openapi-to-rust 0.4.0

Generate strongly-typed Rust structs, HTTP clients, and SSE streaming clients from OpenAPI 3.1 specifications
Documentation
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
4417
4418
4419
4420
4421
4422
4423
4424
4425
4426
4427
4428
4429
4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
4450
4451
4452
4453
4454
4455
4456
4457
4458
4459
4460
4461
4462
4463
4464
4465
4466
4467
4468
4469
4470
4471
4472
4473
4474
4475
4476
4477
4478
4479
4480
4481
4482
4483
4484
4485
4486
4487
4488
4489
4490
4491
4492
4493
4494
4495
4496
4497
4498
4499
4500
4501
4502
4503
4504
4505
4506
4507
4508
4509
4510
4511
4512
4513
4514
4515
4516
4517
4518
4519
4520
4521
4522
4523
4524
4525
4526
4527
4528
4529
4530
4531
4532
4533
4534
4535
4536
4537
4538
4539
4540
4541
4542
4543
4544
4545
4546
4547
4548
4549
4550
4551
4552
4553
4554
4555
4556
4557
4558
4559
4560
4561
4562
4563
4564
4565
4566
4567
4568
4569
4570
4571
4572
4573
4574
4575
4576
4577
4578
4579
4580
4581
4582
4583
4584
4585
4586
4587
4588
4589
4590
4591
4592
4593
4594
4595
4596
4597
4598
4599
4600
4601
4602
4603
4604
4605
4606
4607
4608
4609
4610
4611
4612
4613
4614
4615
4616
4617
4618
4619
4620
4621
4622
4623
4624
4625
4626
4627
4628
4629
4630
4631
4632
4633
4634
4635
4636
4637
4638
4639
4640
4641
4642
4643
4644
4645
4646
4647
4648
4649
4650
4651
4652
4653
4654
4655
4656
4657
4658
4659
4660
4661
4662
4663
4664
4665
4666
4667
4668
4669
4670
4671
4672
4673
4674
4675
4676
4677
4678
4679
4680
4681
4682
4683
4684
4685
4686
4687
4688
4689
4690
4691
4692
4693
4694
4695
4696
4697
4698
4699
4700
4701
4702
4703
4704
4705
4706
4707
4708
4709
4710
4711
4712
4713
4714
4715
4716
4717
4718
4719
4720
4721
4722
4723
4724
4725
4726
4727
4728
4729
4730
4731
4732
4733
4734
4735
4736
4737
4738
4739
4740
4741
4742
4743
4744
4745
4746
4747
4748
4749
4750
4751
4752
4753
4754
4755
4756
4757
4758
4759
4760
4761
4762
4763
4764
4765
4766
4767
4768
4769
4770
4771
4772
4773
4774
4775
4776
4777
4778
4779
4780
4781
4782
4783
4784
4785
4786
4787
4788
4789
4790
4791
4792
4793
4794
4795
4796
4797
4798
4799
4800
4801
4802
4803
4804
4805
4806
4807
4808
4809
4810
4811
4812
4813
4814
4815
4816
4817
4818
4819
4820
4821
4822
4823
4824
4825
4826
4827
4828
4829
4830
4831
4832
4833
4834
4835
4836
4837
4838
4839
4840
4841
4842
4843
4844
4845
4846
4847
4848
4849
4850
4851
4852
4853
4854
4855
4856
4857
4858
4859
4860
4861
4862
4863
4864
4865
4866
4867
4868
4869
4870
4871
4872
4873
4874
4875
4876
4877
4878
4879
4880
4881
4882
4883
4884
4885
4886
4887
4888
4889
4890
4891
4892
4893
4894
4895
4896
4897
4898
4899
4900
4901
4902
4903
4904
4905
4906
4907
4908
4909
4910
4911
4912
4913
4914
4915
4916
4917
4918
4919
4920
4921
4922
4923
4924
4925
4926
4927
4928
4929
4930
4931
4932
4933
4934
4935
4936
4937
4938
4939
4940
4941
4942
4943
4944
4945
4946
4947
4948
4949
4950
4951
4952
4953
4954
4955
4956
4957
4958
4959
4960
4961
4962
4963
4964
4965
4966
4967
4968
4969
4970
4971
4972
4973
4974
4975
4976
4977
4978
4979
4980
4981
4982
4983
4984
4985
4986
4987
4988
4989
4990
4991
4992
4993
4994
4995
4996
4997
4998
4999
5000
5001
5002
5003
5004
5005
5006
5007
5008
5009
5010
5011
5012
5013
5014
5015
5016
5017
5018
5019
5020
5021
5022
5023
5024
5025
5026
5027
5028
5029
5030
5031
5032
5033
5034
5035
5036
5037
5038
5039
5040
5041
5042
5043
5044
5045
5046
5047
5048
5049
5050
5051
5052
5053
5054
5055
5056
5057
5058
5059
5060
5061
5062
5063
5064
5065
5066
5067
5068
5069
5070
5071
5072
5073
5074
5075
5076
5077
5078
5079
5080
5081
5082
5083
5084
5085
5086
5087
5088
5089
5090
5091
5092
5093
5094
5095
5096
5097
5098
5099
5100
5101
5102
5103
5104
5105
5106
5107
5108
5109
5110
5111
5112
5113
5114
5115
5116
5117
5118
5119
5120
5121
5122
5123
5124
5125
5126
5127
5128
5129
5130
5131
5132
5133
5134
5135
5136
5137
5138
5139
5140
5141
5142
5143
5144
5145
5146
5147
5148
5149
5150
5151
5152
5153
5154
5155
5156
5157
5158
5159
5160
5161
5162
5163
5164
5165
5166
5167
5168
5169
5170
5171
5172
5173
5174
5175
5176
5177
5178
5179
5180
5181
5182
5183
5184
5185
5186
5187
5188
5189
5190
5191
5192
5193
5194
5195
5196
5197
5198
5199
5200
5201
5202
5203
5204
5205
5206
5207
5208
5209
5210
5211
5212
5213
5214
5215
5216
5217
5218
5219
5220
5221
5222
5223
5224
5225
5226
5227
5228
5229
5230
5231
5232
5233
5234
5235
5236
5237
5238
5239
5240
5241
5242
5243
5244
5245
5246
5247
5248
5249
5250
5251
5252
5253
5254
5255
5256
5257
5258
5259
5260
5261
5262
5263
5264
5265
5266
5267
5268
5269
5270
5271
5272
5273
5274
5275
5276
5277
5278
5279
5280
5281
5282
5283
5284
5285
5286
5287
5288
5289
5290
5291
5292
5293
5294
5295
5296
5297
5298
5299
5300
5301
5302
5303
5304
5305
5306
5307
5308
5309
5310
5311
5312
5313
5314
5315
5316
5317
5318
5319
5320
5321
5322
5323
5324
5325
5326
5327
5328
5329
5330
5331
5332
5333
5334
5335
5336
5337
5338
5339
5340
5341
5342
5343
5344
5345
5346
5347
5348
5349
5350
5351
5352
5353
5354
5355
5356
5357
5358
5359
5360
5361
5362
5363
5364
5365
5366
5367
5368
5369
5370
5371
5372
5373
5374
5375
5376
5377
5378
5379
5380
5381
5382
5383
5384
5385
5386
5387
5388
5389
5390
5391
5392
5393
5394
5395
5396
5397
5398
5399
5400
5401
5402
5403
5404
5405
5406
5407
5408
5409
5410
5411
5412
5413
5414
5415
5416
5417
5418
5419
5420
5421
5422
5423
5424
5425
5426
5427
5428
5429
5430
5431
5432
5433
5434
5435
5436
5437
5438
5439
5440
5441
5442
5443
5444
5445
5446
5447
5448
5449
5450
5451
5452
5453
5454
5455
5456
5457
5458
5459
5460
5461
5462
5463
5464
5465
5466
5467
5468
5469
5470
5471
5472
5473
5474
5475
5476
5477
5478
5479
5480
5481
5482
5483
5484
5485
5486
5487
5488
5489
5490
5491
5492
5493
5494
5495
5496
5497
5498
5499
5500
5501
5502
5503
5504
5505
5506
5507
5508
5509
5510
5511
5512
5513
5514
5515
5516
5517
5518
5519
5520
5521
5522
5523
5524
5525
5526
5527
5528
5529
5530
5531
5532
5533
5534
5535
5536
5537
5538
5539
5540
5541
5542
5543
5544
5545
5546
5547
5548
5549
5550
5551
5552
5553
5554
5555
5556
5557
5558
5559
5560
5561
5562
5563
5564
5565
5566
5567
5568
5569
5570
5571
5572
5573
5574
5575
5576
5577
5578
5579
5580
5581
5582
5583
5584
5585
5586
5587
5588
5589
5590
5591
5592
5593
5594
5595
5596
5597
5598
5599
5600
5601
5602
5603
5604
5605
5606
5607
5608
5609
5610
5611
5612
5613
5614
5615
5616
5617
5618
5619
5620
5621
5622
openapi: 3.0.1
info:
  title: GroqCloud API
  description: Specification of the Groq cloud API
  termsOfService: https://groq.com/terms-of-use/
  contact:
    name: Groq Support
    email: support@groq.com
  version: '2.1'
servers:
  - url: https://api.groq.com
paths:
  /openai/v1/audio/speech:
    post:
      operationId: createSpeech
      tags:
        - Audio
      summary: Generates audio from the input text.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CreateSpeechRequest'
      responses:
        '200':
          description: OK
          headers:
            Transfer-Encoding:
              schema:
                type: string
              description: chunked
          content:
            audio/wav:
              schema:
                type: string
                format: binary
      x-groq-metadata:
        returns: Returns an audio file in `wav` format.
        examples:
          - title: Default
            request:
              curl: |
                curl https://api.groq.com/openai/v1/audio/speech \
                  -H "Authorization: Bearer $GROQ_API_KEY" \
                  -H "Content-Type: application/json" \
                  -d '{
                    "model": "playai-tts",
                    "input": "I love building and shipping new features for our users!",
                    "voice": "Fritz-PlayAI",
                    "response_format": "wav"
                  }'
              py: |
                import os
                from groq import Groq

                client = Groq(api_key=os.environ.get("GROQ_API_KEY"))

                speech_file_path = "speech.wav"
                model = "playai-tts"
                voice = "Fritz-PlayAI"
                text = "I love building and shipping new features for our users!"
                response_format = "wav"

                response = client.audio.speech.create(
                    model=model,
                    voice=voice,
                    input=text,
                    response_format=response_format
                )

                response.write_to_file(speech_file_path)
              js: |
                import fs from "fs";
                import path from "path";
                import Groq from 'groq-sdk';

                const groq = new Groq({
                  apiKey: process.env.GROQ_API_KEY
                });

                const speechFilePath = "speech.wav";
                const model = "playai-tts";
                const voice = "Fritz-PlayAI";
                const text = "I love building and shipping new features for our users!";
                const responseFormat = "wav";

                async function main() {
                  const response = await groq.audio.speech.create({
                    model: model,
                    voice: voice,
                    input: text,
                    response_format: responseFormat
                  });

                  const buffer = Buffer.from(await response.arrayBuffer());
                  await fs.promises.writeFile(speechFilePath, buffer);
                }

                main();
  /openai/v1/audio/transcriptions:
    post:
      operationId: createTranscription
      tags:
        - Audio
      summary: Transcribes audio into the input language.
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              $ref: '#/components/schemas/CreateTranscriptionRequest'
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CreateTranscriptionResponseJson'
      x-groq-metadata:
        returns: Returns an audio transcription object.
        examples:
          - title: Default
            request:
              curl: |
                curl https://api.groq.com/openai/v1/audio/transcriptions \
                  -H "Authorization: Bearer $GROQ_API_KEY" \
                  -H "Content-Type: multipart/form-data" \
                  -F file="@./sample_audio.m4a" \
                  -F model="whisper-large-v3"
              py: |
                import os
                from groq import Groq

                client = Groq()
                filename = os.path.dirname(__file__) + "/sample_audio.m4a"

                with open(filename, "rb") as file:
                    transcription = client.audio.transcriptions.create(
                      file=(filename, file.read()),
                      model="whisper-large-v3",
                      prompt="Specify context or spelling",  # Optional
                      response_format="json",  # Optional
                      language="en",  # Optional
                      temperature=0.0  # Optional
                    )
                    print(transcription.text)
              js: |
                import fs from "fs";
                import Groq from "groq-sdk";

                const groq = new Groq();
                async function main() {
                  const transcription = await groq.audio.transcriptions.create({
                    file: fs.createReadStream("sample_audio.m4a"),
                    model: "whisper-large-v3",
                    prompt: "Specify context or spelling", // Optional
                    response_format: "json", // Optional
                    language: "en", // Optional
                    temperature: 0.0, // Optional
                  });
                  console.log(transcription.text);
                }
                main();
            response: |
              {
                "text": "Your transcribed text appears here...",
                "x_groq": {
                  "id": "req_unique_id"
                }
              }
  /openai/v1/audio/translations:
    post:
      operationId: createTranslation
      tags:
        - Audio
      summary: Translates audio into English.
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              $ref: '#/components/schemas/CreateTranslationRequest'
      responses:
        '200':
          description: OK
          content:
            text/plain:
              schema:
                type: string
            application/json:
              schema:
                $ref: '#/components/schemas/CreateTranslationResponseJson'
      x-groq-metadata:
        returns: Returns an audio translation object.
        examples:
          - title: Default
            request:
              curl: |
                curl https://api.groq.com/openai/v1/audio/translations \
                  -H "Authorization: Bearer $GROQ_API_KEY" \
                  -H "Content-Type: multipart/form-data" \
                  -F file="@./sample_audio.m4a" \
                  -F model="whisper-large-v3"
              py: |
                # Default
                import os
                from groq import Groq

                client = Groq()
                filename = os.path.dirname(__file__) + "/sample_audio.m4a"

                with open(filename, "rb") as file:
                    translation = client.audio.translations.create(
                      file=(filename, file.read()),
                      model="whisper-large-v3",
                      prompt="Specify context or spelling",  # Optional
                      response_format="json",  # Optional
                      temperature=0.0  # Optional
                    )
                    print(translation.text)
              js: |
                // Default
                import fs from "fs";
                import Groq from "groq-sdk";

                const groq = new Groq();
                async function main() {
                  const translation = await groq.audio.translations.create({
                    file: fs.createReadStream("sample_audio.m4a"),
                    model: "whisper-large-v3",
                    prompt: "Specify context or spelling", // Optional
                    response_format: "json", // Optional
                    temperature: 0.0, // Optional
                  });
                  console.log(translation.text);
                }
                main();
            response: |
              {
                "text": "Your translated text appears here...",
                "x_groq": {
                  "id": "req_unique_id"
                }
              }
  /openai/v1/batches:
    post:
      summary: Creates and executes a batch from an uploaded file of requests. [Learn more](/docs/batch).
      operationId: createBatch
      tags:
        - Batch
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
                - input_file_id
                - endpoint
                - completion_window
              properties:
                input_file_id:
                  type: string
                  description: >
                    The ID of an uploaded file that contains requests for the new batch.


                    See [upload file](/docs/api-reference#files-upload) for how to upload a file.


                    Your input file must be formatted as a [JSONL file](/docs/batch), and must be uploaded
                    with the purpose `batch`. The file can be up to 100 MB in size.
                endpoint:
                  type: string
                  enum:
                    - /v1/chat/completions
                  description: >-
                    The endpoint to be used for all requests in the batch. Currently `/v1/chat/completions` is
                    supported.
                completion_window:
                  type: string
                  description: >-
                    The time frame within which the batch should be processed. Durations from `24h` to `7d`
                    are supported.
                metadata:
                  type: object
                  additionalProperties:
                    type: string
                  description: Optional custom metadata for the batch.
                  nullable: true
      responses:
        '200':
          description: Batch created successfully.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Batch'
      x-groq-metadata:
        returns: A created batch object.
        examples:
          - title: Default
            request:
              curl: |
                curl https://api.groq.com/openai/v1/batches \
                  -H "Authorization: Bearer $GROQ_API_KEY" \
                  -H "Content-Type: application/json" \
                  -d '{
                    "input_file_id": "file_01jh6x76wtemjr74t1fh0faj5t",
                    "endpoint": "/v1/chat/completions",
                    "completion_window": "24h"
                  }'
              py: |
                import os
                from groq import Groq

                client = Groq(
                    api_key=os.environ.get("GROQ_API_KEY"),  # This is the default and can be omitted
                )
                batch = client.batches.create(
                    completion_window="24h",
                    endpoint="/v1/chat/completions",
                    input_file_id="file_01jh6x76wtemjr74t1fh0faj5t",
                )
                print(batch.id)
              js: |
                import Groq from 'groq-sdk';

                const client = new Groq({
                  apiKey: process.env['GROQ_API_KEY'], // This is the default and can be omitted
                });

                async function main() {
                  const batch = await client.batches.create({
                    completion_window: "24h",
                    endpoint: "/v1/chat/completions",
                    input_file_id: "file_01jh6x76wtemjr74t1fh0faj5t",
                  });
                  console.log(batch.id);
                }

                main();
            response: |
              {
                "id": "batch_01jh6xa7reempvjyh6n3yst2zw",
                "object": "batch",
                "endpoint": "/v1/chat/completions",
                "errors": null,
                "input_file_id": "file_01jh6x76wtemjr74t1fh0faj5t",
                "completion_window": "24h",
                "status": "validating",
                "output_file_id": null,
                "error_file_id": null,
                "finalizing_at": null,
                "failed_at": null,
                "expired_at": null,
                "cancelled_at": null,
                "request_counts": {
                  "total": 0,
                  "completed": 0,
                  "failed": 0
                },
                "metadata": null,
                "created_at": 1736472600,
                "expires_at": 1736559000,
                "cancelling_at": null,
                "completed_at": null,
                "in_progress_at": null
              }
    get:
      operationId: listBatches
      tags:
        - Batch
      summary: List your organization's batches.
      responses:
        '200':
          description: Batch listed successfully.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ListBatchesResponse'
      x-groq-metadata:
        returns: A list of batches
        examples:
          - title: Default
            request:
              curl: |
                curl https://api.groq.com/openai/v1/batches \
                  -H "Authorization: Bearer $GROQ_API_KEY" \
                  -H "Content-Type: application/json"
              py: |
                import os
                from groq import Groq

                client = Groq(
                    api_key=os.environ.get("GROQ_API_KEY"),  # This is the default and can be omitted
                )
                batch_list = client.batches.list()
                print(batch_list.data)
              js: |
                import Groq from 'groq-sdk';

                const client = new Groq({
                  apiKey: process.env['GROQ_API_KEY'], // This is the default and can be omitted
                });

                async function main() {
                  const batchList = await client.batches.list();
                  console.log(batchList.data);
                }

                main();
            response: |
              {
                "object": "list",
                "data": [
                  {
                    "id": "batch_01jh6xa7reempvjyh6n3yst2zw",
                    "object": "batch",
                    "endpoint": "/v1/chat/completions",
                    "errors": null,
                    "input_file_id": "file_01jh6x76wtemjr74t1fh0faj5t",
                    "completion_window": "24h",
                    "status": "validating",
                    "output_file_id": null,
                    "error_file_id": null,
                    "finalizing_at": null,
                    "failed_at": null,
                    "expired_at": null,
                    "cancelled_at": null,
                    "request_counts": {
                      "total": 0,
                      "completed": 0,
                      "failed": 0
                    },
                    "metadata": null,
                    "created_at": 1736472600,
                    "expires_at": 1736559000,
                    "cancelling_at": null,
                    "completed_at": null,
                    "in_progress_at": null
                  }
                ]
              }
  /openai/v1/batches/{batch_id}:
    get:
      operationId: retrieveBatch
      tags:
        - Batch
      summary: Retrieves a batch.
      parameters:
        - in: path
          name: batch_id
          required: true
          schema:
            type: string
          description: The ID of the batch to retrieve.
      responses:
        '200':
          description: Batch retrieved successfully.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Batch'
      x-groq-metadata:
        returns: A batch object.
        examples:
          - title: Default
            request:
              curl: |
                curl https://api.groq.com/openai/v1/batches/batch_01jh6xa7reempvjyh6n3yst2zw \
                  -H "Authorization: Bearer $GROQ_API_KEY" \
                  -H "Content-Type: application/json"
              py: |
                import os
                from groq import Groq

                client = Groq(
                    api_key=os.environ.get("GROQ_API_KEY"),  # This is the default and can be omitted
                )
                batch = client.batches.retrieve(
                    "batch_01jh6xa7reempvjyh6n3yst2zw",
                )
                print(batch.id)
              js: |
                import Groq from 'groq-sdk';

                const client = new Groq({
                  apiKey: process.env['GROQ_API_KEY'], // This is the default and can be omitted
                });

                async function main() {
                  const batch = await client.batches.retrieve("batch_01jh6xa7reempvjyh6n3yst2zw");
                  console.log(batch.id);
                }

                main();
            response: |
              {
                "id": "batch_01jh6xa7reempvjyh6n3yst2zw",
                "object": "batch",
                "endpoint": "/v1/chat/completions",
                "errors": null,
                "input_file_id": "file_01jh6x76wtemjr74t1fh0faj5t",
                "completion_window": "24h",
                "status": "validating",
                "output_file_id": null,
                "error_file_id": null,
                "finalizing_at": null,
                "failed_at": null,
                "expired_at": null,
                "cancelled_at": null,
                "request_counts": {
                  "total": 0,
                  "completed": 0,
                  "failed": 0
                },
                "metadata": null,
                "created_at": 1736472600,
                "expires_at": 1736559000,
                "cancelling_at": null,
                "completed_at": null,
                "in_progress_at": null
              }
  /openai/v1/batches/{batch_id}/cancel:
    post:
      operationId: cancelBatch
      tags:
        - Batch
      summary: Cancels a batch.
      parameters:
        - in: path
          name: batch_id
          required: true
          schema:
            type: string
          description: The ID of the batch to cancel.
      responses:
        '200':
          description: Batch cancelled successfully.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Batch'
      x-groq-metadata:
        returns: A batch object.
        examples:
          - title: Default
            request:
              curl: |
                curl -X POST https://api.groq.com/openai/v1/batches/batch_01jh6xa7reempvjyh6n3yst2zw/cancel \
                  -H "Authorization: Bearer $GROQ_API_KEY" \
                  -H "Content-Type: application/json"
              py: |
                import os
                from groq import Groq

                client = Groq(
                    api_key=os.environ.get("GROQ_API_KEY"),  # This is the default and can be omitted
                )
                batch = client.batches.cancel(
                    "batch_01jh6xa7reempvjyh6n3yst2zw",
                )
                print(batch.id)
              js: |
                import Groq from 'groq-sdk';

                const client = new Groq({
                  apiKey: process.env['GROQ_API_KEY'], // This is the default and can be omitted
                });

                async function main() {
                  const batch = await client.batches.cancel("batch_01jh6xa7reempvjyh6n3yst2zw");
                  console.log(batch.id);
                }

                main();
            response: |
              {
                "id": "batch_01jh6xa7reempvjyh6n3yst2zw",
                "object": "batch",
                "endpoint": "/v1/chat/completions",
                "errors": null,
                "input_file_id": "file_01jh6x76wtemjr74t1fh0faj5t",
                "completion_window": "24h",
                "status": "cancelling",
                "output_file_id": null,
                "error_file_id": null,
                "finalizing_at": null,
                "failed_at": null,
                "expired_at": null,
                "cancelled_at": null,
                "request_counts": {
                  "total": 0,
                  "completed": 0,
                  "failed": 0
                },
                "metadata": null,
                "created_at": 1736472600,
                "expires_at": 1736559000,
                "cancelling_at": null,
                "completed_at": null,
                "in_progress_at": null
              }
  /openai/v1/chat/completions:
    post:
      operationId: createChatCompletion
      tags:
        - Chat
      summary: Creates a model response for the given chat conversation.
      requestBody:
        required: true
        description: The chat prompt and parameters
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CreateChatCompletionRequest'
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CreateChatCompletionResponse'
      x-groq-metadata:
        returns: >-
          Returns a [chat completion](/docs/api-reference#chat-create) object, or a streamed sequence of [chat
          completion chunk](/docs/api-reference#chat-create) objects if the request is streamed.
        examples:
          - title: Default
            request:
              py: |
                import os

                from groq import Groq

                client = Groq(
                    # This is the default and can be omitted
                    api_key=os.environ.get("GROQ_API_KEY"),
                )

                chat_completion = client.chat.completions.create(
                    messages=[
                        {
                            "role": "system",
                            "content": "You are a helpful assistant."
                        },
                        {
                            "role": "user",
                            "content": "Explain the importance of fast language models",
                        }
                    ],
                    model="llama-3.3-70b-versatile",
                )

                print(chat_completion.choices[0].message.content)
              js: |
                import Groq from "groq-sdk";

                const groq = new Groq({ apiKey: process.env.GROQ_API_KEY });

                async function main() {
                  const completion = await groq.chat.completions
                    .create({
                      messages: [
                        {
                          role: "user",
                          content: "Explain the importance of fast language models",
                        },
                      ],
                      model: "llama-3.3-70b-versatile",
                    })
                  console.log(completion.choices[0].message.content);
                }

                main();
              curl: |
                curl https://api.groq.com/openai/v1/chat/completions -s \
                -H "Content-Type: application/json" \
                -H "Authorization: Bearer $GROQ_API_KEY" \
                -d '{
                  "model": "llama-3.3-70b-versatile",
                  "messages": [{
                      "role": "user",
                      "content": "Explain the importance of fast language models"
                  }]
                }'
            response: |
              {
                "id": "chatcmpl-f51b2cd2-bef7-417e-964e-a08f0b513c22",
                "object": "chat.completion",
                "created": 1730241104,
                "model": "openai/gpt-oss-20b",
                "choices": [
                  {
                    "index": 0,
                    "message": {
                      "role": "assistant",
                      "content": "Fast language models have gained significant attention in recent years due to their ability to process and generate human-like text quickly and efficiently. The importance of fast language models can be understood from their potential applications and benefits:\n\n1. **Real-time Chatbots and Conversational Interfaces**: Fast language models enable the development of chatbots and conversational interfaces that can respond promptly to user queries, making them more engaging and useful.\n2. **Sentiment Analysis and Opinion Mining**: Fast language models can quickly analyze text data to identify sentiments, opinions, and emotions, allowing for improved customer service, market research, and opinion mining.\n3. **Language Translation and Localization**: Fast language models can quickly translate text between languages, facilitating global communication and enabling businesses to reach a broader audience.\n4. **Text Summarization and Generation**: Fast language models can summarize long documents or even generate new text on a given topic, improving information retrieval and processing efficiency.\n5. **Named Entity Recognition and Information Extraction**: Fast language models can rapidly recognize and extract specific entities, such as names, locations, and organizations, from unstructured text data.\n6. **Recommendation Systems**: Fast language models can analyze large amounts of text data to personalize product recommendations, improve customer experience, and increase sales.\n7. **Content Generation for Social Media**: Fast language models can quickly generate engaging content for social media platforms, helping businesses maintain a consistent online presence and increasing their online visibility.\n8. **Sentiment Analysis for Stock Market Analysis**: Fast language models can quickly analyze social media posts, news articles, and other text data to identify sentiment trends, enabling financial analysts to make more informed investment decisions.\n9. **Language Learning and Education**: Fast language models can provide instant feedback and adaptive language learning, making language education more effective and engaging.\n10. **Domain-Specific Knowledge Extraction**: Fast language models can quickly extract relevant information from vast amounts of text data, enabling domain experts to focus on high-level decision-making rather than manual information gathering.\n\nThe benefits of fast language models include:\n\n* **Increased Efficiency**: Fast language models can process large amounts of text data quickly, reducing the time and effort required for tasks such as sentiment analysis, entity recognition, and text summarization.\n* **Improved Accuracy**: Fast language models can analyze and learn from large datasets, leading to more accurate results and more informed decision-making.\n* **Enhanced User Experience**: Fast language models can enable real-time interactions, personalized recommendations, and timely responses, improving the overall user experience.\n* **Cost Savings**: Fast language models can automate many tasks, reducing the need for manual labor and minimizing costs associated with data processing and analysis.\n\nIn summary, fast language models have the potential to transform various industries and applications by providing fast, accurate, and efficient language processing capabilities."
                    },
                    "logprobs": null,
                    "finish_reason": "stop"
                  }
                ],
                "usage": {
                  "queue_time": 0.037493756,
                  "prompt_tokens": 18,
                  "prompt_time": 0.000680594,
                  "completion_tokens": 556,
                  "completion_time": 0.463333333,
                  "total_tokens": 574,
                  "total_time": 0.464013927
                },
                "system_fingerprint": "fp_179b0f92c9",
                "x_groq": { "id": "req_01jbd6g2qdfw2adyrt2az8hz4w" }
              }
  /openai/v1/embeddings:
    post:
      operationId: createEmbedding
      tags:
        - Embeddings
      summary: Creates an embedding vector representing the input text.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CreateEmbeddingRequest'
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CreateEmbeddingResponse'
  /openai/v1/files:
    get:
      operationId: listFiles
      tags:
        - Files
      summary: Returns a list of files.
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ListFilesResponse'
      x-groq-metadata:
        returns: A list of [File](/docs/api-reference#files-upload) objects.
        examples:
          - title: Default
            request:
              curl: |
                curl https://api.groq.com/openai/v1/files \
                  -H "Authorization: Bearer $GROQ_API_KEY" \
                  -H "Content-Type: application/json"
              py: |
                import os
                from groq import Groq

                client = Groq(
                    api_key=os.environ.get("GROQ_API_KEY"),  # This is the default and can be omitted
                )
                file_list = client.files.list()
                print(file_list.data)
              js: |
                import Groq from 'groq-sdk';

                const client = new Groq({
                  apiKey: process.env['GROQ_API_KEY'], // This is the default and can be omitted
                });

                async function main() {
                  const fileList = await client.files.list();
                  console.log(fileList.data);
                }

                main();
            response: |
              {
                "object": "list",
                "data": [
                  {
                    "id": "file_01jh6x76wtemjr74t1fh0faj5t",
                    "object": "file",
                    "bytes": 966,
                    "created_at": 1736472501,
                    "filename": "batch_file.jsonl",
                    "purpose": "batch"
                  }
                ]
              }
    post:
      operationId: uploadFile
      tags:
        - Files
      summary: >
        Upload a file that can be used across various endpoints.


        The Batch API only supports `.jsonl` files up to 100 MB in size. The input also has a specific
        required [format](/docs/batch).


        Please contact us if you need to increase these storage limits.
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              $ref: '#/components/schemas/CreateFileRequest'
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/File'
      x-groq-metadata:
        returns: The uploaded File object.
        examples:
          - title: Default
            request:
              curl: |
                curl https://api.groq.com/openai/v1/files \
                  -H "Authorization: Bearer $GROQ_API_KEY" \
                  -F purpose="batch" \
                  -F "file=@batch_file.jsonl"
              py: |
                import os
                import requests # pip install requests first!

                def upload_file_to_groq(api_key, file_path):
                    url = "https://api.groq.com/openai/v1/files"

                    headers = {
                        "Authorization": f"Bearer {api_key}"
                    }

                    # Prepare the file and form data
                    files = {
                        "file": ("batch_file.jsonl", open(file_path, "rb"))
                    }

                    data = {
                        "purpose": "batch"
                    }

                    # Make the POST request
                    response = requests.post(url, headers=headers, files=files, data=data)

                    return response.json()

                # Usage example
                api_key = os.environ.get("GROQ_API_KEY")
                file_path = "batch_file.jsonl"  # Path to your JSONL file

                try:
                    result = upload_file_to_groq(api_key, file_path)
                    print(result)
                except Exception as e:
                    print(f"Error: {e}")
              js: >
                import Groq from 'groq-sdk';


                const client = new Groq({
                  apiKey: process.env['GROQ_API_KEY'], // This is the default and can be omitted
                });


                const fileContent = '{"custom_id": "request-1", "method": "POST", "url":
                "/v1/chat/completions", "body": {"model": "llama-3.1-8b-instant", "messages": [{"role":
                "user", "content": "Explain the importance of fast language models"}]}}\n';


                async function main() {
                  const blob = new Blob([fileContent]);
                  const file = new File([blob], 'batch.jsonl');

                  const createdFile = await client.files.create({ file: file, purpose: 'batch' });
                  console.log(createdFile.id);
                }


                main();
            response: |
              {
                "id": "file_01jh6x76wtemjr74t1fh0faj5t",
                "object": "file",
                "bytes": 966,
                "created_at": 1736472501,
                "filename": "batch_file.jsonl",
                "purpose": "batch"
              }
  /openai/v1/files/{file_id}:
    delete:
      operationId: deleteFile
      tags:
        - Files
      summary: Delete a file.
      parameters:
        - in: path
          name: file_id
          required: true
          schema:
            type: string
          description: The ID of the file to use for this request.
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DeleteFileResponse'
      x-groq-metadata:
        returns: A deleted file response object.
        examples:
          - title: Default
            request:
              curl: |
                curl -X DELETE https://api.groq.com/openai/v1/files/file_01jh6x76wtemjr74t1fh0faj5t \
                  -H "Authorization: Bearer $GROQ_API_KEY" \
                  -H "Content-Type: application/json"
              py: |
                import os
                from groq import Groq

                client = Groq(
                    api_key=os.environ.get("GROQ_API_KEY"),  # This is the default and can be omitted
                )
                file_delete = client.files.delete(
                    "file_01jh6x76wtemjr74t1fh0faj5t",
                )
                print(file_delete)
              js: |
                import Groq from 'groq-sdk';

                const client = new Groq({
                  apiKey: process.env['GROQ_API_KEY'], // This is the default and can be omitted
                });

                async function main() {
                  const fileDelete = await client.files.delete("file_01jh6x76wtemjr74t1fh0faj5t");
                  console.log(fileDelete);
                }

                main();
            response: |
              {
                "id": "file_01jh6x76wtemjr74t1fh0faj5t",
                "object": "file",
                "deleted": true
              }
    get:
      operationId: retrieveFile
      tags:
        - Files
      summary: Returns information about a file.
      parameters:
        - name: file_id
          in: path
          description: The file to retrieve
          required: true
          schema:
            type: string
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/File'
      x-groq-metadata:
        returns: A file object.
        examples:
          - title: Default
            request:
              curl: |
                curl https://api.groq.com/openai/v1/files/file_01jh6x76wtemjr74t1fh0faj5t \
                  -H "Authorization: Bearer $GROQ_API_KEY" \
                  -H "Content-Type: application/json"
              py: |
                import os
                from groq import Groq

                client = Groq(
                    api_key=os.environ.get("GROQ_API_KEY"),  # This is the default and can be omitted
                )
                file = client.files.info(
                    "file_01jh6x76wtemjr74t1fh0faj5t",
                )
                print(file)
              js: |
                import Groq from 'groq-sdk';

                const client = new Groq({
                  apiKey: process.env['GROQ_API_KEY'], // This is the default and can be omitted
                });

                async function main() {
                    const file = await client.files.info('file_01jh6x76wtemjr74t1fh0faj5t');
                    console.log(file);
                }

                main();
            response: |
              {
                "id": "file_01jh6x76wtemjr74t1fh0faj5t",
                "object": "file",
                "bytes": 966,
                "created_at": 1736472501,
                "filename": "batch_file.jsonl",
                "purpose": "batch"
              }
  /openai/v1/files/{file_id}/content:
    get:
      operationId: downloadFile
      tags:
        - Files
      summary: Returns the contents of the specified file.
      parameters:
        - in: path
          name: file_id
          required: true
          schema:
            type: string
          description: The ID of the file to use for this request.
      responses:
        '200':
          description: OK
          content:
            application/octet-stream:
              schema:
                type: string
                format: binary
      x-groq-metadata:
        returns: The file content
        examples:
          - title: Default
            request:
              curl: |
                curl https://api.groq.com/openai/v1/files/file_01jh6x76wtemjr74t1fh0faj5t/content \
                  -H "Authorization: Bearer $GROQ_API_KEY" \
                  -H "Content-Type: application/json"
              py: |
                import os
                from groq import Groq

                client = Groq(
                    api_key=os.environ.get("GROQ_API_KEY"),  # This is the default and can be omitted
                )
                response = client.files.content(
                    "file_01jh6x76wtemjr74t1fh0faj5t",
                )
                print(response)
              js: |
                import Groq from 'groq-sdk';

                const client = new Groq({
                  apiKey: process.env['GROQ_API_KEY'], // This is the default and can be omitted
                });

                async function main() {
                    const response = await client.files.content('file_01jh6x76wtemjr74t1fh0faj5t');
                    console.log(response);
                }

                main();
  /v1/fine_tunings:
    get:
      operationId: listFineTunings
      summary: >-
        Lists all previously created fine tunings. This endpoint is in closed beta. [Contact
        us](https://groq.com/contact) for more information.
      tags:
        - Fine Tuning
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ListFineTuningsResponse'
      x-groq-metadata:
        returns: The list of fine tunes
        examples:
          - title: Default
            request:
              curl: |
                curl https://api.groq.com/v1/fine_tunings -s \
                    -H "Content-Type: application/json" \
                    -H "Authorization: Bearer $GROQ_API_KEY"
              js: |
                import Groq from "groq-sdk";

                const groq = new Groq({ apiKey: process.env.GROQ_API_KEY });

                async function main() {
                    const fineTunings = await groq.fine_tunings.list();
                    console.log(fineTunings);
                }

                main();
              py: |
                import os

                from groq import Groq

                client = Groq(
                    # This is the default and can be omitted
                    api_key=os.environ.get("GROQ_API_KEY"),
                )

                fine_tunings = client.fine_tunings.list()

                print(fine_tunings)
            response: |
              {
                  "object": "list",
                  "data": [
                      {
                          "id": "string",
                          "name": "string",
                          "base_model": "string",
                          "type": "string",
                          "input_file_id": "string",
                          "created_at": 0,
                          "fine_tuned_model": "string"
                      }
                  ]
              }
    post:
      operationId: createFineTuning
      summary: >-
        Creates a new fine tuning for the already uploaded files This endpoint is in closed beta. [Contact
        us](https://groq.com/contact) for more information.
      tags:
        - Fine Tuning
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CreateFineTuningRequest'
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ReadFineTuningResponse'
      x-groq-metadata:
        returns: The newly created fine tune
        examples:
          - title: Default
            request:
              curl: |
                curl https://api.groq.com/v1/fine_tunings -s \
                    -H "Content-Type: application/json" \
                    -H "Authorization: Bearer $GROQ_API_KEY" \
                    -d '{
                        "input_file_id": "<file-id>",
                        "name": "test-1",
                        "type": "lora",
                        "base_model": "llama-3.1-8b-instant"
                    }'
              js: |
                import Groq from "groq-sdk";

                const groq = new Groq({ apiKey: process.env.GROQ_API_KEY });

                async function main() {
                    const fineTunings = await groq.fine_tunings.create({
                        input_file_id: "<file-id>",
                        name: "test-1",
                        type: "lora",
                        base_model: "llama-3.1-8b-instant"
                    });
                    console.log(fineTunings);
                }

                main();
              py: |
                import os

                from groq import Groq

                client = Groq(
                    # This is the default and can be omitted
                    api_key=os.environ.get("GROQ_API_KEY"),
                )

                fine_tunings = client.fine_tunings.create(
                    input_file_id="<file-id>",
                    name="test-1",
                    type="lora",
                    base_model="llama-3.1-8b-instant"
                )

                print(fine_tunings)
            response: |
              {
                  "id": "string",
                  "object": "object",
                  "data": {
                      "id": "string",
                      "name": "string",
                      "base_model": "string",
                      "type": "string",
                      "input_file_id": "string",
                      "created_at": 0,
                      "fine_tuned_model": "string"
                  }
              }
  /v1/fine_tunings/{id}:
    delete:
      operationId: deleteFineTuning
      summary: >-
        Deletes an existing fine tuning by id This endpoint is in closed beta. [Contact
        us](https://groq.com/contact) for more information.
      tags:
        - Fine Tuning
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DeleteFineTuningResponse'
      parameters:
        - name: id
          required: true
          in: path
          schema:
            type: string
      x-groq-metadata:
        returns: A confirmation of the deleted fine tune
        examples:
          - title: Default
            request:
              curl: |
                curl -X DELETE https://api.groq.com/v1/fine_tunings/:id -s \
                    -H "Content-Type: application/json" \
                    -H "Authorization: Bearer $GROQ_API_KEY"
              js: |
                import Groq from "groq-sdk";

                const groq = new Groq({ apiKey: process.env.GROQ_API_KEY });

                async function main() {
                    await groq.fine_tunings.delete({id: "<id>"});
                }

                main();
              py: |
                import os

                from groq import Groq

                client = Groq(
                    # This is the default and can be omitted
                    api_key=os.environ.get("GROQ_API_KEY"),
                )

                client.fine_tunings.delete(id="<id>")
            response: |
              {
                  "id": "string",
                  "object": "fine_tuning",
                  "deleted": true
              }
    get:
      operationId: getFineTuning
      summary: >-
        Retrieves an existing fine tuning by id This endpoint is in closed beta. [Contact
        us](https://groq.com/contact) for more information.
      tags:
        - Fine Tuning
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ReadFineTuningResponse'
      parameters:
        - name: id
          required: true
          in: path
          schema:
            type: string
      x-groq-metadata:
        returns: A fine tune metadata object
        examples:
          - title: Default
            request:
              curl: |
                curl https://api.groq.com/v1/fine_tunings/:id -s \
                    -H "Content-Type: application/json" \
                    -H "Authorization: Bearer $GROQ_API_KEY"
              js: |
                import Groq from "groq-sdk";

                const groq = new Groq({ apiKey: process.env.GROQ_API_KEY });

                async function main() {
                    const fineTuning = await groq.fine_tunings.get({id: "<id>"});
                    console.log(fineTuning);
                }

                main();
              py: |
                import os

                from groq import Groq

                client = Groq(
                    # This is the default and can be omitted
                    api_key=os.environ.get("GROQ_API_KEY"),
                )

                fine_tuning = client.fine_tunings.get(id="<id>")

                print(fine_tuning)
            response: |
              {
                  "id": "string",
                  "object": "object",
                  "data": {
                      "id": "string",
                      "name": "string",
                      "base_model": "string",
                      "type": "string",
                      "input_file_id": "string",
                      "created_at": 0,
                      "fine_tuned_model": "string"
                  }
              }
  /openai/v1/models:
    get:
      operationId: listModels
      tags:
        - Models
      summary: List all available [models](https://console.groq.com/docs/models).
      description: get all available models
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ListModelsResponse'
      x-groq-metadata:
        returns: A list of model objects.
        examples:
          - title: Default
            request:
              curl: |
                curl https://api.groq.com/openai/v1/models \
                -H "Authorization: Bearer $GROQ_API_KEY"
              js: |
                import Groq from "groq-sdk";

                const groq = new Groq({ apiKey: process.env.GROQ_API_KEY });

                async function main() {
                  const models = await groq.models.list();
                  console.log(models);
                }

                main();
              py: |
                import os
                from groq import Groq

                client = Groq(
                    # This is the default and can be omitted
                    api_key=os.environ.get("GROQ_API_KEY"),
                )

                models = client.models.list()

                print(models)
            response: |
              {
                "object": "list",
                "data": [
                  {
                    "id": "gemma2-9b-it",
                    "object": "model",
                    "created": 1693721698,
                    "owned_by": "Google",
                    "active": true,
                    "context_window": 8192,
                    "public_apps": null
                  },
                  {
                    "id": "llama3-8b-8192",
                    "object": "model",
                    "created": 1693721698,
                    "owned_by": "Meta",
                    "active": true,
                    "context_window": 8192,
                    "public_apps": null
                  },
                  {
                    "id": "llama3-70b-8192",
                    "object": "model",
                    "created": 1693721698,
                    "owned_by": "Meta",
                    "active": true,
                    "context_window": 8192,
                    "public_apps": null
                  },
                  {
                    "id": "whisper-large-v3-turbo",
                    "object": "model",
                    "created": 1728413088,
                    "owned_by": "OpenAI",
                    "active": true,
                    "context_window": 448,
                    "public_apps": null
                  },
                  {
                    "id": "whisper-large-v3",
                    "object": "model",
                    "created": 1693721698,
                    "owned_by": "OpenAI",
                    "active": true,
                    "context_window": 448,
                    "public_apps": null
                  },
                  {
                    "id": "llama-guard-3-8b",
                    "object": "model",
                    "created": 1693721698,
                    "owned_by": "Meta",
                    "active": true,
                    "context_window": 8192,
                    "public_apps": null
                  },
                  {
                    "id": "distil-whisper-large-v3-en",
                    "object": "model",
                    "created": 1693721698,
                    "owned_by": "Hugging Face",
                    "active": true,
                    "context_window": 448,
                    "public_apps": null
                  },
                  {
                    "id": "llama-3.1-8b-instant",
                    "object": "model",
                    "created": 1693721698,
                    "owned_by": "Meta",
                    "active": true,
                    "context_window": 131072,
                    "public_apps": null
                  }
                ]
              }
  /openai/v1/models/{model}:
    get:
      operationId: retrieveModel
      tags:
        - Models
      summary: Get detailed information about a [model](https://console.groq.com/docs/models).
      description: Get a specific model
      parameters:
        - name: model
          in: path
          description: The model to get
          required: true
          schema:
            type: string
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Model'
      x-groq-metadata:
        returns: A model object.
        examples:
          - title: Default
            request:
              curl: |
                curl https://api.groq.com/openai/v1/models/llama-3.3-70b-versatile \
                -H "Authorization: Bearer $GROQ_API_KEY"
              js: |
                import Groq from "groq-sdk";

                const groq = new Groq({ apiKey: process.env.GROQ_API_KEY });

                async function main() {
                  const model = await groq.models.retrieve("llama-3.3-70b-versatile");
                  console.log(model);
                }

                main();
              py: |
                import os
                from groq import Groq

                client = Groq(
                    # This is the default and can be omitted
                    api_key=os.environ.get("GROQ_API_KEY"),
                )

                model = client.models.retrieve("llama-3.3-70b-versatile")

                print(model)
            response: |
              {
                "id": "llama3-8b-8192",
                "object": "model",
                "created": 1693721698,
                "owned_by": "Meta",
                "active": true,
                "context_window": 8192,
                "public_apps": null,
                "max_completion_tokens": 8192
              }
    delete:
      operationId: deleteModel
      tags:
        - Models
      summary: Delete model
      description: Delete a model
      parameters:
        - in: path
          name: model
          description: The model to delete
          required: true
          schema:
            type: string
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DeleteModelResponse'
  /openai/v1/reranking:
    post:
      operationId: createReranking
      tags:
        - Reranking
      summary: Reranks documents based on their relevance to a query.
      description: |
        Given a query and a list of documents, returns the documents ranked by their relevance to the query.
        The documents are scored and sorted in descending order of relevance.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/RerankingRequest'
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/RerankingResponse'
      x-groq-metadata:
        returns: |
          A list of documents sorted by relevance score in descending order. 
          Scores range from 0.0 to 1.0, where higher scores indicate greater relevance to the query.
        examples:
          - title: Basic Reranking
            request:
              curl: |
                curl https://api.groq.com/openai/v1/reranking \
                  -H "Authorization: Bearer $GROQ_API_KEY" \
                  -H "Content-Type: application/json" \
                  -d '{
                    "model": "qwen3-reranker-4b",
                    "query": "artificial intelligence",
                    "docs": [
                      "Machine learning is a subset of AI",
                      "The weather is nice today",
                      "Deep learning uses neural networks"
                    ]
                  }'
              py: |
                import os
                from groq import Groq

                client = Groq(api_key=os.environ.get("GROQ_API_KEY"))

                reranking = client.reranking.create(
                    model="qwen3-reranker-4b",
                    query="artificial intelligence",
                    docs=[
                        "Machine learning is a subset of AI",
                        "The weather is nice today", 
                        "Deep learning uses neural networks"
                    ]
                )
                print(reranking.results)
              js: |
                import Groq from 'groq-sdk';

                const client = new Groq({
                  apiKey: process.env['GROQ_API_KEY'],
                });

                async function main() {
                  const reranking = await client.reranking.create({
                    model: 'qwen3-reranker-4b',
                    query: 'artificial intelligence',
                    docs: [
                      'Machine learning is a subset of AI',
                      'The weather is nice today',
                      'Deep learning uses neural networks'
                    ]
                  });
                  console.log(reranking.results);
                }
                main();
            response: |
              {
                "results": [
                  {
                    "doc": "Machine learning is a subset of AI",
                    "score": 0.92
                  },
                  {
                    "doc": "Deep learning uses neural networks", 
                    "score": 0.87
                  },
                  {
                    "doc": "The weather is nice today",
                    "score": 0.23
                  }
                ]
              }
          - title: Reranking with Custom Instruction
            request:
              json: |
                {
                  "model": "qwen3-reranker-4b",
                  "query": "climate change effects",
                  "docs": [
                    "Global warming causes sea level rise",
                    "Electric cars reduce emissions",
                    "Renewable energy is growing fast"
                  ],
                  "instruction": "Find documents specifically about environmental impacts"
                }
            response: |
              {
                "results": [
                  {
                    "doc": "Global warming causes sea level rise",
                    "score": 0.95
                  },
                  {
                    "doc": "Electric cars reduce emissions",
                    "score": 0.78
                  },
                  {
                    "doc": "Renewable energy is growing fast",
                    "score": 0.65
                  }
                ]
              }
  /openai/v1/responses:
    post:
      operationId: createResponse
      tags:
        - Responses
      summary: Creates a model response for the given input.
      requestBody:
        required: true
        description: The input prompt and parameters
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CreateResponseRequest'
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CreateResponseResponse'
      x-groq-metadata:
        returns: >-
          Returns a [response](/docs/api-reference#responses-create) object, or a streamed sequence of
          [response events](/docs/api-reference#responses-streaming) if the request is streamed.
        examples:
          - title: Default
            request:
              curl: |
                curl https://api.groq.com/openai/v1/responses -s \
                -H "Content-Type: application/json" \
                -H "Authorization: Bearer $GROQ_API_KEY" \
                -d '{
                  "model": "openai/gpt-oss-120b",
                  "input": "Tell me a three sentence bedtime story about a unicorn."
                }'
            response: |
              {
                "id": "resp_01k1x6w9ane6d8rfxm05cb45yk",
                "object": "response",
                "status": "completed",
                "created_at": 1754400695,
                "output": [
                  {
                    "type": "message",
                    "id": "msg_01k1x6w9ane6eb0650crhawwyy",
                    "status": "completed",
                    "role": "assistant",
                    "content": [
                      {
                        "type": "output_text",
                        "text": "When the stars blinked awake, Luna the unicorn curled her mane and whispered wishes to the sleeping pine trees. She galloped through a field of moonlit daisies, gathering dew like tiny silver pearls. With a gentle sigh, she tucked her hooves beneath a silver cloud so the world slept softly, dreaming of her gentle hooves until the morning.",
                        "annotations": []
                      }
                    ]
                  }
                ],
                "previous_response_id": null,
                "model": "llama-3.3-70b-versatile",
                "reasoning": {
                  "effort": null,
                  "summary": null
                },
                "max_output_tokens": null,
                "instructions": null,
                "text": {
                  "format": {
                    "type": "text"
                  }
                },
                "tools": [],
                "tool_choice": "auto",
                "truncation": "disabled",
                "metadata": {},
                "temperature": 1,
                "top_p": 1,
                "user": null,
                "service_tier": "default",
                "error": null,
                "incomplete_details": null,
                "usage": {
                  "input_tokens": 82,
                  "input_tokens_details": {
                    "cached_tokens": 0
                  },
                  "output_tokens": 266,
                  "output_tokens_details": {
                    "reasoning_tokens": 0
                  },
                  "total_tokens": 348
                },
                "parallel_tool_calls": true,
                "store": false
              }
components:
  securitySchemes:
    api_key:
      type: http
      scheme: bearer
      bearerFormat: apiKey
  schemas:
    Error:
      type: object
      properties:
        message:
          type: string
          nullable: false
        type:
          type: string
          nullable: false
        param:
          type: string
          nullable: true
        code:
          type: string
          nullable: true
        failed_generation:
          type: string
          nullable: true
        schema_path:
          type: string
          nullable: true
        schema_path_segments:
          type: array
          description: Segments of the schema path relevant to validation errors.
          items:
            type: string
        schema_kind:
          type: string
          nullable: true
        schema_code:
          type: string
          nullable: true
        debug:
          $ref: '#/components/schemas/DebugData'
      required:
        - type
        - message
    ErrorResponse:
      type: object
      properties:
        error:
          $ref: '#/components/schemas/Error'
      required:
        - error
    CreateSpeechRequest:
      type: object
      additionalProperties: false
      properties:
        model:
          description: |
            One of the [available TTS models](/docs/text-to-speech).
          anyOf:
            - type: string
            - type: string
              enum:
                - playai-tts
                - playai-tts-arabic
          example: playai-tts
        input:
          example: The quick brown fox jumped over the lazy dog
          type: string
          description: The text to generate audio for.
        voice:
          description: >-
            The voice to use when generating the audio. List of voices can be found
            [here](/docs/text-to-speech).
          type: string
          example: Fritz-PlayAI
        response_format:
          description: The format of the generated audio. Supported formats are `flac, mp3, mulaw, ogg, wav`.
          default: mp3
          type: string
          enum:
            - flac
            - mp3
            - mulaw
            - ogg
            - wav
        sample_rate:
          type: integer
          description: The sample rate for generated audio
          default: 48000
          example: 48000
          enum:
            - 8000
            - 16000
            - 22050
            - 24000
            - 32000
            - 44100
            - 48000
        speed:
          description: The speed of the generated audio.
          example: 1
          type: number
          default: 1
          minimum: 0.5
          maximum: 5
      required:
        - model
        - input
        - voice
    CreateTranscriptionRequest:
      type: object
      additionalProperties: false
      properties:
        file:
          description: >
            The audio file object (not file name) to transcribe, in one of these formats: flac, mp3, mp4,
            mpeg, mpga, m4a, ogg, wav, or webm.

            Either a file or a URL must be provided. Note that the file field is not supported in Batch API
            requests.
          type: string
          format: binary
        url:
          description: >
            The audio URL to translate/transcribe (supports Base64URL).

            Either a file or a URL must be provided. For Batch API requests, the URL field is required since
            the file field is not supported.
          type: string
        model:
          description: |
            ID of the model to use. `whisper-large-v3` and `whisper-large-v3-turbo` are currently available.
          example: whisper-large-v3-turbo
          anyOf:
            - type: string
            - type: string
              enum:
                - whisper-large-v3
                - whisper-large-v3-turbo
        language:
          description: >
            The language of the input audio. Supplying the input language in
            [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) format will improve accuracy
            and latency.
          anyOf:
            - type: string
            - type: string
              enum:
                - en
                - zh
                - de
                - es
                - ru
                - ko
                - fr
                - ja
                - pt
                - tr
                - pl
                - ca
                - nl
                - ar
                - sv
                - it
                - id
                - hi
                - fi
                - vi
                - he
                - uk
                - el
                - ms
                - cs
                - ro
                - da
                - hu
                - ta
                - 'no'
                - th
                - ur
                - hr
                - bg
                - lt
                - la
                - mi
                - ml
                - cy
                - sk
                - te
                - fa
                - lv
                - bn
                - sr
                - az
                - sl
                - kn
                - et
                - mk
                - br
                - eu
                - is
                - hy
                - ne
                - mn
                - bs
                - kk
                - sq
                - sw
                - gl
                - mr
                - pa
                - si
                - km
                - sn
                - yo
                - so
                - af
                - oc
                - ka
                - be
                - tg
                - sd
                - gu
                - am
                - yi
                - lo
                - uz
                - fo
                - ht
                - ps
                - tk
                - nn
                - mt
                - sa
                - lb
                - my
                - bo
                - tl
                - mg
                - as
                - tt
                - haw
                - ln
                - ha
                - ba
                - jv
                - su
                - yue
        prompt:
          description: >
            An optional text to guide the model's style or continue a previous audio segment. The
            [prompt](/docs/speech-text) should match the audio language.
          type: string
        response_format:
          description: |
            The format of the transcript output, in one of these options: `json`, `text`, or `verbose_json`.
          type: string
          enum:
            - json
            - text
            - verbose_json
          default: json
        temperature:
          description: >
            The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more
            random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the
            model will use [log probability](https://en.wikipedia.org/wiki/Log_probability) to automatically
            increase the temperature until certain thresholds are hit.
          type: number
          default: 0
        timestamp_granularities:
          description: >
            The timestamp granularities to populate for this transcription. `response_format` must be set
            `verbose_json` to use timestamp granularities. Either or both of these options are supported:
            `word`, or `segment`. Note: There is no additional latency for segment timestamps, but generating
            word timestamps incurs additional latency.
          type: array
          items:
            type: string
            enum:
              - word
              - segment
          default:
            - segment
      oneOf:
        - required:
            - file
        - required:
            - url
      required:
        - model
    CreateTranscriptionResponseJson:
      type: object
      description: Represents a transcription response returned by model, based on the provided input.
      properties:
        text:
          type: string
          description: The transcribed text.
      required:
        - text
    TranscriptionSegment:
      type: object
      properties:
        id:
          type: integer
          description: Unique identifier of the segment.
        seek:
          type: integer
          description: Seek offset of the segment.
        start:
          type: number
          format: float
          description: Start time of the segment in seconds.
        end:
          type: number
          format: float
          description: End time of the segment in seconds.
        text:
          type: string
          description: Text content of the segment.
        tokens:
          type: array
          items:
            type: integer
          description: Array of token IDs for the text content.
        temperature:
          type: number
          format: float
          description: Temperature parameter used for generating the segment.
        avg_logprob:
          type: number
          format: float
          description: Average logprob of the segment. If the value is lower than -1, consider the logprobs failed.
        compression_ratio:
          type: number
          format: float
          description: >-
            Compression ratio of the segment. If the value is greater than 2.4, consider the compression
            failed.
        no_speech_prob:
          type: number
          format: float
          description: >-
            Probability of no speech in the segment. If the value is higher than 1.0 and the `avg_logprob` is
            below -1, consider this segment silent.
        audio_text:
          type: string
          description: Transcribed text for the entire chunk
        token_scores:
          type: array
          items:
            type: number
            format: float
          description: Token-level scores.
        chunk_start:
          type: integer
          description: Start chunk timestamp.
        chunk_end:
          type: integer
          description: End chunk timestamp.
      required:
        - id
        - seek
        - start
        - end
        - text
        - tokens
    TranscriptionWord:
      type: object
      properties:
        word:
          type: string
          description: The text content of the word.
        start:
          type: number
          format: float
          description: Start time of the word in seconds.
        end:
          type: number
          format: float
          description: End time of the word in seconds.
      required:
        - word
        - start
        - end
    CreateTranscriptionResponseVerboseJson:
      type: object
      description: Represents a verbose json transcription response returned by model, based on the provided input.
      properties:
        language:
          type: string
          description: The language of the input audio.
        duration:
          type: string
          description: The duration of the input audio.
        text:
          type: string
          description: The transcribed text.
        words:
          type: array
          description: Extracted words and their corresponding timestamps.
          items:
            $ref: '#/components/schemas/TranscriptionWord'
        segments:
          type: array
          description: Segments of the transcribed text and their corresponding details.
          items:
            $ref: '#/components/schemas/TranscriptionSegment'
      required:
        - language
        - duration
        - text
    CreateTranslationRequest:
      type: object
      additionalProperties: false
      properties:
        file:
          description: >
            The audio file object (not file name) translate, in one of these formats: flac, mp3, mp4, mpeg,
            mpga, m4a, ogg, wav, or webm.
          type: string
          format: binary
        url:
          description: |
            The audio URL to translate/transcribe (supports Base64URL). Either file or url must be provided.
            When using the Batch API only url is supported.
          type: string
        model:
          description: |
            ID of the model to use. `whisper-large-v3` and `whisper-large-v3-turbo` are currently available.
          example: whisper-large-v3-turbo
          anyOf:
            - type: string
            - type: string
              enum:
                - whisper-large-v3
                - whisper-large-v3-turbo
        prompt:
          description: >
            An optional text to guide the model's style or continue a previous audio segment. The
            [prompt](/docs/guides/speech-to-text/prompting) should be in English.
          type: string
        response_format:
          description: |
            The format of the transcript output, in one of these options: `json`, `text`, or `verbose_json`.
          type: string
          enum:
            - json
            - text
            - verbose_json
          default: json
        temperature:
          description: >
            The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more
            random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the
            model will use [log probability](https://en.wikipedia.org/wiki/Log_probability) to automatically
            increase the temperature until certain thresholds are hit.
          type: number
          default: 0
      oneOf:
        - required:
            - file
        - required:
            - url
      required:
        - model
    CreateTranslationResponseJson:
      type: object
      properties:
        text:
          type: string
      required:
        - text
    CreateTranslationResponseVerboseJson:
      type: object
      properties:
        language:
          type: string
          description: The language of the output translation (always `english`).
        duration:
          type: string
          description: The duration of the input audio.
        text:
          type: string
          description: The translated text.
        segments:
          type: array
          description: Segments of the translated text and their corresponding details.
          items:
            $ref: '#/components/schemas/TranscriptionSegment'
      required:
        - language
        - duration
        - text
    Batch:
      type: object
      properties:
        id:
          type: string
        object:
          type: string
          enum:
            - batch
          description: The object type, which is always `batch`.
          x-stainless-const: true
        endpoint:
          type: string
          description: The API endpoint used by the batch.
        errors:
          type: object
          properties:
            object:
              type: string
              description: The object type, which is always `list`.
            data:
              type: array
              items:
                type: object
                properties:
                  code:
                    type: string
                    description: An error code identifying the error type.
                  message:
                    type: string
                    description: A human-readable message providing more details about the error.
                  param:
                    type: string
                    description: The name of the parameter that caused the error, if applicable.
                    nullable: true
                  line:
                    type: integer
                    description: The line number of the input file where the error occurred, if applicable.
                    nullable: true
        input_file_id:
          type: string
          description: The ID of the input file for the batch.
        completion_window:
          type: string
          description: The time frame within which the batch should be processed.
        status:
          type: string
          description: The current status of the batch.
          enum:
            - validating
            - failed
            - in_progress
            - finalizing
            - completed
            - expired
            - cancelling
            - cancelled
        output_file_id:
          type: string
          description: The ID of the file containing the outputs of successfully executed requests.
        error_file_id:
          type: string
          description: The ID of the file containing the outputs of requests with errors.
        created_at:
          type: integer
          description: The Unix timestamp (in seconds) for when the batch was created.
        in_progress_at:
          type: integer
          description: The Unix timestamp (in seconds) for when the batch started processing.
        expires_at:
          type: integer
          description: The Unix timestamp (in seconds) for when the batch will expire.
        finalizing_at:
          type: integer
          description: The Unix timestamp (in seconds) for when the batch started finalizing.
        completed_at:
          type: integer
          description: The Unix timestamp (in seconds) for when the batch was completed.
        failed_at:
          type: integer
          description: The Unix timestamp (in seconds) for when the batch failed.
        expired_at:
          type: integer
          description: The Unix timestamp (in seconds) for when the batch expired.
        cancelling_at:
          type: integer
          description: The Unix timestamp (in seconds) for when the batch started cancelling.
        cancelled_at:
          type: integer
          description: The Unix timestamp (in seconds) for when the batch was cancelled.
        request_counts:
          type: object
          properties:
            total:
              type: integer
              description: Total number of requests in the batch.
            completed:
              type: integer
              description: Number of requests that have been completed successfully.
            failed:
              type: integer
              description: Number of requests that have failed.
          required:
            - total
            - completed
            - failed
          description: The request counts for different statuses within the batch.
        metadata:
          description: >
            Set of key-value pairs that can be attached to an object. This can be useful for storing
            additional information about the object in a structured format.
          type: object
          nullable: true
      required:
        - id
        - object
        - endpoint
        - input_file_id
        - completion_window
        - status
        - created_at
    BatchRequestInput:
      type: object
      description: The per-line object of the batch input file
      properties:
        custom_id:
          type: string
          description: >-
            A developer-provided per-request id that will be used to match outputs to inputs. Must be unique
            for each request in a batch.
        method:
          type: string
          enum:
            - POST
          description: The HTTP method to be used for the request. Currently only `POST` is supported.
          x-stainless-const: true
        url:
          type: string
          description: >-
            The OpenAI API relative URL to be used for the request. Currently `/v1/chat/completions` is
            supported.
    BatchRequestOutput:
      type: object
      description: The per-line object of the batch output and error files
      properties:
        id:
          type: string
        custom_id:
          type: string
          description: A developer-provided per-request id that will be used to match outputs to inputs.
        response:
          type: object
          nullable: true
          properties:
            status_code:
              type: integer
              description: The HTTP status code of the response
            request_id:
              type: string
              description: >-
                An unique identifier for the OpenAI API request. Please include this request ID when
                contacting support.
            body:
              type: object
              description: The JSON body of the response
        error:
          type: object
          nullable: true
          description: >-
            For requests that failed with a non-HTTP error, this will contain more information on the cause of
            the failure.
          properties:
            code:
              type: string
              description: A machine-readable error code.
            message:
              type: string
              description: A human-readable error message.
    ListBatchesResponse:
      type: object
      properties:
        data:
          type: array
          items:
            $ref: '#/components/schemas/Batch'
        object:
          type: string
          enum:
            - list
          x-stainless-const: true
      required:
        - object
        - data
    ChatCompletionRequestMessageContentPart:
      oneOf:
        - $ref: '#/components/schemas/ChatCompletionRequestMessageContentPartText'
        - $ref: '#/components/schemas/ChatCompletionRequestMessageContentPartImage'
        - $ref: '#/components/schemas/ChatCompletionRequestMessageContentPartDocument'
    ChatCompletionRequestMessageContentPartImage:
      type: object
      title: Image content part
      properties:
        type:
          type: string
          enum:
            - image_url
          description: The type of the content part.
        image_url:
          type: object
          properties:
            url:
              type: string
              description: Either a URL of the image or the base64 encoded image data.
              format: uri
            detail:
              type: string
              description: Specifies the detail level of the image.
              enum:
                - auto
                - low
                - high
              default: auto
          required:
            - url
      required:
        - type
        - image_url
    ChatCompletionRequestMessageContentPartText:
      type: object
      title: Text content part
      properties:
        type:
          type: string
          enum:
            - text
          description: The type of the content part.
        text:
          type: string
          description: The text content.
      required:
        - type
        - text
    ChatCompletionRequestMessageContentPartDocument:
      type: object
      title: Document content part
      properties:
        type:
          type: string
          enum:
            - document
          description: The type of the content part.
        document:
          type: object
          properties:
            data:
              type: object
              description: The JSON document data.
              additionalProperties: true
            id:
              type: string
              nullable: true
              description: Optional unique identifier for the document.
          required:
            - data
      required:
        - type
        - document
    ChatCompletionDocument:
      type: object
      title: Document
      description: A document that can be referenced by the model while generating responses.
      additionalProperties: false
      properties:
        id:
          type: string
          nullable: true
          description: Optional unique identifier that can be used for citations in responses.
        source:
          $ref: '#/components/schemas/ChatCompletionDocumentSource'
      required:
        - source
    ChatCompletionDocumentSource:
      title: Document source
      description: The source of the document. Only text and JSON sources are currently supported.
      oneOf:
        - $ref: '#/components/schemas/ChatCompletionDocumentSourceText'
        - $ref: '#/components/schemas/ChatCompletionDocumentSourceJSON'
      discriminator:
        propertyName: type
        mapping:
          text: '#/components/schemas/ChatCompletionDocumentSourceText'
          json: '#/components/schemas/ChatCompletionDocumentSourceJSON'
    ChatCompletionDocumentSourceText:
      type: object
      title: Text document source
      description: A document whose contents are provided inline as text.
      additionalProperties: false
      properties:
        type:
          type: string
          enum:
            - text
          description: Identifies this document source as inline text.
        text:
          type: string
          description: The document contents.
      required:
        - type
        - text
    ChatCompletionDocumentSourceJSON:
      type: object
      title: JSON document source
      description: A document whose contents are provided inline as JSON data.
      additionalProperties: false
      properties:
        type:
          type: string
          enum:
            - json
          description: Identifies this document source as JSON data.
        data:
          type: object
          description: The JSON payload associated with the document.
          additionalProperties: true
      required:
        - type
        - data
    ChatCompletionRequestMessage:
      oneOf:
        - $ref: '#/components/schemas/ChatCompletionRequestSystemMessage'
        - $ref: '#/components/schemas/ChatCompletionRequestUserMessage'
        - $ref: '#/components/schemas/ChatCompletionRequestAssistantMessage'
        - $ref: '#/components/schemas/ChatCompletionRequestToolMessage'
        - $ref: '#/components/schemas/ChatCompletionRequestFunctionMessage'
      discriminator:
        propertyName: role
        mapping:
          system: '#/components/schemas/ChatCompletionRequestSystemMessage'
          developer: '#/components/schemas/ChatCompletionRequestSystemMessage'
          user: '#/components/schemas/ChatCompletionRequestUserMessage'
          assistant: '#/components/schemas/ChatCompletionRequestAssistantMessage'
          tool: '#/components/schemas/ChatCompletionRequestToolMessage'
          function: '#/components/schemas/ChatCompletionRequestFunctionMessage'
    ChatCompletionRequestSystemMessage:
      type: object
      title: System message
      additionalProperties: false
      properties:
        content:
          title: System message content
          description: The contents of the system message.
          oneOf:
            - type: string
              title: Text content
              description: The text contents of the message.
            - type: array
              title: Array of content parts
              description: An array of content parts with a defined type, only `text` is supported for this message type.
              items:
                $ref: '#/components/schemas/ChatCompletionRequestMessageContentPartText'
              minItems: 1
        role:
          type: string
          enum:
            - system
            - developer
          description: The role of the messages author, in this case `system`.
        name:
          type: string
          description: >-
            An optional name for the participant. Provides the model information to differentiate between
            participants of the same role.
      required:
        - content
        - role
    ChatCompletionRequestUserMessage:
      type: object
      title: User message
      additionalProperties: false
      properties:
        content:
          title: User message content
          description: |
            The contents of the user message.
          oneOf:
            - type: string
              description: The text contents of the message.
              title: Text content
            - type: array
              description: >-
                An array of content parts with a defined type, each can be of type `text` or `image_url` when
                passing in images. You can pass multiple images by adding multiple `image_url` content parts.
                Image input is only supported when using the `gpt-4-visual-preview` model.
              title: Array of content parts
              items:
                $ref: '#/components/schemas/ChatCompletionRequestMessageContentPart'
              minItems: 1
        role:
          type: string
          enum:
            - user
          description: The role of the messages author, in this case `user`.
        name:
          type: string
          description: >-
            An optional name for the participant. Provides the model information to differentiate between
            participants of the same role.
      required:
        - content
        - role
    ChatCompletionRequestAssistantMessage:
      type: object
      title: Assistant message
      additionalProperties: false
      properties:
        content:
          title: Assistant message content
          nullable: true
          description: >
            The contents of the assistant message. Required unless `tool_calls` or `function_call` is
            specified.
          oneOf:
            - type: string
              title: Text content
              description: The text contents of the message.
            - type: array
              description: An array of content parts with a defined type, only `text` is supported for this message type.
              title: Array of content parts
              items:
                $ref: '#/components/schemas/ChatCompletionRequestMessageContentPartText'
        reasoning:
          description: >
            The reasoning output by the assistant if reasoning_format was set to 'parsed'.

            This field is supported on [models that support
            reasoning](https://console.groq.com/docs/reasoning).
          nullable: true
          type: string
        role:
          type: string
          enum:
            - assistant
          description: The role of the messages author, in this case `assistant`.
        name:
          type: string
          description: >-
            An optional name for the participant. Provides the model information to differentiate between
            participants of the same role.
        tool_calls:
          $ref: '#/components/schemas/ChatCompletionMessageToolCalls'
        function_call:
          type: object
          deprecated: true
          description: >-
            Deprecated and replaced by `tool_calls`. The name and arguments of a function that should be
            called, as generated by the model.
          properties:
            arguments:
              type: string
              description: >-
                The arguments to call the function with, as generated by the model in JSON format. Note that
                the model does not always generate valid JSON, and may hallucinate parameters not defined by
                your function schema. Validate the arguments in your code before calling your function.
            name:
              type: string
              description: The name of the function to call.
      required:
        - role
    ChatCompletionRequestToolMessage:
      type: object
      title: Tool message
      additionalProperties: false
      properties:
        role:
          type: string
          enum:
            - tool
          description: The role of the messages author, in this case `tool`.
        content:
          description: The contents of the tool message.
          title: Tool message content
          oneOf:
            - type: string
              description: The text contents of the message.
              title: Text content
            - type: array
              description: >-
                An array of content parts with a defined type, each can be of type `text` or `image_url` when
                passing in images. You can pass multiple images by adding multiple `image_url` content parts.
                Image input is only supported when using the `gpt-4-visual-preview` model.
              title: Array of content parts
              items:
                $ref: '#/components/schemas/ChatCompletionRequestMessageContentPart'
              minItems: 1
        tool_call_id:
          type: string
          description: Tool call that this message is responding to.
      required:
        - role
        - content
        - tool_call_id
    ChatCompletionRequestFunctionMessage:
      type: object
      title: Function message
      additionalProperties: false
      deprecated: true
      properties:
        role:
          type: string
          enum:
            - function
          description: The role of the messages author, in this case `function`.
        content:
          nullable: true
          title: Function message content
          type: string
          description: The contents of the function message.
        name:
          type: string
          description: The name of the function to call.
      required:
        - role
        - content
        - name
    FunctionParameters:
      type: object
      description: >-
        Function parameters defined as a JSON Schema object. Refer to
        https://json-schema.org/understanding-json-schema/ for schema documentation.
      additionalProperties: true
    ChatCompletionFunctions:
      type: object
      deprecated: true
      properties:
        description:
          type: string
          description: >-
            A description of what the function does, used by the model to choose when and how to call the
            function.
        name:
          type: string
          description: >-
            The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes,
            with a maximum length of 64.
        parameters:
          $ref: '#/components/schemas/FunctionParameters'
      required:
        - name
    ChatCompletionFunctionCallOption:
      type: object
      description: |
        Specifying a particular function via `{"name": "my_function"}` forces the model to call that function.
      properties:
        name:
          type: string
          description: The name of the function to call.
      required:
        - name
    ChatCompletionTool:
      type: object
      properties:
        type:
          anyOf:
            - type: string
              enum:
                - function
                - browser_search
                - code_interpreter
              description: The type of the tool. `function`, `browser_search`, and `code_interpreter` are supported.
            - type: string
        function:
          $ref: '#/components/schemas/FunctionObject'
      required:
        - type
    FunctionObject:
      type: object
      properties:
        description:
          type: string
          description: >-
            A description of what the function does, used by the model to choose when and how to call the
            function.
        name:
          type: string
          description: >-
            The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes,
            with a maximum length of 64.
        parameters:
          $ref: '#/components/schemas/FunctionParameters'
        strict:
          type: boolean
          default: false
          description: >
            Whether to enable strict schema adherence when generating the output. If set to true, the model
            will always follow the exact schema defined in the `schema` field. Only a subset of JSON Schema is
            supported when `strict` is `true`.
      required:
        - name
    ChatCompletionToolChoiceOption:
      nullable: true
      description: >
        Controls which (if any) tool is called by the model.

        `none` means the model will not call any tool and instead generates a message.

        `auto` means the model can pick between generating a message or calling one or more tools.

        `required` means the model must call one or more tools.

        Specifying a particular tool via `{"type": "function", "function": {"name": "my_function"}}` forces
        the model to call that tool.


        `none` is the default when no tools are present. `auto` is the default if tools are present.
      oneOf:
        - type: string
          description: >
            `none` means the model will not call any tool and instead generates a message. `auto` means the
            model can pick between generating a message or calling one or more tools.
          enum:
            - none
            - auto
            - required
        - $ref: '#/components/schemas/ChatCompletionNamedToolChoice'
      x-groq-meta:
        validator: ChatCompletionToolChoiceOption
    ChatCompletionNamedToolChoice:
      type: object
      description: Specifies a tool the model should use. Use to force the model to call a specific function.
      properties:
        type:
          type: string
          enum:
            - function
          description: The type of the tool. Currently, only `function` is supported.
        function:
          type: object
          properties:
            name:
              type: string
              description: The name of the function to call.
          required:
            - name
      required:
        - type
        - function
    ChatCompletionMessageToolCalls:
      type: array
      description: The tool calls generated by the model, such as function calls.
      items:
        $ref: '#/components/schemas/ChatCompletionMessageToolCall'
    ChatCompletionMessageToolCall:
      type: object
      properties:
        id:
          type: string
          description: The ID of the tool call.
        type:
          type: string
          enum:
            - function
          description: The type of the tool. Currently, only `function` is supported.
        function:
          type: object
          description: The function that the model called.
          properties:
            name:
              type: string
              description: The name of the function to call.
            arguments:
              type: string
              description: >-
                The arguments to call the function with, as generated by the model in JSON format. Note that
                the model does not always generate valid JSON, and may hallucinate parameters not defined by
                your function schema. Validate the arguments in your code before calling your function.
          required:
            - name
            - arguments
      required:
        - id
        - type
        - function
    ChatCompletionMessageToolCallChunk:
      type: object
      properties:
        index:
          type: integer
        id:
          type: string
          description: The ID of the tool call.
        type:
          type: string
          enum:
            - function
          description: The type of the tool. Currently, only `function` is supported.
        function:
          type: object
          properties:
            name:
              type: string
              description: The name of the function to call.
            arguments:
              type: string
              description: >-
                The arguments to call the function with, as generated by the model in JSON format. Note that
                the model does not always generate valid JSON, and may hallucinate parameters not defined by
                your function schema. Validate the arguments in your code before calling your function.
      required:
        - index
    ChatCompletionRole:
      type: string
      description: The role of the author of a message
      enum:
        - system
        - user
        - assistant
        - tool
        - function
    ChatCompletionStreamOptions:
      description: |
        Options for streaming response. Only set this when you set `stream: true`.
      type: object
      nullable: true
      default: null
      properties:
        include_usage:
          type: boolean
          nullable: true
          description: >
            If set, an additional chunk will be streamed before the `data: [DONE]` message. The `usage` field
            on this chunk shows the token usage statistics for the entire request, and the `choices` field
            will always be an empty array. All other chunks will also include a `usage` field, but with a null
            value.
    ChatCompletionResponseMessage:
      type: object
      description: A chat completion message generated by the model.
      properties:
        content:
          type: string
          description: The contents of the message.
          nullable: true
        reasoning:
          type: string
          description: >-
            The model's reasoning for a response. Only available for [models that support
            reasoning](https://console.groq.com/docs/reasoning) when request parameter reasoning_format has
            value `parsed`.
          nullable: true
        tool_calls:
          $ref: '#/components/schemas/ChatCompletionMessageToolCalls'
        executed_tools:
          $ref: '#/components/schemas/ChatCompletionMessageExecutedTools'
        role:
          type: string
          enum:
            - assistant
          description: The role of the author of this message.
        function_call:
          type: object
          deprecated: true
          description: >-
            Deprecated and replaced by `tool_calls`. The name and arguments of a function that should be
            called, as generated by the model.
          properties:
            arguments:
              type: string
              description: >-
                The arguments to call the function with, as generated by the model in JSON format. Note that
                the model does not always generate valid JSON, and may hallucinate parameters not defined by
                your function schema. Validate the arguments in your code before calling your function.
            name:
              type: string
              description: The name of the function to call.
          required:
            - name
            - arguments
        annotations:
          type: array
          description: A list of annotations providing citations and references for the content in the message.
          items:
            $ref: '#/components/schemas/Annotation'
      required:
        - role
        - content
    ChatCompletionMessageExecutedTools:
      type: array
      description: A list of tools that were executed during the chat completion for compound AI systems.
      items:
        type: object
        properties:
          index:
            type: integer
            description: The index of the executed tool.
          type:
            type: string
            description: The type of tool that was executed.
          arguments:
            type: string
            description: The arguments passed to the tool in JSON format.
          output:
            type: string
            nullable: true
            description: The output returned by the tool.
          search_results:
            type: object
            nullable: true
            description: The search results returned by the tool, if applicable.
            properties:
              results:
                type: array
                description: List of search results
                items:
                  type: object
                  properties:
                    title:
                      type: string
                      description: The title of the search result
                    url:
                      type: string
                      description: The URL of the search result
                    content:
                      type: string
                      description: The content of the search result
                    score:
                      type: number
                      format: float
                      description: The relevance score of the search result
              images:
                type: array
                description: List of image URLs returned by the search
                items:
                  type: string
          code_results:
            type: array
            items:
              $ref: '#/components/schemas/CodeExecutionResult'
            description: Array of code execution results
          browser_results:
            type: array
            items:
              $ref: '#/components/schemas/BrowserResult'
            description: Array of browser results
        required:
          - index
          - type
          - arguments
    ChatCompletionStreamResponseDelta:
      type: object
      description: A chat completion delta generated by streamed model responses.
      properties:
        content:
          type: string
          description: The contents of the chunk message.
          nullable: true
        reasoning:
          type: string
          description: >-
            The model's reasoning for a response. Only available for [models that support
            reasoning](https://console.groq.com/docs/reasoning) when request parameter reasoning_format has
            value `parsed`.
          nullable: true
        function_call:
          deprecated: true
          type: object
          description: >-
            Deprecated and replaced by `tool_calls`. The name and arguments of a function that should be
            called, as generated by the model.
          properties:
            arguments:
              type: string
              description: >-
                The arguments to call the function with, as generated by the model in JSON format. Note that
                the model does not always generate valid JSON, and may hallucinate parameters not defined by
                your function schema. Validate the arguments in your code before calling your function.
            name:
              type: string
              description: The name of the function to call.
        tool_calls:
          type: array
          items:
            $ref: '#/components/schemas/ChatCompletionMessageToolCallChunk'
        executed_tools:
          $ref: '#/components/schemas/ChatCompletionMessageExecutedTools'
        role:
          type: string
          enum:
            - system
            - user
            - assistant
            - tool
          description: The role of the author of this message.
        annotations:
          type: array
          description: A list of annotations providing citations and references for the content in the message.
          items:
            $ref: '#/components/schemas/Annotation'
    CreateChatCompletionRequest:
      type: object
      additionalProperties: false
      properties:
        messages:
          description: A list of messages comprising the conversation so far.
          type: array
          minItems: 1
          items:
            $ref: '#/components/schemas/ChatCompletionRequestMessage'
        model:
          description: >-
            ID of the model to use. For details on which models are compatible with the Chat API, see
            available [models](https://console.groq.com/docs/models)
          example: meta-llama/llama-4-scout-17b-16e-instruct
          anyOf:
            - type: string
            - type: string
              enum:
                - compound-beta
                - compound-beta-mini
                - gemma2-9b-it
                - llama-3.1-8b-instant
                - llama-3.3-70b-versatile
                - meta-llama/llama-4-maverick-17b-128e-instruct
                - meta-llama/llama-4-scout-17b-16e-instruct
                - meta-llama/llama-guard-4-12b
                - moonshotai/kimi-k2-instruct
                - openai/gpt-oss-120b
                - openai/gpt-oss-20b
                - qwen/qwen3-32b
        disable_tool_validation:
          type: boolean
          default: false
          description: >
            If set to true, groq will return called tools without validating that the tool is present in
            request.tools. tool_choice=required/none will still be enforced, but the request cannot require a
            specific tool be used.
        frequency_penalty:
          type: number
          default: 0
          minimum: -2
          maximum: 2
          nullable: true
          description: >-
            This is not yet supported by any of our models. Number between -2.0 and 2.0. Positive values
            penalize new tokens based on their existing frequency in the text so far, decreasing the model's
            likelihood to repeat the same line verbatim.
        include_reasoning:
          type: boolean
          nullable: true
          description: >
            Whether to include reasoning in the response.  If true, the response will include a `reasoning`
            field. If false, the model's reasoning will not be included in the response.

            This field is mutually exclusive with `reasoning_format`.
        logit_bias:
          type: object
          default: null
          nullable: true
          additionalProperties:
            type: integer
          description: |
            This is not yet supported by any of our models.
            Modify the likelihood of specified tokens appearing in the completion.
        logprobs:
          description: >
            This is not yet supported by any of our models.

            Whether to return log probabilities of the output tokens or not. If true, returns the log
            probabilities of each output token returned in the `content` of `message`.
          type: boolean
          default: false
          nullable: true
        top_logprobs:
          description: >
            This is not yet supported by any of our models.

            An integer between 0 and 20 specifying the number of most likely tokens to return at each token
            position, each with an associated log probability. `logprobs` must be set to `true` if this
            parameter is used.
          type: integer
          minimum: 0
          maximum: 20
          nullable: true
        max_tokens:
          description: >
            Deprecated in favor of `max_completion_tokens`.

            The maximum number of tokens that can be generated in the chat completion. The total length of
            input tokens and generated tokens is limited by the model's context length.
          type: integer
          nullable: true
          deprecated: true
        max_completion_tokens:
          description: >-
            The maximum number of tokens that can be generated in the chat completion. The total length of
            input tokens and generated tokens is limited by the model's context length.
          type: integer
          nullable: true
        'n':
          type: integer
          minimum: 1
          maximum: 1
          default: 1
          example: 1
          nullable: true
          description: >-
            How many chat completion choices to generate for each input message. Note that the current moment,
            only n=1 is supported. Other values will result in a 400 response.
        presence_penalty:
          type: number
          default: 0
          minimum: -2
          maximum: 2
          nullable: true
          description: >-
            This is not yet supported by any of our models. Number between -2.0 and 2.0. Positive values
            penalize new tokens based on whether they appear in the text so far, increasing the model's
            likelihood to talk about new topics.
        response_format:
          nullable: true
          description: >
            An object specifying the format that the model must output. Setting to `{ "type": "json_schema",
            "json_schema": {...} }` enables Structured Outputs which ensures the model will match your
            supplied JSON schema. `json_schema` response format is only available on [supported
            models](https://console.groq.com/docs/structured-outputs#supported-models). Setting to `{ "type":
            "json_object" }` enables the older JSON mode, which ensures the message the model generates is
            valid JSON. Using `json_schema` is preferred for models that support it.
          oneOf:
            - $ref: '#/components/schemas/ResponseFormatText'
            - $ref: '#/components/schemas/ResponseFormatJsonSchema'
            - $ref: '#/components/schemas/ResponseFormatJsonObject'
        seed:
          type: integer
          nullable: true
          description: >
            If specified, our system will make a best effort to sample deterministically, such that repeated
            requests with the same `seed` and parameters should return the same result.

            Determinism is not guaranteed, and you should refer to the `system_fingerprint` response parameter
            to monitor changes in the backend.
        service_tier:
          type: string
          nullable: true
          description: >
            The service tier to use for the request. Defaults to `on_demand`.

            - `auto` will automatically select the highest tier available within the rate limits of your
            organization.

            - `flex` uses the flex tier, which will succeed or fail quickly.
          enum:
            - auto
            - on_demand
            - flex
            - performance
            - null
        stop:
          description: >
            Up to 4 sequences where the API will stop generating further tokens. The returned text will not
            contain the stop sequence.
          default: null
          nullable: true
          oneOf:
            - type: string
              example: |+

              nullable: true
            - type: array
              minItems: 0
              maxItems: 4
              items:
                type: string
                example: '["\n"]'
        reasoning_effort:
          description: |
            qwen3 models support the following values
            Set to 'none' to disable reasoning.
            Set to 'default' or null to let Qwen reason.

            openai/gpt-oss-20b and openai/gpt-oss-120b support 'low', 'medium', or 'high'.
            'medium' is the default value.
          nullable: true
          default: null
          type: string
          enum:
            - none
            - default
            - low
            - medium
            - high
        reasoning_format:
          description: |
            Specifies how to output reasoning tokens
            This field is mutually exclusive with `include_reasoning`.
          default: null
          nullable: true
          type: string
          enum:
            - hidden
            - raw
            - parsed
        stream:
          description: >
            If set, partial message deltas will be sent. Tokens will be sent as data-only [server-sent
            events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format)
            as they become available, with the stream terminated by a `data: [DONE]` message. [Example
            code](/docs/text-chat#streaming-a-chat-completion).
          type: boolean
          nullable: true
          default: false
        temperature:
          type: number
          minimum: 0
          maximum: 2
          default: 1
          example: 1
          nullable: true
          description: >-
            What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output
            more random, while lower values like 0.2 will make it more focused and deterministic. We generally
            recommend altering this or top_p but not both.
        top_p:
          type: number
          minimum: 0
          maximum: 1
          default: 1
          example: 1
          nullable: true
          description: >-
            An alternative to sampling with temperature, called nucleus sampling, where the model considers
            the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the
            top 10% probability mass are considered. We generally recommend altering this or temperature but
            not both.
        tools:
          type: array
          nullable: true
          maxItems: 128
          description: >
            A list of tools the model may call. Currently, only functions are supported as a tool. Use this to
            provide a list of functions the model may generate JSON inputs for. A max of 128 functions are
            supported.
          items:
            $ref: '#/components/schemas/ChatCompletionTool'
        tool_choice:
          $ref: '#/components/schemas/ChatCompletionToolChoiceOption'
        parallel_tool_calls:
          description: |
            Whether to enable parallel function calling during tool use.
          type: boolean
          nullable: true
          default: true
        user:
          type: string
          description: A unique identifier representing your end-user, which can help us monitor and detect abuse.
          nullable: true
        function_call:
          deprecated: true
          nullable: true
          description: >
            Deprecated in favor of `tool_choice`.


            Controls which (if any) function is called by the model.

            `none` means the model will not call a function and instead generates a message.

            `auto` means the model can pick between generating a message or calling a function.

            Specifying a particular function via `{"name": "my_function"}` forces the model to call that
            function.


            `none` is the default when no functions are present. `auto` is the default if functions are
            present.
          oneOf:
            - type: string
              description: >
                `none` means the model will not call a function and instead generates a message. `auto` means
                the model can pick between generating a message or calling a function.
              enum:
                - none
                - auto
                - required
            - $ref: '#/components/schemas/ChatCompletionFunctionCallOption'
        functions:
          deprecated: true
          nullable: true
          description: |
            Deprecated in favor of `tools`.

            A list of functions the model may generate JSON inputs for.
          type: array
          minItems: 0
          maxItems: 128
          items:
            $ref: '#/components/schemas/ChatCompletionFunctions'
        metadata:
          type: object
          nullable: true
          additionalProperties:
            type: string
          description: |
            This parameter is not currently supported.
        store:
          type: boolean
          nullable: true
          description: |
            This parameter is not currently supported.
        include_domains:
          type: array
          nullable: true
          deprecated: true
          description: |
            Deprecated: Use search_settings.include_domains instead.
            A list of domains to include in the search results when the model uses a web search tool.
          items:
            type: string
        exclude_domains:
          type: array
          nullable: true
          deprecated: true
          description: |
            Deprecated: Use search_settings.exclude_domains instead.
            A list of domains to exclude from the search results when the model uses a web search tool.
          items:
            type: string
        search_settings:
          type: object
          nullable: true
          description: |
            Settings for web search functionality when the model uses a web search tool.
          properties:
            include_domains:
              type: array
              nullable: true
              description: A list of domains to include in the search results.
              items:
                type: string
            exclude_domains:
              type: array
              nullable: true
              description: A list of domains to exclude from the search results.
              items:
                type: string
            include_images:
              type: boolean
              nullable: true
              description: Whether to include images in the search results.
            country:
              type: string
              nullable: true
              description: >-
                Name of country to prioritize search results from (e.g., "united states", "germany",
                "france").
        compound_custom:
          type: object
          nullable: true
          description: Custom configuration of models and tools for Compound.
          properties:
            models:
              type: object
              nullable: true
              properties:
                reasoning_model:
                  type: string
                  nullable: true
                  description: Custom model to use for reasoning.
                answering_model:
                  type: string
                  nullable: true
                  description: Custom model to use for answering.
            tools:
              type: object
              nullable: true
              description: Configuration options for tools available to Compound.
              properties:
                enabled_tools:
                  type: array
                  nullable: true
                  description: A list of tool names that are enabled for the request.
                  items:
                    type: string
                wolfram_settings:
                  type: object
                  nullable: true
                  description: Configuration for the Wolfram tool integration.
                  properties:
                    authorization:
                      type: string
                      nullable: true
                      description: API key used to authorize requests to Wolfram services.
        documents:
          type: array
          nullable: true
          description: >-
            A list of documents to provide context for the conversation. Each document contains text that can
            be referenced by the model.
          items:
            $ref: '#/components/schemas/ChatCompletionDocument'
        citation_options:
          type: string
          enum:
            - enabled
            - disabled
          nullable: true
          default: enabled
          description: >-
            Whether to enable citations in the response. When enabled, the model will include citations for
            information retrieved from provided documents or web searches.
      required:
        - model
        - messages
    ResponseFormatJsonObject:
      type: object
      title: JSON object
      description: >
        JSON object response format. An older method of generating JSON responses. Using `json_schema` is
        recommended for models that support it. Note that the model will not generate JSON without a system or
        user message instructing it to do so.
      properties:
        type:
          type: string
          description: The type of response format being defined. Always `json_object`.
          enum:
            - json_object
          x-stainless-const: true
      required:
        - type
    ResponseFormatJsonSchema:
      type: object
      title: JSON schema
      description: |
        JSON Schema response format. Used to generate structured JSON responses.
      properties:
        type:
          type: string
          description: The type of response format being defined. Always `json_schema`.
          enum:
            - json_schema
          x-stainless-const: true
        json_schema:
          type: object
          title: JSON schema
          description: |
            Structured Outputs configuration options, including a JSON Schema.
          properties:
            description:
              type: string
              description: >
                A description of what the response format is for, used by the model to determine how to
                respond in the format.
            name:
              type: string
              description: >
                The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes,
                with a maximum length of 64.
            schema:
              $ref: '#/components/schemas/ResponseFormatJsonSchemaSchema'
            strict:
              type: boolean
              nullable: true
              default: false
              description: >
                Whether to enable strict schema adherence when generating the output. If set to true, the
                model will always follow the exact schema defined in the `schema` field. Only a subset of JSON
                Schema is supported when `strict` is `true`.
          required:
            - name
      required:
        - type
        - json_schema
    ResponseFormatJsonSchemaSchema:
      type: object
      title: JSON schema
      description: |
        The schema for the response format, described as a JSON Schema object.
        Learn how to build JSON schemas [here](https://json-schema.org/).
      additionalProperties: true
    ResponseFormatText:
      type: object
      title: Text
      description: |
        Default response format. Used to generate text responses.
      properties:
        type:
          type: string
          description: The type of response format being defined. Always `text`.
          enum:
            - text
          x-stainless-const: true
      required:
        - type
    CreateChatCompletionResponse:
      type: object
      description: Represents a chat completion response returned by model, based on the provided input.
      properties:
        id:
          type: string
          description: A unique identifier for the chat completion.
        choices:
          type: array
          description: A list of chat completion choices. Can be more than one if `n` is greater than 1.
          items:
            type: object
            required:
              - finish_reason
              - index
              - message
              - logprobs
            properties:
              finish_reason:
                type: string
                description: >
                  The reason the model stopped generating tokens. This will be `stop` if the model hit a
                  natural stop point or a provided stop sequence,

                  `length` if the maximum number of tokens specified in the request was reached,

                  `tool_calls` if the model called a tool, or `function_call` (deprecated) if the model called
                  a function.
                enum:
                  - stop
                  - length
                  - tool_calls
                  - function_call
              index:
                type: integer
                description: The index of the choice in the list of choices.
              message:
                $ref: '#/components/schemas/ChatCompletionResponseMessage'
              logprobs: &ref_3
                description: Log probability information for the choice.
                type: object
                nullable: true
                properties:
                  content:
                    description: A list of message content tokens with log probability information.
                    type: array
                    items:
                      $ref: '#/components/schemas/ChatCompletionTokenLogprob'
                    nullable: true
                required:
                  - content
        created:
          type: integer
          description: The Unix timestamp (in seconds) of when the chat completion was created.
        model:
          type: string
          description: The model used for the chat completion.
        system_fingerprint:
          type: string
          description: >
            This fingerprint represents the backend configuration that the model runs with.


            Can be used in conjunction with the `seed` request parameter to understand when backend changes
            have been made that might impact determinism.
        object:
          type: string
          description: The object type, which is always `chat.completion`.
          enum:
            - chat.completion
        usage:
          $ref: '#/components/schemas/CompletionUsage'
        usage_breakdown:
          $ref: '#/components/schemas/ChatCompletionUsageBreakdown'
          description: >-
            Detailed usage breakdown by model when multiple models are used in the request for compound AI
            systems.
        service_tier:
          type: string
          nullable: true
          description: The service tier used for the request.
          enum:
            - auto
            - on_demand
            - flex
            - performance
            - null
        mcp_list_tools:
          type: array
          nullable: true
          description: List of discovered MCP tools from connected servers.
          items:
            type: object
            properties:
              id:
                type: string
                description: Unique identifier for this tool list response.
              type:
                type: string
                description: The type identifier.
              server_label:
                type: string
                description: Human-readable label for the MCP server.
              tools:
                type: array
                description: Array of discovered tools from the server.
                items:
                  type: object
                  properties:
                    annotations:
                      description: Additional metadata for the tool.
                    description:
                      type: string
                      description: Description of what the tool does.
                    input_schema:
                      type: object
                      additionalProperties: true
                      description: JSON Schema describing the tool's input parameters.
                    name:
                      type: string
                      description: The name of the tool.
        x_groq:
          $ref: '#/components/schemas/XGroqNonStreaming'
      required:
        - choices
        - created
        - id
        - model
        - object
    ChatCompletionTokenLogprob:
      type: object
      properties:
        token: &ref_0
          description: The token.
          type: string
        logprob: &ref_1
          description: >-
            The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the
            value `-9999.0` is used to signify that the token is very unlikely.
          type: number
        bytes: &ref_2
          description: >-
            A list of integers representing the UTF-8 bytes representation of the token. Useful in instances
            where characters are represented by multiple tokens and their byte representations must be
            combined to generate the correct text representation. Can be `null` if there is no bytes
            representation for the token.
          type: array
          items:
            type: integer
          nullable: true
        top_logprobs:
          description: >-
            List of the most likely tokens and their log probability, at this token position. In rare cases,
            there may be fewer than the number of requested `top_logprobs` returned.
          type: array
          items:
            type: object
            properties:
              token: *ref_0
              logprob: *ref_1
              bytes: *ref_2
            required:
              - token
              - logprob
              - bytes
      required:
        - token
        - logprob
        - bytes
        - top_logprobs
    DebugData:
      type: object
      description: >-
        Debug information including input and output token IDs and strings. Only present when debug=true in
        the request.
      properties:
        input_token_ids:
          type: array
          items:
            type: integer
          description: Token IDs for the input.
        input_tokens:
          type: array
          items:
            type: string
          description: Token strings for the input.
        output_token_ids:
          type: array
          items:
            type: integer
          description: Token IDs for the output.
        output_tokens:
          type: array
          items:
            type: string
          description: Token strings for the output.
    XGroqNonStreaming:
      type: object
      description: Groq-specific metadata for non-streaming chat completion responses.
      properties:
        id:
          type: string
          description: A groq request ID which can be used to refer to a specific request to groq support.
        seed:
          type: integer
          nullable: true
          description: >-
            The seed used for the request. See the seed property on CreateChatCompletionRequest for more
            details.
        usage:
          type: object
          nullable: true
          description: Additional Groq-specific usage metrics (hardware cache statistics).
          properties:
            sram_cached_tokens:
              type: integer
              description: Number of tokens served from SRAM cache.
            dram_cached_tokens:
              type: integer
              description: Number of tokens served from DRAM cache.
        debug:
          allOf:
            - $ref: '#/components/schemas/DebugData'
          nullable: true
      required:
        - id
    XGroq:
      type: object
      description: Groq-specific metadata for streaming responses. Different fields appear in different chunks.
      properties:
        id:
          type: string
          nullable: true
          description: |
            A groq request ID which can be used to refer to a specific request to groq support.
            Sent only in the first and final chunk.
        seed:
          type: integer
          nullable: true
          description: The seed used for the request. Sent in the final chunk.
        usage:
          allOf:
            - $ref: '#/components/schemas/CompletionUsage'
          nullable: true
          description: Usage information for the stream. Only sent in the final chunk.
        usage_breakdown:
          allOf:
            - $ref: '#/components/schemas/ChatCompletionUsageBreakdown'
          nullable: true
          description: >-
            Detailed usage breakdown by model when multiple models are used in the request for compound AI
            systems. Only sent in the final chunk.
        error:
          type: string
          nullable: true
          description: An error string indicating why a stream was stopped early.
        debug:
          allOf:
            - $ref: '#/components/schemas/DebugData'
          nullable: true
    CreateChatCompletionStreamResponse:
      type: object
      description: >-
        Represents a streamed chunk of a chat completion response returned by model, based on the provided
        input.
      properties:
        id:
          type: string
          description: A unique identifier for the chat completion. Each chunk has the same ID.
        choices:
          type: array
          description: |
            A list of chat completion choices. Can contain more than one elements if `n` is greater than 1.
          items:
            type: object
            required:
              - delta
              - finish_reason
              - index
            properties:
              delta:
                $ref: '#/components/schemas/ChatCompletionStreamResponseDelta'
              logprobs: *ref_3
              finish_reason:
                type: string
                description: >
                  The reason the model stopped generating tokens. This will be `stop` if the model hit a
                  natural stop point or a provided stop sequence,

                  `length` if the maximum number of tokens specified in the request was reached,

                  `tool_calls` if the model called a tool, or `function_call` (deprecated) if the model called
                  a function.
                enum:
                  - stop
                  - length
                  - tool_calls
                  - function_call
                nullable: true
              index:
                type: integer
                description: The index of the choice in the list of choices.
        created:
          type: integer
          description: >-
            The Unix timestamp (in seconds) of when the chat completion was created. Each chunk has the same
            timestamp.
        model:
          type: string
          description: The model to generate the completion.
        system_fingerprint:
          type: string
          description: >
            This fingerprint represents the backend configuration that the model runs with.

            Can be used in conjunction with the `seed` request parameter to understand when backend changes
            have been made that might impact determinism.
        object:
          type: string
          description: The object type, which is always `chat.completion.chunk`.
          enum:
            - chat.completion.chunk
        x_groq:
          $ref: '#/components/schemas/XGroq'
      required:
        - choices
        - created
        - id
        - model
        - object
    CompletionUsage:
      type: object
      description: Usage statistics for the completion request.
      properties:
        queue_time:
          type: number
          description: Time the requests was spent queued
        completion_time:
          type: number
          description: Time spent generating tokens
        completion_tokens:
          type: integer
          description: Number of tokens in the generated completion.
        prompt_time:
          type: number
          description: Time spent processing input tokens
        prompt_tokens:
          type: integer
          description: Number of tokens in the prompt.
        total_time:
          type: number
          description: completion time and prompt time combined
        total_tokens:
          type: integer
          description: Total number of tokens used in the request (prompt + completion).
        prompt_tokens_details:
          type: object
          nullable: true
          description: Breakdown of tokens in the prompt.
          properties:
            cached_tokens:
              type: integer
              description: Number of tokens that were cached and reused.
          required:
            - cached_tokens
        completion_tokens_details:
          type: object
          nullable: true
          description: Breakdown of tokens in the completion.
          properties:
            reasoning_tokens:
              type: integer
              description: Number of tokens used for reasoning (for reasoning models).
          required:
            - reasoning_tokens
      required:
        - prompt_tokens
        - completion_tokens
        - total_tokens
    ChatCompletionUsageBreakdown:
      type: object
      description: Usage statistics for compound AI completion requests.
      properties:
        models:
          type: array
          description: List of models used in the request and their individual usage statistics
          items:
            type: object
            properties:
              model:
                type: string
                description: The name/identifier of the model used
              usage:
                $ref: '#/components/schemas/CompletionUsage'
            required:
              - model
              - usage
      required:
        - models
    Chart:
      type: object
      properties:
        type:
          type: string
          description: The type of chart
          enum:
            - bar
            - box_and_whisker
            - line
            - pie
            - scatter
            - superchart
            - unknown
        title:
          type: string
          description: The title of the chart
        x_label:
          type: string
          description: The label for the x-axis
        y_label:
          type: string
          description: The label for the y-axis
        x_unit:
          type: string
          description: The unit for the x-axis
        y_unit:
          type: string
          description: The unit for the y-axis
        x_ticks:
          type: array
          items:
            type: number
          description: The tick values for the x-axis
        y_ticks:
          type: array
          items:
            type: number
          description: The tick values for the y-axis
        x_tick_labels:
          type: array
          items:
            type: string
          description: The labels for the x-axis ticks
        y_tick_labels:
          type: array
          items:
            type: string
          description: The labels for the y-axis ticks
        x_scale:
          type: string
          description: The scale type for the x-axis
        y_scale:
          type: string
          description: The scale type for the y-axis
        elements:
          type: array
          items:
            $ref: '#/components/schemas/ChartElement'
          description: The chart elements (data series, points, etc.)
      required:
        - type
        - elements
    ChartElement:
      type: object
      properties:
        label:
          type: string
          description: The label for this chart element
        group:
          type: string
          description: The group this element belongs to
        value:
          type: number
          description: The value for this element
        points:
          type: array
          items:
            type: array
            items:
              type: number
          description: The points for this element
        angle:
          type: number
          description: The angle for this element
        radius:
          type: number
          description: The radius for this element
        min:
          type: number
          description: The minimum value for this element
        first_quartile:
          type: number
          description: The first quartile value for this element
        median:
          type: number
          description: The median value for this element
        third_quartile:
          type: number
          description: The third quartile value for this element
        max:
          type: number
        outliers:
          type: array
          items:
            type: number
          description: The outliers for this element
      required:
        - label
    BrowserResult:
      type: object
      properties:
        url:
          type: string
          description: The URL of the browser window
        title:
          type: string
          description: The title of the browser window
        live_view_url:
          type: string
          description: The live view URL for the browser window
        content:
          type: string
          description: The content of the browser result
      required:
        - url
        - title
      additionalProperties: false
    CodeExecutionResult:
      type: object
      properties:
        text:
          type: string
          description: The text version of the code execution result
        png:
          type: string
          description: Base64 encoded PNG image output from code execution
        chart:
          $ref: '#/components/schemas/Chart'
        charts:
          type: array
          items:
            $ref: '#/components/schemas/Chart'
          description: Array of charts from a superchart
      additionalProperties: false
    Annotation:
      type: object
      description: An annotation that provides citations or references for content in a message.
      properties:
        type:
          type: string
          description: The type of annotation.
          enum:
            - document_citation
            - function_citation
        document_citation:
          $ref: '#/components/schemas/DocumentCitation'
        function_citation:
          $ref: '#/components/schemas/FunctionCitation'
      required:
        - type
    DocumentCitation:
      type: object
      description: A citation referencing a specific document that was provided in the request.
      properties:
        start_index:
          type: integer
          description: The character index in the message content where this citation begins.
        end_index:
          type: integer
          description: The character index in the message content where this citation ends.
        document_id:
          type: string
          description: The ID of the document being cited, corresponding to a document provided in the request.
      required:
        - start_index
        - end_index
        - document_id
      additionalProperties: false
    FunctionCitation:
      type: object
      description: A citation referencing the result of a function or tool call.
      properties:
        start_index:
          type: integer
          description: The character index in the message content where this citation begins.
        end_index:
          type: integer
          description: The character index in the message content where this citation ends.
        tool_call_id:
          type: string
          description: The ID of the tool call being cited, corresponding to a tool call made during the conversation.
      required:
        - start_index
        - end_index
        - tool_call_id
      additionalProperties: false
    Embedding:
      type: object
      description: |
        Represents an embedding vector returned by embedding endpoint.
      properties:
        index:
          type: integer
          description: The index of the embedding in the list of embeddings.
        embedding:
          oneOf:
            - type: array
              description: >
                The embedding vector, which is a list of floats. The length of vector depends on the model as
                listed in the [embedding guide](/docs/guides/embeddings).
              items:
                type: number
            - type: string
              description: >
                The embedding vector, which is a base64 encoded string. The length of vector depends on the
                model as listed in the [embedding guide](/docs/guides/embeddings).
        object:
          type: string
          description: The object type, which is always "embedding".
          enum:
            - embedding
      required:
        - index
        - object
        - embedding
    CreateEmbeddingRequest:
      type: object
      additionalProperties: false
      properties:
        input:
          description: >
            Input text to embed, encoded as a string or array of tokens. To embed multiple inputs in a single
            request, pass an array of strings or array of token arrays. The input must not exceed the max
            input tokens for the model, cannot be an empty string, and any array must be 2048 dimensions or
            less.
          example: The quick brown fox jumped over the lazy dog
          oneOf:
            - type: string
              title: string
              description: The string that will be turned into an embedding.
              default: ''
              example: This is a test.
            - type: array
              title: array
              description: The array of strings that will be turned into an embeddings.
              minItems: 1
              maxItems: 2048
              items:
                type: string
                default: ''
                example: "['This is a test.']"
          x-groq-meta:
            validator: EmbeddingInput
        model:
          description: |
            ID of the model to use.
          example: nomic-embed-text-v1_5
          anyOf:
            - type: string
            - type: string
              enum:
                - nomic-embed-text-v1_5
        encoding_format:
          description: The format to return the embeddings in. Can only be `float` or `base64`.
          example: float
          default: float
          type: string
          enum:
            - float
            - base64
        user:
          type: string
          description: A unique identifier representing your end-user, which can help us monitor and detect abuse.
          nullable: true
      required:
        - model
        - input
    CreateEmbeddingResponse:
      type: object
      properties:
        data:
          type: array
          description: The list of embeddings generated by the model.
          items:
            $ref: '#/components/schemas/Embedding'
        model:
          type: string
          description: The name of the model used to generate the embedding.
        object:
          type: string
          description: The object type, which is always "list".
          enum:
            - list
        usage:
          type: object
          description: The usage information for the request.
          properties:
            prompt_tokens:
              type: integer
              description: The number of tokens used by the prompt.
            total_tokens:
              type: integer
              description: The total number of tokens used by the request.
          required:
            - prompt_tokens
            - total_tokens
      required:
        - object
        - model
        - data
        - usage
    File:
      title: File
      description: The `File` object represents a document that has been uploaded.
      properties:
        id:
          type: string
          description: The file identifier, which can be referenced in the API endpoints.
        bytes:
          type: integer
          description: The size of the file, in bytes.
        created_at:
          type: integer
          description: The Unix timestamp (in seconds) for when the file was created.
        filename:
          type: string
          description: The name of the file.
        object:
          type: string
          description: The object type, which is always `file`.
          enum:
            - file
          x-stainless-const: true
        purpose:
          type: string
          description: The intended purpose of the file. Supported values are `batch`, and `batch_output`.
          enum:
            - batch
            - batch_output
    CreateFileRequest:
      type: object
      additionalProperties: false
      properties:
        file:
          description: |
            The File object (not file name) to be uploaded.
          type: string
          format: binary
        purpose:
          description: |
            The intended purpose of the uploaded file.
            Use "batch" for [Batch API](/docs/api-reference#batches).
          type: string
          enum:
            - batch
      required:
        - file
        - purpose
    DeleteFileResponse:
      type: object
      properties:
        id:
          type: string
        object:
          type: string
          enum:
            - file
          x-stainless-const: true
        deleted:
          type: boolean
      required:
        - id
        - object
        - deleted
    ListFilesResponse:
      type: object
      properties:
        object:
          type: string
          enum:
            - list
        data:
          type: array
          items:
            $ref: '#/components/schemas/File'
      required:
        - object
        - data
    CreateFineTuningRequest:
      type: object
      properties:
        base_model:
          type: string
          description: |
            BaseModel is the model that the fine tune was originally trained on.
        input_file_id:
          type: string
          description: |
            InputFileID is the id of the file that was uploaded via the /files api.
        name:
          type: string
          description: |
            Name is the given name to a fine tuned model.
        type:
          type: string
          description: |
            Type is the type of fine tuning format such as "lora".
    DeleteFineTuningResponse:
      type: object
      properties:
        deleted:
          type: boolean
        id:
          type: string
        object:
          type: string
    ListFineTuningsResponse:
      type: object
      properties:
        data:
          type: array
          items:
            type: object
            properties:
              base_model:
                type: string
                description: |
                  BaseModel is the model that the fine tune was originally trained on.
              created_at:
                type: number
                description: |
                  CreatedAt is the timestamp of when the fine tuned model was created.
              fine_tuned_model:
                type: string
                description: |
                  FineTunedModel is the final name of the fine tuned model.
              id:
                type: string
                description: |
                  ID is the unique identifier of a fine tune.
              input_file_id:
                type: string
                description: |
                  InputFileID is the id of the file that was uploaded via the /files api.
              name:
                type: string
                description: |
                  Name is the given name to a fine tuned model.
              type:
                type: string
                description: |
                  Type is the type of fine tuning format such as "lora".
        object:
          type: string
    ReadFineTuningResponse:
      type: object
      properties:
        data:
          type: object
          properties:
            base_model:
              type: string
              description: |
                BaseModel is the model that the fine tune was originally trained on.
            created_at:
              type: number
              description: |
                CreatedAt is the timestamp of when the fine tuned model was created.
            fine_tuned_model:
              type: string
              description: |
                FineTunedModel is the final name of the fine tuned model.
            id:
              type: string
              description: |
                ID is the unique identifier of a fine tune.
            input_file_id:
              type: string
              description: |
                InputFileID is the id of the file that was uploaded via the /files api.
            name:
              type: string
              description: |
                Name is the given name to a fine tuned model.
            type:
              type: string
              description: |
                Type is the type of fine tuning format such as "lora".
        id:
          type: string
        object:
          type: string
    Model:
      title: Model
      description: Describes an OpenAI model offering that can be used with the API.
      properties:
        id:
          type: string
          description: The model identifier, which can be referenced in the API endpoints.
        created:
          type: integer
          description: The Unix timestamp (in seconds) when the model was created.
        object:
          type: string
          description: The object type, which is always "model".
          enum:
            - model
        owned_by:
          type: string
          description: The organization that owns the model.
      required:
        - id
        - object
        - created
        - owned_by
    ListModelsResponse:
      type: object
      properties:
        object:
          type: string
          enum:
            - list
        data:
          type: array
          items:
            $ref: '#/components/schemas/Model'
      required:
        - object
        - data
    DeleteModelResponse:
      type: object
      properties:
        id:
          type: string
        deleted:
          type: boolean
        object:
          type: string
      required:
        - id
        - object
        - deleted
    RerankingRequest:
      type: object
      additionalProperties: false
      properties:
        model:
          description: |
            ID of the reranking model to use.
          example: qwen3-reranker-4b
          type: string
        query:
          description: |
            The search query to rank documents against.
          example: artificial intelligence research
          type: string
        docs:
          description: |
            An array of documents to rank. Each document is a string containing the text content.
            Maximum of 100 documents per request.
          type: array
          minItems: 1
          maxItems: 100
          items:
            type: string
            minLength: 1
          example:
            - Machine learning is a subset of artificial intelligence
            - The weather forecast predicts rain tomorrow
            - Deep learning uses neural networks with multiple layers
        instruction:
          description: |
            Optional instruction to guide the reranking process. If not provided, 
            a default instruction will be used.
          example: Find the most relevant document about AI research
          type: string
          nullable: true
      required:
        - model
        - query
        - docs
    RerankingResponse:
      type: object
      properties:
        results:
          type: array
          description: |
            List of documents sorted by relevance score in descending order.
            Each result contains the original document text and its relevance score.
          items:
            $ref: '#/components/schemas/RerankingResult'
      required:
        - results
    RerankingResult:
      type: object
      properties:
        doc:
          type: string
          description: The original document text.
          example: Machine learning is a subset of artificial intelligence
        score:
          type: number
          format: float
          minimum: 0
          maximum: 1
          description: |
            Relevance score between 0.0 and 1.0, where higher scores indicate 
            greater relevance to the query.
          example: 0.92
      required:
        - doc
        - score
    CreateResponseRequest:
      type: object
      additionalProperties: false
      properties:
        model:
          description: >-
            ID of the model to use. For details on which models are compatible with the Responses API, see
            available [models](https://console.groq.com/docs/models)
          example: llama-3.3-70b-versatile
          anyOf:
            - type: string
            - type: string
              enum:
                - gemma2-9b-it
                - llama-3.3-70b-versatile
                - llama-3.1-8b-instant
                - llama-guard-3-8b
                - llama3-70b-8192
                - llama3-8b-8192
        input:
          description: |
            Text input to the model, used to generate a response.
          oneOf:
            - type: string
              title: Text input
              description: A text input to the model, equivalent to a text input with the `user` role.
            - type: array
              title: Input item list
              description: A list of one or many input items to the model, containing different content types.
              items:
                $ref: '#/components/schemas/ResponseInputItem'
        instructions:
          type: string
          description: |
            Inserts a system (or developer) message as the first item in the model's context.
          nullable: true
        max_output_tokens:
          description: >
            An upper bound for the number of tokens that can be generated for a response, including visible
            output tokens and reasoning tokens.
          type: integer
          nullable: true
        temperature:
          type: number
          minimum: 0
          maximum: 2
          default: 1
          example: 1
          nullable: true
          description: >
            Controls randomness in the response generation. Range: 0 to 2. Lower values produce more
            deterministic outputs, higher values increase variety and creativity.
        top_p:
          type: number
          minimum: 0
          maximum: 1
          default: 1
          example: 1
          nullable: true
          description: >
            Nucleus sampling parameter that controls the cumulative probability cutoff. Range: 0 to 1. A value
            of 0.1 restricts sampling to tokens within the top 10% probability mass.
        tools:
          type: array
          nullable: true
          maxItems: 128
          description: >
            List of tools available to the model. Currently supports function definitions only. Maximum of 128
            functions.
          items:
            $ref: '#/components/schemas/ResponseTool'
        tool_choice:
          $ref: '#/components/schemas/ResponseToolChoiceOption'
        text:
          type: object
          description: |
            Response format configuration. Supports plain text or structured JSON output.
          properties:
            format:
              $ref: '#/components/schemas/ResponseFormatConfiguration'
        reasoning:
          type: object
          nullable: true
          description: >
            Configuration for reasoning capabilities when using [models that support
            reasoning](https://console.groq.com/docs/reasoning).
          properties:
            effort:
              type: string
              enum:
                - low
                - medium
                - high
              default: medium
              nullable: true
              description: >
                Level of reasoning effort. Supported values: `low`, `medium`, `high`. Lower values provide
                faster responses with less reasoning depth.
        metadata:
          type: object
          nullable: true
          additionalProperties:
            type: string
          description: |
            Custom key-value pairs for storing additional information. Maximum of 16 pairs.
        parallel_tool_calls:
          type: boolean
          description: |
            Enable parallel execution of multiple tool calls.
          default: true
          nullable: true
        store:
          type: boolean
          description: |
            Response storage flag. Note: Currently only supports false or null values.
          default: false
          nullable: true
        stream:
          description: |
            Enable streaming mode to receive response data as server-sent events.
          type: boolean
          nullable: true
          default: false
        user:
          type: string
          example: user-1234
          description: |
            Optional identifier for tracking end-user requests. Useful for usage monitoring and compliance.
        service_tier:
          type: string
          description: |
            Specifies the latency tier to use for processing the request.
          enum:
            - auto
            - default
            - flex
          nullable: true
          default: auto
        truncation:
          type: string
          description: |
            Context truncation strategy. Supported values: `auto` or `disabled`.
          enum:
            - auto
            - disabled
          nullable: true
          default: disabled
      required:
        - model
        - input
    ResponseInputItem:
      oneOf:
        - $ref: '#/components/schemas/ResponseEasyInputMessage'
        - $ref: '#/components/schemas/ResponseInputMessage'
        - $ref: '#/components/schemas/ResponseItemReference'
        - $ref: '#/components/schemas/ResponseFunctionCall'
        - $ref: '#/components/schemas/ResponseFunctionCallOutput'
      discriminator:
        propertyName: type
        mapping:
          message: '#/components/schemas/ResponseInputMessage'
          item_reference: '#/components/schemas/ResponseItemReference'
          function_call: '#/components/schemas/ResponseFunctionCall'
          function_call_output: '#/components/schemas/ResponseFunctionCallOutput'
    ResponseEasyInputMessage:
      type: object
      title: Easy input message
      description: |
        A message input to the model with a role indicating instruction following hierarchy.
      properties:
        role:
          type: string
          description: |
            The role of the message input. One of `user`, `assistant`, `system`, or `developer`.
          enum:
            - user
            - assistant
            - system
            - developer
        content:
          description: |
            Text input to the model.
          oneOf:
            - type: string
              title: Text input
              description: A text input to the model.
            - type: array
              title: Content array
              description: An array of content parts.
              items:
                $ref: '#/components/schemas/ResponseInputContent'
      required:
        - role
        - content
    ResponseInputMessage:
      type: object
      title: Input message
      description: |
        A message input to the model with explicit type field.
      properties:
        type:
          type: string
          description: The type of the message input. Always set to `message`.
          enum:
            - message
          x-stainless-const: true
        role:
          type: string
          description: >
            The role of the message input. One of `user`, `system`, or `developer`. Note: assistant role is
            not supported with explicit type.
          enum:
            - user
            - system
            - developer
        content:
          type: array
          description: A list of one or many input content items.
          items:
            $ref: '#/components/schemas/ResponseInputContent'
        status:
          type: string
          description: The status of item. Populated when items are returned via API.
          enum:
            - in_progress
            - completed
            - incomplete
      required:
        - type
        - role
        - content
    ResponseInputContent:
      oneOf:
        - $ref: '#/components/schemas/ResponseInputTextContent'
      discriminator:
        propertyName: type
        mapping:
          input_text: '#/components/schemas/ResponseInputTextContent'
    ResponseInputTextContent:
      type: object
      title: Input text
      description: A text input to the model.
      properties:
        type:
          type: string
          enum:
            - input_text
          description: The type of the input item. Always `input_text`.
          x-stainless-const: true
        text:
          type: string
          description: The text input to the model.
      required:
        - type
        - text
    ResponseItemReference:
      type: object
      title: Item reference
      description: An internal identifier for an item to reference.
      properties:
        type:
          type: string
          enum:
            - item_reference
          description: The type of item to reference. Always `item_reference`.
          x-stainless-const: true
        id:
          type: string
          description: The ID of the item to reference.
      required:
        - type
        - id
    ResponseFunctionCall:
      type: object
      title: Function call
      description: A function call generated by the model.
      properties:
        type:
          type: string
          enum:
            - function_call
          description: The type of the function call. Always `function_call`.
          x-stainless-const: true
        id:
          type: string
          description: The unique ID of the function tool call.
        call_id:
          type: string
          description: The unique ID of the function tool call generated by the model.
        name:
          type: string
          description: The name of the function to call.
        arguments:
          type: string
          description: A JSON string of the arguments to pass to the function.
        status:
          type: string
          description: The status of the item.
          enum:
            - in_progress
            - completed
            - incomplete
      required:
        - type
        - call_id
        - name
        - arguments
    ResponseFunctionCallOutput:
      type: object
      title: Function call output
      description: The output of a function tool call.
      properties:
        type:
          type: string
          enum:
            - function_call_output
          description: The type of the function tool call output. Always `function_call_output`.
          x-stainless-const: true
        id:
          type: string
          description: The unique ID of the function tool call output.
        call_id:
          type: string
          description: The unique ID of the function tool call generated by the model.
        output:
          type: string
          description: A JSON string of the output of the function tool call.
        status:
          type: string
          description: The status of the item.
          enum:
            - in_progress
            - completed
            - incomplete
      required:
        - type
        - call_id
        - output
    ResponseTool:
      type: object
      properties:
        type:
          type: string
          enum:
            - function
          description: The type of the tool. Currently, only `function` is supported.
        name:
          type: string
          description: >-
            The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes,
            with a maximum length of 64.
        description:
          type: string
          description: Describes the function's purpose. The model uses this to determine when to invoke the function.
        parameters:
          $ref: '#/components/schemas/FunctionParameters'
        strict:
          type: boolean
          nullable: true
          description: Whether to enable strict schema adherence when generating the function call.
      required:
        - type
        - name
    ResponseToolChoiceOption:
      nullable: true
      description: >
        Controls which (if any) tool is called by the model.

        `none` means the model will not call any tool and instead generates a message.

        `auto` means the model can pick between generating a message or calling one or more tools.

        `required` means the model must call one or more tools.

        Specifying a particular tool via `{"type": "function", "function": {"name": "my_function"}}` forces
        the model to call that tool.


        `none` is the default when no tools are present. `auto` is the default if tools are present.
      oneOf:
        - type: string
          description: >
            `none` means the model will not call any tool and instead generates a message. `auto` means the
            model can pick between generating a message or calling one or more tools. `required` means the
            model must call one or more tools.
          enum:
            - none
            - auto
            - required
        - $ref: '#/components/schemas/ResponseNamedToolChoice'
    ResponseNamedToolChoice:
      type: object
      description: Specifies a tool the model should use. Use to force the model to call a specific function.
      properties:
        type:
          type: string
          enum:
            - function
          description: The type of the tool. Currently, only `function` is supported.
        function:
          type: object
          properties:
            name:
              type: string
              description: The name of the function to call.
          required:
            - name
      required:
        - type
        - function
    ResponseFormatConfiguration:
      description: |
        An object specifying the format that the model must output.
      oneOf:
        - $ref: '#/components/schemas/ResponseFormatText'
        - $ref: '#/components/schemas/ResponseFormatJsonObject'
        - $ref: '#/components/schemas/TextResponseFormatJsonSchema'
    TextResponseFormatJsonSchema:
      type: object
      title: JSON schema
      description: |
        JSON Schema response format. Used to generate structured JSON responses.
      properties:
        type:
          type: string
          description: The type of response format being defined. Always `json_schema`.
          enum:
            - json_schema
          x-stainless-const: true
        name:
          type: string
          description: >
            The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a
            maximum length of 64.
        description:
          type: string
          description: >
            A description of what the response format is for, used by the model to determine how to respond in
            the format.
        schema:
          type: object
          description: |
            The schema for the response format, described as a JSON Schema object.
          additionalProperties: true
        strict:
          type: boolean
          nullable: true
          default: false
          description: |
            Whether to enable strict schema adherence when generating the output.
      required:
        - type
        - name
        - schema
    CreateResponseResponse:
      type: object
      description: Represents a response returned by model, based on the provided input.
      properties:
        id:
          type: string
          description: A unique identifier for the response.
        object:
          type: string
          description: The object type, which is always `response`.
          enum:
            - response
        status:
          type: string
          description: >
            The status of the response generation. One of `completed`, `failed`, `in_progress`, or
            `incomplete`.
          enum:
            - completed
            - failed
            - in_progress
            - incomplete
        created_at:
          type: integer
          description: The Unix timestamp (in seconds) of when the response was created.
        output:
          type: array
          description: An array of content items generated by the model.
          items:
            $ref: '#/components/schemas/ResponseOutputItem'
        previous_response_id:
          type: string
          description: Not supported. Always null.
          nullable: true
        model:
          type: string
          description: The model used for the response.
        reasoning:
          type: object
          nullable: true
          description: >-
            Configuration options for [models that support
            reasoning](https://console.groq.com/docs/reasoning).
          properties:
            effort:
              type: string
              enum:
                - low
                - medium
                - high
              nullable: true
              description: The reasoning effort level used.
            summary:
              type: string
              nullable: true
              description: Not supported. Always null.
        max_output_tokens:
          type: integer
          nullable: true
          description: The maximum number of tokens configured for the response.
        instructions:
          type: string
          nullable: true
          description: The system instructions used for the response.
        text:
          type: object
          description: Text format configuration used for the response.
          properties:
            format:
              $ref: '#/components/schemas/ResponseFormatConfiguration'
        tools:
          type: array
          description: The tools that were available to the model.
          items:
            $ref: '#/components/schemas/ResponseTool'
        tool_choice:
          $ref: '#/components/schemas/ResponseToolChoiceOption'
        truncation:
          type: string
          description: The truncation strategy used.
          enum:
            - auto
            - disabled
        metadata:
          type: object
          nullable: true
          additionalProperties:
            type: string
          description: Metadata attached to the response.
        temperature:
          type: number
          description: The sampling temperature used.
        top_p:
          type: number
          description: The nucleus sampling parameter used.
        user:
          type: string
          nullable: true
          description: The user identifier.
        service_tier:
          type: string
          description: The service tier used for processing.
          enum:
            - auto
            - default
            - flex
        error:
          type: object
          nullable: true
          description: An error object if the response failed.
          properties:
            code:
              type: string
              description: The error code.
            message:
              type: string
              description: A human-readable error message.
          required:
            - code
            - message
        incomplete_details:
          type: object
          nullable: true
          description: Details about why the response is incomplete.
          properties:
            reason:
              type: string
              description: The reason why the response is incomplete.
        usage:
          $ref: '#/components/schemas/ResponseUsage'
        parallel_tool_calls:
          type: boolean
          description: Whether the model can run tool calls in parallel.
        store:
          type: boolean
          description: Whether the response was stored.
        background:
          type: boolean
          description: Whether the response was generated in the background.
          default: false
        top_logprobs:
          type: integer
          description: The number of top log probabilities returned.
          default: 0
        max_tool_calls:
          type: integer
          nullable: true
          description: The maximum number of tool calls allowed.
      required:
        - id
        - object
        - status
        - created_at
        - output
        - model
        - tools
        - tool_choice
        - truncation
        - metadata
        - temperature
        - top_p
        - service_tier
        - error
        - incomplete_details
        - parallel_tool_calls
        - store
    ResponseOutputItem:
      oneOf:
        - $ref: '#/components/schemas/ResponseOutputMessage'
        - $ref: '#/components/schemas/ResponseOutputFunctionCall'
        - $ref: '#/components/schemas/ResponseOutputReasoning'
      discriminator:
        propertyName: type
        mapping:
          message: '#/components/schemas/ResponseOutputMessage'
          function_call: '#/components/schemas/ResponseOutputFunctionCall'
          reasoning: '#/components/schemas/ResponseOutputReasoning'
    ResponseOutputMessage:
      type: object
      title: Output message
      description: An output message from the model.
      properties:
        type:
          type: string
          description: The type of the output message. Always `message`.
          enum:
            - message
          x-stainless-const: true
        id:
          type: string
          description: The unique ID of the output message.
        status:
          type: string
          description: The status of the message.
          enum:
            - in_progress
            - completed
            - incomplete
        role:
          type: string
          description: The role of the output message. Always `assistant`.
          enum:
            - assistant
          x-stainless-const: true
        content:
          type: array
          description: The content of the output message.
          items:
            $ref: '#/components/schemas/ResponseOutputContent'
      required:
        - type
        - id
        - role
        - content
    ResponseOutputContent:
      oneOf:
        - $ref: '#/components/schemas/ResponseOutputTextContent'
      discriminator:
        propertyName: type
        mapping:
          output_text: '#/components/schemas/ResponseOutputTextContent'
    ResponseOutputTextContent:
      type: object
      title: Output text
      description: A text output from the model.
      properties:
        type:
          type: string
          enum:
            - output_text
          description: The type of the output text. Always `output_text`.
          x-stainless-const: true
        text:
          type: string
          description: The text output from the model.
        annotations:
          type: array
          description: The annotations of the text output.
          items:
            $ref: '#/components/schemas/ResponseAnnotation'
        logprobs:
          type: array
          nullable: true
          description: Log probability information for the output.
          items:
            type: string
      required:
        - type
        - text
        - annotations
    ResponseAnnotation:
      oneOf:
        - $ref: '#/components/schemas/ResponseFileCitation'
        - $ref: '#/components/schemas/ResponseUrlCitation'
      discriminator:
        propertyName: type
        mapping:
          file_citation: '#/components/schemas/ResponseFileCitation'
          url_citation: '#/components/schemas/ResponseUrlCitation'
    ResponseFileCitation:
      type: object
      title: File citation
      description: A citation to a file.
      properties:
        type:
          type: string
          enum:
            - file_citation
          description: The type of the annotation. Always `file_citation`.
          x-stainless-const: true
        file_id:
          type: string
          description: The ID of the file.
        index:
          type: integer
          description: The index of the citation in the text.
      required:
        - type
        - file_id
    ResponseUrlCitation:
      type: object
      title: URL citation
      description: A citation for a web resource.
      properties:
        type:
          type: string
          enum:
            - url_citation
          description: The type of the annotation. Always `url_citation`.
          x-stainless-const: true
        url:
          type: string
          description: The URL of the web resource.
        start_index:
          type: integer
          description: The index of the first character of the URL citation in the message.
        end_index:
          type: integer
          description: The index of the last character of the URL citation in the message.
        title:
          type: string
          description: The title of the web resource.
      required:
        - type
        - url
    ResponseOutputFunctionCall:
      type: object
      title: Function call
      description: A function call generated by the model.
      properties:
        type:
          type: string
          enum:
            - function_call
          description: The type of the function call. Always `function_call`.
          x-stainless-const: true
        id:
          type: string
          description: The unique ID of the function tool call.
        status:
          type: string
          description: The status of the function call.
          enum:
            - in_progress
            - completed
            - incomplete
        call_id:
          type: string
          description: The unique ID of the function tool call generated by the model.
        name:
          type: string
          description: The name of the function to call.
        arguments:
          type: string
          description: A JSON string of the arguments to pass to the function.
      required:
        - type
        - id
        - call_id
        - name
        - arguments
    ResponseOutputReasoning:
      type: object
      title: Reasoning
      description: >-
        A reasoning output from the model. Available for [models that support
        reasoning](https://console.groq.com/docs/reasoning).
      properties:
        type:
          type: string
          enum:
            - reasoning
          description: The type of the reasoning output. Always `reasoning`.
          x-stainless-const: true
        id:
          type: string
          description: The unique ID of the reasoning output.
        summary:
          type: array
          description: Summary items (currently empty).
          items:
            type: object
      required:
        - type
        - id
        - summary
    ResponseUsage:
      type: object
      description: Usage statistics for the response request.
      properties:
        input_tokens:
          type: integer
          description: Number of tokens in the input.
        input_tokens_details:
          type: object
          description: Breakdown of input tokens.
          properties:
            cached_tokens:
              type: integer
              description: Number of cached tokens.
            reasoning_tokens:
              type: integer
              description: Number of reasoning tokens.
          required:
            - cached_tokens
        output_tokens:
          type: integer
          description: Number of tokens in the generated output.
        output_tokens_details:
          type: object
          description: Breakdown of output tokens.
          properties:
            cached_tokens:
              type: integer
              description: Number of cached tokens.
            reasoning_tokens:
              type: integer
              description: Number of reasoning tokens.
          required:
            - cached_tokens
            - reasoning_tokens
        total_tokens:
          type: integer
          description: Total number of tokens used in the request (input + output).
      required:
        - input_tokens
        - input_tokens_details
        - output_tokens
        - output_tokens_details
        - total_tokens
security:
  - api_key: []
x-groq-metadata:
  groups:
    - id: chat
      type: endpoints
      title: Chat
      description: ''
      sections:
        - type: endpoint
          key: createChatCompletion
          path: create
    - id: responses
      type: endpoints
      title: Responses (beta)
      description: ''
      sections:
        - type: endpoint
          key: createResponse
          path: create
    - id: audio
      type: endpoints
      title: Audio
      description: ''
      sections:
        - type: endpoint
          key: createTranscription
          path: transcription
        - type: endpoint
          key: createTranslation
          path: translation
        - type: endpoint
          key: createSpeech
          path: speech
    - id: models
      type: endpoints
      title: Models
      description: ''
      sections:
        - type: endpoint
          key: listModels
          path: list
        - type: endpoint
          key: retrieveModel
          path: retrieve
    - id: batches
      type: endpoints
      title: Batches
      description: ''
      sections:
        - type: endpoint
          key: createBatch
          path: create
        - type: endpoint
          key: retrieveBatch
          path: retrieve
        - type: endpoint
          key: listBatches
          path: list
        - type: endpoint
          key: cancelBatch
          path: cancel
    - id: files
      type: endpoints
      title: Files
      description: ''
      sections:
        - type: endpoint
          key: uploadFile
          path: upload
        - type: endpoint
          key: listFiles
          path: list
        - type: endpoint
          key: deleteFile
          path: delete
        - type: endpoint
          key: retrieveFile
          path: retrieve
        - type: endpoint
          key: downloadFile
          path: download
    - id: fine-tuning
      type: endpoints
      title: Fine Tuning
      description: ''
      sections:
        - type: endpoint
          key: listFineTunings
          path: list
        - type: endpoint
          key: createFineTuning
          path: create
        - type: endpoint
          key: getFineTuning
          path: get
        - type: endpoint
          key: deleteFineTuning
          path: delete