@kolisachint/hoocode-ai 0.5.89 → 0.6.0

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 (14) hide show
  1. package/dist/models.generated.d.ts +526 -445
  2. package/dist/models.generated.d.ts.map +1 -1
  3. package/dist/models.generated.js +686 -612
  4. package/dist/models.generated.js.map +1 -1
  5. package/dist/providers/anthropic.d.ts.map +1 -1
  6. package/dist/providers/anthropic.js +5 -2
  7. package/dist/providers/anthropic.js.map +1 -1
  8. package/dist/providers/openai-completions.d.ts.map +1 -1
  9. package/dist/providers/openai-completions.js +7 -2
  10. package/dist/providers/openai-completions.js.map +1 -1
  11. package/dist/providers/openai-responses.d.ts.map +1 -1
  12. package/dist/providers/openai-responses.js +7 -2
  13. package/dist/providers/openai-responses.js.map +1 -1
  14. package/package.json +2 -2
package/dist/models.generated.js CHANGED
@@ -265,6 +265,24 @@ export const MODELS = {
265
265
  contextWindow: 1000000,
266
266
  maxTokens: 128000,
267
267
  },
268
+ "claude-sonnet-5-5": {
269
+ id: "claude-sonnet-5-5",
270
+ name: "Claude Sonnet 5.5",
271
+ api: "anthropic-messages",
272
+ provider: "anthropic",
273
+ baseUrl: "https://api.anthropic.com",
274
+ reasoning: true,
275
+ thinkingLevelMap: { "xhigh": "xhigh" },
276
+ input: ["text", "image"],
277
+ cost: {
278
+ input: 2,
279
+ output: 10,
280
+ cacheRead: 0.2,
281
+ cacheWrite: 2.5,
282
+ },
283
+ contextWindow: 1000000,
284
+ maxTokens: 128000,
285
+ },
268
286
  },
269
287
  "azure-openai-responses": {
270
288
  "gpt-4": {
@@ -923,6 +941,58 @@ export const MODELS = {
923
941
  contextWindow: 1050000,
924
942
  maxTokens: 128000,
925
943
  },
944
+ "gpt-6.1-sol": {
945
+ id: "gpt-6.1-sol",
946
+ name: "GPT-6.1 Sol",
947
+ api: "azure-openai-responses",
948
+ provider: "azure-openai-responses",
949
+ baseUrl: "",
950
+ reasoning: true,
951
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
952
+ input: ["text", "image"],
953
+ cost: {
954
+ input: 2,
955
+ output: 10,
956
+ cacheRead: 0.1,
957
+ cacheWrite: 2.5,
958
+ },
959
+ contextWindow: 1050000,
960
+ maxTokens: 128000,
961
+ },
962
+ "gpt-daybreak-blue-latest": {
963
+ id: "gpt-daybreak-blue-latest",
964
+ name: "Daybreak Blue",
965
+ api: "azure-openai-responses",
966
+ provider: "azure-openai-responses",
967
+ baseUrl: "",
968
+ reasoning: true,
969
+ input: ["text", "image"],
970
+ cost: {
971
+ input: 4,
972
+ output: 20,
973
+ cacheRead: 0.4,
974
+ cacheWrite: 5,
975
+ },
976
+ contextWindow: 1050000,
977
+ maxTokens: 128000,
978
+ },
979
+ "gpt-daybreak-red-latest": {
980
+ id: "gpt-daybreak-red-latest",
981
+ name: "Daybreak Red",
982
+ api: "azure-openai-responses",
983
+ provider: "azure-openai-responses",
984
+ baseUrl: "",
985
+ reasoning: true,
986
+ input: ["text", "image"],
987
+ cost: {
988
+ input: 12.5,
989
+ output: 75,
990
+ cacheRead: 1.25,
991
+ cacheWrite: 15.625,
992
+ },
993
+ contextWindow: 400000,
994
+ maxTokens: 128000,
995
+ },
926
996
  "gpt-realtime-2.1": {
927
997
  id: "gpt-realtime-2.1",
928
998
  name: "GPT-Realtime-2.1",
@@ -1072,11 +1142,11 @@ export const MODELS = {
1072
1142
  cost: {
1073
1143
  input: 0.99,
1074
1144
  output: 1.49,
1075
- cacheRead: 0,
1145
+ cacheRead: 0.99,
1076
1146
  cacheWrite: 0,
1077
1147
  },
1078
- contextWindow: 65536,
1079
- maxTokens: 32768,
1148
+ contextWindow: 131072,
1149
+ maxTokens: 40960,
1080
1150
  },
1081
1151
  },
1082
1152
  "deepseek": {
@@ -1120,74 +1190,6 @@ export const MODELS = {
1120
1190
  },
1121
1191
  },
1122
1192
  "fireworks": {
1123
- "accounts/fireworks/models/deepseek-v4-flash-0731": {
1124
- id: "accounts/fireworks/models/deepseek-v4-flash-0731",
1125
- name: "DeepSeek V4 Flash 0731",
1126
- api: "anthropic-messages",
1127
- provider: "fireworks",
1128
- baseUrl: "https://api.fireworks.ai/inference",
1129
- reasoning: true,
1130
- input: ["text"],
1131
- cost: {
1132
- input: 0.22,
1133
- output: 0.66,
1134
- cacheRead: 0.007,
1135
- cacheWrite: 0,
1136
- },
1137
- contextWindow: 1000000,
1138
- maxTokens: 384000,
1139
- },
1140
- "accounts/fireworks/models/deepseek-v4-flash-vision-exp": {
1141
- id: "accounts/fireworks/models/deepseek-v4-flash-vision-exp",
1142
- name: "DeepSeek V4 Flash Vision Exp",
1143
- api: "anthropic-messages",
1144
- provider: "fireworks",
1145
- baseUrl: "https://api.fireworks.ai/inference",
1146
- reasoning: true,
1147
- input: ["text", "image"],
1148
- cost: {
1149
- input: 0.22,
1150
- output: 0.66,
1151
- cacheRead: 0.007,
1152
- cacheWrite: 0,
1153
- },
1154
- contextWindow: 1000000,
1155
- maxTokens: 384000,
1156
- },
1157
- "accounts/fireworks/models/deepseek-v4-pro": {
1158
- id: "accounts/fireworks/models/deepseek-v4-pro",
1159
- name: "DeepSeek V4 Pro",
1160
- api: "anthropic-messages",
1161
- provider: "fireworks",
1162
- baseUrl: "https://api.fireworks.ai/inference",
1163
- reasoning: true,
1164
- input: ["text"],
1165
- cost: {
1166
- input: 1.2,
1167
- output: 1.2,
1168
- cacheRead: 0.6,
1169
- cacheWrite: 0,
1170
- },
1171
- contextWindow: 1000000,
1172
- maxTokens: 384000,
1173
- },
1174
- "accounts/fireworks/models/deepseek-v4-pro-0813": {
1175
- id: "accounts/fireworks/models/deepseek-v4-pro-0813",
1176
- name: "DeepSeek V4 Pro 0813",
1177
- api: "anthropic-messages",
1178
- provider: "fireworks",
1179
- baseUrl: "https://api.fireworks.ai/inference",
1180
- reasoning: true,
1181
- input: ["text"],
1182
- cost: {
1183
- input: 1.32,
1184
- output: 3.96,
1185
- cacheRead: 0.044,
1186
- cacheWrite: 0,
1187
- },
1188
- contextWindow: 1000000,
1189
- maxTokens: 384000,
1190
- },
1191
1193
  "accounts/fireworks/models/deepseek-v4p1-flash": {
1192
1194
  id: "accounts/fireworks/models/deepseek-v4p1-flash",
1193
1195
  name: "DeepSeek V4.1 Flash",
@@ -1222,23 +1224,6 @@ export const MODELS = {
1222
1224
  contextWindow: 1048576,
1223
1225
  maxTokens: 131072,
1224
1226
  },
1225
- "accounts/fireworks/models/glm-5p2": {
1226
- id: "accounts/fireworks/models/glm-5p2",
1227
- name: "GLM 5.2",
1228
- api: "anthropic-messages",
1229
- provider: "fireworks",
1230
- baseUrl: "https://api.fireworks.ai/inference",
1231
- reasoning: true,
1232
- input: ["text"],
1233
- cost: {
1234
- input: 1.4,
1235
- output: 4.4,
1236
- cacheRead: 0.14,
1237
- cacheWrite: 0,
1238
- },
1239
- contextWindow: 1048575,
1240
- maxTokens: 131072,
1241
- },
1242
1227
  "accounts/fireworks/models/glm-5p3": {
1243
1228
  id: "accounts/fireworks/models/glm-5p3",
1244
1229
  name: "GLM 5.3",
@@ -1307,40 +1292,6 @@ export const MODELS = {
1307
1292
  contextWindow: 1048576,
1308
1293
  maxTokens: 1048576,
1309
1294
  },
1310
- "accounts/fireworks/models/kimi-k2p6": {
1311
- id: "accounts/fireworks/models/kimi-k2p6",
1312
- name: "Kimi K2.6",
1313
- api: "anthropic-messages",
1314
- provider: "fireworks",
1315
- baseUrl: "https://api.fireworks.ai/inference",
1316
- reasoning: true,
1317
- input: ["text", "image"],
1318
- cost: {
1319
- input: 0.95,
1320
- output: 4,
1321
- cacheRead: 0.16,
1322
- cacheWrite: 0,
1323
- },
1324
- contextWindow: 262000,
1325
- maxTokens: 262000,
1326
- },
1327
- "accounts/fireworks/models/kimi-k2p7-code": {
1328
- id: "accounts/fireworks/models/kimi-k2p7-code",
1329
- name: "Kimi K2.7 Code",
1330
- api: "anthropic-messages",
1331
- provider: "fireworks",
1332
- baseUrl: "https://api.fireworks.ai/inference",
1333
- reasoning: true,
1334
- input: ["text", "image"],
1335
- cost: {
1336
- input: 0.95,
1337
- output: 4,
1338
- cacheRead: 0.19,
1339
- cacheWrite: 0,
1340
- },
1341
- contextWindow: 262000,
1342
- maxTokens: 262000,
1343
- },
1344
1295
  "accounts/fireworks/models/kimi-k3": {
1345
1296
  id: "accounts/fireworks/models/kimi-k3",
1346
1297
  name: "Kimi K3",
@@ -1358,23 +1309,6 @@ export const MODELS = {
1358
1309
  contextWindow: 1048576,
1359
1310
  maxTokens: 131072,
1360
1311
  },
1361
- "accounts/fireworks/models/minimax-m2p7": {
1362
- id: "accounts/fireworks/models/minimax-m2p7",
1363
- name: "MiniMax-M2.7",
1364
- api: "anthropic-messages",
1365
- provider: "fireworks",
1366
- baseUrl: "https://api.fireworks.ai/inference",
1367
- reasoning: true,
1368
- input: ["text"],
1369
- cost: {
1370
- input: 1.2,
1371
- output: 1.2,
1372
- cacheRead: 0.6,
1373
- cacheWrite: 0,
1374
- },
1375
- contextWindow: 196608,
1376
- maxTokens: 131072,
1377
- },
1378
1312
  "accounts/fireworks/models/minimax-m3": {
1379
1313
  id: "accounts/fireworks/models/minimax-m3",
1380
1314
  name: "MiniMax-M3",
@@ -1392,23 +1326,6 @@ export const MODELS = {
1392
1326
  contextWindow: 512000,
1393
1327
  maxTokens: 512000,
1394
1328
  },
1395
- "accounts/fireworks/models/muse-glimmer-30b": {
1396
- id: "accounts/fireworks/models/muse-glimmer-30b",
1397
- name: "Muse Glimmer 30B",
1398
- api: "anthropic-messages",
1399
- provider: "fireworks",
1400
- baseUrl: "https://api.fireworks.ai/inference",
1401
- reasoning: true,
1402
- input: ["text", "image"],
1403
- cost: {
1404
- input: 0.35,
1405
- output: 1.5,
1406
- cacheRead: 0.04,
1407
- cacheWrite: 0,
1408
- },
1409
- contextWindow: 131072,
1410
- maxTokens: 131072,
1411
- },
1412
1329
  "accounts/fireworks/models/nemotron-3-ultra-nvfp4": {
1413
1330
  id: "accounts/fireworks/models/nemotron-3-ultra-nvfp4",
1414
1331
  name: "Nemotron 3 Ultra 550B A55B",
@@ -1443,23 +1360,6 @@ export const MODELS = {
1443
1360
  contextWindow: 262144,
1444
1361
  maxTokens: 262144,
1445
1362
  },
1446
- "accounts/fireworks/models/qwen3p7-plus": {
1447
- id: "accounts/fireworks/models/qwen3p7-plus",
1448
- name: "Qwen 3.7 Plus",
1449
- api: "anthropic-messages",
1450
- provider: "fireworks",
1451
- baseUrl: "https://api.fireworks.ai/inference",
1452
- reasoning: true,
1453
- input: ["text", "image"],
1454
- cost: {
1455
- input: 0.4,
1456
- output: 1.6,
1457
- cacheRead: 0.08,
1458
- cacheWrite: 0,
1459
- },
1460
- contextWindow: 262144,
1461
- maxTokens: 65536,
1462
- },
1463
1363
  "accounts/fireworks/models/qwen3p8-2p4t-a95b": {
1464
1364
  id: "accounts/fireworks/models/qwen3p8-2p4t-a95b",
1465
1365
  name: "Qwen3.8 2.4T A95B",
@@ -1511,40 +1411,6 @@ export const MODELS = {
1511
1411
  contextWindow: 1000000,
1512
1412
  maxTokens: 384000,
1513
1413
  },
1514
- "accounts/fireworks/routers/deepseek-pro-latest": {
1515
- id: "accounts/fireworks/routers/deepseek-pro-latest",
1516
- name: "DeepSeek Pro Latest",
1517
- api: "anthropic-messages",
1518
- provider: "fireworks",
1519
- baseUrl: "https://api.fireworks.ai/inference",
1520
- reasoning: true,
1521
- input: ["text"],
1522
- cost: {
1523
- input: 1.32,
1524
- output: 3.96,
1525
- cacheRead: 0.044,
1526
- cacheWrite: 0,
1527
- },
1528
- contextWindow: 1000000,
1529
- maxTokens: 384000,
1530
- },
1531
- "accounts/fireworks/routers/glm-5p2-fast": {
1532
- id: "accounts/fireworks/routers/glm-5p2-fast",
1533
- name: "GLM 5.2 Fast",
1534
- api: "anthropic-messages",
1535
- provider: "fireworks",
1536
- baseUrl: "https://api.fireworks.ai/inference",
1537
- reasoning: true,
1538
- input: ["text"],
1539
- cost: {
1540
- input: 2.1,
1541
- output: 6.6,
1542
- cacheRead: 0.21,
1543
- cacheWrite: 0,
1544
- },
1545
- contextWindow: 1048575,
1546
- maxTokens: 131072,
1547
- },
1548
1414
  "accounts/fireworks/routers/glm-5p3-fast": {
1549
1415
  id: "accounts/fireworks/routers/glm-5p3-fast",
1550
1416
  name: "GLM 5.3 Fast",
@@ -1870,6 +1736,25 @@ export const MODELS = {
1870
1736
  contextWindow: 1000000,
1871
1737
  maxTokens: 128000,
1872
1738
  },
1739
+ "claude-sonnet-5.5": {
1740
+ id: "claude-sonnet-5.5",
1741
+ name: "Claude Sonnet 5.5",
1742
+ api: "anthropic-messages",
1743
+ provider: "github-copilot",
1744
+ baseUrl: "https://api.individual.githubcopilot.com",
1745
+ 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" },
1746
+ reasoning: true,
1747
+ thinkingLevelMap: { "xhigh": "xhigh" },
1748
+ input: ["text", "image"],
1749
+ cost: {
1750
+ input: 2,
1751
+ output: 10,
1752
+ cacheRead: 0.2,
1753
+ cacheWrite: 2.5,
1754
+ },
1755
+ contextWindow: 1000000,
1756
+ maxTokens: 128000,
1757
+ },
1873
1758
  "gemini-3.5-flash": {
1874
1759
  id: "gemini-3.5-flash",
1875
1760
  name: "Gemini 3.5 Flash",
@@ -2177,6 +2062,26 @@ export const MODELS = {
2177
2062
  contextWindow: 1050000,
2178
2063
  maxTokens: 128000,
2179
2064
  },
2065
+ "gpt-6.1-sol": {
2066
+ id: "gpt-6.1-sol",
2067
+ name: "GPT-6.1 Sol",
2068
+ api: "openai-completions",
2069
+ provider: "github-copilot",
2070
+ baseUrl: "https://api.individual.githubcopilot.com",
2071
+ 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" },
2072
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
2073
+ reasoning: true,
2074
+ thinkingLevelMap: { "xhigh": "xhigh" },
2075
+ input: ["text", "image"],
2076
+ cost: {
2077
+ input: 2,
2078
+ output: 10,
2079
+ cacheRead: 0.1,
2080
+ cacheWrite: 2.5,
2081
+ },
2082
+ contextWindow: 1050000,
2083
+ maxTokens: 128000,
2084
+ },
2180
2085
  "grok-4.5": {
2181
2086
  id: "grok-4.5",
2182
2087
  name: "Grok 4.5",
@@ -5545,23 +5450,6 @@ export const MODELS = {
5545
5450
  contextWindow: 32768,
5546
5451
  maxTokens: 16384,
5547
5452
  },
5548
- "moonshotai/kimi-k2-instruct-0905": {
5549
- id: "moonshotai/kimi-k2-instruct-0905",
5550
- name: "Kimi K2 0905",
5551
- api: "openai-completions",
5552
- provider: "nvidia",
5553
- baseUrl: "https://integrate.api.nvidia.com/v1",
5554
- reasoning: false,
5555
- input: ["text"],
5556
- cost: {
5557
- input: 0,
5558
- output: 0,
5559
- cacheRead: 0,
5560
- cacheWrite: 0,
5561
- },
5562
- contextWindow: 262144,
5563
- maxTokens: 262144,
5564
- },
5565
5453
  "moonshotai/kimi-k2.6": {
5566
5454
  id: "moonshotai/kimi-k2.6",
5567
5455
  name: "Kimi K2.6",
@@ -5864,26 +5752,9 @@ export const MODELS = {
5864
5752
  output: 0,
5865
5753
  cacheRead: 0,
5866
5754
  cacheWrite: 0,
5867
- },
5868
- contextWindow: 131072,
5869
- maxTokens: 131072,
5870
- },
5871
- "openai/gpt-oss-120b": {
5872
- id: "openai/gpt-oss-120b",
5873
- name: "GPT-OSS-120B",
5874
- api: "openai-completions",
5875
- provider: "nvidia",
5876
- baseUrl: "https://integrate.api.nvidia.com/v1",
5877
- reasoning: true,
5878
- input: ["text"],
5879
- cost: {
5880
- input: 0,
5881
- output: 0,
5882
- cacheRead: 0,
5883
- cacheWrite: 0,
5884
- },
5885
- contextWindow: 128000,
5886
- maxTokens: 8192,
5755
+ },
5756
+ contextWindow: 131072,
5757
+ maxTokens: 131072,
5887
5758
  },
5888
5759
  "openai/gpt-oss-20b": {
5889
5760
  id: "openai/gpt-oss-20b",
@@ -6798,6 +6669,58 @@ export const MODELS = {
6798
6669
  contextWindow: 1050000,
6799
6670
  maxTokens: 128000,
6800
6671
  },
6672
+ "gpt-6.1-sol": {
6673
+ id: "gpt-6.1-sol",
6674
+ name: "GPT-6.1 Sol",
6675
+ api: "openai-responses",
6676
+ provider: "openai",
6677
+ baseUrl: "https://api.openai.com/v1",
6678
+ reasoning: true,
6679
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
6680
+ input: ["text", "image"],
6681
+ cost: {
6682
+ input: 2,
6683
+ output: 10,
6684
+ cacheRead: 0.1,
6685
+ cacheWrite: 2.5,
6686
+ },
6687
+ contextWindow: 1050000,
6688
+ maxTokens: 128000,
6689
+ },
6690
+ "gpt-daybreak-blue-latest": {
6691
+ id: "gpt-daybreak-blue-latest",
6692
+ name: "Daybreak Blue",
6693
+ api: "openai-responses",
6694
+ provider: "openai",
6695
+ baseUrl: "https://api.openai.com/v1",
6696
+ reasoning: true,
6697
+ input: ["text", "image"],
6698
+ cost: {
6699
+ input: 4,
6700
+ output: 20,
6701
+ cacheRead: 0.4,
6702
+ cacheWrite: 5,
6703
+ },
6704
+ contextWindow: 1050000,
6705
+ maxTokens: 128000,
6706
+ },
6707
+ "gpt-daybreak-red-latest": {
6708
+ id: "gpt-daybreak-red-latest",
6709
+ name: "Daybreak Red",
6710
+ api: "openai-responses",
6711
+ provider: "openai",
6712
+ baseUrl: "https://api.openai.com/v1",
6713
+ reasoning: true,
6714
+ input: ["text", "image"],
6715
+ cost: {
6716
+ input: 12.5,
6717
+ output: 75,
6718
+ cacheRead: 1.25,
6719
+ cacheWrite: 15.625,
6720
+ },
6721
+ contextWindow: 400000,
6722
+ maxTokens: 128000,
6723
+ },
6801
6724
  "gpt-realtime-2.1": {
6802
6725
  id: "gpt-realtime-2.1",
6803
6726
  name: "GPT-Realtime-2.1",
@@ -7471,6 +7394,24 @@ export const MODELS = {
7471
7394
  contextWindow: 1000000,
7472
7395
  maxTokens: 128000,
7473
7396
  },
7397
+ "claude-sonnet-5-5": {
7398
+ id: "claude-sonnet-5-5",
7399
+ name: "Claude Sonnet 5.5",
7400
+ api: "anthropic-messages",
7401
+ provider: "opencode",
7402
+ baseUrl: "https://opencode.ai/zen",
7403
+ reasoning: true,
7404
+ thinkingLevelMap: { "xhigh": "xhigh" },
7405
+ input: ["text", "image"],
7406
+ cost: {
7407
+ input: 2,
7408
+ output: 10,
7409
+ cacheRead: 0.2,
7410
+ cacheWrite: 2.5,
7411
+ },
7412
+ contextWindow: 1000000,
7413
+ maxTokens: 128000,
7414
+ },
7474
7415
  "deepseek-v4-flash": {
7475
7416
  id: "deepseek-v4-flash",
7476
7417
  name: "DeepSeek V4 Flash",
@@ -8154,6 +8095,24 @@ export const MODELS = {
8154
8095
  contextWindow: 1050000,
8155
8096
  maxTokens: 128000,
8156
8097
  },
8098
+ "gpt-6.1-sol": {
8099
+ id: "gpt-6.1-sol",
8100
+ name: "GPT-6.1 Sol",
8101
+ api: "openai-responses",
8102
+ provider: "opencode",
8103
+ baseUrl: "https://opencode.ai/zen/v1",
8104
+ reasoning: true,
8105
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
8106
+ input: ["text", "image"],
8107
+ cost: {
8108
+ input: 2,
8109
+ output: 10,
8110
+ cacheRead: 0.1,
8111
+ cacheWrite: 2.5,
8112
+ },
8113
+ contextWindow: 1050000,
8114
+ maxTokens: 128000,
8115
+ },
8157
8116
  "grok-4.5": {
8158
8117
  id: "grok-4.5",
8159
8118
  name: "Grok 4.5",
@@ -8190,16 +8149,16 @@ export const MODELS = {
8190
8149
  },
8191
8150
  "grok-4.7": {
8192
8151
  id: "grok-4.7",
8193
- name: "Grok 4.7 (30% Off)",
8152
+ name: "Grok 4.7",
8194
8153
  api: "openai-responses",
8195
8154
  provider: "opencode",
8196
8155
  baseUrl: "https://opencode.ai/zen/v1",
8197
8156
  reasoning: true,
8198
8157
  input: ["text", "image"],
8199
8158
  cost: {
8200
- input: 1.4,
8201
- output: 4.2,
8202
- cacheRead: 0.35,
8159
+ input: 2,
8160
+ output: 6,
8161
+ cacheRead: 0.5,
8203
8162
  cacheWrite: 0,
8204
8163
  },
8205
8164
  contextWindow: 500000,
@@ -8307,6 +8266,23 @@ export const MODELS = {
8307
8266
  contextWindow: 262144,
8308
8267
  maxTokens: 32768,
8309
8268
  },
8269
+ "longcat-2.5-preview-free": {
8270
+ id: "longcat-2.5-preview-free",
8271
+ name: "LongCat 2.5 Preview Free",
8272
+ api: "openai-completions",
8273
+ provider: "opencode",
8274
+ baseUrl: "https://opencode.ai/zen/v1",
8275
+ reasoning: true,
8276
+ input: ["text", "image"],
8277
+ cost: {
8278
+ input: 0,
8279
+ output: 0,
8280
+ cacheRead: 0,
8281
+ cacheWrite: 0,
8282
+ },
8283
+ contextWindow: 1000000,
8284
+ maxTokens: 131072,
8285
+ },
8310
8286
  "mimo-v2.6-flash-free": {
8311
8287
  id: "mimo-v2.6-flash-free",
8312
8288
  name: "MiMo-V2.6-Flash Free",
@@ -8392,23 +8368,6 @@ export const MODELS = {
8392
8368
  contextWindow: 1048576,
8393
8369
  maxTokens: 131072,
8394
8370
  },
8395
- "muse-spark-1.2-contributor-free": {
8396
- id: "muse-spark-1.2-contributor-free",
8397
- name: "Muse Spark 1.2 Free",
8398
- api: "openai-responses",
8399
- provider: "opencode",
8400
- baseUrl: "https://opencode.ai/zen/v1",
8401
- reasoning: true,
8402
- input: ["text", "image"],
8403
- cost: {
8404
- input: 0,
8405
- output: 0,
8406
- cacheRead: 0,
8407
- cacheWrite: 0,
8408
- },
8409
- contextWindow: 1048576,
8410
- maxTokens: 131072,
8411
- },
8412
8371
  "muse-spark-1.3": {
8413
8372
  id: "muse-spark-1.3",
8414
8373
  name: "Muse Spark 1.3",
@@ -8528,6 +8487,23 @@ export const MODELS = {
8528
8487
  contextWindow: 1000000,
8529
8488
  maxTokens: 131072,
8530
8489
  },
8490
+ "qwen3.8-max": {
8491
+ id: "qwen3.8-max",
8492
+ name: "Qwen3.8 Max",
8493
+ api: "openai-completions",
8494
+ provider: "opencode",
8495
+ baseUrl: "https://opencode.ai/zen/v1",
8496
+ reasoning: true,
8497
+ input: ["text", "image"],
8498
+ cost: {
8499
+ input: 2,
8500
+ output: 6,
8501
+ cacheRead: 0.25,
8502
+ cacheWrite: 2.5,
8503
+ },
8504
+ contextWindow: 262144,
8505
+ maxTokens: 131072,
8506
+ },
8531
8507
  "space-bunny-free": {
8532
8508
  id: "space-bunny-free",
8533
8509
  name: "Space Bunny Free",
@@ -8623,23 +8599,6 @@ export const MODELS = {
8623
8599
  contextWindow: 1000000,
8624
8600
  maxTokens: 384000,
8625
8601
  },
8626
- "glm-5.1": {
8627
- id: "glm-5.1",
8628
- name: "GLM-5.1",
8629
- api: "openai-completions",
8630
- provider: "opencode-go",
8631
- baseUrl: "https://opencode.ai/zen/go/v1",
8632
- reasoning: true,
8633
- input: ["text"],
8634
- cost: {
8635
- input: 1.4,
8636
- output: 4.4,
8637
- cacheRead: 0.26,
8638
- cacheWrite: 0,
8639
- },
8640
- contextWindow: 202752,
8641
- maxTokens: 32768,
8642
- },
8643
8602
  "glm-5.2": {
8644
8603
  id: "glm-5.2",
8645
8604
  name: "GLM-5.2",
@@ -8795,24 +8754,6 @@ export const MODELS = {
8795
8754
  contextWindow: 1024000,
8796
8755
  maxTokens: 64000,
8797
8756
  },
8798
- "kimi-k2.6": {
8799
- id: "kimi-k2.6",
8800
- name: "Kimi K2.6",
8801
- api: "openai-completions",
8802
- provider: "opencode-go",
8803
- baseUrl: "https://opencode.ai/zen/go/v1",
8804
- compat: { "requiresReasoningContentOnAssistantMessages": true },
8805
- reasoning: true,
8806
- input: ["text", "image"],
8807
- cost: {
8808
- input: 0.95,
8809
- output: 4,
8810
- cacheRead: 0.16,
8811
- cacheWrite: 0,
8812
- },
8813
- contextWindow: 262144,
8814
- maxTokens: 65536,
8815
- },
8816
8757
  "kimi-k2.7-code": {
8817
8758
  id: "kimi-k2.7-code",
8818
8759
  name: "Kimi K2.7 Code",
@@ -8864,6 +8805,23 @@ export const MODELS = {
8864
8805
  contextWindow: 1000000,
8865
8806
  maxTokens: 131072,
8866
8807
  },
8808
+ "longcat-2.5-preview-free": {
8809
+ id: "longcat-2.5-preview-free",
8810
+ name: "LongCat 2.5 Preview Free",
8811
+ api: "openai-completions",
8812
+ provider: "opencode-go",
8813
+ baseUrl: "https://opencode.ai/zen/go/v1",
8814
+ reasoning: true,
8815
+ input: ["text", "image"],
8816
+ cost: {
8817
+ input: 0,
8818
+ output: 0,
8819
+ cacheRead: 0,
8820
+ cacheWrite: 0,
8821
+ },
8822
+ contextWindow: 1000000,
8823
+ maxTokens: 131072,
8824
+ },
8867
8825
  "mimo-v2.5": {
8868
8826
  id: "mimo-v2.5",
8869
8827
  name: "MiMo V2.5",
@@ -9000,42 +8958,6 @@ export const MODELS = {
9000
8958
  contextWindow: 1048576,
9001
8959
  maxTokens: 131072,
9002
8960
  },
9003
- "qwen3.6-plus": {
9004
- id: "qwen3.6-plus",
9005
- name: "Qwen3.6 Plus",
9006
- api: "openai-completions",
9007
- provider: "opencode-go",
9008
- baseUrl: "https://opencode.ai/zen/go/v1",
9009
- compat: { "thinkingFormat": "qwen" },
9010
- reasoning: true,
9011
- input: ["text", "image"],
9012
- cost: {
9013
- input: 0.5,
9014
- output: 3,
9015
- cacheRead: 0.05,
9016
- cacheWrite: 0.625,
9017
- },
9018
- contextWindow: 1000000,
9019
- maxTokens: 65536,
9020
- },
9021
- "qwen3.7-max": {
9022
- id: "qwen3.7-max",
9023
- name: "Qwen3.7 Max",
9024
- api: "openai-completions",
9025
- provider: "opencode-go",
9026
- baseUrl: "https://opencode.ai/zen/go/v1",
9027
- compat: { "thinkingFormat": "qwen" },
9028
- reasoning: true,
9029
- input: ["text"],
9030
- cost: {
9031
- input: 2.5,
9032
- output: 7.5,
9033
- cacheRead: 0.5,
9034
- cacheWrite: 3.125,
9035
- },
9036
- contextWindow: 1000000,
9037
- maxTokens: 65536,
9038
- },
9039
8961
  "qwen3.7-plus": {
9040
8962
  id: "qwen3.7-plus",
9041
8963
  name: "Qwen3.7 Plus",
@@ -9277,23 +9199,6 @@ export const MODELS = {
9277
9199
  contextWindow: 300000,
9278
9200
  maxTokens: 5120,
9279
9201
  },
9280
- "anthropic/claude-3-haiku": {
9281
- id: "anthropic/claude-3-haiku",
9282
- name: "Anthropic: Claude 3 Haiku",
9283
- api: "openai-completions",
9284
- provider: "openrouter",
9285
- baseUrl: "https://openrouter.ai/api/v1",
9286
- reasoning: false,
9287
- input: ["text", "image"],
9288
- cost: {
9289
- input: 0.25,
9290
- output: 1.25,
9291
- cacheRead: 0.03,
9292
- cacheWrite: 0.3,
9293
- },
9294
- contextWindow: 200000,
9295
- maxTokens: 4096,
9296
- },
9297
9202
  "anthropic/claude-fable-5": {
9298
9203
  id: "anthropic/claude-fable-5",
9299
9204
  name: "Anthropic: Claude Fable 5",
@@ -9723,17 +9628,53 @@ export const MODELS = {
9723
9628
  reasoning: true,
9724
9629
  input: ["text", "image"],
9725
9630
  cost: {
9726
- input: 1.5,
9727
- output: 7.5,
9728
- cacheRead: 0.15,
9729
- cacheWrite: 1.875,
9631
+ input: 1.5,
9632
+ output: 7.5,
9633
+ cacheRead: 0.15,
9634
+ cacheWrite: 1.875,
9635
+ },
9636
+ contextWindow: 1000000,
9637
+ maxTokens: 128000,
9638
+ },
9639
+ "anthropic/claude-sonnet-5": {
9640
+ id: "anthropic/claude-sonnet-5",
9641
+ name: "Anthropic: Claude Sonnet 5",
9642
+ api: "openai-completions",
9643
+ provider: "openrouter",
9644
+ baseUrl: "https://openrouter.ai/api/v1",
9645
+ reasoning: true,
9646
+ thinkingLevelMap: { "xhigh": "xhigh" },
9647
+ input: ["text", "image"],
9648
+ cost: {
9649
+ input: 2,
9650
+ output: 10,
9651
+ cacheRead: 0.19999999999999998,
9652
+ cacheWrite: 2.5,
9653
+ },
9654
+ contextWindow: 1000000,
9655
+ maxTokens: 128000,
9656
+ },
9657
+ "anthropic/claude-sonnet-5.5": {
9658
+ id: "anthropic/claude-sonnet-5.5",
9659
+ name: "Anthropic: Claude Sonnet 5.5",
9660
+ api: "openai-completions",
9661
+ provider: "openrouter",
9662
+ baseUrl: "https://openrouter.ai/api/v1",
9663
+ reasoning: true,
9664
+ thinkingLevelMap: { "xhigh": "xhigh" },
9665
+ input: ["text", "image"],
9666
+ cost: {
9667
+ input: 2,
9668
+ output: 10,
9669
+ cacheRead: 0.19999999999999998,
9670
+ cacheWrite: 2.5,
9730
9671
  },
9731
9672
  contextWindow: 1000000,
9732
9673
  maxTokens: 128000,
9733
9674
  },
9734
- "anthropic/claude-sonnet-5": {
9735
- id: "anthropic/claude-sonnet-5",
9736
- name: "Anthropic: Claude Sonnet 5",
9675
+ "anthropic/claude-sonnet-5.5:batch": {
9676
+ id: "anthropic/claude-sonnet-5.5:batch",
9677
+ name: "Anthropic: Claude Sonnet 5.5 (batch)",
9737
9678
  api: "openai-completions",
9738
9679
  provider: "openrouter",
9739
9680
  baseUrl: "https://openrouter.ai/api/v1",
@@ -9741,10 +9682,10 @@ export const MODELS = {
9741
9682
  thinkingLevelMap: { "xhigh": "xhigh" },
9742
9683
  input: ["text", "image"],
9743
9684
  cost: {
9744
- input: 2,
9745
- output: 10,
9746
- cacheRead: 0.19999999999999998,
9747
- cacheWrite: 2.5,
9685
+ input: 1,
9686
+ output: 5,
9687
+ cacheRead: 0.09999999999999999,
9688
+ cacheWrite: 1.25,
9748
9689
  },
9749
9690
  contextWindow: 1000000,
9750
9691
  maxTokens: 128000,
@@ -9979,13 +9920,13 @@ export const MODELS = {
9979
9920
  reasoning: false,
9980
9921
  input: ["text"],
9981
9922
  cost: {
9982
- input: 0.32,
9983
- output: 0.8899999999999999,
9923
+ input: 0.2574,
9924
+ output: 1.0287,
9984
9925
  cacheRead: 0,
9985
9926
  cacheWrite: 0,
9986
9927
  },
9987
9928
  contextWindow: 163840,
9988
- maxTokens: 16384,
9929
+ maxTokens: 16000,
9989
9930
  },
9990
9931
  "deepseek/deepseek-chat-v3-0324": {
9991
9932
  id: "deepseek/deepseek-chat-v3-0324",
@@ -9996,9 +9937,9 @@ export const MODELS = {
9996
9937
  reasoning: false,
9997
9938
  input: ["text"],
9998
9939
  cost: {
9999
- input: 0.25,
10000
- output: 1,
10001
- cacheRead: 0,
9940
+ input: 0.29,
9941
+ output: 1.1400000000000001,
9942
+ cacheRead: 0.11,
10002
9943
  cacheWrite: 0,
10003
9944
  },
10004
9945
  contextWindow: 163840,
@@ -10064,13 +10005,13 @@ export const MODELS = {
10064
10005
  reasoning: true,
10065
10006
  input: ["text"],
10066
10007
  cost: {
10067
- input: 0.27,
10008
+ input: 0.3,
10068
10009
  output: 1,
10069
10010
  cacheRead: 0.135,
10070
10011
  cacheWrite: 0,
10071
10012
  },
10072
10013
  contextWindow: 163840,
10073
- maxTokens: 32768,
10014
+ maxTokens: 65536,
10074
10015
  },
10075
10016
  "deepseek/deepseek-v3.2": {
10076
10017
  id: "deepseek/deepseek-v3.2",
@@ -10081,9 +10022,9 @@ export const MODELS = {
10081
10022
  reasoning: true,
10082
10023
  input: ["text"],
10083
10024
  cost: {
10084
- input: 0.26899999999999996,
10085
- output: 0.39999999999999997,
10086
- cacheRead: 0.13449999999999998,
10025
+ input: 0.28,
10026
+ output: 0.42,
10027
+ cacheRead: 0.028,
10087
10028
  cacheWrite: 0,
10088
10029
  },
10089
10030
  contextWindow: 163840,
@@ -10104,7 +10045,7 @@ export const MODELS = {
10104
10045
  cacheWrite: 0,
10105
10046
  },
10106
10047
  contextWindow: 163840,
10107
- maxTokens: 65536,
10048
+ maxTokens: 147456,
10108
10049
  },
10109
10050
  "deepseek/deepseek-v4-flash": {
10110
10051
  id: "deepseek/deepseek-v4-flash",
@@ -10117,13 +10058,13 @@ export const MODELS = {
10117
10058
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
10118
10059
  input: ["text"],
10119
10060
  cost: {
10120
- input: 0.088606,
10121
- output: 0.177212,
10122
- cacheRead: 0.017721200000000003,
10061
+ input: 0.04186,
10062
+ output: 0.08372,
10063
+ cacheRead: 0.008372000000000001,
10123
10064
  cacheWrite: 0,
10124
10065
  },
10125
10066
  contextWindow: 1048576,
10126
- maxTokens: 384000,
10067
+ maxTokens: 131072,
10127
10068
  },
10128
10069
  "deepseek/deepseek-v4-flash-0731": {
10129
10070
  id: "deepseek/deepseek-v4-flash-0731",
@@ -10136,12 +10077,12 @@ export const MODELS = {
10136
10077
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
10137
10078
  input: ["text"],
10138
10079
  cost: {
10139
- input: 0.03,
10140
- output: 0.32,
10141
- cacheRead: 0.016,
10080
+ input: 0.0108,
10081
+ output: 1.28,
10082
+ cacheRead: 0.0108,
10142
10083
  cacheWrite: 0,
10143
10084
  },
10144
- contextWindow: 1310720,
10085
+ contextWindow: 1048576,
10145
10086
  maxTokens: 943718,
10146
10087
  },
10147
10088
  "deepseek/deepseek-v4-flash-vision-exp": {
@@ -10155,13 +10096,13 @@ export const MODELS = {
10155
10096
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
10156
10097
  input: ["text", "image"],
10157
10098
  cost: {
10158
- input: 0.22,
10159
- output: 0.66,
10160
- cacheRead: 0.007,
10099
+ input: 0.21559999999999999,
10100
+ output: 0.6468,
10101
+ cacheRead: 0.00686,
10161
10102
  cacheWrite: 0,
10162
10103
  },
10163
10104
  contextWindow: 1048576,
10164
- maxTokens: 943718,
10105
+ maxTokens: 262144,
10165
10106
  },
10166
10107
  "deepseek/deepseek-v4-pro": {
10167
10108
  id: "deepseek/deepseek-v4-pro",
@@ -10174,9 +10115,9 @@ export const MODELS = {
10174
10115
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
10175
10116
  input: ["text"],
10176
10117
  cost: {
10177
- input: 0.9396,
10178
- output: 1.8792,
10179
- cacheRead: 0.07830000000000001,
10118
+ input: 0.20879999999999999,
10119
+ output: 0.41759999999999997,
10120
+ cacheRead: 0.0174,
10180
10121
  cacheWrite: 0,
10181
10122
  },
10182
10123
  contextWindow: 1048576,
@@ -10193,13 +10134,13 @@ export const MODELS = {
10193
10134
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
10194
10135
  input: ["text"],
10195
10136
  cost: {
10196
- input: 0.46199999999999997,
10197
- output: 1.386,
10198
- cacheRead: 0.015399999999999999,
10137
+ input: 0.66,
10138
+ output: 1.9800000000000002,
10139
+ cacheRead: 0.022,
10199
10140
  cacheWrite: 0,
10200
10141
  },
10201
10142
  contextWindow: 1048576,
10202
- maxTokens: 384000,
10143
+ maxTokens: 393216,
10203
10144
  },
10204
10145
  "deepseek/deepseek-v4.1-flash": {
10205
10146
  id: "deepseek/deepseek-v4.1-flash",
@@ -10212,13 +10153,13 @@ export const MODELS = {
10212
10153
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
10213
10154
  input: ["text", "image"],
10214
10155
  cost: {
10215
- input: 0.14,
10216
- output: 0.42,
10217
- cacheRead: 0.004200000000000001,
10156
+ input: 0.03,
10157
+ output: 0.5,
10158
+ cacheRead: 0.01,
10218
10159
  cacheWrite: 0,
10219
10160
  },
10220
10161
  contextWindow: 1048576,
10221
- maxTokens: 131072,
10162
+ maxTokens: 943718,
10222
10163
  },
10223
10164
  "deepseek/deepseek-v4.1-flash:batch": {
10224
10165
  id: "deepseek/deepseek-v4.1-flash:batch",
@@ -10902,23 +10843,6 @@ export const MODELS = {
10902
10843
  contextWindow: 262144,
10903
10844
  maxTokens: 235929,
10904
10845
  },
10905
- "inclusionai/ling-3.0-flash-fin:free": {
10906
- id: "inclusionai/ling-3.0-flash-fin:free",
10907
- name: "inclusionAI: Ling 3.0 Flash Fin (free)",
10908
- api: "openai-completions",
10909
- provider: "openrouter",
10910
- baseUrl: "https://openrouter.ai/api/v1",
10911
- reasoning: true,
10912
- input: ["text"],
10913
- cost: {
10914
- input: 0,
10915
- output: 0,
10916
- cacheRead: 0,
10917
- cacheWrite: 0,
10918
- },
10919
- contextWindow: 262144,
10920
- maxTokens: 32768,
10921
- },
10922
10846
  "inclusionai/ling-3.0-flash-sante:free": {
10923
10847
  id: "inclusionai/ling-3.0-flash-sante:free",
10924
10848
  name: "inclusionAI: Ling 3.0 Flash Sante (free)",
@@ -10945,9 +10869,9 @@ export const MODELS = {
10945
10869
  reasoning: true,
10946
10870
  input: ["text", "image"],
10947
10871
  cost: {
10948
- input: 0.06,
10949
- output: 0.18,
10950
- cacheRead: 0.012,
10872
+ input: 0.020999999999999998,
10873
+ output: 0.061599999999999995,
10874
+ cacheRead: 0.004200000000000001,
10951
10875
  cacheWrite: 0,
10952
10876
  },
10953
10877
  contextWindow: 262144,
@@ -11098,13 +11022,13 @@ export const MODELS = {
11098
11022
  reasoning: true,
11099
11023
  input: ["text", "image"],
11100
11024
  cost: {
11101
- input: 0.3,
11102
- output: 1.2,
11025
+ input: 0.35,
11026
+ output: 1.5,
11103
11027
  cacheRead: 0.04,
11104
11028
  cacheWrite: 0,
11105
11029
  },
11106
11030
  contextWindow: 131072,
11107
- maxTokens: 16384,
11031
+ maxTokens: 117964,
11108
11032
  },
11109
11033
  "meta/muse-spark-1.1": {
11110
11034
  id: "meta/muse-spark-1.1",
@@ -11200,7 +11124,7 @@ export const MODELS = {
11200
11124
  reasoning: true,
11201
11125
  input: ["text"],
11202
11126
  cost: {
11203
- input: 0.39999999999999997,
11127
+ input: 0.55,
11204
11128
  output: 2.2,
11205
11129
  cacheRead: 0,
11206
11130
  cacheWrite: 0,
@@ -11268,13 +11192,13 @@ export const MODELS = {
11268
11192
  reasoning: true,
11269
11193
  input: ["text"],
11270
11194
  cost: {
11271
- input: 0.3,
11272
- output: 1.2,
11273
- cacheRead: 0.06,
11195
+ input: 0.21,
11196
+ output: 0.84,
11197
+ cacheRead: 0.041999999999999996,
11274
11198
  cacheWrite: 0,
11275
11199
  },
11276
11200
  contextWindow: 204800,
11277
- maxTokens: 131072,
11201
+ maxTokens: 176947,
11278
11202
  },
11279
11203
  "minimax/minimax-m3": {
11280
11204
  id: "minimax/minimax-m3",
@@ -11327,6 +11251,23 @@ export const MODELS = {
11327
11251
  contextWindow: 256000,
11328
11252
  maxTokens: 204800,
11329
11253
  },
11254
+ "mistralai/devstral-2512": {
11255
+ id: "mistralai/devstral-2512",
11256
+ name: "Mistral: Devstral 2 2512",
11257
+ api: "openai-completions",
11258
+ provider: "openrouter",
11259
+ baseUrl: "https://openrouter.ai/api/v1",
11260
+ reasoning: false,
11261
+ input: ["text"],
11262
+ cost: {
11263
+ input: 0.39999999999999997,
11264
+ output: 2,
11265
+ cacheRead: 0.04,
11266
+ cacheWrite: 0,
11267
+ },
11268
+ contextWindow: 262144,
11269
+ maxTokens: 209715,
11270
+ },
11330
11271
  "mistralai/ministral-14b-2512": {
11331
11272
  id: "mistralai/ministral-14b-2512",
11332
11273
  name: "Mistral: Ministral 3 14B 2512",
@@ -11429,6 +11370,23 @@ export const MODELS = {
11429
11370
  contextWindow: 131072,
11430
11371
  maxTokens: 104857,
11431
11372
  },
11373
+ "mistralai/mistral-large-2512": {
11374
+ id: "mistralai/mistral-large-2512",
11375
+ name: "Mistral: Mistral Large 3 2512",
11376
+ api: "openai-completions",
11377
+ provider: "openrouter",
11378
+ baseUrl: "https://openrouter.ai/api/v1",
11379
+ reasoning: false,
11380
+ input: ["text", "image"],
11381
+ cost: {
11382
+ input: 0.5,
11383
+ output: 1.5,
11384
+ cacheRead: 0.049999999999999996,
11385
+ cacheWrite: 0,
11386
+ },
11387
+ contextWindow: 262144,
11388
+ maxTokens: 209715,
11389
+ },
11432
11390
  "mistralai/mistral-large-2512:batch": {
11433
11391
  id: "mistralai/mistral-large-2512:batch",
11434
11392
  name: "Mistral: Mistral Large 3 2512 (batch)",
@@ -11712,11 +11670,11 @@ export const MODELS = {
11712
11670
  cost: {
11713
11671
  input: 0.6,
11714
11672
  output: 2.5,
11715
- cacheRead: 0.15,
11673
+ cacheRead: 0,
11716
11674
  cacheWrite: 0,
11717
11675
  },
11718
11676
  contextWindow: 262144,
11719
- maxTokens: 98304,
11677
+ maxTokens: 235929,
11720
11678
  },
11721
11679
  "moonshotai/kimi-k2.5": {
11722
11680
  id: "moonshotai/kimi-k2.5",
@@ -11744,9 +11702,9 @@ export const MODELS = {
11744
11702
  reasoning: true,
11745
11703
  input: ["text", "image"],
11746
11704
  cost: {
11747
- input: 0.95,
11748
- output: 4,
11749
- cacheRead: 0.16,
11705
+ input: 0.43415,
11706
+ output: 1.8279999999999998,
11707
+ cacheRead: 0.07311999999999999,
11750
11708
  cacheWrite: 0,
11751
11709
  },
11752
11710
  contextWindow: 262144,
@@ -11761,8 +11719,8 @@ export const MODELS = {
11761
11719
  reasoning: true,
11762
11720
  input: ["text", "image"],
11763
11721
  cost: {
11764
- input: 0.6562,
11765
- output: 3.3000000000000003,
11722
+ input: 0.6712,
11723
+ output: 3.35,
11766
11724
  cacheRead: 0.18,
11767
11725
  cacheWrite: 0,
11768
11726
  },
@@ -11778,9 +11736,9 @@ export const MODELS = {
11778
11736
  reasoning: true,
11779
11737
  input: ["text", "image"],
11780
11738
  cost: {
11781
- input: 3,
11782
- output: 15,
11783
- cacheRead: 0.3,
11739
+ input: 0.6797000000000001,
11740
+ output: 10,
11741
+ cacheRead: 0.6797000000000001,
11784
11742
  cacheWrite: 0,
11785
11743
  },
11786
11744
  contextWindow: 1048576,
@@ -11803,35 +11761,18 @@ export const MODELS = {
11803
11761
  contextWindow: 1048576,
11804
11762
  maxTokens: 16384,
11805
11763
  },
11806
- "nex-agi/nex-n2.5-mini:free": {
11807
- id: "nex-agi/nex-n2.5-mini:free",
11808
- name: "Nex AGI: Nex-N2.5-Mini (free)",
11809
- api: "openai-completions",
11810
- provider: "openrouter",
11811
- baseUrl: "https://openrouter.ai/api/v1",
11812
- reasoning: true,
11813
- input: ["text", "image"],
11814
- cost: {
11815
- input: 0,
11816
- output: 0,
11817
- cacheRead: 0,
11818
- cacheWrite: 0,
11819
- },
11820
- contextWindow: 262144,
11821
- maxTokens: 235929,
11822
- },
11823
- "nex-agi/nex-n2.5-pro:free": {
11824
- id: "nex-agi/nex-n2.5-pro:free",
11825
- name: "Nex AGI: Nex-N2.5-Pro (free)",
11764
+ "nex-agi/nex-n2.5-pro": {
11765
+ id: "nex-agi/nex-n2.5-pro",
11766
+ name: "Nex AGI: Nex-N2.5-Pro",
11826
11767
  api: "openai-completions",
11827
11768
  provider: "openrouter",
11828
11769
  baseUrl: "https://openrouter.ai/api/v1",
11829
11770
  reasoning: true,
11830
11771
  input: ["text", "image"],
11831
11772
  cost: {
11832
- input: 0,
11833
- output: 0,
11834
- cacheRead: 0,
11773
+ input: 0.075,
11774
+ output: 0.25,
11775
+ cacheRead: 0.015,
11835
11776
  cacheWrite: 0,
11836
11777
  },
11837
11778
  contextWindow: 262144,
@@ -11948,9 +11889,9 @@ export const MODELS = {
11948
11889
  reasoning: true,
11949
11890
  input: ["text"],
11950
11891
  cost: {
11951
- input: 0.08,
11952
- output: 0.19999999999999998,
11953
- cacheRead: 0.04,
11892
+ input: 0.0595,
11893
+ output: 0.16999999999999998,
11894
+ cacheRead: 0.02975,
11954
11895
  cacheWrite: 0,
11955
11896
  },
11956
11897
  contextWindow: 262144,
@@ -12976,10 +12917,10 @@ export const MODELS = {
12976
12917
  thinkingLevelMap: { "xhigh": "xhigh" },
12977
12918
  input: ["text", "image"],
12978
12919
  cost: {
12979
- input: 2,
12980
- output: 10,
12981
- cacheRead: 0.19999999999999998,
12982
- cacheWrite: 2.5,
12920
+ input: 4,
12921
+ output: 20,
12922
+ cacheRead: 0.39999999999999997,
12923
+ cacheWrite: 5,
12983
12924
  },
12984
12925
  contextWindow: 1050000,
12985
12926
  maxTokens: 128000,
@@ -13313,6 +13254,40 @@ export const MODELS = {
13313
13254
  contextWindow: 1050000,
13314
13255
  maxTokens: 128000,
13315
13256
  },
13257
+ "openai/gpt-6.1-sol": {
13258
+ id: "openai/gpt-6.1-sol",
13259
+ name: "OpenAI: GPT-6.1 Sol",
13260
+ api: "openai-completions",
13261
+ provider: "openrouter",
13262
+ baseUrl: "https://openrouter.ai/api/v1",
13263
+ reasoning: true,
13264
+ input: ["text", "image"],
13265
+ cost: {
13266
+ input: 2,
13267
+ output: 10,
13268
+ cacheRead: 0.09999999999999999,
13269
+ cacheWrite: 2.5,
13270
+ },
13271
+ contextWindow: 1050000,
13272
+ maxTokens: 128000,
13273
+ },
13274
+ "openai/gpt-6.1-sol-pro": {
13275
+ id: "openai/gpt-6.1-sol-pro",
13276
+ name: "OpenAI: GPT-6.1 Sol Pro",
13277
+ api: "openai-completions",
13278
+ provider: "openrouter",
13279
+ baseUrl: "https://openrouter.ai/api/v1",
13280
+ reasoning: true,
13281
+ input: ["text", "image"],
13282
+ cost: {
13283
+ input: 2,
13284
+ output: 10,
13285
+ cacheRead: 0.09999999999999999,
13286
+ cacheWrite: 2.5,
13287
+ },
13288
+ contextWindow: 1050000,
13289
+ maxTokens: 128000,
13290
+ },
13316
13291
  "openai/gpt-audio": {
13317
13292
  id: "openai/gpt-audio",
13318
13293
  name: "OpenAI: GPT Audio",
@@ -13373,13 +13348,13 @@ export const MODELS = {
13373
13348
  reasoning: true,
13374
13349
  input: ["text"],
13375
13350
  cost: {
13376
- input: 0.15,
13377
- output: 0.6,
13378
- cacheRead: 0.075,
13351
+ input: 0.037,
13352
+ output: 0.16999999999999998,
13353
+ cacheRead: 0,
13379
13354
  cacheWrite: 0,
13380
13355
  },
13381
13356
  contextWindow: 131072,
13382
- maxTokens: 65536,
13357
+ maxTokens: 117964,
13383
13358
  },
13384
13359
  "openai/gpt-oss-120b:batch": {
13385
13360
  id: "openai/gpt-oss-120b:batch",
@@ -13409,7 +13384,7 @@ export const MODELS = {
13409
13384
  cost: {
13410
13385
  input: 0.018,
13411
13386
  output: 0.09,
13412
- cacheRead: 0,
13387
+ cacheRead: 0.009,
13413
13388
  cacheWrite: 0,
13414
13389
  },
13415
13390
  contextWindow: 131072,
@@ -13670,6 +13645,23 @@ export const MODELS = {
13670
13645
  contextWindow: 200000,
13671
13646
  maxTokens: 4096,
13672
13647
  },
13648
+ "perceptron/perceptron-mk1.5": {
13649
+ id: "perceptron/perceptron-mk1.5",
13650
+ name: "Perceptron: Perceptron Mk1.5",
13651
+ api: "openai-completions",
13652
+ provider: "openrouter",
13653
+ baseUrl: "https://openrouter.ai/api/v1",
13654
+ reasoning: true,
13655
+ input: ["text", "image"],
13656
+ cost: {
13657
+ input: 0.15,
13658
+ output: 1.5,
13659
+ cacheRead: 0,
13660
+ cacheWrite: 0,
13661
+ },
13662
+ contextWindow: 36864,
13663
+ maxTokens: 8192,
13664
+ },
13673
13665
  "poolside/laguna-s-2.1": {
13674
13666
  id: "poolside/laguna-s-2.1",
13675
13667
  name: "Poolside: Laguna S 2.1",
@@ -13749,7 +13741,7 @@ export const MODELS = {
13749
13741
  cost: {
13750
13742
  input: 0.075,
13751
13743
  output: 0.5,
13752
- cacheRead: 0,
13744
+ cacheRead: 0.0375,
13753
13745
  cacheWrite: 0,
13754
13746
  },
13755
13747
  contextWindow: 262144,
@@ -13917,13 +13909,13 @@ export const MODELS = {
13917
13909
  reasoning: false,
13918
13910
  input: ["text"],
13919
13911
  cost: {
13920
- input: 0.09999999999999999,
13921
- output: 0.3,
13912
+ input: 0.04815,
13913
+ output: 0.19305,
13922
13914
  cacheRead: 0,
13923
13915
  cacheWrite: 0,
13924
13916
  },
13925
13917
  contextWindow: 262144,
13926
- maxTokens: 235929,
13918
+ maxTokens: 32000,
13927
13919
  },
13928
13920
  "qwen/qwen3-30b-a3b-thinking-2507": {
13929
13921
  id: "qwen/qwen3-30b-a3b-thinking-2507",
@@ -14172,13 +14164,13 @@ export const MODELS = {
14172
14164
  reasoning: false,
14173
14165
  input: ["text", "image"],
14174
14166
  cost: {
14175
- input: 0.13,
14176
- output: 0.52,
14167
+ input: 0.15,
14168
+ output: 0.6,
14177
14169
  cacheRead: 0,
14178
14170
  cacheWrite: 0,
14179
14171
  },
14180
14172
  contextWindow: 262144,
14181
- maxTokens: 32768,
14173
+ maxTokens: 16384,
14182
14174
  },
14183
14175
  "qwen/qwen3-vl-30b-a3b-thinking": {
14184
14176
  id: "qwen/qwen3-vl-30b-a3b-thinking",
@@ -14291,13 +14283,13 @@ export const MODELS = {
14291
14283
  reasoning: true,
14292
14284
  input: ["text", "image"],
14293
14285
  cost: {
14294
- input: 0.3125,
14295
- output: 1.25,
14296
- cacheRead: 0.15625,
14286
+ input: 0.1625,
14287
+ output: 1.3,
14288
+ cacheRead: 0,
14297
14289
  cacheWrite: 0,
14298
14290
  },
14299
14291
  contextWindow: 262144,
14300
- maxTokens: 16384,
14292
+ maxTokens: 65536,
14301
14293
  },
14302
14294
  "qwen/qwen3.5-397b-a17b": {
14303
14295
  id: "qwen/qwen3.5-397b-a17b",
@@ -14394,12 +14386,12 @@ export const MODELS = {
14394
14386
  input: ["text", "image"],
14395
14387
  cost: {
14396
14388
  input: 0.32,
14397
- output: 2.7,
14398
- cacheRead: 0.15,
14389
+ output: 3.1999999999999997,
14390
+ cacheRead: 0,
14399
14391
  cacheWrite: 0,
14400
14392
  },
14401
14393
  contextWindow: 262144,
14402
- maxTokens: 262140,
14394
+ maxTokens: 81920,
14403
14395
  },
14404
14396
  "qwen/qwen3.6-35b-a3b": {
14405
14397
  id: "qwen/qwen3.6-35b-a3b",
@@ -14874,7 +14866,7 @@ export const MODELS = {
14874
14866
  cacheRead: 0.16999999999999998,
14875
14867
  cacheWrite: 0,
14876
14868
  },
14877
- contextWindow: 1048576,
14869
+ contextWindow: 524288,
14878
14870
  maxTokens: 471859,
14879
14871
  },
14880
14872
  "thinkingmachines/inkling-small": {
@@ -14891,7 +14883,7 @@ export const MODELS = {
14891
14883
  cacheRead: 0.09999999999999999,
14892
14884
  cacheWrite: 0,
14893
14885
  },
14894
- contextWindow: 1048576,
14886
+ contextWindow: 524288,
14895
14887
  maxTokens: 262144,
14896
14888
  },
14897
14889
  "thinkingmachines/inkling-small:free": {
@@ -14928,6 +14920,23 @@ export const MODELS = {
14928
14920
  contextWindow: 1048576,
14929
14921
  maxTokens: 262144,
14930
14922
  },
14923
+ "typesafe/jev-router": {
14924
+ id: "typesafe/jev-router",
14925
+ name: "TypeSafe: Jev Router",
14926
+ api: "openai-completions",
14927
+ provider: "openrouter",
14928
+ baseUrl: "https://openrouter.ai/api/v1",
14929
+ reasoning: true,
14930
+ input: ["text", "image"],
14931
+ cost: {
14932
+ input: -1000000,
14933
+ output: -1000000,
14934
+ cacheRead: 0,
14935
+ cacheWrite: 0,
14936
+ },
14937
+ contextWindow: 1000000,
14938
+ maxTokens: 4096,
14939
+ },
14931
14940
  "unbiased/pareto": {
14932
14941
  id: "unbiased/pareto",
14933
14942
  name: "Pareto",
@@ -15090,9 +15099,9 @@ export const MODELS = {
15090
15099
  reasoning: true,
15091
15100
  input: ["text", "image"],
15092
15101
  cost: {
15093
- input: 1.5999999999999999,
15094
- output: 4.8,
15095
- cacheRead: 0.39999999999999997,
15102
+ input: 2,
15103
+ output: 6,
15104
+ cacheRead: 0.5,
15096
15105
  cacheWrite: 0,
15097
15106
  },
15098
15107
  contextWindow: 500000,
@@ -15163,7 +15172,7 @@ export const MODELS = {
15163
15172
  cacheRead: 0.0028,
15164
15173
  cacheWrite: 0,
15165
15174
  },
15166
- contextWindow: 1048576,
15175
+ contextWindow: 1050000,
15167
15176
  maxTokens: 131072,
15168
15177
  },
15169
15178
  "xiaomi/mimo-v2.6-pro": {
@@ -15180,7 +15189,7 @@ export const MODELS = {
15180
15189
  cacheRead: 0.0036,
15181
15190
  cacheWrite: 0,
15182
15191
  },
15183
- contextWindow: 1048576,
15192
+ contextWindow: 1050000,
15184
15193
  maxTokens: 131072,
15185
15194
  },
15186
15195
  "xiaomi/mimo-v2.6-pro-ultraspeed": {
@@ -15279,7 +15288,7 @@ export const MODELS = {
15279
15288
  cost: {
15280
15289
  input: 0.3,
15281
15290
  output: 0.8999999999999999,
15282
- cacheRead: 0.055,
15291
+ cacheRead: 0.049999999999999996,
15283
15292
  cacheWrite: 0,
15284
15293
  },
15285
15294
  contextWindow: 131072,
@@ -15294,9 +15303,9 @@ export const MODELS = {
15294
15303
  reasoning: true,
15295
15304
  input: ["text"],
15296
15305
  cost: {
15297
- input: 0.39999999999999997,
15298
- output: 1.75,
15299
- cacheRead: 0.08,
15306
+ input: 0.6,
15307
+ output: 2.2,
15308
+ cacheRead: 0.11,
15300
15309
  cacheWrite: 0,
15301
15310
  },
15302
15311
  contextWindow: 204800,
@@ -15362,13 +15371,13 @@ export const MODELS = {
15362
15371
  reasoning: true,
15363
15372
  input: ["text"],
15364
15373
  cost: {
15365
- input: 0.966,
15366
- output: 3.036,
15367
- cacheRead: 0.1794,
15374
+ input: 0.9646,
15375
+ output: 3.0316,
15376
+ cacheRead: 0.17914,
15368
15377
  cacheWrite: 0,
15369
15378
  },
15370
15379
  contextWindow: 204800,
15371
- maxTokens: 128000,
15380
+ maxTokens: 131072,
15372
15381
  },
15373
15382
  "z-ai/glm-5.2": {
15374
15383
  id: "z-ai/glm-5.2",
@@ -15379,13 +15388,13 @@ export const MODELS = {
15379
15388
  reasoning: true,
15380
15389
  input: ["text"],
15381
15390
  cost: {
15382
- input: 0.6496,
15383
- output: 2.0416,
15384
- cacheRead: 0.12064,
15391
+ input: 1.4,
15392
+ output: 4.4,
15393
+ cacheRead: 0.26,
15385
15394
  cacheWrite: 0,
15386
15395
  },
15387
15396
  contextWindow: 1048576,
15388
- maxTokens: 131072,
15397
+ maxTokens: 943718,
15389
15398
  },
15390
15399
  "z-ai/glm-5.3": {
15391
15400
  id: "z-ai/glm-5.3",
@@ -15396,13 +15405,13 @@ export const MODELS = {
15396
15405
  reasoning: true,
15397
15406
  input: ["text"],
15398
15407
  cost: {
15399
- input: 0.84,
15400
- output: 2.64,
15401
- cacheRead: 0.156,
15408
+ input: 0.2219,
15409
+ output: 3.39,
15410
+ cacheRead: 0.1775,
15402
15411
  cacheWrite: 0,
15403
15412
  },
15404
- contextWindow: 1310720,
15405
- maxTokens: 131072,
15413
+ contextWindow: 1048576,
15414
+ maxTokens: 943718,
15406
15415
  },
15407
15416
  "z-ai/glm-5.3-flash": {
15408
15417
  id: "z-ai/glm-5.3-flash",
@@ -15415,11 +15424,11 @@ export const MODELS = {
15415
15424
  cost: {
15416
15425
  input: 0.15,
15417
15426
  output: 0.5,
15418
- cacheRead: 0.049999999999999996,
15427
+ cacheRead: 0.03,
15419
15428
  cacheWrite: 0,
15420
15429
  },
15421
- contextWindow: 1310720,
15422
- maxTokens: 943718,
15430
+ contextWindow: 1048576,
15431
+ maxTokens: 943717,
15423
15432
  },
15424
15433
  "z-ai/glm-5.3-flash:batch": {
15425
15434
  id: "z-ai/glm-5.3-flash:batch",
@@ -15586,9 +15595,9 @@ export const MODELS = {
15586
15595
  reasoning: true,
15587
15596
  input: ["text", "image"],
15588
15597
  cost: {
15589
- input: 0.04,
15590
- output: 1,
15591
- cacheRead: 0.01,
15598
+ input: 0.0243,
15599
+ output: 0.6,
15600
+ cacheRead: 0.0243,
15592
15601
  cacheWrite: 0,
15593
15602
  },
15594
15603
  contextWindow: 1048576,
@@ -15603,13 +15612,13 @@ export const MODELS = {
15603
15612
  reasoning: true,
15604
15613
  input: ["text"],
15605
15614
  cost: {
15606
- input: 0.39,
15607
- output: 2.9000000000000004,
15608
- cacheRead: 0.25,
15615
+ input: 0.1853,
15616
+ output: 3.5,
15617
+ cacheRead: 0.1853,
15609
15618
  cacheWrite: 0,
15610
15619
  },
15611
15620
  contextWindow: 1048576,
15612
- maxTokens: 943718,
15621
+ maxTokens: 393216,
15613
15622
  },
15614
15623
  "~deepseek/deepseek-v4-flash-latest": {
15615
15624
  id: "~deepseek/deepseek-v4-flash-latest",
@@ -15622,12 +15631,12 @@ export const MODELS = {
15622
15631
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
15623
15632
  input: ["text"],
15624
15633
  cost: {
15625
- input: 0.03,
15626
- output: 0.32,
15627
- cacheRead: 0.016,
15634
+ input: 0.0108,
15635
+ output: 1.28,
15636
+ cacheRead: 0.0108,
15628
15637
  cacheWrite: 0,
15629
15638
  },
15630
- contextWindow: 1310720,
15639
+ contextWindow: 1048576,
15631
15640
  maxTokens: 943718,
15632
15641
  },
15633
15642
  "~google/gemini-flash-latest": {
@@ -15673,9 +15682,9 @@ export const MODELS = {
15673
15682
  reasoning: true,
15674
15683
  input: ["text", "image"],
15675
15684
  cost: {
15676
- input: 1.4,
15677
- output: 10.75,
15678
- cacheRead: 0.3,
15685
+ input: 0.6797000000000001,
15686
+ output: 10,
15687
+ cacheRead: 0.6797000000000001,
15679
15688
  cacheWrite: 0,
15680
15689
  },
15681
15690
  contextWindow: 1048576,
@@ -15743,7 +15752,7 @@ export const MODELS = {
15743
15752
  cost: {
15744
15753
  input: 2,
15745
15754
  output: 10,
15746
- cacheRead: 0.19999999999999998,
15755
+ cacheRead: 0.09999999999999999,
15747
15756
  cacheWrite: 2.5,
15748
15757
  },
15749
15758
  contextWindow: 1050000,
@@ -15775,9 +15784,9 @@ export const MODELS = {
15775
15784
  reasoning: true,
15776
15785
  input: ["text", "image"],
15777
15786
  cost: {
15778
- input: 1.5999999999999999,
15779
- output: 4.8,
15780
- cacheRead: 0.39999999999999997,
15787
+ input: 2,
15788
+ output: 6,
15789
+ cacheRead: 0.5,
15781
15790
  cacheWrite: 0,
15782
15791
  },
15783
15792
  contextWindow: 500000,
@@ -15792,13 +15801,13 @@ export const MODELS = {
15792
15801
  reasoning: true,
15793
15802
  input: ["text", "image"],
15794
15803
  cost: {
15795
- input: 0.045,
15796
- output: 0.14,
15804
+ input: 0.02,
15805
+ output: 0.3,
15797
15806
  cacheRead: 0.01,
15798
15807
  cacheWrite: 0,
15799
15808
  },
15800
- contextWindow: 1310720,
15801
- maxTokens: 128000,
15809
+ contextWindow: 1048576,
15810
+ maxTokens: 943718,
15802
15811
  },
15803
15812
  "~z-ai/glm-latest": {
15804
15813
  id: "~z-ai/glm-latest",
@@ -15809,13 +15818,13 @@ export const MODELS = {
15809
15818
  reasoning: true,
15810
15819
  input: ["text"],
15811
15820
  cost: {
15812
- input: 0.5625,
15813
- output: 2.5,
15814
- cacheRead: 0.125,
15821
+ input: 0.06,
15822
+ output: 2.694,
15823
+ cacheRead: 0.176,
15815
15824
  cacheWrite: 0,
15816
15825
  },
15817
- contextWindow: 1310720,
15818
- maxTokens: 131072,
15826
+ contextWindow: 1048576,
15827
+ maxTokens: 943718,
15819
15828
  },
15820
15829
  },
15821
15830
  "together": {
@@ -16044,44 +16053,6 @@ export const MODELS = {
16044
16053
  contextWindow: 131072,
16045
16054
  maxTokens: 131072,
16046
16055
  },
16047
- "moonshotai/Kimi-K2.6": {
16048
- id: "moonshotai/Kimi-K2.6",
16049
- name: "Kimi K2.6",
16050
- api: "openai-completions",
16051
- provider: "together",
16052
- baseUrl: "https://api.together.ai/v1",
16053
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
16054
- reasoning: true,
16055
- thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
16056
- input: ["text", "image"],
16057
- cost: {
16058
- input: 1.2,
16059
- output: 4.5,
16060
- cacheRead: 0.2,
16061
- cacheWrite: 0,
16062
- },
16063
- contextWindow: 262144,
16064
- maxTokens: 131000,
16065
- },
16066
- "moonshotai/Kimi-K2.7-Code": {
16067
- id: "moonshotai/Kimi-K2.7-Code",
16068
- name: "Kimi K2.7 Code",
16069
- api: "openai-completions",
16070
- provider: "together",
16071
- baseUrl: "https://api.together.ai/v1",
16072
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
16073
- reasoning: true,
16074
- thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
16075
- input: ["text"],
16076
- cost: {
16077
- input: 0.95,
16078
- output: 4,
16079
- cacheRead: 0.19,
16080
- cacheWrite: 0,
16081
- },
16082
- contextWindow: 262144,
16083
- maxTokens: 131072,
16084
- },
16085
16056
  "moonshotai/Kimi-K3": {
16086
16057
  id: "moonshotai/Kimi-K3",
16087
16058
  name: "Kimi K3",
@@ -16569,7 +16540,7 @@ export const MODELS = {
16569
16540
  input: ["text", "image"],
16570
16541
  cost: {
16571
16542
  input: 0.39999999999999997,
16572
- output: 2.5,
16543
+ output: 2.4,
16573
16544
  cacheRead: 0.04,
16574
16545
  cacheWrite: 0.5,
16575
16546
  },
@@ -16758,7 +16729,7 @@ export const MODELS = {
16758
16729
  input: 4,
16759
16730
  output: 12,
16760
16731
  cacheRead: 0.5,
16761
- cacheWrite: 0,
16732
+ cacheWrite: 5,
16762
16733
  },
16763
16734
  contextWindow: 1000000,
16764
16735
  maxTokens: 131072,
@@ -17165,6 +17136,24 @@ export const MODELS = {
17165
17136
  contextWindow: 1000000,
17166
17137
  maxTokens: 128000,
17167
17138
  },
17139
+ "anthropic/claude-sonnet-5.5": {
17140
+ id: "anthropic/claude-sonnet-5.5",
17141
+ name: "Claude Sonnet 5.5",
17142
+ api: "anthropic-messages",
17143
+ provider: "vercel-ai-gateway",
17144
+ baseUrl: "https://ai-gateway.vercel.sh",
17145
+ reasoning: true,
17146
+ thinkingLevelMap: { "xhigh": "xhigh" },
17147
+ input: ["text", "image"],
17148
+ cost: {
17149
+ input: 2,
17150
+ output: 10,
17151
+ cacheRead: 0.19999999999999998,
17152
+ cacheWrite: 2.5,
17153
+ },
17154
+ contextWindow: 1000000,
17155
+ maxTokens: 128000,
17156
+ },
17168
17157
  "arcee-ai/trinity-large-thinking": {
17169
17158
  id: "arcee-ai/trinity-large-thinking",
17170
17159
  name: "Trinity Large Thinking",
@@ -17378,9 +17367,9 @@ export const MODELS = {
17378
17367
  reasoning: true,
17379
17368
  input: ["text", "image"],
17380
17369
  cost: {
17381
- input: 0.22,
17382
- output: 0.66,
17383
- cacheRead: 0.007,
17370
+ input: 0.21559999999999999,
17371
+ output: 0.6468,
17372
+ cacheRead: 0.0068,
17384
17373
  cacheWrite: 0,
17385
17374
  },
17386
17375
  contextWindow: 1048576,
@@ -17437,6 +17426,23 @@ export const MODELS = {
17437
17426
  contextWindow: 1048576,
17438
17427
  maxTokens: 32768,
17439
17428
  },
17429
+ "fireworks/ember-1": {
17430
+ id: "fireworks/ember-1",
17431
+ name: "Ember-1",
17432
+ api: "anthropic-messages",
17433
+ provider: "vercel-ai-gateway",
17434
+ baseUrl: "https://ai-gateway.vercel.sh",
17435
+ reasoning: true,
17436
+ input: ["text", "image"],
17437
+ cost: {
17438
+ input: 3,
17439
+ output: 15,
17440
+ cacheRead: 0.3,
17441
+ cacheWrite: 0,
17442
+ },
17443
+ contextWindow: 1048576,
17444
+ maxTokens: 1048576,
17445
+ },
17440
17446
  "google/gemini-2.5-flash": {
17441
17447
  id: "google/gemini-2.5-flash",
17442
17448
  name: "Gemini 2.5 Flash",
@@ -17735,26 +17741,9 @@ export const MODELS = {
17735
17741
  reasoning: true,
17736
17742
  input: ["text"],
17737
17743
  cost: {
17738
- input: 0,
17739
- output: 0,
17740
- cacheRead: 0,
17741
- cacheWrite: 0,
17742
- },
17743
- contextWindow: 256000,
17744
- maxTokens: 32000,
17745
- },
17746
- "inclusionai/ling-3.0-flash-fin-free": {
17747
- id: "inclusionai/ling-3.0-flash-fin-free",
17748
- name: "Ling 3.0 Flash Fin (Free)",
17749
- api: "anthropic-messages",
17750
- provider: "vercel-ai-gateway",
17751
- baseUrl: "https://ai-gateway.vercel.sh",
17752
- reasoning: true,
17753
- input: ["text"],
17754
- cost: {
17755
- input: 0,
17756
- output: 0,
17757
- cacheRead: 0,
17744
+ input: 0.075,
17745
+ output: 0.22,
17746
+ cacheRead: 0.015,
17758
17747
  cacheWrite: 0,
17759
17748
  },
17760
17749
  contextWindow: 256000,
@@ -17811,6 +17800,40 @@ export const MODELS = {
17811
17800
  contextWindow: 256000,
17812
17801
  maxTokens: 32000,
17813
17802
  },
17803
+ "inclusionai/ling-3.1-flash": {
17804
+ id: "inclusionai/ling-3.1-flash",
17805
+ name: "Ling 3.1 Flash",
17806
+ api: "anthropic-messages",
17807
+ provider: "vercel-ai-gateway",
17808
+ baseUrl: "https://ai-gateway.vercel.sh",
17809
+ reasoning: true,
17810
+ input: ["text"],
17811
+ cost: {
17812
+ input: 0,
17813
+ output: 0,
17814
+ cacheRead: 0,
17815
+ cacheWrite: 0,
17816
+ },
17817
+ contextWindow: 262144,
17818
+ maxTokens: 32768,
17819
+ },
17820
+ "inclusionai/ling-3.1-flash-free": {
17821
+ id: "inclusionai/ling-3.1-flash-free",
17822
+ name: "Ling 3.1 Flash (Free)",
17823
+ api: "anthropic-messages",
17824
+ provider: "vercel-ai-gateway",
17825
+ baseUrl: "https://ai-gateway.vercel.sh",
17826
+ reasoning: true,
17827
+ input: ["text"],
17828
+ cost: {
17829
+ input: 0,
17830
+ output: 0,
17831
+ cacheRead: 0,
17832
+ cacheWrite: 0,
17833
+ },
17834
+ contextWindow: 262144,
17835
+ maxTokens: 32768,
17836
+ },
17814
17837
  "interfaze/interfaze-beta": {
17815
17838
  id: "interfaze/interfaze-beta",
17816
17839
  name: "Interfaze Beta",
@@ -17828,6 +17851,23 @@ export const MODELS = {
17828
17851
  contextWindow: 1000000,
17829
17852
  maxTokens: 32000,
17830
17853
  },
17854
+ "meituan/longcat-2.5-preview": {
17855
+ id: "meituan/longcat-2.5-preview",
17856
+ name: "LongCat 2.5 Preview",
17857
+ api: "anthropic-messages",
17858
+ provider: "vercel-ai-gateway",
17859
+ baseUrl: "https://ai-gateway.vercel.sh",
17860
+ reasoning: true,
17861
+ input: ["text", "image"],
17862
+ cost: {
17863
+ input: 0.3,
17864
+ output: 1.2,
17865
+ cacheRead: 0.006,
17866
+ cacheWrite: 0,
17867
+ },
17868
+ contextWindow: 1048576,
17869
+ maxTokens: 131072,
17870
+ },
17831
17871
  "meta/llama-3.1-70b": {
17832
17872
  id: "meta/llama-3.1-70b",
17833
17873
  name: "Llama 3.1 70B Instruct",
@@ -18383,7 +18423,7 @@ export const MODELS = {
18383
18423
  cost: {
18384
18424
  input: 0.95,
18385
18425
  output: 4,
18386
- cacheRead: 0.16,
18426
+ cacheRead: 0.19,
18387
18427
  cacheWrite: 0,
18388
18428
  },
18389
18429
  contextWindow: 256000,
@@ -19430,6 +19470,40 @@ export const MODELS = {
19430
19470
  contextWindow: 1050000,
19431
19471
  maxTokens: 128000,
19432
19472
  },
19473
+ "openai/gpt-6.1-sol": {
19474
+ id: "openai/gpt-6.1-sol",
19475
+ name: "GPT-6.1 Sol",
19476
+ api: "anthropic-messages",
19477
+ provider: "vercel-ai-gateway",
19478
+ baseUrl: "https://ai-gateway.vercel.sh",
19479
+ reasoning: true,
19480
+ input: ["text", "image"],
19481
+ cost: {
19482
+ input: 2,
19483
+ output: 10,
19484
+ cacheRead: 0.09999999999999999,
19485
+ cacheWrite: 2.5,
19486
+ },
19487
+ contextWindow: 1050000,
19488
+ maxTokens: 128000,
19489
+ },
19490
+ "openai/gpt-6.1-sol-fast": {
19491
+ id: "openai/gpt-6.1-sol-fast",
19492
+ name: "GPT-6.1 Sol (Fast)",
19493
+ api: "anthropic-messages",
19494
+ provider: "vercel-ai-gateway",
19495
+ baseUrl: "https://ai-gateway.vercel.sh",
19496
+ reasoning: true,
19497
+ input: ["text", "image"],
19498
+ cost: {
19499
+ input: 4,
19500
+ output: 20,
19501
+ cacheRead: 0.19999999999999998,
19502
+ cacheWrite: 5,
19503
+ },
19504
+ contextWindow: 1050000,
19505
+ maxTokens: 128000,
19506
+ },
19433
19507
  "openai/gpt-oss-120b": {
19434
19508
  id: "openai/gpt-oss-120b",
19435
19509
  name: "GPT OSS 120B",
@@ -19949,9 +20023,9 @@ export const MODELS = {
19949
20023
  reasoning: true,
19950
20024
  input: ["text", "image"],
19951
20025
  cost: {
19952
- input: 1.2,
19953
- output: 3.5999999999999996,
19954
- cacheRead: 0.3,
20026
+ input: 2,
20027
+ output: 6,
20028
+ cacheRead: 0.5,
19955
20029
  cacheWrite: 0,
19956
20030
  },
19957
20031
  contextWindow: 500000,
@@ -20068,7 +20142,7 @@ export const MODELS = {
20068
20142
  reasoning: true,
20069
20143
  input: ["text", "image"],
20070
20144
  cost: {
20071
- input: 0.5,
20145
+ input: 0.44999999999999996,
20072
20146
  output: 1.2,
20073
20147
  cacheRead: 0.09999999999999999,
20074
20148
  cacheWrite: 0,
@@ -20240,7 +20314,7 @@ export const MODELS = {
20240
20314
  cost: {
20241
20315
  input: 0.6,
20242
20316
  output: 2.2,
20243
- cacheRead: 0.12,
20317
+ cacheRead: 0,
20244
20318
  cacheWrite: 0,
20245
20319
  },
20246
20320
  contextWindow: 200000,
@@ -20357,9 +20431,9 @@ export const MODELS = {
20357
20431
  reasoning: true,
20358
20432
  input: ["text"],
20359
20433
  cost: {
20360
- input: 2.0999999999999996,
20361
- output: 6.6000000000000005,
20362
- cacheRead: 0.21,
20434
+ input: 2.8,
20435
+ output: 8.8,
20436
+ cacheRead: 0.56,
20363
20437
  cacheWrite: 0,
20364
20438
  },
20365
20439
  contextWindow: 1000000,