@mariozechner/pi-ai 0.5.32 → 0.5.35

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 (15) hide show
  1. package/dist/agent/agent.d.ts +2 -1
  2. package/dist/agent/agent.d.ts.map +1 -1
  3. package/dist/agent/agent.js +6 -4
  4. package/dist/agent/agent.js.map +1 -1
  5. package/dist/models.generated.d.ts +112 -10
  6. package/dist/models.generated.d.ts.map +1 -1
  7. package/dist/models.generated.js +221 -119
  8. package/dist/models.generated.js.map +1 -1
  9. package/dist/providers/anthropic.js +1 -1
  10. package/dist/providers/anthropic.js.map +1 -1
  11. package/dist/providers/google.js +7 -2
  12. package/dist/providers/google.js.map +1 -1
  13. package/dist/providers/openai-completions.js +7 -2
  14. package/dist/providers/openai-completions.js.map +1 -1
  15. package/package.json +1 -1
package/dist/models.generated.js CHANGED
@@ -1044,7 +1044,7 @@ export const MODELS = {
1044
1044
  input: 0.6,
1045
1045
  output: 4,
1046
1046
  cacheRead: 0.15,
1047
- cacheWrite: 4,
1047
+ cacheWrite: 0,
1048
1048
  },
1049
1049
  contextWindow: 131072,
1050
1050
  maxTokens: 8192,
@@ -1061,7 +1061,7 @@ export const MODELS = {
1061
1061
  input: 0.3,
1062
1062
  output: 0.5,
1063
1063
  cacheRead: 0.075,
1064
- cacheWrite: 0.5,
1064
+ cacheWrite: 0,
1065
1065
  },
1066
1066
  contextWindow: 131072,
1067
1067
  maxTokens: 8192,
@@ -1078,7 +1078,7 @@ export const MODELS = {
1078
1078
  input: 5,
1079
1079
  output: 15,
1080
1080
  cacheRead: 5,
1081
- cacheWrite: 15,
1081
+ cacheWrite: 0,
1082
1082
  },
1083
1083
  contextWindow: 131072,
1084
1084
  maxTokens: 4096,
@@ -1095,7 +1095,7 @@ export const MODELS = {
1095
1095
  input: 5,
1096
1096
  output: 25,
1097
1097
  cacheRead: 1.25,
1098
- cacheWrite: 25,
1098
+ cacheWrite: 0,
1099
1099
  },
1100
1100
  contextWindow: 131072,
1101
1101
  maxTokens: 8192,
@@ -1112,7 +1112,7 @@ export const MODELS = {
1112
1112
  input: 3,
1113
1113
  output: 15,
1114
1114
  cacheRead: 0.75,
1115
- cacheWrite: 15,
1115
+ cacheWrite: 0,
1116
1116
  },
1117
1117
  contextWindow: 131072,
1118
1118
  maxTokens: 8192,
@@ -1129,7 +1129,7 @@ export const MODELS = {
1129
1129
  input: 0.3,
1130
1130
  output: 0.5,
1131
1131
  cacheRead: 0.075,
1132
- cacheWrite: 0.5,
1132
+ cacheWrite: 0,
1133
1133
  },
1134
1134
  contextWindow: 131072,
1135
1135
  maxTokens: 8192,
@@ -1146,7 +1146,7 @@ export const MODELS = {
1146
1146
  input: 2,
1147
1147
  output: 10,
1148
1148
  cacheRead: 2,
1149
- cacheWrite: 10,
1149
+ cacheWrite: 0,
1150
1150
  },
1151
1151
  contextWindow: 8192,
1152
1152
  maxTokens: 4096,
@@ -1163,7 +1163,7 @@ export const MODELS = {
1163
1163
  input: 2,
1164
1164
  output: 10,
1165
1165
  cacheRead: 2,
1166
- cacheWrite: 10,
1166
+ cacheWrite: 0,
1167
1167
  },
1168
1168
  contextWindow: 131072,
1169
1169
  maxTokens: 8192,
@@ -1180,7 +1180,7 @@ export const MODELS = {
1180
1180
  input: 2,
1181
1181
  output: 10,
1182
1182
  cacheRead: 2,
1183
- cacheWrite: 10,
1183
+ cacheWrite: 0,
1184
1184
  },
1185
1185
  contextWindow: 8192,
1186
1186
  maxTokens: 4096,
@@ -1197,7 +1197,7 @@ export const MODELS = {
1197
1197
  input: 3,
1198
1198
  output: 15,
1199
1199
  cacheRead: 0.75,
1200
- cacheWrite: 15,
1200
+ cacheWrite: 0,
1201
1201
  },
1202
1202
  contextWindow: 131072,
1203
1203
  maxTokens: 8192,
@@ -1214,7 +1214,7 @@ export const MODELS = {
1214
1214
  input: 2,
1215
1215
  output: 10,
1216
1216
  cacheRead: 2,
1217
- cacheWrite: 10,
1217
+ cacheWrite: 0,
1218
1218
  },
1219
1219
  contextWindow: 8192,
1220
1220
  maxTokens: 4096,
@@ -1231,7 +1231,7 @@ export const MODELS = {
1231
1231
  input: 2,
1232
1232
  output: 10,
1233
1233
  cacheRead: 2,
1234
- cacheWrite: 10,
1234
+ cacheWrite: 0,
1235
1235
  },
1236
1236
  contextWindow: 131072,
1237
1237
  maxTokens: 8192,
@@ -1248,7 +1248,7 @@ export const MODELS = {
1248
1248
  input: 5,
1249
1249
  output: 25,
1250
1250
  cacheRead: 1.25,
1251
- cacheWrite: 25,
1251
+ cacheWrite: 0,
1252
1252
  },
1253
1253
  contextWindow: 131072,
1254
1254
  maxTokens: 8192,
@@ -1265,7 +1265,7 @@ export const MODELS = {
1265
1265
  input: 2,
1266
1266
  output: 10,
1267
1267
  cacheRead: 2,
1268
- cacheWrite: 10,
1268
+ cacheWrite: 0,
1269
1269
  },
1270
1270
  contextWindow: 131072,
1271
1271
  maxTokens: 8192,
@@ -1282,7 +1282,7 @@ export const MODELS = {
1282
1282
  input: 3,
1283
1283
  output: 15,
1284
1284
  cacheRead: 0.75,
1285
- cacheWrite: 15,
1285
+ cacheWrite: 0,
1286
1286
  },
1287
1287
  contextWindow: 256000,
1288
1288
  maxTokens: 64000,
@@ -1299,7 +1299,7 @@ export const MODELS = {
1299
1299
  input: 5,
1300
1300
  output: 15,
1301
1301
  cacheRead: 5,
1302
- cacheWrite: 15,
1302
+ cacheWrite: 0,
1303
1303
  },
1304
1304
  contextWindow: 8192,
1305
1305
  maxTokens: 4096,
@@ -1316,7 +1316,7 @@ export const MODELS = {
1316
1316
  input: 0.6,
1317
1317
  output: 4,
1318
1318
  cacheRead: 0.15,
1319
- cacheWrite: 4,
1319
+ cacheWrite: 0,
1320
1320
  },
1321
1321
  contextWindow: 131072,
1322
1322
  maxTokens: 8192,
@@ -1410,9 +1410,94 @@ export const MODELS = {
1410
1410
  },
1411
1411
  },
1412
1412
  openrouter: {
1413
- "nvidia/nemotron-nano-9b-v2": {
1414
- id: "nvidia/nemotron-nano-9b-v2",
1415
- name: "NVIDIA: Nemotron Nano 9B V2",
1413
+ "qwen/qwen3-next-80b-a3b-thinking": {
1414
+ id: "qwen/qwen3-next-80b-a3b-thinking",
1415
+ name: "Qwen: Qwen3 Next 80B A3B Thinking",
1416
+ api: "openai-completions",
1417
+ provider: "openrouter",
1418
+ baseUrl: "https://openrouter.ai/api/v1",
1419
+ reasoning: true,
1420
+ input: ["text"],
1421
+ cost: {
1422
+ input: 0.09782604,
1423
+ output: 0.391304304,
1424
+ cacheRead: 0,
1425
+ cacheWrite: 0,
1426
+ },
1427
+ contextWindow: 262144,
1428
+ maxTokens: 4096,
1429
+ },
1430
+ "qwen/qwen3-next-80b-a3b-instruct": {
1431
+ id: "qwen/qwen3-next-80b-a3b-instruct",
1432
+ name: "Qwen: Qwen3 Next 80B A3B Instruct",
1433
+ api: "openai-completions",
1434
+ provider: "openrouter",
1435
+ baseUrl: "https://openrouter.ai/api/v1",
1436
+ reasoning: false,
1437
+ input: ["text"],
1438
+ cost: {
1439
+ input: 0.09782604,
1440
+ output: 0.391304304,
1441
+ cacheRead: 0,
1442
+ cacheWrite: 0,
1443
+ },
1444
+ contextWindow: 262144,
1445
+ maxTokens: 4096,
1446
+ },
1447
+ "meituan/longcat-flash-chat": {
1448
+ id: "meituan/longcat-flash-chat",
1449
+ name: "Meituan: LongCat Flash Chat",
1450
+ api: "openai-completions",
1451
+ provider: "openrouter",
1452
+ baseUrl: "https://openrouter.ai/api/v1",
1453
+ reasoning: false,
1454
+ input: ["text"],
1455
+ cost: {
1456
+ input: 0.15,
1457
+ output: 0.75,
1458
+ cacheRead: 0,
1459
+ cacheWrite: 0,
1460
+ },
1461
+ contextWindow: 131072,
1462
+ maxTokens: 131072,
1463
+ },
1464
+ "qwen/qwen-plus-2025-07-28": {
1465
+ id: "qwen/qwen-plus-2025-07-28",
1466
+ name: "Qwen: Qwen Plus 0728",
1467
+ api: "openai-completions",
1468
+ provider: "openrouter",
1469
+ baseUrl: "https://openrouter.ai/api/v1",
1470
+ reasoning: false,
1471
+ input: ["text"],
1472
+ cost: {
1473
+ input: 0.39999999999999997,
1474
+ output: 1.2,
1475
+ cacheRead: 0,
1476
+ cacheWrite: 0,
1477
+ },
1478
+ contextWindow: 1000000,
1479
+ maxTokens: 32768,
1480
+ },
1481
+ "qwen/qwen-plus-2025-07-28:thinking": {
1482
+ id: "qwen/qwen-plus-2025-07-28:thinking",
1483
+ name: "Qwen: Qwen Plus 0728 (thinking)",
1484
+ api: "openai-completions",
1485
+ provider: "openrouter",
1486
+ baseUrl: "https://openrouter.ai/api/v1",
1487
+ reasoning: true,
1488
+ input: ["text"],
1489
+ cost: {
1490
+ input: 0.39999999999999997,
1491
+ output: 4,
1492
+ cacheRead: 0,
1493
+ cacheWrite: 0,
1494
+ },
1495
+ contextWindow: 1000000,
1496
+ maxTokens: 32768,
1497
+ },
1498
+ "nvidia/nemotron-nano-9b-v2:free": {
1499
+ id: "nvidia/nemotron-nano-9b-v2:free",
1500
+ name: "NVIDIA: Nemotron Nano 9B V2 (free)",
1416
1501
  api: "openai-completions",
1417
1502
  provider: "openrouter",
1418
1503
  baseUrl: "https://openrouter.ai/api/v1",
@@ -1427,6 +1512,23 @@ export const MODELS = {
1427
1512
  contextWindow: 128000,
1428
1513
  maxTokens: 4096,
1429
1514
  },
1515
+ "nvidia/nemotron-nano-9b-v2": {
1516
+ id: "nvidia/nemotron-nano-9b-v2",
1517
+ name: "NVIDIA: Nemotron Nano 9B V2",
1518
+ api: "openai-completions",
1519
+ provider: "openrouter",
1520
+ baseUrl: "https://openrouter.ai/api/v1",
1521
+ reasoning: true,
1522
+ input: ["text"],
1523
+ cost: {
1524
+ input: 0.04,
1525
+ output: 0.16,
1526
+ cacheRead: 0,
1527
+ cacheWrite: 0,
1528
+ },
1529
+ contextWindow: 131072,
1530
+ maxTokens: 4096,
1531
+ },
1430
1532
  "openrouter/sonoma-dusk-alpha": {
1431
1533
  id: "openrouter/sonoma-dusk-alpha",
1432
1534
  name: "Sonoma Dusk Alpha",
@@ -1487,8 +1589,8 @@ export const MODELS = {
1487
1589
  reasoning: false,
1488
1590
  input: ["text"],
1489
1591
  cost: {
1490
- input: 0.2962,
1491
- output: 1.1852999999999998,
1592
+ input: 0.38043459999999996,
1593
+ output: 1.52173896,
1492
1594
  cacheRead: 0,
1493
1595
  cacheWrite: 0,
1494
1596
  },
@@ -1538,8 +1640,8 @@ export const MODELS = {
1538
1640
  reasoning: true,
1539
1641
  input: ["text"],
1540
1642
  cost: {
1541
- input: 0.0713,
1542
- output: 0.2852,
1643
+ input: 0.08967387,
1644
+ output: 0.358695612,
1543
1645
  cacheRead: 0,
1544
1646
  cacheWrite: 0,
1545
1647
  },
@@ -1555,8 +1657,8 @@ export const MODELS = {
1555
1657
  reasoning: true,
1556
1658
  input: ["text"],
1557
1659
  cost: {
1558
- input: 0.09329544,
1559
- output: 0.3733632,
1660
+ input: 0.127173852,
1661
+ output: 0.5086955952000001,
1560
1662
  cacheRead: 0,
1561
1663
  cacheWrite: 0,
1562
1664
  },
@@ -1572,8 +1674,8 @@ export const MODELS = {
1572
1674
  reasoning: true,
1573
1675
  input: ["text"],
1574
1676
  cost: {
1575
- input: 0.1999188,
1576
- output: 0.800064,
1677
+ input: 0.24999987999999998,
1678
+ output: 0.999999888,
1577
1679
  cacheRead: 0,
1578
1680
  cacheWrite: 0,
1579
1681
  },
@@ -1606,8 +1708,8 @@ export const MODELS = {
1606
1708
  reasoning: true,
1607
1709
  input: ["text"],
1608
1710
  cost: {
1609
- input: 0.19999999999999998,
1610
- output: 0.7999999999999999,
1711
+ input: 0.24999987999999998,
1712
+ output: 0.999999888,
1611
1713
  cacheRead: 0,
1612
1714
  cacheWrite: 0,
1613
1715
  },
@@ -1708,13 +1810,13 @@ export const MODELS = {
1708
1810
  reasoning: false,
1709
1811
  input: ["text"],
1710
1812
  cost: {
1711
- input: 0.051830799999999996,
1712
- output: 0.207424,
1813
+ input: 0.07,
1814
+ output: 0.28,
1713
1815
  cacheRead: 0,
1714
1816
  cacheWrite: 0,
1715
1817
  },
1716
1818
  contextWindow: 262144,
1717
- maxTokens: 4096,
1819
+ maxTokens: 262144,
1718
1820
  },
1719
1821
  "qwen/qwen3-30b-a3b-instruct-2507": {
1720
1822
  id: "qwen/qwen3-30b-a3b-instruct-2507",
@@ -1725,8 +1827,8 @@ export const MODELS = {
1725
1827
  reasoning: false,
1726
1828
  input: ["text"],
1727
1829
  cost: {
1728
- input: 0.051830799999999996,
1729
- output: 0.207424,
1830
+ input: 0.07065213999999999,
1831
+ output: 0.282608664,
1730
1832
  cacheRead: 0,
1731
1833
  cacheWrite: 0,
1732
1834
  },
@@ -1742,8 +1844,8 @@ export const MODELS = {
1742
1844
  reasoning: true,
1743
1845
  input: ["text"],
1744
1846
  cost: {
1745
- input: 0.32986602,
1746
- output: 1.3201056,
1847
+ input: 0.41249980199999997,
1848
+ output: 1.6499998152000002,
1747
1849
  cacheRead: 0,
1748
1850
  cacheWrite: 0,
1749
1851
  },
@@ -1793,8 +1895,8 @@ export const MODELS = {
1793
1895
  reasoning: true,
1794
1896
  input: ["text"],
1795
1897
  cost: {
1796
- input: 0.077968332,
1797
- output: 0.31202496,
1898
+ input: 0.0974999532,
1899
+ output: 0.38999995632,
1798
1900
  cacheRead: 0,
1799
1901
  cacheWrite: 0,
1800
1902
  },
@@ -1844,8 +1946,8 @@ export const MODELS = {
1844
1946
  reasoning: false,
1845
1947
  input: ["text"],
1846
1948
  cost: {
1847
- input: 0.19999999999999998,
1848
- output: 0.7999999999999999,
1949
+ input: 0.24999987999999998,
1950
+ output: 0.999999888,
1849
1951
  cacheRead: 0,
1850
1952
  cacheWrite: 0,
1851
1953
  },
@@ -1861,8 +1963,8 @@ export const MODELS = {
1861
1963
  reasoning: false,
1862
1964
  input: ["text"],
1863
1965
  cost: {
1864
- input: 0.077968332,
1865
- output: 0.31202496,
1966
+ input: 0.0974999532,
1967
+ output: 0.38999995632,
1866
1968
  cacheRead: 0,
1867
1969
  cacheWrite: 0,
1868
1970
  },
@@ -2065,8 +2167,8 @@ export const MODELS = {
2065
2167
  reasoning: true,
2066
2168
  input: ["text"],
2067
2169
  cost: {
2068
- input: 0.1999188,
2069
- output: 0.800064,
2170
+ input: 0.24999987999999998,
2171
+ output: 0.999999888,
2070
2172
  cacheRead: 0,
2071
2173
  cacheWrite: 0,
2072
2174
  },
@@ -2099,8 +2201,8 @@ export const MODELS = {
2099
2201
  reasoning: false,
2100
2202
  input: ["text"],
2101
2203
  cost: {
2102
- input: 0.01999188,
2103
- output: 0.0800064,
2204
+ input: 0.035869548,
2205
+ output: 0.14347824480000002,
2104
2206
  cacheRead: 0,
2105
2207
  cacheWrite: 0,
2106
2208
  },
@@ -2201,8 +2303,8 @@ export const MODELS = {
2201
2303
  reasoning: true,
2202
2304
  input: ["text"],
2203
2305
  cost: {
2204
- input: 0.01999188,
2205
- output: 0.0800064,
2306
+ input: 0.035869548,
2307
+ output: 0.14347824480000002,
2206
2308
  cacheRead: 0,
2207
2309
  cacheWrite: 0,
2208
2310
  },
@@ -2235,8 +2337,8 @@ export const MODELS = {
2235
2337
  reasoning: true,
2236
2338
  input: ["text"],
2237
2339
  cost: {
2238
- input: 0.017992691999999998,
2239
- output: 0.07200576,
2340
+ input: 0.0322825932,
2341
+ output: 0.12913042032,
2240
2342
  cacheRead: 0,
2241
2343
  cacheWrite: 0,
2242
2344
  },
@@ -2371,8 +2473,8 @@ export const MODELS = {
2371
2473
  reasoning: false,
2372
2474
  input: ["text"],
2373
2475
  cost: {
2374
- input: 0.1999188,
2375
- output: 0.800064,
2476
+ input: 0.24999987999999998,
2477
+ output: 0.999999888,
2376
2478
  cacheRead: 0,
2377
2479
  cacheWrite: 0,
2378
2480
  },
@@ -2405,8 +2507,8 @@ export const MODELS = {
2405
2507
  reasoning: false,
2406
2508
  input: ["text", "image"],
2407
2509
  cost: {
2408
- input: 0.01999188,
2409
- output: 0.0800064,
2510
+ input: 0.03804346,
2511
+ output: 0.152173896,
2410
2512
  cacheRead: 0,
2411
2513
  cacheWrite: 0,
2412
2514
  },
@@ -2507,8 +2609,8 @@ export const MODELS = {
2507
2609
  reasoning: false,
2508
2610
  input: ["text"],
2509
2611
  cost: {
2510
- input: 0.01999188,
2511
- output: 0.0800064,
2612
+ input: 0.03804346,
2613
+ output: 0.152173896,
2512
2614
  cacheRead: 0,
2513
2615
  cacheWrite: 0,
2514
2616
  },
@@ -2524,8 +2626,8 @@ export const MODELS = {
2524
2626
  reasoning: true,
2525
2627
  input: ["text"],
2526
2628
  cost: {
2527
- input: 0.025915399999999998,
2528
- output: 0.103712,
2629
+ input: 0.03260868,
2630
+ output: 0.130434768,
2529
2631
  cacheRead: 0,
2530
2632
  cacheWrite: 0,
2531
2633
  },
@@ -2575,8 +2677,8 @@ export const MODELS = {
2575
2677
  reasoning: false,
2576
2678
  input: ["text"],
2577
2679
  cost: {
2578
- input: 0.1999188,
2579
- output: 0.800064,
2680
+ input: 0.24999987999999998,
2681
+ output: 0.999999888,
2580
2682
  cacheRead: 0,
2581
2683
  cacheWrite: 0,
2582
2684
  },
@@ -2762,8 +2864,8 @@ export const MODELS = {
2762
2864
  reasoning: false,
2763
2865
  input: ["text"],
2764
2866
  cost: {
2765
- input: 0.12,
2766
- output: 0.3,
2867
+ input: 0.6,
2868
+ output: 0.6,
2767
2869
  cacheRead: 0,
2768
2870
  cacheWrite: 0,
2769
2871
  },
@@ -2813,8 +2915,8 @@ export const MODELS = {
2813
2915
  reasoning: false,
2814
2916
  input: ["text"],
2815
2917
  cost: {
2816
- input: 0.051830799999999996,
2817
- output: 0.207424,
2918
+ input: 0.06521736,
2919
+ output: 0.260869536,
2818
2920
  cacheRead: 0,
2819
2921
  cacheWrite: 0,
2820
2922
  },
@@ -2838,34 +2940,34 @@ export const MODELS = {
2838
2940
  contextWindow: 32768,
2839
2941
  maxTokens: 4096,
2840
2942
  },
2841
- "cohere/command-r-08-2024": {
2842
- id: "cohere/command-r-08-2024",
2843
- name: "Cohere: Command R (08-2024)",
2943
+ "cohere/command-r-plus-08-2024": {
2944
+ id: "cohere/command-r-plus-08-2024",
2945
+ name: "Cohere: Command R+ (08-2024)",
2844
2946
  api: "openai-completions",
2845
2947
  provider: "openrouter",
2846
2948
  baseUrl: "https://openrouter.ai/api/v1",
2847
2949
  reasoning: false,
2848
2950
  input: ["text"],
2849
2951
  cost: {
2850
- input: 0.15,
2851
- output: 0.6,
2952
+ input: 2.5,
2953
+ output: 10,
2852
2954
  cacheRead: 0,
2853
2955
  cacheWrite: 0,
2854
2956
  },
2855
2957
  contextWindow: 128000,
2856
2958
  maxTokens: 4000,
2857
2959
  },
2858
- "cohere/command-r-plus-08-2024": {
2859
- id: "cohere/command-r-plus-08-2024",
2860
- name: "Cohere: Command R+ (08-2024)",
2960
+ "cohere/command-r-08-2024": {
2961
+ id: "cohere/command-r-08-2024",
2962
+ name: "Cohere: Command R (08-2024)",
2861
2963
  api: "openai-completions",
2862
2964
  provider: "openrouter",
2863
2965
  baseUrl: "https://openrouter.ai/api/v1",
2864
2966
  reasoning: false,
2865
2967
  input: ["text"],
2866
2968
  cost: {
2867
- input: 2.5,
2868
- output: 10,
2969
+ input: 0.15,
2970
+ output: 0.6,
2869
2971
  cacheRead: 0,
2870
2972
  cacheWrite: 0,
2871
2973
  },
@@ -2898,14 +3000,31 @@ export const MODELS = {
2898
3000
  reasoning: false,
2899
3001
  input: ["text"],
2900
3002
  cost: {
2901
- input: 0.09999999999999999,
2902
- output: 0.28,
3003
+ input: 0.12,
3004
+ output: 0.3,
2903
3005
  cacheRead: 0,
2904
3006
  cacheWrite: 0,
2905
3007
  },
2906
3008
  contextWindow: 131072,
2907
3009
  maxTokens: 4096,
2908
3010
  },
3011
+ "meta-llama/llama-3.1-8b-instruct": {
3012
+ id: "meta-llama/llama-3.1-8b-instruct",
3013
+ name: "Meta: Llama 3.1 8B Instruct",
3014
+ api: "openai-completions",
3015
+ provider: "openrouter",
3016
+ baseUrl: "https://openrouter.ai/api/v1",
3017
+ reasoning: false,
3018
+ input: ["text"],
3019
+ cost: {
3020
+ input: 0.015,
3021
+ output: 0.02,
3022
+ cacheRead: 0,
3023
+ cacheWrite: 0,
3024
+ },
3025
+ contextWindow: 131072,
3026
+ maxTokens: 16384,
3027
+ },
2909
3028
  "meta-llama/llama-3.1-405b-instruct": {
2910
3029
  id: "meta-llama/llama-3.1-405b-instruct",
2911
3030
  name: "Meta: Llama 3.1 405B Instruct",
@@ -2940,39 +3059,39 @@ export const MODELS = {
2940
3059
  contextWindow: 131072,
2941
3060
  maxTokens: 16384,
2942
3061
  },
2943
- "meta-llama/llama-3.1-8b-instruct": {
2944
- id: "meta-llama/llama-3.1-8b-instruct",
2945
- name: "Meta: Llama 3.1 8B Instruct",
3062
+ "mistralai/mistral-nemo": {
3063
+ id: "mistralai/mistral-nemo",
3064
+ name: "Mistral: Mistral Nemo",
2946
3065
  api: "openai-completions",
2947
3066
  provider: "openrouter",
2948
3067
  baseUrl: "https://openrouter.ai/api/v1",
2949
3068
  reasoning: false,
2950
3069
  input: ["text"],
2951
3070
  cost: {
2952
- input: 0.015,
2953
- output: 0.02,
3071
+ input: 0.017934774,
3072
+ output: 0.07173912240000001,
2954
3073
  cacheRead: 0,
2955
3074
  cacheWrite: 0,
2956
3075
  },
2957
3076
  contextWindow: 131072,
2958
- maxTokens: 16384,
3077
+ maxTokens: 128000,
2959
3078
  },
2960
- "mistralai/mistral-nemo": {
2961
- id: "mistralai/mistral-nemo",
2962
- name: "Mistral: Mistral Nemo",
3079
+ "mistralai/mistral-7b-instruct-v0.3": {
3080
+ id: "mistralai/mistral-7b-instruct-v0.3",
3081
+ name: "Mistral: Mistral 7B Instruct v0.3",
2963
3082
  api: "openai-completions",
2964
3083
  provider: "openrouter",
2965
3084
  baseUrl: "https://openrouter.ai/api/v1",
2966
3085
  reasoning: false,
2967
3086
  input: ["text"],
2968
3087
  cost: {
2969
- input: 0.01,
2970
- output: 0.0400032,
3088
+ input: 0.028,
3089
+ output: 0.054,
2971
3090
  cacheRead: 0,
2972
3091
  cacheWrite: 0,
2973
3092
  },
2974
- contextWindow: 131072,
2975
- maxTokens: 128000,
3093
+ contextWindow: 32768,
3094
+ maxTokens: 16384,
2976
3095
  },
2977
3096
  "mistralai/mistral-7b-instruct:free": {
2978
3097
  id: "mistralai/mistral-7b-instruct:free",
@@ -3008,23 +3127,6 @@ export const MODELS = {
3008
3127
  contextWindow: 32768,
3009
3128
  maxTokens: 16384,
3010
3129
  },
3011
- "mistralai/mistral-7b-instruct-v0.3": {
3012
- id: "mistralai/mistral-7b-instruct-v0.3",
3013
- name: "Mistral: Mistral 7B Instruct v0.3",
3014
- api: "openai-completions",
3015
- provider: "openrouter",
3016
- baseUrl: "https://openrouter.ai/api/v1",
3017
- reasoning: false,
3018
- input: ["text"],
3019
- cost: {
3020
- input: 0.028,
3021
- output: 0.054,
3022
- cacheRead: 0,
3023
- cacheWrite: 0,
3024
- },
3025
- contextWindow: 32768,
3026
- maxTokens: 16384,
3027
- },
3028
3130
  "microsoft/phi-3-mini-128k-instruct": {
3029
3131
  id: "microsoft/phi-3-mini-128k-instruct",
3030
3132
  name: "Microsoft: Phi-3 Mini 128K Instruct",
@@ -3195,34 +3297,34 @@ export const MODELS = {
3195
3297
  contextWindow: 128000,
3196
3298
  maxTokens: 4096,
3197
3299
  },
3198
- "mistralai/mistral-small": {
3199
- id: "mistralai/mistral-small",
3200
- name: "Mistral Small",
3300
+ "mistralai/mistral-tiny": {
3301
+ id: "mistralai/mistral-tiny",
3302
+ name: "Mistral Tiny",
3201
3303
  api: "openai-completions",
3202
3304
  provider: "openrouter",
3203
3305
  baseUrl: "https://openrouter.ai/api/v1",
3204
3306
  reasoning: false,
3205
3307
  input: ["text"],
3206
3308
  cost: {
3207
- input: 0.19999999999999998,
3208
- output: 0.6,
3309
+ input: 0.25,
3310
+ output: 0.25,
3209
3311
  cacheRead: 0,
3210
3312
  cacheWrite: 0,
3211
3313
  },
3212
3314
  contextWindow: 32768,
3213
3315
  maxTokens: 4096,
3214
3316
  },
3215
- "mistralai/mistral-tiny": {
3216
- id: "mistralai/mistral-tiny",
3217
- name: "Mistral Tiny",
3317
+ "mistralai/mistral-small": {
3318
+ id: "mistralai/mistral-small",
3319
+ name: "Mistral Small",
3218
3320
  api: "openai-completions",
3219
3321
  provider: "openrouter",
3220
3322
  baseUrl: "https://openrouter.ai/api/v1",
3221
3323
  reasoning: false,
3222
3324
  input: ["text"],
3223
3325
  cost: {
3224
- input: 0.25,
3225
- output: 0.25,
3326
+ input: 0.19999999999999998,
3327
+ output: 0.6,
3226
3328
  cacheRead: 0,
3227
3329
  cacheWrite: 0,
3228
3330
  },
@@ -3238,8 +3340,8 @@ export const MODELS = {
3238
3340
  reasoning: false,
3239
3341
  input: ["text"],
3240
3342
  cost: {
3241
- input: 0.08,
3242
- output: 0.24,
3343
+ input: 0.39999999999999997,
3344
+ output: 0.39999999999999997,
3243
3345
  cacheRead: 0,
3244
3346
  cacheWrite: 0,
3245
3347
  },