@theokit/sdk 4.19.0 → 4.19.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -1,1620 +0,0 @@
1
- [
2
- {
3
- "id": "openai",
4
- "displayName": "OpenAI",
5
- "apiMode": "chat_completions",
6
- "authType": "api_key",
7
- "baseUrl": "https://api.openai.com/v1",
8
- "envVars": [
9
- "OPENAI_API_KEY"
10
- ],
11
- "fallbackModels": [
12
- "gpt-4o-mini",
13
- "gpt-4o"
14
- ],
15
- "capabilities": {
16
- "supportsToolUse": true,
17
- "supportsVision": true,
18
- "supportsStructuredOutput": true,
19
- "supportsStreaming": true,
20
- "supportsCacheControl": false
21
- },
22
- "aliases": [
23
- "openai",
24
- "openai-chatgpt"
25
- ],
26
- "models": {
27
- "gpt-4o-mini": {
28
- "name": "GPT-4o mini",
29
- "release_date": "2024-07-18",
30
- "attachment": true,
31
- "reasoning": false,
32
- "temperature": true,
33
- "tool_call": true,
34
- "structured_output": true,
35
- "cost": {
36
- "input": 0.15,
37
- "output": 0.6,
38
- "cache_read": 0.075
39
- },
40
- "limit": {
41
- "context": 128000,
42
- "output": 16384
43
- },
44
- "modalities": {
45
- "input": [
46
- "text",
47
- "image"
48
- ],
49
- "output": [
50
- "text"
51
- ]
52
- },
53
- "cache_control": false
54
- },
55
- "gpt-4o": {
56
- "name": "GPT-4o",
57
- "release_date": "2024-05-13",
58
- "attachment": true,
59
- "reasoning": false,
60
- "temperature": true,
61
- "tool_call": true,
62
- "structured_output": true,
63
- "cost": {
64
- "input": 2.5,
65
- "output": 10,
66
- "cache_read": 1.25
67
- },
68
- "limit": {
69
- "context": 128000,
70
- "output": 16384
71
- },
72
- "modalities": {
73
- "input": [
74
- "text",
75
- "image"
76
- ],
77
- "output": [
78
- "text"
79
- ]
80
- },
81
- "cache_control": false
82
- },
83
- "gpt-4-turbo": {
84
- "name": "GPT-4 Turbo",
85
- "release_date": "2023-11-06",
86
- "attachment": true,
87
- "reasoning": false,
88
- "temperature": true,
89
- "tool_call": true,
90
- "structured_output": false,
91
- "cost": {
92
- "input": 10,
93
- "output": 30
94
- },
95
- "limit": {
96
- "context": 128000,
97
- "output": 4096
98
- },
99
- "modalities": {
100
- "input": [
101
- "text",
102
- "image"
103
- ],
104
- "output": [
105
- "text"
106
- ]
107
- },
108
- "cache_control": false
109
- },
110
- "o1": {
111
- "name": "o1",
112
- "release_date": "2024-12-05",
113
- "attachment": true,
114
- "reasoning": true,
115
- "temperature": false,
116
- "tool_call": true,
117
- "structured_output": true,
118
- "cost": {
119
- "input": 15,
120
- "output": 60,
121
- "cache_read": 7.5
122
- },
123
- "limit": {
124
- "context": 200000,
125
- "output": 100000
126
- },
127
- "modalities": {
128
- "input": [
129
- "text"
130
- ],
131
- "output": [
132
- "text"
133
- ]
134
- },
135
- "cache_control": false
136
- },
137
- "o3": {
138
- "name": "o3",
139
- "release_date": "2025-04-16",
140
- "attachment": true,
141
- "reasoning": true,
142
- "temperature": false,
143
- "tool_call": true,
144
- "structured_output": true,
145
- "cost": {
146
- "input": 2,
147
- "output": 8,
148
- "cache_read": 0.5
149
- },
150
- "limit": {
151
- "context": 200000,
152
- "output": 100000
153
- },
154
- "modalities": {
155
- "input": [
156
- "text"
157
- ],
158
- "output": [
159
- "text"
160
- ]
161
- },
162
- "cache_control": false
163
- },
164
- "gpt-4.1": {
165
- "name": "GPT-4.1",
166
- "release_date": "2025-04-14",
167
- "attachment": true,
168
- "reasoning": false,
169
- "temperature": true,
170
- "tool_call": true,
171
- "structured_output": true,
172
- "cost": {
173
- "input": 2,
174
- "output": 8,
175
- "cache_read": 0.5
176
- },
177
- "limit": {
178
- "context": 1047576,
179
- "output": 32768
180
- },
181
- "modalities": {
182
- "input": [
183
- "text",
184
- "image"
185
- ],
186
- "output": [
187
- "text"
188
- ]
189
- },
190
- "cache_control": false
191
- },
192
- "gpt-5.4": {
193
- "limit": {
194
- "context": 400000,
195
- "output": 128000
196
- }
197
- },
198
- "gpt-5.4-mini": {
199
- "limit": {
200
- "context": 400000,
201
- "output": 128000
202
- }
203
- },
204
- "gpt-5.3": {
205
- "limit": {
206
- "context": 400000,
207
- "output": 128000
208
- }
209
- },
210
- "gpt-5.2": {
211
- "limit": {
212
- "context": 400000,
213
- "output": 128000
214
- }
215
- }
216
- }
217
- },
218
- {
219
- "id": "anthropic",
220
- "displayName": "Anthropic",
221
- "apiMode": "anthropic_messages",
222
- "authType": "api_key",
223
- "baseUrl": "https://api.anthropic.com/v1",
224
- "envVars": [
225
- "ANTHROPIC_API_KEY"
226
- ],
227
- "fallbackModels": [
228
- "claude-sonnet-4-20250514",
229
- "claude-3-5-haiku-latest"
230
- ],
231
- "capabilities": {
232
- "supportsToolUse": true,
233
- "supportsVision": true,
234
- "supportsStructuredOutput": false,
235
- "supportsStreaming": true,
236
- "supportsCacheControl": true
237
- },
238
- "aliases": [
239
- "anthropic"
240
- ],
241
- "models": {
242
- "claude-3-5-haiku-latest": {
243
- "tool_call": true,
244
- "structured_output": false,
245
- "cache_control": true,
246
- "modalities": {
247
- "input": [
248
- "text"
249
- ]
250
- },
251
- "limit": {
252
- "context": 200000,
253
- "output": 8192
254
- }
255
- },
256
- "claude-opus-4-7": {
257
- "name": "Claude Opus 4.7",
258
- "release_date": "2026-04-14",
259
- "attachment": true,
260
- "reasoning": true,
261
- "temperature": false,
262
- "tool_call": true,
263
- "structured_output": true,
264
- "cost": {
265
- "input": 5,
266
- "output": 25,
267
- "cache_read": 0.5,
268
- "cache_write": 6.25
269
- },
270
- "limit": {
271
- "context": 1000000,
272
- "output": 128000
273
- },
274
- "modalities": {
275
- "input": [
276
- "text",
277
- "image",
278
- "pdf"
279
- ],
280
- "output": [
281
- "text"
282
- ]
283
- },
284
- "cache_control": true
285
- },
286
- "claude-sonnet-4-6": {
287
- "name": "Claude Sonnet 4.6",
288
- "release_date": "2026-02-17",
289
- "attachment": true,
290
- "reasoning": true,
291
- "temperature": true,
292
- "tool_call": true,
293
- "structured_output": true,
294
- "cost": {
295
- "input": 3,
296
- "output": 15,
297
- "cache_read": 0.3,
298
- "cache_write": 3.75
299
- },
300
- "limit": {
301
- "context": 1000000,
302
- "output": 128000
303
- },
304
- "modalities": {
305
- "input": [
306
- "text",
307
- "image",
308
- "pdf"
309
- ],
310
- "output": [
311
- "text"
312
- ]
313
- },
314
- "cache_control": true
315
- },
316
- "claude-haiku-4-5-20251001": {
317
- "name": "Claude Haiku 4.5",
318
- "release_date": "2025-10-15",
319
- "attachment": true,
320
- "reasoning": true,
321
- "temperature": true,
322
- "tool_call": true,
323
- "structured_output": true,
324
- "cost": {
325
- "input": 1,
326
- "output": 5,
327
- "cache_read": 0.1,
328
- "cache_write": 1.25
329
- },
330
- "limit": {
331
- "context": 200000,
332
- "output": 64000
333
- },
334
- "modalities": {
335
- "input": [
336
- "text",
337
- "image",
338
- "pdf"
339
- ],
340
- "output": [
341
- "text"
342
- ]
343
- },
344
- "cache_control": true
345
- },
346
- "claude-opus-4": {
347
- "tool_call": true,
348
- "structured_output": false,
349
- "cache_control": true,
350
- "modalities": {
351
- "input": [
352
- "text",
353
- "image"
354
- ]
355
- },
356
- "limit": {
357
- "context": 200000,
358
- "output": 32000
359
- }
360
- },
361
- "claude-sonnet-4": {
362
- "tool_call": true,
363
- "structured_output": false,
364
- "cache_control": true,
365
- "modalities": {
366
- "input": [
367
- "text",
368
- "image"
369
- ]
370
- },
371
- "limit": {
372
- "context": 200000,
373
- "output": 16000
374
- }
375
- },
376
- "claude-3-5-sonnet": {
377
- "tool_call": true,
378
- "structured_output": false,
379
- "cache_control": true,
380
- "modalities": {
381
- "input": [
382
- "text",
383
- "image"
384
- ]
385
- },
386
- "limit": {
387
- "context": 200000,
388
- "output": 8192
389
- }
390
- },
391
- "claude-3-5-sonnet-latest": {
392
- "tool_call": true,
393
- "structured_output": false,
394
- "cache_control": true,
395
- "modalities": {
396
- "input": [
397
- "text",
398
- "image"
399
- ]
400
- },
401
- "limit": {
402
- "context": 200000,
403
- "output": 8192
404
- }
405
- },
406
- "claude-3-haiku": {
407
- "tool_call": true,
408
- "structured_output": false,
409
- "cache_control": true,
410
- "modalities": {
411
- "input": [
412
- "text",
413
- "image"
414
- ]
415
- },
416
- "limit": {
417
- "context": 200000,
418
- "output": 4096
419
- }
420
- },
421
- "claude-3-opus": {
422
- "tool_call": true,
423
- "structured_output": false,
424
- "cache_control": true,
425
- "modalities": {
426
- "input": [
427
- "text",
428
- "image"
429
- ]
430
- },
431
- "limit": {
432
- "context": 200000,
433
- "output": 4096
434
- }
435
- },
436
- "claude-opus-4.1": {
437
- "tool_call": true,
438
- "structured_output": false,
439
- "cache_control": true,
440
- "modalities": {
441
- "input": [
442
- "text",
443
- "image"
444
- ]
445
- },
446
- "limit": {
447
- "context": 200000,
448
- "output": 32000
449
- }
450
- },
451
- "claude-sonnet-4.5": {
452
- "tool_call": true,
453
- "structured_output": false,
454
- "cache_control": true,
455
- "modalities": {
456
- "input": [
457
- "text",
458
- "image"
459
- ]
460
- },
461
- "limit": {
462
- "context": 200000,
463
- "output": 16000
464
- }
465
- },
466
- "claude-3.5-sonnet": {
467
- "tool_call": true,
468
- "structured_output": false,
469
- "cache_control": true,
470
- "modalities": {
471
- "input": [
472
- "text",
473
- "image"
474
- ]
475
- },
476
- "limit": {
477
- "context": 200000,
478
- "output": 8192
479
- }
480
- }
481
- }
482
- },
483
- {
484
- "id": "openrouter",
485
- "displayName": "OpenRouter",
486
- "apiMode": "chat_completions",
487
- "authType": "api_key",
488
- "baseUrl": "https://openrouter.ai/api/v1",
489
- "envVars": [
490
- "OPENROUTER_API_KEY"
491
- ],
492
- "fallbackModels": [
493
- "openai/gpt-4o-mini"
494
- ],
495
- "capabilities": {
496
- "supportsToolUse": true,
497
- "supportsVision": true,
498
- "supportsStructuredOutput": true,
499
- "supportsStreaming": true,
500
- "supportsCacheControl": false
501
- },
502
- "aliases": [
503
- "openrouter"
504
- ]
505
- },
506
- {
507
- "id": "groq",
508
- "displayName": "Groq",
509
- "apiMode": "chat_completions",
510
- "authType": "api_key",
511
- "baseUrl": "https://api.groq.com/openai/v1",
512
- "envVars": [
513
- "GROQ_API_KEY"
514
- ],
515
- "fallbackModels": [
516
- "llama-3.3-70b-versatile"
517
- ],
518
- "capabilities": {
519
- "supportsToolUse": true,
520
- "supportsVision": true,
521
- "supportsStructuredOutput": true,
522
- "supportsStreaming": true,
523
- "supportsCacheControl": false
524
- },
525
- "models": {
526
- "llama-3.3-70b-versatile": {
527
- "name": "Llama 3.3 70B",
528
- "release_date": "2024-12-06",
529
- "attachment": false,
530
- "reasoning": false,
531
- "temperature": true,
532
- "tool_call": true,
533
- "cost": {
534
- "input": 0.59,
535
- "output": 0.79
536
- },
537
- "limit": {
538
- "context": 131072,
539
- "output": 32768
540
- },
541
- "modalities": {
542
- "input": [
543
- "text"
544
- ],
545
- "output": [
546
- "text"
547
- ]
548
- }
549
- }
550
- }
551
- },
552
- {
553
- "id": "mistral",
554
- "displayName": "Mistral AI",
555
- "apiMode": "chat_completions",
556
- "authType": "api_key",
557
- "baseUrl": "https://api.mistral.ai/v1",
558
- "envVars": [
559
- "MISTRAL_API_KEY"
560
- ],
561
- "fallbackModels": [
562
- "mistral-large-latest"
563
- ],
564
- "capabilities": {
565
- "supportsToolUse": true,
566
- "supportsVision": true,
567
- "supportsStructuredOutput": true,
568
- "supportsStreaming": true,
569
- "supportsCacheControl": false
570
- },
571
- "models": {
572
- "mistral-large-latest": {
573
- "name": "Mistral Large (latest)",
574
- "release_date": "2024-11-01",
575
- "attachment": true,
576
- "reasoning": false,
577
- "temperature": true,
578
- "tool_call": true,
579
- "cost": {
580
- "input": 0.5,
581
- "output": 1.5
582
- },
583
- "limit": {
584
- "context": 262144,
585
- "output": 262144
586
- },
587
- "modalities": {
588
- "input": [
589
- "text",
590
- "image"
591
- ],
592
- "output": [
593
- "text"
594
- ]
595
- }
596
- }
597
- }
598
- },
599
- {
600
- "id": "deepseek",
601
- "displayName": "DeepSeek",
602
- "apiMode": "chat_completions",
603
- "authType": "api_key",
604
- "baseUrl": "https://api.deepseek.com/v1",
605
- "envVars": [
606
- "DEEPSEEK_API_KEY"
607
- ],
608
- "fallbackModels": [
609
- "deepseek-chat"
610
- ],
611
- "capabilities": {
612
- "supportsToolUse": true,
613
- "supportsVision": false,
614
- "supportsStructuredOutput": true,
615
- "supportsStreaming": true,
616
- "supportsCacheControl": false
617
- },
618
- "models": {
619
- "deepseek-chat": {
620
- "name": "DeepSeek Chat",
621
- "release_date": "2025-12-01",
622
- "attachment": true,
623
- "reasoning": false,
624
- "temperature": true,
625
- "tool_call": true,
626
- "cost": {
627
- "input": 0.14,
628
- "output": 0.28,
629
- "cache_read": 0.0028
630
- },
631
- "limit": {
632
- "context": 1000000,
633
- "output": 384000
634
- },
635
- "modalities": {
636
- "input": [
637
- "text"
638
- ],
639
- "output": [
640
- "text"
641
- ]
642
- }
643
- },
644
- "deepseek-v4-flash": {
645
- "name": "DeepSeek V4 Flash",
646
- "release_date": "2026-04-24",
647
- "attachment": false,
648
- "reasoning": true,
649
- "temperature": true,
650
- "tool_call": true,
651
- "structured_output": false,
652
- "cost": {
653
- "input": 0.14,
654
- "output": 0.28,
655
- "cache_read": 0.0028
656
- },
657
- "limit": {
658
- "context": 1048576,
659
- "output": 8000
660
- },
661
- "modalities": {
662
- "input": [
663
- "text"
664
- ],
665
- "output": [
666
- "text"
667
- ]
668
- },
669
- "cache_control": false
670
- },
671
- "deepseek-v3.2": {
672
- "tool_call": true,
673
- "structured_output": false,
674
- "cache_control": false,
675
- "modalities": {
676
- "input": [
677
- "text"
678
- ]
679
- },
680
- "limit": {
681
- "context": 131072,
682
- "output": 8000
683
- }
684
- }
685
- }
686
- },
687
- {
688
- "id": "together",
689
- "displayName": "Together AI",
690
- "apiMode": "chat_completions",
691
- "authType": "api_key",
692
- "baseUrl": "https://api.together.xyz/v1",
693
- "envVars": [
694
- "TOGETHER_API_KEY"
695
- ],
696
- "fallbackModels": [
697
- "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo"
698
- ],
699
- "capabilities": {
700
- "supportsToolUse": true,
701
- "supportsVision": true,
702
- "supportsStructuredOutput": true,
703
- "supportsStreaming": true,
704
- "supportsCacheControl": false
705
- }
706
- },
707
- {
708
- "id": "fireworks",
709
- "displayName": "Fireworks AI",
710
- "apiMode": "chat_completions",
711
- "authType": "api_key",
712
- "baseUrl": "https://api.fireworks.ai/inference/v1",
713
- "envVars": [
714
- "FIREWORKS_API_KEY"
715
- ],
716
- "fallbackModels": [
717
- "accounts/fireworks/models/llama-v3p1-70b-instruct"
718
- ],
719
- "capabilities": {
720
- "supportsToolUse": true,
721
- "supportsVision": true,
722
- "supportsStructuredOutput": true,
723
- "supportsStreaming": true,
724
- "supportsCacheControl": false
725
- }
726
- },
727
- {
728
- "id": "google-gemini",
729
- "displayName": "Google Gemini",
730
- "apiMode": "chat_completions",
731
- "authType": "api_key",
732
- "baseUrl": "https://generativelanguage.googleapis.com/v1beta/openai",
733
- "envVars": [
734
- "GOOGLE_API_KEY",
735
- "GEMINI_API_KEY"
736
- ],
737
- "fallbackModels": [
738
- "gemini-2.0-flash"
739
- ],
740
- "capabilities": {
741
- "supportsToolUse": true,
742
- "supportsVision": true,
743
- "supportsStructuredOutput": true,
744
- "supportsStreaming": true,
745
- "supportsCacheControl": false
746
- },
747
- "aliases": [
748
- "gemini",
749
- "google"
750
- ],
751
- "models": {
752
- "gemini-2.0-flash": {
753
- "name": "Gemini 2.0 Flash",
754
- "release_date": "2024-12-11",
755
- "attachment": true,
756
- "reasoning": false,
757
- "temperature": true,
758
- "tool_call": true,
759
- "structured_output": true,
760
- "cost": {
761
- "input": 0.1,
762
- "output": 0.4,
763
- "cache_read": 0.025
764
- },
765
- "limit": {
766
- "context": 1048576,
767
- "output": 8192
768
- },
769
- "modalities": {
770
- "input": [
771
- "text",
772
- "image",
773
- "audio",
774
- "video",
775
- "pdf"
776
- ],
777
- "output": [
778
- "text"
779
- ]
780
- },
781
- "status": "deprecated"
782
- },
783
- "gemini-2.5-flash-lite": {
784
- "name": "Gemini 2.5 Flash-Lite",
785
- "release_date": "2025-06-17",
786
- "attachment": true,
787
- "reasoning": true,
788
- "temperature": true,
789
- "tool_call": true,
790
- "structured_output": true,
791
- "cost": {
792
- "input": 0.1,
793
- "output": 0.4,
794
- "cache_read": 0.01
795
- },
796
- "limit": {
797
- "context": 1048576,
798
- "output": 8000
799
- },
800
- "modalities": {
801
- "input": [
802
- "text",
803
- "image"
804
- ],
805
- "output": [
806
- "text"
807
- ]
808
- },
809
- "cache_control": false
810
- },
811
- "gemini-2.5-pro": {
812
- "name": "Gemini 2.5 Pro",
813
- "release_date": "2025-06-17",
814
- "attachment": true,
815
- "reasoning": true,
816
- "temperature": true,
817
- "tool_call": true,
818
- "structured_output": true,
819
- "cost": {
820
- "input": 1.25,
821
- "output": 10,
822
- "cache_read": 0.125
823
- },
824
- "limit": {
825
- "context": 1048576,
826
- "output": 8000
827
- },
828
- "modalities": {
829
- "input": [
830
- "text",
831
- "image"
832
- ],
833
- "output": [
834
- "text"
835
- ]
836
- },
837
- "cache_control": false
838
- }
839
- }
840
- },
841
- {
842
- "id": "ollama",
843
- "displayName": "Ollama",
844
- "apiMode": "chat_completions",
845
- "authType": "none",
846
- "baseUrl": "http://localhost:11434/v1",
847
- "envVars": [],
848
- "fallbackModels": [
849
- "llama3.2"
850
- ],
851
- "capabilities": {
852
- "supportsToolUse": true,
853
- "supportsVision": true,
854
- "supportsStructuredOutput": true,
855
- "supportsStreaming": true,
856
- "supportsCacheControl": false
857
- },
858
- "aliases": [
859
- "ollama"
860
- ]
861
- },
862
- {
863
- "id": "lmstudio",
864
- "displayName": "LM Studio",
865
- "apiMode": "chat_completions",
866
- "authType": "none",
867
- "baseUrl": "http://localhost:1234/v1",
868
- "envVars": [],
869
- "fallbackModels": [
870
- "lmstudio-community/default"
871
- ],
872
- "capabilities": {
873
- "supportsToolUse": true,
874
- "supportsVision": false,
875
- "supportsStructuredOutput": true,
876
- "supportsStreaming": true,
877
- "supportsCacheControl": false
878
- },
879
- "aliases": [
880
- "lmstudio"
881
- ]
882
- },
883
- {
884
- "id": "llamacpp",
885
- "displayName": "llama.cpp",
886
- "apiMode": "chat_completions",
887
- "authType": "none",
888
- "baseUrl": "http://localhost:8080/v1",
889
- "envVars": [],
890
- "fallbackModels": [
891
- "default"
892
- ],
893
- "capabilities": {
894
- "supportsToolUse": true,
895
- "supportsVision": false,
896
- "supportsStructuredOutput": false,
897
- "supportsStreaming": true,
898
- "supportsCacheControl": false
899
- },
900
- "aliases": [
901
- "llamacpp"
902
- ]
903
- },
904
- {
905
- "id": "bedrock",
906
- "displayName": "AWS Bedrock",
907
- "apiMode": "bedrock",
908
- "authType": "aws_sdk",
909
- "baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com",
910
- "envVars": [
911
- "AWS_ACCESS_KEY_ID",
912
- "AWS_SECRET_ACCESS_KEY"
913
- ],
914
- "fallbackModels": [
915
- "anthropic.claude-3-5-sonnet-20241022-v2:0"
916
- ],
917
- "capabilities": {
918
- "supportsToolUse": true,
919
- "supportsVision": true,
920
- "supportsStructuredOutput": false,
921
- "supportsStreaming": true,
922
- "supportsCacheControl": true
923
- },
924
- "aliases": [
925
- "bedrock"
926
- ]
927
- },
928
- {
929
- "id": "vertex",
930
- "displayName": "Google Vertex AI",
931
- "apiMode": "chat_completions",
932
- "authType": "gcp_oauth",
933
- "baseUrl": "https://us-central1-aiplatform.googleapis.com/v1",
934
- "envVars": [
935
- "GOOGLE_APPLICATION_CREDENTIALS"
936
- ],
937
- "fallbackModels": [
938
- "gemini-1.5-pro"
939
- ],
940
- "capabilities": {
941
- "supportsToolUse": true,
942
- "supportsVision": true,
943
- "supportsStructuredOutput": true,
944
- "supportsStreaming": true,
945
- "supportsCacheControl": false
946
- },
947
- "aliases": [
948
- "vertex"
949
- ]
950
- },
951
- {
952
- "id": "cohere",
953
- "displayName": "Cohere",
954
- "apiMode": "chat_completions",
955
- "authType": "api_key",
956
- "baseUrl": "https://api.cohere.com/v2",
957
- "envVars": [
958
- "COHERE_API_KEY"
959
- ],
960
- "fallbackModels": [
961
- "command-r-plus"
962
- ],
963
- "capabilities": {
964
- "supportsToolUse": true,
965
- "supportsVision": false,
966
- "supportsStructuredOutput": true,
967
- "supportsStreaming": true,
968
- "supportsCacheControl": false
969
- }
970
- },
971
- {
972
- "id": "perplexity",
973
- "displayName": "Perplexity",
974
- "apiMode": "chat_completions",
975
- "authType": "api_key",
976
- "baseUrl": "https://api.perplexity.ai",
977
- "envVars": [
978
- "PERPLEXITY_API_KEY"
979
- ],
980
- "fallbackModels": [
981
- "llama-3.1-sonar-large-128k-online"
982
- ],
983
- "capabilities": {
984
- "supportsToolUse": false,
985
- "supportsVision": false,
986
- "supportsStructuredOutput": false,
987
- "supportsStreaming": true,
988
- "supportsCacheControl": false
989
- }
990
- },
991
- {
992
- "id": "xai",
993
- "displayName": "xAI (Grok)",
994
- "apiMode": "chat_completions",
995
- "authType": "api_key",
996
- "baseUrl": "https://api.x.ai/v1",
997
- "envVars": [
998
- "XAI_API_KEY"
999
- ],
1000
- "fallbackModels": [
1001
- "grok-2"
1002
- ],
1003
- "capabilities": {
1004
- "supportsToolUse": true,
1005
- "supportsVision": true,
1006
- "supportsStructuredOutput": true,
1007
- "supportsStreaming": true,
1008
- "supportsCacheControl": false
1009
- },
1010
- "aliases": [
1011
- "grok"
1012
- ]
1013
- },
1014
- {
1015
- "id": "sambanova",
1016
- "displayName": "SambaNova",
1017
- "apiMode": "chat_completions",
1018
- "authType": "api_key",
1019
- "baseUrl": "https://api.sambanova.ai/v1",
1020
- "envVars": [
1021
- "SAMBANOVA_API_KEY"
1022
- ],
1023
- "fallbackModels": [
1024
- "Meta-Llama-3.1-70B-Instruct"
1025
- ],
1026
- "capabilities": {
1027
- "supportsToolUse": true,
1028
- "supportsVision": false,
1029
- "supportsStructuredOutput": true,
1030
- "supportsStreaming": true,
1031
- "supportsCacheControl": false
1032
- }
1033
- },
1034
- {
1035
- "id": "cerebras",
1036
- "displayName": "Cerebras",
1037
- "apiMode": "chat_completions",
1038
- "authType": "api_key",
1039
- "baseUrl": "https://api.cerebras.ai/v1",
1040
- "envVars": [
1041
- "CEREBRAS_API_KEY"
1042
- ],
1043
- "fallbackModels": [
1044
- "llama3.1-70b"
1045
- ],
1046
- "capabilities": {
1047
- "supportsToolUse": true,
1048
- "supportsVision": false,
1049
- "supportsStructuredOutput": true,
1050
- "supportsStreaming": true,
1051
- "supportsCacheControl": false
1052
- }
1053
- },
1054
- {
1055
- "id": "deepinfra",
1056
- "displayName": "DeepInfra",
1057
- "apiMode": "chat_completions",
1058
- "authType": "api_key",
1059
- "baseUrl": "https://api.deepinfra.com/v1/openai",
1060
- "envVars": [
1061
- "DEEPINFRA_API_KEY"
1062
- ],
1063
- "fallbackModels": [
1064
- "meta-llama/Meta-Llama-3.1-70B-Instruct"
1065
- ],
1066
- "capabilities": {
1067
- "supportsToolUse": true,
1068
- "supportsVision": true,
1069
- "supportsStructuredOutput": true,
1070
- "supportsStreaming": true,
1071
- "supportsCacheControl": false
1072
- }
1073
- },
1074
- {
1075
- "id": "huggingface",
1076
- "displayName": "Hugging Face",
1077
- "apiMode": "chat_completions",
1078
- "authType": "api_key",
1079
- "baseUrl": "https://api-inference.huggingface.co/v1",
1080
- "envVars": [
1081
- "HF_TOKEN",
1082
- "HUGGINGFACE_API_KEY"
1083
- ],
1084
- "fallbackModels": [
1085
- "meta-llama/Llama-3.2-3B-Instruct"
1086
- ],
1087
- "capabilities": {
1088
- "supportsToolUse": true,
1089
- "supportsVision": false,
1090
- "supportsStructuredOutput": false,
1091
- "supportsStreaming": true,
1092
- "supportsCacheControl": false
1093
- }
1094
- },
1095
- {
1096
- "id": "nvidia",
1097
- "displayName": "NVIDIA NIM",
1098
- "apiMode": "chat_completions",
1099
- "authType": "api_key",
1100
- "baseUrl": "https://integrate.api.nvidia.com/v1",
1101
- "envVars": [
1102
- "NVIDIA_API_KEY"
1103
- ],
1104
- "fallbackModels": [
1105
- "meta/llama-3.1-70b-instruct"
1106
- ],
1107
- "capabilities": {
1108
- "supportsToolUse": true,
1109
- "supportsVision": true,
1110
- "supportsStructuredOutput": true,
1111
- "supportsStreaming": true,
1112
- "supportsCacheControl": false
1113
- }
1114
- },
1115
- {
1116
- "id": "lepton",
1117
- "displayName": "Lepton AI",
1118
- "apiMode": "chat_completions",
1119
- "authType": "api_key",
1120
- "baseUrl": "https://llama3-1-70b.lepton.run/api/v1",
1121
- "envVars": [
1122
- "LEPTON_API_KEY"
1123
- ],
1124
- "fallbackModels": [
1125
- "llama3-1-70b"
1126
- ],
1127
- "capabilities": {
1128
- "supportsToolUse": true,
1129
- "supportsVision": false,
1130
- "supportsStructuredOutput": false,
1131
- "supportsStreaming": true,
1132
- "supportsCacheControl": false
1133
- }
1134
- },
1135
- {
1136
- "id": "anyscale",
1137
- "displayName": "Anyscale",
1138
- "apiMode": "chat_completions",
1139
- "authType": "api_key",
1140
- "baseUrl": "https://api.endpoints.anyscale.com/v1",
1141
- "envVars": [
1142
- "ANYSCALE_API_KEY"
1143
- ],
1144
- "fallbackModels": [
1145
- "meta-llama/Meta-Llama-3-70B-Instruct"
1146
- ],
1147
- "capabilities": {
1148
- "supportsToolUse": true,
1149
- "supportsVision": false,
1150
- "supportsStructuredOutput": true,
1151
- "supportsStreaming": true,
1152
- "supportsCacheControl": false
1153
- }
1154
- },
1155
- {
1156
- "id": "replicate",
1157
- "displayName": "Replicate",
1158
- "apiMode": "chat_completions",
1159
- "authType": "api_key",
1160
- "baseUrl": "https://openai-proxy.replicate.com/v1",
1161
- "envVars": [
1162
- "REPLICATE_API_TOKEN"
1163
- ],
1164
- "fallbackModels": [
1165
- "meta/meta-llama-3-70b-instruct"
1166
- ],
1167
- "capabilities": {
1168
- "supportsToolUse": false,
1169
- "supportsVision": true,
1170
- "supportsStructuredOutput": false,
1171
- "supportsStreaming": true,
1172
- "supportsCacheControl": false
1173
- }
1174
- },
1175
- {
1176
- "id": "ai21",
1177
- "displayName": "AI21 Labs",
1178
- "apiMode": "chat_completions",
1179
- "authType": "api_key",
1180
- "baseUrl": "https://api.ai21.com/studio/v1",
1181
- "envVars": [
1182
- "AI21_API_KEY"
1183
- ],
1184
- "fallbackModels": [
1185
- "jamba-1.5-large"
1186
- ],
1187
- "capabilities": {
1188
- "supportsToolUse": true,
1189
- "supportsVision": false,
1190
- "supportsStructuredOutput": true,
1191
- "supportsStreaming": true,
1192
- "supportsCacheControl": false
1193
- }
1194
- },
1195
- {
1196
- "id": "aleph-alpha",
1197
- "displayName": "Aleph Alpha",
1198
- "apiMode": "chat_completions",
1199
- "authType": "api_key",
1200
- "baseUrl": "https://api.aleph-alpha.com/v1",
1201
- "envVars": [
1202
- "ALEPH_ALPHA_API_KEY"
1203
- ],
1204
- "fallbackModels": [
1205
- "luminous-extended"
1206
- ],
1207
- "capabilities": {
1208
- "supportsToolUse": false,
1209
- "supportsVision": false,
1210
- "supportsStructuredOutput": false,
1211
- "supportsStreaming": true,
1212
- "supportsCacheControl": false
1213
- }
1214
- },
1215
- {
1216
- "id": "cloudflare",
1217
- "displayName": "Cloudflare Workers AI",
1218
- "apiMode": "chat_completions",
1219
- "authType": "api_key",
1220
- "baseUrl": "https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/v1",
1221
- "envVars": [
1222
- "CLOUDFLARE_API_TOKEN",
1223
- "CLOUDFLARE_ACCOUNT_ID"
1224
- ],
1225
- "fallbackModels": [
1226
- "@cf/meta/llama-3.1-70b-instruct"
1227
- ],
1228
- "capabilities": {
1229
- "supportsToolUse": true,
1230
- "supportsVision": false,
1231
- "supportsStructuredOutput": false,
1232
- "supportsStreaming": true,
1233
- "supportsCacheControl": false
1234
- }
1235
- },
1236
- {
1237
- "id": "azure-openai",
1238
- "displayName": "Azure OpenAI",
1239
- "apiMode": "chat_completions",
1240
- "authType": "api_key",
1241
- "baseUrl": "https://{resource}.openai.azure.com/openai/deployments/{deployment}",
1242
- "envVars": [
1243
- "AZURE_OPENAI_API_KEY",
1244
- "AZURE_OPENAI_ENDPOINT"
1245
- ],
1246
- "fallbackModels": [
1247
- "gpt-4o"
1248
- ],
1249
- "capabilities": {
1250
- "supportsToolUse": true,
1251
- "supportsVision": true,
1252
- "supportsStructuredOutput": true,
1253
- "supportsStreaming": true,
1254
- "supportsCacheControl": false
1255
- }
1256
- },
1257
- {
1258
- "id": "github-models",
1259
- "displayName": "GitHub Models",
1260
- "apiMode": "chat_completions",
1261
- "authType": "api_key",
1262
- "baseUrl": "https://models.inference.ai.azure.com",
1263
- "envVars": [
1264
- "GITHUB_TOKEN"
1265
- ],
1266
- "fallbackModels": [
1267
- "gpt-4o-mini"
1268
- ],
1269
- "capabilities": {
1270
- "supportsToolUse": true,
1271
- "supportsVision": true,
1272
- "supportsStructuredOutput": true,
1273
- "supportsStreaming": true,
1274
- "supportsCacheControl": false
1275
- }
1276
- },
1277
- {
1278
- "id": "hyperbolic",
1279
- "displayName": "Hyperbolic",
1280
- "apiMode": "chat_completions",
1281
- "authType": "api_key",
1282
- "baseUrl": "https://api.hyperbolic.xyz/v1",
1283
- "envVars": [
1284
- "HYPERBOLIC_API_KEY"
1285
- ],
1286
- "fallbackModels": [
1287
- "meta-llama/Meta-Llama-3.1-70B-Instruct"
1288
- ],
1289
- "capabilities": {
1290
- "supportsToolUse": true,
1291
- "supportsVision": false,
1292
- "supportsStructuredOutput": true,
1293
- "supportsStreaming": true,
1294
- "supportsCacheControl": false
1295
- }
1296
- },
1297
- {
1298
- "id": "novita",
1299
- "displayName": "Novita AI",
1300
- "apiMode": "chat_completions",
1301
- "authType": "api_key",
1302
- "baseUrl": "https://api.novita.ai/v3/openai",
1303
- "envVars": [
1304
- "NOVITA_API_KEY"
1305
- ],
1306
- "fallbackModels": [
1307
- "meta-llama/llama-3.1-70b-instruct"
1308
- ],
1309
- "capabilities": {
1310
- "supportsToolUse": true,
1311
- "supportsVision": false,
1312
- "supportsStructuredOutput": true,
1313
- "supportsStreaming": true,
1314
- "supportsCacheControl": false
1315
- }
1316
- },
1317
- {
1318
- "id": "moonshot",
1319
- "displayName": "Moonshot (Kimi)",
1320
- "apiMode": "chat_completions",
1321
- "authType": "api_key",
1322
- "baseUrl": "https://api.moonshot.cn/v1",
1323
- "envVars": [
1324
- "MOONSHOT_API_KEY"
1325
- ],
1326
- "fallbackModels": [
1327
- "moonshot-v1-8k"
1328
- ],
1329
- "capabilities": {
1330
- "supportsToolUse": true,
1331
- "supportsVision": false,
1332
- "supportsStructuredOutput": false,
1333
- "supportsStreaming": true,
1334
- "supportsCacheControl": false
1335
- }
1336
- },
1337
- {
1338
- "id": "qwen",
1339
- "displayName": "Qwen (Alibaba)",
1340
- "apiMode": "chat_completions",
1341
- "authType": "api_key",
1342
- "baseUrl": "https://dashscope.aliyuncs.com/compatible-mode/v1",
1343
- "envVars": [
1344
- "DASHSCOPE_API_KEY"
1345
- ],
1346
- "fallbackModels": [
1347
- "qwen-plus"
1348
- ],
1349
- "capabilities": {
1350
- "supportsToolUse": true,
1351
- "supportsVision": true,
1352
- "supportsStructuredOutput": true,
1353
- "supportsStreaming": true,
1354
- "supportsCacheControl": false
1355
- },
1356
- "aliases": [
1357
- "dashscope"
1358
- ],
1359
- "models": {
1360
- "qwen3-coder-30b-a3b-instruct": {
1361
- "tool_call": true,
1362
- "structured_output": false,
1363
- "cache_control": false,
1364
- "modalities": {
1365
- "input": [
1366
- "text"
1367
- ]
1368
- },
1369
- "limit": {
1370
- "context": 160000,
1371
- "output": 8000
1372
- }
1373
- }
1374
- }
1375
- },
1376
- {
1377
- "id": "zhipu",
1378
- "displayName": "Zhipu AI (GLM)",
1379
- "apiMode": "chat_completions",
1380
- "authType": "api_key",
1381
- "baseUrl": "https://open.bigmodel.cn/api/paas/v4",
1382
- "envVars": [
1383
- "ZHIPU_API_KEY"
1384
- ],
1385
- "fallbackModels": [
1386
- "glm-4-plus"
1387
- ],
1388
- "capabilities": {
1389
- "supportsToolUse": true,
1390
- "supportsVision": true,
1391
- "supportsStructuredOutput": true,
1392
- "supportsStreaming": true,
1393
- "supportsCacheControl": false
1394
- },
1395
- "aliases": [
1396
- "glm",
1397
- "z-ai"
1398
- ],
1399
- "models": {
1400
- "glm-4.7-flash": {
1401
- "name": "GLM-4.7-Flash",
1402
- "release_date": "2026-01-19",
1403
- "attachment": false,
1404
- "reasoning": true,
1405
- "temperature": true,
1406
- "tool_call": true,
1407
- "cost": {
1408
- "input": 0,
1409
- "output": 0,
1410
- "cache_read": 0,
1411
- "cache_write": 0
1412
- },
1413
- "limit": {
1414
- "context": 202752,
1415
- "output": 8000
1416
- },
1417
- "modalities": {
1418
- "input": [
1419
- "text"
1420
- ],
1421
- "output": [
1422
- "text"
1423
- ]
1424
- },
1425
- "structured_output": false,
1426
- "cache_control": false
1427
- }
1428
- }
1429
- },
1430
- {
1431
- "id": "minimax",
1432
- "displayName": "MiniMax",
1433
- "apiMode": "chat_completions",
1434
- "authType": "api_key",
1435
- "baseUrl": "https://api.minimax.chat/v1",
1436
- "envVars": [
1437
- "MINIMAX_API_KEY"
1438
- ],
1439
- "fallbackModels": [
1440
- "MiniMax-Text-01"
1441
- ],
1442
- "capabilities": {
1443
- "supportsToolUse": true,
1444
- "supportsVision": false,
1445
- "supportsStructuredOutput": false,
1446
- "supportsStreaming": true,
1447
- "supportsCacheControl": false
1448
- }
1449
- },
1450
- {
1451
- "id": "baichuan",
1452
- "displayName": "Baichuan",
1453
- "apiMode": "chat_completions",
1454
- "authType": "api_key",
1455
- "baseUrl": "https://api.baichuan-ai.com/v1",
1456
- "envVars": [
1457
- "BAICHUAN_API_KEY"
1458
- ],
1459
- "fallbackModels": [
1460
- "Baichuan4"
1461
- ],
1462
- "capabilities": {
1463
- "supportsToolUse": true,
1464
- "supportsVision": false,
1465
- "supportsStructuredOutput": false,
1466
- "supportsStreaming": true,
1467
- "supportsCacheControl": false
1468
- }
1469
- },
1470
- {
1471
- "id": "voyage",
1472
- "displayName": "Voyage AI",
1473
- "apiMode": "chat_completions",
1474
- "authType": "api_key",
1475
- "baseUrl": "https://api.voyageai.com/v1",
1476
- "envVars": [
1477
- "VOYAGE_API_KEY"
1478
- ],
1479
- "fallbackModels": [
1480
- "voyage-3"
1481
- ],
1482
- "capabilities": {
1483
- "supportsToolUse": false,
1484
- "supportsVision": false,
1485
- "supportsStructuredOutput": false,
1486
- "supportsStreaming": false,
1487
- "supportsCacheControl": false
1488
- }
1489
- },
1490
- {
1491
- "id": "jina",
1492
- "displayName": "Jina AI",
1493
- "apiMode": "chat_completions",
1494
- "authType": "api_key",
1495
- "baseUrl": "https://api.jina.ai/v1",
1496
- "envVars": [
1497
- "JINA_API_KEY"
1498
- ],
1499
- "fallbackModels": [
1500
- "jina-embeddings-v3"
1501
- ],
1502
- "capabilities": {
1503
- "supportsToolUse": false,
1504
- "supportsVision": false,
1505
- "supportsStructuredOutput": false,
1506
- "supportsStreaming": false,
1507
- "supportsCacheControl": false
1508
- }
1509
- },
1510
- {
1511
- "id": "helicone",
1512
- "displayName": "Helicone (Gateway)",
1513
- "apiMode": "chat_completions",
1514
- "authType": "api_key",
1515
- "baseUrl": "https://oai.helicone.ai/v1",
1516
- "envVars": [
1517
- "HELICONE_API_KEY",
1518
- "OPENAI_API_KEY"
1519
- ],
1520
- "fallbackModels": [
1521
- "gpt-4o-mini"
1522
- ],
1523
- "capabilities": {
1524
- "supportsToolUse": true,
1525
- "supportsVision": true,
1526
- "supportsStructuredOutput": true,
1527
- "supportsStreaming": true,
1528
- "supportsCacheControl": false
1529
- },
1530
- "models": {
1531
- "gpt-4o-mini": {
1532
- "name": "OpenAI GPT-4o-mini",
1533
- "release_date": "2024-07-18",
1534
- "attachment": false,
1535
- "reasoning": false,
1536
- "temperature": true,
1537
- "tool_call": true,
1538
- "cost": {
1539
- "input": 0.15,
1540
- "output": 0.6,
1541
- "cache_read": 0.075
1542
- },
1543
- "limit": {
1544
- "context": 128000,
1545
- "output": 16384
1546
- },
1547
- "modalities": {
1548
- "input": [
1549
- "text",
1550
- "image"
1551
- ],
1552
- "output": [
1553
- "text"
1554
- ]
1555
- }
1556
- }
1557
- }
1558
- },
1559
- {
1560
- "id": "portkey",
1561
- "displayName": "Portkey (Gateway)",
1562
- "apiMode": "chat_completions",
1563
- "authType": "api_key",
1564
- "baseUrl": "https://api.portkey.ai/v1",
1565
- "envVars": [
1566
- "PORTKEY_API_KEY"
1567
- ],
1568
- "fallbackModels": [
1569
- "gpt-4o-mini"
1570
- ],
1571
- "capabilities": {
1572
- "supportsToolUse": true,
1573
- "supportsVision": true,
1574
- "supportsStructuredOutput": true,
1575
- "supportsStreaming": true,
1576
- "supportsCacheControl": false
1577
- }
1578
- },
1579
- {
1580
- "id": "baseten",
1581
- "displayName": "Baseten",
1582
- "apiMode": "chat_completions",
1583
- "authType": "api_key",
1584
- "baseUrl": "https://bridge.baseten.co/v1",
1585
- "envVars": [
1586
- "BASETEN_API_KEY"
1587
- ],
1588
- "fallbackModels": [
1589
- "meta-llama/Meta-Llama-3-70B-Instruct"
1590
- ],
1591
- "capabilities": {
1592
- "supportsToolUse": true,
1593
- "supportsVision": false,
1594
- "supportsStructuredOutput": true,
1595
- "supportsStreaming": true,
1596
- "supportsCacheControl": false
1597
- }
1598
- },
1599
- {
1600
- "id": "modal",
1601
- "displayName": "Modal",
1602
- "apiMode": "chat_completions",
1603
- "authType": "api_key",
1604
- "baseUrl": "https://api.modal.com/v1",
1605
- "envVars": [
1606
- "MODAL_TOKEN_ID",
1607
- "MODAL_TOKEN_SECRET"
1608
- ],
1609
- "fallbackModels": [
1610
- "meta-llama/Meta-Llama-3-70B-Instruct"
1611
- ],
1612
- "capabilities": {
1613
- "supportsToolUse": true,
1614
- "supportsVision": false,
1615
- "supportsStructuredOutput": false,
1616
- "supportsStreaming": true,
1617
- "supportsCacheControl": false
1618
- }
1619
- }
1620
- ]