@openachieve/ai 0.78.0 → 0.79.0

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.
@@ -1086,6 +1086,59 @@ export const MODELS = {
1086
1086
  contextWindow: 262144,
1087
1087
  maxTokens: 131072,
1088
1088
  },
1089
+ "openai.gpt-5.4": {
1090
+ id: "openai.gpt-5.4",
1091
+ name: "GPT-5.4",
1092
+ api: "bedrock-converse-stream",
1093
+ provider: "amazon-bedrock",
1094
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1095
+ reasoning: true,
1096
+ thinkingLevelMap: { "xhigh": "xhigh" },
1097
+ input: ["text", "image"],
1098
+ cost: {
1099
+ input: 2.75,
1100
+ output: 16.5,
1101
+ cacheRead: 0.275,
1102
+ cacheWrite: 0,
1103
+ },
1104
+ contextWindow: 272000,
1105
+ maxTokens: 128000,
1106
+ },
1107
+ "openai.gpt-5.5": {
1108
+ id: "openai.gpt-5.5",
1109
+ name: "GPT-5.5",
1110
+ api: "bedrock-converse-stream",
1111
+ provider: "amazon-bedrock",
1112
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1113
+ reasoning: true,
1114
+ thinkingLevelMap: { "xhigh": "xhigh" },
1115
+ input: ["text", "image"],
1116
+ cost: {
1117
+ input: 5.5,
1118
+ output: 33,
1119
+ cacheRead: 0.55,
1120
+ cacheWrite: 0,
1121
+ },
1122
+ contextWindow: 272000,
1123
+ maxTokens: 128000,
1124
+ },
1125
+ "openai.gpt-oss-120b": {
1126
+ id: "openai.gpt-oss-120b",
1127
+ name: "gpt-oss-120b",
1128
+ api: "bedrock-converse-stream",
1129
+ provider: "amazon-bedrock",
1130
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1131
+ reasoning: false,
1132
+ input: ["text"],
1133
+ cost: {
1134
+ input: 0.15,
1135
+ output: 0.6,
1136
+ cacheRead: 0,
1137
+ cacheWrite: 0,
1138
+ },
1139
+ contextWindow: 128000,
1140
+ maxTokens: 16384,
1141
+ },
1089
1142
  "openai.gpt-oss-120b-1:0": {
1090
1143
  id: "openai.gpt-oss-120b-1:0",
1091
1144
  name: "gpt-oss-120b",
@@ -1103,6 +1156,23 @@ export const MODELS = {
1103
1156
  contextWindow: 128000,
1104
1157
  maxTokens: 16384,
1105
1158
  },
1159
+ "openai.gpt-oss-20b": {
1160
+ id: "openai.gpt-oss-20b",
1161
+ name: "gpt-oss-20b",
1162
+ api: "bedrock-converse-stream",
1163
+ provider: "amazon-bedrock",
1164
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1165
+ reasoning: false,
1166
+ input: ["text"],
1167
+ cost: {
1168
+ input: 0.07,
1169
+ output: 0.3,
1170
+ cacheRead: 0,
1171
+ cacheWrite: 0,
1172
+ },
1173
+ contextWindow: 128000,
1174
+ maxTokens: 16384,
1175
+ },
1106
1176
  "openai.gpt-oss-20b-1:0": {
1107
1177
  id: "openai.gpt-oss-20b-1:0",
1108
1178
  name: "gpt-oss-20b",
@@ -3887,6 +3957,24 @@ export const MODELS = {
3887
3957
  contextWindow: 202800,
3888
3958
  maxTokens: 131072,
3889
3959
  },
3960
+ "accounts/fireworks/routers/kimi-k2p6-fast": {
3961
+ id: "accounts/fireworks/routers/kimi-k2p6-fast",
3962
+ name: "Kimi K2.6 Fast",
3963
+ api: "anthropic-messages",
3964
+ provider: "fireworks",
3965
+ baseUrl: "https://api.fireworks.ai/inference",
3966
+ compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
3967
+ reasoning: true,
3968
+ input: ["text", "image"],
3969
+ cost: {
3970
+ input: 2,
3971
+ output: 8,
3972
+ cacheRead: 0.3,
3973
+ cacheWrite: 0,
3974
+ },
3975
+ contextWindow: 262000,
3976
+ maxTokens: 262000,
3977
+ },
3890
3978
  "accounts/fireworks/routers/kimi-k2p6-turbo": {
3891
3979
  id: "accounts/fireworks/routers/kimi-k2p6-turbo",
3892
3980
  name: "Kimi K2.6 Turbo",
@@ -6019,11 +6107,11 @@ export const MODELS = {
6019
6107
  api: "mistral-conversations",
6020
6108
  provider: "mistral",
6021
6109
  baseUrl: "https://api.mistral.ai",
6022
- reasoning: true,
6110
+ reasoning: false,
6023
6111
  input: ["text", "image"],
6024
6112
  cost: {
6025
- input: 1.5,
6026
- output: 7.5,
6113
+ input: 0.4,
6114
+ output: 2,
6027
6115
  cacheRead: 0,
6028
6116
  cacheWrite: 0,
6029
6117
  },
@@ -8367,9 +8455,9 @@ export const MODELS = {
8367
8455
  contextWindow: 200000,
8368
8456
  maxTokens: 32000,
8369
8457
  },
8370
- "nemotron-3-super-free": {
8371
- id: "nemotron-3-super-free",
8372
- name: "Nemotron 3 Super Free",
8458
+ "nemotron-3-ultra-free": {
8459
+ id: "nemotron-3-ultra-free",
8460
+ name: "Nemotron 3 Ultra Free",
8373
8461
  api: "openai-completions",
8374
8462
  provider: "opencode",
8375
8463
  baseUrl: "https://opencode.ai/zen/v1",
@@ -8381,7 +8469,7 @@ export const MODELS = {
8381
8469
  cacheRead: 0,
8382
8470
  cacheWrite: 0,
8383
8471
  },
8384
- contextWindow: 204800,
8472
+ contextWindow: 1000000,
8385
8473
  maxTokens: 128000,
8386
8474
  },
8387
8475
  "qwen3.5-plus": {
@@ -8628,7 +8716,7 @@ export const MODELS = {
8628
8716
  cacheRead: 0.05,
8629
8717
  cacheWrite: 0.625,
8630
8718
  },
8631
- contextWindow: 262144,
8719
+ contextWindow: 1000000,
8632
8720
  maxTokens: 65536,
8633
8721
  },
8634
8722
  "qwen3.7-max": {
@@ -8662,7 +8750,7 @@ export const MODELS = {
8662
8750
  cacheRead: 0.04,
8663
8751
  cacheWrite: 0.5,
8664
8752
  },
8665
- contextWindow: 262144,
8753
+ contextWindow: 1000000,
8666
8754
  maxTokens: 65536,
8667
8755
  },
8668
8756
  },
@@ -9844,7 +9932,7 @@ export const MODELS = {
9844
9932
  input: ["text"],
9845
9933
  cost: {
9846
9934
  input: 0.02,
9847
- output: 0.049999999999999996,
9935
+ output: 0.03,
9848
9936
  cacheRead: 0,
9849
9937
  cacheWrite: 0,
9850
9938
  },
@@ -10533,6 +10621,23 @@ export const MODELS = {
10533
10621
  contextWindow: 1000000,
10534
10622
  maxTokens: 262144,
10535
10623
  },
10624
+ "nvidia/nemotron-3-ultra-550b-a55b": {
10625
+ id: "nvidia/nemotron-3-ultra-550b-a55b",
10626
+ name: "NVIDIA: Nemotron 3 Ultra",
10627
+ api: "openai-completions",
10628
+ provider: "openrouter",
10629
+ baseUrl: "https://openrouter.ai/api/v1",
10630
+ reasoning: true,
10631
+ input: ["text"],
10632
+ cost: {
10633
+ input: 0.5,
10634
+ output: 2.5,
10635
+ cacheRead: 0.15,
10636
+ cacheWrite: 0,
10637
+ },
10638
+ contextWindow: 1000000,
10639
+ maxTokens: 16384,
10640
+ },
10536
10641
  "nvidia/nemotron-3-ultra-550b-a55b:free": {
10537
10642
  id: "nvidia/nemotron-3-ultra-550b-a55b:free",
10538
10643
  name: "NVIDIA: Nemotron 3 Ultra (free)",
@@ -11801,7 +11906,7 @@ export const MODELS = {
11801
11906
  cacheWrite: 0,
11802
11907
  },
11803
11908
  contextWindow: 131072,
11804
- maxTokens: 20000,
11909
+ maxTokens: 16384,
11805
11910
  },
11806
11911
  "qwen/qwen3-30b-a3b-instruct-2507": {
11807
11912
  id: "qwen/qwen3-30b-a3b-instruct-2507",
@@ -12466,23 +12571,6 @@ export const MODELS = {
12466
12571
  contextWindow: 256000,
12467
12572
  maxTokens: 128000,
12468
12573
  },
12469
- "sao10k/l3-euryale-70b": {
12470
- id: "sao10k/l3-euryale-70b",
12471
- name: "Sao10k: Llama 3 Euryale 70B v2.1",
12472
- api: "openai-completions",
12473
- provider: "openrouter",
12474
- baseUrl: "https://openrouter.ai/api/v1",
12475
- reasoning: false,
12476
- input: ["text"],
12477
- cost: {
12478
- input: 1.48,
12479
- output: 1.48,
12480
- cacheRead: 0,
12481
- cacheWrite: 0,
12482
- },
12483
- contextWindow: 8192,
12484
- maxTokens: 8192,
12485
- },
12486
12574
  "sao10k/l3.1-euryale-70b": {
12487
12575
  id: "sao10k/l3.1-euryale-70b",
12488
12576
  name: "Sao10K: Llama 3.1 Euryale 70B v2.2",
@@ -13216,7 +13304,7 @@ export const MODELS = {
13216
13304
  },
13217
13305
  "deepseek-ai/DeepSeek-V3": {
13218
13306
  id: "deepseek-ai/DeepSeek-V3",
13219
- name: "DeepSeek V3",
13307
+ name: "DeepSeek-V3",
13220
13308
  api: "openai-completions",
13221
13309
  provider: "together",
13222
13310
  baseUrl: "https://api.together.ai/v1",
@@ -13364,6 +13452,25 @@ export const MODELS = {
13364
13452
  contextWindow: 262144,
13365
13453
  maxTokens: 131000,
13366
13454
  },
13455
+ "nvidia/nemotron-3-ultra-550b-a55b": {
13456
+ id: "nvidia/nemotron-3-ultra-550b-a55b",
13457
+ name: "Nemotron 3 Ultra 550B A55B",
13458
+ api: "openai-completions",
13459
+ provider: "together",
13460
+ baseUrl: "https://api.together.ai/v1",
13461
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
13462
+ reasoning: true,
13463
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
13464
+ input: ["text"],
13465
+ cost: {
13466
+ input: 0.6,
13467
+ output: 3.6,
13468
+ cacheRead: 0.2,
13469
+ cacheWrite: 0,
13470
+ },
13471
+ contextWindow: 512300,
13472
+ maxTokens: 512300,
13473
+ },
13367
13474
  "openai/gpt-oss-120b": {
13368
13475
  id: "openai/gpt-oss-120b",
13369
13476
  name: "GPT OSS 120B",
@@ -15060,6 +15167,23 @@ export const MODELS = {
15060
15167
  contextWindow: 256000,
15061
15168
  maxTokens: 32000,
15062
15169
  },
15170
+ "nvidia/nemotron-3-ultra-550b-a55b": {
15171
+ id: "nvidia/nemotron-3-ultra-550b-a55b",
15172
+ name: "Nemotron 3 Ultra",
15173
+ api: "anthropic-messages",
15174
+ provider: "vercel-ai-gateway",
15175
+ baseUrl: "https://ai-gateway.vercel.sh",
15176
+ reasoning: true,
15177
+ input: ["text"],
15178
+ cost: {
15179
+ input: 0.6,
15180
+ output: 2.4,
15181
+ cacheRead: 0.12,
15182
+ cacheWrite: 0,
15183
+ },
15184
+ contextWindow: 1000000,
15185
+ maxTokens: 65000,
15186
+ },
15063
15187
  "nvidia/nemotron-nano-12b-v2-vl": {
15064
15188
  id: "nvidia/nemotron-nano-12b-v2-vl",
15065
15189
  name: "Nvidia Nemotron Nano 12B V2 VL",