dsh-claude-style 0.18.2-dev.38 → 0.18.3-dev.41

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.
package/lib/prices.json CHANGED
@@ -1,7 +1,7 @@
1
1
  {
2
2
  "schemaVersion": 1,
3
- "updatedAt": "2026-10-21",
4
- "capturedAt": "2026-10-21T05:35:13.684Z",
3
+ "updatedAt": "2026-10-22",
4
+ "capturedAt": "2026-10-22T08:34:01.825Z",
5
5
  "source": {
6
6
  "zh": "https://api-docs.deepseek.com/zh-cn/quick_start/pricing/",
7
7
  "en": "https://api-docs.deepseek.com/quick_start/pricing/"
@@ -148,10 +148,10 @@
148
148
  "alicloud-deepseek-v4-pro": "1.69 0.13 3.38",
149
149
  "alicloud-glm-5.1": "0.84 0.169 3.38",
150
150
  "all-mini-lm-l6-v2": "0.009 0.009 0",
151
- "amazon--nova-lite": "0.3 0.3 2.37",
152
- "amazon--nova-micro": "0.03 0.03 0.1",
153
- "amazon--nova-pro": "0.56 0.56 2.13",
154
- "amazon--titan-embed-text": "0.14 0.14 0",
151
+ "amazon--nova-lite": "0.3 0.3 2.5",
152
+ "amazon--nova-micro": "0.035 0.035 0.14",
153
+ "amazon--nova-pro": "0.8 0.8 3.2",
154
+ "amazon--titan-embed-text": "0.02 0.02 0",
155
155
  "amazon.nova-2-lite-v1:0": "0.33 0.0825 2.75",
156
156
  "amazon.nova-lite-v1:0": "0.06 0.015 0.24",
157
157
  "amazon.nova-lite-v1:0@us": "0.06 0.015 0.24",
@@ -253,7 +253,7 @@
253
253
  "bee-hive": "5 0.5 20",
254
254
  "bee-swarm": "25 2.5 150",
255
255
  "bge-m3": "0.015 0.015 0",
256
- "bge-multilingual-gemma2": "0.1 0.1 0",
256
+ "bge-multilingual-gemma2": "0.11215 0.11215 0",
257
257
  "bge-reranker-v2-m3": "0.01 0.01 0",
258
258
  "bge_multilingual_gemma2": "0.08 0.08 0",
259
259
  "bielik-11b-v3.0-instruct": "0.67 0.67 0.67",
@@ -261,6 +261,7 @@
261
261
  "c4ai-aya-expanse-32b": "0.5 0.5 1.5",
262
262
  "ca.amazon.nova-lite-v1:0": "0.064 0.016 0.256",
263
263
  "celeris-1": "2 1 6",
264
+ "chat-latest": "5 0.5 30",
264
265
  "chatgpt-4o-latest": "4.75 3.5 17",
265
266
  "claude-3-5-haiku": "0.8 0.08 4",
266
267
  "claude-3-7-sonnet-20250219": "3 1.65 15",
@@ -298,7 +299,7 @@
298
299
  "claude-mythos-5": "10 1 50",
299
300
  "claude-opus-4": "15 1.5 75",
300
301
  "claude-opus-4-1": "15 1.5 75",
301
- "claude-opus-4-1-20250805": "15 13.5 75",
302
+ "claude-opus-4-1-20250805": "15 1.5 75",
302
303
  "claude-opus-4-1-20250805-thinking": "15 15 75",
303
304
  "claude-opus-4-1@20250805": "15 1.5 75",
304
305
  "claude-opus-4-20250514": "15 13.5 75",
@@ -345,7 +346,7 @@
345
346
  "claude-opus-5-5@default": "4 0.2 20",
346
347
  "claude-opus-5-5@eu": "4.4 0.22 22",
347
348
  "claude-opus-5-fast": "10 1 50",
348
- "claude-opus-5-thinking": "5 5 25",
349
+ "claude-opus-5-thinking": "5 0.5 25",
349
350
  "claude-opus-5.5": "4 0.2 20",
350
351
  "claude-opus-5.5-fast": "8 0.4 40",
351
352
  "claude-opus-5@default": "5 0.5 25",
@@ -362,13 +363,13 @@
362
363
  "claude-sonnet-4-20250514": "3 2.7 15",
363
364
  "claude-sonnet-4-5": "3 0.3 15",
364
365
  "claude-sonnet-4-5-20250929": "3 0.3 15",
365
- "claude-sonnet-4-5-20250929-thinking": "3 3 15",
366
+ "claude-sonnet-4-5-20250929-thinking": "3 0.3 15",
366
367
  "claude-sonnet-4-5-think": "3.3 0.33 16.5",
367
368
  "claude-sonnet-4-5@20250929": "3 0.3 15",
368
369
  "claude-sonnet-4-5@eu": "3.3 0.3 16.5",
369
370
  "claude-sonnet-4-6": "3 0.3 15",
370
371
  "claude-sonnet-4-6-think": "3 0.3 15",
371
- "claude-sonnet-4-6-thinking": "3 3 15",
372
+ "claude-sonnet-4-6-thinking": "3 0.3 15",
372
373
  "claude-sonnet-4-6@default": "3 0.3 15",
373
374
  "claude-sonnet-4-6@eu": "3.3 0.3 16.5",
374
375
  "claude-sonnet-4.5": "3 0.3 15",
@@ -408,10 +409,10 @@
408
409
  "coding-router:low": "0.14 0.028 0.28",
409
410
  "coding-router:max": "5 0.5 30",
410
411
  "coding-router:medium": "0.14 0.028 0.28",
411
- "coding-xiaomi-mimo-v2.5": "0.08 0.016 0.4",
412
- "coding-xiaomi-mimo-v2.5-pro": "0.2 0.04 0.6",
412
+ "coding-xiaomi-mimo-v2.5": "0.08 0.0016 0.16",
413
+ "coding-xiaomi-mimo-v2.5-pro": "0.2 0.0016 0.4",
413
414
  "cogito-v1-preview-qwen-32b": "1.8 0.9 1.8",
414
- "cohere--command-a-reasoning": "0.63 0.63 5.05",
415
+ "cohere--command-a-reasoning": "2.5 2.5 10",
415
416
  "cohere-command-a": "2.5 2.5 10",
416
417
  "cohere-embed-v-4-0": "0.12 0.12 0",
417
418
  "cohere-embed-v3-english": "0.1 0.1 0",
@@ -476,18 +477,18 @@
476
477
  "deep-research-preview-04-2026": "2 1.1 12",
477
478
  "deepseek-3.2": "0.5 0.15 1.6",
478
479
  "deepseek-4-flash": "0.14 0.028 0.28",
479
- "deepseek-chat": "0.2574 0.03 0.6",
480
+ "deepseek-chat": "0.2574 0.03 0.66",
480
481
  "deepseek-chat-cheaper": "0.1 0.05 0.425",
481
482
  "deepseek-chat-v3-0324": "0.29 0.11 1.14",
482
483
  "deepseek-chat-v3.1": "0.25 0.13 0.95",
483
484
  "deepseek-flash": "0.15 0.003 0.6",
484
- "deepseek-flash-latest": "0.07 0.008 0.5",
485
+ "deepseek-flash-latest": "0.025 0.004 0.25",
485
486
  "deepseek-latest": "0.66 0.022 1.98",
486
487
  "deepseek-ocr": "0.2 0.2 0.7",
487
488
  "deepseek-ocr-2": "0.45985 0.0612 0.74875",
488
- "deepseek-pro-latest": "0.225 0.23 8",
489
- "deepseek-r1": "0.7 0.7 2.5",
490
- "deepseek-r1-0528": "0.574 0.35 2.294",
489
+ "deepseek-pro-latest": "0.2235 0.22 8",
490
+ "deepseek-r1": "0.7 0.7 2.45",
491
+ "deepseek-r1-0528": "0.548833 0.35 2.249667",
491
492
  "deepseek-r1-0528-qwen3-8b": "0.06 0.06 0.09",
492
493
  "deepseek-r1-distill-llama-70b": "0.1585 0.1585 0.5005",
493
494
  "deepseek-r1-distill-llama-70b-abliterated": "0.7 0.35 0.7",
@@ -496,31 +497,33 @@
496
497
  "deepseek-r1-distill-qwen-32b-abliterated": "1.4 0.7 1.4",
497
498
  "deepseek-r1-distill-qwen-7b": "0.072 0.072 0.144",
498
499
  "deepseek-r1-turbo": "0.7 0.7 2.5",
499
- "deepseek-reasoner": "0.3535 0.049 0.9875",
500
+ "deepseek-reasoner": "0.401 0.03885 1.203",
500
501
  "deepseek-tng-r1t2-chimera": "0.3 0.3 1.2",
501
- "deepseek-v3": "0.2835 0.275 1.1",
502
- "deepseek-v3-0324": "0.25 0.25 0.9",
502
+ "deepseek-v3": "0.298895 0.28 1.147",
503
+ "deepseek-v3-0324": "0.25 0.2 1",
503
504
  "deepseek-v3-1": "0.587 0.587 1.7105",
504
505
  "deepseek-v3-2-exp": "0.287 0.287 0.431",
505
506
  "deepseek-v3.1": "0.27 0.27 1",
506
507
  "deepseek-v3.1-maas": "0.6 0.06 1.7",
507
508
  "deepseek-v3.1-terminus": "0.27 0.27 1",
509
+ "deepseek-v3.1-terminus-thinking": "0.57971 0.57971 1.73913",
508
510
  "deepseek-v3.1-terminus:thinking": "0.25 0.125 0.7",
509
511
  "deepseek-v3.1:thinking": "0.2 0.1 0.7",
510
- "deepseek-v3.2": "0.28 0.205 0.42",
512
+ "deepseek-v3.2": "0.28 0.13065 0.42",
513
+ "deepseek-v3.2-251201": "0.289855 0.028986 0.434783",
511
514
  "deepseek-v3.2-exp": "0.27 0.27 0.41",
512
- "deepseek-v3.2-exp-thinking": "0.28 0.14 0.42",
515
+ "deepseek-v3.2-exp-thinking": "0.284928 0.214928 0.427391",
513
516
  "deepseek-v3.2-maas": "0.56 0.056 1.68",
514
517
  "deepseek-v3.2-speciale": "0.58 0.58 1.68",
515
518
  "deepseek-v3.2-tee": "1 0.1 1",
516
519
  "deepseek-v3.2-thinking": "0.455 0.455 1.14",
517
520
  "deepseek-v3.2:thinking": "0.2088 0.0216 0.3096",
518
- "deepseek-v4-1-flash": "0.3 0.08 1.2",
521
+ "deepseek-v4-1-flash": "0.3 0.03 1.2",
519
522
  "deepseek-v4-1-flash-1017": "0.3 0.15375 1.2",
520
- "deepseek-v4-flash": "0.14 0.022 0.28",
523
+ "deepseek-v4-flash": "0.14 0.025 0.28",
521
524
  "deepseek-v4-flash-0423": "0.14 0.028 0.28",
522
525
  "deepseek-v4-flash-0423:thinking": "0.14 0.028 0.28",
523
- "deepseek-v4-flash-0731": "0.14 0.028 0.2898",
526
+ "deepseek-v4-flash-0731": "0.146 0.028 0.3",
524
527
  "deepseek-v4-flash-0731-fast": "0.28 0.07 0.7",
525
528
  "deepseek-v4-flash-0731-tee": "0.44 0.044 1.32",
526
529
  "deepseek-v4-flash-0731:thinking": "0.05 0.013 0.16",
@@ -529,14 +532,14 @@
529
532
  "deepseek-v4-flash-fast": "0.28 0.07 0.56",
530
533
  "deepseek-v4-flash-flex": "0.091 0.0182 0.182",
531
534
  "deepseek-v4-flash-ga-260731": "0.4453 0.01484 1.3359",
532
- "deepseek-v4-flash-latest": "0.0605 0.0056 0.528",
535
+ "deepseek-v4-flash-latest": "0.07375 0.028 0.2184",
533
536
  "deepseek-v4-flash-speed": "0.14 0.028 0.28",
534
537
  "deepseek-v4-flash-vision-exp": "0.2156 0.00686 0.6468",
535
538
  "deepseek-v4-flash:0731": "0.22 0.007 0.66",
536
539
  "deepseek-v4-flash:thinking": "0.14 0.0028 0.28",
537
- "deepseek-v4-pro": "1.32 0.13 3.25",
540
+ "deepseek-v4-pro": "1.32 0.13 3.3",
538
541
  "deepseek-v4-pro-0423": "1.485 0.9 3.63",
539
- "deepseek-v4-pro-0813": "1.32 0.05 3.96",
542
+ "deepseek-v4-pro-0813": "1.32 0.045953 3.96",
540
543
  "deepseek-v4-pro-0813:thinking": "0.66 0.022 1.98",
541
544
  "deepseek-v4-pro-0813@eu": "1.75 0.44 3.5",
542
545
  "deepseek-v4-pro-el": "1.67 1.67 3.33",
@@ -544,18 +547,20 @@
544
547
  "deepseek-v4-pro:0813": "0.66 0.022 1.98",
545
548
  "deepseek-v4-pro:thinking": "0.7 0.07 1.4",
546
549
  "deepseek-v4-pro@eu": "1.75 0.44 3.5",
547
- "deepseek-v4.1-flash": "0.23592 0.006 0.952",
550
+ "deepseek-v4.1-flash": "0.243 0.006 0.98",
548
551
  "deepseek-v4.1-flash-1017": "0.3 0.006 1.2",
549
552
  "deepseek-v4.1-flash-1017-fast": "0.6 0.014 2.4",
553
+ "deepseek-v4.1-flash-1017:peft:262144": "0.6 0.12 3.6",
550
554
  "deepseek-v4.1-flash-1017:thinking": "0.1 0.003 0.6",
551
555
  "deepseek-v4.1-flash-1017@eu": "0.5 0.05 1.5",
552
- "deepseek-v4.1-flash-552b": "0.25 0.1 1",
553
- "deepseek-v4.1-flash-fast": "0.38 0.014 1.8",
556
+ "deepseek-v4.1-flash-552b": "0.280375 0.11215 1.1215",
557
+ "deepseek-v4.1-flash-fast": "0.425 0.014 1.8",
554
558
  "deepseek-v4.1-flash-flex": "0.0975 0.00975 0.39",
555
559
  "deepseek-v4.1-flash-marathon": "0.14 0.0028 0.28",
556
560
  "deepseek-v4.1-flash:1017": "0.15 0.003 0.6",
557
- "deepseek-v4.1-flash:fast": "0.6 0.6 2.4",
558
- "deepseek-v4.1-flash:thinking": "0.14 0.0042 0.42",
561
+ "deepseek-v4.1-flash:fast": "0.6 0.012 2.4",
562
+ "deepseek-v4.1-flash:peft:262144": "0.6 0.12 3.6",
563
+ "deepseek-v4.1-flash:thinking": "0.09 0.006 0.25",
559
564
  "deepseek-v4.1-flash@eu": "0.5 0.05 1.5",
560
565
  "deepseek-v4p1-flash": "0.3 0.006 1.2",
561
566
  "deepseek-v4p1-flash-1017": "0.3 0.006 1.2",
@@ -582,7 +587,9 @@
582
587
  "dola-seed-2.0-pro": "0.5 0.5 3",
583
588
  "dolphin-mistral-24b-venice-edition": "0.2 0.2 0.9",
584
589
  "doubao-1.5-pro-256k": "0.799 0.3995 1.445",
585
- "doubao-1.5-pro-32k": "0.1343 0.06715 0.3349",
590
+ "doubao-1.5-pro-32k": "0.125121 0.091546 0.312378",
591
+ "doubao-1.5-thinking-pro": "0.57971 0.57971 2.318841",
592
+ "doubao-1.5-vision-pro": "0.434783 0.434783 1.304348",
586
593
  "doubao-1.5-vision-pro-32k": "0.459 0.2295 1.377",
587
594
  "doubao-seed-1-6": "0.12 0.023 0.29",
588
595
  "doubao-seed-1-6-251015": "0.11875 0.02375 1.18747",
@@ -592,33 +599,36 @@
592
599
  "doubao-seed-1-6-vision": "0.12 0.023 1.15",
593
600
  "doubao-seed-1-6-vision-250815": "0.116375 0.068875 1.165235",
594
601
  "doubao-seed-1-8": "0.12 0.023 0.29",
595
- "doubao-seed-1-8-251215": "0.114 0.114 0.286",
602
+ "doubao-seed-1-8-251215": "0.1143 0.1143 0.286",
596
603
  "doubao-seed-1-8-251228": "0.11875 0.02375 1.18747",
597
- "doubao-seed-1.8": "0.11 0.02 0.28",
598
- "doubao-seed-2-0-code-preview": "0.48 0.09644 2.41",
604
+ "doubao-seed-1.6": "0.115942 0.115942 1.15942",
605
+ "doubao-seed-1.6-flash": "0.021739 0.021739 0.217391",
606
+ "doubao-seed-1.6-thinking": "0.115942 0.115942 1.15942",
607
+ "doubao-seed-1.8": "0.11 0.0215 0.28",
608
+ "doubao-seed-2-0-code-preview": "0.4822 0.09644 2.411",
599
609
  "doubao-seed-2-0-code-preview-260215": "0.628495 0.243 3.13397",
600
610
  "doubao-seed-2-0-lite-260215": "0.1462 0.0731 0.8738",
601
- "doubao-seed-2-0-lite-260428": "0.08453 0.017365 0.52218",
611
+ "doubao-seed-2-0-lite-260428": "0.089735 0.017946 0.53841",
602
612
  "doubao-seed-2-0-mini-260215": "0.0493 0.02465 0.4845",
603
- "doubao-seed-2-0-mini-260428": "0.029845 0.00579 0.288435",
604
- "doubao-seed-2-0-pro": "0.48 0.09644 2.41",
613
+ "doubao-seed-2-0-mini-260428": "0.029913 0.005984 0.299115",
614
+ "doubao-seed-2-0-pro": "0.4958 0.09916 2.479",
605
615
  "doubao-seed-2-0-pro-260215": "0.628495 0.243 3.12547",
606
616
  "doubao-seed-2-1-pro-260628": "0.8906 0.17812 4.45301",
607
617
  "doubao-seed-2-1-turbo-260628": "0.4453 0.08906 2.22651",
608
- "doubao-seed-2.0-code": "0.785 0.52 3.92",
609
- "doubao-seed-2.0-lite": "0.11 0.025 0.635",
610
- "doubao-seed-2.0-mini": "0.045 0.015 0.42",
611
- "doubao-seed-2.0-pro": "0.56 0.115 2.8",
618
+ "doubao-seed-2.0-code": "0.566884 0.116377 2.83942",
619
+ "doubao-seed-2.0-lite": "0.09 0.02 0.51587",
620
+ "doubao-seed-2.0-mini": "0.03 0.01 0.284928",
621
+ "doubao-seed-2.0-pro": "0.456884 0.091377 2.27942",
612
622
  "doubao-seed-2.1-pro": "0.8536 0.3208 4.268",
613
623
  "doubao-seed-2.1-turbo": "0.4268 0.159 2.1348",
614
624
  "doubao-seed-character": "0.1635 0.027 0.627",
615
625
  "doubao-seed-character-260628": "0.11875 0.02375 0.29687",
616
- "doubao-seed-code": "0.17 0.03 1.12",
626
+ "doubao-seed-code": "0.17 0.032 1.12",
617
627
  "doubao-seed-evolving": "0.8873 0.17756 4.436505",
618
628
  "dracarys-72b-instruct": "0.493 0.2465 0.493",
619
629
  "dsv4": "0.04 0.02 0.21",
620
630
  "e5-large-v2": "0.02 0.02 0",
621
- "e5-mistral-7b-instruct": "0.02 0.02 0.02",
631
+ "e5-mistral-7b-instruct": "0.02243 0.02243 0",
622
632
  "echo": "10 10 50",
623
633
  "efficient": "0.325 0.0325 1.95",
624
634
  "ember-1": "3 0.3 15",
@@ -680,7 +690,7 @@
680
690
  "gemini-2.5-flash-nothinking": "0.3 0.03 2.5",
681
691
  "gemini-2.5-flash-preview-04-17": "0.15 0.015 0.6",
682
692
  "gemini-2.5-flash-preview-04-17:thinking": "0.15 0.015 3.5",
683
- "gemini-2.5-flash-preview-05-20": "0.1425 0.075 1.875",
693
+ "gemini-2.5-flash-preview-05-20": "0.14625 0.02175 1.9625",
684
694
  "gemini-2.5-flash-preview-05-20:thinking": "0.15 0.015 3.5",
685
695
  "gemini-2.5-flash-preview-09-2025": "0.3 0.165 2.5",
686
696
  "gemini-2.5-flash-preview-09-2025-thinking": "0.3 0.03 2.5",
@@ -692,17 +702,17 @@
692
702
  "gemini-2.5-pro-preview": "0.9375 0.09375 7.5",
693
703
  "gemini-2.5-pro-preview-03-25": "2.5 0.25 10",
694
704
  "gemini-2.5-pro-preview-05-06": "2.5 0.25 10",
695
- "gemini-2.5-pro-preview-06-05": "1.8125 0.6875 9.5",
705
+ "gemini-2.5-pro-preview-06-05": "1.84375 0.18435 9.75",
696
706
  "gemini-2.5-pro-preview-tts": "1 1 20",
697
707
  "gemini-2.5-pro-tts": "1 1 20",
698
708
  "gemini-2.5-pro@eu": "1.25 0.31 10",
699
- "gemini-3-1-flash-lite": "0.25 0.025 1.5",
700
- "gemini-3-1-pro": "2 0.2 12",
709
+ "gemini-3-1-flash-lite": "0.267857 0.026786 1.607143",
710
+ "gemini-3-1-pro": "1.6 0.16 9.571429",
701
711
  "gemini-3-1-pro-preview": "2.25 0.35 13.5",
702
712
  "gemini-3-5-flash": "1.525 0.1525 9.225",
703
713
  "gemini-3-5-flash-lite": "0.3375 0.03375 2.8125",
704
- "gemini-3-6-flash": "1.21875 0.121875 6.09375",
705
- "gemini-3-7-flash": "1.21875 0.121875 6.09375",
714
+ "gemini-3-6-flash": "0.9375 0.09375 4.6875",
715
+ "gemini-3-7-flash": "0.9375 0.09375 4.6875",
706
716
  "gemini-3-8-flash": "0.975 0.0975 4.875",
707
717
  "gemini-3-flash": "0.5 0.05 3",
708
718
  "gemini-3-flash-preview": "0.5 0.05 3",
@@ -767,7 +777,7 @@
767
777
  "gemma-3": "0.15 0.15 0.3",
768
778
  "gemma-3-12b": "0.15 0.15 0.5",
769
779
  "gemma-3-12b-it": "0.05 0.05 0.15",
770
- "gemma-3-27b-it": "0.1 0.0995 0.3",
780
+ "gemma-3-27b-it": "0.1 0.1 0.3",
771
781
  "gemma-3-4b-it": "0.05 0.05 0.1",
772
782
  "gemma-3-4b-pt": "0.15 0.15 0.15",
773
783
  "gemma-4": "2 0.5 5",
@@ -786,7 +796,7 @@
786
796
  "gemma-4-26b-a4b-it-musica": "0.12 0.06 0.38",
787
797
  "gemma-4-26b-a4b-it-opusdistill": "0.12 0.06 0.38",
788
798
  "gemma-4-26b-a4b-it-shadowsiren": "0.12 0.06 0.38",
789
- "gemma-4-26b-a4b-it:thinking": "0.0765 0.0425 0.255",
799
+ "gemma-4-26b-a4b-it:thinking": "0.09 0.05 0.3",
790
800
  "gemma-4-26b-a4b-meromero": "0.12 0.06 0.38",
791
801
  "gemma-4-26b-a4b-meromero:thinking": "0.12 0.06 0.38",
792
802
  "gemma-4-26b-a4b-uncensored": "0.15 0.075 0.7",
@@ -809,16 +819,19 @@
809
819
  "gemma-4-31b-meromero-v2:thinking": "0.1 0.05 0.45",
810
820
  "gemma-4-31b-queen": "0.306 0.153 0.306",
811
821
  "gemma-4-31b-turbo-tee": "0.12 0.012 0.37",
822
+ "gemma-4-dark-thoughts-v2-31b": "0.1 0.05 0.45",
812
823
  "gemma-4-e2b-it": "0.1 0.1 0.1",
813
824
  "gemma-4-e4b-it": "0.11 0.11 0.15",
825
+ "gemma-4-giftige-blume-31b-v2": "0.1 0.05 0.45",
814
826
  "gemma-4-uncensored": "0.1625 0.1625 0.5",
815
827
  "gemma-sea-lion-v4-27b-it": "0.351 0.351 0.555",
816
828
  "gemma2-9b-it": "0.01 0.01 0.03",
817
829
  "gemma4": "0.57 0.57 1.71",
818
- "gemma4-26b": "0.1 0.1 0.5",
830
+ "gemma4-26b": "0.11215 0.11215 0.56075",
819
831
  "gemma4-31b": "0.4 0.4 1",
820
832
  "gemma4-31b-splituntied": "0.1 0.05 0.3",
821
833
  "gemma4-31b:thinking": "0.4 0.4 1",
834
+ "gemma4-gutenberg-31b": "0.1 0.05 0.45",
822
835
  "gemma4:31b": "0.14 0.05 0.4",
823
836
  "gliguard-llmguardrails-300m": "0.15 0.15 0.15",
824
837
  "gliguard-pii-multi": "0.15 0.15 0.15",
@@ -840,7 +853,7 @@
840
853
  "glm-4.1v-thinking-flash": "0.3 0.15 0.3",
841
854
  "glm-4.1v-thinking-flashx": "0.3 0.15 0.3",
842
855
  "glm-4.5": "0.6 0.11 2.2",
843
- "glm-4.5-air": "0.13 0.03 0.86",
856
+ "glm-4.5-air": "0.14 0.03 0.89637",
844
857
  "glm-4.5-air:thinking": "0.12 0.06 0.8",
845
858
  "glm-4.5-airx": "1.1 0.22 4.5",
846
859
  "glm-4.5-fp8": "0.2 0.2 0.8",
@@ -854,12 +867,12 @@
854
867
  "glm-4.6-turbo": "1 0.5 3",
855
868
  "glm-4.6-turbo:thinking": "1 0.5 3",
856
869
  "glm-4.6:thinking": "0.5 0.1 2",
857
- "glm-4.6v": "0.3 0.055 0.9",
870
+ "glm-4.6v": "0.3 0.05 0.9",
858
871
  "glm-4.6v-flash": "0.1609 0.1522 0.5592",
859
872
  "glm-4.6v-flashx": "0.04 0.004 0.4",
860
873
  "glm-4.6v-original": "0.6 0.3 0.9",
861
- "glm-4.7": "0.6 0.11 2.2",
862
- "glm-4.7-flash": "0.06525 0.0605 0.4",
874
+ "glm-4.7": "0.57 0.11 2.2",
875
+ "glm-4.7-flash": "0.07 0.02 0.4",
863
876
  "glm-4.7-flash:thinking": "0.07 0.01 0.4",
864
877
  "glm-4.7-flashx": "0.07 0.01 0.4",
865
878
  "glm-4.7-maas": "0.6 0.06 2.2",
@@ -868,37 +881,37 @@
868
881
  "glm-4.7:thinking": "0.4004 0.08008 1.9292",
869
882
  "glm-5": "1 0.2 3.2",
870
883
  "glm-5-1": "0.825 0.165 3.301",
871
- "glm-5-2": "1.4 0.26 4.4",
884
+ "glm-5-2": "1.4 0.2 4.4",
872
885
  "glm-5-2-260617": "1.18747 0.29687 4.15615",
873
- "glm-5-3": "1.4 0.45 4.4",
874
- "glm-5-3-flash": "0.1125 0.0525 0.375",
886
+ "glm-5-3": "1.4 0.355 4.4",
887
+ "glm-5-3-flash": "0.114286 0.03 0.342857",
875
888
  "glm-5-3-flash-260828": "0.11875 0.03414 0.41563",
876
889
  "glm-5-fp8": "0.6 0.12 1.92",
877
890
  "glm-5-maas": "1 0.1 3.2",
878
891
  "glm-5-original": "0.6 0.1 1.9",
879
892
  "glm-5-original:thinking": "0.6 0.1 1.9",
880
893
  "glm-5-turbo": "1.2 0.24 4",
881
- "glm-5.1": "1.392 0.26 4.4",
894
+ "glm-5.1": "1.38 0.26 4.4",
882
895
  "glm-5.1-fp8": "1.19 0.091 3.74",
883
896
  "glm-5.1-tee": "0.98 0.098 3.08",
884
897
  "glm-5.1-thinking": "0.7 0.18 2.5",
885
898
  "glm-5.1:thinking": "0.7 0.18 2.5",
886
899
  "glm-5.1@eu": "1.4 1.4 4.4",
887
900
  "glm-5.2": "1.4 0.26 4.4",
888
- "glm-5.2-caveman": "1.254 0.3135 5.016",
889
- "glm-5.2-caveman-lite": "1.254 0.3135 5.016",
890
- "glm-5.2-caveman-ultra": "1.254 0.3135 5.016",
901
+ "glm-5.2-caveman": "1.738325 0.4486 5.1589",
902
+ "glm-5.2-caveman-lite": "1.738325 0.4486 5.1589",
903
+ "glm-5.2-caveman-ultra": "1.738325 0.4486 5.1589",
891
904
  "glm-5.2-fast": "2.156 0.231 6.776",
892
905
  "glm-5.2-flex": "0.9425 0.09425 2.925",
893
906
  "glm-5.2-fp8": "1.0895 0.221 3.64",
894
- "glm-5.2-honey": "1.254 0.3135 5.016",
895
- "glm-5.2-honey-lite": "1.254 0.3135 5.016",
896
- "glm-5.2-honey-ultra": "1.254 0.3135 5.016",
907
+ "glm-5.2-honey": "1.738325 0.4486 5.1589",
908
+ "glm-5.2-honey-lite": "1.738325 0.4486 5.1589",
909
+ "glm-5.2-honey-ultra": "1.738325 0.4486 5.1589",
897
910
  "glm-5.2-maas": "1.4 0.14 4.4",
898
911
  "glm-5.2-nitro": "0.8 0.8 2.4",
899
- "glm-5.2-ponytail": "1.254 0.3135 5.016",
900
- "glm-5.2-ponytail-lite": "1.254 0.3135 5.016",
901
- "glm-5.2-ponytail-ultra": "1.254 0.3135 5.016",
912
+ "glm-5.2-ponytail": "1.738325 0.4486 5.1589",
913
+ "glm-5.2-ponytail-lite": "1.738325 0.4486 5.1589",
914
+ "glm-5.2-ponytail-ultra": "1.738325 0.4486 5.1589",
902
915
  "glm-5.2-short": "1.45 0.145 4.5",
903
916
  "glm-5.2-short-fast": "1.45 0.145 4.5",
904
917
  "glm-5.2-short-fast-flex": "0.9425 0.09425 2.925",
@@ -913,15 +926,18 @@
913
926
  "glm-5.3-flash-apex-abliterated": "0.15 0.075 0.5",
914
927
  "glm-5.3-flash-cybersecurity": "0.15 0.075 0.5",
915
928
  "glm-5.3-flash-flex": "0.0975 0.0195 0.325",
929
+ "glm-5.3-flash-nvfp4": "0.15 0.03 0.5",
916
930
  "glm-5.3-flash-uncensored": "0.2 0.07 0.8",
917
- "glm-5.3-flash:fast": "0.15 0.15 0.5",
931
+ "glm-5.3-flash:fast": "0.3 0.06 1",
932
+ "glm-5.3-flash:peft:262144": "0.84 0.168 2.11",
918
933
  "glm-5.3-flash@eu": "0.2 0.07 0.6",
919
934
  "glm-5.3-flashx": "0.37 0.075 1.25",
920
935
  "glm-5.3-flex": "0.9425 0.09425 2.925",
921
936
  "glm-5.3-marathon": "1.4 0.26 4.4",
922
937
  "glm-5.3-prime": "2.8 0.56 8.8",
923
938
  "glm-5.3-uncensored": "1.25 0.3 2.25",
924
- "glm-5.3:fast": "2.8 2.8 8.8",
939
+ "glm-5.3:fast": "2.8 0.52 8.8",
940
+ "glm-5.3:peft:262144": "3.78 0.756 12.15",
925
941
  "glm-5.3:thinking": "0.6 0.2 1.1",
926
942
  "glm-5.3@eu": "1.2 0.26 4.2",
927
943
  "glm-5.x-menthol": "0.4 0.4 1.75",
@@ -932,13 +948,13 @@
932
948
  "glm-5v-turbo": "1.2 0.24 4",
933
949
  "glm-5v-turbo:thinking": "1.2 0.24 4",
934
950
  "glm-fast-latest": "2.1 0.39 6.6",
935
- "glm-flash-latest": "0.100846 0.016875 0.4375",
951
+ "glm-flash-latest": "0.07915 0.01915 0.34125",
936
952
  "glm-latest": "0.6 0.1733 1.4",
937
953
  "glm-z1-9b-0414": "0.2 0.1 0.2",
938
954
  "glm-z1-airx": "0.7 0.35 0.7",
939
955
  "glm5.2": "2.31 2.31 6",
940
956
  "glm5.2-fast": "3 0.5 10.25",
941
- "glm5.3-754b": "1 0.25 3.5",
957
+ "glm5.3-754b": "1.1215 0.280375 3.92525",
942
958
  "global.amazon.nova-2-lite-v1:0": "0.3 0.075 2.5",
943
959
  "global.anthropic.claude-fable-5": "10 1 50",
944
960
  "global.anthropic.claude-fable-5-1": "10 0.25 50",
@@ -1004,7 +1020,7 @@
1004
1020
  "gpt-4o-2024-05-13": "5 5 15",
1005
1021
  "gpt-4o-2024-08-06": "2.5 1.25 10",
1006
1022
  "gpt-4o-2024-11-20": "2.5 1.25 10",
1007
- "gpt-4o-aug": "2.2 1.1 9",
1023
+ "gpt-4o-aug": "2.2727 1.1364 9.0909",
1008
1024
  "gpt-4o-fast": "4.25 2.125 17",
1009
1025
  "gpt-4o-mini": "0.15 0.075 0.6",
1010
1026
  "gpt-4o-mini-2024-07-18": "0.15 0.075 0.6",
@@ -1012,7 +1028,7 @@
1012
1028
  "gpt-4o-mini-search": "0.14 0.14 0.54",
1013
1029
  "gpt-4o-mini-transcribe": "1.25 1.25 5",
1014
1030
  "gpt-4o-mini@eu": "0.165 0.0825 0.66",
1015
- "gpt-4o-search": "2.2 2.2 9",
1031
+ "gpt-4o-search": "2.2727 2.2727 9.0909",
1016
1032
  "gpt-4o-transcribe": "2.5 2.5 10",
1017
1033
  "gpt-5": "1.25 0.125 10",
1018
1034
  "gpt-5-1": "1.4375 0.14375 11.5",
@@ -1021,11 +1037,11 @@
1021
1037
  "gpt-5-4": "2.875 0.2875 17.25",
1022
1038
  "gpt-5-4-mini": "0.75 0.075 4.5",
1023
1039
  "gpt-5-4-nano": "0.2 0.02 1.25",
1024
- "gpt-5-5": "5 0.5 30",
1040
+ "gpt-5-5": "5.357143 0.535714 33",
1025
1041
  "gpt-5-5-pro": "30 30 180",
1026
- "gpt-5-6-luna": "0.2 0.02 1.2",
1027
- "gpt-5-6-sol": "5 0.5 30",
1028
- "gpt-5-6-terra": "2 0.2 12",
1042
+ "gpt-5-6-luna": "0.2 0.02 1.171429",
1043
+ "gpt-5-6-sol": "3.985714 0.844286 23.857143",
1044
+ "gpt-5-6-terra": "2.2 1.3 13.142857",
1029
1045
  "gpt-5-chat": "1.1 0.11 9",
1030
1046
  "gpt-5-chat-latest": "1.25 0.125 10",
1031
1047
  "gpt-5-codex": "1.25 0.125 10",
@@ -1081,16 +1097,16 @@
1081
1097
  "gpt-5.6": "2.75 0.275 16",
1082
1098
  "gpt-5.6-luna": "0.2 0.02 1.2",
1083
1099
  "gpt-5.6-luna-fast": "0.4 0.04 2.4",
1084
- "gpt-5.6-luna-pro": "0.2 0.023754 1.2",
1100
+ "gpt-5.6-luna-pro": "0.2 0.02 1.2",
1085
1101
  "gpt-5.6-luna@eu": "0.22 0.022 1.32",
1086
1102
  "gpt-5.6-sol": "4 0.4 20",
1087
1103
  "gpt-5.6-sol-fast": "8 0.8 40",
1088
- "gpt-5.6-sol-pro": "4.5 0.47508 23.754",
1104
+ "gpt-5.6-sol-pro": "4.5 0.45 23.754",
1089
1105
  "gpt-5.6-sol:official": "2.5 0.25 12.5",
1090
1106
  "gpt-5.6-sol@eu": "4.4 0.44 22",
1091
1107
  "gpt-5.6-terra": "2 0.2 12",
1092
1108
  "gpt-5.6-terra-fast": "4 0.4 24",
1093
- "gpt-5.6-terra-pro": "2 0.23754 12",
1109
+ "gpt-5.6-terra-pro": "2 0.2 12",
1094
1110
  "gpt-5.6-terra@eu": "2.2 0.22 13.2",
1095
1111
  "gpt-5@eu": "1.375 0.1375 11",
1096
1112
  "gpt-6-1-sol": "2 0.1 10",
@@ -1126,17 +1142,18 @@
1126
1142
  "gpt-luna-latest": "0.1 0.01 0.5",
1127
1143
  "gpt-mini-latest": "0.75 0.075 4.5",
1128
1144
  "gpt-oss-120b": "0.15 0.1 0.6",
1129
- "gpt-oss-120b-cs": "0.35 0.35 0.75",
1145
+ "gpt-oss-120b-cs": "0.3535 0.3535 0.7576",
1130
1146
  "gpt-oss-120b-high-throughput": "0.09 0.09 0.36",
1131
1147
  "gpt-oss-120b-maas": "0.09 0.09 0.36",
1132
- "gpt-oss-20b": "0.05 0.03875 0.2",
1148
+ "gpt-oss-120b:peft:131072": "0.33 0.066 0.84",
1149
+ "gpt-oss-20b": "0.0625 0.0375 0.2",
1133
1150
  "gpt-oss-20b-maas": "0.07 0.007 0.25",
1134
1151
  "gpt-oss-safeguard-120b": "0.15 0.15 0.6",
1135
1152
  "gpt-oss-safeguard-20b": "0.075 0.0375 0.3",
1136
1153
  "gpt-oss:120b": "0.15 0.014 0.6",
1137
1154
  "gpt-oss:20b": "0.07 0.035 0.3",
1138
1155
  "gpt-pro-latest": "4 0.4 20",
1139
- "gpt-realtime-1.5": "4 2.2 16",
1156
+ "gpt-realtime-1.5": "4 0.4 16",
1140
1157
  "gpt-realtime-2": "4 0.4 24",
1141
1158
  "gpt-realtime-2.1": "4 0.4 24",
1142
1159
  "gpt-realtime-mini": "0.6 0.06 2.4",
@@ -1149,12 +1166,10 @@
1149
1166
  "green-l-raw": "0.285 0.285 0.912",
1150
1167
  "green-r": "0.399 0.399 1.083",
1151
1168
  "green-r-raw": "0.399 0.399 1.083",
1152
- "green-s": "0.00437 0.00437 0",
1153
- "green-s-pro": "0.00437 0.00437 0",
1154
1169
  "grok-3": "3 0.75 15",
1155
1170
  "grok-3-mini": "0.3 0.075 0.5",
1156
1171
  "grok-4": "3 0.75 15",
1157
- "grok-4-0709": "2.85 2.85 14.25",
1172
+ "grok-4-0709": "2.925 2.925 14.625",
1158
1173
  "grok-4-1-fast-non-reasoning": "0.2 0.05 0.5",
1159
1174
  "grok-4-1-fast-reasoning": "0.2 0.05 0.5",
1160
1175
  "grok-4-20": "1.42 0.23 2.83",
@@ -1165,7 +1180,7 @@
1165
1180
  "grok-4-20-non-reasoning": "1.625 1.1 4.25",
1166
1181
  "grok-4-20-reasoning": "1.625 1.1 4.25",
1167
1182
  "grok-4-3": "1.25 0.2 2.5",
1168
- "grok-4-5": "2 0.3 6",
1183
+ "grok-4-5": "2.135 0.32 6.4",
1169
1184
  "grok-4-6": "2 0.5 6",
1170
1185
  "grok-4-7": "2 0.5 6",
1171
1186
  "grok-4-fast-non-reasoning": "0.2 0.18 0.5",
@@ -1189,7 +1204,7 @@
1189
1204
  "grok-4.20-reasoning": "1.25 0.2 2.5",
1190
1205
  "grok-4.20-reasoning-beta": "1.25 0.2 2.5",
1191
1206
  "grok-4.3": "1.25 0.2 2.5",
1192
- "grok-4.5": "2 0.4 6",
1207
+ "grok-4.5": "2 0.3 6",
1193
1208
  "grok-4.6": "2 0.5 6",
1194
1209
  "grok-4.7": "2 0.5 6",
1195
1210
  "grok-build-0-1": "1 0.2 2",
@@ -1200,7 +1215,7 @@
1200
1215
  "hermes-2-pro-llama-3-8b": "0.14 0.14 0.14",
1201
1216
  "hermes-3-llama-3.1-405b": "1 1 1",
1202
1217
  "hermes-3-llama-3.1-70b": "0.7 0.7 0.7",
1203
- "hermes-4-405b": "1 0.996 3",
1218
+ "hermes-4-405b": "1 1 3",
1204
1219
  "hermes-4-405b:thinking": "0.3 0.15 1.2",
1205
1220
  "hermes-high": "0.6 0.2 1.1",
1206
1221
  "hermes-low": "0.6 0.2 1.1",
@@ -1228,8 +1243,11 @@
1228
1243
  "inkling-256k": "1.87 0.374 4.68",
1229
1244
  "inkling-nvfp4": "1.2 0.27 5",
1230
1245
  "inkling-small": "0.5 0.1 1.2",
1246
+ "inkling-small:peft:262144": "0.58 0.116 1.44",
1247
+ "inkling-small:peft:262144:sampling-nvfp4": "0.3 0.06 1.2",
1231
1248
  "inkling-small:thinking": "0.45 0.1 1.2",
1232
1249
  "inkling:peft:262144": "1.87 0.374 4.68",
1250
+ "inkling:peft:262144:sampling-nvfp4": "1 0.17 4.05",
1233
1251
  "inkling:thinking": "0.95 0.16 4.05",
1234
1252
  "interfaze-beta": "1.5 1.5 3.5",
1235
1253
  "jamba-large": "2 2 8",
@@ -1247,32 +1265,32 @@
1247
1265
  "k2-think": "0.17 0.085 0.68",
1248
1266
  "kat-coder-pro": "0.3 0.3 1.2",
1249
1267
  "kat-coder-pro-v2": "0.3 0.06 1.2",
1250
- "kb-whisper-large": "0.0023 0.0023 0.0023",
1251
1268
  "kimi-fast-latest": "4.5 0.45 22.5",
1252
1269
  "kimi-k2": "0.57 0.57 2.3",
1253
1270
  "kimi-k2-0711": "0.57 0.57 2.3",
1254
1271
  "kimi-k2-0905": "0.6 0.6 2.5",
1255
- "kimi-k2-0905-preview": "0.632 0.632 2.53",
1272
+ "kimi-k2-0905-preview": "0.62854 0.62854 2.5146",
1256
1273
  "kimi-k2-5": "0.56 0.22 3.5",
1257
- "kimi-k2-6": "0.8939 0.16 3.7131",
1258
- "kimi-k2-7-code": "0.85 0.555 3.75",
1274
+ "kimi-k2-6": "0.82195 0.1694 3.60655",
1275
+ "kimi-k2-7-code": "0.75 0.16 3.5",
1259
1276
  "kimi-k2-7-code-highspeed": "1.9 1.9 8",
1260
1277
  "kimi-k2-instruct": "0.57 0.57 2.3",
1261
1278
  "kimi-k2-instruct-0711": "0.4 0.2 1.8",
1262
- "kimi-k2-instruct-0905": "0.4 0.2 1.9",
1279
+ "kimi-k2-instruct-0905": "0.57 0.285 2.3",
1263
1280
  "kimi-k2-instruct-fast": "0.4 0.2 1.8",
1264
1281
  "kimi-k2-instruct-fp4": "0.4 0.2 1.8",
1265
- "kimi-k2-thinking": "0.6 0.275 2.5",
1282
+ "kimi-k2-thinking": "0.6 0.3 2.5",
1266
1283
  "kimi-k2-thinking-maas": "0.6 0.06 2.5",
1267
1284
  "kimi-k2-thinking-turbo": "1.15 0.15 8",
1268
1285
  "kimi-k2-turbo-preview": "0.15 0.15 8",
1269
- "kimi-k2.5": "0.6 0.12 3",
1286
+ "kimi-k2.5": "0.6 0.1 3",
1270
1287
  "kimi-k2.5:thinking": "0.375 0.07 2",
1271
1288
  "kimi-k2.5@eu": "0.72 0.72 3.6",
1272
1289
  "kimi-k2.6": "0.95 0.16 4",
1273
1290
  "kimi-k2.6-fast": "1.655 1.655 8.778",
1274
1291
  "kimi-k2.6-nitro": "0.275 0.275 1.1",
1275
1292
  "kimi-k2.6-tee": "0.45 0.045 1.95",
1293
+ "kimi-k2.6:peft:131072": "2.205 0.441 5.49",
1276
1294
  "kimi-k2.6:thinking": "0.45 0.045 1.95",
1277
1295
  "kimi-k2.6@eu": "0.95 0.95 4",
1278
1296
  "kimi-k2.7-code": "0.95 0.19 4",
@@ -1287,7 +1305,7 @@
1287
1305
  "kimi-k3-fast-api": "4.5 0.45 22.5",
1288
1306
  "kimi-k3-flex": "1.95 0.195 9.75",
1289
1307
  "kimi-k3-tee": "1.85 0.185 9.5",
1290
- "kimi-k3:fast": "6 6 30",
1308
+ "kimi-k3:fast": "6 0.6 30",
1291
1309
  "kimi-k3@eu": "3 0.45 15",
1292
1310
  "kimi-latest": "1.2 0.228 15",
1293
1311
  "kloker": "0.23 0.23 1.16",
@@ -1314,6 +1332,7 @@
1314
1332
  "lfm2-24b-a2b": "0.03 0.03 0.12",
1315
1333
  "lfm2.5-24b-a2b": "0.05 0.025 0.7",
1316
1334
  "lightonocr-2-1b": "0.1785 0.1785 0.3465",
1335
+ "lightonocr-3-0.8b": "2.464 2.464 0",
1317
1336
  "ling-1t": "0.565 0.34 2.265",
1318
1337
  "ling-2.6-1t": "0.3 0.3 2.5",
1319
1338
  "ling-2.6-flash": "0.1 0.1 0.3",
@@ -1323,7 +1342,7 @@
1323
1342
  "ling-3.0-flash-vl": "0.06 0.012 0.18",
1324
1343
  "ling-3.0-flash:thinking": "0.075 0.015 0.22",
1325
1344
  "ling-3.1-flash": "0.3 0.06 0.9",
1326
- "ling-flash-2.0": "0.14 0.14 0.57",
1345
+ "ling-flash-2.0": "0.144724 0.144724 0.583895",
1327
1346
  "llama-3-3-70b-instruct": "0.7526 0.7526 0.7526",
1328
1347
  "llama-3-70b-instruct": "0.51 0.51 0.74",
1329
1348
  "llama-3.05-nemotron-tenyxchat-storybreaker-70b": "0.493 0.2465 0.493",
@@ -1345,8 +1364,8 @@
1345
1364
  "llama-3.2-3b": "0.125 0.125 0.35",
1346
1365
  "llama-3.2-3b-instruct": "0.0403 0.04 0.19",
1347
1366
  "llama-3.2-90b-vision-instruct": "0.35 0.175 0.4",
1348
- "llama-3.3-70b": "0.7 0.7 2.8",
1349
- "llama-3.3-70b-instruct": "0.6 0.6 0.71",
1367
+ "llama-3.3-70b": "0.71 0.71 1.76",
1368
+ "llama-3.3-70b-instruct": "0.6 0.6 0.724",
1350
1369
  "llama-3.3-70b-instruct-abliterated": "0.7 0.35 0.7",
1351
1370
  "llama-3.3-70b-instruct-fp8": "1.15 1.15 1.15",
1352
1371
  "llama-3.3-70b-instruct-fp8-dynamic": "0.53 0.53 0.76",
@@ -1360,13 +1379,13 @@
1360
1379
  "llama-4-maverick-17b-128e-instruct-fp8": "0.25 0.25 0.85",
1361
1380
  "llama-4-maverick-17b-128e-instruct-maas": "0.35 0.35 1.15",
1362
1381
  "llama-4-maverick-17b-instruct": "0.27 0.27 0.85",
1363
- "llama-4-scout": "0.0825 0.08 0.3",
1382
+ "llama-4-scout": "0.085 0.08 0.3",
1364
1383
  "llama-4-scout-17b-16e-instruct": "0.2 0.2 0.78",
1365
1384
  "llama-4-scout-17b-16e-instruct-maas": "0.25 0.25 0.7",
1366
1385
  "llama-4-scout-17b-instruct": "0.18 0.18 0.59",
1367
1386
  "llama-guard-3-8b": "0.484 0.484 0.03",
1368
1387
  "llama-guard-4": "0.21 0.21 0.21",
1369
- "llama-guard-4-12b": "0.162 0.162 0.162",
1388
+ "llama-guard-4-12b": "0.18 0.18 0.18",
1370
1389
  "llama-prompt-guard-2-22m": "0.03 0.015 0.03",
1371
1390
  "llama-prompt-guard-2-86m": "0.04 0.02 0.04",
1372
1391
  "llama-xlam-2-70b-fc-r": "2.5 1.25 2.5",
@@ -1375,10 +1394,10 @@
1375
1394
  "llama3.3-70b-instruct": "0.65 0.65 0.65",
1376
1395
  "longcat-2.0": "0.75 0.015 2.95",
1377
1396
  "longcat-2.0:thinking": "0.75 0.015 3",
1378
- "longcat-2.5-preview": "0.525 0.0105 2.075",
1397
+ "longcat-2.5-preview": "0.3 0.006 1.2",
1379
1398
  "lucidnova-rf1-100b": "2 2 5",
1380
- "lucidquery-agi-01-frontier": "4.5 4.5 22",
1381
- "lucidquery-agi-01-swift": "2.5 2.5 15",
1399
+ "lucidquery-agi-01-frontier": "5.04675 5.04675 24.673",
1400
+ "lucidquery-agi-01-swift": "2.80375 2.80375 16.8225",
1382
1401
  "lucidquery-nexus-coder": "2 2 5",
1383
1402
  "lumimaid-v0.2-70b": "1 0.5 1.5",
1384
1403
  "m2-her": "0.3 0.3 1.2",
@@ -1422,14 +1441,16 @@
1422
1441
  "meta.llama3-3-70b-instruct-v1:0": "0.72 0.72 0.72",
1423
1442
  "meta.llama4-maverick-17b-instruct-v1:0": "0.24 0.24 0.97",
1424
1443
  "meta.llama4-scout-17b-instruct-v1:0": "0.17 0.17 0.66",
1444
+ "mimo-v2-5": "0.165714 0.165714 0.331429",
1445
+ "mimo-v2-5-pro": "0.52 0.52 1.028571",
1425
1446
  "mimo-v2-6-flash": "0.14 0.14 0.28",
1426
1447
  "mimo-v2-6-pro": "0.435 0.435 0.87",
1427
1448
  "mimo-v2-6-pro-ultraspeed": "4.35 4.35 8.7",
1428
1449
  "mimo-v2-flash": "0.1 0.01 0.3",
1429
1450
  "mimo-v2-omni": "0.27 0.0414 1.14",
1430
1451
  "mimo-v2-pro": "1 0.2 3",
1431
- "mimo-v2.5": "0.14 0.003 0.28",
1432
- "mimo-v2.5-pro": "0.47 0.0043 0.94",
1452
+ "mimo-v2.5": "0.14 0.0028 0.28",
1453
+ "mimo-v2.5-pro": "0.435 0.00392 0.87",
1433
1454
  "mimo-v2.5-pro-ultraspeed": "1.305 0.0108 2.61",
1434
1455
  "mimo-v2.5-pro:thinking": "0.435 0.0036 0.87",
1435
1456
  "mimo-v2.5:thinking": "0.14 0.0028 0.28",
@@ -1445,18 +1466,18 @@
1445
1466
  "minicpm-v-4.5": "0.651 0.651 1.097",
1446
1467
  "minimax-01": "0.2 0.2 1.1",
1447
1468
  "minimax-latest": "0.265 0.055 1.08",
1448
- "minimax-m1": "0.2697 0.266 1.7664",
1469
+ "minimax-m1": "0.4 0.4 2.2",
1449
1470
  "minimax-m1-80k": "0.55 0.55 2.2",
1450
- "minimax-m2": "0.3 0.085 1.2",
1471
+ "minimax-m2": "0.3 0.17 1.2",
1451
1472
  "minimax-m2-5": "0.3 0.03 1.2",
1452
1473
  "minimax-m2-7": "0.3 0.06 1.2",
1453
- "minimax-m2-7-highspeed": "0.45 0.315 1.8",
1474
+ "minimax-m2-7-highspeed": "0.594286 0.06 2.4",
1454
1475
  "minimax-m2-her": "0.3 0.03 1.2",
1455
1476
  "minimax-m2.1": "0.3 0.0307 1.2",
1456
1477
  "minimax-m2.1-lightning": "0.21 0.075 1.44",
1457
1478
  "minimax-m2.5": "0.3 0.03 1.2",
1458
1479
  "minimax-m2.5-highspeed": "0.6 0.03 2.4",
1459
- "minimax-m2.5-lightning": "0.45 0.045 3.6",
1480
+ "minimax-m2.5-lightning": "0.45 0.03 2.4",
1460
1481
  "minimax-m2.7": "0.3 0.06 1.2",
1461
1482
  "minimax-m2.7-highspeed": "0.6 0.06 2.4",
1462
1483
  "minimax-m2.7-turbo": "0.6 0.06 2.4",
@@ -1467,7 +1488,7 @@
1467
1488
  "minimax-m3-1-flash": "0.15 0.015 0.6",
1468
1489
  "minimax-m3-preview": "0.3 0.06 1.2",
1469
1490
  "minimax-m3.1-flash": "0.15 0.015 0.6",
1470
- "minimax-m3:fast": "0.6 0.6 2.4",
1491
+ "minimax-m3:fast": "0.6 0.12 2.4",
1471
1492
  "minimax-m3:thinking": "0.23 0.05 0.96",
1472
1493
  "minimax-m3@eu": "0.4 0.1 2",
1473
1494
  "minimax-text-01": "0.2 0.2 1.1",
@@ -1477,7 +1498,7 @@
1477
1498
  "ministral-14b": "0.2 0.11 0.2",
1478
1499
  "ministral-14b-2512": "0.2 0.022 0.2",
1479
1500
  "ministral-14b-instruct-2512": "0.1 0.05 0.4",
1480
- "ministral-3-14b-instruct-2512": "0.353225 0.353225 0.4743",
1501
+ "ministral-3-14b-instruct-2512": "0.35351 0.35351 0.47468",
1481
1502
  "ministral-3-14b-reasoning-2512": "2.5 2.5 1.7",
1482
1503
  "ministral-3-3b-reasoning-2512": "1.039 1.039 0.54825",
1483
1504
  "ministral-3b": "0.07 0.04 0.07",
@@ -1497,14 +1518,15 @@
1497
1518
  "mistral-large-2402": "4.284 4.284 12.952",
1498
1519
  "mistral-large-2407": "2 0.2 6",
1499
1520
  "mistral-large-2411": "2 2 6",
1500
- "mistral-large-2512": "0.5 0.061 1.5",
1521
+ "mistral-large-2512": "0.5 0.0523 1.5",
1501
1522
  "mistral-large-3": "0.5 0.275 1.5",
1502
1523
  "mistral-large-3:675b": "0.5 0.5 1.5",
1503
- "mistral-large-4": "0.6956 0.0716 2.13795",
1524
+ "mistral-large-4": "1.02 0.105 3.135",
1504
1525
  "mistral-large-4-0": "1.0625 0.1095 3.2655",
1505
1526
  "mistral-large-4@eu": "0.68 0.07 2.09",
1506
1527
  "mistral-large-instruct-2411": "2 1 6",
1507
- "mistral-large-latest": "1.25 0.5 3.75",
1528
+ "mistral-large-latest": "1.25 0.35 3.75",
1529
+ "mistral-large2": "2 2 6",
1508
1530
  "mistral-medium": "0.4 0.4 2",
1509
1531
  "mistral-medium-2505": "0.4 0.4 2",
1510
1532
  "mistral-medium-2508": "0.4 0.4 2",
@@ -1514,31 +1536,31 @@
1514
1536
  "mistral-medium-3-5@eu": "1.65 1.65 8.25",
1515
1537
  "mistral-medium-3.1": "0.4 0.047508 2",
1516
1538
  "mistral-medium-3.5": "1.5 0.1569 7.5",
1517
- "mistral-medium-3.5-128b": "1.725 1.725 7.5",
1539
+ "mistral-medium-3.5-128b": "1.725 1.725 8.41125",
1518
1540
  "mistral-medium-3.5:thinking": "1.5 0.75 7.5",
1519
- "mistral-medium-latest": "1.5 0.4 7.5",
1541
+ "mistral-medium-latest": "1.5 0.15 7.5",
1520
1542
  "mistral-medium-latest@eu": "0.44 0.44 2.2",
1521
1543
  "mistral-nemo": "0.15 0.15 0.15",
1522
1544
  "mistral-nemo-12b-instruct": "0.038 0.038 0.1",
1523
- "mistral-nemo-instruct-2407": "0.1003 0.02 0.1207",
1545
+ "mistral-nemo-instruct-2407": "0.1003 0.0257 0.1207",
1524
1546
  "mistral-nemo-instruct-2407-tee": "0.0245 0.00245 0.0978",
1525
1547
  "mistral-saba": "0.2 0.023754 0.6",
1526
1548
  "mistral-small": "0.1125 0.045 0.4",
1527
1549
  "mistral-small-24b-instruct-2501": "0.05 0.05 0.08",
1528
1550
  "mistral-small-2503": "0.1 0.1 0.3",
1529
1551
  "mistral-small-2506": "0.1 0.1 0.3",
1530
- "mistral-small-2603": "0.15 0.020631 0.6",
1552
+ "mistral-small-2603": "0.15 0.016 0.6",
1531
1553
  "mistral-small-2603@eu": "0.165 0.165 0.66",
1532
1554
  "mistral-small-3-1-24b-instruct-2503": "0.106 0.106 0.318",
1533
1555
  "mistral-small-3-2-24b-instruct": "0.09375 0.09375 0.25",
1534
1556
  "mistral-small-3.1-24b-instruct": "0.351 0.351 0.555",
1535
1557
  "mistral-small-3.2-24b-instruct": "0.101578 0.096875 0.28754",
1536
- "mistral-small-3.2-24b-instruct-2506": "0.15 0.15 0.33",
1558
+ "mistral-small-3.2-24b-instruct-2506": "0.168225 0.168225 0.33645",
1537
1559
  "mistral-small-4": "0.15 0.15 0.6",
1538
- "mistral-small-4-119b": "0.75 0.75 3",
1560
+ "mistral-small-4-119b": "0.56075 0.56075 2.35515",
1539
1561
  "mistral-small-4-119b-2603": "0.25 0.2 0.93",
1540
1562
  "mistral-small-4-119b-2603:thinking": "0.4 0.2 1.4",
1541
- "mistral-small-latest": "0.15 0.0825 0.6",
1563
+ "mistral-small-latest": "0.15 0.015 0.6",
1542
1564
  "mistral.devstral-2-123b": "0.4 0.4 2",
1543
1565
  "mistral.magistral-small-2509": "0.5 0.5 1.5",
1544
1566
  "mistral.ministral-3-14b-instruct": "0.2 0.2 0.2",
@@ -1551,12 +1573,12 @@
1551
1573
  "mistral.voxtral-mini-3b-2507@us": "0.04 0.04 0.04",
1552
1574
  "mistral.voxtral-small-24b-2507": "0.1 0.1 0.3",
1553
1575
  "mistral.voxtral-small-24b-2507@us": "0.1 0.1 0.3",
1554
- "mistral4-119b": "0.2 0.2 0.6",
1555
- "mistralai--mistral-medium-instruct": "0.36 0.36 1.22",
1556
- "mistralai--mistral-small": "0.07 0.07 0.28",
1576
+ "mistral4-119b": "0.2243 0.2243 0.6729",
1577
+ "mistralai--mistral-medium-instruct": "0.4 0.4 2",
1578
+ "mistralai--mistral-small": "0.15 0.15 0.6",
1557
1579
  "mixtral-8x22b-instruct": "2.1 0.23754 6.3",
1558
1580
  "mixtral-8x22b-instruct-v0.1": "2 0.2 6",
1559
- "mixtral-8x7b-instruct-v0.1": "0.488 0.488 0.758",
1581
+ "mixtral-8x7b-instruct-v0.1": "0.444 0.444 0.579",
1560
1582
  "mm-poly-8b": "0.658 0.658 1.11",
1561
1583
  "mn-12b-mag-mell-r1": "0.493 0.2465 0.493",
1562
1584
  "mn-loosecannon-12b-v1": "0.493 0.2465 0.493",
@@ -1590,7 +1612,7 @@
1590
1612
  "mythomax-l2-13b": "0.09515 0.085 0.11",
1591
1613
  "namazu": "0.95 0.15 4",
1592
1614
  "nano-banana": "0.21 0.021 1.8",
1593
- "nano-banana-pro": "2 0.2 12",
1615
+ "nano-banana-pro": "2.0202 0.202 12.1212",
1594
1616
  "nemomix-unleashed-12b": "0.493 0.2465 0.493",
1595
1617
  "nemotron-120b-a12b": "0.3 0.06 0.75",
1596
1618
  "nemotron-3-120b-a12b": "0.5 0.5 1.5",
@@ -1602,16 +1624,17 @@
1602
1624
  "nemotron-3-nano-omni@eu": "0.06 0.06 0.24",
1603
1625
  "nemotron-3-nano:30b": "0.06 0.06 0.24",
1604
1626
  "nemotron-3-super": "0.015 0.015 0.6",
1605
- "nemotron-3-super-120b-a12b": "0.2 0.15 0.775",
1627
+ "nemotron-3-super-120b-a12b": "0.15 0.15 0.65",
1606
1628
  "nemotron-3-super-120b-a12b:thinking": "0.05 0.025 0.25",
1607
1629
  "nemotron-3-ultra": "0.1 0.1 1.55",
1608
1630
  "nemotron-3-ultra-550b": "0.5 0.1 2.2",
1609
- "nemotron-3-ultra-550b-a55b": "0.6 0.135 2.45",
1631
+ "nemotron-3-ultra-550b-a55b": "0.6 0.12 2.45",
1610
1632
  "nemotron-3-ultra-550b-a55b:thinking": "0.5 0.25 2.5",
1611
1633
  "nemotron-3-ultra-nvfp4": "0.6 0.12 2.4",
1612
1634
  "nemotron-3.5-content-safety": "0.125 0.125 0.175",
1613
1635
  "nemotron-3.5-lightning": "0.05 0.0125 0.2",
1614
1636
  "nemotron-3.5-lightning:thinking": "0.05 0.01 0.2",
1637
+ "nemotron-3.5-super-120b-a12b": "0.2 0.04 0.5",
1615
1638
  "nemotron-3.5-super-vl": "0.175 0.05 0.5",
1616
1639
  "nemotron-3_5-lightning": "0.06 0.06 0.24",
1617
1640
  "nemotron-lightning-3.5-30b-a3b": "0.05 0.01 0.2",
@@ -1638,22 +1661,27 @@
1638
1661
  "nova-premier-v1": "2.5 0.625 12.5",
1639
1662
  "nova-pro": "0.8 0.2 3.2",
1640
1663
  "nova-pro-v1": "0.8 0.8 3.2",
1641
- "nvidia--llama-3.2-nv-embedqa-1b": "0.07 0.07 0",
1642
1664
  "nvidia-nemotron-3-5-super-vl-120b-a12b": "0.25 0.125 1.25",
1643
1665
  "nvidia-nemotron-3-nano-30b-a3b": "0.06 0.06 0.24",
1644
- "nvidia-nemotron-3-nano-30b-a3b-bf16": "0.05 0.05 0.2",
1666
+ "nvidia-nemotron-3-nano-30b-a3b-bf16": "0.1225 0.0445 0.3475",
1645
1667
  "nvidia-nemotron-3-nano-30b-a3b-fp8": "0.06 0.06 0.25",
1646
1668
  "nvidia-nemotron-3-super-120b": "0.3 0.06 0.65",
1647
1669
  "nvidia-nemotron-3-super-120b-a12b": "0.2 0.125 1.45",
1670
+ "nvidia-nemotron-3-super-120b-a12b-bf16": "0.57 0.114 1.44",
1671
+ "nvidia-nemotron-3-super-120b-a12b-bf16:peft:262144": "0.57 0.114 1.44",
1648
1672
  "nvidia-nemotron-3-super-120b-a12b-fp8": "0.09 0.09 0.45",
1649
- "nvidia-nemotron-3-super-120b-a12b-nvfp4": "0.3 0.3 1",
1673
+ "nvidia-nemotron-3-super-120b-a12b-nvfp4": "0.3 0.06 1",
1650
1674
  "nvidia-nemotron-3-ultra": "0.5 0.5 2.5",
1651
1675
  "nvidia-nemotron-3-ultra-550b-a55b": "0.6 0.12 2.4",
1652
- "nvidia-nemotron-3-ultra-550b-a55b-bf16": "0.5 0.15 2.5",
1676
+ "nvidia-nemotron-3-ultra-550b-a55b-bf16": "1.15 0.255 4.3625",
1677
+ "nvidia-nemotron-3-ultra-550b-a55b-bf16:peft:262144": "1.8 0.36 6.225",
1653
1678
  "nvidia-nemotron-3.5-lightning-30b-a3b": "0.07 0.04 0.2",
1654
- "nvidia-nemotron-3.5-lightning-30b-a3b-bf16": "0.06 0.0225 0.175",
1679
+ "nvidia-nemotron-3.5-lightning-30b-a3b-bf16": "0.07 0.035 0.2",
1680
+ "nvidia-nemotron-3.5-lightning-30b-a3b-bf16:peft:262144": "0.184 0.0368 0.495",
1655
1681
  "nvidia-nemotron-3.5-super-vl": "0.15 0.02 0.5",
1656
1682
  "nvidia-nemotron-3.5-super-vl-120b-a12b": "0.15 0.02 0.5",
1683
+ "nvidia-nemotron-3.5-super-vl-120b-a12b-bf16": "0.57 0.114 1.44",
1684
+ "nvidia-nemotron-3.5-super-vl-120b-a12b-bf16:peft:262144": "0.57 0.114 1.44",
1657
1685
  "nvidia-nemotron-3.5-super-vl-120b-a12b-nvfp4": "0.08 0.04 0.45",
1658
1686
  "nvidia.nemotron-nano-12b-v2": "0.2 0.2 0.6",
1659
1687
  "nvidia.nemotron-nano-3-30b": "0.06 0.06 0.24",
@@ -1682,11 +1710,12 @@
1682
1710
  "openai-gpt-4o-2024-11-20": "2.5 1.25 10",
1683
1711
  "openai-gpt-4o-mini": "0.15 0.075 0.6",
1684
1712
  "openai-gpt-4o-mini-2024-07-18": "0.15 0.075 0.6",
1685
- "openai-gpt-5": "1.25 0.125 10",
1686
- "openai-gpt-5-mini": "0.25 0.025 2",
1687
- "openai-gpt-5-nano": "0.05 0.005 0.4",
1713
+ "openai-gpt-5": "1.25 0.1275 10",
1714
+ "openai-gpt-5-mini": "0.25 0.0275 2",
1715
+ "openai-gpt-5-nano": "0.055 0.0075 0.42",
1716
+ "openai-gpt-5.1": "1.25 0.13 10",
1688
1717
  "openai-gpt-5.1-codex-max": "1.25 0.125 10",
1689
- "openai-gpt-5.2": "1.75 0.175 14",
1718
+ "openai-gpt-5.2": "1.75 0.1775 14",
1690
1719
  "openai-gpt-5.2-pro": "21 21 168",
1691
1720
  "openai-gpt-5.3-codex": "1.75 0.175 14",
1692
1721
  "openai-gpt-5.4": "2.5 0.25 15",
@@ -1743,6 +1772,7 @@
1743
1772
  "openai.gpt-oss-safeguard-20b@us": "0.07 0.07 0.2",
1744
1773
  "openreasoning-nemotron-32b": "0.1 0.05 0.4",
1745
1774
  "orion-26b-a4b-v1.1": "0.1 0.05 0.45",
1775
+ "ornith-1.5-122b": "0.2 0.05 0.8",
1746
1776
  "ornith-1.5-35b-a3b": "0.1 0.03 0.4",
1747
1777
  "ornith-1.5-35b-a3b:thinking": "0.1 0.05 0.4",
1748
1778
  "osmosis-structure-0.6b": "0.1 0.1 0.5",
@@ -1764,7 +1794,7 @@
1764
1794
  "phi-4-reasoning": "0.125 0.125 0.5",
1765
1795
  "phi-4-reasoning-plus": "0.125 0.125 0.5",
1766
1796
  "pixtral-12b": "0.15 0.15 0.15",
1767
- "pixtral-12b-2409": "0.223 0.223 0.223",
1797
+ "pixtral-12b-2409": "0.2175 0.2175 0.2175",
1768
1798
  "pixtral-large-2502": "1.993 1.993 5.978",
1769
1799
  "pixtral-large-latest": "2 2 6",
1770
1800
  "pokee-isaac": "0.15 0.075 1",
@@ -1797,6 +1827,7 @@
1797
1827
  "qwen-math-plus": "0.574 0.574 1.721",
1798
1828
  "qwen-math-turbo": "0.287 0.287 0.861",
1799
1829
  "qwen-max": "1.6 0.416 6.4",
1830
+ "qwen-max-2025-01-25": "0.347826 0.347826 1.391304",
1800
1831
  "qwen-max-latest": "2 0.25 6",
1801
1832
  "qwen-mt-plus": "1.3595 1.3595 4.0725",
1802
1833
  "qwen-mt-turbo": "0.1305 0.1305 0.385",
@@ -1806,8 +1837,9 @@
1806
1837
  "qwen-plus-character": "0.115 0.115 0.287",
1807
1838
  "qwen-plus-character-ja": "0.5 0.5 1.4",
1808
1839
  "qwen-plus-latest": "0.4 0.08 1.2",
1809
- "qwen-turbo": "0.04998 0.02499 0.09",
1840
+ "qwen-turbo": "0.04699 0.034234 0.09",
1810
1841
  "qwen-vl-max": "0.23 0.138 0.58",
1842
+ "qwen-vl-max-2025-01-25": "0.434783 0.434783 1.304348",
1811
1843
  "qwen-vl-ocr": "0.0565 0.0565 0.116",
1812
1844
  "qwen-vl-plus": "0.1625 0.1625 0.4585",
1813
1845
  "qwen.qwen3-235b-a22b-2507-v1:0": "0.22 0.22 0.88",
@@ -1830,29 +1862,29 @@
1830
1862
  "qwen2-5-vl-7b-instruct": "0.3185 0.3185 0.8835",
1831
1863
  "qwen2.5-32b-instruct-abliterated": "0.7 0.35 0.7",
1832
1864
  "qwen2.5-72b-instruct": "0.59 0.59 0.59",
1833
- "qwen2.5-7b-instruct": "0.05 0.05 0.05",
1865
+ "qwen2.5-7b-instruct": "0.045 0.045 0.075",
1834
1866
  "qwen2.5-7b-instruct-turbo": "0.3 0.3 0.3",
1835
1867
  "qwen2.5-coder-0.5b": "0.1 0.1 0.1",
1836
1868
  "qwen2.5-coder-32b-instruct": "0.4303 0.38015 0.6003",
1837
1869
  "qwen2.5-coder-7b-fast": "0.03 0.03 0.09",
1838
1870
  "qwen2.5-vl-32b-instruct": "0.125 0.1125 0.41",
1839
- "qwen2.5-vl-72b-instruct": "0.8 0.4 1",
1871
+ "qwen2.5-vl-72b-instruct": "0.905 0.705 1.005",
1840
1872
  "qwen3-1.7b-base": "0.1 0.1 0.1",
1841
- "qwen3-14b": "0.12 0.12 0.28",
1842
- "qwen3-235b-a22b": "0.287 0.2435 1.147",
1873
+ "qwen3-14b": "0.08 0.076 0.24",
1874
+ "qwen3-235b-a22b": "0.287 0.287 1.147",
1843
1875
  "qwen3-235b-a22b-2507": "0.09 0.09 0.55",
1844
1876
  "qwen3-235b-a22b-fp8": "0.2 0.2 0.8",
1845
- "qwen3-235b-a22b-instruct-2507": "0.2 0.15 0.6",
1877
+ "qwen3-235b-a22b-instruct-2507": "0.2 0.175 0.675",
1846
1878
  "qwen3-235b-a22b-instruct-2507-maas": "0.22 0.22 0.88",
1847
1879
  "qwen3-235b-a22b-instruct-2507-tput": "0.2 0.2 0.6",
1848
1880
  "qwen3-235b-a22b-thinking": "0.3 0.3 2.9",
1849
1881
  "qwen3-235b-a22b-thinking-2507": "0.3 0.3 3",
1850
1882
  "qwen3-235b-a22b-thinking-2507-tee": "0.2989 0.02989 1.1957",
1851
- "qwen3-30b-a3b": "0.115 0.115 0.5",
1883
+ "qwen3-30b-a3b": "0.108696 0.108696 0.5",
1852
1884
  "qwen3-30b-a3b-fp8": "0.07045 0.07045 0.3925",
1853
- "qwen3-30b-a3b-instruct-2507": "0.09 0.09 0.3",
1854
- "qwen3-30b-a3b-thinking-2507": "0.36 0.36 1.3",
1855
- "qwen3-32b": "0.1645 0.1645 0.59",
1885
+ "qwen3-30b-a3b-instruct-2507": "0.1 0.1 0.3",
1886
+ "qwen3-30b-a3b-thinking-2507": "0.234348 0.234348 1.193478",
1887
+ "qwen3-32b": "0.179 0.179 0.59779",
1856
1888
  "qwen3-32b-fp8": "0.1 0.1 0.45",
1857
1889
  "qwen3-32b-tee": "0.104 0.0104 0.416",
1858
1890
  "qwen3-4b-base": "0.15 0.15 0.15",
@@ -1872,37 +1904,36 @@
1872
1904
  "qwen3-6-plus": "0.5 0.5 3",
1873
1905
  "qwen3-7-flash": "0.03 0.006 0.13",
1874
1906
  "qwen3-7-max": "2.5 2.5 7.5",
1875
- "qwen3-7-plus": "0.4 0.4 1.6",
1907
+ "qwen3-7-plus": "0.391429 0.237143 1.542857",
1876
1908
  "qwen3-8-27b": "0.17 0.08 0.5",
1877
1909
  "qwen3-8-flash": "0.16 0.16 0.47",
1878
- "qwen3-8-max": "2 2 6",
1910
+ "qwen3-8-max": "2.2 1.148571 6.428571",
1879
1911
  "qwen3-8-max-0902": "2 2 6",
1880
1912
  "qwen3-8-omni-flash": "0.3 0.3 0.94",
1881
- "qwen3-8b": "0.126 0.126 0.2435",
1882
- "qwen3-asr-flash": "0.0335 0.0335 0.0335",
1913
+ "qwen3-8b": "0.18 0.072 0.287",
1883
1914
  "qwen3-coder": "0.3 0.1 1",
1884
1915
  "qwen3-coder-30b-a3b": "0.15 0.15 0.6",
1885
- "qwen3-coder-30b-a3b-instruct": "0.1 0.07 0.3",
1886
- "qwen3-coder-480b-a35b-instruct": "0.38 0.38 1.6",
1916
+ "qwen3-coder-30b-a3b-instruct": "0.1 0.07 0.4",
1917
+ "qwen3-coder-480b-a35b-instruct": "0.39 0.39 1.7",
1887
1918
  "qwen3-coder-480b-a35b-instruct-fp8": "1.1 1.1 1.4",
1888
- "qwen3-coder-480b-a35b-instruct-int4-mixed-ar": "0.22 0.11 0.95",
1919
+ "qwen3-coder-480b-a35b-instruct-int4-mixed-ar": "0.46125 0.230625 2.29375",
1889
1920
  "qwen3-coder-480b-a35b-instruct-turbo": "0.325 0.07 1.25",
1890
1921
  "qwen3-coder-flash": "0.3 0.06 1.5",
1891
- "qwen3-coder-next": "0.2 0.184113 1.0486",
1922
+ "qwen3-coder-next": "0.2 0.184255 1.04936",
1892
1923
  "qwen3-coder-next-fp8": "0.5 0.5 1.2",
1893
1924
  "qwen3-coder-plus": "1 0.2 5",
1894
1925
  "qwen3-embedding-0.6b": "0.025 0.025 0.005",
1895
1926
  "qwen3-embedding-4b": "0.01 0.01 0",
1896
1927
  "qwen3-embedding-8b": "0.085 0.085 0",
1897
1928
  "qwen3-livetranslate-flash-realtime": "10 10 10",
1898
- "qwen3-max": "1.0225 0.4795 4.69",
1929
+ "qwen3-max": "0.869565 0.6 3.478261",
1899
1930
  "qwen3-max-2025-09-23": "0.86 0.86 3.43",
1900
1931
  "qwen3-max-2026-01-23": "1.2002 0.6001 6.001",
1901
- "qwen3-max-preview": "1.08 1.08 4.8",
1932
+ "qwen3-max-preview": "0.974783 0.974783 4.13913",
1902
1933
  "qwen3-max-thinking": "1.2 0.24 6",
1903
1934
  "qwen3-next-80b": "0.35 0.35 1.9",
1904
- "qwen3-next-80b-a3b-instruct": "0.147 0.147 1.15",
1905
- "qwen3-next-80b-a3b-thinking": "0.15 0.15 1.317",
1935
+ "qwen3-next-80b-a3b-instruct": "0.144928 0.144928 1.2",
1936
+ "qwen3-next-80b-a3b-thinking": "0.15 0.15 1.434",
1906
1937
  "qwen3-omni-30b-a3b-thinking": "0.25 0.25 0.97",
1907
1938
  "qwen3-omni-flash": "0.344 0.344 1.3245",
1908
1939
  "qwen3-omni-flash-realtime": "0.375 0.375 1.454",
@@ -1917,15 +1948,15 @@
1917
1948
  "qwen3-vl-30b-a3b": "0.154 0.154 0.6155",
1918
1949
  "qwen3-vl-30b-a3b-instruct": "0.15 0.15 0.6",
1919
1950
  "qwen3-vl-30b-a3b-thinking": "0.29 0.29 1",
1920
- "qwen3-vl-32b-instruct": "0.2 0.2 0.6",
1921
- "qwen3-vl-32b-thinking": "0.2 0.2 1.5",
1922
- "qwen3-vl-8b-instruct": "0.215 0.15 0.715",
1923
- "qwen3-vl-embedding-8b": "0.09 0.09 0.09",
1951
+ "qwen3-vl-32b-instruct": "0.174724 0.174724 0.598895",
1952
+ "qwen3-vl-32b-thinking": "0.174724 0.174724 1.497237",
1953
+ "qwen3-vl-8b-instruct": "0.215 0.12 0.715",
1954
+ "qwen3-vl-embedding-8b": "0.09 0.09 0",
1924
1955
  "qwen3-vl-flash": "0.022 0.0044 0.215",
1925
1956
  "qwen3-vl-instruct": "0.2 0.11 0.88",
1926
1957
  "qwen3-vl-plus": "0.2 0.04 1.6",
1927
- "qwen3.5-122b": "0.9 0.9 3.6",
1928
- "qwen3.5-122b-a10b": "0.29 0.29 2.36",
1958
+ "qwen3.5-122b": "1.1215 1.1215 4.7103",
1959
+ "qwen3.5-122b-a10b": "0.345 0.29 2.8",
1929
1960
  "qwen3.5-122b-a10b-fp8": "0.5 0.5 3.97",
1930
1961
  "qwen3.5-122b-a10b:thinking": "0.26 0.103788 2.08",
1931
1962
  "qwen3.5-27b": "0.28 0.265 2.28",
@@ -1933,45 +1964,51 @@
1933
1964
  "qwen3.5-27b-queen-derestricted": "0.306 0.153 0.306",
1934
1965
  "qwen3.5-27b:thinking": "0.25 0.135 2",
1935
1966
  "qwen3.5-2b": "0.02 0.02 0.1",
1936
- "qwen3.5-35b-a3b": "0.235 0.235 1.55",
1967
+ "qwen3.5-35b-a3b": "0.20125 0.15625 1.3",
1968
+ "qwen3.5-35b-a3b-base": "0.54 0.108 1.335",
1937
1969
  "qwen3.5-35b-a3b:thinking": "0.14 0.05 1",
1938
1970
  "qwen3.5-397b-a17b": "0.55 0.39 3.5",
1939
1971
  "qwen3.5-397b-a17b-fp8": "0.99 0.99 4.46",
1940
1972
  "qwen3.5-397b-a17b-tee": "0.45 0.045 3",
1973
+ "qwen3.5-397b-a17b:peft:262144": "1.65 0.33 7.5",
1941
1974
  "qwen3.5-397b-a17b:thinking": "0.39 0.3 2.34",
1942
- "qwen3.5-9b": "0.1055 0.1 0.1735",
1975
+ "qwen3.5-4b": "0.185 0.053 0.5375",
1976
+ "qwen3.5-4b:peft:262144": "0.33 0.066 1.005",
1977
+ "qwen3.5-9b": "0.1 0.1 0.18",
1978
+ "qwen3.5-9b-base": "0.3 0.06 0.807",
1943
1979
  "qwen3.5-flash": "0.1 0.01 0.4",
1944
1980
  "qwen3.5-flash-02-23": "0.065 0.065 0.26",
1945
1981
  "qwen3.5-flash:thinking": "0.1 0.05 0.4",
1946
- "qwen3.5-plus": "0.4 0.0775 2.4",
1982
+ "qwen3.5-plus": "0.4 0.06 2.4",
1947
1983
  "qwen3.5-plus-02-15": "0.26 0.26 1.56",
1948
1984
  "qwen3.5-plus-20260420": "0.3 0.3 1.8",
1949
1985
  "qwen3.5-plus:thinking": "0.4 0.04 2.4",
1950
1986
  "qwen3.5:397b": "0.6 0.6 3.6",
1951
1987
  "qwen3.6": "0.04 0.02 0.35",
1952
- "qwen3.6-27b": "0.448 0.438 3.19",
1988
+ "qwen3.6-27b": "0.446 0.4126 3.19",
1953
1989
  "qwen3.6-27b-tee": "0.25 0.025 2",
1954
1990
  "qwen3.6-27b:thinking": "0.203 0.1015 2.24",
1955
- "qwen3.6-35b": "0.22 0.0895 0.825",
1956
- "qwen3.6-35b-a3b": "0.239 0.215 1.4325",
1991
+ "qwen3.6-35b": "0.229112 0.098613 0.855375",
1992
+ "qwen3.6-35b-a3b": "0.248 0.19 1.38",
1957
1993
  "qwen3.6-35b-a3b-fp8": "0.17 0.056 1.1",
1994
+ "qwen3.6-35b-a3b:peft:262144": "0.45 0.09 1.335",
1958
1995
  "qwen3.6-35b-a3b:thinking": "0.112 0.056 0.8",
1959
1996
  "qwen3.6-35b-fast": "0.29 0.029 1.15",
1960
1997
  "qwen3.6-35b-flex": "0.1885 0.01885 0.7475",
1961
- "qwen3.6-flash": "0.19 0.04375 1.1465",
1998
+ "qwen3.6-flash": "0.19 0.03125 1.145",
1962
1999
  "qwen3.6-max-preview": "1.305 0.2 7.84",
1963
- "qwen3.6-plus": "0.5 0.05 3",
2000
+ "qwen3.6-plus": "0.4125 0.05 2.475",
1964
2001
  "qwen3.7-flash": "0.03 0.006 0.13",
1965
2002
  "qwen3.7-flash:thinking": "0.03 0.006 0.13",
1966
2003
  "qwen3.7-max": "1.8 0.295 5.3",
1967
2004
  "qwen3.7-max-2026-06-08": "1.8 1.8 5.3",
1968
2005
  "qwen3.7-max:thinking": "1.475 0.295 4.425",
1969
- "qwen3.7-plus": "0.4 0.0755 1.6",
2006
+ "qwen3.7-plus": "0.4 0.0675 1.6",
1970
2007
  "qwen3.7-plus:thinking": "0.4 0.08 1.6",
1971
2008
  "qwen3.8-2.4t-a95b": "2 0.25 6",
1972
2009
  "qwen3.8-2.4t-a95b-nvfp4": "2 0.2 6",
1973
2010
  "qwen3.8-2.4t-a95b@eu": "2.5 0.63 6",
1974
- "qwen3.8-27b": "0.41 0.1 3",
2011
+ "qwen3.8-27b": "0.42 0.1 3",
1975
2012
  "qwen3.8-27b-antislop": "0.1 0.05 0.6",
1976
2013
  "qwen3.8-27b-cybersecurity": "0.1 0.05 0.6",
1977
2014
  "qwen3.8-27b-darkidol": "0.1 0.05 0.6",
@@ -1993,6 +2030,7 @@
1993
2030
  "qwen3.8-27b-uncensored": "1 0.22 3",
1994
2031
  "qwen3.8-27b-uncensored-fast": "1 0.22 3",
1995
2032
  "qwen3.8-27b-uncensored:thinking": "1 0.22 3",
2033
+ "qwen3.8-27b:peft:262144": "0.6975 0.1395 5.595",
1996
2034
  "qwen3.8-27b:thinking": "0.15 0.04 0.7",
1997
2035
  "qwen3.8-flash": "0.15 0.016 0.47",
1998
2036
  "qwen3.8-flash-next": "0.2 0.05 0.5",
@@ -2010,6 +2048,7 @@
2010
2048
  "qwerky-72b": "0.5 0.25 0.5",
2011
2049
  "qwq-32b": "0.4 0.4 0.861",
2012
2050
  "qwq-plus": "0.515 0.515 1.487",
2051
+ "reflection-beam": "0.4 0.04 1.2",
2013
2052
  "reka-edge": "0.1 0.1 0.1",
2014
2053
  "reka-edge-2603": "0.1 0.1 0.1",
2015
2054
  "reka-flash-3": "0.1 0.1 0.2",
@@ -2017,17 +2056,17 @@
2017
2056
  "relace-search": "1 1 3",
2018
2057
  "remm-slerp-l2-13b": "0.51885 0.37475 0.840775",
2019
2058
  "ring-1t": "0.565 0.34 2.265",
2020
- "ring-2.6-1t": "0.3 0.18 2.5",
2059
+ "ring-2.6-1t": "0.215908 0.163182 1.799231",
2021
2060
  "rnj-1-instruct": "0.15 0.15 0.15",
2022
2061
  "roc": "2.875 2.875 11.516",
2023
2062
  "rocinante-12b-v1.1": "0.408 0.204 0.595",
2024
- "route-llm": "3 3 15",
2063
+ "route-llm": "2 0.1 10",
2025
2064
  "sakana-namazu": "0.95 0.15 4",
2026
- "sap-abap-1": "0.48 0.48 1.7",
2027
- "sarvam-105b": "0.047 0.0368 0.1862",
2065
+ "sarvam-105b": "0.054 0.0336 0.2124",
2028
2066
  "sarvam-30b": "0.02 0.02 0.1",
2029
2067
  "scaledown-extract-1": "0.05 0.05 0",
2030
2068
  "scaledown-summarize-1": "0.05 0.05 0",
2069
+ "schattenblume-31b": "0.1 0.05 0.45",
2031
2070
  "schematron-v2-small": "0.05 0.05 0.23",
2032
2071
  "schematron-v2-turbo": "0.03 0.03 0.15",
2033
2072
  "seed-1-6-250615": "0.25 0.05 2",
@@ -2051,9 +2090,10 @@
2051
2090
  "seed-2.0-mini": "0.1 0.06 0.4",
2052
2091
  "seed-2.0-pro": "0.5 0.1 3",
2053
2092
  "seed-2.1-turbo": "0.5 0.1 2.5",
2054
- "seed-oss-36b-instruct": "0.21 0.21 0.57",
2093
+ "seed-oss-36b-instruct": "0.217086 0.217086 0.583895",
2055
2094
  "shisa-v2-llama3.3-70b": "0.5 0.25 0.5",
2056
2095
  "shisa-v2.1-llama3.3-70b": "0.5 0.25 0.5",
2096
+ "skyfall-31b-v4.2": "0.12 0.06 0.15",
2057
2097
  "skyfall-36b-v2": "0.55 0.25 0.8",
2058
2098
  "small": "0.0255 0.0025 0.2005",
2059
2099
  "smollm3-3b-base": "0.15 0.15 0.15",
@@ -2061,9 +2101,9 @@
2061
2101
  "solar-mini4": "0.075 0.0075 0.3",
2062
2102
  "solar-mini4:thinking": "0.05 0.005 0.2",
2063
2103
  "solar-pro-3": "0.15 0.015 0.6",
2064
- "solar-pro2": "0.2 0.2 0.425",
2065
- "solar-pro3": "0.2 0.2 0.425",
2066
- "solar-pro4": "0.095631 0.03 0.382524",
2104
+ "solar-pro2": "0.2 0.1325 0.425",
2105
+ "solar-pro3": "0.2 0.1325 0.425",
2106
+ "solar-pro4": "0.15 0.03 0.6",
2067
2107
  "solar-pro4:thinking": "0.03 0.006 0.12",
2068
2108
  "sonar": "1 1 1",
2069
2109
  "sonar-deep-research": "2 2 8",
@@ -2078,12 +2118,12 @@
2078
2118
  "step-3": "0.21 0.21 0.57",
2079
2119
  "step-3-5-flash": "0.1 0.02 0.3",
2080
2120
  "step-3-5-flash-2603": "0.1 0.02 0.3",
2081
- "step-3-7-flash": "0.2 0.04 1.15",
2121
+ "step-3-7-flash": "0.22 0.044 1.260714",
2082
2122
  "step-3.5-flash": "0.1 0.1 0.3",
2083
- "step-3.5-flash-2603": "0.1 0.02 0.3",
2123
+ "step-3.5-flash-2603": "0.1 0.02092 0.3",
2084
2124
  "step-3.7-flash": "0.2 0.04 1.15",
2085
2125
  "step-3.7-flash:thinking": "0.2 0.04 1.15",
2086
- "step-5-preview": "1 0.061385 2.7",
2126
+ "step-5-preview": "1 0.1 2.7",
2087
2127
  "summarize": "0.045 0.045 0",
2088
2128
  "ternary-bonsai-2-27b": "0.075 0.0375 0.5",
2089
2129
  "text-embedding-3-large": "0.13 0.13 0",
@@ -2098,6 +2138,7 @@
2098
2138
  "umans-coder": "0.15 0.03 0.5",
2099
2139
  "umans-deepseek-v4-flash-0731": "0.14 0.028 0.28",
2100
2140
  "umans-deepseek-v4.1-flash": "0.15 0.028 0.6",
2141
+ "umans-deepseek-v4.1-flash-1017": "0.15 0.028 0.6",
2101
2142
  "umans-flash": "0.15 0.05 1",
2102
2143
  "umans-glm-5.3": "1.4 0.26 4.4",
2103
2144
  "umans-glm-5.3-flash": "0.15 0.03 0.5",
@@ -2157,12 +2198,12 @@
2157
2198
  "vision-small": "1.05 1.05 3.16",
2158
2199
  "viv-fast": "0.13 0.05 0.4",
2159
2200
  "voxtral-mini-3b": "0.00462 0.00462 0",
2160
- "voxtral-small-24b-2507": "0.1 0.01 0.3",
2201
+ "voxtral-small-24b-2507": "0.11877 0.011877 0.35631",
2161
2202
  "voxtral-small-2507": "0.1115 0.056 0.384",
2162
- "voxtral-small-latest": "0.1 0.1 0.35",
2203
+ "voxtral-small-latest": "0.1 0.1 0.4",
2163
2204
  "wayfarer-large-70b-llama-3.3": "0.7 0.35 0.7",
2164
2205
  "weaver": "0.4 0.4 0.75",
2165
- "whisper-large-v3": "0.0065 0.0065 0.00115",
2206
+ "whisper-large-v3": "0.01 0.01 0.0023",
2166
2207
  "whisper-large-v3-turbo": "0.0023 0.0023 0.0023",
2167
2208
  "wizardlm-2-8x22b": "0.493 0.48 0.493",
2168
2209
  "writer.palmyra-x4-v1:0": "2.5 2.5 10",