@llmgateway/models 0.0.1

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.
Files changed (112) hide show
  1. package/dist/get-cheapest-from-available-providers.d.ts +30 -0
  2. package/dist/get-cheapest-from-available-providers.js +183 -0
  3. package/dist/get-cheapest-from-available-providers.js.map +1 -0
  4. package/dist/get-cheapest-model-for-provider.d.ts +2 -0
  5. package/dist/get-cheapest-model-for-provider.js +49 -0
  6. package/dist/get-cheapest-model-for-provider.js.map +1 -0
  7. package/dist/get-provider-endpoint.d.ts +3 -0
  8. package/dist/get-provider-endpoint.js +243 -0
  9. package/dist/get-provider-endpoint.js.map +1 -0
  10. package/dist/get-provider-headers.d.ts +5 -0
  11. package/dist/get-provider-headers.js +45 -0
  12. package/dist/get-provider-headers.js.map +1 -0
  13. package/dist/helpers.d.ts +1 -0
  14. package/dist/helpers.js +27 -0
  15. package/dist/helpers.js.map +1 -0
  16. package/dist/index.d.ts +16 -0
  17. package/dist/index.js +17 -0
  18. package/dist/index.js.map +1 -0
  19. package/dist/models/alibaba.d.ts +686 -0
  20. package/dist/models/alibaba.js +789 -0
  21. package/dist/models/alibaba.js.map +1 -0
  22. package/dist/models/anthropic.d.ts +572 -0
  23. package/dist/models/anthropic.js +638 -0
  24. package/dist/models/anthropic.js.map +1 -0
  25. package/dist/models/aws-bedrock.d.ts +1 -0
  26. package/dist/models/aws-bedrock.js +2 -0
  27. package/dist/models/aws-bedrock.js.map +1 -0
  28. package/dist/models/bytedance.d.ts +131 -0
  29. package/dist/models/bytedance.js +151 -0
  30. package/dist/models/bytedance.js.map +1 -0
  31. package/dist/models/deepseek.d.ts +175 -0
  32. package/dist/models/deepseek.js +197 -0
  33. package/dist/models/deepseek.js.map +1 -0
  34. package/dist/models/google.d.ts +1065 -0
  35. package/dist/models/google.js +1201 -0
  36. package/dist/models/google.js.map +1 -0
  37. package/dist/models/llmgateway.d.ts +39 -0
  38. package/dist/models/llmgateway.js +59 -0
  39. package/dist/models/llmgateway.js.map +1 -0
  40. package/dist/models/meta.d.ts +263 -0
  41. package/dist/models/meta.js +300 -0
  42. package/dist/models/meta.js.map +1 -0
  43. package/dist/models/microsoft.d.ts +1 -0
  44. package/dist/models/microsoft.js +2 -0
  45. package/dist/models/microsoft.js.map +1 -0
  46. package/dist/models/minimax.d.ts +59 -0
  47. package/dist/models/minimax.js +68 -0
  48. package/dist/models/minimax.js.map +1 -0
  49. package/dist/models/mistral.d.ts +78 -0
  50. package/dist/models/mistral.js +92 -0
  51. package/dist/models/mistral.js.map +1 -0
  52. package/dist/models/moonshot.d.ts +165 -0
  53. package/dist/models/moonshot.js +184 -0
  54. package/dist/models/moonshot.js.map +1 -0
  55. package/dist/models/nousresearch.d.ts +21 -0
  56. package/dist/models/nousresearch.js +26 -0
  57. package/dist/models/nousresearch.js.map +1 -0
  58. package/dist/models/openai.d.ts +1018 -0
  59. package/dist/models/openai.js +1213 -0
  60. package/dist/models/openai.js.map +1 -0
  61. package/dist/models/perplexity.d.ts +67 -0
  62. package/dist/models/perplexity.js +78 -0
  63. package/dist/models/perplexity.js.map +1 -0
  64. package/dist/models/routeway.d.ts +161 -0
  65. package/dist/models/routeway.js +187 -0
  66. package/dist/models/routeway.js.map +1 -0
  67. package/dist/models/xai.d.ts +270 -0
  68. package/dist/models/xai.js +311 -0
  69. package/dist/models/xai.js.map +1 -0
  70. package/dist/models/zai.d.ts +492 -0
  71. package/dist/models/zai.js +551 -0
  72. package/dist/models/zai.js.map +1 -0
  73. package/dist/models.d.ts +5304 -0
  74. package/dist/models.js +37 -0
  75. package/dist/models.js.map +1 -0
  76. package/dist/models.spec.d.ts +1 -0
  77. package/dist/models.spec.js +263 -0
  78. package/dist/models.spec.js.map +1 -0
  79. package/dist/prepare-request-body.d.ts +10 -0
  80. package/dist/prepare-request-body.js +1081 -0
  81. package/dist/prepare-request-body.js.map +1 -0
  82. package/dist/prepare-request-body.spec.d.ts +1 -0
  83. package/dist/prepare-request-body.spec.js +231 -0
  84. package/dist/prepare-request-body.spec.js.map +1 -0
  85. package/dist/process-image-url.d.ts +4 -0
  86. package/dist/process-image-url.js +121 -0
  87. package/dist/process-image-url.js.map +1 -0
  88. package/dist/provider.d.ts +9 -0
  89. package/dist/provider.js +64 -0
  90. package/dist/provider.js.map +1 -0
  91. package/dist/providers.d.ts +405 -0
  92. package/dist/providers.js +413 -0
  93. package/dist/providers.js.map +1 -0
  94. package/dist/testing.d.ts +7 -0
  95. package/dist/testing.js +19 -0
  96. package/dist/testing.js.map +1 -0
  97. package/dist/transform-anthropic-messages.d.ts +2 -0
  98. package/dist/transform-anthropic-messages.js +185 -0
  99. package/dist/transform-anthropic-messages.js.map +1 -0
  100. package/dist/transform-google-messages.d.ts +25 -0
  101. package/dist/transform-google-messages.js +122 -0
  102. package/dist/transform-google-messages.js.map +1 -0
  103. package/dist/type-guards.d.ts +20 -0
  104. package/dist/type-guards.js +35 -0
  105. package/dist/type-guards.js.map +1 -0
  106. package/dist/types.d.ts +291 -0
  107. package/dist/types.js +28 -0
  108. package/dist/types.js.map +1 -0
  109. package/dist/validate-provider-key.d.ts +4 -0
  110. package/dist/validate-provider-key.js +113 -0
  111. package/dist/validate-provider-key.js.map +1 -0
  112. package/package.json +29 -0
@@ -0,0 +1,1213 @@
1
+ export const openaiModels = [
2
+ {
3
+ id: "gpt-4o-mini",
4
+ name: "GPT-4o Mini",
5
+ description: "Affordable small model for fast, lightweight tasks with text and vision capabilities.",
6
+ family: "openai",
7
+ releasedAt: new Date("2024-07-18"),
8
+ providers: [
9
+ {
10
+ providerId: "openai",
11
+ modelName: "gpt-4o-mini",
12
+ inputPrice: 0.15 / 1e6,
13
+ outputPrice: 0.6 / 1e6,
14
+ cachedInputPrice: 0.075 / 1e6,
15
+ requestPrice: 0,
16
+ contextSize: 128000,
17
+ maxOutput: 16384,
18
+ streaming: true,
19
+ vision: false,
20
+ tools: true,
21
+ jsonOutputSchema: true,
22
+ jsonOutput: true,
23
+ },
24
+ {
25
+ providerId: "azure",
26
+ stability: "unstable",
27
+ modelName: "gpt-4o-mini",
28
+ inputPrice: 0.15 / 1e6,
29
+ outputPrice: 0.6 / 1e6,
30
+ cachedInputPrice: 0.075 / 1e6,
31
+ contextSize: 128000,
32
+ maxOutput: 16384,
33
+ streaming: true,
34
+ vision: false,
35
+ tools: true,
36
+ jsonOutput: true,
37
+ },
38
+ ],
39
+ },
40
+ {
41
+ id: "gpt-4o-search-preview",
42
+ name: "GPT-4o Search Preview",
43
+ description: "GPT-4o with native web search capabilities for up-to-date information.",
44
+ family: "openai",
45
+ releasedAt: new Date("2024-10-01"),
46
+ providers: [
47
+ {
48
+ providerId: "openai",
49
+ modelName: "gpt-4o-search-preview",
50
+ inputPrice: 2.5 / 1e6,
51
+ outputPrice: 10.0 / 1e6,
52
+ requestPrice: 0,
53
+ webSearch: true,
54
+ webSearchPrice: 0.025,
55
+ contextSize: 128000,
56
+ maxOutput: 16384,
57
+ streaming: true,
58
+ vision: true,
59
+ tools: false,
60
+ jsonOutput: false,
61
+ },
62
+ ],
63
+ },
64
+ {
65
+ id: "gpt-4o-mini-search-preview",
66
+ name: "GPT-4o Mini Search Preview",
67
+ description: "Cost-effective GPT-4o Mini with native web search capabilities.",
68
+ family: "openai",
69
+ releasedAt: new Date("2024-10-01"),
70
+ providers: [
71
+ {
72
+ providerId: "openai",
73
+ modelName: "gpt-4o-mini-search-preview",
74
+ inputPrice: 0.15 / 1e6,
75
+ outputPrice: 0.6 / 1e6,
76
+ requestPrice: 0,
77
+ webSearch: true,
78
+ webSearchPrice: 0.025,
79
+ contextSize: 128000,
80
+ maxOutput: 16384,
81
+ streaming: true,
82
+ vision: true,
83
+ tools: false,
84
+ jsonOutput: false,
85
+ },
86
+ ],
87
+ },
88
+ {
89
+ id: "gpt-4",
90
+ name: "GPT-4",
91
+ description: "Original GPT-4 model with strong reasoning and tool use capabilities.",
92
+ family: "openai",
93
+ releasedAt: new Date("2023-03-14"),
94
+ providers: [
95
+ {
96
+ test: "skip",
97
+ providerId: "openai",
98
+ modelName: "gpt-4",
99
+ inputPrice: 30.0 / 1e6,
100
+ outputPrice: 60.0 / 1e6,
101
+ requestPrice: 0,
102
+ contextSize: 8192,
103
+ maxOutput: 8192,
104
+ streaming: true,
105
+ vision: false,
106
+ tools: true,
107
+ supportedParameters: [
108
+ "temperature",
109
+ "max_tokens",
110
+ "top_p",
111
+ "frequency_penalty",
112
+ "presence_penalty",
113
+ "response_format",
114
+ "tools",
115
+ "tool_choice",
116
+ ],
117
+ jsonOutput: false,
118
+ },
119
+ {
120
+ test: "skip",
121
+ providerId: "azure",
122
+ stability: "unstable",
123
+ modelName: "gpt-4",
124
+ inputPrice: 30.0 / 1e6,
125
+ outputPrice: 60.0 / 1e6,
126
+ contextSize: 8192,
127
+ maxOutput: 8192,
128
+ streaming: true,
129
+ vision: false,
130
+ tools: true,
131
+ jsonOutput: false,
132
+ },
133
+ ],
134
+ },
135
+ {
136
+ id: "gpt-4o",
137
+ name: "GPT-4o",
138
+ description: "Multimodal flagship model with vision, fast responses, and tool support.",
139
+ family: "openai",
140
+ releasedAt: new Date("2024-05-13"),
141
+ providers: [
142
+ {
143
+ providerId: "openai",
144
+ modelName: "gpt-4o",
145
+ inputPrice: 2.5 / 1e6,
146
+ outputPrice: 10.0 / 1e6,
147
+ cachedInputPrice: 1.25 / 1e6,
148
+ requestPrice: 0,
149
+ imageInputPrice: 0.00553,
150
+ contextSize: 128000,
151
+ maxOutput: 16384,
152
+ streaming: true,
153
+ vision: true,
154
+ tools: true,
155
+ webSearch: true,
156
+ jsonOutputSchema: true,
157
+ jsonOutput: true,
158
+ },
159
+ {
160
+ test: "skip",
161
+ providerId: "azure",
162
+ stability: "unstable",
163
+ modelName: "gpt-4o",
164
+ inputPrice: 2.5 / 1e6,
165
+ outputPrice: 10.0 / 1e6,
166
+ cachedInputPrice: 1.25 / 1e6,
167
+ imageInputPrice: 0.00553,
168
+ contextSize: 128000,
169
+ maxOutput: 16384,
170
+ streaming: true,
171
+ vision: true,
172
+ tools: true,
173
+ jsonOutput: true,
174
+ },
175
+ ],
176
+ },
177
+ {
178
+ id: "gpt-3.5-turbo",
179
+ name: "GPT-3.5 Turbo",
180
+ description: "Fast and cost-effective model for simple tasks and conversational applications.",
181
+ family: "openai",
182
+ releasedAt: new Date("2022-11-30"),
183
+ providers: [
184
+ {
185
+ providerId: "openai",
186
+ modelName: "gpt-3.5-turbo",
187
+ inputPrice: 0.5 / 1e6,
188
+ outputPrice: 1.5 / 1e6,
189
+ requestPrice: 0,
190
+ contextSize: 16385,
191
+ maxOutput: undefined,
192
+ streaming: true,
193
+ vision: false,
194
+ tools: true,
195
+ jsonOutputSchema: false,
196
+ jsonOutput: true,
197
+ },
198
+ {
199
+ test: "skip",
200
+ providerId: "azure",
201
+ stability: "unstable",
202
+ modelName: "gpt-35-turbo",
203
+ inputPrice: 0.5 / 1e6,
204
+ outputPrice: 1.5 / 1e6,
205
+ contextSize: 16385,
206
+ maxOutput: 4096,
207
+ streaming: true,
208
+ vision: false,
209
+ tools: true,
210
+ jsonOutput: true,
211
+ },
212
+ ],
213
+ },
214
+ {
215
+ id: "gpt-4-turbo",
216
+ name: "GPT-4 Turbo",
217
+ description: "Enhanced GPT-4 with vision capabilities and improved performance.",
218
+ family: "openai",
219
+ releasedAt: new Date("2023-11-06"),
220
+ providers: [
221
+ {
222
+ test: "skip",
223
+ providerId: "openai",
224
+ modelName: "gpt-4-turbo",
225
+ inputPrice: 10.0 / 1e6,
226
+ outputPrice: 30.0 / 1e6,
227
+ requestPrice: 0,
228
+ contextSize: 128000,
229
+ maxOutput: undefined,
230
+ streaming: true,
231
+ vision: true,
232
+ tools: true,
233
+ jsonOutputSchema: true,
234
+ jsonOutput: true,
235
+ },
236
+ {
237
+ test: "skip",
238
+ providerId: "azure",
239
+ stability: "unstable",
240
+ modelName: "gpt-4-turbo",
241
+ inputPrice: 10.0 / 1e6,
242
+ outputPrice: 30.0 / 1e6,
243
+ contextSize: 128000,
244
+ maxOutput: 4096,
245
+ streaming: true,
246
+ vision: true,
247
+ tools: true,
248
+ jsonOutput: true,
249
+ },
250
+ ],
251
+ },
252
+ {
253
+ id: "gpt-4.1",
254
+ name: "GPT-4.1",
255
+ description: "Updated GPT-4 with vision support and parallel tool calls.",
256
+ family: "openai",
257
+ releasedAt: new Date("2025-04-14"),
258
+ providers: [
259
+ {
260
+ providerId: "openai",
261
+ modelName: "gpt-4.1",
262
+ inputPrice: 2.0 / 1e6,
263
+ outputPrice: 8.0 / 1e6,
264
+ requestPrice: 0,
265
+ contextSize: 1000000,
266
+ maxOutput: undefined,
267
+ streaming: true,
268
+ vision: true,
269
+ tools: true,
270
+ parallelToolCalls: true,
271
+ jsonOutputSchema: true,
272
+ jsonOutput: true,
273
+ },
274
+ {
275
+ test: "skip",
276
+ providerId: "azure",
277
+ stability: "unstable",
278
+ modelName: "gpt-4.1",
279
+ inputPrice: 2.0 / 1e6,
280
+ outputPrice: 8.0 / 1e6,
281
+ requestPrice: 0,
282
+ contextSize: 1000000,
283
+ maxOutput: undefined,
284
+ streaming: true,
285
+ vision: true,
286
+ tools: true,
287
+ parallelToolCalls: true,
288
+ jsonOutputSchema: true,
289
+ jsonOutput: true,
290
+ },
291
+ ],
292
+ },
293
+ {
294
+ id: "o1",
295
+ name: "o1",
296
+ description: "Advanced reasoning model that thinks before responding for complex problem-solving.",
297
+ family: "openai",
298
+ releasedAt: new Date("2024-09-12"),
299
+ providers: [
300
+ {
301
+ test: "skip",
302
+ providerId: "openai",
303
+ modelName: "o1",
304
+ inputPrice: 15.0 / 1e6,
305
+ outputPrice: 60.0 / 1e6,
306
+ requestPrice: 0,
307
+ contextSize: 200000,
308
+ maxOutput: undefined,
309
+ streaming: true,
310
+ vision: true,
311
+ reasoning: true,
312
+ tools: false,
313
+ jsonOutputSchema: true,
314
+ jsonOutput: true,
315
+ },
316
+ {
317
+ test: "skip",
318
+ providerId: "azure",
319
+ stability: "unstable",
320
+ modelName: "o1",
321
+ inputPrice: 15.0 / 1e6,
322
+ outputPrice: 60.0 / 1e6,
323
+ requestPrice: 0,
324
+ contextSize: 200000,
325
+ maxOutput: undefined,
326
+ streaming: true,
327
+ vision: true,
328
+ reasoning: true,
329
+ tools: false,
330
+ jsonOutputSchema: true,
331
+ jsonOutput: true,
332
+ },
333
+ ],
334
+ },
335
+ {
336
+ id: "o1-mini",
337
+ name: "o1 Mini",
338
+ description: "Smaller, faster reasoning model optimized for coding and math tasks.",
339
+ family: "openai",
340
+ releasedAt: new Date("2024-09-12"),
341
+ providers: [
342
+ {
343
+ stability: "unstable",
344
+ providerId: "openai",
345
+ modelName: "o1-mini",
346
+ inputPrice: 1.1 / 1e6,
347
+ outputPrice: 4.4 / 1e6,
348
+ requestPrice: 0,
349
+ contextSize: 128000,
350
+ maxOutput: undefined,
351
+ streaming: false,
352
+ vision: false,
353
+ tools: false,
354
+ reasoning: false,
355
+ supportsResponsesApi: false,
356
+ jsonOutput: false,
357
+ },
358
+ {
359
+ test: "skip",
360
+ providerId: "azure",
361
+ stability: "unstable",
362
+ modelName: "o1-mini",
363
+ inputPrice: 1.1 / 1e6,
364
+ outputPrice: 4.4 / 1e6,
365
+ requestPrice: 0,
366
+ contextSize: 128000,
367
+ maxOutput: undefined,
368
+ streaming: false,
369
+ vision: false,
370
+ tools: false,
371
+ reasoning: false,
372
+ supportsResponsesApi: false,
373
+ jsonOutput: false,
374
+ },
375
+ ],
376
+ supportsSystemRole: false,
377
+ },
378
+ {
379
+ id: "gpt-4.1-mini",
380
+ name: "GPT-4.1 Mini",
381
+ description: "Compact version of GPT-4.1 with vision and tool support.",
382
+ family: "openai",
383
+ releasedAt: new Date("2025-04-14"),
384
+ providers: [
385
+ {
386
+ providerId: "openai",
387
+ modelName: "gpt-4.1-mini",
388
+ inputPrice: 0.4 / 1e6,
389
+ outputPrice: 1.6 / 1e6,
390
+ requestPrice: 0,
391
+ contextSize: 1000000,
392
+ maxOutput: undefined,
393
+ streaming: true,
394
+ vision: true,
395
+ tools: true,
396
+ parallelToolCalls: true,
397
+ jsonOutputSchema: true,
398
+ jsonOutput: true,
399
+ },
400
+ {
401
+ test: "skip",
402
+ providerId: "azure",
403
+ stability: "unstable",
404
+ modelName: "gpt-4.1-mini",
405
+ inputPrice: 0.4 / 1e6,
406
+ outputPrice: 1.6 / 1e6,
407
+ requestPrice: 0,
408
+ contextSize: 1000000,
409
+ maxOutput: undefined,
410
+ streaming: true,
411
+ vision: true,
412
+ tools: true,
413
+ parallelToolCalls: true,
414
+ jsonOutputSchema: true,
415
+ jsonOutput: true,
416
+ },
417
+ ],
418
+ },
419
+ {
420
+ id: "gpt-4.1-nano",
421
+ name: "GPT-4.1 Nano",
422
+ description: "Ultra-lightweight GPT-4.1 variant for high-volume, cost-sensitive applications.",
423
+ family: "openai",
424
+ releasedAt: new Date("2025-04-14"),
425
+ providers: [
426
+ {
427
+ providerId: "openai",
428
+ modelName: "gpt-4.1-nano",
429
+ inputPrice: 0.1 / 1e6,
430
+ outputPrice: 0.4 / 1e6,
431
+ requestPrice: 0,
432
+ contextSize: 1000000,
433
+ maxOutput: undefined,
434
+ streaming: true,
435
+ vision: true,
436
+ tools: true,
437
+ parallelToolCalls: true,
438
+ jsonOutputSchema: true,
439
+ jsonOutput: true,
440
+ },
441
+ {
442
+ test: "skip",
443
+ providerId: "azure",
444
+ stability: "unstable",
445
+ modelName: "gpt-4.1-nano",
446
+ inputPrice: 0.1 / 1e6,
447
+ outputPrice: 0.4 / 1e6,
448
+ requestPrice: 0,
449
+ contextSize: 1000000,
450
+ maxOutput: undefined,
451
+ streaming: true,
452
+ vision: true,
453
+ tools: true,
454
+ parallelToolCalls: true,
455
+ jsonOutputSchema: true,
456
+ jsonOutput: true,
457
+ },
458
+ ],
459
+ },
460
+ {
461
+ id: "o3",
462
+ name: "o3",
463
+ description: "Next-generation reasoning model with enhanced problem-solving capabilities.",
464
+ family: "openai",
465
+ releasedAt: new Date("2025-06-01"),
466
+ providers: [
467
+ {
468
+ providerId: "openai",
469
+ modelName: "o3",
470
+ inputPrice: 2 / 1e6,
471
+ outputPrice: 8 / 1e6,
472
+ requestPrice: 0,
473
+ contextSize: 200000,
474
+ maxOutput: undefined,
475
+ streaming: false,
476
+ vision: true,
477
+ tools: false,
478
+ jsonOutputSchema: true,
479
+ jsonOutput: true,
480
+ },
481
+ {
482
+ test: "skip",
483
+ providerId: "azure",
484
+ stability: "unstable",
485
+ modelName: "o3",
486
+ inputPrice: 2 / 1e6,
487
+ outputPrice: 8 / 1e6,
488
+ requestPrice: 0,
489
+ contextSize: 200000,
490
+ maxOutput: undefined,
491
+ streaming: false,
492
+ vision: true,
493
+ tools: false,
494
+ jsonOutputSchema: true,
495
+ jsonOutput: true,
496
+ },
497
+ ],
498
+ },
499
+ {
500
+ id: "o3-mini",
501
+ name: "o3 Mini",
502
+ description: "Compact o3 reasoning model balancing performance and cost for complex tasks.",
503
+ family: "openai",
504
+ releasedAt: new Date("2025-06-01"),
505
+ providers: [
506
+ {
507
+ providerId: "openai",
508
+ modelName: "o3-mini",
509
+ inputPrice: 1.1 / 1e6,
510
+ outputPrice: 4.4 / 1e6,
511
+ requestPrice: 0,
512
+ contextSize: 200000,
513
+ maxOutput: undefined,
514
+ streaming: true,
515
+ vision: false,
516
+ tools: false,
517
+ jsonOutputSchema: true,
518
+ jsonOutput: true,
519
+ },
520
+ {
521
+ test: "skip",
522
+ providerId: "azure",
523
+ stability: "unstable",
524
+ modelName: "o3-mini",
525
+ inputPrice: 1.1 / 1e6,
526
+ outputPrice: 4.4 / 1e6,
527
+ requestPrice: 0,
528
+ contextSize: 200000,
529
+ maxOutput: undefined,
530
+ streaming: true,
531
+ vision: false,
532
+ tools: false,
533
+ jsonOutputSchema: true,
534
+ jsonOutput: true,
535
+ },
536
+ ],
537
+ },
538
+ {
539
+ id: "gpt-oss-120b",
540
+ name: "GPT OSS 120B",
541
+ description: "Open-source 120B parameter model with reasoning capabilities via Groq inference.",
542
+ family: "openai",
543
+ releasedAt: new Date("2025-08-05"),
544
+ providers: [
545
+ {
546
+ providerId: "groq",
547
+ modelName: "openai/gpt-oss-120b",
548
+ inputPrice: 0.15 / 1e6,
549
+ outputPrice: 0.75 / 1e6,
550
+ requestPrice: 0,
551
+ contextSize: 131072,
552
+ maxOutput: 32766,
553
+ streaming: true,
554
+ vision: false,
555
+ tools: true,
556
+ reasoning: true,
557
+ jsonOutput: true,
558
+ },
559
+ {
560
+ providerId: "cerebras",
561
+ modelName: "gpt-oss-120b",
562
+ inputPrice: 0.35 / 1e6,
563
+ outputPrice: 0.75 / 1e6,
564
+ requestPrice: 0,
565
+ contextSize: 131072,
566
+ maxOutput: 32768,
567
+ streaming: true,
568
+ vision: false,
569
+ tools: true,
570
+ reasoning: true,
571
+ jsonOutput: true,
572
+ },
573
+ {
574
+ test: "skip",
575
+ providerId: "nanogpt",
576
+ modelName: "openai/gpt-oss-120b",
577
+ inputPrice: 0.05 / 1e6,
578
+ outputPrice: 0.25 / 1e6,
579
+ requestPrice: 0,
580
+ contextSize: 131072,
581
+ maxOutput: 32766,
582
+ streaming: true,
583
+ vision: false,
584
+ tools: true,
585
+ reasoning: true,
586
+ jsonOutput: true,
587
+ },
588
+ {
589
+ providerId: "bytedance",
590
+ modelName: "gpt-oss-120b-250805",
591
+ inputPrice: 0.1 / 1e6,
592
+ cachedInputPrice: 0.02 / 1e6,
593
+ outputPrice: 0.5 / 1e6,
594
+ requestPrice: 0,
595
+ contextSize: 128000,
596
+ maxOutput: 32000,
597
+ streaming: true,
598
+ vision: false,
599
+ tools: true,
600
+ reasoning: true,
601
+ jsonOutput: false,
602
+ },
603
+ ],
604
+ },
605
+ {
606
+ id: "gpt-oss-20b",
607
+ name: "GPT OSS 20B",
608
+ description: "Lightweight open-source 20B model with reasoning support for efficient inference.",
609
+ family: "openai",
610
+ releasedAt: new Date("2025-08-05"),
611
+ providers: [
612
+ {
613
+ providerId: "groq",
614
+ modelName: "openai/gpt-oss-20b",
615
+ inputPrice: 0.1 / 1e6,
616
+ outputPrice: 0.5 / 1e6,
617
+ requestPrice: 0,
618
+ contextSize: 131072,
619
+ maxOutput: 32766,
620
+ streaming: true,
621
+ vision: false,
622
+ tools: true,
623
+ reasoning: true,
624
+ jsonOutput: true,
625
+ },
626
+ {
627
+ test: "skip",
628
+ providerId: "nanogpt",
629
+ modelName: "openai/gpt-oss-20b",
630
+ inputPrice: 0.04 / 1e6,
631
+ outputPrice: 0.15 / 1e6,
632
+ requestPrice: 0,
633
+ contextSize: 131072,
634
+ maxOutput: 32766,
635
+ streaming: true,
636
+ vision: false,
637
+ tools: true,
638
+ reasoning: true,
639
+ jsonOutput: true,
640
+ },
641
+ ],
642
+ },
643
+ {
644
+ id: "gpt-5",
645
+ name: "GPT-5",
646
+ description: "Latest flagship model with reasoning, vision, and enhanced capabilities.",
647
+ family: "openai",
648
+ releasedAt: new Date("2025-08-01"),
649
+ providers: [
650
+ {
651
+ providerId: "openai",
652
+ modelName: "gpt-5",
653
+ inputPrice: 1.25 / 1e6,
654
+ outputPrice: 10.0 / 1e6,
655
+ cachedInputPrice: 0.125 / 1e6,
656
+ requestPrice: 0,
657
+ contextSize: 400000,
658
+ maxOutput: 128000,
659
+ reasoning: true,
660
+ streaming: true,
661
+ vision: true,
662
+ tools: true,
663
+ webSearch: true,
664
+ webSearchPrice: 0.01,
665
+ supportsResponsesApi: true,
666
+ jsonOutputSchema: true,
667
+ supportedParameters: [
668
+ "temperature",
669
+ "top_p",
670
+ "frequency_penalty",
671
+ "presence_penalty",
672
+ "response_format",
673
+ "tools",
674
+ "tool_choice",
675
+ ],
676
+ jsonOutput: true,
677
+ },
678
+ {
679
+ test: "skip",
680
+ providerId: "azure",
681
+ stability: "unstable",
682
+ modelName: "gpt-5",
683
+ inputPrice: 1.25 / 1e6,
684
+ outputPrice: 10.0 / 1e6,
685
+ cachedInputPrice: 0.125 / 1e6,
686
+ requestPrice: 0,
687
+ contextSize: 400000,
688
+ maxOutput: 128000,
689
+ reasoning: true,
690
+ reasoningOutput: "omit",
691
+ streaming: true,
692
+ vision: true,
693
+ tools: true,
694
+ jsonOutputSchema: true,
695
+ supportedParameters: [
696
+ "temperature",
697
+ "top_p",
698
+ "frequency_penalty",
699
+ "presence_penalty",
700
+ "response_format",
701
+ "tools",
702
+ "tool_choice",
703
+ ],
704
+ jsonOutput: true,
705
+ },
706
+ ],
707
+ },
708
+ {
709
+ id: "gpt-5-mini",
710
+ name: "GPT-5 Mini",
711
+ description: "Compact GPT-5 variant with reasoning and vision at reduced cost.",
712
+ family: "openai",
713
+ releasedAt: new Date("2025-08-01"),
714
+ providers: [
715
+ {
716
+ providerId: "openai",
717
+ modelName: "gpt-5-mini",
718
+ inputPrice: 0.25 / 1e6,
719
+ outputPrice: 2 / 1e6,
720
+ cachedInputPrice: 0.025 / 1e6,
721
+ requestPrice: 0,
722
+ contextSize: 400000,
723
+ maxOutput: 128000,
724
+ reasoning: true,
725
+ streaming: true,
726
+ vision: true,
727
+ tools: true,
728
+ webSearch: true,
729
+ webSearchPrice: 0.01,
730
+ supportsResponsesApi: true,
731
+ jsonOutputSchema: true,
732
+ supportedParameters: [
733
+ "temperature",
734
+ "top_p",
735
+ "frequency_penalty",
736
+ "presence_penalty",
737
+ "response_format",
738
+ "tools",
739
+ "tool_choice",
740
+ ],
741
+ jsonOutput: true,
742
+ },
743
+ {
744
+ test: "skip",
745
+ providerId: "azure",
746
+ stability: "unstable",
747
+ modelName: "gpt-5-mini",
748
+ inputPrice: 0.25 / 1e6,
749
+ outputPrice: 2 / 1e6,
750
+ cachedInputPrice: 0.025 / 1e6,
751
+ requestPrice: 0,
752
+ contextSize: 400000,
753
+ maxOutput: 128000,
754
+ reasoning: true,
755
+ streaming: true,
756
+ vision: true,
757
+ tools: true,
758
+ jsonOutputSchema: true,
759
+ supportedParameters: [
760
+ "temperature",
761
+ "top_p",
762
+ "frequency_penalty",
763
+ "presence_penalty",
764
+ "response_format",
765
+ "tools",
766
+ "tool_choice",
767
+ ],
768
+ jsonOutput: true,
769
+ },
770
+ ],
771
+ },
772
+ {
773
+ id: "gpt-5-nano",
774
+ name: "GPT-5 Nano",
775
+ description: "Ultra-efficient GPT-5 variant for high-volume applications with reasoning support.",
776
+ family: "openai",
777
+ releasedAt: new Date("2025-08-01"),
778
+ providers: [
779
+ {
780
+ providerId: "openai",
781
+ modelName: "gpt-5-nano",
782
+ inputPrice: 0.05 / 1e6,
783
+ outputPrice: 0.4 / 1e6,
784
+ cachedInputPrice: 0.005 / 1e6,
785
+ requestPrice: 0,
786
+ contextSize: 400000,
787
+ maxOutput: 128000,
788
+ reasoning: true,
789
+ streaming: true,
790
+ vision: false,
791
+ tools: true,
792
+ webSearch: true,
793
+ webSearchPrice: 0.01,
794
+ supportsResponsesApi: true,
795
+ jsonOutputSchema: true,
796
+ supportedParameters: [
797
+ "temperature",
798
+ "top_p",
799
+ "frequency_penalty",
800
+ "presence_penalty",
801
+ "response_format",
802
+ "tools",
803
+ "tool_choice",
804
+ ],
805
+ jsonOutput: true,
806
+ },
807
+ {
808
+ test: "skip",
809
+ providerId: "azure",
810
+ stability: "unstable",
811
+ modelName: "gpt-5-nano",
812
+ inputPrice: 0.05 / 1e6,
813
+ outputPrice: 0.4 / 1e6,
814
+ cachedInputPrice: 0.005 / 1e6,
815
+ requestPrice: 0,
816
+ contextSize: 400000,
817
+ maxOutput: 128000,
818
+ reasoning: true,
819
+ streaming: true,
820
+ vision: false,
821
+ tools: true,
822
+ jsonOutputSchema: true,
823
+ supportedParameters: [
824
+ "temperature",
825
+ "top_p",
826
+ "frequency_penalty",
827
+ "presence_penalty",
828
+ "response_format",
829
+ "tools",
830
+ "tool_choice",
831
+ ],
832
+ jsonOutput: true,
833
+ },
834
+ ],
835
+ },
836
+ {
837
+ id: "gpt-5-chat-latest",
838
+ name: "GPT-5 Chat Latest",
839
+ description: "GPT-5 optimized for conversational interactions without tool calling.",
840
+ family: "openai",
841
+ releasedAt: new Date("2025-08-01"),
842
+ providers: [
843
+ {
844
+ providerId: "openai",
845
+ modelName: "gpt-5-chat-latest",
846
+ inputPrice: 1.25 / 1e6,
847
+ outputPrice: 10.0 / 1e6,
848
+ cachedInputPrice: 0.125 / 1e6,
849
+ requestPrice: 0,
850
+ contextSize: 400000,
851
+ maxOutput: 128000,
852
+ streaming: true,
853
+ vision: true,
854
+ tools: false,
855
+ jsonOutputSchema: true,
856
+ supportedParameters: [
857
+ "temperature",
858
+ "top_p",
859
+ "frequency_penalty",
860
+ "presence_penalty",
861
+ "response_format",
862
+ ],
863
+ jsonOutput: true,
864
+ },
865
+ ],
866
+ },
867
+ {
868
+ id: "gpt-5.1",
869
+ name: "GPT-5.1",
870
+ description: "Iterative improvement on GPT-5 with enhanced reasoning and tool support.",
871
+ family: "openai",
872
+ releasedAt: new Date("2025-11-01"),
873
+ providers: [
874
+ {
875
+ providerId: "openai",
876
+ modelName: "gpt-5.1",
877
+ inputPrice: 1.25 / 1e6,
878
+ outputPrice: 10.0 / 1e6,
879
+ cachedInputPrice: 0.125 / 1e6,
880
+ requestPrice: 0,
881
+ contextSize: 400000,
882
+ maxOutput: 128000,
883
+ streaming: true,
884
+ vision: true,
885
+ tools: true,
886
+ webSearch: true,
887
+ webSearchPrice: 0.01,
888
+ reasoning: true,
889
+ reasoningOutput: "omit",
890
+ supportsResponsesApi: true,
891
+ jsonOutputSchema: true,
892
+ supportedParameters: [
893
+ "temperature",
894
+ "top_p",
895
+ "frequency_penalty",
896
+ "presence_penalty",
897
+ "response_format",
898
+ ],
899
+ jsonOutput: true,
900
+ },
901
+ {
902
+ test: "skip",
903
+ providerId: "azure",
904
+ modelName: "gpt-5.1",
905
+ inputPrice: 1.25 / 1e6,
906
+ outputPrice: 10.0 / 1e6,
907
+ cachedInputPrice: 0.125 / 1e6,
908
+ discount: 0.3,
909
+ requestPrice: 0,
910
+ contextSize: 400000,
911
+ maxOutput: 128000,
912
+ streaming: true,
913
+ vision: true,
914
+ tools: true,
915
+ reasoning: true,
916
+ reasoningOutput: "omit",
917
+ jsonOutputSchema: true,
918
+ supportedParameters: [
919
+ "temperature",
920
+ "top_p",
921
+ "frequency_penalty",
922
+ "presence_penalty",
923
+ "response_format",
924
+ ],
925
+ jsonOutput: true,
926
+ },
927
+ ],
928
+ },
929
+ {
930
+ id: "gpt-5-pro",
931
+ name: "GPT-5 Pro",
932
+ description: "Premium GPT-5 tier with extended output limits and advanced reasoning for complex tasks.",
933
+ family: "openai",
934
+ releasedAt: new Date("2025-08-01"),
935
+ providers: [
936
+ {
937
+ test: "skip",
938
+ providerId: "openai",
939
+ modelName: "gpt-5-pro",
940
+ inputPrice: 15 / 1e6,
941
+ outputPrice: 120.0 / 1e6,
942
+ requestPrice: 0,
943
+ contextSize: 400000,
944
+ maxOutput: 272000,
945
+ streaming: true,
946
+ reasoning: true,
947
+ reasoningOutput: "omit",
948
+ vision: true,
949
+ tools: true,
950
+ webSearch: true,
951
+ webSearchPrice: 0.01,
952
+ supportsResponsesApi: true,
953
+ jsonOutputSchema: true,
954
+ jsonOutput: true,
955
+ },
956
+ ],
957
+ },
958
+ {
959
+ id: "gpt-5.1-codex",
960
+ name: "GPT-5.1 Codex",
961
+ description: "GPT-5.1 specialized for code generation and software development tasks.",
962
+ family: "openai",
963
+ releasedAt: new Date("2025-11-13"),
964
+ providers: [
965
+ {
966
+ providerId: "openai",
967
+ modelName: "gpt-5.1-codex",
968
+ inputPrice: 1.25 / 1e6,
969
+ outputPrice: 10 / 1e6,
970
+ requestPrice: 0,
971
+ contextSize: 400000,
972
+ maxOutput: 272000,
973
+ streaming: true,
974
+ reasoning: true,
975
+ reasoningOutput: "omit",
976
+ vision: true,
977
+ tools: true,
978
+ webSearch: true,
979
+ webSearchPrice: 0.01,
980
+ supportsResponsesApi: true,
981
+ jsonOutputSchema: false,
982
+ jsonOutput: true,
983
+ },
984
+ {
985
+ test: "skip",
986
+ providerId: "azure",
987
+ stability: "unstable",
988
+ modelName: "gpt-5.1-codex",
989
+ inputPrice: 1.25 / 1e6,
990
+ outputPrice: 10 / 1e6,
991
+ requestPrice: 0,
992
+ contextSize: 400000,
993
+ maxOutput: 272000,
994
+ streaming: true,
995
+ reasoning: true,
996
+ reasoningOutput: "omit",
997
+ vision: true,
998
+ tools: true,
999
+ supportsResponsesApi: true,
1000
+ jsonOutputSchema: false,
1001
+ jsonOutput: true,
1002
+ },
1003
+ ],
1004
+ },
1005
+ {
1006
+ id: "gpt-5.1-codex-mini",
1007
+ name: "GPT-5.1 Codex mini",
1008
+ description: "Lightweight code-focused model for efficient software development workflows.",
1009
+ family: "openai",
1010
+ releasedAt: new Date("2025-11-12"),
1011
+ providers: [
1012
+ {
1013
+ providerId: "openai",
1014
+ modelName: "gpt-5.1-codex-mini",
1015
+ inputPrice: 0.25 / 1e6,
1016
+ outputPrice: 2 / 1e6,
1017
+ cachedInputPrice: 0.025 / 1e6,
1018
+ requestPrice: 0,
1019
+ contextSize: 400000,
1020
+ maxOutput: 128000,
1021
+ streaming: true,
1022
+ reasoning: true,
1023
+ reasoningOutput: "omit",
1024
+ vision: true,
1025
+ tools: true,
1026
+ webSearch: true,
1027
+ webSearchPrice: 0.01,
1028
+ supportsResponsesApi: true,
1029
+ jsonOutputSchema: false,
1030
+ jsonOutput: true,
1031
+ },
1032
+ {
1033
+ test: "skip",
1034
+ providerId: "azure",
1035
+ stability: "unstable",
1036
+ modelName: "gpt-5.1-codex-mini",
1037
+ inputPrice: 0.25 / 1e6,
1038
+ outputPrice: 2 / 1e6,
1039
+ cachedInputPrice: 0.025 / 1e6,
1040
+ requestPrice: 0,
1041
+ contextSize: 400000,
1042
+ maxOutput: 128000,
1043
+ streaming: true,
1044
+ reasoning: true,
1045
+ reasoningOutput: "omit",
1046
+ vision: true,
1047
+ tools: true,
1048
+ supportsResponsesApi: true,
1049
+ jsonOutputSchema: false,
1050
+ jsonOutput: true,
1051
+ },
1052
+ ],
1053
+ },
1054
+ {
1055
+ id: "gpt-5.2",
1056
+ name: "GPT-5.2",
1057
+ description: "Latest GPT-5 model with enhanced reasoning and tool support.",
1058
+ family: "openai",
1059
+ releasedAt: new Date("2025-12-11"),
1060
+ providers: [
1061
+ {
1062
+ providerId: "openai",
1063
+ modelName: "gpt-5.2",
1064
+ inputPrice: 1.75 / 1e6,
1065
+ outputPrice: 14.0 / 1e6,
1066
+ cachedInputPrice: 0.175 / 1e6,
1067
+ requestPrice: 0,
1068
+ contextSize: 400000,
1069
+ maxOutput: 128000,
1070
+ streaming: true,
1071
+ vision: true,
1072
+ tools: true,
1073
+ webSearch: true,
1074
+ webSearchPrice: 0.01,
1075
+ reasoning: true,
1076
+ reasoningOutput: "omit",
1077
+ supportsResponsesApi: true,
1078
+ jsonOutputSchema: true,
1079
+ supportedParameters: [
1080
+ "temperature",
1081
+ "top_p",
1082
+ "frequency_penalty",
1083
+ "presence_penalty",
1084
+ "response_format",
1085
+ ],
1086
+ jsonOutput: true,
1087
+ },
1088
+ {
1089
+ test: "skip",
1090
+ providerId: "azure",
1091
+ modelName: "gpt-5.2",
1092
+ inputPrice: 1.75 / 1e6,
1093
+ outputPrice: 14.0 / 1e6,
1094
+ cachedInputPrice: 0.175 / 1e6,
1095
+ discount: 0.3,
1096
+ requestPrice: 0,
1097
+ contextSize: 400000,
1098
+ maxOutput: 128000,
1099
+ streaming: true,
1100
+ vision: true,
1101
+ tools: true,
1102
+ reasoning: true,
1103
+ reasoningOutput: "omit",
1104
+ jsonOutputSchema: true,
1105
+ supportedParameters: [
1106
+ "temperature",
1107
+ "top_p",
1108
+ "frequency_penalty",
1109
+ "presence_penalty",
1110
+ "response_format",
1111
+ ],
1112
+ jsonOutput: true,
1113
+ },
1114
+ ],
1115
+ },
1116
+ {
1117
+ id: "gpt-5.2-pro",
1118
+ name: "GPT-5.2 Pro",
1119
+ description: "Premium GPT-5.2 model with extended output limits and advanced reasoning for complex tasks.",
1120
+ family: "openai",
1121
+ releasedAt: new Date("2025-12-11"),
1122
+ providers: [
1123
+ {
1124
+ providerId: "openai",
1125
+ modelName: "gpt-5.2-pro",
1126
+ inputPrice: 21.0 / 1e6,
1127
+ outputPrice: 168.0 / 1e6,
1128
+ requestPrice: 0,
1129
+ contextSize: 400000,
1130
+ maxOutput: 272000,
1131
+ streaming: true,
1132
+ reasoning: true,
1133
+ reasoningOutput: "omit",
1134
+ vision: true,
1135
+ tools: true,
1136
+ webSearch: true,
1137
+ webSearchPrice: 0.01,
1138
+ supportsResponsesApi: true,
1139
+ jsonOutputSchema: false,
1140
+ jsonOutput: true,
1141
+ },
1142
+ {
1143
+ test: "skip",
1144
+ providerId: "azure",
1145
+ stability: "unstable",
1146
+ modelName: "gpt-5.2-pro",
1147
+ inputPrice: 21.0 / 1e6,
1148
+ outputPrice: 168.0 / 1e6,
1149
+ requestPrice: 0,
1150
+ contextSize: 400000,
1151
+ maxOutput: 272000,
1152
+ streaming: true,
1153
+ reasoning: true,
1154
+ reasoningOutput: "omit",
1155
+ vision: true,
1156
+ tools: true,
1157
+ supportsResponsesApi: true,
1158
+ jsonOutputSchema: false,
1159
+ jsonOutput: true,
1160
+ },
1161
+ ],
1162
+ },
1163
+ {
1164
+ id: "gpt-5.2-chat-latest",
1165
+ name: "GPT-5.2 Chat",
1166
+ description: "GPT-5.2 Chat is the ChatGPT production snapshot for chat use. Use it to try the latest chat-focused updates.",
1167
+ family: "openai",
1168
+ releasedAt: new Date("2025-12-11"),
1169
+ providers: [
1170
+ {
1171
+ providerId: "openai",
1172
+ modelName: "gpt-5.2-chat-latest",
1173
+ inputPrice: 1.75 / 1e6,
1174
+ outputPrice: 14.0 / 1e6,
1175
+ cachedInputPrice: 0.175 / 1e6,
1176
+ requestPrice: 0,
1177
+ contextSize: 128000,
1178
+ maxOutput: 16400,
1179
+ streaming: true,
1180
+ reasoning: true,
1181
+ reasoningOutput: "omit",
1182
+ vision: true,
1183
+ tools: true,
1184
+ webSearch: true,
1185
+ webSearchPrice: 0.01,
1186
+ supportsResponsesApi: true,
1187
+ jsonOutputSchema: false,
1188
+ jsonOutput: false,
1189
+ },
1190
+ {
1191
+ test: "skip",
1192
+ providerId: "azure",
1193
+ stability: "unstable",
1194
+ modelName: "gpt-5.2-chat-latest",
1195
+ inputPrice: 1.75 / 1e6,
1196
+ outputPrice: 14.0 / 1e6,
1197
+ cachedInputPrice: 0.175 / 1e6,
1198
+ requestPrice: 0,
1199
+ contextSize: 128000,
1200
+ maxOutput: 16400,
1201
+ streaming: true,
1202
+ reasoning: true,
1203
+ reasoningOutput: "omit",
1204
+ vision: true,
1205
+ tools: true,
1206
+ supportsResponsesApi: true,
1207
+ jsonOutputSchema: false,
1208
+ jsonOutput: false,
1209
+ },
1210
+ ],
1211
+ },
1212
+ ];
1213
+ //# sourceMappingURL=openai.js.map