELS = {
18055
18568
  contextWindow: 1048576,
18056
18569
  maxTokens: 32768,
18057
18570
  },
18571
+ "fireworks/ember-1": {
18572
+ id: "fireworks/ember-1",
18573
+ name: "Ember-1",
18574
+ api: "anthropic-messages",
18575
+ provider: "vercel-ai-gateway",
18576
+ baseUrl: "https://ai-gateway.vercel.sh",
18577
+ reasoning: true,
18578
+ input: ["text", "image"],
18579
+ cost: {
18580
+ input: 3,
18581
+ output: 15,
18582
+ cacheRead: 0.3,
18583
+ cacheWrite: 0,
18584
+ },
18585
+ contextWindow: 1048576,
18586
+ maxTokens: 1048576,
18587
+ },
18058
18588
  "google/gemini-2.5-flash": {
18059
18589
  id: "google/gemini-2.5-flash",
18060
18590
  name: "Gemini 2.5 Flash",
@@ -18353,26 +18883,9 @@ export const MODELS = {
18353
18883
  reasoning: true,
18354
18884
  input: ["text"],
18355
18885
  cost: {
18356
- input: 0,
18357
- output: 0,
18358
- cacheRead: 0,
18359
- cacheWrite: 0,
18360
- },
18361
- contextWindow: 256000,
18362
- maxTokens: 32000,
18363
- },
18364
- "inclusionai/ling-3.0-flash-fin-free": {
18365
- id: "inclusionai/ling-3.0-flash-fin-free",
18366
- name: "Ling 3.0 Flash Fin (Free)",
18367
- api: "anthropic-messages",
18368
- provider: "vercel-ai-gateway",
18369
- baseUrl: "https://ai-gateway.vercel.sh",
18370
- reasoning: true,
18371
- input: ["text"],
18372
- cost: {
18373
- input: 0,
18374
- output: 0,
18375
- cacheRead: 0,
18886
+ input: 0.075,
18887
+ output: 0.22,
18888
+ cacheRead: 0.015,
18376
18889
  cacheWrite: 0,
18377
18890
  },
18378
18891
  contextWindow: 256000,
@@ -18422,13 +18935,47 @@ export const MODELS = {
18422
18935
  input: ["text", "image"],
18423
18936
  cost: {
18424
18937
  input: 0.075,
18425
- output: 0.015,
18426
- cacheRead: 0.22,
18938
+ output: 0.22,
18939
+ cacheRead: 0.015,
18427
18940
  cacheWrite: 0,
18428
18941
  },
18429
18942
  contextWindow: 256000,
18430
18943
  maxTokens: 32000,
18431
18944
  },
18945
+ "inclusionai/ling-3.1-flash": {
18946
+ id: "inclusionai/ling-3.1-flash",
18947
+ name: "Ling 3.1 Flash",
18948
+ api: "anthropic-messages",
18949
+ provider: "vercel-ai-gateway",
18950
+ baseUrl: "https://ai-gateway.vercel.sh",
18951
+ reasoning: true,
18952
+ input: ["text"],
18953
+ cost: {
18954
+ input: 0,
18955
+ output: 0,
18956
+ cacheRead: 0,
18957
+ cacheWrite: 0,
18958
+ },
18959
+ contextWindow: 262144,
18960
+ maxTokens: 32768,
18961
+ },
18962
+ "inclusionai/ling-3.1-flash-free": {
18963
+ id: "inclusionai/ling-3.1-flash-free",
18964
+ name: "Ling 3.1 Flash (Free)",
18965
+ api: "anthropic-messages",
18966
+ provider: "vercel-ai-gateway",
18967
+ baseUrl: "https://ai-gateway.vercel.sh",
18968
+ reasoning: true,
18969
+ input: ["text"],
18970
+ cost: {
18971
+ input: 0,
18972
+ output: 0,
18973
+ cacheRead: 0,
18974
+ cacheWrite: 0,
18975
+ },
18976
+ contextWindow: 262144,
18977
+ maxTokens: 32768,
18978
+ },
18432
18979
  "interfaze/interfaze-beta": {
18433
18980
  id: "interfaze/interfaze-beta",
18434
18981
  name: "Interfaze Beta",
@@ -18446,6 +18993,23 @@ export const MODELS = {
18446
18993
  contextWindow: 1000000,
18447
18994
  maxTokens: 32000,
18448
18995
  },
18996
+ "meituan/longcat-2.5-preview": {
18997
+ id: "meituan/longcat-2.5-preview",
18998
+ name: "LongCat 2.5 Preview",
18999
+ api: "anthropic-messages",
19000
+ provider: "vercel-ai-gateway",
19001
+ baseUrl: "https://ai-gateway.vercel.sh",
19002
+ reasoning: true,
19003
+ input: ["text", "image"],
19004
+ cost: {
19005
+ input: 0.3,
19006
+ output: 1.2,
19007
+ cacheRead: 0.006,
19008
+ cacheWrite: 0,
19009
+ },
19010
+ contextWindow: 1048576,
19011
+ maxTokens: 131072,
19012
+ },
18449
19013
  "meta/llama-3.1-70b": {
18450
19014
  id: "meta/llama-3.1-70b",
18451
19015
  name: "Llama 3.1 70B Instruct",
@@ -19001,7 +19565,7 @@ export const MODELS = {
19001
19565
  cost: {
19002
19566
  input: 0.95,
19003
19567
  output: 4,
19004
- cacheRead: 0.16,
19568
+ cacheRead: 0.19,
19005
19569
  cacheWrite: 0,
19006
19570
  },
19007
19571
  contextWindow: 256000,
@@ -20027,6 +20591,40 @@ export const MODELS = {
20027
20591
  contextWindow: 1050000,
20028
20592
  maxTokens: 128000,
20029
20593
  },
20594
+ "openai/gpt-6.1-sol": {
20595
+ id: "openai/gpt-6.1-sol",
20596
+ name: "GPT-6.1 Sol",
20597
+ api: "anthropic-messages",
20598
+ provider: "vercel-ai-gateway",
20599
+ baseUrl: "https://ai-gateway.vercel.sh",
20600
+ reasoning: true,
20601
+ input: ["text", "image"],
20602
+ cost: {
20603
+ input: 2,
20604
+ output: 10,
20605
+ cacheRead: 0.09999999999999999,
20606
+ cacheWrite: 2.5,
20607
+ },
20608
+ contextWindow: 1050000,
20609
+ maxTokens: 128000,
20610
+ },
20611
+ "openai/gpt-6.1-sol-fast": {
20612
+ id: "openai/gpt-6.1-sol-fast",
20613
+ name: "GPT-6.1 Sol (Fast)",
20614
+ api: "anthropic-messages",
20615
+ provider: "vercel-ai-gateway",
20616
+ baseUrl: "https://ai-gateway.vercel.sh",
20617
+ reasoning: true,
20618
+ input: ["text", "image"],
20619
+ cost: {
20620
+ input: 4,
20621
+ output: 20,
20622
+ cacheRead: 0.19999999999999998,
20623
+ cacheWrite: 5,
20624
+ },
20625
+ contextWindow: 1050000,
20626
+ maxTokens: 128000,
20627
+ },
20030
20628
  "openai/gpt-oss-120b": {
20031
20629
  id: "openai/gpt-oss-120b",
20032
20630
  name: "GPT OSS 120B",
@@ -20546,9 +21144,9 @@ export const MODELS = {
20546
21144
  reasoning: true,
20547
21145
  input: ["text", "image"],
20548
21146
  cost: {
20549
- input: 1.2,
20550
- output: 3.5999999999999996,
20551
- cacheRead: 0.3,
21147
+ input: 2,
21148
+ output: 6,
21149
+ cacheRead: 0.5,
20552
21150
  cacheWrite: 0,
20553
21151
  },
20554
21152
  contextWindow: 500000,
@@ -20665,7 +21263,7 @@ export const MODELS = {
20665
21263
  reasoning: true,
20666
21264
  input: ["text", "image"],
20667
21265
  cost: {
20668
- input: 0.5,
21266
+ input: 0.44999999999999996,
20669
21267
  output: 1.2,
20670
21268
  cacheRead: 0.09999999999999999,
20671
21269
  cacheWrite: 0,
@@ -20837,7 +21435,7 @@ export const MODELS = {
20837
21435
  cost: {
20838
21436
  input: 0.6,
20839
21437
  output: 2.2,
20840
- cacheRead: 0.12,
21438
+ cacheRead: 0,
20841
21439
  cacheWrite: 0,
20842
21440
  },
20843
21441
  contextWindow: 200000,
@@ -20954,9 +21552,9 @@ export const MODELS = {
20954
21552
  reasoning: true,
20955
21553
  input: ["text"],
20956
21554
  cost: {
20957
- input: 2.0999999999999996,
20958
- output: 6.6000000000000005,
20959
- cacheRead: 0.21,
21555
+ input: 2.8,
21556
+ output: 8.8,
21557
+ cacheRead: 0.56,
20960
21558
  cacheWrite: 0,
20961
21559
  },
20962
21560
  contextWindow: 1000000,