@openachieve/ai 0.78.0 → 0.79.1

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.
@@ -1110,6 +1110,63 @@ export declare const MODELS: {
1110
1110
  contextWindow: number;
1111
1111
  maxTokens: number;
1112
1112
  };
1113
+ readonly "openai.gpt-5.4": {
1114
+ id: string;
1115
+ name: string;
1116
+ api: "bedrock-converse-stream";
1117
+ provider: string;
1118
+ baseUrl: string;
1119
+ reasoning: true;
1120
+ thinkingLevelMap: {
1121
+ xhigh: string;
1122
+ };
1123
+ input: ("image" | "text")[];
1124
+ cost: {
1125
+ input: number;
1126
+ output: number;
1127
+ cacheRead: number;
1128
+ cacheWrite: number;
1129
+ };
1130
+ contextWindow: number;
1131
+ maxTokens: number;
1132
+ };
1133
+ readonly "openai.gpt-5.5": {
1134
+ id: string;
1135
+ name: string;
1136
+ api: "bedrock-converse-stream";
1137
+ provider: string;
1138
+ baseUrl: string;
1139
+ reasoning: true;
1140
+ thinkingLevelMap: {
1141
+ xhigh: string;
1142
+ };
1143
+ input: ("image" | "text")[];
1144
+ cost: {
1145
+ input: number;
1146
+ output: number;
1147
+ cacheRead: number;
1148
+ cacheWrite: number;
1149
+ };
1150
+ contextWindow: number;
1151
+ maxTokens: number;
1152
+ };
1153
+ readonly "openai.gpt-oss-120b": {
1154
+ id: string;
1155
+ name: string;
1156
+ api: "bedrock-converse-stream";
1157
+ provider: string;
1158
+ baseUrl: string;
1159
+ reasoning: false;
1160
+ input: "text"[];
1161
+ cost: {
1162
+ input: number;
1163
+ output: number;
1164
+ cacheRead: number;
1165
+ cacheWrite: number;
1166
+ };
1167
+ contextWindow: number;
1168
+ maxTokens: number;
1169
+ };
1113
1170
  readonly "openai.gpt-oss-120b-1:0": {
1114
1171
  id: string;
1115
1172
  name: string;
@@ -1127,6 +1184,23 @@ export declare const MODELS: {
1127
1184
  contextWindow: number;
1128
1185
  maxTokens: number;
1129
1186
  };
1187
+ readonly "openai.gpt-oss-20b": {
1188
+ id: string;
1189
+ name: string;
1190
+ api: "bedrock-converse-stream";
1191
+ provider: string;
1192
+ baseUrl: string;
1193
+ reasoning: false;
1194
+ input: "text"[];
1195
+ cost: {
1196
+ input: number;
1197
+ output: number;
1198
+ cacheRead: number;
1199
+ cacheWrite: number;
1200
+ };
1201
+ contextWindow: number;
1202
+ maxTokens: number;
1203
+ };
1130
1204
  readonly "openai.gpt-oss-20b-1:0": {
1131
1205
  id: string;
1132
1206
  name: string;
@@ -4160,6 +4234,29 @@ export declare const MODELS: {
4160
4234
  contextWindow: number;
4161
4235
  maxTokens: number;
4162
4236
  };
4237
+ readonly "accounts/fireworks/routers/kimi-k2p6-fast": {
4238
+ id: string;
4239
+ name: string;
4240
+ api: "anthropic-messages";
4241
+ provider: string;
4242
+ baseUrl: string;
4243
+ compat: {
4244
+ sendSessionAffinityHeaders: true;
4245
+ supportsEagerToolInputStreaming: false;
4246
+ supportsCacheControlOnTools: false;
4247
+ supportsLongCacheRetention: false;
4248
+ };
4249
+ reasoning: true;
4250
+ input: ("image" | "text")[];
4251
+ cost: {
4252
+ input: number;
4253
+ output: number;
4254
+ cacheRead: number;
4255
+ cacheWrite: number;
4256
+ };
4257
+ contextWindow: number;
4258
+ maxTokens: number;
4259
+ };
4163
4260
  readonly "accounts/fireworks/routers/kimi-k2p6-turbo": {
4164
4261
  id: string;
4165
4262
  name: string;
@@ -6595,7 +6692,7 @@ export declare const MODELS: {
6595
6692
  api: "mistral-conversations";
6596
6693
  provider: string;
6597
6694
  baseUrl: string;
6598
- reasoning: true;
6695
+ reasoning: false;
6599
6696
  input: ("image" | "text")[];
6600
6697
  cost: {
6601
6698
  input: number;
@@ -6802,18 +6899,450 @@ export declare const MODELS: {
6802
6899
  contextWindow: number;
6803
6900
  maxTokens: number;
6804
6901
  };
6805
- readonly "kimi-k2-0905-preview": {
6902
+ readonly "kimi-k2-0905-preview": {
6903
+ id: string;
6904
+ name: string;
6905
+ api: "openai-completions";
6906
+ provider: string;
6907
+ baseUrl: string;
6908
+ compat: {
6909
+ supportsStore: false;
6910
+ supportsDeveloperRole: false;
6911
+ supportsReasoningEffort: false;
6912
+ maxTokensField: "max_tokens";
6913
+ supportsStrictMode: false;
6914
+ };
6915
+ reasoning: false;
6916
+ input: "text"[];
6917
+ cost: {
6918
+ input: number;
6919
+ output: number;
6920
+ cacheRead: number;
6921
+ cacheWrite: number;
6922
+ };
6923
+ contextWindow: number;
6924
+ maxTokens: number;
6925
+ };
6926
+ readonly "kimi-k2-thinking": {
6927
+ id: string;
6928
+ name: string;
6929
+ api: "openai-completions";
6930
+ provider: string;
6931
+ baseUrl: string;
6932
+ compat: {
6933
+ supportsStore: false;
6934
+ supportsDeveloperRole: false;
6935
+ supportsReasoningEffort: false;
6936
+ maxTokensField: "max_tokens";
6937
+ supportsStrictMode: false;
6938
+ };
6939
+ reasoning: true;
6940
+ input: "text"[];
6941
+ cost: {
6942
+ input: number;
6943
+ output: number;
6944
+ cacheRead: number;
6945
+ cacheWrite: number;
6946
+ };
6947
+ contextWindow: number;
6948
+ maxTokens: number;
6949
+ };
6950
+ readonly "kimi-k2-thinking-turbo": {
6951
+ id: string;
6952
+ name: string;
6953
+ api: "openai-completions";
6954
+ provider: string;
6955
+ baseUrl: string;
6956
+ compat: {
6957
+ supportsStore: false;
6958
+ supportsDeveloperRole: false;
6959
+ supportsReasoningEffort: false;
6960
+ maxTokensField: "max_tokens";
6961
+ supportsStrictMode: false;
6962
+ };
6963
+ reasoning: true;
6964
+ input: "text"[];
6965
+ cost: {
6966
+ input: number;
6967
+ output: number;
6968
+ cacheRead: number;
6969
+ cacheWrite: number;
6970
+ };
6971
+ contextWindow: number;
6972
+ maxTokens: number;
6973
+ };
6974
+ readonly "kimi-k2-turbo-preview": {
6975
+ id: string;
6976
+ name: string;
6977
+ api: "openai-completions";
6978
+ provider: string;
6979
+ baseUrl: string;
6980
+ compat: {
6981
+ supportsStore: false;
6982
+ supportsDeveloperRole: false;
6983
+ supportsReasoningEffort: false;
6984
+ maxTokensField: "max_tokens";
6985
+ supportsStrictMode: false;
6986
+ };
6987
+ reasoning: false;
6988
+ input: "text"[];
6989
+ cost: {
6990
+ input: number;
6991
+ output: number;
6992
+ cacheRead: number;
6993
+ cacheWrite: number;
6994
+ };
6995
+ contextWindow: number;
6996
+ maxTokens: number;
6997
+ };
6998
+ readonly "kimi-k2.5": {
6999
+ id: string;
7000
+ name: string;
7001
+ api: "openai-completions";
7002
+ provider: string;
7003
+ baseUrl: string;
7004
+ compat: {
7005
+ supportsStore: false;
7006
+ supportsDeveloperRole: false;
7007
+ supportsReasoningEffort: false;
7008
+ maxTokensField: "max_tokens";
7009
+ supportsStrictMode: false;
7010
+ };
7011
+ reasoning: true;
7012
+ input: ("image" | "text")[];
7013
+ cost: {
7014
+ input: number;
7015
+ output: number;
7016
+ cacheRead: number;
7017
+ cacheWrite: number;
7018
+ };
7019
+ contextWindow: number;
7020
+ maxTokens: number;
7021
+ };
7022
+ readonly "kimi-k2.6": {
7023
+ id: string;
7024
+ name: string;
7025
+ api: "openai-completions";
7026
+ provider: string;
7027
+ baseUrl: string;
7028
+ compat: {
7029
+ supportsStore: false;
7030
+ supportsDeveloperRole: false;
7031
+ supportsReasoningEffort: false;
7032
+ maxTokensField: "max_tokens";
7033
+ supportsStrictMode: false;
7034
+ };
7035
+ reasoning: true;
7036
+ input: ("image" | "text")[];
7037
+ cost: {
7038
+ input: number;
7039
+ output: number;
7040
+ cacheRead: number;
7041
+ cacheWrite: number;
7042
+ };
7043
+ contextWindow: number;
7044
+ maxTokens: number;
7045
+ };
7046
+ };
7047
+ readonly "moonshotai-cn": {
7048
+ readonly "kimi-k2-0711-preview": {
7049
+ id: string;
7050
+ name: string;
7051
+ api: "openai-completions";
7052
+ provider: string;
7053
+ baseUrl: string;
7054
+ compat: {
7055
+ supportsStore: false;
7056
+ supportsDeveloperRole: false;
7057
+ supportsReasoningEffort: false;
7058
+ maxTokensField: "max_tokens";
7059
+ supportsStrictMode: false;
7060
+ };
7061
+ reasoning: false;
7062
+ input: "text"[];
7063
+ cost: {
7064
+ input: number;
7065
+ output: number;
7066
+ cacheRead: number;
7067
+ cacheWrite: number;
7068
+ };
7069
+ contextWindow: number;
7070
+ maxTokens: number;
7071
+ };
7072
+ readonly "kimi-k2-0905-preview": {
7073
+ id: string;
7074
+ name: string;
7075
+ api: "openai-completions";
7076
+ provider: string;
7077
+ baseUrl: string;
7078
+ compat: {
7079
+ supportsStore: false;
7080
+ supportsDeveloperRole: false;
7081
+ supportsReasoningEffort: false;
7082
+ maxTokensField: "max_tokens";
7083
+ supportsStrictMode: false;
7084
+ };
7085
+ reasoning: false;
7086
+ input: "text"[];
7087
+ cost: {
7088
+ input: number;
7089
+ output: number;
7090
+ cacheRead: number;
7091
+ cacheWrite: number;
7092
+ };
7093
+ contextWindow: number;
7094
+ maxTokens: number;
7095
+ };
7096
+ readonly "kimi-k2-thinking": {
7097
+ id: string;
7098
+ name: string;
7099
+ api: "openai-completions";
7100
+ provider: string;
7101
+ baseUrl: string;
7102
+ compat: {
7103
+ supportsStore: false;
7104
+ supportsDeveloperRole: false;
7105
+ supportsReasoningEffort: false;
7106
+ maxTokensField: "max_tokens";
7107
+ supportsStrictMode: false;
7108
+ };
7109
+ reasoning: true;
7110
+ input: "text"[];
7111
+ cost: {
7112
+ input: number;
7113
+ output: number;
7114
+ cacheRead: number;
7115
+ cacheWrite: number;
7116
+ };
7117
+ contextWindow: number;
7118
+ maxTokens: number;
7119
+ };
7120
+ readonly "kimi-k2-thinking-turbo": {
7121
+ id: string;
7122
+ name: string;
7123
+ api: "openai-completions";
7124
+ provider: string;
7125
+ baseUrl: string;
7126
+ compat: {
7127
+ supportsStore: false;
7128
+ supportsDeveloperRole: false;
7129
+ supportsReasoningEffort: false;
7130
+ maxTokensField: "max_tokens";
7131
+ supportsStrictMode: false;
7132
+ };
7133
+ reasoning: true;
7134
+ input: "text"[];
7135
+ cost: {
7136
+ input: number;
7137
+ output: number;
7138
+ cacheRead: number;
7139
+ cacheWrite: number;
7140
+ };
7141
+ contextWindow: number;
7142
+ maxTokens: number;
7143
+ };
7144
+ readonly "kimi-k2-turbo-preview": {
7145
+ id: string;
7146
+ name: string;
7147
+ api: "openai-completions";
7148
+ provider: string;
7149
+ baseUrl: string;
7150
+ compat: {
7151
+ supportsStore: false;
7152
+ supportsDeveloperRole: false;
7153
+ supportsReasoningEffort: false;
7154
+ maxTokensField: "max_tokens";
7155
+ supportsStrictMode: false;
7156
+ };
7157
+ reasoning: false;
7158
+ input: "text"[];
7159
+ cost: {
7160
+ input: number;
7161
+ output: number;
7162
+ cacheRead: number;
7163
+ cacheWrite: number;
7164
+ };
7165
+ contextWindow: number;
7166
+ maxTokens: number;
7167
+ };
7168
+ readonly "kimi-k2.5": {
7169
+ id: string;
7170
+ name: string;
7171
+ api: "openai-completions";
7172
+ provider: string;
7173
+ baseUrl: string;
7174
+ compat: {
7175
+ supportsStore: false;
7176
+ supportsDeveloperRole: false;
7177
+ supportsReasoningEffort: false;
7178
+ maxTokensField: "max_tokens";
7179
+ supportsStrictMode: false;
7180
+ };
7181
+ reasoning: true;
7182
+ input: ("image" | "text")[];
7183
+ cost: {
7184
+ input: number;
7185
+ output: number;
7186
+ cacheRead: number;
7187
+ cacheWrite: number;
7188
+ };
7189
+ contextWindow: number;
7190
+ maxTokens: number;
7191
+ };
7192
+ readonly "kimi-k2.6": {
7193
+ id: string;
7194
+ name: string;
7195
+ api: "openai-completions";
7196
+ provider: string;
7197
+ baseUrl: string;
7198
+ compat: {
7199
+ supportsStore: false;
7200
+ supportsDeveloperRole: false;
7201
+ supportsReasoningEffort: false;
7202
+ maxTokensField: "max_tokens";
7203
+ supportsStrictMode: false;
7204
+ };
7205
+ reasoning: true;
7206
+ input: ("image" | "text")[];
7207
+ cost: {
7208
+ input: number;
7209
+ output: number;
7210
+ cacheRead: number;
7211
+ cacheWrite: number;
7212
+ };
7213
+ contextWindow: number;
7214
+ maxTokens: number;
7215
+ };
7216
+ };
7217
+ readonly nvidia: {
7218
+ readonly "abacusai/dracarys-llama-3_1-70b-instruct": {
7219
+ id: string;
7220
+ name: string;
7221
+ api: "openai-completions";
7222
+ provider: string;
7223
+ baseUrl: string;
7224
+ headers: {
7225
+ "NVCF-POLL-SECONDS": string;
7226
+ };
7227
+ compat: {
7228
+ supportsStore: false;
7229
+ supportsDeveloperRole: false;
7230
+ supportsReasoningEffort: false;
7231
+ maxTokensField: "max_tokens";
7232
+ supportsStrictMode: false;
7233
+ supportsLongCacheRetention: false;
7234
+ };
7235
+ reasoning: false;
7236
+ input: "text"[];
7237
+ cost: {
7238
+ input: number;
7239
+ output: number;
7240
+ cacheRead: number;
7241
+ cacheWrite: number;
7242
+ };
7243
+ contextWindow: number;
7244
+ maxTokens: number;
7245
+ };
7246
+ readonly "deepseek-ai/deepseek-v3.1-terminus": {
7247
+ id: string;
7248
+ name: string;
7249
+ api: "openai-completions";
7250
+ provider: string;
7251
+ baseUrl: string;
7252
+ headers: {
7253
+ "NVCF-POLL-SECONDS": string;
7254
+ };
7255
+ compat: {
7256
+ supportsStore: false;
7257
+ supportsDeveloperRole: false;
7258
+ supportsReasoningEffort: false;
7259
+ maxTokensField: "max_tokens";
7260
+ supportsStrictMode: false;
7261
+ supportsLongCacheRetention: false;
7262
+ };
7263
+ reasoning: true;
7264
+ input: "text"[];
7265
+ cost: {
7266
+ input: number;
7267
+ output: number;
7268
+ cacheRead: number;
7269
+ cacheWrite: number;
7270
+ };
7271
+ contextWindow: number;
7272
+ maxTokens: number;
7273
+ };
7274
+ readonly "deepseek-ai/deepseek-v3.2": {
7275
+ id: string;
7276
+ name: string;
7277
+ api: "openai-completions";
7278
+ provider: string;
7279
+ baseUrl: string;
7280
+ headers: {
7281
+ "NVCF-POLL-SECONDS": string;
7282
+ };
7283
+ compat: {
7284
+ supportsStore: false;
7285
+ supportsDeveloperRole: false;
7286
+ supportsReasoningEffort: false;
7287
+ maxTokensField: "max_tokens";
7288
+ supportsStrictMode: false;
7289
+ supportsLongCacheRetention: false;
7290
+ };
7291
+ reasoning: true;
7292
+ input: "text"[];
7293
+ cost: {
7294
+ input: number;
7295
+ output: number;
7296
+ cacheRead: number;
7297
+ cacheWrite: number;
7298
+ };
7299
+ contextWindow: number;
7300
+ maxTokens: number;
7301
+ };
7302
+ readonly "google/gemma-3-27b-it": {
7303
+ id: string;
7304
+ name: string;
7305
+ api: "openai-completions";
7306
+ provider: string;
7307
+ baseUrl: string;
7308
+ headers: {
7309
+ "NVCF-POLL-SECONDS": string;
7310
+ };
7311
+ compat: {
7312
+ supportsStore: false;
7313
+ supportsDeveloperRole: false;
7314
+ supportsReasoningEffort: false;
7315
+ maxTokensField: "max_tokens";
7316
+ supportsStrictMode: false;
7317
+ supportsLongCacheRetention: false;
7318
+ };
7319
+ reasoning: true;
7320
+ input: ("image" | "text")[];
7321
+ cost: {
7322
+ input: number;
7323
+ output: number;
7324
+ cacheRead: number;
7325
+ cacheWrite: number;
7326
+ };
7327
+ contextWindow: number;
7328
+ maxTokens: number;
7329
+ };
7330
+ readonly "meta/llama-3.1-70b-instruct": {
6806
7331
  id: string;
6807
7332
  name: string;
6808
7333
  api: "openai-completions";
6809
7334
  provider: string;
6810
7335
  baseUrl: string;
7336
+ headers: {
7337
+ "NVCF-POLL-SECONDS": string;
7338
+ };
6811
7339
  compat: {
6812
7340
  supportsStore: false;
6813
7341
  supportsDeveloperRole: false;
6814
7342
  supportsReasoningEffort: false;
6815
7343
  maxTokensField: "max_tokens";
6816
7344
  supportsStrictMode: false;
7345
+ supportsLongCacheRetention: false;
6817
7346
  };
6818
7347
  reasoning: false;
6819
7348
  input: "text"[];
@@ -6826,20 +7355,24 @@ export declare const MODELS: {
6826
7355
  contextWindow: number;
6827
7356
  maxTokens: number;
6828
7357
  };
6829
- readonly "kimi-k2-thinking": {
7358
+ readonly "meta/llama-3.1-8b-instruct": {
6830
7359
  id: string;
6831
7360
  name: string;
6832
7361
  api: "openai-completions";
6833
7362
  provider: string;
6834
7363
  baseUrl: string;
7364
+ headers: {
7365
+ "NVCF-POLL-SECONDS": string;
7366
+ };
6835
7367
  compat: {
6836
7368
  supportsStore: false;
6837
7369
  supportsDeveloperRole: false;
6838
7370
  supportsReasoningEffort: false;
6839
7371
  maxTokensField: "max_tokens";
6840
7372
  supportsStrictMode: false;
7373
+ supportsLongCacheRetention: false;
6841
7374
  };
6842
- reasoning: true;
7375
+ reasoning: false;
6843
7376
  input: "text"[];
6844
7377
  cost: {
6845
7378
  input: number;
@@ -6850,21 +7383,25 @@ export declare const MODELS: {
6850
7383
  contextWindow: number;
6851
7384
  maxTokens: number;
6852
7385
  };
6853
- readonly "kimi-k2-thinking-turbo": {
7386
+ readonly "meta/llama-3.2-11b-vision-instruct": {
6854
7387
  id: string;
6855
7388
  name: string;
6856
7389
  api: "openai-completions";
6857
7390
  provider: string;
6858
7391
  baseUrl: string;
7392
+ headers: {
7393
+ "NVCF-POLL-SECONDS": string;
7394
+ };
6859
7395
  compat: {
6860
7396
  supportsStore: false;
6861
7397
  supportsDeveloperRole: false;
6862
7398
  supportsReasoningEffort: false;
6863
7399
  maxTokensField: "max_tokens";
6864
7400
  supportsStrictMode: false;
7401
+ supportsLongCacheRetention: false;
6865
7402
  };
6866
- reasoning: true;
6867
- input: "text"[];
7403
+ reasoning: false;
7404
+ input: ("image" | "text")[];
6868
7405
  cost: {
6869
7406
  input: number;
6870
7407
  output: number;
@@ -6874,21 +7411,25 @@ export declare const MODELS: {
6874
7411
  contextWindow: number;
6875
7412
  maxTokens: number;
6876
7413
  };
6877
- readonly "kimi-k2-turbo-preview": {
7414
+ readonly "meta/llama-3.2-90b-vision-instruct": {
6878
7415
  id: string;
6879
7416
  name: string;
6880
7417
  api: "openai-completions";
6881
7418
  provider: string;
6882
7419
  baseUrl: string;
7420
+ headers: {
7421
+ "NVCF-POLL-SECONDS": string;
7422
+ };
6883
7423
  compat: {
6884
7424
  supportsStore: false;
6885
7425
  supportsDeveloperRole: false;
6886
7426
  supportsReasoningEffort: false;
6887
7427
  maxTokensField: "max_tokens";
6888
7428
  supportsStrictMode: false;
7429
+ supportsLongCacheRetention: false;
6889
7430
  };
6890
7431
  reasoning: false;
6891
- input: "text"[];
7432
+ input: ("image" | "text")[];
6892
7433
  cost: {
6893
7434
  input: number;
6894
7435
  output: number;
@@ -6898,21 +7439,25 @@ export declare const MODELS: {
6898
7439
  contextWindow: number;
6899
7440
  maxTokens: number;
6900
7441
  };
6901
- readonly "kimi-k2.5": {
7442
+ readonly "meta/llama-3.3-70b-instruct": {
6902
7443
  id: string;
6903
7444
  name: string;
6904
7445
  api: "openai-completions";
6905
7446
  provider: string;
6906
7447
  baseUrl: string;
7448
+ headers: {
7449
+ "NVCF-POLL-SECONDS": string;
7450
+ };
6907
7451
  compat: {
6908
7452
  supportsStore: false;
6909
7453
  supportsDeveloperRole: false;
6910
7454
  supportsReasoningEffort: false;
6911
7455
  maxTokensField: "max_tokens";
6912
7456
  supportsStrictMode: false;
7457
+ supportsLongCacheRetention: false;
6913
7458
  };
6914
- reasoning: true;
6915
- input: ("image" | "text")[];
7459
+ reasoning: false;
7460
+ input: "text"[];
6916
7461
  cost: {
6917
7462
  input: number;
6918
7463
  output: number;
@@ -6922,21 +7467,25 @@ export declare const MODELS: {
6922
7467
  contextWindow: number;
6923
7468
  maxTokens: number;
6924
7469
  };
6925
- readonly "kimi-k2.6": {
7470
+ readonly "minimaxai/minimax-m2.5": {
6926
7471
  id: string;
6927
7472
  name: string;
6928
7473
  api: "openai-completions";
6929
7474
  provider: string;
6930
7475
  baseUrl: string;
7476
+ headers: {
7477
+ "NVCF-POLL-SECONDS": string;
7478
+ };
6931
7479
  compat: {
6932
7480
  supportsStore: false;
6933
7481
  supportsDeveloperRole: false;
6934
7482
  supportsReasoningEffort: false;
6935
7483
  maxTokensField: "max_tokens";
6936
7484
  supportsStrictMode: false;
7485
+ supportsLongCacheRetention: false;
6937
7486
  };
6938
7487
  reasoning: true;
6939
- input: ("image" | "text")[];
7488
+ input: "text"[];
6940
7489
  cost: {
6941
7490
  input: number;
6942
7491
  output: number;
@@ -6946,22 +7495,24 @@ export declare const MODELS: {
6946
7495
  contextWindow: number;
6947
7496
  maxTokens: number;
6948
7497
  };
6949
- };
6950
- readonly "moonshotai-cn": {
6951
- readonly "kimi-k2-0711-preview": {
7498
+ readonly "mistralai/devstral-2-123b-instruct-2512": {
6952
7499
  id: string;
6953
7500
  name: string;
6954
7501
  api: "openai-completions";
6955
7502
  provider: string;
6956
7503
  baseUrl: string;
7504
+ headers: {
7505
+ "NVCF-POLL-SECONDS": string;
7506
+ };
6957
7507
  compat: {
6958
7508
  supportsStore: false;
6959
7509
  supportsDeveloperRole: false;
6960
7510
  supportsReasoningEffort: false;
6961
7511
  maxTokensField: "max_tokens";
6962
7512
  supportsStrictMode: false;
7513
+ supportsLongCacheRetention: false;
6963
7514
  };
6964
- reasoning: false;
7515
+ reasoning: true;
6965
7516
  input: "text"[];
6966
7517
  cost: {
6967
7518
  input: number;
@@ -6972,18 +7523,22 @@ export declare const MODELS: {
6972
7523
  contextWindow: number;
6973
7524
  maxTokens: number;
6974
7525
  };
6975
- readonly "kimi-k2-0905-preview": {
7526
+ readonly "mistralai/mistral-7b-instruct-v03": {
6976
7527
  id: string;
6977
7528
  name: string;
6978
7529
  api: "openai-completions";
6979
7530
  provider: string;
6980
7531
  baseUrl: string;
7532
+ headers: {
7533
+ "NVCF-POLL-SECONDS": string;
7534
+ };
6981
7535
  compat: {
6982
7536
  supportsStore: false;
6983
7537
  supportsDeveloperRole: false;
6984
7538
  supportsReasoningEffort: false;
6985
7539
  maxTokensField: "max_tokens";
6986
7540
  supportsStrictMode: false;
7541
+ supportsLongCacheRetention: false;
6987
7542
  };
6988
7543
  reasoning: false;
6989
7544
  input: "text"[];
@@ -6996,21 +7551,25 @@ export declare const MODELS: {
6996
7551
  contextWindow: number;
6997
7552
  maxTokens: number;
6998
7553
  };
6999
- readonly "kimi-k2-thinking": {
7554
+ readonly "mistralai/mistral-large-3-675b-instruct-2512": {
7000
7555
  id: string;
7001
7556
  name: string;
7002
7557
  api: "openai-completions";
7003
7558
  provider: string;
7004
7559
  baseUrl: string;
7560
+ headers: {
7561
+ "NVCF-POLL-SECONDS": string;
7562
+ };
7005
7563
  compat: {
7006
7564
  supportsStore: false;
7007
7565
  supportsDeveloperRole: false;
7008
7566
  supportsReasoningEffort: false;
7009
7567
  maxTokensField: "max_tokens";
7010
7568
  supportsStrictMode: false;
7569
+ supportsLongCacheRetention: false;
7011
7570
  };
7012
- reasoning: true;
7013
- input: "text"[];
7571
+ reasoning: false;
7572
+ input: ("image" | "text")[];
7014
7573
  cost: {
7015
7574
  input: number;
7016
7575
  output: number;
@@ -7020,20 +7579,24 @@ export declare const MODELS: {
7020
7579
  contextWindow: number;
7021
7580
  maxTokens: number;
7022
7581
  };
7023
- readonly "kimi-k2-thinking-turbo": {
7582
+ readonly "mistralai/mistral-small-4-119b-2603": {
7024
7583
  id: string;
7025
7584
  name: string;
7026
7585
  api: "openai-completions";
7027
7586
  provider: string;
7028
7587
  baseUrl: string;
7588
+ headers: {
7589
+ "NVCF-POLL-SECONDS": string;
7590
+ };
7029
7591
  compat: {
7030
7592
  supportsStore: false;
7031
7593
  supportsDeveloperRole: false;
7032
7594
  supportsReasoningEffort: false;
7033
7595
  maxTokensField: "max_tokens";
7034
7596
  supportsStrictMode: false;
7597
+ supportsLongCacheRetention: false;
7035
7598
  };
7036
- reasoning: true;
7599
+ reasoning: false;
7037
7600
  input: "text"[];
7038
7601
  cost: {
7039
7602
  input: number;
@@ -7044,18 +7607,22 @@ export declare const MODELS: {
7044
7607
  contextWindow: number;
7045
7608
  maxTokens: number;
7046
7609
  };
7047
- readonly "kimi-k2-turbo-preview": {
7610
+ readonly "mistralai/mixtral-8x22b-instruct": {
7048
7611
  id: string;
7049
7612
  name: string;
7050
7613
  api: "openai-completions";
7051
7614
  provider: string;
7052
7615
  baseUrl: string;
7616
+ headers: {
7617
+ "NVCF-POLL-SECONDS": string;
7618
+ };
7053
7619
  compat: {
7054
7620
  supportsStore: false;
7055
7621
  supportsDeveloperRole: false;
7056
7622
  supportsReasoningEffort: false;
7057
7623
  maxTokensField: "max_tokens";
7058
7624
  supportsStrictMode: false;
7625
+ supportsLongCacheRetention: false;
7059
7626
  };
7060
7627
  reasoning: false;
7061
7628
  input: "text"[];
@@ -7068,21 +7635,25 @@ export declare const MODELS: {
7068
7635
  contextWindow: number;
7069
7636
  maxTokens: number;
7070
7637
  };
7071
- readonly "kimi-k2.5": {
7638
+ readonly "mistralai/mixtral-8x7b-instruct": {
7072
7639
  id: string;
7073
7640
  name: string;
7074
7641
  api: "openai-completions";
7075
7642
  provider: string;
7076
7643
  baseUrl: string;
7644
+ headers: {
7645
+ "NVCF-POLL-SECONDS": string;
7646
+ };
7077
7647
  compat: {
7078
7648
  supportsStore: false;
7079
7649
  supportsDeveloperRole: false;
7080
7650
  supportsReasoningEffort: false;
7081
7651
  maxTokensField: "max_tokens";
7082
7652
  supportsStrictMode: false;
7653
+ supportsLongCacheRetention: false;
7083
7654
  };
7084
- reasoning: true;
7085
- input: ("image" | "text")[];
7655
+ reasoning: false;
7656
+ input: "text"[];
7086
7657
  cost: {
7087
7658
  input: number;
7088
7659
  output: number;
@@ -7092,21 +7663,25 @@ export declare const MODELS: {
7092
7663
  contextWindow: number;
7093
7664
  maxTokens: number;
7094
7665
  };
7095
- readonly "kimi-k2.6": {
7666
+ readonly "moonshotai/kimi-k2-instruct": {
7096
7667
  id: string;
7097
7668
  name: string;
7098
7669
  api: "openai-completions";
7099
7670
  provider: string;
7100
7671
  baseUrl: string;
7672
+ headers: {
7673
+ "NVCF-POLL-SECONDS": string;
7674
+ };
7101
7675
  compat: {
7102
7676
  supportsStore: false;
7103
7677
  supportsDeveloperRole: false;
7104
7678
  supportsReasoningEffort: false;
7105
7679
  maxTokensField: "max_tokens";
7106
7680
  supportsStrictMode: false;
7681
+ supportsLongCacheRetention: false;
7107
7682
  };
7108
7683
  reasoning: true;
7109
- input: ("image" | "text")[];
7684
+ input: "text"[];
7110
7685
  cost: {
7111
7686
  input: number;
7112
7687
  output: number;
@@ -7116,9 +7691,7 @@ export declare const MODELS: {
7116
7691
  contextWindow: number;
7117
7692
  maxTokens: number;
7118
7693
  };
7119
- };
7120
- readonly nvidia: {
7121
- readonly "meta/llama-3.1-70b-instruct": {
7694
+ readonly "moonshotai/kimi-k2-instruct-0905": {
7122
7695
  id: string;
7123
7696
  name: string;
7124
7697
  api: "openai-completions";
@@ -7146,7 +7719,7 @@ export declare const MODELS: {
7146
7719
  contextWindow: number;
7147
7720
  maxTokens: number;
7148
7721
  };
7149
- readonly "meta/llama-3.1-8b-instruct": {
7722
+ readonly "moonshotai/kimi-k2-thinking": {
7150
7723
  id: string;
7151
7724
  name: string;
7152
7725
  api: "openai-completions";
@@ -7163,7 +7736,7 @@ export declare const MODELS: {
7163
7736
  supportsStrictMode: false;
7164
7737
  supportsLongCacheRetention: false;
7165
7738
  };
7166
- reasoning: false;
7739
+ reasoning: true;
7167
7740
  input: "text"[];
7168
7741
  cost: {
7169
7742
  input: number;
@@ -7174,7 +7747,7 @@ export declare const MODELS: {
7174
7747
  contextWindow: number;
7175
7748
  maxTokens: number;
7176
7749
  };
7177
- readonly "meta/llama-3.2-11b-vision-instruct": {
7750
+ readonly "moonshotai/kimi-k2.6": {
7178
7751
  id: string;
7179
7752
  name: string;
7180
7753
  api: "openai-completions";
@@ -7191,7 +7764,7 @@ export declare const MODELS: {
7191
7764
  supportsStrictMode: false;
7192
7765
  supportsLongCacheRetention: false;
7193
7766
  };
7194
- reasoning: false;
7767
+ reasoning: true;
7195
7768
  input: ("image" | "text")[];
7196
7769
  cost: {
7197
7770
  input: number;
@@ -7202,7 +7775,7 @@ export declare const MODELS: {
7202
7775
  contextWindow: number;
7203
7776
  maxTokens: number;
7204
7777
  };
7205
- readonly "meta/llama-3.2-90b-vision-instruct": {
7778
+ readonly "nvidia/llama-3_3-nemotron-super-49b-v1": {
7206
7779
  id: string;
7207
7780
  name: string;
7208
7781
  api: "openai-completions";
@@ -7219,8 +7792,8 @@ export declare const MODELS: {
7219
7792
  supportsStrictMode: false;
7220
7793
  supportsLongCacheRetention: false;
7221
7794
  };
7222
- reasoning: false;
7223
- input: ("image" | "text")[];
7795
+ reasoning: true;
7796
+ input: "text"[];
7224
7797
  cost: {
7225
7798
  input: number;
7226
7799
  output: number;
@@ -7230,7 +7803,7 @@ export declare const MODELS: {
7230
7803
  contextWindow: number;
7231
7804
  maxTokens: number;
7232
7805
  };
7233
- readonly "meta/llama-3.3-70b-instruct": {
7806
+ readonly "nvidia/llama-3_3-nemotron-super-49b-v1_5": {
7234
7807
  id: string;
7235
7808
  name: string;
7236
7809
  api: "openai-completions";
@@ -7247,7 +7820,7 @@ export declare const MODELS: {
7247
7820
  supportsStrictMode: false;
7248
7821
  supportsLongCacheRetention: false;
7249
7822
  };
7250
- reasoning: false;
7823
+ reasoning: true;
7251
7824
  input: "text"[];
7252
7825
  cost: {
7253
7826
  input: number;
@@ -7258,7 +7831,7 @@ export declare const MODELS: {
7258
7831
  contextWindow: number;
7259
7832
  maxTokens: number;
7260
7833
  };
7261
- readonly "mistralai/mistral-large-3-675b-instruct-2512": {
7834
+ readonly "nvidia/nemotron-3-nano-30b-a3b": {
7262
7835
  id: string;
7263
7836
  name: string;
7264
7837
  api: "openai-completions";
@@ -7275,8 +7848,8 @@ export declare const MODELS: {
7275
7848
  supportsStrictMode: false;
7276
7849
  supportsLongCacheRetention: false;
7277
7850
  };
7278
- reasoning: false;
7279
- input: ("image" | "text")[];
7851
+ reasoning: true;
7852
+ input: "text"[];
7280
7853
  cost: {
7281
7854
  input: number;
7282
7855
  output: number;
@@ -7286,7 +7859,7 @@ export declare const MODELS: {
7286
7859
  contextWindow: number;
7287
7860
  maxTokens: number;
7288
7861
  };
7289
- readonly "mistralai/mistral-small-4-119b-2603": {
7862
+ readonly "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning": {
7290
7863
  id: string;
7291
7864
  name: string;
7292
7865
  api: "openai-completions";
@@ -7303,8 +7876,8 @@ export declare const MODELS: {
7303
7876
  supportsStrictMode: false;
7304
7877
  supportsLongCacheRetention: false;
7305
7878
  };
7306
- reasoning: false;
7307
- input: "text"[];
7879
+ reasoning: true;
7880
+ input: ("image" | "text")[];
7308
7881
  cost: {
7309
7882
  input: number;
7310
7883
  output: number;
@@ -7314,7 +7887,7 @@ export declare const MODELS: {
7314
7887
  contextWindow: number;
7315
7888
  maxTokens: number;
7316
7889
  };
7317
- readonly "moonshotai/kimi-k2.6": {
7890
+ readonly "nvidia/nemotron-3-super-120b-a12b": {
7318
7891
  id: string;
7319
7892
  name: string;
7320
7893
  api: "openai-completions";
@@ -7332,7 +7905,7 @@ export declare const MODELS: {
7332
7905
  supportsLongCacheRetention: false;
7333
7906
  };
7334
7907
  reasoning: true;
7335
- input: ("image" | "text")[];
7908
+ input: "text"[];
7336
7909
  cost: {
7337
7910
  input: number;
7338
7911
  output: number;
@@ -7342,7 +7915,7 @@ export declare const MODELS: {
7342
7915
  contextWindow: number;
7343
7916
  maxTokens: number;
7344
7917
  };
7345
- readonly "nvidia/llama-3.3-nemotron-super-49b-v1": {
7918
+ readonly "nvidia/nemotron-voicechat": {
7346
7919
  id: string;
7347
7920
  name: string;
7348
7921
  api: "openai-completions";
@@ -7359,7 +7932,7 @@ export declare const MODELS: {
7359
7932
  supportsStrictMode: false;
7360
7933
  supportsLongCacheRetention: false;
7361
7934
  };
7362
- reasoning: true;
7935
+ reasoning: false;
7363
7936
  input: "text"[];
7364
7937
  cost: {
7365
7938
  input: number;
@@ -7370,7 +7943,7 @@ export declare const MODELS: {
7370
7943
  contextWindow: number;
7371
7944
  maxTokens: number;
7372
7945
  };
7373
- readonly "nvidia/llama-3.3-nemotron-super-49b-v1.5": {
7946
+ readonly "nvidia/nvidia-nemotron-nano-9b-v2": {
7374
7947
  id: string;
7375
7948
  name: string;
7376
7949
  api: "openai-completions";
@@ -7398,7 +7971,7 @@ export declare const MODELS: {
7398
7971
  contextWindow: number;
7399
7972
  maxTokens: number;
7400
7973
  };
7401
- readonly "nvidia/nemotron-3-nano-30b-a3b": {
7974
+ readonly "openai/gpt-oss-20b": {
7402
7975
  id: string;
7403
7976
  name: string;
7404
7977
  api: "openai-completions";
@@ -7426,7 +7999,7 @@ export declare const MODELS: {
7426
7999
  contextWindow: number;
7427
8000
  maxTokens: number;
7428
8001
  };
7429
- readonly "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning": {
8002
+ readonly "qwen/qwen2.5-coder-32b-instruct": {
7430
8003
  id: string;
7431
8004
  name: string;
7432
8005
  api: "openai-completions";
@@ -7443,8 +8016,8 @@ export declare const MODELS: {
7443
8016
  supportsStrictMode: false;
7444
8017
  supportsLongCacheRetention: false;
7445
8018
  };
7446
- reasoning: true;
7447
- input: ("image" | "text")[];
8019
+ reasoning: false;
8020
+ input: "text"[];
7448
8021
  cost: {
7449
8022
  input: number;
7450
8023
  output: number;
@@ -7454,7 +8027,7 @@ export declare const MODELS: {
7454
8027
  contextWindow: number;
7455
8028
  maxTokens: number;
7456
8029
  };
7457
- readonly "nvidia/nemotron-3-super-120b-a12b": {
8030
+ readonly "qwen/qwen3-coder-480b-a35b-instruct": {
7458
8031
  id: string;
7459
8032
  name: string;
7460
8033
  api: "openai-completions";
@@ -7471,7 +8044,7 @@ export declare const MODELS: {
7471
8044
  supportsStrictMode: false;
7472
8045
  supportsLongCacheRetention: false;
7473
8046
  };
7474
- reasoning: true;
8047
+ reasoning: false;
7475
8048
  input: "text"[];
7476
8049
  cost: {
7477
8050
  input: number;
@@ -7482,7 +8055,7 @@ export declare const MODELS: {
7482
8055
  contextWindow: number;
7483
8056
  maxTokens: number;
7484
8057
  };
7485
- readonly "nvidia/nvidia-nemotron-nano-9b-v2": {
8058
+ readonly "qwen/qwen3-next-80b-a3b-thinking": {
7486
8059
  id: string;
7487
8060
  name: string;
7488
8061
  api: "openai-completions";
@@ -7510,7 +8083,7 @@ export declare const MODELS: {
7510
8083
  contextWindow: number;
7511
8084
  maxTokens: number;
7512
8085
  };
7513
- readonly "openai/gpt-oss-20b": {
8086
+ readonly "qwen/qwen3.5-122b-a10b": {
7514
8087
  id: string;
7515
8088
  name: string;
7516
8089
  api: "openai-completions";
@@ -7528,7 +8101,7 @@ export declare const MODELS: {
7528
8101
  supportsLongCacheRetention: false;
7529
8102
  };
7530
8103
  reasoning: true;
7531
- input: "text"[];
8104
+ input: ("image" | "text")[];
7532
8105
  cost: {
7533
8106
  input: number;
7534
8107
  output: number;
@@ -7538,7 +8111,7 @@ export declare const MODELS: {
7538
8111
  contextWindow: number;
7539
8112
  maxTokens: number;
7540
8113
  };
7541
- readonly "qwen/qwen3-coder-480b-a35b-instruct": {
8114
+ readonly "stepfun-ai/step-3.5-flash": {
7542
8115
  id: string;
7543
8116
  name: string;
7544
8117
  api: "openai-completions";
@@ -7555,7 +8128,7 @@ export declare const MODELS: {
7555
8128
  supportsStrictMode: false;
7556
8129
  supportsLongCacheRetention: false;
7557
8130
  };
7558
- reasoning: false;
8131
+ reasoning: true;
7559
8132
  input: "text"[];
7560
8133
  cost: {
7561
8134
  input: number;
@@ -7566,7 +8139,7 @@ export declare const MODELS: {
7566
8139
  contextWindow: number;
7567
8140
  maxTokens: number;
7568
8141
  };
7569
- readonly "qwen/qwen3.5-122b-a10b": {
8142
+ readonly "stepfun-ai/step-3.7-flash": {
7570
8143
  id: string;
7571
8144
  name: string;
7572
8145
  api: "openai-completions";
@@ -7594,7 +8167,7 @@ export declare const MODELS: {
7594
8167
  contextWindow: number;
7595
8168
  maxTokens: number;
7596
8169
  };
7597
- readonly "stepfun-ai/step-3.5-flash": {
8170
+ readonly "upstage/solar-10_7b-instruct": {
7598
8171
  id: string;
7599
8172
  name: string;
7600
8173
  api: "openai-completions";
@@ -7611,7 +8184,7 @@ export declare const MODELS: {
7611
8184
  supportsStrictMode: false;
7612
8185
  supportsLongCacheRetention: false;
7613
8186
  };
7614
- reasoning: true;
8187
+ reasoning: false;
7615
8188
  input: "text"[];
7616
8189
  cost: {
7617
8190
  input: number;
@@ -7622,7 +8195,7 @@ export declare const MODELS: {
7622
8195
  contextWindow: number;
7623
8196
  maxTokens: number;
7624
8197
  };
7625
- readonly "stepfun-ai/step-3.7-flash": {
8198
+ readonly "z-ai/glm-5.1": {
7626
8199
  id: string;
7627
8200
  name: string;
7628
8201
  api: "openai-completions";
@@ -7640,7 +8213,7 @@ export declare const MODELS: {
7640
8213
  supportsLongCacheRetention: false;
7641
8214
  };
7642
8215
  reasoning: true;
7643
- input: ("image" | "text")[];
8216
+ input: "text"[];
7644
8217
  cost: {
7645
8218
  input: number;
7646
8219
  output: number;
@@ -7650,7 +8223,7 @@ export declare const MODELS: {
7650
8223
  contextWindow: number;
7651
8224
  maxTokens: number;
7652
8225
  };
7653
- readonly "z-ai/glm-5.1": {
8226
+ readonly "z-ai/glm4.7": {
7654
8227
  id: string;
7655
8228
  name: string;
7656
8229
  api: "openai-completions";
@@ -9380,7 +9953,7 @@ export declare const MODELS: {
9380
9953
  contextWindow: number;
9381
9954
  maxTokens: number;
9382
9955
  };
9383
- readonly "nemotron-3-super-free": {
9956
+ readonly "nemotron-3-ultra-free": {
9384
9957
  id: string;
9385
9958
  name: string;
9386
9959
  api: "openai-completions";
@@ -11609,6 +12182,23 @@ export declare const MODELS: {
11609
12182
  contextWindow: number;
11610
12183
  maxTokens: number;
11611
12184
  };
12185
+ readonly "nvidia/nemotron-3-ultra-550b-a55b": {
12186
+ id: string;
12187
+ name: string;
12188
+ api: "openai-completions";
12189
+ provider: string;
12190
+ baseUrl: string;
12191
+ reasoning: true;
12192
+ input: "text"[];
12193
+ cost: {
12194
+ input: number;
12195
+ output: number;
12196
+ cacheRead: number;
12197
+ cacheWrite: number;
12198
+ };
12199
+ contextWindow: number;
12200
+ maxTokens: number;
12201
+ };
11612
12202
  readonly "nvidia/nemotron-3-ultra-550b-a55b:free": {
11613
12203
  id: string;
11614
12204
  name: string;
@@ -13569,23 +14159,6 @@ export declare const MODELS: {
13569
14159
  contextWindow: number;
13570
14160
  maxTokens: number;
13571
14161
  };
13572
- readonly "sao10k/l3-euryale-70b": {
13573
- id: string;
13574
- name: string;
13575
- api: "openai-completions";
13576
- provider: string;
13577
- baseUrl: string;
13578
- reasoning: false;
13579
- input: "text"[];
13580
- cost: {
13581
- input: number;
13582
- output: number;
13583
- cacheRead: number;
13584
- cacheWrite: number;
13585
- };
13586
- contextWindow: number;
13587
- maxTokens: number;
13588
- };
13589
14162
  readonly "sao10k/l3.1-euryale-70b": {
13590
14163
  id: string;
13591
14164
  name: string;
@@ -14646,6 +15219,37 @@ export declare const MODELS: {
14646
15219
  contextWindow: number;
14647
15220
  maxTokens: number;
14648
15221
  };
15222
+ readonly "nvidia/nemotron-3-ultra-550b-a55b": {
15223
+ id: string;
15224
+ name: string;
15225
+ api: "openai-completions";
15226
+ provider: string;
15227
+ baseUrl: string;
15228
+ compat: {
15229
+ supportsStore: false;
15230
+ supportsDeveloperRole: false;
15231
+ supportsReasoningEffort: false;
15232
+ maxTokensField: "max_tokens";
15233
+ supportsStrictMode: false;
15234
+ supportsLongCacheRetention: false;
15235
+ thinkingFormat: "together";
15236
+ };
15237
+ reasoning: true;
15238
+ thinkingLevelMap: {
15239
+ minimal: null;
15240
+ low: null;
15241
+ medium: null;
15242
+ };
15243
+ input: "text"[];
15244
+ cost: {
15245
+ input: number;
15246
+ output: number;
15247
+ cacheRead: number;
15248
+ cacheWrite: number;
15249
+ };
15250
+ contextWindow: number;
15251
+ maxTokens: number;
15252
+ };
14649
15253
  readonly "openai/gpt-oss-120b": {
14650
15254
  id: string;
14651
15255
  name: string;
@@ -16381,6 +16985,23 @@ export declare const MODELS: {
16381
16985
  contextWindow: number;
16382
16986
  maxTokens: number;
16383
16987
  };
16988
+ readonly "nvidia/nemotron-3-ultra-550b-a55b": {
16989
+ id: string;
16990
+ name: string;
16991
+ api: "anthropic-messages";
16992
+ provider: string;
16993
+ baseUrl: string;
16994
+ reasoning: true;
16995
+ input: "text"[];
16996
+ cost: {
16997
+ input: number;
16998
+ output: number;
16999
+ cacheRead: number;
17000
+ cacheWrite: number;
17001
+ };
17002
+ contextWindow: number;
17003
+ maxTokens: number;
17004
+ };
16384
17005
  readonly "nvidia/nemotron-nano-12b-v2-vl": {
16385
17006
  id: string;
16386
17007
  name: string;