active_harness_pricing 0.1.3 → 0.1.4

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.
@@ -0,0 +1,3226 @@
1
+ {
2
+ "aion-1-0": {
3
+ "name": "Aion-1.0",
4
+ "input_per_1m": 4.0,
5
+ "output_per_1m": 8.0,
6
+ "context_window": 131072
7
+ },
8
+ "aion-1-0-mini": {
9
+ "name": "Aion-1.0-Mini",
10
+ "input_per_1m": 0.7,
11
+ "output_per_1m": 1.4,
12
+ "context_window": 131072
13
+ },
14
+ "aion-2-0": {
15
+ "name": "Aion 2.0",
16
+ "input_per_1m": 0.8,
17
+ "output_per_1m": 1.6,
18
+ "context_window": 131072
19
+ },
20
+ "aion-rp-1-0-8b": {
21
+ "name": "Aion-RP 1.0 (8B)",
22
+ "input_per_1m": 0.8,
23
+ "output_per_1m": 1.6,
24
+ "context_window": 32768
25
+ },
26
+ "allam-7b-instruct-preview": {
27
+ "name": "ALLaM 7B Instruct Preview",
28
+ "context_window": 4096
29
+ },
30
+ "apriel-1-5-15b-thinker": {
31
+ "name": "Apriel 1.5 15B Thinker",
32
+ "context_window": 131072
33
+ },
34
+ "apriel-1-6-15b-thinker": {
35
+ "name": "Apriel 1.6 15B Thinker",
36
+ "context_window": 131072
37
+ },
38
+ "azure-openai": {
39
+ "name": "Azure OpenAI",
40
+ "input_per_1m": 75.0,
41
+ "output_per_1m": 150.0,
42
+ "context_window": 128000
43
+ },
44
+ "babbage": {
45
+ "name": "Babbage",
46
+ "input_per_1m": 0.5,
47
+ "output_per_1m": 0.5,
48
+ "context_window": 2048
49
+ },
50
+ "chatgpt-4o": {
51
+ "name": "ChatGPT-4o",
52
+ "input_per_1m": 5.0,
53
+ "output_per_1m": 15.0,
54
+ "context_window": 128000
55
+ },
56
+ "chronos-hermes-13b": {
57
+ "name": "Austism/chronos-hermes-13b",
58
+ "input_per_1m": 0.3,
59
+ "output_per_1m": 0.3,
60
+ "context_window": 4096
61
+ },
62
+ "claude-2": {
63
+ "name": "Claude 2",
64
+ "input_per_1m": 8.0,
65
+ "output_per_1m": 24.0,
66
+ "context_window": 100000
67
+ },
68
+ "claude-3-5-haiku": {
69
+ "name": "Claude 3.5 Haiku",
70
+ "input_per_1m": 0.8,
71
+ "output_per_1m": 4.0,
72
+ "context_window": 200000
73
+ },
74
+ "claude-3-5-sonnet": {
75
+ "name": "Claude 3.5 Sonnet",
76
+ "input_per_1m": 3.0,
77
+ "output_per_1m": 15.0,
78
+ "context_window": 200000
79
+ },
80
+ "claude-3-7-sonnet": {
81
+ "name": "Claude 3.7 Sonnet",
82
+ "input_per_1m": 3.0,
83
+ "output_per_1m": 15.0,
84
+ "context_window": 200000
85
+ },
86
+ "claude-3-haiku": {
87
+ "name": "Claude 3 Haiku",
88
+ "input_per_1m": 0.25,
89
+ "output_per_1m": 1.25,
90
+ "context_window": 200000
91
+ },
92
+ "claude-3-opus": {
93
+ "name": "Claude 3 Opus",
94
+ "input_per_1m": 15.0,
95
+ "output_per_1m": 75.0,
96
+ "context_window": 200000
97
+ },
98
+ "claude-3-sonnet": {
99
+ "name": "Claude 3 Sonnet",
100
+ "input_per_1m": 3.0,
101
+ "output_per_1m": 15.0
102
+ },
103
+ "claude-fable-5": {
104
+ "name": "Claude Fable 5",
105
+ "input_per_1m": 10.0,
106
+ "output_per_1m": 50.0,
107
+ "context_window": 1000000
108
+ },
109
+ "claude-haiku-4-5": {
110
+ "name": "Claude Haiku 4.5",
111
+ "input_per_1m": 1.0,
112
+ "output_per_1m": 5.0,
113
+ "context_window": 200000,
114
+ "tokens_per_second": 121.55,
115
+ "time_to_first_token": 0.617
116
+ },
117
+ "claude-instant": {
118
+ "name": "Claude Instant",
119
+ "input_per_1m": 0.8,
120
+ "output_per_1m": 2.4
121
+ },
122
+ "claude-opus-4": {
123
+ "name": "Claude Opus 4",
124
+ "input_per_1m": 15.0,
125
+ "output_per_1m": 75.0,
126
+ "context_window": 200000,
127
+ "tokens_per_second": 40.96,
128
+ "time_to_first_token": 1.701
129
+ },
130
+ "claude-opus-4-1": {
131
+ "name": "Claude Opus 4.1",
132
+ "input_per_1m": 15.0,
133
+ "output_per_1m": 75.0,
134
+ "context_window": 200000,
135
+ "tokens_per_second": 40.16,
136
+ "time_to_first_token": 1.908
137
+ },
138
+ "claude-opus-4-5": {
139
+ "name": "Claude Opus 4.5",
140
+ "input_per_1m": 5.0,
141
+ "output_per_1m": 25.0,
142
+ "context_window": 200000,
143
+ "tokens_per_second": 62.578,
144
+ "time_to_first_token": 1.338
145
+ },
146
+ "claude-opus-4-6": {
147
+ "name": "Claude Opus 4.6",
148
+ "input_per_1m": 5.0,
149
+ "output_per_1m": 25.0,
150
+ "context_window": 1000000,
151
+ "tokens_per_second": 51.927,
152
+ "time_to_first_token": 1.072
153
+ },
154
+ "claude-opus-4-7": {
155
+ "name": "Claude Opus 4.7",
156
+ "input_per_1m": 5.0,
157
+ "output_per_1m": 25.0,
158
+ "context_window": 1000000,
159
+ "tokens_per_second": 44.753,
160
+ "time_to_first_token": 0.783
161
+ },
162
+ "claude-opus-4-8": {
163
+ "name": "Claude Opus 4.8",
164
+ "input_per_1m": 5.0,
165
+ "output_per_1m": 25.0,
166
+ "tokens_per_second": 67.785,
167
+ "time_to_first_token": 41.62
168
+ },
169
+ "claude-opus-4-8-fast": {
170
+ "name": "Claude Opus 4.8 Fast",
171
+ "input_per_1m": 10.0,
172
+ "output_per_1m": 50.0
173
+ },
174
+ "claude-sonnet-4": {
175
+ "name": "Claude Sonnet 4",
176
+ "input_per_1m": 3.0,
177
+ "output_per_1m": 15.0,
178
+ "context_window": 200000,
179
+ "tokens_per_second": 52.179,
180
+ "time_to_first_token": 1.063
181
+ },
182
+ "claude-sonnet-4-5": {
183
+ "name": "Claude Sonnet 4.5",
184
+ "input_per_1m": 3.0,
185
+ "output_per_1m": 15.0,
186
+ "context_window": 1000000,
187
+ "tokens_per_second": 59.879,
188
+ "time_to_first_token": 1.198
189
+ },
190
+ "claude-sonnet-4-6": {
191
+ "name": "Claude Sonnet 4.6",
192
+ "input_per_1m": 3.0,
193
+ "output_per_1m": 15.0,
194
+ "context_window": 1000000,
195
+ "tokens_per_second": 52.598,
196
+ "time_to_first_token": 0.942
197
+ },
198
+ "code-llama-13b": {
199
+ "name": "Code Llama 13B",
200
+ "input_per_1m": 0.2,
201
+ "output_per_1m": 0.2,
202
+ "context_window": 16384
203
+ },
204
+ "code-llama-13b-instruct": {
205
+ "name": "Code Llama 13B Instruct",
206
+ "input_per_1m": 0.2,
207
+ "output_per_1m": 0.2,
208
+ "context_window": 16384
209
+ },
210
+ "code-llama-13b-python": {
211
+ "name": "Code Llama 13B Python",
212
+ "input_per_1m": 0.2,
213
+ "output_per_1m": 0.2,
214
+ "context_window": 16384
215
+ },
216
+ "code-llama-34b": {
217
+ "name": "Code Llama 34B",
218
+ "input_per_1m": 0.9,
219
+ "output_per_1m": 0.9,
220
+ "context_window": 16384
221
+ },
222
+ "code-llama-34b-instruct": {
223
+ "name": "Code Llama 34B Instruct",
224
+ "input_per_1m": 0.776,
225
+ "output_per_1m": 0.776,
226
+ "context_window": 16384
227
+ },
228
+ "code-llama-34b-python": {
229
+ "name": "Code Llama 34B Python",
230
+ "input_per_1m": 0.9,
231
+ "output_per_1m": 0.9,
232
+ "context_window": 16384
233
+ },
234
+ "code-llama-70b": {
235
+ "name": "Code Llama 70B",
236
+ "input_per_1m": 0.9,
237
+ "output_per_1m": 0.9,
238
+ "context_window": 4096
239
+ },
240
+ "code-llama-70b-instruct": {
241
+ "name": "Code Llama 70B Instruct",
242
+ "input_per_1m": 0.9,
243
+ "output_per_1m": 0.9,
244
+ "context_window": 4096
245
+ },
246
+ "code-llama-70b-python": {
247
+ "name": "Code Llama 70B Python",
248
+ "input_per_1m": 0.9,
249
+ "output_per_1m": 0.9,
250
+ "context_window": 4096
251
+ },
252
+ "code-llama-7b": {
253
+ "name": "Code Llama 7B",
254
+ "input_per_1m": 0.2,
255
+ "output_per_1m": 0.2,
256
+ "context_window": 16384
257
+ },
258
+ "code-llama-7b-instruct": {
259
+ "name": "Code Llama 7B Instruct",
260
+ "input_per_1m": 0.2,
261
+ "output_per_1m": 0.2,
262
+ "context_window": 16384
263
+ },
264
+ "codegemma-2b": {
265
+ "name": "CodeGemma 2B",
266
+ "input_per_1m": 0.1,
267
+ "output_per_1m": 0.1,
268
+ "context_window": 8192
269
+ },
270
+ "codegemma-7b": {
271
+ "name": "CodeGemma 7B",
272
+ "input_per_1m": 0.2,
273
+ "output_per_1m": 0.2,
274
+ "context_window": 128000
275
+ },
276
+ "codellama-7b-instruct-solidity": {
277
+ "name": "CodeLLaMa 7B Instruct Solidity",
278
+ "context_window": 4096
279
+ },
280
+ "codeqwen-1-5-7b": {
281
+ "name": "CodeQwen 1.5 7B",
282
+ "input_per_1m": 0.2,
283
+ "output_per_1m": 0.2,
284
+ "context_window": 65536
285
+ },
286
+ "coder-large": {
287
+ "name": "Coder Large",
288
+ "input_per_1m": 0.5,
289
+ "output_per_1m": 0.8,
290
+ "context_window": 32768
291
+ },
292
+ "codestral-2508": {
293
+ "name": "Codestral 2508",
294
+ "input_per_1m": 0.3,
295
+ "output_per_1m": 0.9,
296
+ "context_window": 256000
297
+ },
298
+ "codex-mini": {
299
+ "name": "Codex Mini",
300
+ "input_per_1m": 1.5,
301
+ "output_per_1m": 6.0,
302
+ "context_window": 200000
303
+ },
304
+ "cogito-v1-preview-llama-3b": {
305
+ "name": "Cogito v1 Preview Llama 3B",
306
+ "input_per_1m": 0.1,
307
+ "output_per_1m": 0.1,
308
+ "context_window": 131072
309
+ },
310
+ "cogito-v1-preview-llama-70b": {
311
+ "name": "Cogito v1 Preview Llama 70B",
312
+ "context_window": 131072
313
+ },
314
+ "cogito-v1-preview-llama-70b-turbo": {
315
+ "name": "Cogito v1 Preview Llama 70B Turbo"
316
+ },
317
+ "cogito-v1-preview-llama-8b": {
318
+ "name": "Cogito v1 Preview Llama 8B",
319
+ "context_window": 131072
320
+ },
321
+ "cogito-v1-preview-qwen-14b": {
322
+ "name": "Cogito v1 Preview Qwen 14B",
323
+ "context_window": 131072
324
+ },
325
+ "cogito-v1-preview-qwen-32b": {
326
+ "name": "Cogito v1 Preview Qwen 32B",
327
+ "context_window": 131072
328
+ },
329
+ "cogito-v2-1-671b": {
330
+ "name": "Cogito v2.1 671B",
331
+ "input_per_1m": 0.9,
332
+ "output_per_1m": 0.9,
333
+ "context_window": 128000
334
+ },
335
+ "cogito-v2-preview-llama-109b": {
336
+ "name": "Cogito V2 Preview Llama 109B",
337
+ "context_window": 131072
338
+ },
339
+ "cogito-v2-preview-llama-405b": {
340
+ "name": "Cogito V2 Preview Llama 405B",
341
+ "context_window": 131072
342
+ },
343
+ "cogito-v2-preview-llama-70b": {
344
+ "name": "Cogito V2 Preview Llama 70B",
345
+ "context_window": 131072
346
+ },
347
+ "command": {
348
+ "name": "Command",
349
+ "input_per_1m": 1.0,
350
+ "output_per_1m": 2.0
351
+ },
352
+ "command-a": {
353
+ "name": "Command A",
354
+ "input_per_1m": 2.5,
355
+ "output_per_1m": 10.0,
356
+ "context_window": 256000,
357
+ "tokens_per_second": 73.097,
358
+ "time_to_first_token": 0.297
359
+ },
360
+ "command-light": {
361
+ "name": "Command Light",
362
+ "input_per_1m": 0.3,
363
+ "output_per_1m": 0.6
364
+ },
365
+ "command-r": {
366
+ "name": "Command R",
367
+ "input_per_1m": 0.15,
368
+ "output_per_1m": 0.6,
369
+ "context_window": 128000
370
+ },
371
+ "command-r-08-2024": {
372
+ "name": "Command R (08-2024)",
373
+ "input_per_1m": 0.15,
374
+ "output_per_1m": 0.6,
375
+ "context_window": 128000
376
+ },
377
+ "command-r7b-12-2024": {
378
+ "name": "Command R7B (12-2024)",
379
+ "input_per_1m": 0.0375,
380
+ "output_per_1m": 0.15,
381
+ "context_window": 128000
382
+ },
383
+ "curie": {
384
+ "name": "curie",
385
+ "input_per_1m": 1.0,
386
+ "output_per_1m": 1.0,
387
+ "context_window": 2048
388
+ },
389
+ "cydonia-24b": {
390
+ "name": "Cydonia 24B V4.1",
391
+ "input_per_1m": 0.3,
392
+ "output_per_1m": 0.5,
393
+ "context_window": 131072
394
+ },
395
+ "deepcoder-14b-preview": {
396
+ "name": "DeepCoder 14B Preview"
397
+ },
398
+ "deephermes-3-mistral-24b-preview": {
399
+ "name": "DeepHermes 3 Mistral 24B Preview",
400
+ "context_window": 32768
401
+ },
402
+ "deepseek": {
403
+ "name": "DeepSeek V3",
404
+ "input_per_1m": 0.014,
405
+ "output_per_1m": 0.028,
406
+ "context_window": 163840
407
+ },
408
+ "deepseek-coder-1-3b-base": {
409
+ "name": "DeepSeek Coder 1.3B Base",
410
+ "input_per_1m": 0.1,
411
+ "output_per_1m": 0.1,
412
+ "context_window": 16384
413
+ },
414
+ "deepseek-coder-33b-instruct": {
415
+ "name": "DeepSeek Coder 33B Instruct",
416
+ "input_per_1m": 0.8,
417
+ "output_per_1m": 0.8,
418
+ "context_window": 16384
419
+ },
420
+ "deepseek-coder-7b-base": {
421
+ "name": "DeepSeek Coder 7B Base",
422
+ "input_per_1m": 0.2,
423
+ "output_per_1m": 0.2,
424
+ "context_window": 4096
425
+ },
426
+ "deepseek-coder-7b-instruct": {
427
+ "name": "DeepSeek Coder 7B Instruct v1.5",
428
+ "input_per_1m": 0.2,
429
+ "output_per_1m": 0.2,
430
+ "context_window": 4096
431
+ },
432
+ "deepseek-prover": {
433
+ "name": "DeepSeek Prover V2",
434
+ "context_window": 163840
435
+ },
436
+ "deepseek-r1-0528-qwen3-8b": {
437
+ "name": "DeepSeek R1 0528 Qwen3 8B",
438
+ "input_per_1m": 0.2,
439
+ "output_per_1m": 0.2,
440
+ "context_window": 128000
441
+ },
442
+ "deepseek-r1t-chimera": {
443
+ "name": "DeepSeek R1T Chimera",
444
+ "context_window": 163840
445
+ },
446
+ "deepseek-r1t2-chimera": {
447
+ "name": "DeepSeek R1T2 Chimera",
448
+ "context_window": 163840
449
+ },
450
+ "deepseek-v3-1-nex-n1": {
451
+ "name": "DeepSeek V3.1 Nex N1",
452
+ "context_window": 131072
453
+ },
454
+ "deepseek-v3-1-terminus": {
455
+ "name": "DeepSeek V3.1 Terminus",
456
+ "input_per_1m": 0.27,
457
+ "output_per_1m": 1.0,
458
+ "context_window": 163840
459
+ },
460
+ "deepseek-v3-2": {
461
+ "name": "DeepSeek V3.2 Exp",
462
+ "input_per_1m": 0.27,
463
+ "output_per_1m": 0.41,
464
+ "context_window": 163840
465
+ },
466
+ "deepseek-v3-2-speciale": {
467
+ "name": "DeepSeek V3.2 Speciale",
468
+ "context_window": 163840
469
+ },
470
+ "deepseek-v4-flash-non-reasoning": {
471
+ "name": "DeepSeek V4 Flash (Non-Reasoning)",
472
+ "input_per_1m": 0.098,
473
+ "output_per_1m": 0.196,
474
+ "context_window": 1048576,
475
+ "tokens_per_second": 103.445,
476
+ "time_to_first_token": 1.029
477
+ },
478
+ "deepseek-v4-pro": {
479
+ "name": "DeepSeek V4 Pro",
480
+ "input_per_1m": 0.435,
481
+ "output_per_1m": 0.87,
482
+ "context_window": 1048576,
483
+ "tokens_per_second": 80.583,
484
+ "time_to_first_token": 1.212
485
+ },
486
+ "devstral-2-123b": {
487
+ "name": "Devstral 2 123B",
488
+ "input_per_1m": 0.4,
489
+ "output_per_1m": 2.0
490
+ },
491
+ "devstral-2-2512": {
492
+ "name": "Devstral 2 2512",
493
+ "input_per_1m": 0.4,
494
+ "output_per_1m": 2.0,
495
+ "context_window": 262144,
496
+ "tokens_per_second": 74.286,
497
+ "time_to_first_token": 0.583
498
+ },
499
+ "devstral-medium": {
500
+ "name": "Devstral Medium",
501
+ "context_window": 131072,
502
+ "tokens_per_second": 60.716,
503
+ "time_to_first_token": 0.569
504
+ },
505
+ "devstral-small-1-1": {
506
+ "name": "Devstral Small 1.1",
507
+ "input_per_1m": 0.07,
508
+ "output_per_1m": 0.28,
509
+ "context_window": 131072,
510
+ "tokens_per_second": 72.725,
511
+ "time_to_first_token": 0.571
512
+ },
513
+ "devstral-small-2505": {
514
+ "name": "Devstral Small 2505",
515
+ "context_window": 128000
516
+ },
517
+ "dolphin-2-6-mixtral-8x7b": {
518
+ "name": "Dolphin 2.6 Mixtral 8x7B",
519
+ "input_per_1m": 0.5,
520
+ "output_per_1m": 0.5,
521
+ "context_window": 32768
522
+ },
523
+ "dolphin-2-9-2-qwen2-72b": {
524
+ "name": "Dolphin 2.9.2 Qwen2 72B",
525
+ "input_per_1m": 0.9,
526
+ "output_per_1m": 0.9,
527
+ "context_window": 131072
528
+ },
529
+ "ernie-4-5-21b-a3b": {
530
+ "name": "ERNIE 4.5 21B A3B",
531
+ "input_per_1m": 0.9,
532
+ "output_per_1m": 0.9,
533
+ "context_window": 120000
534
+ },
535
+ "ernie-4-5-21b-a3b-thinking": {
536
+ "name": "ERNIE 4.5 21B A3B Thinking",
537
+ "context_window": 131072
538
+ },
539
+ "ernie-4-5-300b-a47b": {
540
+ "name": "ERNIE 4.5 300B A47B",
541
+ "input_per_1m": 0.9,
542
+ "output_per_1m": 0.9,
543
+ "context_window": 123000
544
+ },
545
+ "ernie-4-5-vl-28b-a3b": {
546
+ "name": "ERNIE 4.5 VL 28B A3B",
547
+ "context_window": 30000
548
+ },
549
+ "ernie-4-5-vl-424b-a47b": {
550
+ "name": "ERNIE 4.5 VL 424B A47B",
551
+ "input_per_1m": 0.42,
552
+ "output_per_1m": 1.25,
553
+ "context_window": 123000
554
+ },
555
+ "facebook-cwm": {
556
+ "name": "Facebook CWM"
557
+ },
558
+ "fare-20b": {
559
+ "name": "FARE 20B",
560
+ "input_per_1m": 0.9,
561
+ "output_per_1m": 0.9,
562
+ "context_window": 131072
563
+ },
564
+ "gemini-1-0-pro": {
565
+ "name": "Gemini 1.0 Pro",
566
+ "input_per_1m": 0.125,
567
+ "output_per_1m": 0.375,
568
+ "context_window": 32760
569
+ },
570
+ "gemini-1-5-flash": {
571
+ "name": "Gemini 1.5 Flash",
572
+ "input_per_1m": 0.35,
573
+ "output_per_1m": 1.05,
574
+ "context_window": 1048576
575
+ },
576
+ "gemini-2-0-flash": {
577
+ "name": "Gemini 2.0 Flash",
578
+ "input_per_1m": 0.1,
579
+ "output_per_1m": 0.4,
580
+ "context_window": 1048576
581
+ },
582
+ "gemini-2-0-flash-experimental": {
583
+ "name": "Gemini 2.0 Flash Experimental",
584
+ "context_window": 1048576
585
+ },
586
+ "gemini-2-0-flash-lite": {
587
+ "name": "Gemini 2.0 Flash Lite",
588
+ "input_per_1m": 0.075,
589
+ "output_per_1m": 0.3,
590
+ "context_window": 1048576
591
+ },
592
+ "gemini-2-5-computer-use-preview": {
593
+ "name": "Gemini 2.5 Computer Use Preview",
594
+ "input_per_1m": 1.25,
595
+ "output_per_1m": 10.0,
596
+ "context_window": 131072
597
+ },
598
+ "gemini-2-5-flash": {
599
+ "name": "Gemini 2.5 Flash",
600
+ "input_per_1m": 0.3,
601
+ "output_per_1m": 2.5,
602
+ "context_window": 1048576
603
+ },
604
+ "gemini-2-5-flash-image-nano-banana": {
605
+ "name": "Gemini 2.5 Flash Image (Nano Banana)",
606
+ "input_per_1m": 0.3,
607
+ "output_per_1m": 2.5,
608
+ "context_window": 32768
609
+ },
610
+ "gemini-2-5-flash-image-preview-nano-banana": {
611
+ "name": "Gemini 2.5 Flash Image Preview (Nano Banana)",
612
+ "context_window": 1048576
613
+ },
614
+ "gemini-2-5-flash-lite": {
615
+ "name": "Gemini 2.5 Flash Lite",
616
+ "input_per_1m": 0.1,
617
+ "output_per_1m": 0.4,
618
+ "context_window": 1048576,
619
+ "tokens_per_second": 284.285,
620
+ "time_to_first_token": 0.322
621
+ },
622
+ "gemini-2-5-flash-lite-preview-09-2025": {
623
+ "name": "Gemini 2.5 Flash Lite Preview 09-2025",
624
+ "input_per_1m": 0.1,
625
+ "output_per_1m": 0.4,
626
+ "context_window": 1048576
627
+ },
628
+ "gemini-2-5-flash-preview-09-2025": {
629
+ "name": "Gemini 2.5 Flash Preview 09-2025",
630
+ "context_window": 1048576
631
+ },
632
+ "gemini-2-5-pro": {
633
+ "name": "Gemini 2.5 Pro",
634
+ "input_per_1m": 1.0,
635
+ "output_per_1m": 20.0,
636
+ "context_window": 1048576,
637
+ "tokens_per_second": 142.147,
638
+ "time_to_first_token": 15.764
639
+ },
640
+ "gemini-2-5-pro-preview": {
641
+ "name": "Gemini 2.5 Pro Preview 06-05",
642
+ "input_per_1m": 1.25,
643
+ "output_per_1m": 10.0,
644
+ "context_window": 1048576
645
+ },
646
+ "gemini-3-1-flash-lite-preview": {
647
+ "name": "Gemini 3.1 Flash Lite Preview",
648
+ "input_per_1m": 0.25,
649
+ "output_per_1m": 1.5,
650
+ "context_window": 1048576,
651
+ "tokens_per_second": 306.346,
652
+ "time_to_first_token": 5.295
653
+ },
654
+ "gemini-3-1-pro-preview": {
655
+ "name": "Gemini 3.1 Pro Preview",
656
+ "input_per_1m": 2.0,
657
+ "output_per_1m": 12.0,
658
+ "context_window": 1048576,
659
+ "tokens_per_second": 132.896,
660
+ "time_to_first_token": 31.965
661
+ },
662
+ "gemini-3-1-pro-preview-custom-tools": {
663
+ "name": "Gemini 3.1 Pro Preview Custom Tools",
664
+ "input_per_1m": 2.0,
665
+ "output_per_1m": 12.0,
666
+ "context_window": 1048576
667
+ },
668
+ "gemini-3-5-flash": {
669
+ "name": "Gemini 3.5 Flash",
670
+ "input_per_1m": 1.5,
671
+ "output_per_1m": 9.0,
672
+ "context_window": 1048576,
673
+ "tokens_per_second": 209.117,
674
+ "time_to_first_token": 0.822
675
+ },
676
+ "gemini-3-flash-preview": {
677
+ "name": "Gemini 3 Flash Preview",
678
+ "input_per_1m": 0.5,
679
+ "output_per_1m": 3.0,
680
+ "context_window": 1048576,
681
+ "tokens_per_second": 200.454,
682
+ "time_to_first_token": 0.796
683
+ },
684
+ "gemini-3-pro-preview": {
685
+ "name": "Gemini 3 Pro Preview",
686
+ "input_per_1m": 2.0,
687
+ "output_per_1m": 12.0,
688
+ "context_window": 1048576
689
+ },
690
+ "gemma-2-27b": {
691
+ "name": "Gemma 2 27B",
692
+ "input_per_1m": 0.65,
693
+ "output_per_1m": 0.65,
694
+ "context_window": 8192
695
+ },
696
+ "gemma-2-9b": {
697
+ "name": "Gemma 2 9B",
698
+ "context_window": 8192
699
+ },
700
+ "gemma-2b": {
701
+ "name": "Gemma 2B",
702
+ "input_per_1m": 0.1,
703
+ "output_per_1m": 0.1,
704
+ "context_window": 8192
705
+ },
706
+ "gemma-3-12b": {
707
+ "name": "Gemma 3 12B",
708
+ "input_per_1m": 0.05,
709
+ "output_per_1m": 0.15,
710
+ "context_window": 131072
711
+ },
712
+ "gemma-3-1b": {
713
+ "name": "Gemma 3 1B",
714
+ "context_window": 128000
715
+ },
716
+ "gemma-3-1b-pretrained": {
717
+ "name": "Gemma 3 1B (Pretrained)"
718
+ },
719
+ "gemma-3-270m-instruct": {
720
+ "name": "Gemma 3 270M Instruct"
721
+ },
722
+ "gemma-3-27b": {
723
+ "name": "Gemma 3 27B",
724
+ "context_window": 128000
725
+ },
726
+ "gemma-3-4b": {
727
+ "name": "Gemma 3 4B",
728
+ "context_window": 131072
729
+ },
730
+ "gemma-3n-4b": {
731
+ "name": "Gemma 3n 4B",
732
+ "input_per_1m": 0.06,
733
+ "output_per_1m": 0.12,
734
+ "context_window": 32768,
735
+ "tokens_per_second": 45.949,
736
+ "time_to_first_token": 0.499
737
+ },
738
+ "gemma-4-26b-a4b-instruct": {
739
+ "name": "Gemma 4 26B A4B Instruct",
740
+ "context_window": 262144,
741
+ "tokens_per_second": 45.527,
742
+ "time_to_first_token": 0.765
743
+ },
744
+ "gemma-4-31b-instruct": {
745
+ "name": "Gemma 4 31B Instruct",
746
+ "input_per_1m": 0.12,
747
+ "output_per_1m": 0.35,
748
+ "context_window": 262144,
749
+ "tokens_per_second": 34.999,
750
+ "time_to_first_token": 0.973
751
+ },
752
+ "gemma-4-e2b-it": {
753
+ "name": "Gemma 4 E2B IT",
754
+ "context_window": 131072
755
+ },
756
+ "gemma-4-e4b-it": {
757
+ "name": "Gemma 4 E4B IT"
758
+ },
759
+ "gemma-7b": {
760
+ "name": "Gemma 7B",
761
+ "input_per_1m": 0.2,
762
+ "output_per_1m": 0.2,
763
+ "context_window": 8000
764
+ },
765
+ "gemma-7b-instruct": {
766
+ "name": "Gemma 7B Instruct",
767
+ "input_per_1m": 0.07,
768
+ "output_per_1m": 0.07,
769
+ "context_window": 8192
770
+ },
771
+ "glm-4-1v-9b-thinking": {
772
+ "name": "GLM 4.1V 9B Thinking",
773
+ "context_window": 32768
774
+ },
775
+ "glm-4-32b": {
776
+ "name": "GLM 4 32B",
777
+ "context_window": 128000
778
+ },
779
+ "glm-4-5": {
780
+ "name": "GLM 4.5",
781
+ "input_per_1m": 0.6,
782
+ "output_per_1m": 2.2,
783
+ "context_window": 131072
784
+ },
785
+ "glm-4-5-air": {
786
+ "name": "GLM 4.5 Air",
787
+ "input_per_1m": 0.13,
788
+ "output_per_1m": 0.85,
789
+ "context_window": 131072,
790
+ "tokens_per_second": 75.702,
791
+ "time_to_first_token": 1.556
792
+ },
793
+ "glm-4-5v": {
794
+ "name": "GLM 4.5V",
795
+ "context_window": 65536,
796
+ "tokens_per_second": 26.792,
797
+ "time_to_first_token": 75.013
798
+ },
799
+ "glm-4-6": {
800
+ "name": "GLM 4.6",
801
+ "input_per_1m": 0.43,
802
+ "output_per_1m": 1.74,
803
+ "context_window": 204800,
804
+ "tokens_per_second": 60.362,
805
+ "time_to_first_token": 1.687
806
+ },
807
+ "glm-4-6v": {
808
+ "name": "GLM 4.6V",
809
+ "input_per_1m": 0.3,
810
+ "output_per_1m": 0.9,
811
+ "context_window": 131072,
812
+ "tokens_per_second": 81.089,
813
+ "time_to_first_token": 1.21
814
+ },
815
+ "glm-4-7": {
816
+ "name": "GLM 4.7",
817
+ "context_window": 202752,
818
+ "tokens_per_second": 97.749,
819
+ "time_to_first_token": 0.635
820
+ },
821
+ "glm-4-7-flash": {
822
+ "name": "GLM-4.7-Flash",
823
+ "input_per_1m": 0.06,
824
+ "output_per_1m": 0.4,
825
+ "context_window": 202752,
826
+ "tokens_per_second": 110.388,
827
+ "time_to_first_token": 1.251
828
+ },
829
+ "glm-5": {
830
+ "name": "GLM 5",
831
+ "input_per_1m": 0.6,
832
+ "output_per_1m": 1.92,
833
+ "context_window": 202752,
834
+ "tokens_per_second": 74.519,
835
+ "time_to_first_token": 1.156
836
+ },
837
+ "glm-5-1": {
838
+ "name": "GLM 5.1",
839
+ "input_per_1m": 0.98,
840
+ "output_per_1m": 3.08,
841
+ "context_window": 202752,
842
+ "tokens_per_second": 70.6,
843
+ "time_to_first_token": 0.743
844
+ },
845
+ "glm-5-fp4": {
846
+ "name": "GLM-5 FP4"
847
+ },
848
+ "glm-5-turbo": {
849
+ "name": "GLM-5 Turbo",
850
+ "input_per_1m": 1.2,
851
+ "output_per_1m": 4.0,
852
+ "context_window": 202752
853
+ },
854
+ "glm-5v-turbo": {
855
+ "name": "GLM-5V Turbo",
856
+ "context_window": 202752
857
+ },
858
+ "goliath-120b": {
859
+ "name": "Goliath 120B",
860
+ "context_window": 6144
861
+ },
862
+ "gpt-3-5-turbo": {
863
+ "name": "GPT-3.5 Turbo",
864
+ "input_per_1m": 0.5,
865
+ "output_per_1m": 1.5,
866
+ "context_window": 16385,
867
+ "tokens_per_second": 148.577,
868
+ "time_to_first_token": 0.567
869
+ },
870
+ "gpt-3-5-turbo-16k": {
871
+ "name": "GPT-3.5 Turbo 16k",
872
+ "input_per_1m": 3.0,
873
+ "output_per_1m": 4.0,
874
+ "context_window": 16385
875
+ },
876
+ "gpt-3-5-turbo-instruct": {
877
+ "name": "GPT-3.5 Turbo Instruct",
878
+ "input_per_1m": 1.5,
879
+ "output_per_1m": 2.0,
880
+ "context_window": 4095
881
+ },
882
+ "gpt-4": {
883
+ "name": "GPT-4",
884
+ "input_per_1m": 30.0,
885
+ "output_per_1m": 60.0,
886
+ "context_window": 8191,
887
+ "tokens_per_second": 34.511,
888
+ "time_to_first_token": 0.936
889
+ },
890
+ "gpt-4-1": {
891
+ "name": "GPT-4.1",
892
+ "input_per_1m": 2.0,
893
+ "output_per_1m": 8.0,
894
+ "context_window": 1047576,
895
+ "tokens_per_second": 129.561,
896
+ "time_to_first_token": 0.519
897
+ },
898
+ "gpt-4-1-mini": {
899
+ "name": "GPT-4.1 Mini",
900
+ "input_per_1m": 0.2,
901
+ "output_per_1m": 0.8,
902
+ "context_window": 1047576,
903
+ "tokens_per_second": 94.429,
904
+ "time_to_first_token": 0.472
905
+ },
906
+ "gpt-4-1-nano": {
907
+ "name": "GPT-4.1 Nano",
908
+ "input_per_1m": 0.05,
909
+ "output_per_1m": 0.2,
910
+ "context_window": 1047576,
911
+ "tokens_per_second": 158.996,
912
+ "time_to_first_token": 0.355
913
+ },
914
+ "gpt-4-turbo": {
915
+ "name": "GPT-4 Turbo",
916
+ "input_per_1m": 5.0,
917
+ "output_per_1m": 15.0,
918
+ "context_window": 128000,
919
+ "tokens_per_second": 31.82,
920
+ "time_to_first_token": 1.309
921
+ },
922
+ "gpt-4o": {
923
+ "name": "GPT-4o",
924
+ "input_per_1m": 2.5,
925
+ "output_per_1m": 10.0,
926
+ "context_window": 128000
927
+ },
928
+ "gpt-4o-mini": {
929
+ "name": "GPT-4o-mini",
930
+ "input_per_1m": 0.15,
931
+ "output_per_1m": 0.6,
932
+ "context_window": 128000,
933
+ "tokens_per_second": 75.042,
934
+ "time_to_first_token": 0.494
935
+ },
936
+ "gpt-5": {
937
+ "name": "GPT-5",
938
+ "input_per_1m": 0.625,
939
+ "output_per_1m": 5.0,
940
+ "context_window": 400000,
941
+ "tokens_per_second": 75.724,
942
+ "time_to_first_token": 0.794
943
+ },
944
+ "gpt-5-1": {
945
+ "name": "GPT-5.1",
946
+ "input_per_1m": 1.25,
947
+ "output_per_1m": 10.0,
948
+ "context_window": 400000,
949
+ "tokens_per_second": 119.577,
950
+ "time_to_first_token": 0.624
951
+ },
952
+ "gpt-5-1-chat": {
953
+ "name": "GPT-5.1 Chat",
954
+ "input_per_1m": 1.25,
955
+ "output_per_1m": 10.0,
956
+ "context_window": 128000
957
+ },
958
+ "gpt-5-1-codex": {
959
+ "name": "GPT-5.1-Codex",
960
+ "input_per_1m": 1.25,
961
+ "output_per_1m": 10.0,
962
+ "context_window": 400000,
963
+ "tokens_per_second": 206.47,
964
+ "time_to_first_token": 10.485
965
+ },
966
+ "gpt-5-1-codex-max": {
967
+ "name": "GPT-5.1-Codex-Max",
968
+ "input_per_1m": 1.25,
969
+ "output_per_1m": 10.0,
970
+ "context_window": 400000
971
+ },
972
+ "gpt-5-1-codex-mini": {
973
+ "name": "GPT-5.1-Codex-Mini",
974
+ "input_per_1m": 0.25,
975
+ "output_per_1m": 2.0,
976
+ "context_window": 400000,
977
+ "tokens_per_second": 219.093,
978
+ "time_to_first_token": 3.14
979
+ },
980
+ "gpt-5-2": {
981
+ "name": "GPT-5.2",
982
+ "input_per_1m": 0.875,
983
+ "output_per_1m": 7.0,
984
+ "context_window": 400000,
985
+ "tokens_per_second": 77.651,
986
+ "time_to_first_token": 0.686
987
+ },
988
+ "gpt-5-2-chat": {
989
+ "name": "GPT-5.2 Chat",
990
+ "input_per_1m": 0.875,
991
+ "output_per_1m": 7.0,
992
+ "context_window": 128000
993
+ },
994
+ "gpt-5-2-codex": {
995
+ "name": "GPT-5.2-Codex",
996
+ "input_per_1m": 1.75,
997
+ "output_per_1m": 14.0,
998
+ "context_window": 400000,
999
+ "tokens_per_second": 137.22,
1000
+ "time_to_first_token": 3.553
1001
+ },
1002
+ "gpt-5-2-pro": {
1003
+ "name": "GPT-5.2 Pro",
1004
+ "input_per_1m": 10.5,
1005
+ "output_per_1m": 84.0,
1006
+ "context_window": 400000,
1007
+ "tokens_per_second": 79.954,
1008
+ "time_to_first_token": 105.68
1009
+ },
1010
+ "gpt-5-3-chat": {
1011
+ "name": "GPT-5.3 Chat",
1012
+ "input_per_1m": 1.75,
1013
+ "output_per_1m": 14.0,
1014
+ "context_window": 128000
1015
+ },
1016
+ "gpt-5-3-codex": {
1017
+ "name": "GPT-5.3 Codex",
1018
+ "input_per_1m": 1.75,
1019
+ "output_per_1m": 14.0,
1020
+ "context_window": 400000,
1021
+ "tokens_per_second": 98.981,
1022
+ "time_to_first_token": 76.442
1023
+ },
1024
+ "gpt-5-4": {
1025
+ "name": "GPT-5.4",
1026
+ "input_per_1m": 2.5,
1027
+ "output_per_1m": 15.0,
1028
+ "context_window": 1050000,
1029
+ "tokens_per_second": 119.472,
1030
+ "time_to_first_token": 0.736
1031
+ },
1032
+ "gpt-5-4-mini": {
1033
+ "name": "GPT-5.4 Mini",
1034
+ "input_per_1m": 0.75,
1035
+ "output_per_1m": 4.5,
1036
+ "tokens_per_second": 177.861,
1037
+ "time_to_first_token": 0.525
1038
+ },
1039
+ "gpt-5-4-nano": {
1040
+ "name": "GPT-5.4 Nano",
1041
+ "input_per_1m": 0.2,
1042
+ "output_per_1m": 1.25,
1043
+ "tokens_per_second": 150.824,
1044
+ "time_to_first_token": 0.47
1045
+ },
1046
+ "gpt-5-4-pro": {
1047
+ "name": "GPT-5.4 Pro",
1048
+ "input_per_1m": 30.0,
1049
+ "output_per_1m": 180.0,
1050
+ "context_window": 1050000
1051
+ },
1052
+ "gpt-5-5-pro": {
1053
+ "name": "GPT-5.5 Pro",
1054
+ "input_per_1m": 5.0,
1055
+ "output_per_1m": 30.0,
1056
+ "context_window": 1050000
1057
+ },
1058
+ "gpt-5-5-short-context-pp": {
1059
+ "name": "GPT-5.5 Short Context PP",
1060
+ "input_per_1m": 12.5,
1061
+ "output_per_1m": 75.0
1062
+ },
1063
+ "gpt-5-chat": {
1064
+ "name": "GPT-5 Chat",
1065
+ "input_per_1m": 1.25,
1066
+ "output_per_1m": 10.0,
1067
+ "context_window": 128000,
1068
+ "tokens_per_second": 189.422,
1069
+ "time_to_first_token": 0.506
1070
+ },
1071
+ "gpt-5-chat-latest-05-05-2026": {
1072
+ "name": "GPT-5 Chat Latest 05-05-2026",
1073
+ "input_per_1m": 5.0,
1074
+ "output_per_1m": 30.0
1075
+ },
1076
+ "gpt-5-chat-latest-05-28-2026": {
1077
+ "name": "GPT-5 Chat Latest 05-28-2026",
1078
+ "input_per_1m": 5.0,
1079
+ "output_per_1m": 30.0
1080
+ },
1081
+ "gpt-5-codex": {
1082
+ "name": "GPT-5 Codex",
1083
+ "input_per_1m": 1.25,
1084
+ "output_per_1m": 10.0,
1085
+ "context_window": 400000,
1086
+ "tokens_per_second": 180.976,
1087
+ "time_to_first_token": 13.177
1088
+ },
1089
+ "gpt-5-mini": {
1090
+ "name": "GPT-5 Mini",
1091
+ "input_per_1m": 0.25,
1092
+ "output_per_1m": 2.0,
1093
+ "context_window": 400000,
1094
+ "tokens_per_second": 95.838,
1095
+ "time_to_first_token": 17.313
1096
+ },
1097
+ "gpt-5-nano": {
1098
+ "name": "GPT-5 Nano",
1099
+ "input_per_1m": 0.05,
1100
+ "output_per_1m": 0.4,
1101
+ "context_window": 400000,
1102
+ "tokens_per_second": 172.045,
1103
+ "time_to_first_token": 0.657
1104
+ },
1105
+ "gpt-5-pro": {
1106
+ "name": "GPT-5 Pro",
1107
+ "input_per_1m": 15.0,
1108
+ "output_per_1m": 120.0,
1109
+ "context_window": 400000
1110
+ },
1111
+ "gpt-oss-120b": {
1112
+ "name": "GPT-OSS-120b",
1113
+ "input_per_1m": 0.039,
1114
+ "output_per_1m": 0.19,
1115
+ "context_window": 131072,
1116
+ "tokens_per_second": 367.911,
1117
+ "time_to_first_token": 0.491
1118
+ },
1119
+ "gpt-oss-20b": {
1120
+ "name": "GPT-OSS-20b",
1121
+ "input_per_1m": 0.03,
1122
+ "output_per_1m": 0.13,
1123
+ "context_window": 131072,
1124
+ "tokens_per_second": 238.775,
1125
+ "time_to_first_token": 0.453
1126
+ },
1127
+ "granite-4-0-micro": {
1128
+ "name": "Granite 4.0 Micro",
1129
+ "input_per_1m": 0.017,
1130
+ "output_per_1m": 0.112,
1131
+ "context_window": 131000
1132
+ },
1133
+ "granite-4-1-8b": {
1134
+ "name": "Granite 4.1 8B",
1135
+ "input_per_1m": 0.05,
1136
+ "output_per_1m": 0.1
1137
+ },
1138
+ "grok-3": {
1139
+ "name": "Grok 3",
1140
+ "input_per_1m": 3.0,
1141
+ "output_per_1m": 15.0,
1142
+ "context_window": 131072
1143
+ },
1144
+ "grok-3-beta": {
1145
+ "name": "Grok 3 Beta",
1146
+ "context_window": 131072
1147
+ },
1148
+ "grok-3-fast": {
1149
+ "name": "Grok 3 Fast",
1150
+ "input_per_1m": 5.0,
1151
+ "output_per_1m": 25.0,
1152
+ "context_window": 131072
1153
+ },
1154
+ "grok-3-mini": {
1155
+ "name": "Grok 3 Mini",
1156
+ "input_per_1m": 0.25,
1157
+ "output_per_1m": 1.27,
1158
+ "context_window": 131072,
1159
+ "tokens_per_second": 63.954,
1160
+ "time_to_first_token": 0.564
1161
+ },
1162
+ "grok-3-mini-beta": {
1163
+ "name": "Grok 3 Mini Beta",
1164
+ "context_window": 131072
1165
+ },
1166
+ "grok-4": {
1167
+ "name": "Grok 4",
1168
+ "input_per_1m": 3.0,
1169
+ "output_per_1m": 15.0,
1170
+ "context_window": 256000
1171
+ },
1172
+ "grok-4-1-fast": {
1173
+ "name": "Grok 4.1 Fast",
1174
+ "context_window": 2000000
1175
+ },
1176
+ "grok-4-20-beta": {
1177
+ "name": "x-ai/grok-4.20-beta",
1178
+ "input_per_1m": 1.25,
1179
+ "output_per_1m": 2.5
1180
+ },
1181
+ "grok-4-20-multi-agent-beta": {
1182
+ "name": "x-ai/grok-4.20-multi-agent-beta",
1183
+ "input_per_1m": 1.25,
1184
+ "output_per_1m": 2.5
1185
+ },
1186
+ "grok-4-3": {
1187
+ "name": "Grok 4.3",
1188
+ "input_per_1m": 1.25,
1189
+ "output_per_1m": 2.5
1190
+ },
1191
+ "grok-4-fast": {
1192
+ "name": "Grok 4 Fast",
1193
+ "input_per_1m": 0.2,
1194
+ "output_per_1m": 0.5,
1195
+ "context_window": 2000000
1196
+ },
1197
+ "grok-build-0-1": {
1198
+ "name": "Grok Build 0.1",
1199
+ "input_per_1m": 1.0,
1200
+ "output_per_1m": 2.0
1201
+ },
1202
+ "grok-code-fast-1": {
1203
+ "name": "Grok Code Fast 1",
1204
+ "input_per_1m": 0.2,
1205
+ "output_per_1m": 1.5,
1206
+ "context_window": 256000
1207
+ },
1208
+ "hermes-2-pro-llama-3-8b": {
1209
+ "name": "Hermes 2 Pro - Llama-3 8B",
1210
+ "input_per_1m": 0.14,
1211
+ "output_per_1m": 0.14,
1212
+ "context_window": 8192
1213
+ },
1214
+ "hermes-2-pro-mistral-7b": {
1215
+ "name": "Hermes 2 Pro Mistral 7B",
1216
+ "input_per_1m": 0.2,
1217
+ "output_per_1m": 0.2,
1218
+ "context_window": 32768
1219
+ },
1220
+ "hermes-3-405b-instruct": {
1221
+ "name": "Hermes 3 405B Instruct",
1222
+ "input_per_1m": 1.0,
1223
+ "output_per_1m": 1.0,
1224
+ "context_window": 131072
1225
+ },
1226
+ "hermes-3-70b-instruct": {
1227
+ "name": "Hermes 3 70B Instruct",
1228
+ "input_per_1m": 0.7,
1229
+ "output_per_1m": 0.7,
1230
+ "context_window": 65536,
1231
+ "tokens_per_second": 29.593,
1232
+ "time_to_first_token": 0.387
1233
+ },
1234
+ "hermes-4-405b": {
1235
+ "name": "Hermes 4 405B",
1236
+ "input_per_1m": 1.0,
1237
+ "output_per_1m": 3.0,
1238
+ "context_window": 131072,
1239
+ "tokens_per_second": 40.494,
1240
+ "time_to_first_token": 0.773
1241
+ },
1242
+ "hermes-4-70b": {
1243
+ "name": "Hermes 4 70B",
1244
+ "input_per_1m": 0.13,
1245
+ "output_per_1m": 0.4,
1246
+ "context_window": 131072,
1247
+ "tokens_per_second": 88.97,
1248
+ "time_to_first_token": 0.616
1249
+ },
1250
+ "holo3-35b-a3b": {
1251
+ "name": "Hcompany/Holo3-35B-A3B"
1252
+ },
1253
+ "hunyuan-a13b-instruct": {
1254
+ "name": "Hunyuan A13B Instruct",
1255
+ "input_per_1m": 0.14,
1256
+ "output_per_1m": 0.57,
1257
+ "context_window": 131072
1258
+ },
1259
+ "hunyuan-hy3-preview": {
1260
+ "name": "Hunyuan HY3 Preview",
1261
+ "input_per_1m": 0.066,
1262
+ "output_per_1m": 0.26,
1263
+ "context_window": 262144
1264
+ },
1265
+ "inflection-3-pi": {
1266
+ "name": "Inflection 3 Pi",
1267
+ "input_per_1m": 2.5,
1268
+ "output_per_1m": 10.0,
1269
+ "context_window": 8000
1270
+ },
1271
+ "inflection-3-productivity": {
1272
+ "name": "Inflection 3 Productivity",
1273
+ "input_per_1m": 2.5,
1274
+ "output_per_1m": 10.0,
1275
+ "context_window": 8000
1276
+ },
1277
+ "intellect-3": {
1278
+ "name": "INTELLECT-3",
1279
+ "input_per_1m": 0.2,
1280
+ "output_per_1m": 1.1,
1281
+ "context_window": 131072
1282
+ },
1283
+ "internvl3-38b": {
1284
+ "name": "InternVL3 38B",
1285
+ "input_per_1m": 0.9,
1286
+ "output_per_1m": 0.9,
1287
+ "context_window": 16384
1288
+ },
1289
+ "internvl3-78b": {
1290
+ "name": "InternVL3 78B",
1291
+ "input_per_1m": 0.9,
1292
+ "output_per_1m": 0.9,
1293
+ "context_window": 16384
1294
+ },
1295
+ "internvl3-8b": {
1296
+ "name": "InternVL3 8B",
1297
+ "input_per_1m": 0.2,
1298
+ "output_per_1m": 0.2,
1299
+ "context_window": 16384
1300
+ },
1301
+ "jamba-1-5-large": {
1302
+ "name": "Jamba 1.5 Large",
1303
+ "input_per_1m": 2.0,
1304
+ "output_per_1m": 8.0
1305
+ },
1306
+ "jamba-1-5-mini": {
1307
+ "name": "Jamba 1.5 Mini",
1308
+ "input_per_1m": 0.2,
1309
+ "output_per_1m": 0.4
1310
+ },
1311
+ "jamba-instruct": {
1312
+ "name": "Jamba Instruct",
1313
+ "input_per_1m": 0.5,
1314
+ "output_per_1m": 0.7,
1315
+ "context_window": 256000
1316
+ },
1317
+ "jamba-large-1-7": {
1318
+ "name": "Jamba Large 1.7",
1319
+ "input_per_1m": 2.0,
1320
+ "output_per_1m": 8.0,
1321
+ "context_window": 256000,
1322
+ "tokens_per_second": 56.87,
1323
+ "time_to_first_token": 0.99
1324
+ },
1325
+ "jamba-mini-1-7": {
1326
+ "name": "Jamba Mini 1.7",
1327
+ "context_window": 256000
1328
+ },
1329
+ "jurassic-2-mid": {
1330
+ "name": "Jurassic-2 Mid",
1331
+ "input_per_1m": 12.5,
1332
+ "output_per_1m": 12.5
1333
+ },
1334
+ "jurassic-2-ultra": {
1335
+ "name": "Jurassic-2 Ultra",
1336
+ "input_per_1m": 18.8,
1337
+ "output_per_1m": 18.8
1338
+ },
1339
+ "kat-coder-pro": {
1340
+ "name": "KAT-Coder-Pro V1",
1341
+ "context_window": 256000,
1342
+ "tokens_per_second": 118.729,
1343
+ "time_to_first_token": 0.905
1344
+ },
1345
+ "kat-dev-32b": {
1346
+ "name": "KAT Dev 32B",
1347
+ "input_per_1m": 0.9,
1348
+ "output_per_1m": 0.9,
1349
+ "context_window": 131072
1350
+ },
1351
+ "kat-dev-72b": {
1352
+ "name": "KAT Dev 72B Exp",
1353
+ "input_per_1m": 0.9,
1354
+ "output_per_1m": 0.9,
1355
+ "context_window": 131072
1356
+ },
1357
+ "kimi-dev-72b": {
1358
+ "name": "Kimi Dev 72B",
1359
+ "context_window": 131072
1360
+ },
1361
+ "kimi-k2-0711": {
1362
+ "name": "Kimi K2 0711",
1363
+ "input_per_1m": 0.55,
1364
+ "output_per_1m": 2.2,
1365
+ "context_window": 131000,
1366
+ "tokens_per_second": 25.169,
1367
+ "time_to_first_token": 1.574
1368
+ },
1369
+ "kimi-k2-0905-exacto": {
1370
+ "name": "Kimi K2 0905 (exacto)",
1371
+ "input_per_1m": 0.6,
1372
+ "output_per_1m": 2.5,
1373
+ "context_window": 262144,
1374
+ "tokens_per_second": 24.461,
1375
+ "time_to_first_token": 1.5
1376
+ },
1377
+ "kimi-k2-5": {
1378
+ "name": "Kimi K2.5",
1379
+ "input_per_1m": 0.4,
1380
+ "output_per_1m": 1.9,
1381
+ "context_window": 262144,
1382
+ "tokens_per_second": 35.533,
1383
+ "time_to_first_token": 1.293
1384
+ },
1385
+ "kimi-k2-5-turbo": {
1386
+ "name": "Kimi K2.5 Turbo"
1387
+ },
1388
+ "kimi-k2-6": {
1389
+ "name": "Kimi K2.6",
1390
+ "input_per_1m": 0.74,
1391
+ "output_per_1m": 3.5,
1392
+ "context_window": 256000,
1393
+ "tokens_per_second": 35.17,
1394
+ "time_to_first_token": 1.33
1395
+ },
1396
+ "kimi-k2-thinking": {
1397
+ "name": "Kimi K2 Thinking",
1398
+ "input_per_1m": 0.6,
1399
+ "output_per_1m": 2.5,
1400
+ "context_window": 131072
1401
+ },
1402
+ "lfm2-2-6b": {
1403
+ "name": "LiquidAI/LFM2-2.6B",
1404
+ "context_window": 32768
1405
+ },
1406
+ "lfm2-24b-a2b": {
1407
+ "name": "LiquidAI/LFM2-24B-A2B",
1408
+ "input_per_1m": 0.03,
1409
+ "output_per_1m": 0.12,
1410
+ "context_window": 32768,
1411
+ "tokens_per_second": 132.45,
1412
+ "time_to_first_token": 0.291
1413
+ },
1414
+ "lfm2-24b-a2b-preview": {
1415
+ "name": "LFM2 24B A2B Preview",
1416
+ "context_window": 128000
1417
+ },
1418
+ "lfm2-8b-a1b": {
1419
+ "name": "LiquidAI/LFM2-8B-A1B",
1420
+ "context_window": 32768
1421
+ },
1422
+ "ling-2-6-flash": {
1423
+ "name": "Ling 2.6 Flash",
1424
+ "input_per_1m": 0.01,
1425
+ "output_per_1m": 0.03,
1426
+ "context_window": 262144
1427
+ },
1428
+ "llama-2-13b": {
1429
+ "name": "Llama 2 13B",
1430
+ "input_per_1m": 0.2,
1431
+ "output_per_1m": 0.2,
1432
+ "context_window": 4096
1433
+ },
1434
+ "llama-2-13b-chat": {
1435
+ "name": "Llama 2 13B Chat",
1436
+ "input_per_1m": 0.2,
1437
+ "output_per_1m": 0.2,
1438
+ "context_window": 4096
1439
+ },
1440
+ "llama-2-70b": {
1441
+ "name": "Llama 2 70B",
1442
+ "input_per_1m": 0.9,
1443
+ "output_per_1m": 0.9,
1444
+ "context_window": 4096
1445
+ },
1446
+ "llama-2-70b-chat": {
1447
+ "name": "Llama 2 70B Chat",
1448
+ "input_per_1m": 1.95,
1449
+ "output_per_1m": 2.56,
1450
+ "context_window": 4096
1451
+ },
1452
+ "llama-2-7b": {
1453
+ "name": "Llama 2 7B",
1454
+ "input_per_1m": 0.2,
1455
+ "output_per_1m": 0.2,
1456
+ "context_window": 4096
1457
+ },
1458
+ "llama-2-7b-chat": {
1459
+ "name": "Llama 2 7B Chat",
1460
+ "context_window": 4096,
1461
+ "tokens_per_second": 122.373,
1462
+ "time_to_first_token": 1.056
1463
+ },
1464
+ "llama-3-1-405b-base": {
1465
+ "name": "Llama 3.1 405B (base)",
1466
+ "context_window": 32768
1467
+ },
1468
+ "llama-3-1-405b-instruct": {
1469
+ "name": "Llama 3.1 405B Instruct",
1470
+ "input_per_1m": 0.9,
1471
+ "output_per_1m": 0.9,
1472
+ "context_window": 131000,
1473
+ "tokens_per_second": 51.435,
1474
+ "time_to_first_token": 0.69
1475
+ },
1476
+ "llama-3-1-405b-instruct-long": {
1477
+ "name": "Llama 3.1 405B Instruct Long",
1478
+ "input_per_1m": 0.9,
1479
+ "output_per_1m": 0.9,
1480
+ "context_window": 1048576
1481
+ },
1482
+ "llama-3-1-70b": {
1483
+ "name": "Llama 3.1 70B",
1484
+ "input_per_1m": 0.72,
1485
+ "output_per_1m": 0.72,
1486
+ "context_window": 131072
1487
+ },
1488
+ "llama-3-1-70b-hanami-x1": {
1489
+ "name": "Llama 3.1 70B Hanami x1",
1490
+ "input_per_1m": 3.0,
1491
+ "output_per_1m": 3.0,
1492
+ "context_window": 16000
1493
+ },
1494
+ "llama-3-1-70b-instruct": {
1495
+ "name": "Llama 3.1 70B Instruct",
1496
+ "context_window": 131072,
1497
+ "tokens_per_second": 32.095,
1498
+ "time_to_first_token": 0.625
1499
+ },
1500
+ "llama-3-1-70b-instruct-1b": {
1501
+ "name": "Llama 3.1 70B Instruct 1B",
1502
+ "input_per_1m": 0.9,
1503
+ "output_per_1m": 0.9,
1504
+ "context_window": 131072
1505
+ },
1506
+ "llama-3-1-8b-instruct": {
1507
+ "name": "Llama 3.1 8B Instruct",
1508
+ "input_per_1m": 0.02,
1509
+ "output_per_1m": 0.03,
1510
+ "context_window": 16384,
1511
+ "tokens_per_second": 204.001,
1512
+ "time_to_first_token": 0.5
1513
+ },
1514
+ "llama-3-1-euryale-70b": {
1515
+ "name": "Llama 3.1 Euryale 70B v2.2",
1516
+ "input_per_1m": 0.85,
1517
+ "output_per_1m": 0.85,
1518
+ "context_window": 32768
1519
+ },
1520
+ "llama-3-1-nemotron-70b-instruct": {
1521
+ "name": "Llama 3.1 Nemotron 70B Instruct",
1522
+ "context_window": 131072,
1523
+ "tokens_per_second": 302.17,
1524
+ "time_to_first_token": 4.311
1525
+ },
1526
+ "llama-3-1-nemotron-ultra-253b": {
1527
+ "name": "Llama 3.1 Nemotron Ultra 253B v1",
1528
+ "context_window": 128000
1529
+ },
1530
+ "llama-3-2-11b-vision-instruct": {
1531
+ "name": "Llama 3.2 11B Vision Instruct",
1532
+ "context_window": 131072,
1533
+ "tokens_per_second": 87.104,
1534
+ "time_to_first_token": 0.566
1535
+ },
1536
+ "llama-3-2-1b": {
1537
+ "name": "Llama 3.2 1B",
1538
+ "input_per_1m": 0.1,
1539
+ "output_per_1m": 0.1,
1540
+ "context_window": 131072
1541
+ },
1542
+ "llama-3-2-1b-instruct": {
1543
+ "name": "Llama 3.2 1B Instruct",
1544
+ "context_window": 60000,
1545
+ "tokens_per_second": 86.504,
1546
+ "time_to_first_token": 0.569
1547
+ },
1548
+ "llama-3-2-3b": {
1549
+ "name": "Llama 3.2 3B",
1550
+ "input_per_1m": 0.1,
1551
+ "output_per_1m": 0.1,
1552
+ "context_window": 131072
1553
+ },
1554
+ "llama-3-2-3b-instruct": {
1555
+ "name": "Llama 3.2 3B Instruct",
1556
+ "context_window": 80000,
1557
+ "tokens_per_second": 51.835,
1558
+ "time_to_first_token": 0.587
1559
+ },
1560
+ "llama-3-2-90b-vision-instruct": {
1561
+ "name": "Llama 3.2 90B Vision Instruct",
1562
+ "context_window": 128000,
1563
+ "tokens_per_second": 48.19,
1564
+ "time_to_first_token": 0.567
1565
+ },
1566
+ "llama-3-3-70b-instruct": {
1567
+ "name": "Llama 3.3 70B Instruct",
1568
+ "context_window": 131072,
1569
+ "tokens_per_second": 96.14,
1570
+ "time_to_first_token": 0.606
1571
+ },
1572
+ "llama-3-3-70b-instruct-fp8-lora": {
1573
+ "name": "Llama 3.3 70B Instruct FP8 LoRA"
1574
+ },
1575
+ "llama-3-3-euryale-70b": {
1576
+ "name": "Llama 3.3 Euryale 70B",
1577
+ "input_per_1m": 0.65,
1578
+ "output_per_1m": 0.75,
1579
+ "context_window": 131072
1580
+ },
1581
+ "llama-3-3-nemotron-super-49b": {
1582
+ "name": "Llama 3.3 Nemotron Super 49B V1.5",
1583
+ "context_window": 131072
1584
+ },
1585
+ "llama-3-3-swallow-70b-instruct": {
1586
+ "name": "Llama 3.3 Swallow 70B Instruct v0.4",
1587
+ "context_window": 131072
1588
+ },
1589
+ "llama-3-70b-instruct": {
1590
+ "name": "Llama 3 70B Instruct",
1591
+ "input_per_1m": 0.51,
1592
+ "output_per_1m": 0.74,
1593
+ "context_window": 8192,
1594
+ "tokens_per_second": 45.581,
1595
+ "time_to_first_token": 0.709
1596
+ },
1597
+ "llama-3-70b-instruct-hf": {
1598
+ "name": "Llama 3 70B Instruct (HF)",
1599
+ "input_per_1m": 0.9,
1600
+ "output_per_1m": 0.9,
1601
+ "context_window": 8192
1602
+ },
1603
+ "llama-3-8b": {
1604
+ "name": "Llama 3 8B",
1605
+ "input_per_1m": 0.05,
1606
+ "output_per_1m": 0.08,
1607
+ "context_window": 8192
1608
+ },
1609
+ "llama-3-8b-instruct": {
1610
+ "name": "Llama 3 8B Instruct",
1611
+ "input_per_1m": 0.04,
1612
+ "output_per_1m": 0.04,
1613
+ "context_window": 8192,
1614
+ "tokens_per_second": 81.487,
1615
+ "time_to_first_token": 0.482
1616
+ },
1617
+ "llama-3-8b-instruct-hf": {
1618
+ "name": "Llama 3 8B Instruct (HF)",
1619
+ "input_per_1m": 0.2,
1620
+ "output_per_1m": 0.2,
1621
+ "context_window": 8192
1622
+ },
1623
+ "llama-3-8b-lunaris": {
1624
+ "name": "Llama 3 8B Lunaris",
1625
+ "input_per_1m": 0.04,
1626
+ "output_per_1m": 0.05,
1627
+ "context_window": 8192
1628
+ },
1629
+ "llama-3-euryale-70b": {
1630
+ "name": "Llama 3 Euryale 70B v2.1",
1631
+ "context_window": 8192
1632
+ },
1633
+ "llama-4-maverick": {
1634
+ "name": "Llama 4 Maverick",
1635
+ "context_window": 1048576,
1636
+ "tokens_per_second": 96.623,
1637
+ "time_to_first_token": 0.619
1638
+ },
1639
+ "llama-4-scout": {
1640
+ "name": "Llama 4 Scout",
1641
+ "context_window": 327680,
1642
+ "tokens_per_second": 115.377,
1643
+ "time_to_first_token": 0.598
1644
+ },
1645
+ "llama-4-scout-17b-16e-instruct-fp8-lora": {
1646
+ "name": "Llama 4 Scout 17B 16E Instruct FP8 LoRA"
1647
+ },
1648
+ "llemma-7b": {
1649
+ "name": "Llemma 7b",
1650
+ "context_window": 4096
1651
+ },
1652
+ "longcat-flash-chat": {
1653
+ "name": "LongCat Flash Chat",
1654
+ "context_window": 131072
1655
+ },
1656
+ "lumimaid-v0-2-8b": {
1657
+ "name": "Lumimaid v0.2 8B",
1658
+ "context_window": 32768
1659
+ },
1660
+ "maestro-reasoning": {
1661
+ "name": "Maestro Reasoning",
1662
+ "context_window": 131072
1663
+ },
1664
+ "magistral-medium": {
1665
+ "name": "Magistral Medium",
1666
+ "input_per_1m": 2.0,
1667
+ "output_per_1m": 5.0,
1668
+ "context_window": 40000
1669
+ },
1670
+ "magnum-v4-72b": {
1671
+ "name": "Magnum v4 72B",
1672
+ "input_per_1m": 3.0,
1673
+ "output_per_1m": 5.0,
1674
+ "context_window": 16384
1675
+ },
1676
+ "marin-8b-instruct": {
1677
+ "name": "Marin 8B Instruct",
1678
+ "context_window": 131072
1679
+ },
1680
+ "medgemma-27b": {
1681
+ "name": "MedGemma 27B",
1682
+ "context_window": 8192
1683
+ },
1684
+ "mercury": {
1685
+ "name": "Mercury",
1686
+ "context_window": 128000
1687
+ },
1688
+ "mercury-2": {
1689
+ "name": "Mercury 2",
1690
+ "input_per_1m": 0.25,
1691
+ "output_per_1m": 0.75,
1692
+ "context_window": 128000,
1693
+ "tokens_per_second": 1133.969,
1694
+ "time_to_first_token": 3.159
1695
+ },
1696
+ "mercury-coder": {
1697
+ "name": "Mercury Coder",
1698
+ "context_window": 128000
1699
+ },
1700
+ "midnight-rose-70b": {
1701
+ "name": "sophosympatheia/midnight-rose-70b",
1702
+ "input_per_1m": 0.8,
1703
+ "output_per_1m": 0.8,
1704
+ "context_window": 4096
1705
+ },
1706
+ "mimo": {
1707
+ "name": "MiMo v2.5",
1708
+ "input_per_1m": 0.14,
1709
+ "output_per_1m": 0.28,
1710
+ "context_window": 1048576
1711
+ },
1712
+ "mimo-v2-5-pro": {
1713
+ "name": "MiMo v2.5 Pro",
1714
+ "input_per_1m": 0.435,
1715
+ "output_per_1m": 0.87,
1716
+ "context_window": 1048576,
1717
+ "tokens_per_second": 52.218,
1718
+ "time_to_first_token": 1.779
1719
+ },
1720
+ "mimo-v2-flash": {
1721
+ "name": "MiMo-V2-Flash",
1722
+ "input_per_1m": 0.1,
1723
+ "output_per_1m": 0.3,
1724
+ "context_window": 262144,
1725
+ "tokens_per_second": 161.361,
1726
+ "time_to_first_token": 1.201
1727
+ },
1728
+ "mimo-v2-omni": {
1729
+ "name": "MiMo v2 Omni",
1730
+ "context_window": 262144,
1731
+ "tokens_per_second": 77.664,
1732
+ "time_to_first_token": 2.498
1733
+ },
1734
+ "mimo-v2-pro": {
1735
+ "name": "MiMo v2 Pro",
1736
+ "tokens_per_second": 40.808,
1737
+ "time_to_first_token": 2.22
1738
+ },
1739
+ "minimax-01": {
1740
+ "name": "MiniMax-01",
1741
+ "input_per_1m": 0.2,
1742
+ "output_per_1m": 1.1,
1743
+ "context_window": 1000192
1744
+ },
1745
+ "minimax-m1": {
1746
+ "name": "MiniMax M1",
1747
+ "context_window": 1000000
1748
+ },
1749
+ "minimax-m2": {
1750
+ "name": "MiniMax M2",
1751
+ "context_window": 196608,
1752
+ "tokens_per_second": 132.771,
1753
+ "time_to_first_token": 1.324
1754
+ },
1755
+ "minimax-m2-1": {
1756
+ "name": "MiniMax M2.1",
1757
+ "input_per_1m": 0.29,
1758
+ "output_per_1m": 0.95,
1759
+ "context_window": 196608,
1760
+ "tokens_per_second": 207.852,
1761
+ "time_to_first_token": 7.641
1762
+ },
1763
+ "minimax-m2-5": {
1764
+ "name": "MiniMax M2.5",
1765
+ "input_per_1m": 0.15,
1766
+ "output_per_1m": 1.2,
1767
+ "context_window": 196608,
1768
+ "tokens_per_second": 221.706,
1769
+ "time_to_first_token": 6.532
1770
+ },
1771
+ "minimax-m2-7": {
1772
+ "name": "MiniMax M2.7",
1773
+ "input_per_1m": 0.25,
1774
+ "output_per_1m": 1.0,
1775
+ "context_window": 204800,
1776
+ "tokens_per_second": 39.067,
1777
+ "time_to_first_token": 1.742
1778
+ },
1779
+ "minimax-m2-her": {
1780
+ "name": "MiniMax M2 Her",
1781
+ "input_per_1m": 0.3,
1782
+ "output_per_1m": 1.2,
1783
+ "context_window": 65536
1784
+ },
1785
+ "minimax-m3": {
1786
+ "name": "MiniMax M3",
1787
+ "input_per_1m": 0.3,
1788
+ "output_per_1m": 1.2,
1789
+ "context_window": 1048576,
1790
+ "tokens_per_second": 56.711,
1791
+ "time_to_first_token": 2.045
1792
+ },
1793
+ "ministral-3-14b-2512": {
1794
+ "name": "Ministral 3 14B 2512",
1795
+ "input_per_1m": 0.2,
1796
+ "output_per_1m": 0.2,
1797
+ "context_window": 262144,
1798
+ "tokens_per_second": 107.351,
1799
+ "time_to_first_token": 0.433
1800
+ },
1801
+ "ministral-3-3b-2512": {
1802
+ "name": "Ministral 3 3B 2512",
1803
+ "input_per_1m": 0.1,
1804
+ "output_per_1m": 0.1,
1805
+ "context_window": 131072
1806
+ },
1807
+ "ministral-3-8b-2512": {
1808
+ "name": "Ministral 3 8B 2512",
1809
+ "input_per_1m": 0.15,
1810
+ "output_per_1m": 0.15,
1811
+ "context_window": 262144,
1812
+ "tokens_per_second": 108.803,
1813
+ "time_to_first_token": 0.434
1814
+ },
1815
+ "ministral-3b": {
1816
+ "name": "Ministral 3B",
1817
+ "input_per_1m": 0.04,
1818
+ "output_per_1m": 0.04,
1819
+ "context_window": 128000,
1820
+ "tokens_per_second": 181.298,
1821
+ "time_to_first_token": 0.381
1822
+ },
1823
+ "ministral-8b": {
1824
+ "name": "Ministral 8B",
1825
+ "input_per_1m": 0.1,
1826
+ "output_per_1m": 0.1,
1827
+ "context_window": 128000
1828
+ },
1829
+ "mistral-7b": {
1830
+ "name": "Mistral 7B",
1831
+ "input_per_1m": 0.2,
1832
+ "output_per_1m": 0.2,
1833
+ "context_window": 32000
1834
+ },
1835
+ "mistral-7b-instruct": {
1836
+ "name": "Mistral 7B Instruct",
1837
+ "input_per_1m": 0.059,
1838
+ "output_per_1m": 0.059,
1839
+ "context_window": 4096,
1840
+ "tokens_per_second": 104.378,
1841
+ "time_to_first_token": 0.443
1842
+ },
1843
+ "mistral-7b-openorca": {
1844
+ "name": "Mistral 7B OpenOrca",
1845
+ "input_per_1m": 0.2,
1846
+ "output_per_1m": 0.2,
1847
+ "context_window": 32768
1848
+ },
1849
+ "mistral-large": {
1850
+ "name": "Mistral Large",
1851
+ "input_per_1m": 0.5,
1852
+ "output_per_1m": 1.5,
1853
+ "context_window": 128000
1854
+ },
1855
+ "mistral-large-2407": {
1856
+ "name": "Mistral Large 2407",
1857
+ "input_per_1m": 2.0,
1858
+ "output_per_1m": 6.0,
1859
+ "context_window": 131072
1860
+ },
1861
+ "mistral-large-2411": {
1862
+ "name": "Mistral Large 2411",
1863
+ "context_window": 131072,
1864
+ "tokens_per_second": 65.483,
1865
+ "time_to_first_token": 0.773
1866
+ },
1867
+ "mistral-large-3-2512": {
1868
+ "name": "Mistral Large 3 2512",
1869
+ "input_per_1m": 0.5,
1870
+ "output_per_1m": 1.5,
1871
+ "context_window": 262144
1872
+ },
1873
+ "mistral-medium-3": {
1874
+ "name": "Mistral Medium 3",
1875
+ "input_per_1m": 0.4,
1876
+ "output_per_1m": 2.0,
1877
+ "context_window": 131072,
1878
+ "tokens_per_second": 46.163,
1879
+ "time_to_first_token": 0.572
1880
+ },
1881
+ "mistral-medium-3-1": {
1882
+ "name": "Mistral Medium 3.1",
1883
+ "input_per_1m": 0.4,
1884
+ "output_per_1m": 2.0,
1885
+ "context_window": 131072,
1886
+ "tokens_per_second": 74.853,
1887
+ "time_to_first_token": 0.541
1888
+ },
1889
+ "mistral-nemo": {
1890
+ "name": "Mistral Nemo",
1891
+ "context_window": 131072
1892
+ },
1893
+ "mistral-small": {
1894
+ "name": "Mistral Small",
1895
+ "input_per_1m": 0.1,
1896
+ "output_per_1m": 0.3,
1897
+ "context_window": 32000,
1898
+ "tokens_per_second": 159.128,
1899
+ "time_to_first_token": 0.533
1900
+ },
1901
+ "mistral-small-24b-instruct-2501": {
1902
+ "name": "Mistral Small 24B Instruct 2501",
1903
+ "input_per_1m": 0.05,
1904
+ "output_per_1m": 0.08,
1905
+ "context_window": 32768,
1906
+ "tokens_per_second": 165.134,
1907
+ "time_to_first_token": 0.541
1908
+ },
1909
+ "mistral-small-2603": {
1910
+ "name": "Mistral Small 2603",
1911
+ "input_per_1m": 0.15,
1912
+ "output_per_1m": 0.6
1913
+ },
1914
+ "mistral-small-3-1-24b": {
1915
+ "name": "Mistral Small 3.1 24B",
1916
+ "input_per_1m": 0.1,
1917
+ "output_per_1m": 0.3,
1918
+ "context_window": 128000,
1919
+ "tokens_per_second": 165.009,
1920
+ "time_to_first_token": 0.573
1921
+ },
1922
+ "mistral-small-3-2-24b": {
1923
+ "name": "Mistral Small 3.2 24B",
1924
+ "context_window": 131072,
1925
+ "tokens_per_second": 146.837,
1926
+ "time_to_first_token": 0.427
1927
+ },
1928
+ "mistral-small-creative": {
1929
+ "name": "Mistral Small Creative",
1930
+ "context_window": 32768
1931
+ },
1932
+ "mistral-tiny": {
1933
+ "name": "Mistral Tiny",
1934
+ "input_per_1m": 0.14,
1935
+ "output_per_1m": 0.42,
1936
+ "context_window": 32000
1937
+ },
1938
+ "mixtral-8x22b": {
1939
+ "name": "Mixtral 8x22B",
1940
+ "input_per_1m": 1.2,
1941
+ "output_per_1m": 1.2,
1942
+ "context_window": 65336
1943
+ },
1944
+ "mixtral-8x22b-instruct": {
1945
+ "name": "Mixtral 8x22B Instruct",
1946
+ "context_window": 65536
1947
+ },
1948
+ "mixtral-8x7b": {
1949
+ "name": "Mixtral 8x7B",
1950
+ "input_per_1m": 0.24,
1951
+ "output_per_1m": 0.24,
1952
+ "context_window": 32000
1953
+ },
1954
+ "mixtral-8x7b-instruct": {
1955
+ "name": "Mixtral 8x7B Instruct",
1956
+ "input_per_1m": 0.14,
1957
+ "output_per_1m": 0.42,
1958
+ "context_window": 32768
1959
+ },
1960
+ "mixtral-8x7b-instruct-hf": {
1961
+ "name": "Mixtral 8x7B Instruct (HF)",
1962
+ "input_per_1m": 0.5,
1963
+ "output_per_1m": 0.5,
1964
+ "context_window": 32768
1965
+ },
1966
+ "mixtral-8x7b-instruct-v0-1-fp8-lora": {
1967
+ "name": "Mixtral 8x7B Instruct v0.1 FP8 LoRA"
1968
+ },
1969
+ "molmo-2-4b": {
1970
+ "name": "Molmo 2 4B",
1971
+ "input_per_1m": 0.2,
1972
+ "output_per_1m": 0.2,
1973
+ "context_window": 36864
1974
+ },
1975
+ "molmo-2-8b": {
1976
+ "name": "Molmo 2 8B",
1977
+ "input_per_1m": 0.2,
1978
+ "output_per_1m": 0.2,
1979
+ "context_window": 36864
1980
+ },
1981
+ "molmo-7b-d-0924": {
1982
+ "name": "Molmo 7B D 0924"
1983
+ },
1984
+ "morph-v3-fast": {
1985
+ "name": "Morph V3 Fast",
1986
+ "input_per_1m": 0.8,
1987
+ "output_per_1m": 1.2,
1988
+ "context_window": 81920
1989
+ },
1990
+ "morph-v3-large": {
1991
+ "name": "Morph V3 Large",
1992
+ "input_per_1m": 0.9,
1993
+ "output_per_1m": 1.9,
1994
+ "context_window": 262144
1995
+ },
1996
+ "mythomax-13b": {
1997
+ "name": "MythoMax 13B",
1998
+ "input_per_1m": 0.06,
1999
+ "output_per_1m": 0.06,
2000
+ "context_window": 4096
2001
+ },
2002
+ "nano-banana-pro-gemini-3-pro-image-preview": {
2003
+ "name": "Nano Banana Pro (Gemini 3 Pro Image Preview)",
2004
+ "input_per_1m": 2.0,
2005
+ "output_per_1m": 120.0,
2006
+ "context_window": 65536
2007
+ },
2008
+ "nemotron-3-nano-30b-a3b": {
2009
+ "name": "Nemotron 3 Nano 30B A3B",
2010
+ "context_window": 262144,
2011
+ "tokens_per_second": 80.589,
2012
+ "time_to_first_token": 0.331
2013
+ },
2014
+ "nemotron-3-super-120b-a12b": {
2015
+ "name": "Nemotron 3 Super 120B A12B"
2016
+ },
2017
+ "nemotron-3-ultra-550b-a55b": {
2018
+ "name": "Nemotron 3 Ultra 550B A55B",
2019
+ "input_per_1m": 0.5,
2020
+ "output_per_1m": 2.5,
2021
+ "context_window": 1000000,
2022
+ "tokens_per_second": 168.572,
2023
+ "time_to_first_token": 0.803
2024
+ },
2025
+ "nemotron-nano-12b": {
2026
+ "name": "Nemotron Nano 12B V2",
2027
+ "input_per_1m": 0.2,
2028
+ "output_per_1m": 0.2,
2029
+ "context_window": 128000
2030
+ },
2031
+ "nemotron-nano-12b-2-vl": {
2032
+ "name": "Nemotron Nano 12B 2 VL",
2033
+ "input_per_1m": 0.2,
2034
+ "output_per_1m": 0.6,
2035
+ "context_window": 131072,
2036
+ "tokens_per_second": 219.12,
2037
+ "time_to_first_token": 0.547
2038
+ },
2039
+ "nemotron-nano-9b": {
2040
+ "name": "Nemotron Nano 9B V2",
2041
+ "input_per_1m": 0.06,
2042
+ "output_per_1m": 0.25,
2043
+ "context_window": 131072,
2044
+ "tokens_per_second": 135.617,
2045
+ "time_to_first_token": 1.427
2046
+ },
2047
+ "noromaid-20b": {
2048
+ "name": "Noromaid 20B",
2049
+ "context_window": 4096
2050
+ },
2051
+ "nous-capybara-7b": {
2052
+ "name": "Nous Capybara 7B v1.9",
2053
+ "input_per_1m": 0.2,
2054
+ "output_per_1m": 0.2,
2055
+ "context_window": 32768
2056
+ },
2057
+ "nous-hermes-2-mixtral-8x7b-dpo": {
2058
+ "name": "Nous Hermes 2 Mixtral 8x7B DPO",
2059
+ "input_per_1m": 0.5,
2060
+ "output_per_1m": 0.5,
2061
+ "context_window": 32768
2062
+ },
2063
+ "nous-hermes-2-yi-34b": {
2064
+ "name": "Nous Hermes 2 Yi 34B",
2065
+ "input_per_1m": 0.8,
2066
+ "output_per_1m": 0.8,
2067
+ "context_window": 4096
2068
+ },
2069
+ "nous-hermes-llama-2-13b": {
2070
+ "name": "Nous Hermes Llama 2 13B",
2071
+ "input_per_1m": 0.17,
2072
+ "output_per_1m": 0.17,
2073
+ "context_window": 4096
2074
+ },
2075
+ "nous-hermes-llama-2-70b": {
2076
+ "name": "Nous Hermes Llama 2 70B",
2077
+ "input_per_1m": 0.9,
2078
+ "output_per_1m": 0.9,
2079
+ "context_window": 4096
2080
+ },
2081
+ "nous-hermes-llama-2-7b": {
2082
+ "name": "Nous Hermes Llama 2 7B",
2083
+ "input_per_1m": 0.2,
2084
+ "output_per_1m": 0.2,
2085
+ "context_window": 4096
2086
+ },
2087
+ "nova-2-lite": {
2088
+ "name": "Nova 2 Lite",
2089
+ "input_per_1m": 0.3,
2090
+ "output_per_1m": 2.5,
2091
+ "context_window": 1000000,
2092
+ "tokens_per_second": 229.635,
2093
+ "time_to_first_token": 0.812
2094
+ },
2095
+ "nova-lite-1-0": {
2096
+ "name": "Nova Lite 1.0",
2097
+ "input_per_1m": 0.06,
2098
+ "output_per_1m": 0.24,
2099
+ "context_window": 300000,
2100
+ "tokens_per_second": 189.168,
2101
+ "time_to_first_token": 0.664
2102
+ },
2103
+ "nova-micro-1-0": {
2104
+ "name": "Nova Micro 1.0",
2105
+ "input_per_1m": 0.035,
2106
+ "output_per_1m": 0.14,
2107
+ "context_window": 128000,
2108
+ "tokens_per_second": 294.052,
2109
+ "time_to_first_token": 0.603
2110
+ },
2111
+ "nova-premier-1-0": {
2112
+ "name": "Nova Premier 1.0",
2113
+ "input_per_1m": 2.5,
2114
+ "output_per_1m": 12.5,
2115
+ "context_window": 1000000,
2116
+ "tokens_per_second": 75.135,
2117
+ "time_to_first_token": 1.094
2118
+ },
2119
+ "nova-pro-1-0": {
2120
+ "name": "Nova Pro 1.0",
2121
+ "input_per_1m": 0.8,
2122
+ "output_per_1m": 3.2,
2123
+ "context_window": 300000
2124
+ },
2125
+ "o1": {
2126
+ "name": "o1",
2127
+ "input_per_1m": 15.0,
2128
+ "output_per_1m": 60.0,
2129
+ "context_window": 200000,
2130
+ "tokens_per_second": 112.837,
2131
+ "time_to_first_token": 19.491
2132
+ },
2133
+ "o1-mini": {
2134
+ "name": "o1 Mini",
2135
+ "input_per_1m": 0.55,
2136
+ "output_per_1m": 2.2,
2137
+ "context_window": 128000
2138
+ },
2139
+ "o1-pro": {
2140
+ "name": "o1-pro",
2141
+ "input_per_1m": 150.0,
2142
+ "output_per_1m": 600.0,
2143
+ "context_window": 200000
2144
+ },
2145
+ "o3": {
2146
+ "name": "o3",
2147
+ "input_per_1m": 2.0,
2148
+ "output_per_1m": 8.0,
2149
+ "context_window": 200000,
2150
+ "tokens_per_second": 144.392,
2151
+ "time_to_first_token": 6.341
2152
+ },
2153
+ "o3-deep-research": {
2154
+ "name": "o3 Deep Research",
2155
+ "input_per_1m": 10.0,
2156
+ "output_per_1m": 40.0,
2157
+ "context_window": 200000
2158
+ },
2159
+ "o3-mini": {
2160
+ "name": "o3 Mini",
2161
+ "input_per_1m": 0.55,
2162
+ "output_per_1m": 2.2,
2163
+ "context_window": 200000,
2164
+ "tokens_per_second": 216.542,
2165
+ "time_to_first_token": 6.093
2166
+ },
2167
+ "o3-mini-high": {
2168
+ "name": "o3 Mini High",
2169
+ "input_per_1m": 1.1,
2170
+ "output_per_1m": 4.4,
2171
+ "context_window": 200000,
2172
+ "tokens_per_second": 211.934,
2173
+ "time_to_first_token": 16.263
2174
+ },
2175
+ "o3-pro": {
2176
+ "name": "o3 Pro",
2177
+ "input_per_1m": 20.0,
2178
+ "output_per_1m": 80.0,
2179
+ "context_window": 200000,
2180
+ "tokens_per_second": 31.828,
2181
+ "time_to_first_token": 65.658
2182
+ },
2183
+ "o4-mini": {
2184
+ "name": "o4 Mini",
2185
+ "input_per_1m": 1.1,
2186
+ "output_per_1m": 4.4,
2187
+ "context_window": 200000,
2188
+ "tokens_per_second": 194.832,
2189
+ "time_to_first_token": 23.586
2190
+ },
2191
+ "o4-mini-deep-research": {
2192
+ "name": "o4 Mini Deep Research",
2193
+ "input_per_1m": 2.0,
2194
+ "output_per_1m": 8.0,
2195
+ "context_window": 200000
2196
+ },
2197
+ "o4-mini-high": {
2198
+ "name": "o4 Mini High",
2199
+ "input_per_1m": 1.1,
2200
+ "output_per_1m": 4.4,
2201
+ "context_window": 200000
2202
+ },
2203
+ "olmo-2-32b-instruct": {
2204
+ "name": "Olmo 2 32B Instruct",
2205
+ "context_window": 128000
2206
+ },
2207
+ "olmo-3-1-32b-instruct": {
2208
+ "name": "Olmo 3.1 32B Instruct",
2209
+ "context_window": 65536
2210
+ },
2211
+ "olmo-3-1-32b-think": {
2212
+ "name": "Olmo 3.1 32B Think",
2213
+ "context_window": 65536
2214
+ },
2215
+ "olmo-3-32b-think": {
2216
+ "name": "Olmo 3 32B Think",
2217
+ "context_window": 65536
2218
+ },
2219
+ "olmo-3-7b-instruct": {
2220
+ "name": "Olmo 3 7B Instruct",
2221
+ "context_window": 65536
2222
+ },
2223
+ "olmo-3-7b-think": {
2224
+ "name": "Olmo 3 7B Think",
2225
+ "context_window": 65536
2226
+ },
2227
+ "olmo-7b-instruct": {
2228
+ "name": "OLMo 7B Instruct",
2229
+ "input_per_1m": 0.2,
2230
+ "output_per_1m": 0.2,
2231
+ "context_window": 2048
2232
+ },
2233
+ "openchat-3-5-0106": {
2234
+ "name": "OpenChat 3.5 0106",
2235
+ "input_per_1m": 0.2,
2236
+ "output_per_1m": 0.2,
2237
+ "context_window": 8192
2238
+ },
2239
+ "openchat-7b": {
2240
+ "name": "OpenChat 7B",
2241
+ "input_per_1m": 0.06,
2242
+ "output_per_1m": 0.06,
2243
+ "context_window": 8192
2244
+ },
2245
+ "openhermes-2-5-mistral-7b": {
2246
+ "name": "OpenHermes 2.5 Mistral 7B",
2247
+ "input_per_1m": 0.17,
2248
+ "output_per_1m": 0.17,
2249
+ "context_window": 32768
2250
+ },
2251
+ "openhermes-2-mistral-7b": {
2252
+ "name": "OpenHermes 2 Mistral 7B",
2253
+ "input_per_1m": 0.2,
2254
+ "output_per_1m": 0.2,
2255
+ "context_window": 32768
2256
+ },
2257
+ "palmyra-x5": {
2258
+ "name": "Palmyra X5",
2259
+ "input_per_1m": 0.6,
2260
+ "output_per_1m": 6.0,
2261
+ "context_window": 1040000
2262
+ },
2263
+ "phi-3-5-mini-128k-instruct": {
2264
+ "name": "Phi-3.5 Mini 128K Instruct",
2265
+ "context_window": 128000
2266
+ },
2267
+ "phi-3-medium-128k-instruct": {
2268
+ "name": "Phi-3 Medium 128K Instruct",
2269
+ "context_window": 128000
2270
+ },
2271
+ "phi-3-mini-128k-instruct": {
2272
+ "name": "Phi-3 Mini 128K Instruct",
2273
+ "context_window": 128000
2274
+ },
2275
+ "phi-4": {
2276
+ "name": "Phi 4",
2277
+ "input_per_1m": 0.065,
2278
+ "output_per_1m": 0.14,
2279
+ "context_window": 16384,
2280
+ "tokens_per_second": 35.543,
2281
+ "time_to_first_token": 0.498
2282
+ },
2283
+ "phi-4-multimodal-instruct": {
2284
+ "name": "Phi 4 Multimodal Instruct",
2285
+ "context_window": 131072,
2286
+ "tokens_per_second": 12.401,
2287
+ "time_to_first_token": 0.39
2288
+ },
2289
+ "phi-4-reasoning-plus": {
2290
+ "name": "Phi 4 Reasoning Plus",
2291
+ "context_window": 32000
2292
+ },
2293
+ "phind-codellama-34b": {
2294
+ "name": "Phind CodeLlama 34B v1",
2295
+ "input_per_1m": 0.9,
2296
+ "output_per_1m": 0.9,
2297
+ "context_window": 16384
2298
+ },
2299
+ "phind-codellama-34b-python": {
2300
+ "name": "Phind CodeLlama 34B Python v1",
2301
+ "input_per_1m": 0.9,
2302
+ "output_per_1m": 0.9,
2303
+ "context_window": 16384
2304
+ },
2305
+ "pixtral-12b": {
2306
+ "name": "Pixtral 12B",
2307
+ "input_per_1m": 0.15,
2308
+ "output_per_1m": 0.15,
2309
+ "context_window": 128000
2310
+ },
2311
+ "pixtral-large-2411": {
2312
+ "name": "Pixtral Large 2411",
2313
+ "context_window": 131072,
2314
+ "tokens_per_second": 61.965,
2315
+ "time_to_first_token": 0.645
2316
+ },
2317
+ "pythia-12b": {
2318
+ "name": "Pythia 12B",
2319
+ "input_per_1m": 0.2,
2320
+ "output_per_1m": 0.2,
2321
+ "context_window": 2048
2322
+ },
2323
+ "qwen-1-5-72b-chat": {
2324
+ "name": "Qwen 1.5 72B Chat",
2325
+ "input_per_1m": 0.9,
2326
+ "output_per_1m": 0.9,
2327
+ "context_window": 32768
2328
+ },
2329
+ "qwen-max": {
2330
+ "name": "Qwen-Max",
2331
+ "context_window": 32768
2332
+ },
2333
+ "qwen-plus": {
2334
+ "name": "Qwen-Plus",
2335
+ "input_per_1m": 0.26,
2336
+ "output_per_1m": 0.78,
2337
+ "context_window": 1000000
2338
+ },
2339
+ "qwen-plus-0728-thinking": {
2340
+ "name": "Qwen Plus 0728 (thinking)",
2341
+ "input_per_1m": 0.26,
2342
+ "output_per_1m": 0.78,
2343
+ "context_window": 1000000
2344
+ },
2345
+ "qwen-turbo": {
2346
+ "name": "Qwen-Turbo",
2347
+ "context_window": 131072,
2348
+ "tokens_per_second": 103.505,
2349
+ "time_to_first_token": 1.197
2350
+ },
2351
+ "qwen-vl-max": {
2352
+ "name": "Qwen VL Max",
2353
+ "context_window": 131072
2354
+ },
2355
+ "qwen-vl-plus": {
2356
+ "name": "Qwen VL Plus",
2357
+ "context_window": 131072
2358
+ },
2359
+ "qwen1-5-0-5b": {
2360
+ "name": "Qwen1.5 0.5B",
2361
+ "input_per_1m": 0.1,
2362
+ "output_per_1m": 0.1,
2363
+ "context_window": 32768
2364
+ },
2365
+ "qwen1-5-0-5b-chat": {
2366
+ "name": "Qwen1.5 0.5B Chat",
2367
+ "input_per_1m": 0.1,
2368
+ "output_per_1m": 0.1,
2369
+ "context_window": 32768
2370
+ },
2371
+ "qwen1-5-14b-chat": {
2372
+ "name": "Qwen1.5 14B Chat",
2373
+ "input_per_1m": 0.3,
2374
+ "output_per_1m": 0.3,
2375
+ "context_window": 32768
2376
+ },
2377
+ "qwen2-1-5b": {
2378
+ "name": "Qwen2 1.5B"
2379
+ },
2380
+ "qwen2-1-5b-instruct": {
2381
+ "name": "Qwen2 1.5B Instruct",
2382
+ "input_per_1m": 0.02,
2383
+ "output_per_1m": 0.02
2384
+ },
2385
+ "qwen2-5-0-5b-instruct": {
2386
+ "name": "Qwen2.5 0.5B Instruct",
2387
+ "input_per_1m": 0.2,
2388
+ "output_per_1m": 0.2,
2389
+ "context_window": 32768
2390
+ },
2391
+ "qwen2-5-1-5b-instruct": {
2392
+ "name": "Qwen2.5 1.5B Instruct",
2393
+ "context_window": 32768
2394
+ },
2395
+ "qwen2-5-14b": {
2396
+ "name": "Qwen2.5 14B",
2397
+ "context_window": 131072
2398
+ },
2399
+ "qwen2-5-14b-instruct": {
2400
+ "name": "Qwen2.5 14B Instruct",
2401
+ "input_per_1m": 0.2,
2402
+ "output_per_1m": 0.2,
2403
+ "context_window": 33000
2404
+ },
2405
+ "qwen2-5-32b": {
2406
+ "name": "Qwen2.5 32B",
2407
+ "context_window": 131072
2408
+ },
2409
+ "qwen2-5-32b-instruct": {
2410
+ "name": "Qwen2.5 32B Instruct",
2411
+ "context_window": 128000
2412
+ },
2413
+ "qwen2-5-72b": {
2414
+ "name": "Qwen2.5 72B",
2415
+ "input_per_1m": 0.9,
2416
+ "output_per_1m": 0.9,
2417
+ "context_window": 131072
2418
+ },
2419
+ "qwen2-5-72b-instruct": {
2420
+ "name": "Qwen2.5 72B Instruct",
2421
+ "input_per_1m": 0.36,
2422
+ "output_per_1m": 0.4,
2423
+ "context_window": 32768
2424
+ },
2425
+ "qwen2-5-7b": {
2426
+ "name": "Qwen2.5 7B",
2427
+ "input_per_1m": 0.2,
2428
+ "output_per_1m": 0.2,
2429
+ "context_window": 131072
2430
+ },
2431
+ "qwen2-5-7b-instruct": {
2432
+ "name": "Qwen2.5 7B Instruct",
2433
+ "input_per_1m": 0.04,
2434
+ "output_per_1m": 0.1,
2435
+ "context_window": 32768
2436
+ },
2437
+ "qwen2-5-coder-0-5b": {
2438
+ "name": "Qwen2.5 Coder 0.5B",
2439
+ "input_per_1m": 0.2,
2440
+ "output_per_1m": 0.2,
2441
+ "context_window": 32768
2442
+ },
2443
+ "qwen2-5-coder-0-5b-instruct": {
2444
+ "name": "Qwen2.5 Coder 0.5B Instruct",
2445
+ "input_per_1m": 0.2,
2446
+ "output_per_1m": 0.2,
2447
+ "context_window": 32768
2448
+ },
2449
+ "qwen2-5-coder-1-5b": {
2450
+ "name": "Qwen2.5 Coder 1.5B",
2451
+ "input_per_1m": 0.2,
2452
+ "output_per_1m": 0.2,
2453
+ "context_window": 32768
2454
+ },
2455
+ "qwen2-5-coder-1-5b-instruct": {
2456
+ "name": "Qwen2.5 Coder 1.5B Instruct",
2457
+ "input_per_1m": 0.2,
2458
+ "output_per_1m": 0.2,
2459
+ "context_window": 32768
2460
+ },
2461
+ "qwen2-5-coder-14b": {
2462
+ "name": "Qwen2.5 Coder 14B",
2463
+ "input_per_1m": 0.2,
2464
+ "output_per_1m": 0.2,
2465
+ "context_window": 32768
2466
+ },
2467
+ "qwen2-5-coder-14b-instruct": {
2468
+ "name": "Qwen2.5 Coder 14B Instruct",
2469
+ "input_per_1m": 0.2,
2470
+ "output_per_1m": 0.2,
2471
+ "context_window": 32768
2472
+ },
2473
+ "qwen2-5-coder-32b": {
2474
+ "name": "Qwen2.5 Coder 32B",
2475
+ "input_per_1m": 0.9,
2476
+ "output_per_1m": 0.9,
2477
+ "context_window": 32768
2478
+ },
2479
+ "qwen2-5-coder-32b-instruct": {
2480
+ "name": "Qwen2.5 Coder 32B Instruct",
2481
+ "input_per_1m": 0.66,
2482
+ "output_per_1m": 1.0,
2483
+ "context_window": 32768
2484
+ },
2485
+ "qwen2-5-coder-32b-instruct-128k": {
2486
+ "name": "Qwen2.5 Coder 32B Instruct 128K",
2487
+ "input_per_1m": 0.9,
2488
+ "output_per_1m": 0.9,
2489
+ "context_window": 131072
2490
+ },
2491
+ "qwen2-5-coder-32b-instruct-32k-rope": {
2492
+ "name": "Qwen2.5 Coder 32B Instruct 32K RoPE",
2493
+ "input_per_1m": 0.9,
2494
+ "output_per_1m": 0.9,
2495
+ "context_window": 32768
2496
+ },
2497
+ "qwen2-5-coder-32b-instruct-64k": {
2498
+ "name": "Qwen2.5 Coder 32B Instruct 64K",
2499
+ "input_per_1m": 0.9,
2500
+ "output_per_1m": 0.9,
2501
+ "context_window": 65536
2502
+ },
2503
+ "qwen2-5-coder-3b": {
2504
+ "name": "Qwen2.5 Coder 3B",
2505
+ "input_per_1m": 0.1,
2506
+ "output_per_1m": 0.1,
2507
+ "context_window": 32768
2508
+ },
2509
+ "qwen2-5-coder-3b-instruct": {
2510
+ "name": "Qwen2.5 Coder 3B Instruct",
2511
+ "context_window": 32768
2512
+ },
2513
+ "qwen2-5-coder-7b": {
2514
+ "name": "Qwen2.5 Coder 7B",
2515
+ "input_per_1m": 0.2,
2516
+ "output_per_1m": 0.2,
2517
+ "context_window": 32768
2518
+ },
2519
+ "qwen2-5-coder-7b-instruct": {
2520
+ "name": "Qwen2.5 Coder 7B Instruct",
2521
+ "input_per_1m": 0.2,
2522
+ "output_per_1m": 0.2,
2523
+ "context_window": 32768
2524
+ },
2525
+ "qwen2-5-math-72b-instruct": {
2526
+ "name": "Qwen2.5 Math 72B Instruct",
2527
+ "input_per_1m": 0.9,
2528
+ "output_per_1m": 0.9,
2529
+ "context_window": 4096
2530
+ },
2531
+ "qwen2-5-vl-32b-instruct": {
2532
+ "name": "Qwen2.5 VL 32B Instruct",
2533
+ "input_per_1m": 0.9,
2534
+ "output_per_1m": 0.9,
2535
+ "context_window": 128000
2536
+ },
2537
+ "qwen2-5-vl-3b-instruct": {
2538
+ "name": "Qwen2.5 VL 3B Instruct",
2539
+ "input_per_1m": 0.1,
2540
+ "output_per_1m": 0.1,
2541
+ "context_window": 128000
2542
+ },
2543
+ "qwen2-5-vl-72b-instruct": {
2544
+ "name": "Qwen2.5 VL 72B Instruct",
2545
+ "input_per_1m": 0.8,
2546
+ "output_per_1m": 1.0,
2547
+ "context_window": 32768
2548
+ },
2549
+ "qwen2-5-vl-7b-instruct": {
2550
+ "name": "Qwen2.5-VL 7B Instruct",
2551
+ "input_per_1m": 0.2,
2552
+ "output_per_1m": 0.2,
2553
+ "context_window": 32768
2554
+ },
2555
+ "qwen2-72b-instruct": {
2556
+ "name": "Qwen2 72B Instruct",
2557
+ "context_window": 32768
2558
+ },
2559
+ "qwen2-7b-instruct": {
2560
+ "name": "Qwen2 7B Instruct",
2561
+ "context_window": 32768
2562
+ },
2563
+ "qwen2-vl-2b-instruct": {
2564
+ "name": "Qwen2 VL 2B Instruct",
2565
+ "input_per_1m": 0.1,
2566
+ "output_per_1m": 0.1,
2567
+ "context_window": 32768
2568
+ },
2569
+ "qwen2-vl-72b-instruct": {
2570
+ "name": "Qwen2 VL 72B Instruct",
2571
+ "input_per_1m": 0.45,
2572
+ "output_per_1m": 0.45,
2573
+ "context_window": 131072
2574
+ },
2575
+ "qwen2-vl-7b-instruct": {
2576
+ "name": "Qwen2 VL 7B Instruct",
2577
+ "input_per_1m": 0.2,
2578
+ "output_per_1m": 0.2,
2579
+ "context_window": 131072
2580
+ },
2581
+ "qwen3-0-6b": {
2582
+ "name": "Qwen3 0.6B",
2583
+ "context_window": 40960
2584
+ },
2585
+ "qwen3-0-6b-base": {
2586
+ "name": "Qwen3 0.6B Base"
2587
+ },
2588
+ "qwen3-1-7b": {
2589
+ "name": "Qwen3 1.7B",
2590
+ "context_window": 131072
2591
+ },
2592
+ "qwen3-1-7b-base": {
2593
+ "name": "Qwen3 1.7B Base"
2594
+ },
2595
+ "qwen3-14b": {
2596
+ "name": "Qwen3 14B",
2597
+ "context_window": 40960,
2598
+ "tokens_per_second": 63.568,
2599
+ "time_to_first_token": 1.139
2600
+ },
2601
+ "qwen3-14b-base": {
2602
+ "name": "Qwen3 14B Base"
2603
+ },
2604
+ "qwen3-235b-a22b": {
2605
+ "name": "Qwen3 235B A22B",
2606
+ "input_per_1m": 0.455,
2607
+ "output_per_1m": 1.82,
2608
+ "context_window": 131072,
2609
+ "tokens_per_second": 62.49,
2610
+ "time_to_first_token": 1.23
2611
+ },
2612
+ "qwen3-235b-a22b-instruct-2507": {
2613
+ "name": "Qwen3 235B A22B Instruct 2507",
2614
+ "input_per_1m": 0.09,
2615
+ "output_per_1m": 0.1,
2616
+ "context_window": 262144,
2617
+ "tokens_per_second": 70.081,
2618
+ "time_to_first_token": 1.1
2619
+ },
2620
+ "qwen3-235b-a22b-thinking-2507": {
2621
+ "name": "Qwen3 235B A22B Thinking 2507",
2622
+ "input_per_1m": 0.1,
2623
+ "output_per_1m": 0.1,
2624
+ "context_window": 262144
2625
+ },
2626
+ "qwen3-30b-a3b": {
2627
+ "name": "Qwen3 30B A3B",
2628
+ "context_window": 40960,
2629
+ "tokens_per_second": 103.391,
2630
+ "time_to_first_token": 1.091
2631
+ },
2632
+ "qwen3-30b-a3b-base": {
2633
+ "name": "Qwen3 30B A3B Base"
2634
+ },
2635
+ "qwen3-30b-a3b-instruct-2507": {
2636
+ "name": "Qwen3 30B A3B Instruct 2507",
2637
+ "context_window": 262144,
2638
+ "tokens_per_second": 149.079,
2639
+ "time_to_first_token": 1.085
2640
+ },
2641
+ "qwen3-30b-a3b-thinking-2507": {
2642
+ "name": "Qwen3 30B A3B Thinking 2507",
2643
+ "input_per_1m": 0.08,
2644
+ "output_per_1m": 0.4,
2645
+ "context_window": 32768
2646
+ },
2647
+ "qwen3-32b": {
2648
+ "name": "Qwen3 32B",
2649
+ "context_window": 40960,
2650
+ "tokens_per_second": 98.81,
2651
+ "time_to_first_token": 1.083
2652
+ },
2653
+ "qwen3-4b": {
2654
+ "name": "Qwen3 4B",
2655
+ "input_per_1m": 0.2,
2656
+ "output_per_1m": 0.2,
2657
+ "context_window": 40960
2658
+ },
2659
+ "qwen3-4b-base": {
2660
+ "name": "Qwen3 4B Base"
2661
+ },
2662
+ "qwen3-4b-instruct-2507": {
2663
+ "name": "Qwen3 4B Instruct 2507",
2664
+ "context_window": 262144
2665
+ },
2666
+ "qwen3-5-0-8b": {
2667
+ "name": "Qwen3.5 0.8B",
2668
+ "tokens_per_second": 23.474,
2669
+ "time_to_first_token": 0.469
2670
+ },
2671
+ "qwen3-5-122b-a10b": {
2672
+ "name": "Qwen3.5-122B-A10B",
2673
+ "context_window": 262144,
2674
+ "tokens_per_second": 167.752,
2675
+ "time_to_first_token": 1.125
2676
+ },
2677
+ "qwen3-5-27b": {
2678
+ "name": "Qwen3.5-27B",
2679
+ "input_per_1m": 0.195,
2680
+ "output_per_1m": 1.56,
2681
+ "context_window": 262144,
2682
+ "tokens_per_second": 92.552,
2683
+ "time_to_first_token": 1.521
2684
+ },
2685
+ "qwen3-5-2b-non-reasoning": {
2686
+ "name": "Qwen3.5 2B (Non-reasoning)",
2687
+ "tokens_per_second": 21.65,
2688
+ "time_to_first_token": 0.604
2689
+ },
2690
+ "qwen3-5-35b-a3b": {
2691
+ "name": "Qwen3.5-35B-A3B",
2692
+ "context_window": 262144,
2693
+ "tokens_per_second": 189.628,
2694
+ "time_to_first_token": 1.345
2695
+ },
2696
+ "qwen3-5-397b-a17b": {
2697
+ "name": "Qwen3.5 397B A17B",
2698
+ "input_per_1m": 0.39,
2699
+ "output_per_1m": 2.34,
2700
+ "context_window": 262144,
2701
+ "tokens_per_second": 52.0,
2702
+ "time_to_first_token": 1.63
2703
+ },
2704
+ "qwen3-5-4b-non-reasoning": {
2705
+ "name": "Qwen3.5 4B (Non-reasoning)",
2706
+ "tokens_per_second": 24.073,
2707
+ "time_to_first_token": 0.482
2708
+ },
2709
+ "qwen3-5-9b": {
2710
+ "name": "Qwen3.5 9B",
2711
+ "input_per_1m": 0.1,
2712
+ "output_per_1m": 0.15,
2713
+ "context_window": 262144
2714
+ },
2715
+ "qwen3-5-flash": {
2716
+ "name": "Qwen3.5-Flash",
2717
+ "input_per_1m": 0.065,
2718
+ "output_per_1m": 0.26,
2719
+ "context_window": 1000000
2720
+ },
2721
+ "qwen3-5-plus": {
2722
+ "name": "Qwen3.5 Plus",
2723
+ "input_per_1m": 0.26,
2724
+ "output_per_1m": 1.56,
2725
+ "context_window": 1000000
2726
+ },
2727
+ "qwen3-6-35b-a3b": {
2728
+ "name": "Qwen3.6 35B A3B",
2729
+ "context_window": 262144,
2730
+ "tokens_per_second": 175.498,
2731
+ "time_to_first_token": 1.376
2732
+ },
2733
+ "qwen3-7-max": {
2734
+ "name": "Qwen3.7 Max",
2735
+ "input_per_1m": 1.25,
2736
+ "output_per_1m": 3.75,
2737
+ "context_window": 1000000,
2738
+ "tokens_per_second": 187.177,
2739
+ "time_to_first_token": 1.711
2740
+ },
2741
+ "qwen3-7-plus": {
2742
+ "name": "Qwen3.7 Plus",
2743
+ "input_per_1m": 0.32,
2744
+ "output_per_1m": 1.28,
2745
+ "context_window": 1000000,
2746
+ "tokens_per_second": 52.646,
2747
+ "time_to_first_token": 1.305
2748
+ },
2749
+ "qwen3-8b": {
2750
+ "name": "Qwen3 8B",
2751
+ "context_window": 40960,
2752
+ "tokens_per_second": 63.399,
2753
+ "time_to_first_token": 1.408
2754
+ },
2755
+ "qwen3-8b-base": {
2756
+ "name": "Qwen3 8B Base"
2757
+ },
2758
+ "qwen3-coder-30b-a3b-instruct": {
2759
+ "name": "Qwen3 Coder 30B A3B Instruct",
2760
+ "context_window": 160000,
2761
+ "tokens_per_second": 111.852,
2762
+ "time_to_first_token": 1.556
2763
+ },
2764
+ "qwen3-coder-480b-a35b-exacto": {
2765
+ "name": "Qwen3 Coder 480B A35B (exacto)",
2766
+ "input_per_1m": 0.22,
2767
+ "output_per_1m": 1.8,
2768
+ "context_window": 262144,
2769
+ "tokens_per_second": 70.281,
2770
+ "time_to_first_token": 1.566
2771
+ },
2772
+ "qwen3-coder-480b-instruct-bf16": {
2773
+ "name": "Qwen3 Coder 480B Instruct BF16",
2774
+ "input_per_1m": 0.9,
2775
+ "output_per_1m": 0.9,
2776
+ "context_window": 262144
2777
+ },
2778
+ "qwen3-coder-flash": {
2779
+ "name": "Qwen3 Coder Flash",
2780
+ "input_per_1m": 0.195,
2781
+ "output_per_1m": 0.975,
2782
+ "context_window": 1000000
2783
+ },
2784
+ "qwen3-coder-next": {
2785
+ "name": "Qwen3 Coder Next",
2786
+ "input_per_1m": 0.12,
2787
+ "output_per_1m": 0.8,
2788
+ "context_window": 262144,
2789
+ "tokens_per_second": 93.246,
2790
+ "time_to_first_token": 1.202
2791
+ },
2792
+ "qwen3-coder-plus": {
2793
+ "name": "Qwen3 Coder Plus",
2794
+ "input_per_1m": 0.65,
2795
+ "output_per_1m": 3.25,
2796
+ "context_window": 1000000
2797
+ },
2798
+ "qwen3-max": {
2799
+ "name": "Qwen3 Max",
2800
+ "input_per_1m": 0.78,
2801
+ "output_per_1m": 3.9,
2802
+ "context_window": 262144,
2803
+ "tokens_per_second": 50.969,
2804
+ "time_to_first_token": 1.699
2805
+ },
2806
+ "qwen3-max-thinking": {
2807
+ "name": "Qwen3 Max Thinking",
2808
+ "input_per_1m": 0.78,
2809
+ "output_per_1m": 3.9,
2810
+ "context_window": 262144,
2811
+ "tokens_per_second": 52.254,
2812
+ "time_to_first_token": 1.774
2813
+ },
2814
+ "qwen3-next-80b-a3b-instruct": {
2815
+ "name": "Qwen3 Next 80B A3B Instruct",
2816
+ "context_window": 262144,
2817
+ "tokens_per_second": 166.817,
2818
+ "time_to_first_token": 1.131
2819
+ },
2820
+ "qwen3-next-80b-a3b-thinking": {
2821
+ "name": "Qwen3 Next 80B A3B Thinking",
2822
+ "input_per_1m": 0.0975,
2823
+ "output_per_1m": 0.78,
2824
+ "context_window": 128000
2825
+ },
2826
+ "qwen3-omni-30b-a3b-instruct": {
2827
+ "name": "Qwen3 Omni 30B A3B Instruct",
2828
+ "input_per_1m": 0.9,
2829
+ "output_per_1m": 0.9,
2830
+ "context_window": 65536,
2831
+ "tokens_per_second": 105.394,
2832
+ "time_to_first_token": 0.929
2833
+ },
2834
+ "qwen3-vl-235b-a22b-instruct": {
2835
+ "name": "Qwen3 VL 235B A22B Instruct",
2836
+ "context_window": 262144,
2837
+ "tokens_per_second": 50.815,
2838
+ "time_to_first_token": 1.12
2839
+ },
2840
+ "qwen3-vl-235b-a22b-thinking": {
2841
+ "name": "Qwen3 VL 235B A22B Thinking",
2842
+ "input_per_1m": 0.26,
2843
+ "output_per_1m": 2.6,
2844
+ "context_window": 131072
2845
+ },
2846
+ "qwen3-vl-30b-a3b-instruct": {
2847
+ "name": "Qwen3 VL 30B A3B Instruct",
2848
+ "input_per_1m": 0.13,
2849
+ "output_per_1m": 0.52,
2850
+ "context_window": 131072,
2851
+ "tokens_per_second": 123.194,
2852
+ "time_to_first_token": 1.05
2853
+ },
2854
+ "qwen3-vl-30b-a3b-thinking": {
2855
+ "name": "Qwen3 VL 30B A3B Thinking",
2856
+ "input_per_1m": 0.13,
2857
+ "output_per_1m": 1.56,
2858
+ "context_window": 131072
2859
+ },
2860
+ "qwen3-vl-32b-instruct": {
2861
+ "name": "Qwen3 VL 32B Instruct",
2862
+ "input_per_1m": 0.104,
2863
+ "output_per_1m": 0.416,
2864
+ "context_window": 131072,
2865
+ "tokens_per_second": 74.569,
2866
+ "time_to_first_token": 1.232
2867
+ },
2868
+ "qwen3-vl-8b-instruct": {
2869
+ "name": "Qwen3 VL 8B Instruct",
2870
+ "input_per_1m": 0.08,
2871
+ "output_per_1m": 0.5,
2872
+ "context_window": 131072,
2873
+ "tokens_per_second": 146.178,
2874
+ "time_to_first_token": 0.949
2875
+ },
2876
+ "qwen3-vl-8b-thinking": {
2877
+ "name": "Qwen3 VL 8B Thinking",
2878
+ "input_per_1m": 0.117,
2879
+ "output_per_1m": 1.365,
2880
+ "context_window": 131072
2881
+ },
2882
+ "qwq-32b": {
2883
+ "name": "QwQ 32B",
2884
+ "input_per_1m": 0.9,
2885
+ "output_per_1m": 0.9,
2886
+ "context_window": 32768
2887
+ },
2888
+ "qwq-32b-preview": {
2889
+ "name": "QwQ 32B Preview",
2890
+ "input_per_1m": 0.9,
2891
+ "output_per_1m": 0.9,
2892
+ "context_window": 32768
2893
+ },
2894
+ "qwq-32b-rpr": {
2895
+ "name": "QwQ 32B RpR v1",
2896
+ "context_window": 32768
2897
+ },
2898
+ "r1": {
2899
+ "name": "R1",
2900
+ "input_per_1m": 0.55,
2901
+ "output_per_1m": 2.19,
2902
+ "context_window": 64000
2903
+ },
2904
+ "r1-0528": {
2905
+ "name": "R1 0528",
2906
+ "input_per_1m": 0.5,
2907
+ "output_per_1m": 2.18,
2908
+ "context_window": 163840
2909
+ },
2910
+ "r1-distill-llama-70b": {
2911
+ "name": "R1 Distill Llama 70B",
2912
+ "input_per_1m": 0.75,
2913
+ "output_per_1m": 0.99,
2914
+ "context_window": 131072,
2915
+ "tokens_per_second": 34.522,
2916
+ "time_to_first_token": 0.486
2917
+ },
2918
+ "r1-distill-llama-8b": {
2919
+ "name": "R1 Distill Llama 8B",
2920
+ "input_per_1m": 0.04,
2921
+ "output_per_1m": 0.04,
2922
+ "context_window": 32768
2923
+ },
2924
+ "r1-distill-qwen-1-5b": {
2925
+ "name": "R1 Distill Qwen 1.5B",
2926
+ "input_per_1m": 0.18,
2927
+ "output_per_1m": 0.18,
2928
+ "context_window": 131072
2929
+ },
2930
+ "r1-distill-qwen-14b": {
2931
+ "name": "R1 Distill Qwen 14B",
2932
+ "input_per_1m": 0.15,
2933
+ "output_per_1m": 0.15,
2934
+ "context_window": 32768
2935
+ },
2936
+ "r1-distill-qwen-32b": {
2937
+ "name": "R1 Distill Qwen 32B",
2938
+ "input_per_1m": 0.29,
2939
+ "output_per_1m": 0.29,
2940
+ "context_window": 32768
2941
+ },
2942
+ "r1-distill-qwen-7b": {
2943
+ "name": "R1 Distill Qwen 7B",
2944
+ "context_window": 32768
2945
+ },
2946
+ "r1t-chimera": {
2947
+ "name": "R1T Chimera",
2948
+ "context_window": 163840
2949
+ },
2950
+ "reka-flash-3": {
2951
+ "name": "Reka Flash 3",
2952
+ "context_window": 65536
2953
+ },
2954
+ "relace-apply-3": {
2955
+ "name": "Relace Apply 3",
2956
+ "input_per_1m": 0.85,
2957
+ "output_per_1m": 1.25,
2958
+ "context_window": 256000
2959
+ },
2960
+ "relace-search": {
2961
+ "name": "Relace Search",
2962
+ "input_per_1m": 1.0,
2963
+ "output_per_1m": 3.0,
2964
+ "context_window": 256000
2965
+ },
2966
+ "remm-slerp-13b": {
2967
+ "name": "ReMM SLERP 13B",
2968
+ "input_per_1m": 0.3,
2969
+ "output_per_1m": 0.3,
2970
+ "context_window": 6144
2971
+ },
2972
+ "rime-mist": {
2973
+ "name": "rime-labs/rime-mist-v3"
2974
+ },
2975
+ "rime-mist-v3-omni": {
2976
+ "name": "rime-labs/rime-mist-v3-omni"
2977
+ },
2978
+ "rnj-1-instruct": {
2979
+ "name": "Rnj 1 Instruct",
2980
+ "input_per_1m": 0.15,
2981
+ "output_per_1m": 0.15,
2982
+ "context_window": 32768
2983
+ },
2984
+ "rocinante-12b": {
2985
+ "name": "Rocinante 12B",
2986
+ "input_per_1m": 0.17,
2987
+ "output_per_1m": 0.43,
2988
+ "context_window": 32768
2989
+ },
2990
+ "saba": {
2991
+ "name": "Saba",
2992
+ "input_per_1m": 0.2,
2993
+ "output_per_1m": 0.6,
2994
+ "context_window": 32768
2995
+ },
2996
+ "sarvam-m": {
2997
+ "name": "Sarvam M",
2998
+ "context_window": 8192
2999
+ },
3000
+ "seed-1-6": {
3001
+ "name": "Seed 1.6",
3002
+ "input_per_1m": 0.25,
3003
+ "output_per_1m": 2.0,
3004
+ "context_window": 262144
3005
+ },
3006
+ "seed-1-6-flash": {
3007
+ "name": "Seed 1.6 Flash",
3008
+ "input_per_1m": 0.075,
3009
+ "output_per_1m": 0.3,
3010
+ "context_window": 262144
3011
+ },
3012
+ "seed-2-0-lite": {
3013
+ "name": "Seed 2.0 Lite",
3014
+ "input_per_1m": 0.25,
3015
+ "output_per_1m": 2.0,
3016
+ "context_window": 262144
3017
+ },
3018
+ "seed-2-0-mini": {
3019
+ "name": "Seed 2.0 Mini",
3020
+ "input_per_1m": 0.1,
3021
+ "output_per_1m": 0.4,
3022
+ "context_window": 262144
3023
+ },
3024
+ "seed-oss-36b-instruct": {
3025
+ "name": "Seed OSS 36B Instruct",
3026
+ "input_per_1m": 0.9,
3027
+ "output_per_1m": 0.9,
3028
+ "context_window": 262000,
3029
+ "tokens_per_second": 26.568,
3030
+ "time_to_first_token": 1.569
3031
+ },
3032
+ "skyfall-36b": {
3033
+ "name": "Skyfall 36B V2",
3034
+ "input_per_1m": 0.55,
3035
+ "output_per_1m": 0.8,
3036
+ "context_window": 32768
3037
+ },
3038
+ "snorkel-mistral-pairrm-dpo": {
3039
+ "name": "Snorkel Mistral PairRM DPO",
3040
+ "input_per_1m": 0.2,
3041
+ "output_per_1m": 0.2,
3042
+ "context_window": 32768
3043
+ },
3044
+ "solar-10-7b-instruct": {
3045
+ "name": "SOLAR 10.7B Instruct v1",
3046
+ "input_per_1m": 0.3,
3047
+ "output_per_1m": 0.3,
3048
+ "context_window": 4096
3049
+ },
3050
+ "sonar": {
3051
+ "name": "Sonar",
3052
+ "input_per_1m": 1.0,
3053
+ "output_per_1m": 1.0,
3054
+ "context_window": 127072
3055
+ },
3056
+ "sonar-deep-research": {
3057
+ "name": "Sonar Deep Research",
3058
+ "input_per_1m": 2.0,
3059
+ "output_per_1m": 8.0,
3060
+ "context_window": 128000
3061
+ },
3062
+ "sonar-pro": {
3063
+ "name": "Sonar Pro",
3064
+ "input_per_1m": 3.0,
3065
+ "output_per_1m": 15.0,
3066
+ "context_window": 200000
3067
+ },
3068
+ "sonar-pro-search": {
3069
+ "name": "Sonar Pro Search",
3070
+ "input_per_1m": 3.0,
3071
+ "output_per_1m": 15.0,
3072
+ "context_window": 200000
3073
+ },
3074
+ "sonar-reasoning": {
3075
+ "name": "Sonar Reasoning",
3076
+ "input_per_1m": 1.0,
3077
+ "output_per_1m": 5.0,
3078
+ "context_window": 127000
3079
+ },
3080
+ "sonar-reasoning-pro": {
3081
+ "name": "Sonar Reasoning Pro",
3082
+ "input_per_1m": 2.0,
3083
+ "output_per_1m": 8.0,
3084
+ "context_window": 128000
3085
+ },
3086
+ "sorcererlm-8x22b": {
3087
+ "name": "SorcererLM 8x22B",
3088
+ "context_window": 16000
3089
+ },
3090
+ "spotlight": {
3091
+ "name": "Spotlight",
3092
+ "context_window": 131072
3093
+ },
3094
+ "step-3-5-flash": {
3095
+ "name": "Step 3.5 Flash",
3096
+ "input_per_1m": 0.09,
3097
+ "output_per_1m": 0.3,
3098
+ "context_window": 256000,
3099
+ "tokens_per_second": 174.77,
3100
+ "time_to_first_token": 6.879
3101
+ },
3102
+ "step3": {
3103
+ "name": "Step3",
3104
+ "context_window": 256000
3105
+ },
3106
+ "switchpoint-router": {
3107
+ "name": "Switchpoint Router",
3108
+ "input_per_1m": 0.85,
3109
+ "output_per_1m": 3.4,
3110
+ "context_window": 131072
3111
+ },
3112
+ "text-ada-001": {
3113
+ "name": "text-ada-001",
3114
+ "input_per_1m": 0.2,
3115
+ "output_per_1m": 0.2,
3116
+ "context_window": 2048
3117
+ },
3118
+ "text-davinci-002": {
3119
+ "name": "text-davinci-002",
3120
+ "input_per_1m": 10.0,
3121
+ "output_per_1m": 10.0,
3122
+ "context_window": 4097
3123
+ },
3124
+ "text-davinci-003": {
3125
+ "name": "text-davinci-003",
3126
+ "input_per_1m": 20.0,
3127
+ "output_per_1m": 20.0,
3128
+ "context_window": 4097
3129
+ },
3130
+ "together-moa-1-turbo": {
3131
+ "name": "Together MoA-1-Turbo",
3132
+ "context_window": 32768
3133
+ },
3134
+ "tongyi-deepresearch-30b-a3b": {
3135
+ "name": "Tongyi DeepResearch 30B A3B",
3136
+ "context_window": 131072
3137
+ },
3138
+ "toppy-m-7b": {
3139
+ "name": "Toppy M 7B",
3140
+ "input_per_1m": 0.2,
3141
+ "output_per_1m": 0.2,
3142
+ "context_window": 32768
3143
+ },
3144
+ "trinity-large-preview": {
3145
+ "name": "Trinity Large Preview",
3146
+ "context_window": 131000
3147
+ },
3148
+ "trinity-large-thinking": {
3149
+ "name": "Trinity Large Thinking",
3150
+ "input_per_1m": 0.22,
3151
+ "output_per_1m": 0.85,
3152
+ "context_window": 262144
3153
+ },
3154
+ "trinity-mini": {
3155
+ "name": "Trinity Mini",
3156
+ "input_per_1m": 0.045,
3157
+ "output_per_1m": 0.15,
3158
+ "context_window": 131072
3159
+ },
3160
+ "ui-tars-7b": {
3161
+ "name": "UI-TARS 7B",
3162
+ "input_per_1m": 0.1,
3163
+ "output_per_1m": 0.2,
3164
+ "context_window": 128000
3165
+ },
3166
+ "unslopnemo-12b": {
3167
+ "name": "UnslopNemo 12B",
3168
+ "input_per_1m": 0.4,
3169
+ "output_per_1m": 0.4,
3170
+ "context_window": 32768
3171
+ },
3172
+ "v0-1-0-md": {
3173
+ "name": "vercel/v0-1.0-md",
3174
+ "input_per_1m": 3.0,
3175
+ "output_per_1m": 15.0,
3176
+ "context_window": 128000
3177
+ },
3178
+ "v0-1-5-md": {
3179
+ "name": "vercel/v0-1-5-md",
3180
+ "input_per_1m": 3.0,
3181
+ "output_per_1m": 15.0,
3182
+ "context_window": 128000
3183
+ },
3184
+ "vicuna-13b": {
3185
+ "name": "lmsys/vicuna-13b-v1.5",
3186
+ "input_per_1m": 0.3,
3187
+ "output_per_1m": 0.3,
3188
+ "context_window": 4096
3189
+ },
3190
+ "virtuoso-large": {
3191
+ "name": "Virtuoso Large",
3192
+ "input_per_1m": 0.75,
3193
+ "output_per_1m": 1.2,
3194
+ "context_window": 131072
3195
+ },
3196
+ "voxtral-small-24b-2507": {
3197
+ "name": "Voxtral Small 24B 2507",
3198
+ "input_per_1m": 0.1,
3199
+ "output_per_1m": 0.3,
3200
+ "context_window": 32000
3201
+ },
3202
+ "weaver-alpha": {
3203
+ "name": "Weaver (alpha)",
3204
+ "input_per_1m": 0.75,
3205
+ "output_per_1m": 1.0,
3206
+ "context_window": 8000
3207
+ },
3208
+ "wizardlm-2-8x22b": {
3209
+ "name": "WizardLM-2 8x22B",
3210
+ "input_per_1m": 0.62,
3211
+ "output_per_1m": 0.62,
3212
+ "context_window": 65535
3213
+ },
3214
+ "yi-34b": {
3215
+ "name": "zero-one-ai/Yi-34B",
3216
+ "input_per_1m": 0.8,
3217
+ "output_per_1m": 0.8,
3218
+ "context_window": 4096
3219
+ },
3220
+ "zephyr-7b-beta": {
3221
+ "name": "Zephyr 7B Beta",
3222
+ "input_per_1m": 0.2,
3223
+ "output_per_1m": 0.2,
3224
+ "context_window": 16384
3225
+ }
3226
+ }