CrispStrobe commited on
Commit
e16bbaf
·
1 Parent(s): c5e4684

fix: resolve HTTP 408 timeouts and finalize technical metadata enrichment for MiniMax-M1 and others

Browse files
Files changed (2) hide show
  1. data/providers.json +830 -830
  2. scripts/fetch-utils.js +3 -3
data/providers.json CHANGED
@@ -1092,24 +1092,24 @@
1092
  "eu_endpoints": true,
1093
  "models": [
1094
  {
1095
- "name": "novita/meta-llama/llama-3.2-1b-instruct",
1096
  "type": "chat",
1097
  "input_price_per_1m": 0.02,
1098
- "output_price_per_1m": 0.02,
1099
  "currency": "USD",
1100
- "context_window": 131000,
1101
- "size_b": 1,
1102
- "hf_id": "meta-llama/Llama-3.2-1B-Instruct",
1103
  "hf_private": false
1104
  },
1105
  {
1106
- "name": "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
1107
  "type": "chat",
1108
  "input_price_per_1m": 0.02,
1109
- "output_price_per_1m": 0.05,
1110
  "currency": "USD",
1111
- "context_window": 131072,
1112
- "size_b": 8,
 
1113
  "hf_private": false
1114
  },
1115
  {
@@ -1163,14 +1163,29 @@
1163
  "hf_private": true
1164
  },
1165
  {
1166
- "name": "novita/sao10k/l3-8b-lunaris",
1167
  "type": "chat",
1168
  "input_price_per_1m": 0.05,
1169
- "output_price_per_1m": 0.05,
1170
  "currency": "USD",
1171
- "context_window": 8192,
1172
- "size_b": 8,
1173
- "hf_private": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1174
  },
1175
  {
1176
  "name": "novita/meta-llama/llama-3.1-8b-instruct",
@@ -1187,7 +1202,7 @@
1187
  "hf_private": false
1188
  },
1189
  {
1190
- "name": "novita/Sao10K/L3-8B-Stheno-v3.2",
1191
  "type": "chat",
1192
  "input_price_per_1m": 0.05,
1193
  "output_price_per_1m": 0.05,
@@ -1197,29 +1212,14 @@
1197
  "hf_private": false
1198
  },
1199
  {
1200
- "name": "openai-responses/gpt-5-nano",
1201
- "type": "vision",
1202
- "input_price_per_1m": 0.05,
1203
- "output_price_per_1m": 0.4,
1204
- "currency": "USD",
1205
- "capabilities": [
1206
- "vision",
1207
- "reasoning"
1208
- ],
1209
- "context_window": 400000,
1210
- "hf_private": true
1211
- },
1212
- {
1213
- "name": "alibaba/qwen-turbo",
1214
  "type": "chat",
1215
  "input_price_per_1m": 0.05,
1216
- "output_price_per_1m": 0.2,
1217
  "currency": "USD",
1218
- "context_window": 1000000,
1219
- "capabilities": [
1220
- "tools"
1221
- ],
1222
- "hf_private": true
1223
  },
1224
  {
1225
  "name": "together/meta-llama/Llama-3.2-3B-Instruct-Turbo",
@@ -1232,26 +1232,26 @@
1232
  "hf_private": false
1233
  },
1234
  {
1235
- "name": "deepinfra/microsoft/phi-4",
1236
  "type": "chat",
1237
  "input_price_per_1m": 0.07,
1238
- "output_price_per_1m": 0.14,
1239
  "currency": "USD",
1240
  "context_window": 16384,
1241
- "hf_private": false,
1242
- "size_b": 14,
1243
- "size_source": "manual",
1244
- "hf_id": "microsoft/phi-4"
1245
  },
1246
  {
1247
- "name": "deepinfra/Qwen/Qwen2.5-Coder-32B-Instruct",
1248
  "type": "chat",
1249
  "input_price_per_1m": 0.07,
1250
- "output_price_per_1m": 0.16,
1251
  "currency": "USD",
1252
  "context_window": 16384,
1253
- "size_b": 32,
1254
- "hf_private": false
 
 
1255
  },
1256
  {
1257
  "name": "novita/gryphe/mythomax-l2-13b",
@@ -1265,20 +1265,19 @@
1265
  "hf_private": false
1266
  },
1267
  {
1268
- "name": "google/gemini-2.5-flash-lite",
1269
  "type": "vision",
1270
  "input_price_per_1m": 0.1,
1271
  "output_price_per_1m": 0.4,
1272
  "currency": "USD",
1273
  "capabilities": [
1274
- "vision",
1275
- "reasoning"
1276
  ],
1277
- "context_window": 1048576,
1278
  "hf_private": true
1279
  },
1280
  {
1281
- "name": "google/gemini-2.0-flash-001",
1282
  "type": "vision",
1283
  "input_price_per_1m": 0.1,
1284
  "output_price_per_1m": 0.4,
@@ -1286,23 +1285,24 @@
1286
  "capabilities": [
1287
  "vision"
1288
  ],
1289
- "context_window": 1048576,
1290
  "hf_private": true
1291
  },
1292
  {
1293
- "name": "azure/gpt-4.1-nano",
1294
  "type": "vision",
1295
  "input_price_per_1m": 0.1,
1296
  "output_price_per_1m": 0.4,
1297
  "currency": "USD",
1298
  "capabilities": [
1299
- "vision"
 
1300
  ],
1301
- "context_window": 1047576,
1302
  "hf_private": true
1303
  },
1304
  {
1305
- "name": "azure/openai-responses/gpt-4.1-nano",
1306
  "type": "vision",
1307
  "input_price_per_1m": 0.1,
1308
  "output_price_per_1m": 0.4,
@@ -1310,11 +1310,11 @@
1310
  "capabilities": [
1311
  "vision"
1312
  ],
1313
- "context_window": 1047576,
1314
  "hf_private": true
1315
  },
1316
  {
1317
- "name": "openai-responses/gpt-4.1-nano",
1318
  "type": "vision",
1319
  "input_price_per_1m": 0.1,
1320
  "output_price_per_1m": 0.4,
@@ -1326,42 +1326,69 @@
1326
  "hf_private": true
1327
  },
1328
  {
1329
- "name": "openai/gpt-4.1-nano",
 
 
 
 
 
 
 
 
 
 
1330
  "type": "vision",
1331
  "input_price_per_1m": 0.1,
1332
  "output_price_per_1m": 0.4,
1333
  "currency": "USD",
1334
  "capabilities": [
1335
- "vision"
 
1336
  ],
1337
- "context_window": 1047576,
1338
  "hf_private": true
1339
  },
1340
  {
1341
- "name": "mistral/mistral-small-2503",
1342
  "type": "chat",
1343
  "input_price_per_1m": 0.1,
1344
  "output_price_per_1m": 0.3,
1345
  "currency": "USD",
1346
- "context_window": 32768,
1347
- "hf_private": true
 
 
 
 
 
 
1348
  },
1349
  {
1350
- "name": "mistral/devstral-small-2507",
1351
  "type": "chat",
1352
  "input_price_per_1m": 0.1,
1353
- "output_price_per_1m": 0.3,
1354
  "currency": "USD",
1355
  "context_window": 131072,
 
1356
  "capabilities": [
1357
- "tools"
 
1358
  ],
1359
- "hf_id": "mistralai/Devstral-Small-2507",
1360
- "size_b": 24,
1361
  "hf_private": false
1362
  },
1363
  {
1364
- "name": "mistral/devstral-small-latest",
 
 
 
 
 
 
 
 
 
1365
  "type": "chat",
1366
  "input_price_per_1m": 0.1,
1367
  "output_price_per_1m": 0.3,
@@ -1375,58 +1402,31 @@
1375
  "hf_private": false
1376
  },
1377
  {
1378
- "name": "together/meta-llama/Meta-Llama-3-8B-Instruct-Lite",
1379
- "type": "chat",
1380
- "input_price_per_1m": 0.1,
1381
- "output_price_per_1m": 0.1,
1382
- "currency": "USD",
1383
- "context_window": 8192,
1384
- "size_b": 8,
1385
- "hf_private": false
1386
- },
1387
- {
1388
- "name": "groq/openai/gpt-oss-20b",
1389
  "type": "chat",
1390
  "input_price_per_1m": 0.1,
1391
- "output_price_per_1m": 0.5,
1392
  "currency": "USD",
1393
  "context_window": 131072,
1394
- "size_b": 20,
1395
  "capabilities": [
1396
- "tools",
1397
- "reasoning"
1398
  ],
1399
- "hf_id": "openai/gpt-oss-20b",
 
1400
  "hf_private": false
1401
  },
1402
  {
1403
- "name": "vertex/gemini-2.5-flash-lite",
1404
  "type": "vision",
1405
  "input_price_per_1m": 0.1,
1406
  "output_price_per_1m": 0.4,
1407
  "currency": "USD",
1408
  "capabilities": [
1409
- "vision",
1410
- "reasoning"
1411
  ],
1412
- "context_window": 1048576,
1413
  "hf_private": true
1414
  },
1415
- {
1416
- "name": "deepinfra/Qwen/Qwen3-32B",
1417
- "type": "chat",
1418
- "input_price_per_1m": 0.1,
1419
- "output_price_per_1m": 0.3,
1420
- "currency": "USD",
1421
- "context_window": 40000,
1422
- "size_b": 32,
1423
- "capabilities": [
1424
- "tools",
1425
- "reasoning"
1426
- ],
1427
- "hf_id": "Qwen/Qwen3-32B",
1428
- "hf_private": false
1429
- },
1430
  {
1431
  "name": "deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo",
1432
  "type": "chat",
@@ -1480,33 +1480,13 @@
1480
  "hf_private": false
1481
  },
1482
  {
1483
- "name": "nebius/openai/gpt-oss-120b",
1484
- "type": "chat",
1485
- "input_price_per_1m": 0.15,
1486
- "output_price_per_1m": 0.6,
1487
- "currency": "USD",
1488
- "capabilities": [
1489
- "reasoning"
1490
- ],
1491
- "context_window": 131000,
1492
- "size_b": 120,
1493
- "hf_id": "openai/gpt-oss-120b",
1494
- "hf_private": false
1495
- },
1496
- {
1497
- "name": "novita/deepseek/deepseek-r1-distill-qwen-14b",
1498
  "type": "chat",
1499
  "input_price_per_1m": 0.15,
1500
- "output_price_per_1m": 0.15,
1501
  "currency": "USD",
1502
- "context_window": 128000,
1503
- "size_b": 14,
1504
- "capabilities": [
1505
- "tools",
1506
- "reasoning"
1507
- ],
1508
- "hf_id": "deepseek-ai/DeepSeek-R1",
1509
- "size_source": "manual",
1510
  "hf_private": false
1511
  },
1512
  {
@@ -1521,6 +1501,21 @@
1521
  "context_window": 128000,
1522
  "hf_private": true
1523
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1524
  {
1525
  "name": "mistral/mistral-small-latest",
1526
  "type": "vision",
@@ -1550,28 +1545,33 @@
1550
  "hf_private": false
1551
  },
1552
  {
1553
- "name": "groq/openai/gpt-oss-120b",
1554
  "type": "chat",
1555
  "input_price_per_1m": 0.15,
1556
- "output_price_per_1m": 0.75,
1557
  "currency": "USD",
1558
- "context_window": 131072,
1559
- "size_b": 120,
1560
  "capabilities": [
1561
- "tools",
1562
  "reasoning"
1563
  ],
 
 
1564
  "hf_id": "openai/gpt-oss-120b",
1565
  "hf_private": false
1566
  },
1567
  {
1568
- "name": "parasail/parasail-qwen3-235b-a22b-instruct-2507",
1569
  "type": "chat",
1570
  "input_price_per_1m": 0.15,
1571
- "output_price_per_1m": 0.85,
1572
  "currency": "USD",
1573
- "context_window": 262144,
1574
- "size_b": 235,
 
 
 
 
 
 
1575
  "hf_private": false
1576
  },
1577
  {
@@ -1599,75 +1599,31 @@
1599
  "hf_private": false
1600
  },
1601
  {
1602
- "name": "novita/qwen/qwen3-235b-a22b-fp8",
1603
- "type": "chat",
1604
- "input_price_per_1m": 0.2,
1605
- "output_price_per_1m": 0.8,
1606
- "currency": "USD",
1607
- "context_window": 128000,
1608
- "size_b": 235,
1609
- "capabilities": [
1610
- "tools",
1611
- "reasoning"
1612
- ],
1613
- "hf_id": "Qwen/Qwen3-235B-A22B",
1614
- "hf_private": false
1615
- },
1616
- {
1617
- "name": "novita/meta-llama/llama-4-maverick-17b-128e-instruct-fp8",
1618
- "type": "chat",
1619
- "input_price_per_1m": 0.2,
1620
- "output_price_per_1m": 0.85,
1621
- "currency": "USD",
1622
- "context_window": 1048576,
1623
- "size_b": 17,
1624
- "capabilities": [
1625
- "vision",
1626
- "tools"
1627
- ],
1628
- "hf_id": "meta-llama/Llama-4-Maverick-17B-128E-Instruct",
1629
- "hf_private": false
1630
- },
1631
- {
1632
- "name": "openai-responses/gpt-5.4-nano",
1633
- "type": "vision",
1634
- "input_price_per_1m": 0.2,
1635
- "output_price_per_1m": 1.25,
1636
- "currency": "USD",
1637
- "capabilities": [
1638
- "vision",
1639
- "reasoning"
1640
- ],
1641
- "context_window": 400000,
1642
- "hf_private": true
1643
- },
1644
- {
1645
- "name": "openai/gpt-5.4-nano",
1646
  "type": "vision",
1647
  "input_price_per_1m": 0.2,
1648
- "output_price_per_1m": 1.25,
1649
  "currency": "USD",
1650
  "capabilities": [
1651
- "vision",
1652
- "reasoning"
1653
  ],
1654
- "context_window": 400000,
1655
  "hf_private": true
1656
  },
1657
  {
1658
- "name": "xai/grok-code-fast-1",
1659
  "type": "vision",
1660
  "input_price_per_1m": 0.2,
1661
- "output_price_per_1m": 1.5,
1662
  "currency": "USD",
1663
  "capabilities": [
1664
  "vision"
1665
  ],
1666
- "context_window": 256000,
1667
  "hf_private": true
1668
  },
1669
  {
1670
- "name": "xai/grok-4-fast",
1671
  "type": "chat",
1672
  "input_price_per_1m": 0.2,
1673
  "output_price_per_1m": 0.5,
@@ -1681,7 +1637,7 @@
1681
  "hf_private": true
1682
  },
1683
  {
1684
- "name": "xai/grok-4-1-fast-reasoning",
1685
  "type": "vision",
1686
  "input_price_per_1m": 0.2,
1687
  "output_price_per_1m": 0.5,
@@ -1693,7 +1649,7 @@
1693
  "hf_private": true
1694
  },
1695
  {
1696
- "name": "xai/grok-4-fast-non-reasoning",
1697
  "type": "chat",
1698
  "input_price_per_1m": 0.2,
1699
  "output_price_per_1m": 0.5,
@@ -1707,15 +1663,30 @@
1707
  "hf_private": true
1708
  },
1709
  {
1710
- "name": "xai/grok-4-1-fast-non-reasoning",
1711
  "type": "vision",
1712
  "input_price_per_1m": 0.2,
1713
- "output_price_per_1m": 0.5,
1714
  "currency": "USD",
1715
  "capabilities": [
1716
  "vision"
1717
  ],
1718
- "context_window": 2000000,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1719
  "hf_private": true
1720
  },
1721
  {
@@ -1728,6 +1699,21 @@
1728
  "size_b": 8,
1729
  "hf_private": false
1730
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1731
  {
1732
  "name": "deepinfra/zai-org/GLM-4.5-Air",
1733
  "type": "chat",
@@ -1744,12 +1730,25 @@
1744
  "hf_private": false
1745
  },
1746
  {
1747
- "name": "deepinfra/Qwen/Qwen3-235B-A22B",
 
 
 
 
 
 
 
 
 
 
 
 
 
1748
  "type": "chat",
1749
  "input_price_per_1m": 0.2,
1750
- "output_price_per_1m": 0.6,
1751
  "currency": "USD",
1752
- "context_window": 40000,
1753
  "size_b": 235,
1754
  "capabilities": [
1755
  "tools",
@@ -1759,45 +1758,42 @@
1759
  "hf_private": false
1760
  },
1761
  {
1762
- "name": "alibaba/qwen3-30b-a3b-instruct-2507",
1763
- "type": "vision",
1764
  "input_price_per_1m": 0.2,
1765
- "output_price_per_1m": 0.8,
1766
  "currency": "USD",
 
 
1767
  "capabilities": [
1768
- "vision"
 
1769
  ],
1770
- "context_window": 131072,
1771
- "size_b": 30,
1772
- "hf_id": "Qwen/Qwen3-30B-A3B-Instruct-2507",
1773
  "hf_private": false
1774
  },
1775
  {
1776
- "name": "deepinfra/Qwen/Qwen2.5-72B-Instruct",
1777
  "type": "chat",
1778
  "input_price_per_1m": 0.23,
1779
  "output_price_per_1m": 0.4,
1780
  "currency": "USD",
1781
- "context_window": 131072,
1782
- "size_b": 72,
1783
- "capabilities": [
1784
- "vision"
1785
- ],
1786
- "hf_id": "Qwen/Qwen2.5-VL-72B-Instruct",
1787
  "hf_private": false
1788
  },
1789
  {
1790
- "name": "deepinfra/meta-llama/Llama-3.3-70B-Instruct",
1791
  "type": "chat",
1792
  "input_price_per_1m": 0.23,
1793
  "output_price_per_1m": 0.4,
1794
  "currency": "USD",
1795
  "context_window": 131072,
1796
- "size_b": 70,
1797
  "capabilities": [
1798
- "tools"
1799
  ],
1800
- "hf_id": "meta-llama/Llama-3.3-70B-Instruct",
1801
  "hf_private": false
1802
  },
1803
  {
@@ -1815,50 +1811,53 @@
1815
  "hf_private": false
1816
  },
1817
  {
1818
- "name": "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct",
1819
  "type": "chat",
1820
  "input_price_per_1m": 0.23,
1821
  "output_price_per_1m": 0.4,
1822
  "currency": "USD",
1823
- "context_window": 130815,
1824
  "size_b": 70,
 
 
 
 
1825
  "hf_private": false
1826
  },
1827
  {
1828
- "name": "google/gemini-3.1-flash-lite-preview",
1829
- "type": "vision",
1830
  "input_price_per_1m": 0.25,
1831
- "output_price_per_1m": 1.5,
1832
  "currency": "USD",
1833
  "capabilities": [
1834
- "vision"
1835
  ],
1836
- "context_window": 1048576,
1837
  "hf_private": true
1838
  },
1839
  {
1840
- "name": "azure/gpt-5-mini",
1841
- "type": "chat",
1842
  "input_price_per_1m": 0.25,
1843
- "output_price_per_1m": 2,
1844
  "currency": "USD",
1845
  "capabilities": [
1846
- "reasoning"
1847
  ],
1848
- "context_window": 200000,
1849
  "hf_private": true
1850
  },
1851
  {
1852
- "name": "openai-responses/gpt-5-mini",
1853
  "type": "vision",
1854
  "input_price_per_1m": 0.25,
1855
- "output_price_per_1m": 2,
1856
  "currency": "USD",
1857
  "capabilities": [
1858
- "vision",
1859
- "reasoning"
1860
  ],
1861
- "context_window": 400000,
1862
  "hf_private": true
1863
  },
1864
  {
@@ -1872,15 +1871,16 @@
1872
  "hf_private": false
1873
  },
1874
  {
1875
- "name": "vertex/gemini-3.1-flash-lite-preview",
1876
  "type": "vision",
1877
  "input_price_per_1m": 0.25,
1878
- "output_price_per_1m": 1.5,
1879
  "currency": "USD",
1880
  "capabilities": [
1881
- "vision"
 
1882
  ],
1883
- "context_window": 1048576,
1884
  "hf_private": true
1885
  },
1886
  {
@@ -1922,7 +1922,19 @@
1922
  "hf_private": true
1923
  },
1924
  {
1925
- "name": "google/gemini-2.5-flash",
 
 
 
 
 
 
 
 
 
 
 
 
1926
  "type": "vision",
1927
  "input_price_per_1m": 0.3,
1928
  "output_price_per_1m": 2.5,
@@ -1935,94 +1947,75 @@
1935
  "hf_private": true
1936
  },
1937
  {
1938
- "name": "nebius/deepseek-ai/DeepSeek-V3.2",
1939
  "type": "chat",
1940
  "input_price_per_1m": 0.3,
1941
- "output_price_per_1m": 0.45,
1942
  "currency": "USD",
1943
- "capabilities": [
1944
- "reasoning"
1945
- ],
1946
- "context_window": 164000,
1947
- "hf_id": "deepseek-ai/DeepSeek-V3.2",
1948
- "size_b": 685.4,
1949
  "hf_private": false
1950
  },
1951
  {
1952
- "name": "nebius/minimax/minimax-m2.1",
1953
- "type": "chat",
1954
  "input_price_per_1m": 0.3,
1955
- "output_price_per_1m": 1.2,
1956
  "currency": "USD",
1957
  "capabilities": [
1958
- "reasoning"
1959
  ],
1960
- "context_window": 200000,
1961
- "hf_id": "MiniMaxAI/MiniMax-M2.1",
1962
- "size_b": 228.7,
1963
- "hf_private": false
1964
  },
1965
  {
1966
- "name": "novita/deepseek/deepseek-r1-distill-qwen-32b",
1967
- "type": "chat",
1968
  "input_price_per_1m": 0.3,
1969
- "output_price_per_1m": 0.3,
1970
  "currency": "USD",
1971
- "context_window": 12800,
1972
- "size_b": 32,
1973
  "capabilities": [
 
1974
  "reasoning"
1975
  ],
1976
- "hf_id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
1977
- "hf_private": false
1978
  },
1979
  {
1980
- "name": "novita/MiniMax-M2.7",
1981
- "type": "vision",
1982
  "input_price_per_1m": 0.3,
1983
- "output_price_per_1m": 1.2,
1984
  "currency": "USD",
1985
- "capabilities": [
1986
- "vision",
1987
- "reasoning"
1988
- ],
1989
- "context_window": 200000,
1990
- "hf_id": "MiniMaxAI/MiniMax-M2.7",
1991
- "hf_private": false,
1992
- "size_b": 230,
1993
- "size_source": "manual"
1994
  },
1995
  {
1996
- "name": "novita/minimax-m2.7",
1997
  "type": "vision",
1998
  "input_price_per_1m": 0.3,
1999
- "output_price_per_1m": 1.2,
2000
  "currency": "USD",
2001
  "capabilities": [
2002
  "vision",
2003
  "reasoning"
2004
  ],
2005
- "context_window": 200000,
2006
- "hf_id": "MiniMaxAI/MiniMax-M2.7",
2007
- "hf_private": false,
2008
- "size_b": 230,
2009
- "size_source": "manual"
2010
  },
2011
  {
2012
- "name": "minimaxi/MiniMax-M2.7",
2013
  "type": "vision",
2014
  "input_price_per_1m": 0.3,
2015
- "output_price_per_1m": 1.2,
2016
  "currency": "USD",
2017
  "capabilities": [
2018
  "vision",
2019
  "reasoning"
2020
  ],
2021
- "context_window": 200000,
2022
- "hf_id": "MiniMaxAI/MiniMax-M2.7",
2023
- "hf_private": false,
2024
- "size_b": 230,
2025
- "size_source": "manual"
2026
  },
2027
  {
2028
  "name": "minimaxi/MiniMax-M2",
@@ -2055,29 +2048,35 @@
2055
  "hf_private": false
2056
  },
2057
  {
2058
- "name": "xai/grok-3-mini",
2059
- "type": "chat",
2060
  "input_price_per_1m": 0.3,
2061
- "output_price_per_1m": 0.5,
2062
  "currency": "USD",
2063
  "capabilities": [
 
2064
  "reasoning"
2065
  ],
2066
- "context_window": 131072,
2067
- "hf_private": true
 
 
 
2068
  },
2069
  {
2070
- "name": "coding/gemini-2.5-flash",
2071
- "type": "vision",
2072
  "input_price_per_1m": 0.3,
2073
- "output_price_per_1m": 2.5,
2074
  "currency": "USD",
 
2075
  "capabilities": [
2076
- "vision",
2077
  "reasoning"
2078
  ],
2079
- "context_window": 1048576,
2080
- "hf_private": true
 
2081
  },
2082
  {
2083
  "name": "mistral/codestral-latest",
@@ -2089,77 +2088,78 @@
2089
  "hf_private": true
2090
  },
2091
  {
2092
- "name": "together/Qwen/Qwen2.5-7B-Instruct-Turbo",
2093
  "type": "chat",
2094
  "input_price_per_1m": 0.3,
2095
- "output_price_per_1m": 0.3,
2096
  "currency": "USD",
2097
- "context_window": 32768,
2098
- "size_b": 7,
 
 
 
 
2099
  "hf_private": false
2100
  },
2101
  {
2102
- "name": "vertex/gemini-2.5-flash",
2103
- "type": "vision",
2104
  "input_price_per_1m": 0.3,
2105
- "output_price_per_1m": 2.5,
2106
  "currency": "USD",
2107
  "capabilities": [
2108
- "vision",
2109
  "reasoning"
2110
  ],
2111
- "context_window": 1048576,
2112
- "hf_private": true
 
 
2113
  },
2114
  {
2115
- "name": "vertex/gemini-2.5-flash-image",
2116
  "type": "vision",
2117
  "input_price_per_1m": 0.3,
2118
- "output_price_per_1m": 2.5,
2119
  "currency": "USD",
2120
  "capabilities": [
2121
  "vision",
2122
  "reasoning"
2123
  ],
2124
- "context_window": 1048576,
2125
- "hf_private": true
 
 
 
2126
  },
2127
  {
2128
- "name": "deepinfra/deepseek-ai/DeepSeek-V3.1",
2129
- "type": "chat",
2130
  "input_price_per_1m": 0.3,
2131
- "output_price_per_1m": 1,
2132
  "currency": "USD",
2133
- "context_window": 163840,
2134
  "capabilities": [
2135
- "tools",
2136
  "reasoning"
2137
  ],
2138
- "hf_id": "deepseek-ai/DeepSeek-V3.1-Terminus",
2139
- "size_b": 671,
2140
- "hf_private": false
 
 
2141
  },
2142
  {
2143
- "name": "parasail/parasail-gemma3-27b-it",
2144
  "type": "chat",
2145
  "input_price_per_1m": 0.3,
2146
- "output_price_per_1m": 0.5,
2147
- "currency": "USD",
2148
- "context_window": 128000,
2149
- "size_b": 27,
2150
- "hf_private": false
2151
- },
2152
- {
2153
- "name": "alibaba/qwen3-coder-flash",
2154
- "type": "vision",
2155
- "input_price_per_1m": 0.3,
2156
- "output_price_per_1m": 1.5,
2157
  "currency": "USD",
 
 
2158
  "capabilities": [
2159
- "vision"
2160
  ],
2161
- "context_window": 1048576,
2162
- "hf_private": true
2163
  },
2164
  {
2165
  "name": "deepinfra/meta-llama/Llama-3.2-90B-Vision-Instruct",
@@ -2224,59 +2224,19 @@
2224
  "hf_private": true
2225
  },
2226
  {
2227
- "name": "nebius/Qwen/Qwen3-Coder-480B-A35B-Instruct",
2228
  "type": "chat",
2229
  "input_price_per_1m": 0.4,
2230
- "output_price_per_1m": 1.8,
2231
  "currency": "USD",
2232
- "context_window": 262000,
2233
- "size_b": 480,
2234
  "capabilities": [
2235
  "tools"
2236
  ],
2237
- "hf_id": "Qwen/Qwen3-Coder-480B-A35B-Instruct",
2238
- "hf_private": false
2239
- },
2240
- {
2241
- "name": "nebius/zai-org/GLM-4.7",
2242
- "type": "chat",
2243
- "input_price_per_1m": 0.4,
2244
- "output_price_per_1m": 2,
2245
- "currency": "USD",
2246
- "capabilities": [
2247
- "reasoning"
2248
- ],
2249
- "context_window": 200000,
2250
- "hf_id": "zai-org/GLM-4.7",
2251
- "size_b": 358.3,
2252
- "hf_private": false
2253
- },
2254
- {
2255
- "name": "novita/deepseek/deepseek-v3-turbo",
2256
- "type": "chat",
2257
- "input_price_per_1m": 0.4,
2258
- "output_price_per_1m": 1.3,
2259
- "currency": "USD",
2260
- "context_window": 128000,
2261
  "hf_private": true
2262
  },
2263
  {
2264
- "name": "novita/deepseek/deepseek-v3-0324",
2265
- "type": "chat",
2266
- "input_price_per_1m": 0.4,
2267
- "output_price_per_1m": 1.3,
2268
- "currency": "USD",
2269
- "context_window": 128000,
2270
- "capabilities": [
2271
- "tools",
2272
- "reasoning"
2273
- ],
2274
- "size_b": 685,
2275
- "hf_id": "deepseek-ai/DeepSeek-V3-0324",
2276
- "hf_private": false
2277
- },
2278
- {
2279
- "name": "openai-responses/gpt-4.1-mini",
2280
  "type": "vision",
2281
  "input_price_per_1m": 0.4,
2282
  "output_price_per_1m": 1.6,
@@ -2288,16 +2248,18 @@
2288
  "hf_private": true
2289
  },
2290
  {
2291
- "name": "openai/gpt-4.1-mini",
2292
- "type": "vision",
2293
  "input_price_per_1m": 0.4,
2294
  "output_price_per_1m": 1.6,
2295
  "currency": "USD",
 
 
2296
  "capabilities": [
2297
- "vision"
2298
  ],
2299
- "context_window": 1047576,
2300
- "hf_private": true
2301
  },
2302
  {
2303
  "name": "mistral/mistral-medium-latest",
@@ -2308,15 +2270,6 @@
2308
  "context_window": 131072,
2309
  "hf_private": true
2310
  },
2311
- {
2312
- "name": "mistral/devstral-latest",
2313
- "type": "chat",
2314
- "input_price_per_1m": 0.4,
2315
- "output_price_per_1m": 2,
2316
- "currency": "USD",
2317
- "context_window": 256000,
2318
- "hf_private": true
2319
- },
2320
  {
2321
  "name": "mistral/devstral-medium-2507",
2322
  "type": "chat",
@@ -2330,91 +2283,59 @@
2330
  "hf_private": true
2331
  },
2332
  {
2333
- "name": "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct",
2334
- "type": "chat",
2335
- "input_price_per_1m": 0.4,
2336
- "output_price_per_1m": 1.6,
2337
- "currency": "USD",
2338
- "context_window": 262144,
2339
- "size_b": 480,
2340
- "capabilities": [
2341
- "tools"
2342
- ],
2343
- "hf_id": "Qwen/Qwen3-Coder-480B-A35B-Instruct",
2344
- "hf_private": false
2345
- },
2346
- {
2347
- "name": "alibaba/qwen-plus",
2348
  "type": "chat",
2349
  "input_price_per_1m": 0.4,
2350
- "output_price_per_1m": 1.2,
2351
- "currency": "USD",
2352
- "context_window": 131072,
2353
- "capabilities": [
2354
- "tools"
2355
- ],
2356
- "hf_private": true
2357
- },
2358
- {
2359
- "name": "google/gemini-3.1-flash-image-preview",
2360
- "type": "vision",
2361
- "input_price_per_1m": 0.5,
2362
  "output_price_per_1m": 2,
2363
  "currency": "USD",
2364
- "capabilities": [
2365
- "vision",
2366
- "reasoning"
2367
- ],
2368
- "context_window": 131072,
2369
  "hf_private": true
2370
  },
2371
  {
2372
- "name": "google/gemini-3-flash-preview",
2373
  "type": "vision",
2374
- "input_price_per_1m": 0.5,
2375
- "output_price_per_1m": 3,
2376
  "currency": "USD",
2377
  "capabilities": [
2378
- "vision",
2379
- "reasoning"
2380
  ],
2381
- "context_window": 1048576,
2382
  "hf_private": true
2383
  },
2384
  {
2385
- "name": "nebius/moonshotai/Kimi-K2-Instruct",
2386
  "type": "chat",
2387
- "input_price_per_1m": 0.5,
2388
- "output_price_per_1m": 2.4,
2389
  "currency": "USD",
2390
- "context_window": 131000,
 
2391
  "capabilities": [
2392
  "tools"
2393
  ],
2394
- "hf_id": "moonshotai/Kimi-K2-Instruct",
2395
- "size_b": 1026.5,
2396
  "hf_private": false
2397
  },
2398
  {
2399
- "name": "nebius/moonshotai/kimi-k2.5",
2400
- "type": "vision",
2401
- "input_price_per_1m": 0.5,
2402
- "output_price_per_1m": 2.5,
2403
  "currency": "USD",
2404
  "capabilities": [
2405
- "vision",
2406
  "reasoning"
2407
  ],
2408
- "context_window": 256000,
2409
- "hf_id": "moonshotai/Kimi-K2.5",
2410
- "size_b": 1058.6,
2411
  "hf_private": false
2412
  },
2413
  {
2414
- "name": "nebius/deepseek-ai/DeepSeek-V3-0324",
2415
  "type": "chat",
2416
- "input_price_per_1m": 0.5,
2417
- "output_price_per_1m": 1.5,
2418
  "currency": "USD",
2419
  "context_window": 128000,
2420
  "capabilities": [
@@ -2426,19 +2347,16 @@
2426
  "hf_private": false
2427
  },
2428
  {
2429
- "name": "mistral/mistral-large-latest",
2430
  "type": "chat",
2431
- "input_price_per_1m": 0.5,
2432
- "output_price_per_1m": 1.5,
2433
  "currency": "USD",
2434
- "context_window": 131072,
2435
- "capabilities": [
2436
- "tools"
2437
- ],
2438
  "hf_private": true
2439
  },
2440
  {
2441
- "name": "vertex/gemini-3.1-flash-image-preview",
2442
  "type": "vision",
2443
  "input_price_per_1m": 0.5,
2444
  "output_price_per_1m": 2,
@@ -2451,7 +2369,7 @@
2451
  "hf_private": true
2452
  },
2453
  {
2454
- "name": "vertex/gemini-3-flash-preview",
2455
  "type": "vision",
2456
  "input_price_per_1m": 0.5,
2457
  "output_price_per_1m": 3,
@@ -2464,53 +2382,50 @@
2464
  "hf_private": true
2465
  },
2466
  {
2467
- "name": "novita/meta-llama/llama-3-70b-instruct",
2468
- "type": "chat",
2469
- "input_price_per_1m": 0.51,
2470
- "output_price_per_1m": 0.74,
2471
  "currency": "USD",
2472
- "context_window": 8192,
2473
- "size_b": 70,
2474
  "capabilities": [
2475
- "tools"
 
2476
  ],
2477
- "hf_id": "meta-llama/Llama-3.3-70B-Instruct",
2478
- "hf_private": false
2479
  },
2480
  {
2481
- "name": "openai/o4-mini",
2482
- "type": "chat",
2483
- "input_price_per_1m": 0.55,
2484
- "output_price_per_1m": 2.2,
2485
  "currency": "USD",
2486
  "capabilities": [
 
2487
  "reasoning"
2488
  ],
2489
- "context_window": 200000,
2490
  "hf_private": true
2491
  },
2492
  {
2493
- "name": "vertex/deepseek-v3.2",
2494
- "type": "vision",
2495
- "input_price_per_1m": 0.56,
2496
- "output_price_per_1m": 1.68,
2497
  "currency": "USD",
 
2498
  "capabilities": [
2499
- "vision",
2500
- "reasoning"
2501
  ],
2502
- "context_window": 163840,
2503
- "hf_id": "deepseek-ai/DeepSeek-V3.2",
2504
- "size_b": 685.4,
2505
- "hf_private": false
2506
  },
2507
  {
2508
- "name": "novita/moonshotai/kimi-k2-instruct",
2509
  "type": "chat",
2510
- "input_price_per_1m": 0.57,
2511
- "output_price_per_1m": 2.3,
2512
  "currency": "USD",
2513
- "context_window": 131072,
2514
  "capabilities": [
2515
  "tools"
2516
  ],
@@ -2519,90 +2434,88 @@
2519
  "hf_private": false
2520
  },
2521
  {
2522
- "name": "nebius/zai-org/GLM-4.5",
2523
  "type": "chat",
2524
- "input_price_per_1m": 0.6,
2525
- "output_price_per_1m": 2.2,
2526
  "currency": "USD",
2527
  "context_window": 128000,
2528
  "capabilities": [
2529
  "tools",
2530
  "reasoning"
2531
- ],
2532
- "hf_id": "zai-org/GLM-4.5",
2533
- "size_b": 358.3,
2534
  "hf_private": false
2535
  },
2536
  {
2537
- "name": "novita/zai-org/glm-4.6",
2538
- "type": "chat",
2539
- "input_price_per_1m": 0.6,
2540
- "output_price_per_1m": 2.2,
2541
  "currency": "USD",
2542
- "context_window": 204800,
2543
  "capabilities": [
2544
- "tools",
2545
  "reasoning"
2546
  ],
2547
- "hf_id": "zai-org/GLM-4.6",
2548
- "size_b": 356.8,
 
2549
  "hf_private": false
2550
  },
2551
  {
2552
- "name": "novita/zai-org/glm-4.5",
2553
  "type": "chat",
2554
- "input_price_per_1m": 0.6,
2555
- "output_price_per_1m": 2.2,
2556
  "currency": "USD",
2557
- "context_window": 131072,
 
2558
  "capabilities": [
2559
- "tools",
2560
- "reasoning"
2561
  ],
2562
- "hf_id": "zai-org/GLM-4.5",
2563
- "size_b": 358.3,
2564
  "hf_private": false
2565
  },
2566
  {
2567
- "name": "zai/GLM-4.7",
2568
  "type": "chat",
2569
- "input_price_per_1m": 0.6,
2570
  "output_price_per_1m": 2.2,
2571
  "currency": "USD",
2572
  "capabilities": [
2573
  "reasoning"
2574
  ],
2575
  "context_window": 200000,
2576
- "hf_id": "zai-org/GLM-4.7",
2577
- "size_b": 358.3,
2578
- "hf_private": false
2579
  },
2580
  {
2581
- "name": "zai/GLM-4.5",
2582
- "type": "chat",
2583
- "input_price_per_1m": 0.6,
2584
- "output_price_per_1m": 2.2,
2585
  "currency": "USD",
2586
  "capabilities": [
 
2587
  "reasoning"
2588
  ],
2589
- "context_window": 131072,
2590
- "hf_id": "zai-org/GLM-4.5",
2591
- "size_b": 358.3,
2592
  "hf_private": false
2593
  },
2594
  {
2595
- "name": "zai/GLM-4.6",
2596
  "type": "chat",
2597
- "input_price_per_1m": 0.6,
2598
- "output_price_per_1m": 2.2,
2599
  "currency": "USD",
 
2600
  "capabilities": [
2601
- "reasoning"
2602
  ],
2603
- "context_window": 200000,
2604
- "hf_id": "zai-org/GLM-4.6",
2605
- "size_b": 356.8,
2606
  "hf_private": false
2607
  },
2608
  {
@@ -2677,6 +2590,21 @@
2677
  "size_b": 1026.5,
2678
  "hf_private": false
2679
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2680
  {
2681
  "name": "minimaxi/MiniMax-M2.7-highspeed",
2682
  "type": "vision",
@@ -2724,18 +2652,90 @@
2724
  "hf_private": false
2725
  },
2726
  {
2727
- "name": "alibaba/qwen3.5",
2728
- "type": "vision",
2729
  "input_price_per_1m": 0.6,
2730
- "output_price_per_1m": 3.6,
2731
  "currency": "USD",
2732
  "capabilities": [
2733
- "vision",
2734
  "reasoning"
2735
  ],
2736
- "context_window": 256000,
2737
- "size_b": 9,
2738
- "hf_id": "Qwen/Qwen3.5-9B",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2739
  "hf_private": false
2740
  },
2741
  {
@@ -2763,13 +2763,16 @@
2763
  "hf_private": true
2764
  },
2765
  {
2766
- "name": "novita/deepseek/deepseek-prover-v2-671b",
2767
- "type": "chat",
2768
  "input_price_per_1m": 0.7,
2769
- "output_price_per_1m": 2.5,
2770
  "currency": "USD",
2771
- "context_window": 160000,
2772
- "size_b": 671,
 
 
 
2773
  "hf_private": false
2774
  },
2775
  {
@@ -2789,20 +2792,17 @@
2789
  "hf_private": false
2790
  },
2791
  {
2792
- "name": "parasail/parasail-qwen25-vl-72b-instruct",
2793
- "type": "vision",
2794
  "input_price_per_1m": 0.7,
2795
- "output_price_per_1m": 0.7,
2796
  "currency": "USD",
2797
- "capabilities": [
2798
- "vision"
2799
- ],
2800
- "context_window": 32768,
2801
- "size_b": 72,
2802
  "hf_private": false
2803
  },
2804
  {
2805
- "name": "openai-responses/gpt-5.4-mini",
2806
  "type": "vision",
2807
  "input_price_per_1m": 0.75,
2808
  "output_price_per_1m": 4.5,
@@ -2815,7 +2815,7 @@
2815
  "hf_private": true
2816
  },
2817
  {
2818
- "name": "openai/gpt-5.4-mini",
2819
  "type": "vision",
2820
  "input_price_per_1m": 0.75,
2821
  "output_price_per_1m": 4.5,
@@ -2827,6 +2827,16 @@
2827
  "context_window": 400000,
2828
  "hf_private": true
2829
  },
 
 
 
 
 
 
 
 
 
 
2830
  {
2831
  "name": "nebius/deepseek-ai/DeepSeek-R1-0528",
2832
  "type": "chat",
@@ -2842,20 +2852,6 @@
2842
  "size_b": 684.5,
2843
  "hf_private": false
2844
  },
2845
- {
2846
- "name": "novita/qwen/qwen2.5-vl-72b-instruct",
2847
- "type": "chat",
2848
- "input_price_per_1m": 0.8,
2849
- "output_price_per_1m": 0.8,
2850
- "currency": "USD",
2851
- "context_window": 96000,
2852
- "size_b": 72,
2853
- "capabilities": [
2854
- "vision"
2855
- ],
2856
- "hf_id": "Qwen/Qwen2.5-VL-72B-Instruct",
2857
- "hf_private": false
2858
- },
2859
  {
2860
  "name": "novita/deepseek/deepseek-r1-distill-llama-70b",
2861
  "type": "chat",
@@ -2871,13 +2867,17 @@
2871
  "hf_private": false
2872
  },
2873
  {
2874
- "name": "deepinfra/meta-llama/Meta-Llama-3.1-405B-Instruct",
2875
  "type": "chat",
2876
  "input_price_per_1m": 0.8,
2877
  "output_price_per_1m": 0.8,
2878
  "currency": "USD",
2879
- "context_window": 130815,
2880
- "size_b": 405,
 
 
 
 
2881
  "hf_private": false
2882
  },
2883
  {
@@ -2958,50 +2958,70 @@
2958
  "tools",
2959
  "reasoning"
2960
  ],
2961
- "hf_id": "deepseek-ai/DeepSeek-V3.1-Terminus",
2962
- "size_b": 671,
2963
- "hf_private": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2964
  },
2965
  {
2966
- "name": "parasail/parasail-kimi-k2-instruct",
2967
- "type": "chat",
2968
- "input_price_per_1m": 0.99,
2969
- "output_price_per_1m": 2.99,
2970
  "currency": "USD",
2971
- "context_window": 131072,
 
 
 
2972
  "hf_private": true
2973
  },
2974
  {
2975
- "name": "novita/GLM-5",
2976
- "type": "chat",
2977
  "input_price_per_1m": 1,
2978
- "output_price_per_1m": 3.2,
2979
  "currency": "USD",
2980
  "capabilities": [
2981
- "reasoning"
2982
  ],
2983
- "context_window": 202800,
2984
- "hf_id": "zai-org/GLM-5",
2985
- "size_b": 753.9,
2986
- "hf_private": false
2987
  },
2988
  {
2989
- "name": "zai/GLM-5",
2990
  "type": "vision",
2991
  "input_price_per_1m": 1,
2992
- "output_price_per_1m": 3.2,
2993
  "currency": "USD",
2994
  "capabilities": [
2995
  "vision",
2996
  "reasoning"
2997
  ],
2998
  "context_window": 200000,
2999
- "hf_id": "zai-org/GLM-5",
3000
- "size_b": 753.9,
3001
- "hf_private": false
3002
  },
3003
  {
3004
- "name": "bedrock/claude-haiku-4-5",
3005
  "type": "vision",
3006
  "input_price_per_1m": 1,
3007
  "output_price_per_1m": 5,
@@ -3013,17 +3033,19 @@
3013
  "hf_private": true
3014
  },
3015
  {
3016
- "name": "openai/o3",
3017
  "type": "vision",
3018
  "input_price_per_1m": 1,
3019
- "output_price_per_1m": 4,
3020
  "currency": "USD",
3021
  "capabilities": [
3022
  "vision",
3023
  "reasoning"
3024
  ],
3025
  "context_window": 200000,
3026
- "hf_private": true
 
 
3027
  },
3028
  {
3029
  "name": "groq/moonshotai/kimi-k2-instruct",
@@ -3066,40 +3088,18 @@
3066
  "hf_private": true
3067
  },
3068
  {
3069
- "name": "anthropic/claude-haiku-4-5",
3070
- "type": "vision",
3071
- "input_price_per_1m": 1,
3072
- "output_price_per_1m": 5,
3073
- "currency": "USD",
3074
- "capabilities": [
3075
- "vision"
3076
- ],
3077
- "context_window": 200000,
3078
- "hf_private": true
3079
- },
3080
- {
3081
- "name": "vertex/claude-haiku-4-5",
3082
- "type": "vision",
3083
- "input_price_per_1m": 1,
3084
- "output_price_per_1m": 5,
3085
- "currency": "USD",
3086
- "capabilities": [
3087
- "vision"
3088
- ],
3089
- "context_window": 200000,
3090
- "hf_private": true
3091
- },
3092
- {
3093
- "name": "alibaba/qwen3-coder-plus",
3094
- "type": "vision",
3095
  "input_price_per_1m": 1,
3096
- "output_price_per_1m": 5,
3097
  "currency": "USD",
3098
  "capabilities": [
3099
- "vision"
3100
  ],
3101
- "context_window": 1048576,
3102
- "hf_private": true
 
 
3103
  },
3104
  {
3105
  "name": "azure/o4-mini",
@@ -3114,7 +3114,7 @@
3114
  "hf_private": true
3115
  },
3116
  {
3117
- "name": "openai-responses/o3-mini",
3118
  "type": "chat",
3119
  "input_price_per_1m": 1.1,
3120
  "output_price_per_1m": 4.4,
@@ -3126,7 +3126,7 @@
3126
  "hf_private": true
3127
  },
3128
  {
3129
- "name": "openai-responses/o4-mini",
3130
  "type": "chat",
3131
  "input_price_per_1m": 1.1,
3132
  "output_price_per_1m": 4.4,
@@ -3138,7 +3138,7 @@
3138
  "hf_private": true
3139
  },
3140
  {
3141
- "name": "openai/o3-mini",
3142
  "type": "chat",
3143
  "input_price_per_1m": 1.1,
3144
  "output_price_per_1m": 4.4,
@@ -3173,19 +3173,6 @@
3173
  "size_b": 72,
3174
  "hf_private": false
3175
  },
3176
- {
3177
- "name": "google/gemini-2.5-pro",
3178
- "type": "vision",
3179
- "input_price_per_1m": 1.25,
3180
- "output_price_per_1m": 10,
3181
- "currency": "USD",
3182
- "capabilities": [
3183
- "vision",
3184
- "reasoning"
3185
- ],
3186
- "context_window": 1048576,
3187
- "hf_private": true
3188
- },
3189
  {
3190
  "name": "azure/gpt-5",
3191
  "type": "chat",
@@ -3211,7 +3198,7 @@
3211
  "hf_private": true
3212
  },
3213
  {
3214
- "name": "openai-responses/gpt-5.1",
3215
  "type": "vision",
3216
  "input_price_per_1m": 1.25,
3217
  "output_price_per_1m": 10,
@@ -3220,11 +3207,11 @@
3220
  "vision",
3221
  "reasoning"
3222
  ],
3223
- "context_window": 400000,
3224
  "hf_private": true
3225
  },
3226
  {
3227
- "name": "openai-responses/gpt-5-codex",
3228
  "type": "vision",
3229
  "input_price_per_1m": 1.25,
3230
  "output_price_per_1m": 10,
@@ -3233,11 +3220,11 @@
3233
  "vision",
3234
  "reasoning"
3235
  ],
3236
- "context_window": 400000,
3237
  "hf_private": true
3238
  },
3239
  {
3240
- "name": "openai-responses/gpt-5",
3241
  "type": "vision",
3242
  "input_price_per_1m": 1.25,
3243
  "output_price_per_1m": 10,
@@ -3246,11 +3233,11 @@
3246
  "vision",
3247
  "reasoning"
3248
  ],
3249
- "context_window": 400000,
3250
  "hf_private": true
3251
  },
3252
  {
3253
- "name": "openai-responses/gpt-5.1-codex",
3254
  "type": "vision",
3255
  "input_price_per_1m": 1.25,
3256
  "output_price_per_1m": 10,
@@ -3276,7 +3263,22 @@
3276
  "hf_private": true
3277
  },
3278
  {
3279
- "name": "openai/gpt-5.1",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3280
  "type": "vision",
3281
  "input_price_per_1m": 1.25,
3282
  "output_price_per_1m": 10,
@@ -3285,11 +3287,11 @@
3285
  "vision",
3286
  "reasoning"
3287
  ],
3288
- "context_window": 400000,
3289
  "hf_private": true
3290
  },
3291
  {
3292
- "name": "openai/gpt-5.1-chat",
3293
  "type": "vision",
3294
  "input_price_per_1m": 1.25,
3295
  "output_price_per_1m": 10,
@@ -3298,11 +3300,11 @@
3298
  "vision",
3299
  "reasoning"
3300
  ],
3301
- "context_window": 128000,
3302
  "hf_private": true
3303
  },
3304
  {
3305
- "name": "coding/gemini-2.5-pro",
3306
  "type": "vision",
3307
  "input_price_per_1m": 1.25,
3308
  "output_price_per_1m": 10,
@@ -3311,26 +3313,24 @@
3311
  "vision",
3312
  "reasoning"
3313
  ],
3314
- "context_window": 1048576,
3315
  "hf_private": true
3316
  },
3317
  {
3318
- "name": "together/deepseek-ai/DeepSeek-V3",
3319
- "type": "chat",
3320
  "input_price_per_1m": 1.25,
3321
- "output_price_per_1m": 1.25,
3322
  "currency": "USD",
3323
- "context_window": 131072,
3324
  "capabilities": [
3325
- "tools",
3326
  "reasoning"
3327
  ],
3328
- "hf_id": "deepseek-ai/DeepSeek-V3.1-Terminus",
3329
- "size_b": 671,
3330
- "hf_private": false
3331
  },
3332
  {
3333
- "name": "vertex/gemini-2.5-pro",
3334
  "type": "vision",
3335
  "input_price_per_1m": 1.25,
3336
  "output_price_per_1m": 10,
@@ -3339,11 +3339,11 @@
3339
  "vision",
3340
  "reasoning"
3341
  ],
3342
- "context_window": 1048576,
3343
  "hf_private": true
3344
  },
3345
  {
3346
- "name": "novita/sao10k/l31-70b-euryale-v2.2",
3347
  "type": "chat",
3348
  "input_price_per_1m": 1.48,
3349
  "output_price_per_1m": 1.48,
@@ -3353,7 +3353,7 @@
3353
  "hf_private": false
3354
  },
3355
  {
3356
- "name": "novita/sao10k/l3-70b-euryale-v2.1",
3357
  "type": "chat",
3358
  "input_price_per_1m": 1.48,
3359
  "output_price_per_1m": 1.48,
@@ -3374,18 +3374,6 @@
3374
  ],
3375
  "hf_private": true
3376
  },
3377
- {
3378
- "name": "azure/gpt-5.2",
3379
- "type": "chat",
3380
- "input_price_per_1m": 1.75,
3381
- "output_price_per_1m": 14,
3382
- "currency": "USD",
3383
- "capabilities": [
3384
- "reasoning"
3385
- ],
3386
- "context_window": 200000,
3387
- "hf_private": true
3388
- },
3389
  {
3390
  "name": "azure/openai-responses/gpt-5.2-codex",
3391
  "type": "vision",
@@ -3413,20 +3401,19 @@
3413
  "hf_private": true
3414
  },
3415
  {
3416
- "name": "openai-responses/gpt-5.3-chat",
3417
- "type": "vision",
3418
  "input_price_per_1m": 1.75,
3419
  "output_price_per_1m": 14,
3420
  "currency": "USD",
3421
  "capabilities": [
3422
- "vision",
3423
  "reasoning"
3424
  ],
3425
- "context_window": 128000,
3426
  "hf_private": true
3427
  },
3428
  {
3429
- "name": "openai-responses/gpt-5.2",
3430
  "type": "vision",
3431
  "input_price_per_1m": 1.75,
3432
  "output_price_per_1m": 14,
@@ -3435,11 +3422,11 @@
3435
  "vision",
3436
  "reasoning"
3437
  ],
3438
- "context_window": 400000,
3439
  "hf_private": true
3440
  },
3441
  {
3442
- "name": "openai-responses/gpt-5.3-codex",
3443
  "type": "vision",
3444
  "input_price_per_1m": 1.75,
3445
  "output_price_per_1m": 14,
@@ -3448,11 +3435,11 @@
3448
  "vision",
3449
  "reasoning"
3450
  ],
3451
- "context_window": 400000,
3452
  "hf_private": true
3453
  },
3454
  {
3455
- "name": "openai-responses/gpt-5.2-codex",
3456
  "type": "vision",
3457
  "input_price_per_1m": 1.75,
3458
  "output_price_per_1m": 14,
@@ -3465,7 +3452,7 @@
3465
  "hf_private": true
3466
  },
3467
  {
3468
- "name": "openai/gpt-5.2",
3469
  "type": "vision",
3470
  "input_price_per_1m": 1.75,
3471
  "output_price_per_1m": 14,
@@ -3478,7 +3465,7 @@
3478
  "hf_private": true
3479
  },
3480
  {
3481
- "name": "openai/gpt-5.2-chat",
3482
  "type": "vision",
3483
  "input_price_per_1m": 1.75,
3484
  "output_price_per_1m": 14,
@@ -3487,11 +3474,11 @@
3487
  "vision",
3488
  "reasoning"
3489
  ],
3490
- "context_window": 128000,
3491
  "hf_private": true
3492
  },
3493
  {
3494
- "name": "openai/gpt-5.3-chat",
3495
  "type": "vision",
3496
  "input_price_per_1m": 1.75,
3497
  "output_price_per_1m": 14,
@@ -3500,33 +3487,32 @@
3500
  "vision",
3501
  "reasoning"
3502
  ],
3503
- "context_window": 128000,
3504
  "hf_private": true
3505
  },
3506
  {
3507
- "name": "google/gemini-3-pro-preview",
3508
  "type": "vision",
3509
- "input_price_per_1m": 2,
3510
- "output_price_per_1m": 12,
3511
  "currency": "USD",
3512
  "capabilities": [
3513
  "vision",
3514
  "reasoning"
3515
  ],
3516
- "context_window": 1048576,
3517
  "hf_private": true
3518
  },
3519
  {
3520
- "name": "google/gemini-3.1-pro-preview",
3521
  "type": "vision",
3522
  "input_price_per_1m": 2,
3523
- "output_price_per_1m": 12,
3524
  "currency": "USD",
3525
  "capabilities": [
3526
- "vision",
3527
- "reasoning"
3528
  ],
3529
- "context_window": 1048576,
3530
  "hf_private": true
3531
  },
3532
  {
@@ -3542,36 +3528,51 @@
3542
  "hf_private": true
3543
  },
3544
  {
3545
- "name": "azure/openai-responses/gpt-4.1",
3546
  "type": "vision",
3547
  "input_price_per_1m": 2,
3548
- "output_price_per_1m": 8,
3549
  "currency": "USD",
3550
  "capabilities": [
3551
- "vision"
 
3552
  ],
3553
- "context_window": 1047576,
3554
  "hf_private": true
3555
  },
3556
  {
3557
- "name": "nebius/deepseek-ai/DeepSeek-V3-0324-fast",
3558
  "type": "chat",
3559
  "input_price_per_1m": 2,
3560
- "output_price_per_1m": 6,
3561
  "currency": "USD",
3562
- "context_window": 128000,
 
 
 
 
 
 
 
 
 
 
 
 
 
3563
  "hf_private": true
3564
  },
3565
  {
3566
- "name": "openai-responses/gpt-4.1",
3567
  "type": "vision",
3568
  "input_price_per_1m": 2,
3569
- "output_price_per_1m": 8,
3570
  "currency": "USD",
3571
  "capabilities": [
3572
- "vision"
 
3573
  ],
3574
- "context_window": 1047576,
3575
  "hf_private": true
3576
  },
3577
  {
@@ -3600,34 +3601,42 @@
3600
  "hf_private": true
3601
  },
3602
  {
3603
- "name": "xai/grok-2-1212",
3604
- "type": "chat",
3605
  "input_price_per_1m": 2,
3606
- "output_price_per_1m": 10,
3607
  "currency": "USD",
3608
- "context_window": 131072,
 
 
 
 
3609
  "hf_private": true
3610
  },
3611
  {
3612
- "name": "xai/grok-4.2-beta",
3613
  "type": "vision",
3614
  "input_price_per_1m": 2,
3615
- "output_price_per_1m": 6,
3616
  "currency": "USD",
3617
  "capabilities": [
3618
  "vision",
3619
  "reasoning"
3620
  ],
3621
- "context_window": 2000000,
3622
  "hf_private": true
3623
  },
3624
  {
3625
- "name": "mistral/pixtral-large-latest",
3626
- "type": "chat",
3627
  "input_price_per_1m": 2,
3628
- "output_price_per_1m": 5,
3629
  "currency": "USD",
3630
- "context_window": 131072,
 
 
 
 
3631
  "hf_private": true
3632
  },
3633
  {
@@ -3644,42 +3653,33 @@
3644
  "hf_private": true
3645
  },
3646
  {
3647
- "name": "vertex/gemini-3-pro-preview",
3648
- "type": "vision",
3649
  "input_price_per_1m": 2,
3650
- "output_price_per_1m": 12,
3651
  "currency": "USD",
3652
- "capabilities": [
3653
- "vision",
3654
- "reasoning"
3655
- ],
3656
- "context_window": 1048576,
3657
  "hf_private": true
3658
  },
3659
  {
3660
- "name": "vertex/gemini-3.1-pro-preview",
3661
  "type": "vision",
3662
  "input_price_per_1m": 2,
3663
- "output_price_per_1m": 12,
3664
  "currency": "USD",
3665
  "capabilities": [
3666
- "vision",
3667
- "reasoning"
3668
  ],
3669
- "context_window": 1048576,
3670
  "hf_private": true
3671
  },
3672
  {
3673
- "name": "vertex/gemini-3-pro-image-preview",
3674
- "type": "vision",
3675
  "input_price_per_1m": 2,
3676
- "output_price_per_1m": 12,
3677
  "currency": "USD",
3678
- "capabilities": [
3679
- "vision",
3680
- "reasoning"
3681
- ],
3682
- "context_window": 1048576,
3683
  "hf_private": true
3684
  },
3685
  {
@@ -3696,20 +3696,19 @@
3696
  "hf_private": true
3697
  },
3698
  {
3699
- "name": "openai-responses/gpt-5.4",
3700
  "type": "vision",
3701
  "input_price_per_1m": 2.5,
3702
- "output_price_per_1m": 15,
3703
  "currency": "USD",
3704
  "capabilities": [
3705
- "vision",
3706
- "reasoning"
3707
  ],
3708
- "context_window": 1050000,
3709
  "hf_private": true
3710
  },
3711
  {
3712
- "name": "openai/gpt-4o-2024-05-13",
3713
  "type": "vision",
3714
  "input_price_per_1m": 2.5,
3715
  "output_price_per_1m": 10,
@@ -3721,7 +3720,7 @@
3721
  "hf_private": true
3722
  },
3723
  {
3724
- "name": "openai/gpt-4o",
3725
  "type": "vision",
3726
  "input_price_per_1m": 2.5,
3727
  "output_price_per_1m": 10,
@@ -3746,7 +3745,7 @@
3746
  "hf_private": true
3747
  },
3748
  {
3749
- "name": "openai/gpt-4o-2024-11-20",
3750
  "type": "vision",
3751
  "input_price_per_1m": 2.5,
3752
  "output_price_per_1m": 10,
@@ -3758,32 +3757,32 @@
3758
  "hf_private": true
3759
  },
3760
  {
3761
- "name": "openai/gpt-4o-2024-08-06",
3762
  "type": "vision",
3763
  "input_price_per_1m": 2.5,
3764
- "output_price_per_1m": 10,
3765
  "currency": "USD",
3766
  "capabilities": [
3767
- "vision"
 
3768
  ],
3769
- "context_window": 128000,
3770
  "hf_private": true
3771
  },
3772
  {
3773
- "name": "bedrock/claude-3-7-sonnet",
3774
  "type": "vision",
3775
  "input_price_per_1m": 3,
3776
  "output_price_per_1m": 15,
3777
  "currency": "USD",
3778
  "capabilities": [
3779
- "vision",
3780
- "reasoning"
3781
  ],
3782
- "context_window": 200000,
3783
  "hf_private": true
3784
  },
3785
  {
3786
- "name": "bedrock/claude-sonnet-4",
3787
  "type": "vision",
3788
  "input_price_per_1m": 3,
3789
  "output_price_per_1m": 15,
@@ -3809,7 +3808,7 @@
3809
  "hf_private": true
3810
  },
3811
  {
3812
- "name": "bedrock/claude-sonnet-4-5",
3813
  "type": "vision",
3814
  "input_price_per_1m": 3,
3815
  "output_price_per_1m": 15,
@@ -3822,19 +3821,20 @@
3822
  "hf_private": true
3823
  },
3824
  {
3825
- "name": "xai/grok-4",
3826
  "type": "vision",
3827
  "input_price_per_1m": 3,
3828
  "output_price_per_1m": 15,
3829
  "currency": "USD",
3830
  "capabilities": [
3831
- "vision"
 
3832
  ],
3833
- "context_window": 256000,
3834
  "hf_private": true
3835
  },
3836
  {
3837
- "name": "coding/claude-sonnet-4-20250514",
3838
  "type": "vision",
3839
  "input_price_per_1m": 3,
3840
  "output_price_per_1m": 15,
@@ -3846,34 +3846,6 @@
3846
  "context_window": 200000,
3847
  "hf_private": true
3848
  },
3849
- {
3850
- "name": "together/deepseek-ai/DeepSeek-R1",
3851
- "type": "chat",
3852
- "input_price_per_1m": 3,
3853
- "output_price_per_1m": 7,
3854
- "currency": "USD",
3855
- "context_window": 64000,
3856
- "capabilities": [
3857
- "tools",
3858
- "reasoning"
3859
- ],
3860
- "hf_id": "deepseek-ai/DeepSeek-R1",
3861
- "size_b": 671,
3862
- "size_source": "manual",
3863
- "hf_private": false
3864
- },
3865
- {
3866
- "name": "perplexity/sonar-pro",
3867
- "type": "chat",
3868
- "input_price_per_1m": 3,
3869
- "output_price_per_1m": 15,
3870
- "currency": "USD",
3871
- "context_window": 204800,
3872
- "capabilities": [
3873
- "vision"
3874
- ],
3875
- "hf_private": true
3876
- },
3877
  {
3878
  "name": "anthropic/claude-sonnet-4-5",
3879
  "type": "vision",
@@ -3913,6 +3885,22 @@
3913
  "context_window": 1000000,
3914
  "hf_private": true
3915
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3916
  {
3917
  "name": "vertex/claude-3-5-sonnet",
3918
  "type": "vision",
@@ -3926,7 +3914,7 @@
3926
  "hf_private": true
3927
  },
3928
  {
3929
- "name": "vertex/claude-3-7-sonnet",
3930
  "type": "vision",
3931
  "input_price_per_1m": 3,
3932
  "output_price_per_1m": 15,
@@ -3952,7 +3940,7 @@
3952
  "hf_private": true
3953
  },
3954
  {
3955
- "name": "vertex/claude-sonnet-4-5",
3956
  "type": "vision",
3957
  "input_price_per_1m": 3,
3958
  "output_price_per_1m": 15,
@@ -3964,6 +3952,18 @@
3964
  "context_window": 200000,
3965
  "hf_private": true
3966
  },
 
 
 
 
 
 
 
 
 
 
 
 
3967
  {
3968
  "name": "novita/deepseek/deepseek-r1",
3969
  "type": "chat",
@@ -3981,16 +3981,15 @@
3981
  "hf_private": false
3982
  },
3983
  {
3984
- "name": "bedrock/claude-opus-4-5",
3985
- "type": "vision",
3986
  "input_price_per_1m": 5,
3987
  "output_price_per_1m": 25,
3988
  "currency": "USD",
 
3989
  "capabilities": [
3990
- "vision",
3991
- "reasoning"
3992
  ],
3993
- "context_window": 200000,
3994
  "hf_private": true
3995
  },
3996
  {
@@ -4007,27 +4006,16 @@
4007
  "hf_private": true
4008
  },
4009
  {
4010
- "name": "openai/chatgpt-4o",
4011
  "type": "vision",
4012
  "input_price_per_1m": 5,
4013
- "output_price_per_1m": 15,
4014
- "currency": "USD",
4015
- "capabilities": [
4016
- "vision"
4017
- ],
4018
- "context_window": 128000,
4019
- "hf_private": true
4020
- },
4021
- {
4022
- "name": "xai/grok-3",
4023
- "type": "chat",
4024
- "input_price_per_1m": 5,
4025
  "output_price_per_1m": 25,
4026
  "currency": "USD",
4027
- "context_window": 131072,
4028
  "capabilities": [
4029
- "tools"
 
4030
  ],
 
4031
  "hf_private": true
4032
  },
4033
  {
@@ -4057,7 +4045,19 @@
4057
  "hf_private": true
4058
  },
4059
  {
4060
- "name": "vertex/claude-opus-4-6",
 
 
 
 
 
 
 
 
 
 
 
 
4061
  "type": "vision",
4062
  "input_price_per_1m": 5,
4063
  "output_price_per_1m": 25,
@@ -4066,11 +4066,11 @@
4066
  "vision",
4067
  "reasoning"
4068
  ],
4069
- "context_window": 1000000,
4070
  "hf_private": true
4071
  },
4072
  {
4073
- "name": "vertex/claude-opus-4-5",
4074
  "type": "vision",
4075
  "input_price_per_1m": 5,
4076
  "output_price_per_1m": 25,
@@ -4079,7 +4079,7 @@
4079
  "vision",
4080
  "reasoning"
4081
  ],
4082
- "context_window": 200000,
4083
  "hf_private": true
4084
  },
4085
  {
@@ -4096,7 +4096,7 @@
4096
  "hf_private": true
4097
  },
4098
  {
4099
- "name": "bedrock/claude-opus-4",
4100
  "type": "vision",
4101
  "input_price_per_1m": 15,
4102
  "output_price_per_1m": 75,
@@ -4109,23 +4109,23 @@
4109
  "hf_private": true
4110
  },
4111
  {
4112
- "name": "openai-responses/gpt-5-pro",
4113
  "type": "vision",
4114
  "input_price_per_1m": 15,
4115
- "output_price_per_1m": 120,
4116
  "currency": "USD",
4117
  "capabilities": [
4118
  "vision",
4119
  "reasoning"
4120
  ],
4121
- "context_window": 400000,
4122
  "hf_private": true
4123
  },
4124
  {
4125
- "name": "openai/o1",
4126
  "type": "vision",
4127
  "input_price_per_1m": 15,
4128
- "output_price_per_1m": 60,
4129
  "currency": "USD",
4130
  "capabilities": [
4131
  "vision",
@@ -4135,7 +4135,7 @@
4135
  "hf_private": true
4136
  },
4137
  {
4138
- "name": "coding/claude-opus-4-20250514",
4139
  "type": "vision",
4140
  "input_price_per_1m": 15,
4141
  "output_price_per_1m": 75,
@@ -4148,10 +4148,10 @@
4148
  "hf_private": true
4149
  },
4150
  {
4151
- "name": "anthropic/claude-opus-4-1",
4152
  "type": "vision",
4153
  "input_price_per_1m": 15,
4154
- "output_price_per_1m": 75,
4155
  "currency": "USD",
4156
  "capabilities": [
4157
  "vision",
@@ -4161,7 +4161,7 @@
4161
  "hf_private": true
4162
  },
4163
  {
4164
- "name": "anthropic/claude-opus-4",
4165
  "type": "vision",
4166
  "input_price_per_1m": 15,
4167
  "output_price_per_1m": 75,
@@ -4174,7 +4174,7 @@
4174
  "hf_private": true
4175
  },
4176
  {
4177
- "name": "vertex/claude-opus-4",
4178
  "type": "vision",
4179
  "input_price_per_1m": 15,
4180
  "output_price_per_1m": 75,
@@ -4187,16 +4187,16 @@
4187
  "hf_private": true
4188
  },
4189
  {
4190
- "name": "vertex/claude-opus-4-1",
4191
  "type": "vision",
4192
  "input_price_per_1m": 15,
4193
- "output_price_per_1m": 75,
4194
  "currency": "USD",
4195
  "capabilities": [
4196
  "vision",
4197
  "reasoning"
4198
  ],
4199
- "context_window": 200000,
4200
  "hf_private": true
4201
  },
4202
  {
@@ -4226,7 +4226,7 @@
4226
  "hf_private": true
4227
  },
4228
  {
4229
- "name": "openai-responses/gpt-5.4-pro",
4230
  "type": "vision",
4231
  "input_price_per_1m": 30,
4232
  "output_price_per_1m": 180,
@@ -4239,7 +4239,7 @@
4239
  "hf_private": true
4240
  },
4241
  {
4242
- "name": "openai/gpt-5.4-pro",
4243
  "type": "vision",
4244
  "input_price_per_1m": 30,
4245
  "output_price_per_1m": 180,
 
1092
  "eu_endpoints": true,
1093
  "models": [
1094
  {
1095
+ "name": "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
1096
  "type": "chat",
1097
  "input_price_per_1m": 0.02,
1098
+ "output_price_per_1m": 0.05,
1099
  "currency": "USD",
1100
+ "context_window": 131072,
1101
+ "size_b": 8,
 
1102
  "hf_private": false
1103
  },
1104
  {
1105
+ "name": "novita/meta-llama/llama-3.2-1b-instruct",
1106
  "type": "chat",
1107
  "input_price_per_1m": 0.02,
1108
+ "output_price_per_1m": 0.02,
1109
  "currency": "USD",
1110
+ "context_window": 131000,
1111
+ "size_b": 1,
1112
+ "hf_id": "meta-llama/Llama-3.2-1B-Instruct",
1113
  "hf_private": false
1114
  },
1115
  {
 
1163
  "hf_private": true
1164
  },
1165
  {
1166
+ "name": "alibaba/qwen-turbo",
1167
  "type": "chat",
1168
  "input_price_per_1m": 0.05,
1169
+ "output_price_per_1m": 0.2,
1170
  "currency": "USD",
1171
+ "context_window": 1000000,
1172
+ "capabilities": [
1173
+ "tools"
1174
+ ],
1175
+ "hf_private": true
1176
+ },
1177
+ {
1178
+ "name": "openai-responses/gpt-5-nano",
1179
+ "type": "vision",
1180
+ "input_price_per_1m": 0.05,
1181
+ "output_price_per_1m": 0.4,
1182
+ "currency": "USD",
1183
+ "capabilities": [
1184
+ "vision",
1185
+ "reasoning"
1186
+ ],
1187
+ "context_window": 400000,
1188
+ "hf_private": true
1189
  },
1190
  {
1191
  "name": "novita/meta-llama/llama-3.1-8b-instruct",
 
1202
  "hf_private": false
1203
  },
1204
  {
1205
+ "name": "novita/sao10k/l3-8b-lunaris",
1206
  "type": "chat",
1207
  "input_price_per_1m": 0.05,
1208
  "output_price_per_1m": 0.05,
 
1212
  "hf_private": false
1213
  },
1214
  {
1215
+ "name": "novita/Sao10K/L3-8B-Stheno-v3.2",
 
 
 
 
 
 
 
 
 
 
 
 
 
1216
  "type": "chat",
1217
  "input_price_per_1m": 0.05,
1218
+ "output_price_per_1m": 0.05,
1219
  "currency": "USD",
1220
+ "context_window": 8192,
1221
+ "size_b": 8,
1222
+ "hf_private": false
 
 
1223
  },
1224
  {
1225
  "name": "together/meta-llama/Llama-3.2-3B-Instruct-Turbo",
 
1232
  "hf_private": false
1233
  },
1234
  {
1235
+ "name": "deepinfra/Qwen/Qwen2.5-Coder-32B-Instruct",
1236
  "type": "chat",
1237
  "input_price_per_1m": 0.07,
1238
+ "output_price_per_1m": 0.16,
1239
  "currency": "USD",
1240
  "context_window": 16384,
1241
+ "size_b": 32,
1242
+ "hf_private": false
 
 
1243
  },
1244
  {
1245
+ "name": "deepinfra/microsoft/phi-4",
1246
  "type": "chat",
1247
  "input_price_per_1m": 0.07,
1248
+ "output_price_per_1m": 0.14,
1249
  "currency": "USD",
1250
  "context_window": 16384,
1251
+ "hf_private": false,
1252
+ "size_b": 14,
1253
+ "size_source": "manual",
1254
+ "hf_id": "microsoft/phi-4"
1255
  },
1256
  {
1257
  "name": "novita/gryphe/mythomax-l2-13b",
 
1265
  "hf_private": false
1266
  },
1267
  {
1268
+ "name": "azure/gpt-4.1-nano",
1269
  "type": "vision",
1270
  "input_price_per_1m": 0.1,
1271
  "output_price_per_1m": 0.4,
1272
  "currency": "USD",
1273
  "capabilities": [
1274
+ "vision"
 
1275
  ],
1276
+ "context_window": 1047576,
1277
  "hf_private": true
1278
  },
1279
  {
1280
+ "name": "azure/openai-responses/gpt-4.1-nano",
1281
  "type": "vision",
1282
  "input_price_per_1m": 0.1,
1283
  "output_price_per_1m": 0.4,
 
1285
  "capabilities": [
1286
  "vision"
1287
  ],
1288
+ "context_window": 1047576,
1289
  "hf_private": true
1290
  },
1291
  {
1292
+ "name": "google/gemini-2.5-flash-lite",
1293
  "type": "vision",
1294
  "input_price_per_1m": 0.1,
1295
  "output_price_per_1m": 0.4,
1296
  "currency": "USD",
1297
  "capabilities": [
1298
+ "vision",
1299
+ "reasoning"
1300
  ],
1301
+ "context_window": 1048576,
1302
  "hf_private": true
1303
  },
1304
  {
1305
+ "name": "google/gemini-2.0-flash-001",
1306
  "type": "vision",
1307
  "input_price_per_1m": 0.1,
1308
  "output_price_per_1m": 0.4,
 
1310
  "capabilities": [
1311
  "vision"
1312
  ],
1313
+ "context_window": 1048576,
1314
  "hf_private": true
1315
  },
1316
  {
1317
+ "name": "openai/gpt-4.1-nano",
1318
  "type": "vision",
1319
  "input_price_per_1m": 0.1,
1320
  "output_price_per_1m": 0.4,
 
1326
  "hf_private": true
1327
  },
1328
  {
1329
+ "name": "together/meta-llama/Meta-Llama-3-8B-Instruct-Lite",
1330
+ "type": "chat",
1331
+ "input_price_per_1m": 0.1,
1332
+ "output_price_per_1m": 0.1,
1333
+ "currency": "USD",
1334
+ "context_window": 8192,
1335
+ "size_b": 8,
1336
+ "hf_private": false
1337
+ },
1338
+ {
1339
+ "name": "vertex/gemini-2.5-flash-lite",
1340
  "type": "vision",
1341
  "input_price_per_1m": 0.1,
1342
  "output_price_per_1m": 0.4,
1343
  "currency": "USD",
1344
  "capabilities": [
1345
+ "vision",
1346
+ "reasoning"
1347
  ],
1348
+ "context_window": 1048576,
1349
  "hf_private": true
1350
  },
1351
  {
1352
+ "name": "deepinfra/Qwen/Qwen3-32B",
1353
  "type": "chat",
1354
  "input_price_per_1m": 0.1,
1355
  "output_price_per_1m": 0.3,
1356
  "currency": "USD",
1357
+ "context_window": 40000,
1358
+ "size_b": 32,
1359
+ "capabilities": [
1360
+ "tools",
1361
+ "reasoning"
1362
+ ],
1363
+ "hf_id": "Qwen/Qwen3-32B",
1364
+ "hf_private": false
1365
  },
1366
  {
1367
+ "name": "groq/openai/gpt-oss-20b",
1368
  "type": "chat",
1369
  "input_price_per_1m": 0.1,
1370
+ "output_price_per_1m": 0.5,
1371
  "currency": "USD",
1372
  "context_window": 131072,
1373
+ "size_b": 20,
1374
  "capabilities": [
1375
+ "tools",
1376
+ "reasoning"
1377
  ],
1378
+ "hf_id": "openai/gpt-oss-20b",
 
1379
  "hf_private": false
1380
  },
1381
  {
1382
+ "name": "mistral/mistral-small-2503",
1383
+ "type": "chat",
1384
+ "input_price_per_1m": 0.1,
1385
+ "output_price_per_1m": 0.3,
1386
+ "currency": "USD",
1387
+ "context_window": 32768,
1388
+ "hf_private": true
1389
+ },
1390
+ {
1391
+ "name": "mistral/devstral-small-2507",
1392
  "type": "chat",
1393
  "input_price_per_1m": 0.1,
1394
  "output_price_per_1m": 0.3,
 
1402
  "hf_private": false
1403
  },
1404
  {
1405
+ "name": "mistral/devstral-small-latest",
 
 
 
 
 
 
 
 
 
 
1406
  "type": "chat",
1407
  "input_price_per_1m": 0.1,
1408
+ "output_price_per_1m": 0.3,
1409
  "currency": "USD",
1410
  "context_window": 131072,
 
1411
  "capabilities": [
1412
+ "tools"
 
1413
  ],
1414
+ "hf_id": "mistralai/Devstral-Small-2507",
1415
+ "size_b": 24,
1416
  "hf_private": false
1417
  },
1418
  {
1419
+ "name": "openai-responses/gpt-4.1-nano",
1420
  "type": "vision",
1421
  "input_price_per_1m": 0.1,
1422
  "output_price_per_1m": 0.4,
1423
  "currency": "USD",
1424
  "capabilities": [
1425
+ "vision"
 
1426
  ],
1427
+ "context_window": 1047576,
1428
  "hf_private": true
1429
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1430
  {
1431
  "name": "deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo",
1432
  "type": "chat",
 
1480
  "hf_private": false
1481
  },
1482
  {
1483
+ "name": "parasail/parasail-qwen3-235b-a22b-instruct-2507",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1484
  "type": "chat",
1485
  "input_price_per_1m": 0.15,
1486
+ "output_price_per_1m": 0.85,
1487
  "currency": "USD",
1488
+ "context_window": 262144,
1489
+ "size_b": 235,
 
 
 
 
 
 
1490
  "hf_private": false
1491
  },
1492
  {
 
1501
  "context_window": 128000,
1502
  "hf_private": true
1503
  },
1504
+ {
1505
+ "name": "groq/openai/gpt-oss-120b",
1506
+ "type": "chat",
1507
+ "input_price_per_1m": 0.15,
1508
+ "output_price_per_1m": 0.75,
1509
+ "currency": "USD",
1510
+ "context_window": 131072,
1511
+ "size_b": 120,
1512
+ "capabilities": [
1513
+ "tools",
1514
+ "reasoning"
1515
+ ],
1516
+ "hf_id": "openai/gpt-oss-120b",
1517
+ "hf_private": false
1518
+ },
1519
  {
1520
  "name": "mistral/mistral-small-latest",
1521
  "type": "vision",
 
1545
  "hf_private": false
1546
  },
1547
  {
1548
+ "name": "nebius/openai/gpt-oss-120b",
1549
  "type": "chat",
1550
  "input_price_per_1m": 0.15,
1551
+ "output_price_per_1m": 0.6,
1552
  "currency": "USD",
 
 
1553
  "capabilities": [
 
1554
  "reasoning"
1555
  ],
1556
+ "context_window": 131000,
1557
+ "size_b": 120,
1558
  "hf_id": "openai/gpt-oss-120b",
1559
  "hf_private": false
1560
  },
1561
  {
1562
+ "name": "novita/deepseek/deepseek-r1-distill-qwen-14b",
1563
  "type": "chat",
1564
  "input_price_per_1m": 0.15,
1565
+ "output_price_per_1m": 0.15,
1566
  "currency": "USD",
1567
+ "context_window": 128000,
1568
+ "size_b": 14,
1569
+ "capabilities": [
1570
+ "tools",
1571
+ "reasoning"
1572
+ ],
1573
+ "hf_id": "deepseek-ai/DeepSeek-R1",
1574
+ "size_source": "manual",
1575
  "hf_private": false
1576
  },
1577
  {
 
1599
  "hf_private": false
1600
  },
1601
  {
1602
+ "name": "xai/grok-code-fast-1",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1603
  "type": "vision",
1604
  "input_price_per_1m": 0.2,
1605
+ "output_price_per_1m": 1.5,
1606
  "currency": "USD",
1607
  "capabilities": [
1608
+ "vision"
 
1609
  ],
1610
+ "context_window": 256000,
1611
  "hf_private": true
1612
  },
1613
  {
1614
+ "name": "xai/grok-4-1-fast-reasoning",
1615
  "type": "vision",
1616
  "input_price_per_1m": 0.2,
1617
+ "output_price_per_1m": 0.5,
1618
  "currency": "USD",
1619
  "capabilities": [
1620
  "vision"
1621
  ],
1622
+ "context_window": 2000000,
1623
  "hf_private": true
1624
  },
1625
  {
1626
+ "name": "xai/grok-4-fast-non-reasoning",
1627
  "type": "chat",
1628
  "input_price_per_1m": 0.2,
1629
  "output_price_per_1m": 0.5,
 
1637
  "hf_private": true
1638
  },
1639
  {
1640
+ "name": "xai/grok-4-1-fast-non-reasoning",
1641
  "type": "vision",
1642
  "input_price_per_1m": 0.2,
1643
  "output_price_per_1m": 0.5,
 
1649
  "hf_private": true
1650
  },
1651
  {
1652
+ "name": "xai/grok-4-fast",
1653
  "type": "chat",
1654
  "input_price_per_1m": 0.2,
1655
  "output_price_per_1m": 0.5,
 
1663
  "hf_private": true
1664
  },
1665
  {
1666
+ "name": "alibaba/qwen3-30b-a3b-instruct-2507",
1667
  "type": "vision",
1668
  "input_price_per_1m": 0.2,
1669
+ "output_price_per_1m": 0.8,
1670
  "currency": "USD",
1671
  "capabilities": [
1672
  "vision"
1673
  ],
1674
+ "context_window": 131072,
1675
+ "size_b": 30,
1676
+ "hf_id": "Qwen/Qwen3-30B-A3B-Instruct-2507",
1677
+ "hf_private": false
1678
+ },
1679
+ {
1680
+ "name": "openai/gpt-5.4-nano",
1681
+ "type": "vision",
1682
+ "input_price_per_1m": 0.2,
1683
+ "output_price_per_1m": 1.25,
1684
+ "currency": "USD",
1685
+ "capabilities": [
1686
+ "vision",
1687
+ "reasoning"
1688
+ ],
1689
+ "context_window": 400000,
1690
  "hf_private": true
1691
  },
1692
  {
 
1699
  "size_b": 8,
1700
  "hf_private": false
1701
  },
1702
+ {
1703
+ "name": "deepinfra/Qwen/Qwen3-235B-A22B",
1704
+ "type": "chat",
1705
+ "input_price_per_1m": 0.2,
1706
+ "output_price_per_1m": 0.6,
1707
+ "currency": "USD",
1708
+ "context_window": 40000,
1709
+ "size_b": 235,
1710
+ "capabilities": [
1711
+ "tools",
1712
+ "reasoning"
1713
+ ],
1714
+ "hf_id": "Qwen/Qwen3-235B-A22B",
1715
+ "hf_private": false
1716
+ },
1717
  {
1718
  "name": "deepinfra/zai-org/GLM-4.5-Air",
1719
  "type": "chat",
 
1730
  "hf_private": false
1731
  },
1732
  {
1733
+ "name": "openai-responses/gpt-5.4-nano",
1734
+ "type": "vision",
1735
+ "input_price_per_1m": 0.2,
1736
+ "output_price_per_1m": 1.25,
1737
+ "currency": "USD",
1738
+ "capabilities": [
1739
+ "vision",
1740
+ "reasoning"
1741
+ ],
1742
+ "context_window": 400000,
1743
+ "hf_private": true
1744
+ },
1745
+ {
1746
+ "name": "novita/qwen/qwen3-235b-a22b-fp8",
1747
  "type": "chat",
1748
  "input_price_per_1m": 0.2,
1749
+ "output_price_per_1m": 0.8,
1750
  "currency": "USD",
1751
+ "context_window": 128000,
1752
  "size_b": 235,
1753
  "capabilities": [
1754
  "tools",
 
1758
  "hf_private": false
1759
  },
1760
  {
1761
+ "name": "novita/meta-llama/llama-4-maverick-17b-128e-instruct-fp8",
1762
+ "type": "chat",
1763
  "input_price_per_1m": 0.2,
1764
+ "output_price_per_1m": 0.85,
1765
  "currency": "USD",
1766
+ "context_window": 1048576,
1767
+ "size_b": 17,
1768
  "capabilities": [
1769
+ "vision",
1770
+ "tools"
1771
  ],
1772
+ "hf_id": "meta-llama/Llama-4-Maverick-17B-128E-Instruct",
 
 
1773
  "hf_private": false
1774
  },
1775
  {
1776
+ "name": "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct",
1777
  "type": "chat",
1778
  "input_price_per_1m": 0.23,
1779
  "output_price_per_1m": 0.4,
1780
  "currency": "USD",
1781
+ "context_window": 130815,
1782
+ "size_b": 70,
 
 
 
 
1783
  "hf_private": false
1784
  },
1785
  {
1786
+ "name": "deepinfra/Qwen/Qwen2.5-72B-Instruct",
1787
  "type": "chat",
1788
  "input_price_per_1m": 0.23,
1789
  "output_price_per_1m": 0.4,
1790
  "currency": "USD",
1791
  "context_window": 131072,
1792
+ "size_b": 72,
1793
  "capabilities": [
1794
+ "vision"
1795
  ],
1796
+ "hf_id": "Qwen/Qwen2.5-VL-72B-Instruct",
1797
  "hf_private": false
1798
  },
1799
  {
 
1811
  "hf_private": false
1812
  },
1813
  {
1814
+ "name": "deepinfra/meta-llama/Llama-3.3-70B-Instruct",
1815
  "type": "chat",
1816
  "input_price_per_1m": 0.23,
1817
  "output_price_per_1m": 0.4,
1818
  "currency": "USD",
1819
+ "context_window": 131072,
1820
  "size_b": 70,
1821
+ "capabilities": [
1822
+ "tools"
1823
+ ],
1824
+ "hf_id": "meta-llama/Llama-3.3-70B-Instruct",
1825
  "hf_private": false
1826
  },
1827
  {
1828
+ "name": "azure/gpt-5-mini",
1829
+ "type": "chat",
1830
  "input_price_per_1m": 0.25,
1831
+ "output_price_per_1m": 2,
1832
  "currency": "USD",
1833
  "capabilities": [
1834
+ "reasoning"
1835
  ],
1836
+ "context_window": 200000,
1837
  "hf_private": true
1838
  },
1839
  {
1840
+ "name": "google/gemini-3.1-flash-lite-preview",
1841
+ "type": "vision",
1842
  "input_price_per_1m": 0.25,
1843
+ "output_price_per_1m": 1.5,
1844
  "currency": "USD",
1845
  "capabilities": [
1846
+ "vision"
1847
  ],
1848
+ "context_window": 1048576,
1849
  "hf_private": true
1850
  },
1851
  {
1852
+ "name": "vertex/gemini-3.1-flash-lite-preview",
1853
  "type": "vision",
1854
  "input_price_per_1m": 0.25,
1855
+ "output_price_per_1m": 1.5,
1856
  "currency": "USD",
1857
  "capabilities": [
1858
+ "vision"
 
1859
  ],
1860
+ "context_window": 1048576,
1861
  "hf_private": true
1862
  },
1863
  {
 
1871
  "hf_private": false
1872
  },
1873
  {
1874
+ "name": "openai-responses/gpt-5-mini",
1875
  "type": "vision",
1876
  "input_price_per_1m": 0.25,
1877
+ "output_price_per_1m": 2,
1878
  "currency": "USD",
1879
  "capabilities": [
1880
+ "vision",
1881
+ "reasoning"
1882
  ],
1883
+ "context_window": 400000,
1884
  "hf_private": true
1885
  },
1886
  {
 
1922
  "hf_private": true
1923
  },
1924
  {
1925
+ "name": "xai/grok-3-mini",
1926
+ "type": "chat",
1927
+ "input_price_per_1m": 0.3,
1928
+ "output_price_per_1m": 0.5,
1929
+ "currency": "USD",
1930
+ "capabilities": [
1931
+ "reasoning"
1932
+ ],
1933
+ "context_window": 131072,
1934
+ "hf_private": true
1935
+ },
1936
+ {
1937
+ "name": "coding/gemini-2.5-flash",
1938
  "type": "vision",
1939
  "input_price_per_1m": 0.3,
1940
  "output_price_per_1m": 2.5,
 
1947
  "hf_private": true
1948
  },
1949
  {
1950
+ "name": "parasail/parasail-gemma3-27b-it",
1951
  "type": "chat",
1952
  "input_price_per_1m": 0.3,
1953
+ "output_price_per_1m": 0.5,
1954
  "currency": "USD",
1955
+ "context_window": 128000,
1956
+ "size_b": 27,
 
 
 
 
1957
  "hf_private": false
1958
  },
1959
  {
1960
+ "name": "alibaba/qwen3-coder-flash",
1961
+ "type": "vision",
1962
  "input_price_per_1m": 0.3,
1963
+ "output_price_per_1m": 1.5,
1964
  "currency": "USD",
1965
  "capabilities": [
1966
+ "vision"
1967
  ],
1968
+ "context_window": 1048576,
1969
+ "hf_private": true
 
 
1970
  },
1971
  {
1972
+ "name": "google/gemini-2.5-flash",
1973
+ "type": "vision",
1974
  "input_price_per_1m": 0.3,
1975
+ "output_price_per_1m": 2.5,
1976
  "currency": "USD",
 
 
1977
  "capabilities": [
1978
+ "vision",
1979
  "reasoning"
1980
  ],
1981
+ "context_window": 1048576,
1982
+ "hf_private": true
1983
  },
1984
  {
1985
+ "name": "together/Qwen/Qwen2.5-7B-Instruct-Turbo",
1986
+ "type": "chat",
1987
  "input_price_per_1m": 0.3,
1988
+ "output_price_per_1m": 0.3,
1989
  "currency": "USD",
1990
+ "context_window": 32768,
1991
+ "size_b": 7,
1992
+ "hf_private": false
 
 
 
 
 
 
1993
  },
1994
  {
1995
+ "name": "vertex/gemini-2.5-flash",
1996
  "type": "vision",
1997
  "input_price_per_1m": 0.3,
1998
+ "output_price_per_1m": 2.5,
1999
  "currency": "USD",
2000
  "capabilities": [
2001
  "vision",
2002
  "reasoning"
2003
  ],
2004
+ "context_window": 1048576,
2005
+ "hf_private": true
 
 
 
2006
  },
2007
  {
2008
+ "name": "vertex/gemini-2.5-flash-image",
2009
  "type": "vision",
2010
  "input_price_per_1m": 0.3,
2011
+ "output_price_per_1m": 2.5,
2012
  "currency": "USD",
2013
  "capabilities": [
2014
  "vision",
2015
  "reasoning"
2016
  ],
2017
+ "context_window": 1048576,
2018
+ "hf_private": true
 
 
 
2019
  },
2020
  {
2021
  "name": "minimaxi/MiniMax-M2",
 
2048
  "hf_private": false
2049
  },
2050
  {
2051
+ "name": "minimaxi/MiniMax-M2.7",
2052
+ "type": "vision",
2053
  "input_price_per_1m": 0.3,
2054
+ "output_price_per_1m": 1.2,
2055
  "currency": "USD",
2056
  "capabilities": [
2057
+ "vision",
2058
  "reasoning"
2059
  ],
2060
+ "context_window": 200000,
2061
+ "hf_id": "MiniMaxAI/MiniMax-M2.7",
2062
+ "hf_private": false,
2063
+ "size_b": 230,
2064
+ "size_source": "manual"
2065
  },
2066
  {
2067
+ "name": "deepinfra/deepseek-ai/DeepSeek-V3.1",
2068
+ "type": "chat",
2069
  "input_price_per_1m": 0.3,
2070
+ "output_price_per_1m": 1,
2071
  "currency": "USD",
2072
+ "context_window": 163840,
2073
  "capabilities": [
2074
+ "tools",
2075
  "reasoning"
2076
  ],
2077
+ "hf_id": "deepseek-ai/DeepSeek-V3.1-Terminus",
2078
+ "size_b": 671,
2079
+ "hf_private": false
2080
  },
2081
  {
2082
  "name": "mistral/codestral-latest",
 
2088
  "hf_private": true
2089
  },
2090
  {
2091
+ "name": "nebius/minimax/minimax-m2.1",
2092
  "type": "chat",
2093
  "input_price_per_1m": 0.3,
2094
+ "output_price_per_1m": 1.2,
2095
  "currency": "USD",
2096
+ "capabilities": [
2097
+ "reasoning"
2098
+ ],
2099
+ "context_window": 200000,
2100
+ "hf_id": "MiniMaxAI/MiniMax-M2.1",
2101
+ "size_b": 228.7,
2102
  "hf_private": false
2103
  },
2104
  {
2105
+ "name": "nebius/deepseek-ai/DeepSeek-V3.2",
2106
+ "type": "chat",
2107
  "input_price_per_1m": 0.3,
2108
+ "output_price_per_1m": 0.45,
2109
  "currency": "USD",
2110
  "capabilities": [
 
2111
  "reasoning"
2112
  ],
2113
+ "context_window": 164000,
2114
+ "hf_id": "deepseek-ai/DeepSeek-V3.2",
2115
+ "size_b": 685.4,
2116
+ "hf_private": false
2117
  },
2118
  {
2119
+ "name": "novita/MiniMax-M2.7",
2120
  "type": "vision",
2121
  "input_price_per_1m": 0.3,
2122
+ "output_price_per_1m": 1.2,
2123
  "currency": "USD",
2124
  "capabilities": [
2125
  "vision",
2126
  "reasoning"
2127
  ],
2128
+ "context_window": 200000,
2129
+ "hf_id": "MiniMaxAI/MiniMax-M2.7",
2130
+ "hf_private": false,
2131
+ "size_b": 230,
2132
+ "size_source": "manual"
2133
  },
2134
  {
2135
+ "name": "novita/minimax-m2.7",
2136
+ "type": "vision",
2137
  "input_price_per_1m": 0.3,
2138
+ "output_price_per_1m": 1.2,
2139
  "currency": "USD",
 
2140
  "capabilities": [
2141
+ "vision",
2142
  "reasoning"
2143
  ],
2144
+ "context_window": 200000,
2145
+ "hf_id": "MiniMaxAI/MiniMax-M2.7",
2146
+ "hf_private": false,
2147
+ "size_b": 230,
2148
+ "size_source": "manual"
2149
  },
2150
  {
2151
+ "name": "novita/deepseek/deepseek-r1-distill-qwen-32b",
2152
  "type": "chat",
2153
  "input_price_per_1m": 0.3,
2154
+ "output_price_per_1m": 0.3,
 
 
 
 
 
 
 
 
 
 
2155
  "currency": "USD",
2156
+ "context_window": 12800,
2157
+ "size_b": 32,
2158
  "capabilities": [
2159
+ "reasoning"
2160
  ],
2161
+ "hf_id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
2162
+ "hf_private": false
2163
  },
2164
  {
2165
  "name": "deepinfra/meta-llama/Llama-3.2-90B-Vision-Instruct",
 
2224
  "hf_private": true
2225
  },
2226
  {
2227
+ "name": "alibaba/qwen-plus",
2228
  "type": "chat",
2229
  "input_price_per_1m": 0.4,
2230
+ "output_price_per_1m": 1.2,
2231
  "currency": "USD",
2232
+ "context_window": 131072,
 
2233
  "capabilities": [
2234
  "tools"
2235
  ],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2236
  "hf_private": true
2237
  },
2238
  {
2239
+ "name": "openai/gpt-4.1-mini",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2240
  "type": "vision",
2241
  "input_price_per_1m": 0.4,
2242
  "output_price_per_1m": 1.6,
 
2248
  "hf_private": true
2249
  },
2250
  {
2251
+ "name": "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct",
2252
+ "type": "chat",
2253
  "input_price_per_1m": 0.4,
2254
  "output_price_per_1m": 1.6,
2255
  "currency": "USD",
2256
+ "context_window": 262144,
2257
+ "size_b": 480,
2258
  "capabilities": [
2259
+ "tools"
2260
  ],
2261
+ "hf_id": "Qwen/Qwen3-Coder-480B-A35B-Instruct",
2262
+ "hf_private": false
2263
  },
2264
  {
2265
  "name": "mistral/mistral-medium-latest",
 
2270
  "context_window": 131072,
2271
  "hf_private": true
2272
  },
 
 
 
 
 
 
 
 
 
2273
  {
2274
  "name": "mistral/devstral-medium-2507",
2275
  "type": "chat",
 
2283
  "hf_private": true
2284
  },
2285
  {
2286
+ "name": "mistral/devstral-latest",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2287
  "type": "chat",
2288
  "input_price_per_1m": 0.4,
 
 
 
 
 
 
 
 
 
 
 
 
2289
  "output_price_per_1m": 2,
2290
  "currency": "USD",
2291
+ "context_window": 256000,
 
 
 
 
2292
  "hf_private": true
2293
  },
2294
  {
2295
+ "name": "openai-responses/gpt-4.1-mini",
2296
  "type": "vision",
2297
+ "input_price_per_1m": 0.4,
2298
+ "output_price_per_1m": 1.6,
2299
  "currency": "USD",
2300
  "capabilities": [
2301
+ "vision"
 
2302
  ],
2303
+ "context_window": 1047576,
2304
  "hf_private": true
2305
  },
2306
  {
2307
+ "name": "nebius/Qwen/Qwen3-Coder-480B-A35B-Instruct",
2308
  "type": "chat",
2309
+ "input_price_per_1m": 0.4,
2310
+ "output_price_per_1m": 1.8,
2311
  "currency": "USD",
2312
+ "context_window": 262000,
2313
+ "size_b": 480,
2314
  "capabilities": [
2315
  "tools"
2316
  ],
2317
+ "hf_id": "Qwen/Qwen3-Coder-480B-A35B-Instruct",
 
2318
  "hf_private": false
2319
  },
2320
  {
2321
+ "name": "nebius/zai-org/GLM-4.7",
2322
+ "type": "chat",
2323
+ "input_price_per_1m": 0.4,
2324
+ "output_price_per_1m": 2,
2325
  "currency": "USD",
2326
  "capabilities": [
 
2327
  "reasoning"
2328
  ],
2329
+ "context_window": 200000,
2330
+ "hf_id": "zai-org/GLM-4.7",
2331
+ "size_b": 358.3,
2332
  "hf_private": false
2333
  },
2334
  {
2335
+ "name": "novita/deepseek/deepseek-v3-0324",
2336
  "type": "chat",
2337
+ "input_price_per_1m": 0.4,
2338
+ "output_price_per_1m": 1.3,
2339
  "currency": "USD",
2340
  "context_window": 128000,
2341
  "capabilities": [
 
2347
  "hf_private": false
2348
  },
2349
  {
2350
+ "name": "novita/deepseek/deepseek-v3-turbo",
2351
  "type": "chat",
2352
+ "input_price_per_1m": 0.4,
2353
+ "output_price_per_1m": 1.3,
2354
  "currency": "USD",
2355
+ "context_window": 128000,
 
 
 
2356
  "hf_private": true
2357
  },
2358
  {
2359
+ "name": "google/gemini-3.1-flash-image-preview",
2360
  "type": "vision",
2361
  "input_price_per_1m": 0.5,
2362
  "output_price_per_1m": 2,
 
2369
  "hf_private": true
2370
  },
2371
  {
2372
+ "name": "google/gemini-3-flash-preview",
2373
  "type": "vision",
2374
  "input_price_per_1m": 0.5,
2375
  "output_price_per_1m": 3,
 
2382
  "hf_private": true
2383
  },
2384
  {
2385
+ "name": "vertex/gemini-3-flash-preview",
2386
+ "type": "vision",
2387
+ "input_price_per_1m": 0.5,
2388
+ "output_price_per_1m": 3,
2389
  "currency": "USD",
 
 
2390
  "capabilities": [
2391
+ "vision",
2392
+ "reasoning"
2393
  ],
2394
+ "context_window": 1048576,
2395
+ "hf_private": true
2396
  },
2397
  {
2398
+ "name": "vertex/gemini-3.1-flash-image-preview",
2399
+ "type": "vision",
2400
+ "input_price_per_1m": 0.5,
2401
+ "output_price_per_1m": 2,
2402
  "currency": "USD",
2403
  "capabilities": [
2404
+ "vision",
2405
  "reasoning"
2406
  ],
2407
+ "context_window": 131072,
2408
  "hf_private": true
2409
  },
2410
  {
2411
+ "name": "mistral/mistral-large-latest",
2412
+ "type": "chat",
2413
+ "input_price_per_1m": 0.5,
2414
+ "output_price_per_1m": 1.5,
2415
  "currency": "USD",
2416
+ "context_window": 131072,
2417
  "capabilities": [
2418
+ "tools"
 
2419
  ],
2420
+ "hf_private": true
 
 
 
2421
  },
2422
  {
2423
+ "name": "nebius/moonshotai/Kimi-K2-Instruct",
2424
  "type": "chat",
2425
+ "input_price_per_1m": 0.5,
2426
+ "output_price_per_1m": 2.4,
2427
  "currency": "USD",
2428
+ "context_window": 131000,
2429
  "capabilities": [
2430
  "tools"
2431
  ],
 
2434
  "hf_private": false
2435
  },
2436
  {
2437
+ "name": "nebius/deepseek-ai/DeepSeek-V3-0324",
2438
  "type": "chat",
2439
+ "input_price_per_1m": 0.5,
2440
+ "output_price_per_1m": 1.5,
2441
  "currency": "USD",
2442
  "context_window": 128000,
2443
  "capabilities": [
2444
  "tools",
2445
  "reasoning"
2446
+ ],
2447
+ "size_b": 685,
2448
+ "hf_id": "deepseek-ai/DeepSeek-V3-0324",
2449
  "hf_private": false
2450
  },
2451
  {
2452
+ "name": "nebius/moonshotai/kimi-k2.5",
2453
+ "type": "vision",
2454
+ "input_price_per_1m": 0.5,
2455
+ "output_price_per_1m": 2.5,
2456
  "currency": "USD",
 
2457
  "capabilities": [
2458
+ "vision",
2459
  "reasoning"
2460
  ],
2461
+ "context_window": 256000,
2462
+ "hf_id": "moonshotai/Kimi-K2.5",
2463
+ "size_b": 1058.6,
2464
  "hf_private": false
2465
  },
2466
  {
2467
+ "name": "novita/meta-llama/llama-3-70b-instruct",
2468
  "type": "chat",
2469
+ "input_price_per_1m": 0.51,
2470
+ "output_price_per_1m": 0.74,
2471
  "currency": "USD",
2472
+ "context_window": 8192,
2473
+ "size_b": 70,
2474
  "capabilities": [
2475
+ "tools"
 
2476
  ],
2477
+ "hf_id": "meta-llama/Llama-3.3-70B-Instruct",
 
2478
  "hf_private": false
2479
  },
2480
  {
2481
+ "name": "openai/o4-mini",
2482
  "type": "chat",
2483
+ "input_price_per_1m": 0.55,
2484
  "output_price_per_1m": 2.2,
2485
  "currency": "USD",
2486
  "capabilities": [
2487
  "reasoning"
2488
  ],
2489
  "context_window": 200000,
2490
+ "hf_private": true
 
 
2491
  },
2492
  {
2493
+ "name": "vertex/deepseek-v3.2",
2494
+ "type": "vision",
2495
+ "input_price_per_1m": 0.56,
2496
+ "output_price_per_1m": 1.68,
2497
  "currency": "USD",
2498
  "capabilities": [
2499
+ "vision",
2500
  "reasoning"
2501
  ],
2502
+ "context_window": 163840,
2503
+ "hf_id": "deepseek-ai/DeepSeek-V3.2",
2504
+ "size_b": 685.4,
2505
  "hf_private": false
2506
  },
2507
  {
2508
+ "name": "novita/moonshotai/kimi-k2-instruct",
2509
  "type": "chat",
2510
+ "input_price_per_1m": 0.57,
2511
+ "output_price_per_1m": 2.3,
2512
  "currency": "USD",
2513
+ "context_window": 131072,
2514
  "capabilities": [
2515
+ "tools"
2516
  ],
2517
+ "hf_id": "moonshotai/Kimi-K2-Instruct",
2518
+ "size_b": 1026.5,
 
2519
  "hf_private": false
2520
  },
2521
  {
 
2590
  "size_b": 1026.5,
2591
  "hf_private": false
2592
  },
2593
+ {
2594
+ "name": "alibaba/qwen3.5",
2595
+ "type": "vision",
2596
+ "input_price_per_1m": 0.6,
2597
+ "output_price_per_1m": 3.6,
2598
+ "currency": "USD",
2599
+ "capabilities": [
2600
+ "vision",
2601
+ "reasoning"
2602
+ ],
2603
+ "context_window": 256000,
2604
+ "size_b": 9,
2605
+ "hf_id": "Qwen/Qwen3.5-9B",
2606
+ "hf_private": false
2607
+ },
2608
  {
2609
  "name": "minimaxi/MiniMax-M2.7-highspeed",
2610
  "type": "vision",
 
2652
  "hf_private": false
2653
  },
2654
  {
2655
+ "name": "zai/GLM-4.7",
2656
+ "type": "chat",
2657
  "input_price_per_1m": 0.6,
2658
+ "output_price_per_1m": 2.2,
2659
  "currency": "USD",
2660
  "capabilities": [
 
2661
  "reasoning"
2662
  ],
2663
+ "context_window": 200000,
2664
+ "hf_id": "zai-org/GLM-4.7",
2665
+ "size_b": 358.3,
2666
+ "hf_private": false
2667
+ },
2668
+ {
2669
+ "name": "zai/GLM-4.5",
2670
+ "type": "chat",
2671
+ "input_price_per_1m": 0.6,
2672
+ "output_price_per_1m": 2.2,
2673
+ "currency": "USD",
2674
+ "capabilities": [
2675
+ "reasoning"
2676
+ ],
2677
+ "context_window": 131072,
2678
+ "hf_id": "zai-org/GLM-4.5",
2679
+ "size_b": 358.3,
2680
+ "hf_private": false
2681
+ },
2682
+ {
2683
+ "name": "zai/GLM-4.6",
2684
+ "type": "chat",
2685
+ "input_price_per_1m": 0.6,
2686
+ "output_price_per_1m": 2.2,
2687
+ "currency": "USD",
2688
+ "capabilities": [
2689
+ "reasoning"
2690
+ ],
2691
+ "context_window": 200000,
2692
+ "hf_id": "zai-org/GLM-4.6",
2693
+ "size_b": 356.8,
2694
+ "hf_private": false
2695
+ },
2696
+ {
2697
+ "name": "nebius/zai-org/GLM-4.5",
2698
+ "type": "chat",
2699
+ "input_price_per_1m": 0.6,
2700
+ "output_price_per_1m": 2.2,
2701
+ "currency": "USD",
2702
+ "context_window": 128000,
2703
+ "capabilities": [
2704
+ "tools",
2705
+ "reasoning"
2706
+ ],
2707
+ "hf_id": "zai-org/GLM-4.5",
2708
+ "size_b": 358.3,
2709
+ "hf_private": false
2710
+ },
2711
+ {
2712
+ "name": "novita/zai-org/glm-4.6",
2713
+ "type": "chat",
2714
+ "input_price_per_1m": 0.6,
2715
+ "output_price_per_1m": 2.2,
2716
+ "currency": "USD",
2717
+ "context_window": 204800,
2718
+ "capabilities": [
2719
+ "tools",
2720
+ "reasoning"
2721
+ ],
2722
+ "hf_id": "zai-org/GLM-4.6",
2723
+ "size_b": 356.8,
2724
+ "hf_private": false
2725
+ },
2726
+ {
2727
+ "name": "novita/zai-org/glm-4.5",
2728
+ "type": "chat",
2729
+ "input_price_per_1m": 0.6,
2730
+ "output_price_per_1m": 2.2,
2731
+ "currency": "USD",
2732
+ "context_window": 131072,
2733
+ "capabilities": [
2734
+ "tools",
2735
+ "reasoning"
2736
+ ],
2737
+ "hf_id": "zai-org/GLM-4.5",
2738
+ "size_b": 358.3,
2739
  "hf_private": false
2740
  },
2741
  {
 
2763
  "hf_private": true
2764
  },
2765
  {
2766
+ "name": "parasail/parasail-qwen25-vl-72b-instruct",
2767
+ "type": "vision",
2768
  "input_price_per_1m": 0.7,
2769
+ "output_price_per_1m": 0.7,
2770
  "currency": "USD",
2771
+ "capabilities": [
2772
+ "vision"
2773
+ ],
2774
+ "context_window": 32768,
2775
+ "size_b": 72,
2776
  "hf_private": false
2777
  },
2778
  {
 
2792
  "hf_private": false
2793
  },
2794
  {
2795
+ "name": "novita/deepseek/deepseek-prover-v2-671b",
2796
+ "type": "chat",
2797
  "input_price_per_1m": 0.7,
2798
+ "output_price_per_1m": 2.5,
2799
  "currency": "USD",
2800
+ "context_window": 160000,
2801
+ "size_b": 671,
 
 
 
2802
  "hf_private": false
2803
  },
2804
  {
2805
+ "name": "openai/gpt-5.4-mini",
2806
  "type": "vision",
2807
  "input_price_per_1m": 0.75,
2808
  "output_price_per_1m": 4.5,
 
2815
  "hf_private": true
2816
  },
2817
  {
2818
+ "name": "openai-responses/gpt-5.4-mini",
2819
  "type": "vision",
2820
  "input_price_per_1m": 0.75,
2821
  "output_price_per_1m": 4.5,
 
2827
  "context_window": 400000,
2828
  "hf_private": true
2829
  },
2830
+ {
2831
+ "name": "deepinfra/meta-llama/Meta-Llama-3.1-405B-Instruct",
2832
+ "type": "chat",
2833
+ "input_price_per_1m": 0.8,
2834
+ "output_price_per_1m": 0.8,
2835
+ "currency": "USD",
2836
+ "context_window": 130815,
2837
+ "size_b": 405,
2838
+ "hf_private": false
2839
+ },
2840
  {
2841
  "name": "nebius/deepseek-ai/DeepSeek-R1-0528",
2842
  "type": "chat",
 
2852
  "size_b": 684.5,
2853
  "hf_private": false
2854
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2855
  {
2856
  "name": "novita/deepseek/deepseek-r1-distill-llama-70b",
2857
  "type": "chat",
 
2867
  "hf_private": false
2868
  },
2869
  {
2870
+ "name": "novita/qwen/qwen2.5-vl-72b-instruct",
2871
  "type": "chat",
2872
  "input_price_per_1m": 0.8,
2873
  "output_price_per_1m": 0.8,
2874
  "currency": "USD",
2875
+ "context_window": 96000,
2876
+ "size_b": 72,
2877
+ "capabilities": [
2878
+ "vision"
2879
+ ],
2880
+ "hf_id": "Qwen/Qwen2.5-VL-72B-Instruct",
2881
  "hf_private": false
2882
  },
2883
  {
 
2958
  "tools",
2959
  "reasoning"
2960
  ],
2961
+ "hf_id": "deepseek-ai/DeepSeek-V3.1-Terminus",
2962
+ "size_b": 671,
2963
+ "hf_private": false
2964
+ },
2965
+ {
2966
+ "name": "parasail/parasail-kimi-k2-instruct",
2967
+ "type": "chat",
2968
+ "input_price_per_1m": 0.99,
2969
+ "output_price_per_1m": 2.99,
2970
+ "currency": "USD",
2971
+ "context_window": 131072,
2972
+ "hf_private": true
2973
+ },
2974
+ {
2975
+ "name": "alibaba/qwen3-coder-plus",
2976
+ "type": "vision",
2977
+ "input_price_per_1m": 1,
2978
+ "output_price_per_1m": 5,
2979
+ "currency": "USD",
2980
+ "capabilities": [
2981
+ "vision"
2982
+ ],
2983
+ "context_window": 1048576,
2984
+ "hf_private": true
2985
  },
2986
  {
2987
+ "name": "bedrock/claude-haiku-4-5",
2988
+ "type": "vision",
2989
+ "input_price_per_1m": 1,
2990
+ "output_price_per_1m": 5,
2991
  "currency": "USD",
2992
+ "capabilities": [
2993
+ "vision"
2994
+ ],
2995
+ "context_window": 200000,
2996
  "hf_private": true
2997
  },
2998
  {
2999
+ "name": "anthropic/claude-haiku-4-5",
3000
+ "type": "vision",
3001
  "input_price_per_1m": 1,
3002
+ "output_price_per_1m": 5,
3003
  "currency": "USD",
3004
  "capabilities": [
3005
+ "vision"
3006
  ],
3007
+ "context_window": 200000,
3008
+ "hf_private": true
 
 
3009
  },
3010
  {
3011
+ "name": "openai/o3",
3012
  "type": "vision",
3013
  "input_price_per_1m": 1,
3014
+ "output_price_per_1m": 4,
3015
  "currency": "USD",
3016
  "capabilities": [
3017
  "vision",
3018
  "reasoning"
3019
  ],
3020
  "context_window": 200000,
3021
+ "hf_private": true
 
 
3022
  },
3023
  {
3024
+ "name": "vertex/claude-haiku-4-5",
3025
  "type": "vision",
3026
  "input_price_per_1m": 1,
3027
  "output_price_per_1m": 5,
 
3033
  "hf_private": true
3034
  },
3035
  {
3036
+ "name": "zai/GLM-5",
3037
  "type": "vision",
3038
  "input_price_per_1m": 1,
3039
+ "output_price_per_1m": 3.2,
3040
  "currency": "USD",
3041
  "capabilities": [
3042
  "vision",
3043
  "reasoning"
3044
  ],
3045
  "context_window": 200000,
3046
+ "hf_id": "zai-org/GLM-5",
3047
+ "size_b": 753.9,
3048
+ "hf_private": false
3049
  },
3050
  {
3051
  "name": "groq/moonshotai/kimi-k2-instruct",
 
3088
  "hf_private": true
3089
  },
3090
  {
3091
+ "name": "novita/GLM-5",
3092
+ "type": "chat",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3093
  "input_price_per_1m": 1,
3094
+ "output_price_per_1m": 3.2,
3095
  "currency": "USD",
3096
  "capabilities": [
3097
+ "reasoning"
3098
  ],
3099
+ "context_window": 202800,
3100
+ "hf_id": "zai-org/GLM-5",
3101
+ "size_b": 753.9,
3102
+ "hf_private": false
3103
  },
3104
  {
3105
  "name": "azure/o4-mini",
 
3114
  "hf_private": true
3115
  },
3116
  {
3117
+ "name": "openai/o3-mini",
3118
  "type": "chat",
3119
  "input_price_per_1m": 1.1,
3120
  "output_price_per_1m": 4.4,
 
3126
  "hf_private": true
3127
  },
3128
  {
3129
+ "name": "openai-responses/o3-mini",
3130
  "type": "chat",
3131
  "input_price_per_1m": 1.1,
3132
  "output_price_per_1m": 4.4,
 
3138
  "hf_private": true
3139
  },
3140
  {
3141
+ "name": "openai-responses/o4-mini",
3142
  "type": "chat",
3143
  "input_price_per_1m": 1.1,
3144
  "output_price_per_1m": 4.4,
 
3173
  "size_b": 72,
3174
  "hf_private": false
3175
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
3176
  {
3177
  "name": "azure/gpt-5",
3178
  "type": "chat",
 
3198
  "hf_private": true
3199
  },
3200
  {
3201
+ "name": "coding/gemini-2.5-pro",
3202
  "type": "vision",
3203
  "input_price_per_1m": 1.25,
3204
  "output_price_per_1m": 10,
 
3207
  "vision",
3208
  "reasoning"
3209
  ],
3210
+ "context_window": 1048576,
3211
  "hf_private": true
3212
  },
3213
  {
3214
+ "name": "google/gemini-2.5-pro",
3215
  "type": "vision",
3216
  "input_price_per_1m": 1.25,
3217
  "output_price_per_1m": 10,
 
3220
  "vision",
3221
  "reasoning"
3222
  ],
3223
+ "context_window": 1048576,
3224
  "hf_private": true
3225
  },
3226
  {
3227
+ "name": "openai/gpt-5.1-chat",
3228
  "type": "vision",
3229
  "input_price_per_1m": 1.25,
3230
  "output_price_per_1m": 10,
 
3233
  "vision",
3234
  "reasoning"
3235
  ],
3236
+ "context_window": 128000,
3237
  "hf_private": true
3238
  },
3239
  {
3240
+ "name": "openai/gpt-5.1",
3241
  "type": "vision",
3242
  "input_price_per_1m": 1.25,
3243
  "output_price_per_1m": 10,
 
3263
  "hf_private": true
3264
  },
3265
  {
3266
+ "name": "together/deepseek-ai/DeepSeek-V3",
3267
+ "type": "chat",
3268
+ "input_price_per_1m": 1.25,
3269
+ "output_price_per_1m": 1.25,
3270
+ "currency": "USD",
3271
+ "context_window": 131072,
3272
+ "capabilities": [
3273
+ "tools",
3274
+ "reasoning"
3275
+ ],
3276
+ "hf_id": "deepseek-ai/DeepSeek-V3.1-Terminus",
3277
+ "size_b": 671,
3278
+ "hf_private": false
3279
+ },
3280
+ {
3281
+ "name": "vertex/gemini-2.5-pro",
3282
  "type": "vision",
3283
  "input_price_per_1m": 1.25,
3284
  "output_price_per_1m": 10,
 
3287
  "vision",
3288
  "reasoning"
3289
  ],
3290
+ "context_window": 1048576,
3291
  "hf_private": true
3292
  },
3293
  {
3294
+ "name": "openai-responses/gpt-5",
3295
  "type": "vision",
3296
  "input_price_per_1m": 1.25,
3297
  "output_price_per_1m": 10,
 
3300
  "vision",
3301
  "reasoning"
3302
  ],
3303
+ "context_window": 400000,
3304
  "hf_private": true
3305
  },
3306
  {
3307
+ "name": "openai-responses/gpt-5.1",
3308
  "type": "vision",
3309
  "input_price_per_1m": 1.25,
3310
  "output_price_per_1m": 10,
 
3313
  "vision",
3314
  "reasoning"
3315
  ],
3316
+ "context_window": 400000,
3317
  "hf_private": true
3318
  },
3319
  {
3320
+ "name": "openai-responses/gpt-5-codex",
3321
+ "type": "vision",
3322
  "input_price_per_1m": 1.25,
3323
+ "output_price_per_1m": 10,
3324
  "currency": "USD",
 
3325
  "capabilities": [
3326
+ "vision",
3327
  "reasoning"
3328
  ],
3329
+ "context_window": 400000,
3330
+ "hf_private": true
 
3331
  },
3332
  {
3333
+ "name": "openai-responses/gpt-5.1-codex",
3334
  "type": "vision",
3335
  "input_price_per_1m": 1.25,
3336
  "output_price_per_1m": 10,
 
3339
  "vision",
3340
  "reasoning"
3341
  ],
3342
+ "context_window": 400000,
3343
  "hf_private": true
3344
  },
3345
  {
3346
+ "name": "novita/sao10k/l3-70b-euryale-v2.1",
3347
  "type": "chat",
3348
  "input_price_per_1m": 1.48,
3349
  "output_price_per_1m": 1.48,
 
3353
  "hf_private": false
3354
  },
3355
  {
3356
+ "name": "novita/sao10k/l31-70b-euryale-v2.2",
3357
  "type": "chat",
3358
  "input_price_per_1m": 1.48,
3359
  "output_price_per_1m": 1.48,
 
3374
  ],
3375
  "hf_private": true
3376
  },
 
 
 
 
 
 
 
 
 
 
 
 
3377
  {
3378
  "name": "azure/openai-responses/gpt-5.2-codex",
3379
  "type": "vision",
 
3401
  "hf_private": true
3402
  },
3403
  {
3404
+ "name": "azure/gpt-5.2",
3405
+ "type": "chat",
3406
  "input_price_per_1m": 1.75,
3407
  "output_price_per_1m": 14,
3408
  "currency": "USD",
3409
  "capabilities": [
 
3410
  "reasoning"
3411
  ],
3412
+ "context_window": 200000,
3413
  "hf_private": true
3414
  },
3415
  {
3416
+ "name": "openai/gpt-5.3-chat",
3417
  "type": "vision",
3418
  "input_price_per_1m": 1.75,
3419
  "output_price_per_1m": 14,
 
3422
  "vision",
3423
  "reasoning"
3424
  ],
3425
+ "context_window": 128000,
3426
  "hf_private": true
3427
  },
3428
  {
3429
+ "name": "openai/gpt-5.2-chat",
3430
  "type": "vision",
3431
  "input_price_per_1m": 1.75,
3432
  "output_price_per_1m": 14,
 
3435
  "vision",
3436
  "reasoning"
3437
  ],
3438
+ "context_window": 128000,
3439
  "hf_private": true
3440
  },
3441
  {
3442
+ "name": "openai/gpt-5.2",
3443
  "type": "vision",
3444
  "input_price_per_1m": 1.75,
3445
  "output_price_per_1m": 14,
 
3452
  "hf_private": true
3453
  },
3454
  {
3455
+ "name": "openai-responses/gpt-5.2",
3456
  "type": "vision",
3457
  "input_price_per_1m": 1.75,
3458
  "output_price_per_1m": 14,
 
3465
  "hf_private": true
3466
  },
3467
  {
3468
+ "name": "openai-responses/gpt-5.3-codex",
3469
  "type": "vision",
3470
  "input_price_per_1m": 1.75,
3471
  "output_price_per_1m": 14,
 
3474
  "vision",
3475
  "reasoning"
3476
  ],
3477
+ "context_window": 400000,
3478
  "hf_private": true
3479
  },
3480
  {
3481
+ "name": "openai-responses/gpt-5.2-codex",
3482
  "type": "vision",
3483
  "input_price_per_1m": 1.75,
3484
  "output_price_per_1m": 14,
 
3487
  "vision",
3488
  "reasoning"
3489
  ],
3490
+ "context_window": 400000,
3491
  "hf_private": true
3492
  },
3493
  {
3494
+ "name": "openai-responses/gpt-5.3-chat",
3495
  "type": "vision",
3496
+ "input_price_per_1m": 1.75,
3497
+ "output_price_per_1m": 14,
3498
  "currency": "USD",
3499
  "capabilities": [
3500
  "vision",
3501
  "reasoning"
3502
  ],
3503
+ "context_window": 128000,
3504
  "hf_private": true
3505
  },
3506
  {
3507
+ "name": "azure/openai-responses/gpt-4.1",
3508
  "type": "vision",
3509
  "input_price_per_1m": 2,
3510
+ "output_price_per_1m": 8,
3511
  "currency": "USD",
3512
  "capabilities": [
3513
+ "vision"
 
3514
  ],
3515
+ "context_window": 1047576,
3516
  "hf_private": true
3517
  },
3518
  {
 
3528
  "hf_private": true
3529
  },
3530
  {
3531
+ "name": "xai/grok-4.2-beta",
3532
  "type": "vision",
3533
  "input_price_per_1m": 2,
3534
+ "output_price_per_1m": 6,
3535
  "currency": "USD",
3536
  "capabilities": [
3537
+ "vision",
3538
+ "reasoning"
3539
  ],
3540
+ "context_window": 2000000,
3541
  "hf_private": true
3542
  },
3543
  {
3544
+ "name": "xai/grok-2-1212",
3545
  "type": "chat",
3546
  "input_price_per_1m": 2,
3547
+ "output_price_per_1m": 10,
3548
  "currency": "USD",
3549
+ "context_window": 131072,
3550
+ "hf_private": true
3551
+ },
3552
+ {
3553
+ "name": "google/gemini-3-pro-preview",
3554
+ "type": "vision",
3555
+ "input_price_per_1m": 2,
3556
+ "output_price_per_1m": 12,
3557
+ "currency": "USD",
3558
+ "capabilities": [
3559
+ "vision",
3560
+ "reasoning"
3561
+ ],
3562
+ "context_window": 1048576,
3563
  "hf_private": true
3564
  },
3565
  {
3566
+ "name": "google/gemini-3.1-pro-preview",
3567
  "type": "vision",
3568
  "input_price_per_1m": 2,
3569
+ "output_price_per_1m": 12,
3570
  "currency": "USD",
3571
  "capabilities": [
3572
+ "vision",
3573
+ "reasoning"
3574
  ],
3575
+ "context_window": 1048576,
3576
  "hf_private": true
3577
  },
3578
  {
 
3601
  "hf_private": true
3602
  },
3603
  {
3604
+ "name": "vertex/gemini-3-pro-preview",
3605
+ "type": "vision",
3606
  "input_price_per_1m": 2,
3607
+ "output_price_per_1m": 12,
3608
  "currency": "USD",
3609
+ "capabilities": [
3610
+ "vision",
3611
+ "reasoning"
3612
+ ],
3613
+ "context_window": 1048576,
3614
  "hf_private": true
3615
  },
3616
  {
3617
+ "name": "vertex/gemini-3-pro-image-preview",
3618
  "type": "vision",
3619
  "input_price_per_1m": 2,
3620
+ "output_price_per_1m": 12,
3621
  "currency": "USD",
3622
  "capabilities": [
3623
  "vision",
3624
  "reasoning"
3625
  ],
3626
+ "context_window": 1048576,
3627
  "hf_private": true
3628
  },
3629
  {
3630
+ "name": "vertex/gemini-3.1-pro-preview",
3631
+ "type": "vision",
3632
  "input_price_per_1m": 2,
3633
+ "output_price_per_1m": 12,
3634
  "currency": "USD",
3635
+ "capabilities": [
3636
+ "vision",
3637
+ "reasoning"
3638
+ ],
3639
+ "context_window": 1048576,
3640
  "hf_private": true
3641
  },
3642
  {
 
3653
  "hf_private": true
3654
  },
3655
  {
3656
+ "name": "mistral/pixtral-large-latest",
3657
+ "type": "chat",
3658
  "input_price_per_1m": 2,
3659
+ "output_price_per_1m": 5,
3660
  "currency": "USD",
3661
+ "context_window": 131072,
 
 
 
 
3662
  "hf_private": true
3663
  },
3664
  {
3665
+ "name": "openai-responses/gpt-4.1",
3666
  "type": "vision",
3667
  "input_price_per_1m": 2,
3668
+ "output_price_per_1m": 8,
3669
  "currency": "USD",
3670
  "capabilities": [
3671
+ "vision"
 
3672
  ],
3673
+ "context_window": 1047576,
3674
  "hf_private": true
3675
  },
3676
  {
3677
+ "name": "nebius/deepseek-ai/DeepSeek-V3-0324-fast",
3678
+ "type": "chat",
3679
  "input_price_per_1m": 2,
3680
+ "output_price_per_1m": 6,
3681
  "currency": "USD",
3682
+ "context_window": 128000,
 
 
 
 
3683
  "hf_private": true
3684
  },
3685
  {
 
3696
  "hf_private": true
3697
  },
3698
  {
3699
+ "name": "openai/gpt-4o-2024-08-06",
3700
  "type": "vision",
3701
  "input_price_per_1m": 2.5,
3702
+ "output_price_per_1m": 10,
3703
  "currency": "USD",
3704
  "capabilities": [
3705
+ "vision"
 
3706
  ],
3707
+ "context_window": 128000,
3708
  "hf_private": true
3709
  },
3710
  {
3711
+ "name": "openai/gpt-4o",
3712
  "type": "vision",
3713
  "input_price_per_1m": 2.5,
3714
  "output_price_per_1m": 10,
 
3720
  "hf_private": true
3721
  },
3722
  {
3723
+ "name": "openai/gpt-4o-2024-11-20",
3724
  "type": "vision",
3725
  "input_price_per_1m": 2.5,
3726
  "output_price_per_1m": 10,
 
3745
  "hf_private": true
3746
  },
3747
  {
3748
+ "name": "openai/gpt-4o-2024-05-13",
3749
  "type": "vision",
3750
  "input_price_per_1m": 2.5,
3751
  "output_price_per_1m": 10,
 
3757
  "hf_private": true
3758
  },
3759
  {
3760
+ "name": "openai-responses/gpt-5.4",
3761
  "type": "vision",
3762
  "input_price_per_1m": 2.5,
3763
+ "output_price_per_1m": 15,
3764
  "currency": "USD",
3765
  "capabilities": [
3766
+ "vision",
3767
+ "reasoning"
3768
  ],
3769
+ "context_window": 1050000,
3770
  "hf_private": true
3771
  },
3772
  {
3773
+ "name": "xai/grok-4",
3774
  "type": "vision",
3775
  "input_price_per_1m": 3,
3776
  "output_price_per_1m": 15,
3777
  "currency": "USD",
3778
  "capabilities": [
3779
+ "vision"
 
3780
  ],
3781
+ "context_window": 256000,
3782
  "hf_private": true
3783
  },
3784
  {
3785
+ "name": "coding/claude-sonnet-4-20250514",
3786
  "type": "vision",
3787
  "input_price_per_1m": 3,
3788
  "output_price_per_1m": 15,
 
3808
  "hf_private": true
3809
  },
3810
  {
3811
+ "name": "bedrock/claude-3-7-sonnet",
3812
  "type": "vision",
3813
  "input_price_per_1m": 3,
3814
  "output_price_per_1m": 15,
 
3821
  "hf_private": true
3822
  },
3823
  {
3824
+ "name": "bedrock/claude-sonnet-4",
3825
  "type": "vision",
3826
  "input_price_per_1m": 3,
3827
  "output_price_per_1m": 15,
3828
  "currency": "USD",
3829
  "capabilities": [
3830
+ "vision",
3831
+ "reasoning"
3832
  ],
3833
+ "context_window": 200000,
3834
  "hf_private": true
3835
  },
3836
  {
3837
+ "name": "bedrock/claude-sonnet-4-5",
3838
  "type": "vision",
3839
  "input_price_per_1m": 3,
3840
  "output_price_per_1m": 15,
 
3846
  "context_window": 200000,
3847
  "hf_private": true
3848
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3849
  {
3850
  "name": "anthropic/claude-sonnet-4-5",
3851
  "type": "vision",
 
3885
  "context_window": 1000000,
3886
  "hf_private": true
3887
  },
3888
+ {
3889
+ "name": "together/deepseek-ai/DeepSeek-R1",
3890
+ "type": "chat",
3891
+ "input_price_per_1m": 3,
3892
+ "output_price_per_1m": 7,
3893
+ "currency": "USD",
3894
+ "context_window": 64000,
3895
+ "capabilities": [
3896
+ "tools",
3897
+ "reasoning"
3898
+ ],
3899
+ "hf_id": "deepseek-ai/DeepSeek-R1",
3900
+ "size_b": 671,
3901
+ "size_source": "manual",
3902
+ "hf_private": false
3903
+ },
3904
  {
3905
  "name": "vertex/claude-3-5-sonnet",
3906
  "type": "vision",
 
3914
  "hf_private": true
3915
  },
3916
  {
3917
+ "name": "vertex/claude-sonnet-4-5",
3918
  "type": "vision",
3919
  "input_price_per_1m": 3,
3920
  "output_price_per_1m": 15,
 
3940
  "hf_private": true
3941
  },
3942
  {
3943
+ "name": "vertex/claude-3-7-sonnet",
3944
  "type": "vision",
3945
  "input_price_per_1m": 3,
3946
  "output_price_per_1m": 15,
 
3952
  "context_window": 200000,
3953
  "hf_private": true
3954
  },
3955
+ {
3956
+ "name": "perplexity/sonar-pro",
3957
+ "type": "chat",
3958
+ "input_price_per_1m": 3,
3959
+ "output_price_per_1m": 15,
3960
+ "currency": "USD",
3961
+ "context_window": 204800,
3962
+ "capabilities": [
3963
+ "vision"
3964
+ ],
3965
+ "hf_private": true
3966
+ },
3967
  {
3968
  "name": "novita/deepseek/deepseek-r1",
3969
  "type": "chat",
 
3981
  "hf_private": false
3982
  },
3983
  {
3984
+ "name": "xai/grok-3",
3985
+ "type": "chat",
3986
  "input_price_per_1m": 5,
3987
  "output_price_per_1m": 25,
3988
  "currency": "USD",
3989
+ "context_window": 131072,
3990
  "capabilities": [
3991
+ "tools"
 
3992
  ],
 
3993
  "hf_private": true
3994
  },
3995
  {
 
4006
  "hf_private": true
4007
  },
4008
  {
4009
+ "name": "bedrock/claude-opus-4-5",
4010
  "type": "vision",
4011
  "input_price_per_1m": 5,
 
 
 
 
 
 
 
 
 
 
 
 
4012
  "output_price_per_1m": 25,
4013
  "currency": "USD",
 
4014
  "capabilities": [
4015
+ "vision",
4016
+ "reasoning"
4017
  ],
4018
+ "context_window": 200000,
4019
  "hf_private": true
4020
  },
4021
  {
 
4045
  "hf_private": true
4046
  },
4047
  {
4048
+ "name": "openai/chatgpt-4o",
4049
+ "type": "vision",
4050
+ "input_price_per_1m": 5,
4051
+ "output_price_per_1m": 15,
4052
+ "currency": "USD",
4053
+ "capabilities": [
4054
+ "vision"
4055
+ ],
4056
+ "context_window": 128000,
4057
+ "hf_private": true
4058
+ },
4059
+ {
4060
+ "name": "vertex/claude-opus-4-5",
4061
  "type": "vision",
4062
  "input_price_per_1m": 5,
4063
  "output_price_per_1m": 25,
 
4066
  "vision",
4067
  "reasoning"
4068
  ],
4069
+ "context_window": 200000,
4070
  "hf_private": true
4071
  },
4072
  {
4073
+ "name": "vertex/claude-opus-4-6",
4074
  "type": "vision",
4075
  "input_price_per_1m": 5,
4076
  "output_price_per_1m": 25,
 
4079
  "vision",
4080
  "reasoning"
4081
  ],
4082
+ "context_window": 1000000,
4083
  "hf_private": true
4084
  },
4085
  {
 
4096
  "hf_private": true
4097
  },
4098
  {
4099
+ "name": "coding/claude-opus-4-20250514",
4100
  "type": "vision",
4101
  "input_price_per_1m": 15,
4102
  "output_price_per_1m": 75,
 
4109
  "hf_private": true
4110
  },
4111
  {
4112
+ "name": "bedrock/claude-opus-4",
4113
  "type": "vision",
4114
  "input_price_per_1m": 15,
4115
+ "output_price_per_1m": 75,
4116
  "currency": "USD",
4117
  "capabilities": [
4118
  "vision",
4119
  "reasoning"
4120
  ],
4121
+ "context_window": 200000,
4122
  "hf_private": true
4123
  },
4124
  {
4125
+ "name": "anthropic/claude-opus-4-1",
4126
  "type": "vision",
4127
  "input_price_per_1m": 15,
4128
+ "output_price_per_1m": 75,
4129
  "currency": "USD",
4130
  "capabilities": [
4131
  "vision",
 
4135
  "hf_private": true
4136
  },
4137
  {
4138
+ "name": "anthropic/claude-opus-4",
4139
  "type": "vision",
4140
  "input_price_per_1m": 15,
4141
  "output_price_per_1m": 75,
 
4148
  "hf_private": true
4149
  },
4150
  {
4151
+ "name": "openai/o1",
4152
  "type": "vision",
4153
  "input_price_per_1m": 15,
4154
+ "output_price_per_1m": 60,
4155
  "currency": "USD",
4156
  "capabilities": [
4157
  "vision",
 
4161
  "hf_private": true
4162
  },
4163
  {
4164
+ "name": "vertex/claude-opus-4",
4165
  "type": "vision",
4166
  "input_price_per_1m": 15,
4167
  "output_price_per_1m": 75,
 
4174
  "hf_private": true
4175
  },
4176
  {
4177
+ "name": "vertex/claude-opus-4-1",
4178
  "type": "vision",
4179
  "input_price_per_1m": 15,
4180
  "output_price_per_1m": 75,
 
4187
  "hf_private": true
4188
  },
4189
  {
4190
+ "name": "openai-responses/gpt-5-pro",
4191
  "type": "vision",
4192
  "input_price_per_1m": 15,
4193
+ "output_price_per_1m": 120,
4194
  "currency": "USD",
4195
  "capabilities": [
4196
  "vision",
4197
  "reasoning"
4198
  ],
4199
+ "context_window": 400000,
4200
  "hf_private": true
4201
  },
4202
  {
 
4226
  "hf_private": true
4227
  },
4228
  {
4229
+ "name": "openai/gpt-5.4-pro",
4230
  "type": "vision",
4231
  "input_price_per_1m": 30,
4232
  "output_price_per_1m": 180,
 
4239
  "hf_private": true
4240
  },
4241
  {
4242
+ "name": "openai-responses/gpt-5.4-pro",
4243
  "type": "vision",
4244
  "input_price_per_1m": 30,
4245
  "output_price_per_1m": 180,
scripts/fetch-utils.js CHANGED
@@ -4,7 +4,7 @@
4
  * Robust fetch helper with retries, exponential backoff, and timeout.
5
  */
6
  async function fetchRobust(url, options = {}) {
7
- const { retries = 5, backoff = 1000, timeout = 60000, ...fetchOptions } = options;
8
  let lastError;
9
 
10
  for (let i = 0; i < retries; i++) {
@@ -23,8 +23,8 @@ async function fetchRobust(url, options = {}) {
23
 
24
  if (res.ok) return res;
25
 
26
- // Retry on transient status codes: 429 (Rate Limit) and 5xx (Server Errors)
27
- if (res.status === 429 || (res.status >= 500 && res.status < 600)) {
28
  lastError = new Error(`HTTP ${res.status} from ${url}`);
29
  if (i < retries - 1) {
30
  const delay = backoff * Math.pow(2, i) + Math.random() * 1000;
 
4
  * Robust fetch helper with retries, exponential backoff, and timeout.
5
  */
6
  async function fetchRobust(url, options = {}) {
7
+ const { retries = 5, backoff = 1000, timeout = 120000, ...fetchOptions } = options;
8
  let lastError;
9
 
10
  for (let i = 0; i < retries; i++) {
 
23
 
24
  if (res.ok) return res;
25
 
26
+ // Retry on transient status codes: 429 (Rate Limit), 408 (Timeout), and 5xx (Server Errors)
27
+ if (res.status === 429 || res.status === 408 || (res.status >= 500 && res.status < 600)) {
28
  lastError = new Error(`HTTP ${res.status} from ${url}`);
29
  if (i < retries - 1) {
30
  const delay = backoff * Math.pow(2, i) + Math.random() * 1000;