@dreb/ai 2.25.0 → 2.25.2

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.
@@ -1073,6 +1073,57 @@ export const MODELS = {
1073
1073
  contextWindow: 262144,
1074
1074
  maxTokens: 131072,
1075
1075
  },
1076
+ "openai.gpt-5.4": {
1077
+ id: "openai.gpt-5.4",
1078
+ name: "GPT-5.4",
1079
+ api: "bedrock-converse-stream",
1080
+ provider: "amazon-bedrock",
1081
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1082
+ reasoning: true,
1083
+ input: ["text", "image"],
1084
+ cost: {
1085
+ input: 2.75,
1086
+ output: 16.5,
1087
+ cacheRead: 0.275,
1088
+ cacheWrite: 0,
1089
+ },
1090
+ contextWindow: 272000,
1091
+ maxTokens: 128000,
1092
+ },
1093
+ "openai.gpt-5.5": {
1094
+ id: "openai.gpt-5.5",
1095
+ name: "GPT-5.5",
1096
+ api: "bedrock-converse-stream",
1097
+ provider: "amazon-bedrock",
1098
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1099
+ reasoning: true,
1100
+ input: ["text", "image"],
1101
+ cost: {
1102
+ input: 5.5,
1103
+ output: 33,
1104
+ cacheRead: 0.55,
1105
+ cacheWrite: 0,
1106
+ },
1107
+ contextWindow: 272000,
1108
+ maxTokens: 128000,
1109
+ },
1110
+ "openai.gpt-oss-120b": {
1111
+ id: "openai.gpt-oss-120b",
1112
+ name: "gpt-oss-120b",
1113
+ api: "bedrock-converse-stream",
1114
+ provider: "amazon-bedrock",
1115
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1116
+ reasoning: false,
1117
+ input: ["text"],
1118
+ cost: {
1119
+ input: 0.15,
1120
+ output: 0.6,
1121
+ cacheRead: 0,
1122
+ cacheWrite: 0,
1123
+ },
1124
+ contextWindow: 128000,
1125
+ maxTokens: 16384,
1126
+ },
1076
1127
  "openai.gpt-oss-120b-1:0": {
1077
1128
  id: "openai.gpt-oss-120b-1:0",
1078
1129
  name: "gpt-oss-120b",
@@ -1090,6 +1141,23 @@ export const MODELS = {
1090
1141
  contextWindow: 128000,
1091
1142
  maxTokens: 16384,
1092
1143
  },
1144
+ "openai.gpt-oss-20b": {
1145
+ id: "openai.gpt-oss-20b",
1146
+ name: "gpt-oss-20b",
1147
+ api: "bedrock-converse-stream",
1148
+ provider: "amazon-bedrock",
1149
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1150
+ reasoning: false,
1151
+ input: ["text"],
1152
+ cost: {
1153
+ input: 0.07,
1154
+ output: 0.3,
1155
+ cacheRead: 0,
1156
+ cacheWrite: 0,
1157
+ },
1158
+ contextWindow: 128000,
1159
+ maxTokens: 16384,
1160
+ },
1093
1161
  "openai.gpt-oss-20b-1:0": {
1094
1162
  id: "openai.gpt-oss-20b-1:0",
1095
1163
  name: "gpt-oss-20b",
@@ -6973,7 +7041,7 @@ export const MODELS = {
6973
7041
  cacheRead: 0.05,
6974
7042
  cacheWrite: 0.625,
6975
7043
  },
6976
- contextWindow: 262144,
7044
+ contextWindow: 1000000,
6977
7045
  maxTokens: 65536,
6978
7046
  },
6979
7047
  "qwen3.7-max": {
@@ -7007,7 +7075,7 @@ export const MODELS = {
7007
7075
  cacheRead: 0.04,
7008
7076
  cacheWrite: 0.5,
7009
7077
  },
7010
- contextWindow: 262144,
7078
+ contextWindow: 1000000,
7011
7079
  maxTokens: 65536,
7012
7080
  },
7013
7081
  },
@@ -8025,12 +8093,12 @@ export const MODELS = {
8025
8093
  input: ["text", "image"],
8026
8094
  cost: {
8027
8095
  input: 0.12,
8028
- output: 0.37,
8029
- cacheRead: 0,
8096
+ output: 0.36,
8097
+ cacheRead: 0.09,
8030
8098
  cacheWrite: 0,
8031
8099
  },
8032
8100
  contextWindow: 262144,
8033
- maxTokens: 16384,
8101
+ maxTokens: 8192,
8034
8102
  },
8035
8103
  "google/gemma-4-31b-it:free": {
8036
8104
  id: "google/gemma-4-31b-it:free",
@@ -8178,7 +8246,7 @@ export const MODELS = {
8178
8246
  input: ["text"],
8179
8247
  cost: {
8180
8248
  input: 0.02,
8181
- output: 0.049999999999999996,
8249
+ output: 0.03,
8182
8250
  cacheRead: 0,
8183
8251
  cacheWrite: 0,
8184
8252
  },
@@ -8336,7 +8404,7 @@ export const MODELS = {
8336
8404
  cacheWrite: 0,
8337
8405
  },
8338
8406
  contextWindow: 204800,
8339
- maxTokens: 131072,
8407
+ maxTokens: 196608,
8340
8408
  },
8341
8409
  "minimax/minimax-m3": {
8342
8410
  id: "minimax/minimax-m3",
@@ -10138,7 +10206,7 @@ export const MODELS = {
10138
10206
  cacheWrite: 0,
10139
10207
  },
10140
10208
  contextWindow: 131072,
10141
- maxTokens: 20000,
10209
+ maxTokens: 16384,
10142
10210
  },
10143
10211
  "qwen/qwen3-30b-a3b-instruct-2507": {
10144
10212
  id: "qwen/qwen3-30b-a3b-instruct-2507",
@@ -10803,23 +10871,6 @@ export const MODELS = {
10803
10871
  contextWindow: 256000,
10804
10872
  maxTokens: 128000,
10805
10873
  },
10806
- "sao10k/l3-euryale-70b": {
10807
- id: "sao10k/l3-euryale-70b",
10808
- name: "Sao10k: Llama 3 Euryale 70B v2.1",
10809
- api: "openai-completions",
10810
- provider: "openrouter",
10811
- baseUrl: "https://openrouter.ai/api/v1",
10812
- reasoning: false,
10813
- input: ["text"],
10814
- cost: {
10815
- input: 1.48,
10816
- output: 1.48,
10817
- cacheRead: 0,
10818
- cacheWrite: 0,
10819
- },
10820
- contextWindow: 8192,
10821
- maxTokens: 8192,
10822
- },
10823
10874
  "sao10k/l3.1-euryale-70b": {
10824
10875
  id: "sao10k/l3.1-euryale-70b",
10825
10876
  name: "Sao10K: Llama 3.1 Euryale 70B v2.2",
@@ -13058,12 +13109,12 @@ export const MODELS = {
13058
13109
  reasoning: true,
13059
13110
  input: ["text"],
13060
13111
  cost: {
13061
- input: 0.5,
13062
- output: 2.5,
13063
- cacheRead: 0.15,
13112
+ input: 0.6,
13113
+ output: 2.4,
13114
+ cacheRead: 0.12,
13064
13115
  cacheWrite: 0,
13065
13116
  },
13066
- contextWindow: 262144,
13117
+ contextWindow: 1000000,
13067
13118
  maxTokens: 65000,
13068
13119
  },
13069
13120
  "nvidia/nemotron-nano-12b-v2-vl": {