@grida/ai-models 2.20261119.0 → 2.20261119.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/models.json CHANGED
@@ -510,6 +510,46 @@
510
510
  "source_url": "https://ai-gateway.vercel.sh/v1/models",
511
511
  "context_tokens": 1000000,
512
512
  "max_output_tokens": 128000
513
+ },
514
+ "offerings": {
515
+ "anthropic/claude-fable-5.2-fast": {
516
+ "id": "anthropic/claude-fable-5.2-fast",
517
+ "canonical_model_id": "anthropic/claude-fable-5.2",
518
+ "mode": "fast",
519
+ "label": "Claude Fable 5.2 (Fast)",
520
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/anthropic/claude-fable-5.2-fast/endpoints",
521
+ "qualifications": [
522
+ {
523
+ "source_url": "https://vercel.com/docs/ai-gateway/models-and-providers/fast-mode",
524
+ "notes": "Vercel can serve the base route at Standard speed when Fast capacity is unavailable. Fast prices apply when the request was served Fast."
525
+ },
526
+ {
527
+ "source_url": "https://vercel.com/changelog/claude-fable-5-2-now-available-on-ai-gateway",
528
+ "notes": "Vercel documents 30-day retention for prompts and completions on Claude Fable 5.2."
529
+ }
530
+ ],
531
+ "limits": {
532
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/anthropic/claude-fable-5.2-fast/endpoints",
533
+ "context_tokens": 1000000,
534
+ "max_output_tokens": 128000
535
+ },
536
+ "capabilities": {
537
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/anthropic/claude-fable-5.2-fast/endpoints",
538
+ "image_input": true,
539
+ "tools": true,
540
+ "reasoning": true,
541
+ "structured_output": true
542
+ },
543
+ "token_pricing": {
544
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/anthropic/claude-fable-5.2-fast/endpoints",
545
+ "unit": "usd_per_token",
546
+ "scope": "Regular global token rates for requests served on the Vercel Fast endpoint. Optional tools and regional premiums are excluded.",
547
+ "input": "0.000016",
548
+ "output": "0.00008",
549
+ "input_cache_read": "0.0000004",
550
+ "input_cache_write": "0.00002"
551
+ }
552
+ }
513
553
  }
514
554
  },
515
555
  "anthropic": {
@@ -543,6 +583,39 @@
543
583
  "source_url": "https://platform.claude.com/docs/en/models/fable-5-2/overview",
544
584
  "context_tokens": 1000000,
545
585
  "max_output_tokens": 128000
586
+ },
587
+ "modes": {
588
+ "fast": {
589
+ "source_url": "https://platform.claude.com/docs/en/build-with-claude/fast-mode",
590
+ "request": {
591
+ "speed": "fast"
592
+ },
593
+ "qualifications": [
594
+ {
595
+ "source_url": "https://platform.claude.com/docs/en/models/fable-5-2/overview",
596
+ "notes": "Anthropic documents a 30-day data retention requirement for Claude Fable 5.2, subject to explicit authorization from Anthropic for zero data retention."
597
+ }
598
+ ],
599
+ "limits": {
600
+ "source_url": "https://platform.claude.com/docs/en/models/fable-5-2/overview",
601
+ "context_tokens": 1000000,
602
+ "max_output_tokens": 128000
603
+ },
604
+ "capabilities": {
605
+ "source_url": "https://platform.claude.com/docs/en/build-with-claude/fast-mode",
606
+ "streaming": true
607
+ },
608
+ "token_pricing": {
609
+ "source_url": "https://platform.claude.com/docs/en/about-claude/pricing",
610
+ "unit": "usd_per_token",
611
+ "scope": "Regular global Fast token rates across the full context window. Cache-write rates distinguish five-minute and one-hour retention.",
612
+ "input": "0.000016",
613
+ "output": "0.00008",
614
+ "input_cache_read": "0.0000004",
615
+ "input_cache_write": "0.00002",
616
+ "input_cache_write_1h": "0.000032"
617
+ }
618
+ }
546
619
  }
547
620
  },
548
621
  "openrouter": {
@@ -578,6 +651,46 @@
578
651
  "source_url": "https://openrouter.ai/api/v1/models",
579
652
  "context_tokens": 1000000,
580
653
  "max_output_tokens": 128000
654
+ },
655
+ "modes": {
656
+ "fast": {
657
+ "source_url": "https://openrouter.ai/api/v1/models/anthropic/claude-fable-5.2/endpoints",
658
+ "request": {
659
+ "service_tier": "fast",
660
+ "provider": {
661
+ "only": [
662
+ "anthropic/fast"
663
+ ]
664
+ }
665
+ },
666
+ "qualifications": [
667
+ {
668
+ "source_url": "https://openrouter.ai/docs/guides/features/service-tiers",
669
+ "notes": "The provider.only tag selects the anthropic/fast endpoint. OpenRouter reports the tier that actually served the request."
670
+ }
671
+ ],
672
+ "limits": {
673
+ "source_url": "https://openrouter.ai/api/v1/models/anthropic/claude-fable-5.2/endpoints",
674
+ "context_tokens": 1000000,
675
+ "max_output_tokens": 128000
676
+ },
677
+ "capabilities": {
678
+ "source_url": "https://openrouter.ai/api/v1/models/anthropic/claude-fable-5.2/endpoints",
679
+ "tools": true,
680
+ "reasoning": true,
681
+ "structured_output": true
682
+ },
683
+ "token_pricing": {
684
+ "source_url": "https://openrouter.ai/api/v1/models/anthropic/claude-fable-5.2/endpoints",
685
+ "unit": "usd_per_token",
686
+ "scope": "Regular token rates for requests served on the OpenRouter Fast endpoint. Optional tools and regional premiums are excluded. Cache-write rates distinguish five-minute and one-hour retention.",
687
+ "input": "0.000016",
688
+ "output": "0.00008",
689
+ "input_cache_read": "0.0000004",
690
+ "input_cache_write": "0.00002",
691
+ "input_cache_write_1h": "0.000032"
692
+ }
693
+ }
581
694
  }
582
695
  },
583
696
  "grida": {
@@ -1635,6 +1748,42 @@
1635
1748
  "source_url": "https://ai-gateway.vercel.sh/v1/models",
1636
1749
  "context_tokens": 1000000,
1637
1750
  "max_output_tokens": 128000
1751
+ },
1752
+ "offerings": {
1753
+ "anthropic/claude-opus-5.5-fast": {
1754
+ "id": "anthropic/claude-opus-5.5-fast",
1755
+ "canonical_model_id": "anthropic/claude-opus-5.5",
1756
+ "mode": "fast",
1757
+ "label": "Claude Opus 5.5 (Fast)",
1758
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/anthropic/claude-opus-5.5-fast/endpoints",
1759
+ "qualifications": [
1760
+ {
1761
+ "source_url": "https://vercel.com/docs/ai-gateway/models-and-providers/fast-mode",
1762
+ "notes": "Vercel can serve the base route at Standard speed when Fast capacity is unavailable. Fast prices apply when the request was served Fast."
1763
+ }
1764
+ ],
1765
+ "limits": {
1766
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/anthropic/claude-opus-5.5-fast/endpoints",
1767
+ "context_tokens": 1000000,
1768
+ "max_output_tokens": 128000
1769
+ },
1770
+ "capabilities": {
1771
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/anthropic/claude-opus-5.5-fast/endpoints",
1772
+ "image_input": true,
1773
+ "tools": true,
1774
+ "reasoning": true,
1775
+ "structured_output": true
1776
+ },
1777
+ "token_pricing": {
1778
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/anthropic/claude-opus-5.5-fast/endpoints",
1779
+ "unit": "usd_per_token",
1780
+ "scope": "Regular global token rates for requests served on the Vercel Fast endpoint. Optional tools and regional premiums are excluded.",
1781
+ "input": "0.000008",
1782
+ "output": "0.00004",
1783
+ "input_cache_read": "0.0000004",
1784
+ "input_cache_write": "0.00001"
1785
+ }
1786
+ }
1638
1787
  }
1639
1788
  },
1640
1789
  "anthropic": {
@@ -1668,6 +1817,33 @@
1668
1817
  "source_url": "https://platform.claude.com/docs/en/models/opus-5-5/overview",
1669
1818
  "context_tokens": 1000000,
1670
1819
  "max_output_tokens": 128000
1820
+ },
1821
+ "modes": {
1822
+ "fast": {
1823
+ "source_url": "https://platform.claude.com/docs/en/build-with-claude/fast-mode",
1824
+ "request": {
1825
+ "speed": "fast"
1826
+ },
1827
+ "limits": {
1828
+ "source_url": "https://platform.claude.com/docs/en/models/opus-5-5/overview",
1829
+ "context_tokens": 1000000,
1830
+ "max_output_tokens": 128000
1831
+ },
1832
+ "capabilities": {
1833
+ "source_url": "https://platform.claude.com/docs/en/build-with-claude/fast-mode",
1834
+ "streaming": true
1835
+ },
1836
+ "token_pricing": {
1837
+ "source_url": "https://platform.claude.com/docs/en/about-claude/pricing",
1838
+ "unit": "usd_per_token",
1839
+ "scope": "Regular global Fast token rates across the full context window. Cache-write rates distinguish five-minute and one-hour retention.",
1840
+ "input": "0.000008",
1841
+ "output": "0.00004",
1842
+ "input_cache_read": "0.0000004",
1843
+ "input_cache_write": "0.00001",
1844
+ "input_cache_write_1h": "0.000016"
1845
+ }
1846
+ }
1671
1847
  }
1672
1848
  },
1673
1849
  "openrouter": {
@@ -1703,6 +1879,46 @@
1703
1879
  "source_url": "https://openrouter.ai/api/v1/models",
1704
1880
  "context_tokens": 1000000,
1705
1881
  "max_output_tokens": 128000
1882
+ },
1883
+ "modes": {
1884
+ "fast": {
1885
+ "source_url": "https://openrouter.ai/api/v1/models/anthropic/claude-opus-5.5/endpoints",
1886
+ "request": {
1887
+ "service_tier": "fast",
1888
+ "provider": {
1889
+ "only": [
1890
+ "anthropic/fast"
1891
+ ]
1892
+ }
1893
+ },
1894
+ "qualifications": [
1895
+ {
1896
+ "source_url": "https://openrouter.ai/docs/guides/features/service-tiers",
1897
+ "notes": "The provider.only tag selects the anthropic/fast endpoint. OpenRouter reports the tier that actually served the request."
1898
+ }
1899
+ ],
1900
+ "limits": {
1901
+ "source_url": "https://openrouter.ai/api/v1/models/anthropic/claude-opus-5.5/endpoints",
1902
+ "context_tokens": 1000000,
1903
+ "max_output_tokens": 128000
1904
+ },
1905
+ "capabilities": {
1906
+ "source_url": "https://openrouter.ai/api/v1/models/anthropic/claude-opus-5.5/endpoints",
1907
+ "tools": true,
1908
+ "reasoning": true,
1909
+ "structured_output": true
1910
+ },
1911
+ "token_pricing": {
1912
+ "source_url": "https://openrouter.ai/api/v1/models/anthropic/claude-opus-5.5/endpoints",
1913
+ "unit": "usd_per_token",
1914
+ "scope": "Regular token rates for requests served on the OpenRouter Fast endpoint. Optional tools and regional premiums are excluded. Cache-write rates distinguish five-minute and one-hour retention.",
1915
+ "input": "0.000008",
1916
+ "output": "0.00004",
1917
+ "input_cache_read": "0.0000004",
1918
+ "input_cache_write": "0.00001",
1919
+ "input_cache_write_1h": "0.000016"
1920
+ }
1921
+ }
1706
1922
  }
1707
1923
  },
1708
1924
  "grida": {
@@ -3958,6 +4174,37 @@
3958
4174
  "source_url": "https://ai-gateway.vercel.sh/v1/models",
3959
4175
  "context_tokens": 1000000,
3960
4176
  "max_output_tokens": 128000
4177
+ },
4178
+ "offerings": {
4179
+ "openai/gpt-5.5-fast": {
4180
+ "id": "openai/gpt-5.5-fast",
4181
+ "canonical_model_id": "openai/gpt-5.5",
4182
+ "mode": "fast",
4183
+ "label": "GPT 5.5 (Fast)",
4184
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-5.5-fast/endpoints",
4185
+ "qualifications": [
4186
+ {
4187
+ "source_url": "https://vercel.com/docs/ai-gateway/models-and-providers/fast-mode",
4188
+ "notes": "Vercel can serve the base route at Standard speed when Fast capacity is unavailable. Fast prices apply when the request was served Fast."
4189
+ },
4190
+ {
4191
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-5.5-fast/endpoints",
4192
+ "notes": "Vercel shows $12.50 input, $75 output and $1.25 cached input per million tokens, with no separate context price bands. The applicability of those prices across the full published context window is unverified."
4193
+ }
4194
+ ],
4195
+ "limits": {
4196
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-5.5-fast/endpoints",
4197
+ "context_tokens": 1000000,
4198
+ "max_output_tokens": 128000
4199
+ },
4200
+ "capabilities": {
4201
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-5.5-fast/endpoints",
4202
+ "image_input": true,
4203
+ "tools": true,
4204
+ "reasoning": true,
4205
+ "structured_output": true
4206
+ }
4207
+ }
3961
4208
  }
3962
4209
  },
3963
4210
  "openai": {
@@ -4027,6 +4274,20 @@
4027
4274
  "source_url": "https://developers.openai.com/api/docs/models/gpt-5.5",
4028
4275
  "context_tokens": 1050000,
4029
4276
  "max_output_tokens": 128000
4277
+ },
4278
+ "modes": {
4279
+ "fast": {
4280
+ "source_url": "https://developers.openai.com/api/docs/guides/fast-mode",
4281
+ "request": {
4282
+ "service_tier": "fast"
4283
+ },
4284
+ "qualifications": [
4285
+ {
4286
+ "source_url": "https://developers.openai.com/api/docs/pricing.md#fast-pricing-data",
4287
+ "notes": "The published native Fast schedule covers only the row marked below 272K context. It lists $12.50 input, $75 output and $1.25 cached input per million tokens."
4288
+ }
4289
+ ]
4290
+ }
4030
4291
  }
4031
4292
  },
4032
4293
  "openrouter": {
@@ -4095,6 +4356,83 @@
4095
4356
  "source_url": "https://openrouter.ai/api/v1/models",
4096
4357
  "context_tokens": 1050000,
4097
4358
  "max_output_tokens": 128000
4359
+ },
4360
+ "modes": {
4361
+ "fast": {
4362
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-5.5/endpoints",
4363
+ "request": {
4364
+ "service_tier": "fast",
4365
+ "provider": {
4366
+ "only": [
4367
+ "openai/fast"
4368
+ ]
4369
+ }
4370
+ },
4371
+ "qualifications": [
4372
+ {
4373
+ "source_url": "https://openrouter.ai/docs/guides/features/service-tiers",
4374
+ "notes": "The provider.only tag selects the openai/fast endpoint. OpenRouter reports the tier that actually served the request."
4375
+ },
4376
+ {
4377
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-5.5/endpoints",
4378
+ "notes": "The Fast endpoint publishes a separate maximum of 922,000 prompt tokens."
4379
+ }
4380
+ ],
4381
+ "limits": {
4382
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-5.5/endpoints",
4383
+ "context_tokens": 1050000,
4384
+ "max_output_tokens": 128000
4385
+ },
4386
+ "capabilities": {
4387
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-5.5/endpoints",
4388
+ "tools": true,
4389
+ "reasoning": true,
4390
+ "structured_output": true
4391
+ },
4392
+ "token_pricing": {
4393
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-5.5/endpoints",
4394
+ "unit": "usd_per_token",
4395
+ "scope": "Regular token rates for requests served on the OpenRouter Fast endpoint. Optional tools and regional premiums are excluded.",
4396
+ "input": "0.0000125",
4397
+ "output": "0.000075",
4398
+ "input_cache_read": "0.00000125",
4399
+ "tiers": [
4400
+ {
4401
+ "meter": "input",
4402
+ "minimum_input_tokens": 0,
4403
+ "maximum_input_tokens": 272000,
4404
+ "usd_per_token": "0.0000125"
4405
+ },
4406
+ {
4407
+ "meter": "input",
4408
+ "minimum_input_tokens": 272000,
4409
+ "usd_per_token": "0.000025"
4410
+ },
4411
+ {
4412
+ "meter": "output",
4413
+ "minimum_input_tokens": 0,
4414
+ "maximum_input_tokens": 272000,
4415
+ "usd_per_token": "0.000075"
4416
+ },
4417
+ {
4418
+ "meter": "output",
4419
+ "minimum_input_tokens": 272000,
4420
+ "usd_per_token": "0.0001125"
4421
+ },
4422
+ {
4423
+ "meter": "input_cache_read",
4424
+ "minimum_input_tokens": 0,
4425
+ "maximum_input_tokens": 272000,
4426
+ "usd_per_token": "0.00000125"
4427
+ },
4428
+ {
4429
+ "meter": "input_cache_read",
4430
+ "minimum_input_tokens": 272000,
4431
+ "usd_per_token": "0.0000025"
4432
+ }
4433
+ ]
4434
+ }
4435
+ }
4098
4436
  }
4099
4437
  },
4100
4438
  "grida": {
@@ -4669,6 +5007,88 @@
4669
5007
  "source_url": "https://ai-gateway.vercel.sh/v1/models",
4670
5008
  "context_tokens": 1050000,
4671
5009
  "max_output_tokens": 128000
5010
+ },
5011
+ "offerings": {
5012
+ "openai/gpt-5.6-luna-fast": {
5013
+ "id": "openai/gpt-5.6-luna-fast",
5014
+ "canonical_model_id": "openai/gpt-5.6-luna",
5015
+ "mode": "fast",
5016
+ "label": "GPT 5.6 Luna (Fast)",
5017
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-5.6-luna-fast/endpoints",
5018
+ "qualifications": [
5019
+ {
5020
+ "source_url": "https://vercel.com/docs/ai-gateway/models-and-providers/fast-mode",
5021
+ "notes": "Vercel can serve the base route at Standard speed when Fast capacity is unavailable. Fast prices apply when the request was served Fast."
5022
+ }
5023
+ ],
5024
+ "limits": {
5025
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-5.6-luna-fast/endpoints",
5026
+ "context_tokens": 1050000,
5027
+ "max_output_tokens": 128000
5028
+ },
5029
+ "capabilities": {
5030
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-5.6-luna-fast/endpoints",
5031
+ "image_input": true,
5032
+ "tools": true,
5033
+ "reasoning": true,
5034
+ "structured_output": true
5035
+ },
5036
+ "token_pricing": {
5037
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-5.6-luna-fast/endpoints",
5038
+ "unit": "usd_per_token",
5039
+ "scope": "Regular global token rates for requests served on the Vercel Fast endpoint. Optional tools and regional premiums are excluded.",
5040
+ "input": "0.0000004",
5041
+ "output": "0.0000024",
5042
+ "input_cache_read": "0.00000004",
5043
+ "input_cache_write": "0.0000005",
5044
+ "tiers": [
5045
+ {
5046
+ "meter": "input",
5047
+ "minimum_input_tokens": 0,
5048
+ "maximum_input_tokens": 272000,
5049
+ "usd_per_token": "0.0000004"
5050
+ },
5051
+ {
5052
+ "meter": "input",
5053
+ "minimum_input_tokens": 272000,
5054
+ "usd_per_token": "0.0000008"
5055
+ },
5056
+ {
5057
+ "meter": "output",
5058
+ "minimum_input_tokens": 0,
5059
+ "maximum_input_tokens": 272000,
5060
+ "usd_per_token": "0.0000024"
5061
+ },
5062
+ {
5063
+ "meter": "output",
5064
+ "minimum_input_tokens": 272000,
5065
+ "usd_per_token": "0.0000036"
5066
+ },
5067
+ {
5068
+ "meter": "input_cache_read",
5069
+ "minimum_input_tokens": 0,
5070
+ "maximum_input_tokens": 272000,
5071
+ "usd_per_token": "0.00000004"
5072
+ },
5073
+ {
5074
+ "meter": "input_cache_read",
5075
+ "minimum_input_tokens": 272000,
5076
+ "usd_per_token": "0.00000008"
5077
+ },
5078
+ {
5079
+ "meter": "input_cache_write",
5080
+ "minimum_input_tokens": 0,
5081
+ "maximum_input_tokens": 272000,
5082
+ "usd_per_token": "0.0000005"
5083
+ },
5084
+ {
5085
+ "meter": "input_cache_write",
5086
+ "minimum_input_tokens": 272000,
5087
+ "usd_per_token": "0.000001"
5088
+ }
5089
+ ]
5090
+ }
5091
+ }
4672
5092
  }
4673
5093
  },
4674
5094
  "openai": {
@@ -4750,6 +5170,80 @@
4750
5170
  "source_url": "https://developers.openai.com/api/docs/models/gpt-5.6-luna",
4751
5171
  "context_tokens": 1050000,
4752
5172
  "max_output_tokens": 128000
5173
+ },
5174
+ "modes": {
5175
+ "fast": {
5176
+ "source_url": "https://developers.openai.com/api/docs/guides/fast-mode",
5177
+ "request": {
5178
+ "service_tier": "fast"
5179
+ },
5180
+ "qualifications": [
5181
+ {
5182
+ "source_url": "https://developers.openai.com/api/docs/pricing.md#fast-pricing-data",
5183
+ "notes": "OpenAI separately publishes 12-hour cache-write rates of $1.00 in the short-context band and $2.00 in the long-context band per million tokens."
5184
+ }
5185
+ ],
5186
+ "limits": {
5187
+ "source_url": "https://developers.openai.com/api/docs/models/gpt-5.6-luna",
5188
+ "context_tokens": 1050000,
5189
+ "max_output_tokens": 128000
5190
+ },
5191
+ "token_pricing": {
5192
+ "source_url": "https://developers.openai.com/api/docs/pricing.md#fast-pricing-data",
5193
+ "unit": "usd_per_token",
5194
+ "scope": "Regular global Fast token rates, including 30-minute cache writes. Long-context rates apply to the entire request above 272,000 input tokens.",
5195
+ "input": "0.0000004",
5196
+ "output": "0.0000024",
5197
+ "input_cache_read": "0.00000004",
5198
+ "input_cache_write": "0.0000005",
5199
+ "tiers": [
5200
+ {
5201
+ "meter": "input",
5202
+ "minimum_input_tokens": 0,
5203
+ "maximum_input_tokens": 272001,
5204
+ "usd_per_token": "0.0000004"
5205
+ },
5206
+ {
5207
+ "meter": "input",
5208
+ "minimum_input_tokens": 272001,
5209
+ "usd_per_token": "0.0000008"
5210
+ },
5211
+ {
5212
+ "meter": "output",
5213
+ "minimum_input_tokens": 0,
5214
+ "maximum_input_tokens": 272001,
5215
+ "usd_per_token": "0.0000024"
5216
+ },
5217
+ {
5218
+ "meter": "output",
5219
+ "minimum_input_tokens": 272001,
5220
+ "usd_per_token": "0.0000036"
5221
+ },
5222
+ {
5223
+ "meter": "input_cache_read",
5224
+ "minimum_input_tokens": 0,
5225
+ "maximum_input_tokens": 272001,
5226
+ "usd_per_token": "0.00000004"
5227
+ },
5228
+ {
5229
+ "meter": "input_cache_read",
5230
+ "minimum_input_tokens": 272001,
5231
+ "usd_per_token": "0.00000008"
5232
+ },
5233
+ {
5234
+ "meter": "input_cache_write",
5235
+ "minimum_input_tokens": 0,
5236
+ "maximum_input_tokens": 272001,
5237
+ "usd_per_token": "0.0000005"
5238
+ },
5239
+ {
5240
+ "meter": "input_cache_write",
5241
+ "minimum_input_tokens": 272001,
5242
+ "usd_per_token": "0.000001"
5243
+ }
5244
+ ]
5245
+ }
5246
+ }
4753
5247
  }
4754
5248
  },
4755
5249
  "openrouter": {
@@ -4830,6 +5324,95 @@
4830
5324
  "source_url": "https://openrouter.ai/api/v1/models",
4831
5325
  "context_tokens": 1050000,
4832
5326
  "max_output_tokens": 128000
5327
+ },
5328
+ "modes": {
5329
+ "fast": {
5330
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-5.6-luna/endpoints",
5331
+ "request": {
5332
+ "service_tier": "fast",
5333
+ "provider": {
5334
+ "only": [
5335
+ "openai/fast"
5336
+ ]
5337
+ }
5338
+ },
5339
+ "qualifications": [
5340
+ {
5341
+ "source_url": "https://openrouter.ai/docs/guides/features/service-tiers",
5342
+ "notes": "The provider.only tag selects the openai/fast endpoint. OpenRouter reports the tier that actually served the request."
5343
+ },
5344
+ {
5345
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-5.6-luna/endpoints",
5346
+ "notes": "The Fast endpoint publishes a separate maximum of 922,000 prompt tokens."
5347
+ }
5348
+ ],
5349
+ "limits": {
5350
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-5.6-luna/endpoints",
5351
+ "context_tokens": 1050000,
5352
+ "max_output_tokens": 128000
5353
+ },
5354
+ "capabilities": {
5355
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-5.6-luna/endpoints",
5356
+ "tools": true,
5357
+ "reasoning": true,
5358
+ "structured_output": true
5359
+ },
5360
+ "token_pricing": {
5361
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-5.6-luna/endpoints",
5362
+ "unit": "usd_per_token",
5363
+ "scope": "Regular token rates for requests served on the OpenRouter Fast endpoint. Optional tools and regional premiums are excluded.",
5364
+ "input": "0.0000004",
5365
+ "output": "0.0000024",
5366
+ "input_cache_read": "0.00000004",
5367
+ "input_cache_write": "0.0000005",
5368
+ "tiers": [
5369
+ {
5370
+ "meter": "input",
5371
+ "minimum_input_tokens": 0,
5372
+ "maximum_input_tokens": 272000,
5373
+ "usd_per_token": "0.0000004"
5374
+ },
5375
+ {
5376
+ "meter": "input",
5377
+ "minimum_input_tokens": 272000,
5378
+ "usd_per_token": "0.0000008"
5379
+ },
5380
+ {
5381
+ "meter": "output",
5382
+ "minimum_input_tokens": 0,
5383
+ "maximum_input_tokens": 272000,
5384
+ "usd_per_token": "0.0000024"
5385
+ },
5386
+ {
5387
+ "meter": "output",
5388
+ "minimum_input_tokens": 272000,
5389
+ "usd_per_token": "0.0000036"
5390
+ },
5391
+ {
5392
+ "meter": "input_cache_read",
5393
+ "minimum_input_tokens": 0,
5394
+ "maximum_input_tokens": 272000,
5395
+ "usd_per_token": "0.00000004"
5396
+ },
5397
+ {
5398
+ "meter": "input_cache_read",
5399
+ "minimum_input_tokens": 272000,
5400
+ "usd_per_token": "0.00000008"
5401
+ },
5402
+ {
5403
+ "meter": "input_cache_write",
5404
+ "minimum_input_tokens": 0,
5405
+ "maximum_input_tokens": 272000,
5406
+ "usd_per_token": "0.0000005"
5407
+ },
5408
+ {
5409
+ "meter": "input_cache_write",
5410
+ "minimum_input_tokens": 272000,
5411
+ "usd_per_token": "0.000001"
5412
+ }
5413
+ ]
5414
+ }
5415
+ }
4833
5416
  }
4834
5417
  },
4835
5418
  "grida": {
@@ -5125,6 +5708,88 @@
5125
5708
  "source_url": "https://ai-gateway.vercel.sh/v1/models",
5126
5709
  "context_tokens": 1050000,
5127
5710
  "max_output_tokens": 128000
5711
+ },
5712
+ "offerings": {
5713
+ "openai/gpt-5.6-sol-fast": {
5714
+ "id": "openai/gpt-5.6-sol-fast",
5715
+ "canonical_model_id": "openai/gpt-5.6-sol",
5716
+ "mode": "fast",
5717
+ "label": "GPT 5.6 Sol (Fast)",
5718
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-5.6-sol-fast/endpoints",
5719
+ "qualifications": [
5720
+ {
5721
+ "source_url": "https://vercel.com/docs/ai-gateway/models-and-providers/fast-mode",
5722
+ "notes": "Vercel can serve the base route at Standard speed when Fast capacity is unavailable. Fast prices apply when the request was served Fast."
5723
+ }
5724
+ ],
5725
+ "limits": {
5726
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-5.6-sol-fast/endpoints",
5727
+ "context_tokens": 1050000,
5728
+ "max_output_tokens": 128000
5729
+ },
5730
+ "capabilities": {
5731
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-5.6-sol-fast/endpoints",
5732
+ "image_input": true,
5733
+ "tools": true,
5734
+ "reasoning": true,
5735
+ "structured_output": true
5736
+ },
5737
+ "token_pricing": {
5738
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-5.6-sol-fast/endpoints",
5739
+ "unit": "usd_per_token",
5740
+ "scope": "Regular global token rates for requests served on the Vercel Fast endpoint. Optional tools and regional premiums are excluded.",
5741
+ "input": "0.000008",
5742
+ "output": "0.00004",
5743
+ "input_cache_read": "0.0000008",
5744
+ "input_cache_write": "0.00001",
5745
+ "tiers": [
5746
+ {
5747
+ "meter": "input",
5748
+ "minimum_input_tokens": 0,
5749
+ "maximum_input_tokens": 272000,
5750
+ "usd_per_token": "0.000008"
5751
+ },
5752
+ {
5753
+ "meter": "input",
5754
+ "minimum_input_tokens": 272000,
5755
+ "usd_per_token": "0.000016"
5756
+ },
5757
+ {
5758
+ "meter": "output",
5759
+ "minimum_input_tokens": 0,
5760
+ "maximum_input_tokens": 272000,
5761
+ "usd_per_token": "0.00004"
5762
+ },
5763
+ {
5764
+ "meter": "output",
5765
+ "minimum_input_tokens": 272000,
5766
+ "usd_per_token": "0.00006"
5767
+ },
5768
+ {
5769
+ "meter": "input_cache_read",
5770
+ "minimum_input_tokens": 0,
5771
+ "maximum_input_tokens": 272000,
5772
+ "usd_per_token": "0.0000008"
5773
+ },
5774
+ {
5775
+ "meter": "input_cache_read",
5776
+ "minimum_input_tokens": 272000,
5777
+ "usd_per_token": "0.0000016"
5778
+ },
5779
+ {
5780
+ "meter": "input_cache_write",
5781
+ "minimum_input_tokens": 0,
5782
+ "maximum_input_tokens": 272000,
5783
+ "usd_per_token": "0.00001"
5784
+ },
5785
+ {
5786
+ "meter": "input_cache_write",
5787
+ "minimum_input_tokens": 272000,
5788
+ "usd_per_token": "0.00002"
5789
+ }
5790
+ ]
5791
+ }
5792
+ }
5128
5793
  }
5129
5794
  },
5130
5795
  "openai": {
@@ -5151,6 +5816,25 @@
5151
5816
  "source_url": "https://developers.openai.com/api/docs/models/gpt-5.6-sol",
5152
5817
  "context_tokens": 1050000,
5153
5818
  "max_output_tokens": 128000
5819
+ },
5820
+ "modes": {
5821
+ "fast": {
5822
+ "source_url": "https://developers.openai.com/api/docs/guides/fast-mode",
5823
+ "request": {
5824
+ "service_tier": "fast"
5825
+ },
5826
+ "qualifications": [
5827
+ {
5828
+ "source_url": "https://developers.openai.com/api/docs/pricing.md#fast-pricing-data",
5829
+ "notes": "OpenAI flags GPT-5.6 Sol pricing as promotional. A separate regular native Fast schedule is unverified."
5830
+ }
5831
+ ],
5832
+ "limits": {
5833
+ "source_url": "https://developers.openai.com/api/docs/models/gpt-5.6-sol",
5834
+ "context_tokens": 1050000,
5835
+ "max_output_tokens": 128000
5836
+ }
5837
+ }
5154
5838
  }
5155
5839
  },
5156
5840
  "openrouter": {
@@ -5231,23 +5915,112 @@
5231
5915
  "source_url": "https://openrouter.ai/api/v1/models",
5232
5916
  "context_tokens": 1050000,
5233
5917
  "max_output_tokens": 128000
5234
- }
5235
- },
5236
- "grida": {
5237
- "provider": "grida",
5238
- "id": "openai/gpt-5.6-sol",
5239
- "url": "https://gateway.grida.ai/v1/models",
5240
- "endpoints": [
5241
- {
5242
- "id": "openai/gpt-5.6-sol",
5243
- "input": "text",
5244
- "source_url": "https://gateway.grida.ai/v1/models",
5245
- "published_pricing": {
5246
- "source_url": "https://gateway.grida.ai/v1/models",
5247
- "currency": "USD",
5248
- "components": [
5249
- {
5250
- "id": "input_tokens.0",
5918
+ },
5919
+ "modes": {
5920
+ "fast": {
5921
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol/endpoints",
5922
+ "request": {
5923
+ "service_tier": "fast",
5924
+ "provider": {
5925
+ "only": [
5926
+ "openai/fast"
5927
+ ]
5928
+ }
5929
+ },
5930
+ "qualifications": [
5931
+ {
5932
+ "source_url": "https://openrouter.ai/docs/guides/features/service-tiers",
5933
+ "notes": "The provider.only tag selects the openai/fast endpoint. OpenRouter reports the tier that actually served the request."
5934
+ },
5935
+ {
5936
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol/endpoints",
5937
+ "notes": "The Fast endpoint publishes a separate maximum of 922,000 prompt tokens."
5938
+ }
5939
+ ],
5940
+ "limits": {
5941
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol/endpoints",
5942
+ "context_tokens": 1050000,
5943
+ "max_output_tokens": 128000
5944
+ },
5945
+ "capabilities": {
5946
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol/endpoints",
5947
+ "tools": true,
5948
+ "reasoning": true,
5949
+ "structured_output": true
5950
+ },
5951
+ "token_pricing": {
5952
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol/endpoints",
5953
+ "unit": "usd_per_token",
5954
+ "scope": "Regular token rates for requests served on the OpenRouter Fast endpoint. Optional tools and regional premiums are excluded.",
5955
+ "input": "0.000008",
5956
+ "output": "0.00004",
5957
+ "input_cache_read": "0.0000008",
5958
+ "input_cache_write": "0.00001",
5959
+ "tiers": [
5960
+ {
5961
+ "meter": "input",
5962
+ "minimum_input_tokens": 0,
5963
+ "maximum_input_tokens": 272000,
5964
+ "usd_per_token": "0.000008"
5965
+ },
5966
+ {
5967
+ "meter": "input",
5968
+ "minimum_input_tokens": 272000,
5969
+ "usd_per_token": "0.000016"
5970
+ },
5971
+ {
5972
+ "meter": "output",
5973
+ "minimum_input_tokens": 0,
5974
+ "maximum_input_tokens": 272000,
5975
+ "usd_per_token": "0.00004"
5976
+ },
5977
+ {
5978
+ "meter": "output",
5979
+ "minimum_input_tokens": 272000,
5980
+ "usd_per_token": "0.00006"
5981
+ },
5982
+ {
5983
+ "meter": "input_cache_read",
5984
+ "minimum_input_tokens": 0,
5985
+ "maximum_input_tokens": 272000,
5986
+ "usd_per_token": "0.0000008"
5987
+ },
5988
+ {
5989
+ "meter": "input_cache_read",
5990
+ "minimum_input_tokens": 272000,
5991
+ "usd_per_token": "0.0000016"
5992
+ },
5993
+ {
5994
+ "meter": "input_cache_write",
5995
+ "minimum_input_tokens": 0,
5996
+ "maximum_input_tokens": 272000,
5997
+ "usd_per_token": "0.00001"
5998
+ },
5999
+ {
6000
+ "meter": "input_cache_write",
6001
+ "minimum_input_tokens": 272000,
6002
+ "usd_per_token": "0.00002"
6003
+ }
6004
+ ]
6005
+ }
6006
+ }
6007
+ }
6008
+ },
6009
+ "grida": {
6010
+ "provider": "grida",
6011
+ "id": "openai/gpt-5.6-sol",
6012
+ "url": "https://gateway.grida.ai/v1/models",
6013
+ "endpoints": [
6014
+ {
6015
+ "id": "openai/gpt-5.6-sol",
6016
+ "input": "text",
6017
+ "source_url": "https://gateway.grida.ai/v1/models",
6018
+ "published_pricing": {
6019
+ "source_url": "https://gateway.grida.ai/v1/models",
6020
+ "currency": "USD",
6021
+ "components": [
6022
+ {
6023
+ "id": "input_tokens.0",
5251
6024
  "meter": "input_tokens",
5252
6025
  "unit": "token",
5253
6026
  "per_quantity": "1",
@@ -5538,6 +6311,88 @@
5538
6311
  "source_url": "https://ai-gateway.vercel.sh/v1/models",
5539
6312
  "context_tokens": 1050000,
5540
6313
  "max_output_tokens": 128000
6314
+ },
6315
+ "offerings": {
6316
+ "openai/gpt-5.6-terra-fast": {
6317
+ "id": "openai/gpt-5.6-terra-fast",
6318
+ "canonical_model_id": "openai/gpt-5.6-terra",
6319
+ "mode": "fast",
6320
+ "label": "GPT 5.6 Terra (Fast)",
6321
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-5.6-terra-fast/endpoints",
6322
+ "qualifications": [
6323
+ {
6324
+ "source_url": "https://vercel.com/docs/ai-gateway/models-and-providers/fast-mode",
6325
+ "notes": "Vercel can serve the base route at Standard speed when Fast capacity is unavailable. Fast prices apply when the request was served Fast."
6326
+ }
6327
+ ],
6328
+ "limits": {
6329
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-5.6-terra-fast/endpoints",
6330
+ "context_tokens": 1050000,
6331
+ "max_output_tokens": 128000
6332
+ },
6333
+ "capabilities": {
6334
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-5.6-terra-fast/endpoints",
6335
+ "image_input": true,
6336
+ "tools": true,
6337
+ "reasoning": true,
6338
+ "structured_output": true
6339
+ },
6340
+ "token_pricing": {
6341
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-5.6-terra-fast/endpoints",
6342
+ "unit": "usd_per_token",
6343
+ "scope": "Regular global token rates for requests served on the Vercel Fast endpoint. Optional tools and regional premiums are excluded.",
6344
+ "input": "0.000004",
6345
+ "output": "0.000024",
6346
+ "input_cache_read": "0.0000004",
6347
+ "input_cache_write": "0.000005",
6348
+ "tiers": [
6349
+ {
6350
+ "meter": "input",
6351
+ "minimum_input_tokens": 0,
6352
+ "maximum_input_tokens": 272000,
6353
+ "usd_per_token": "0.000004"
6354
+ },
6355
+ {
6356
+ "meter": "input",
6357
+ "minimum_input_tokens": 272000,
6358
+ "usd_per_token": "0.000008"
6359
+ },
6360
+ {
6361
+ "meter": "output",
6362
+ "minimum_input_tokens": 0,
6363
+ "maximum_input_tokens": 272000,
6364
+ "usd_per_token": "0.000024"
6365
+ },
6366
+ {
6367
+ "meter": "output",
6368
+ "minimum_input_tokens": 272000,
6369
+ "usd_per_token": "0.000036"
6370
+ },
6371
+ {
6372
+ "meter": "input_cache_read",
6373
+ "minimum_input_tokens": 0,
6374
+ "maximum_input_tokens": 272000,
6375
+ "usd_per_token": "0.0000004"
6376
+ },
6377
+ {
6378
+ "meter": "input_cache_read",
6379
+ "minimum_input_tokens": 272000,
6380
+ "usd_per_token": "0.0000008"
6381
+ },
6382
+ {
6383
+ "meter": "input_cache_write",
6384
+ "minimum_input_tokens": 0,
6385
+ "maximum_input_tokens": 272000,
6386
+ "usd_per_token": "0.000005"
6387
+ },
6388
+ {
6389
+ "meter": "input_cache_write",
6390
+ "minimum_input_tokens": 272000,
6391
+ "usd_per_token": "0.00001"
6392
+ }
6393
+ ]
6394
+ }
6395
+ }
5541
6396
  }
5542
6397
  },
5543
6398
  "openai": {
@@ -5619,6 +6474,80 @@
5619
6474
  "source_url": "https://developers.openai.com/api/docs/models/gpt-5.6-terra",
5620
6475
  "context_tokens": 1050000,
5621
6476
  "max_output_tokens": 128000
6477
+ },
6478
+ "modes": {
6479
+ "fast": {
6480
+ "source_url": "https://developers.openai.com/api/docs/guides/fast-mode",
6481
+ "request": {
6482
+ "service_tier": "fast"
6483
+ },
6484
+ "qualifications": [
6485
+ {
6486
+ "source_url": "https://developers.openai.com/api/docs/pricing.md#fast-pricing-data",
6487
+ "notes": "OpenAI separately publishes 12-hour cache-write rates of $10.00 in the short-context band and $20.00 in the long-context band per million tokens."
6488
+ }
6489
+ ],
6490
+ "limits": {
6491
+ "source_url": "https://developers.openai.com/api/docs/models/gpt-5.6-terra",
6492
+ "context_tokens": 1050000,
6493
+ "max_output_tokens": 128000
6494
+ },
6495
+ "token_pricing": {
6496
+ "source_url": "https://developers.openai.com/api/docs/pricing.md#fast-pricing-data",
6497
+ "unit": "usd_per_token",
6498
+ "scope": "Regular global Fast token rates, including 30-minute cache writes. Long-context rates apply to the entire request above 272,000 input tokens.",
6499
+ "input": "0.000004",
6500
+ "output": "0.000024",
6501
+ "input_cache_read": "0.0000004",
6502
+ "input_cache_write": "0.000005",
6503
+ "tiers": [
6504
+ {
6505
+ "meter": "input",
6506
+ "minimum_input_tokens": 0,
6507
+ "maximum_input_tokens": 272001,
6508
+ "usd_per_token": "0.000004"
6509
+ },
6510
+ {
6511
+ "meter": "input",
6512
+ "minimum_input_tokens": 272001,
6513
+ "usd_per_token": "0.000008"
6514
+ },
6515
+ {
6516
+ "meter": "output",
6517
+ "minimum_input_tokens": 0,
6518
+ "maximum_input_tokens": 272001,
6519
+ "usd_per_token": "0.000024"
6520
+ },
6521
+ {
6522
+ "meter": "output",
6523
+ "minimum_input_tokens": 272001,
6524
+ "usd_per_token": "0.000036"
6525
+ },
6526
+ {
6527
+ "meter": "input_cache_read",
6528
+ "minimum_input_tokens": 0,
6529
+ "maximum_input_tokens": 272001,
6530
+ "usd_per_token": "0.0000004"
6531
+ },
6532
+ {
6533
+ "meter": "input_cache_read",
6534
+ "minimum_input_tokens": 272001,
6535
+ "usd_per_token": "0.0000008"
6536
+ },
6537
+ {
6538
+ "meter": "input_cache_write",
6539
+ "minimum_input_tokens": 0,
6540
+ "maximum_input_tokens": 272001,
6541
+ "usd_per_token": "0.000005"
6542
+ },
6543
+ {
6544
+ "meter": "input_cache_write",
6545
+ "minimum_input_tokens": 272001,
6546
+ "usd_per_token": "0.00001"
6547
+ }
6548
+ ]
6549
+ }
6550
+ }
5622
6551
  }
5623
6552
  },
5624
6553
  "openrouter": {
@@ -5699,6 +6628,95 @@
5699
6628
  "source_url": "https://openrouter.ai/api/v1/models",
5700
6629
  "context_tokens": 1050000,
5701
6630
  "max_output_tokens": 128000
6631
+ },
6632
+ "modes": {
6633
+ "fast": {
6634
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-5.6-terra/endpoints",
6635
+ "request": {
6636
+ "service_tier": "fast",
6637
+ "provider": {
6638
+ "only": [
6639
+ "openai/fast"
6640
+ ]
6641
+ }
6642
+ },
6643
+ "qualifications": [
6644
+ {
6645
+ "source_url": "https://openrouter.ai/docs/guides/features/service-tiers",
6646
+ "notes": "The provider.only tag selects the openai/fast endpoint. OpenRouter reports the tier that actually served the request."
6647
+ },
6648
+ {
6649
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-5.6-terra/endpoints",
6650
+ "notes": "The Fast endpoint publishes a separate maximum of 922,000 prompt tokens."
6651
+ }
6652
+ ],
6653
+ "limits": {
6654
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-5.6-terra/endpoints",
6655
+ "context_tokens": 1050000,
6656
+ "max_output_tokens": 128000
6657
+ },
6658
+ "capabilities": {
6659
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-5.6-terra/endpoints",
6660
+ "tools": true,
6661
+ "reasoning": true,
6662
+ "structured_output": true
6663
+ },
6664
+ "token_pricing": {
6665
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-5.6-terra/endpoints",
6666
+ "unit": "usd_per_token",
6667
+ "scope": "Regular token rates for requests served on the OpenRouter Fast endpoint. Optional tools and regional premiums are excluded.",
6668
+ "input": "0.000004",
6669
+ "output": "0.000024",
6670
+ "input_cache_read": "0.0000004",
6671
+ "input_cache_write": "0.000005",
6672
+ "tiers": [
6673
+ {
6674
+ "meter": "input",
6675
+ "minimum_input_tokens": 0,
6676
+ "maximum_input_tokens": 272000,
6677
+ "usd_per_token": "0.000004"
6678
+ },
6679
+ {
6680
+ "meter": "input",
6681
+ "minimum_input_tokens": 272000,
6682
+ "usd_per_token": "0.000008"
6683
+ },
6684
+ {
6685
+ "meter": "output",
6686
+ "minimum_input_tokens": 0,
6687
+ "maximum_input_tokens": 272000,
6688
+ "usd_per_token": "0.000024"
6689
+ },
6690
+ {
6691
+ "meter": "output",
6692
+ "minimum_input_tokens": 272000,
6693
+ "usd_per_token": "0.000036"
6694
+ },
6695
+ {
6696
+ "meter": "input_cache_read",
6697
+ "minimum_input_tokens": 0,
6698
+ "maximum_input_tokens": 272000,
6699
+ "usd_per_token": "0.0000004"
6700
+ },
6701
+ {
6702
+ "meter": "input_cache_read",
6703
+ "minimum_input_tokens": 272000,
6704
+ "usd_per_token": "0.0000008"
6705
+ },
6706
+ {
6707
+ "meter": "input_cache_write",
6708
+ "minimum_input_tokens": 0,
6709
+ "maximum_input_tokens": 272000,
6710
+ "usd_per_token": "0.000005"
6711
+ },
6712
+ {
6713
+ "meter": "input_cache_write",
6714
+ "minimum_input_tokens": 272000,
6715
+ "usd_per_token": "0.00001"
6716
+ }
6717
+ ]
6718
+ }
6719
+ }
5702
6720
  }
5703
6721
  },
5704
6722
  "grida": {
@@ -6005,6 +7023,88 @@
6005
7023
  "source_url": "https://ai-gateway.vercel.sh/v1/models",
6006
7024
  "context_tokens": 1050000,
6007
7025
  "max_output_tokens": 128000
7026
+ },
7027
+ "offerings": {
7028
+ "openai/gpt-6-astra-fast": {
7029
+ "id": "openai/gpt-6-astra-fast",
7030
+ "canonical_model_id": "openai/gpt-6-astra",
7031
+ "mode": "fast",
7032
+ "label": "GPT-6 Astra (Fast)",
7033
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-6-astra-fast/endpoints",
7034
+ "qualifications": [
7035
+ {
7036
+ "source_url": "https://vercel.com/docs/ai-gateway/models-and-providers/fast-mode",
7037
+ "notes": "Vercel can serve the base route at Standard speed when Fast capacity is unavailable. Fast prices apply when the request was served Fast."
7038
+ }
7039
+ ],
7040
+ "limits": {
7041
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-6-astra-fast/endpoints",
7042
+ "context_tokens": 1050000,
7043
+ "max_output_tokens": 128000
7044
+ },
7045
+ "capabilities": {
7046
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-6-astra-fast/endpoints",
7047
+ "image_input": true,
7048
+ "tools": true,
7049
+ "reasoning": true,
7050
+ "structured_output": true
7051
+ },
7052
+ "token_pricing": {
7053
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-6-astra-fast/endpoints",
7054
+ "unit": "usd_per_token",
7055
+ "scope": "Regular global token rates for requests served on the Vercel Fast endpoint. Optional tools and regional premiums are excluded.",
7056
+ "input": "0.00002",
7057
+ "output": "0.0001",
7058
+ "input_cache_read": "0.000002",
7059
+ "input_cache_write": "0.000025",
7060
+ "tiers": [
7061
+ {
7062
+ "meter": "input",
7063
+ "minimum_input_tokens": 0,
7064
+ "maximum_input_tokens": 272001,
7065
+ "usd_per_token": "0.00002"
7066
+ },
7067
+ {
7068
+ "meter": "input",
7069
+ "minimum_input_tokens": 272001,
7070
+ "usd_per_token": "0.00004"
7071
+ },
7072
+ {
7073
+ "meter": "output",
7074
+ "minimum_input_tokens": 0,
7075
+ "maximum_input_tokens": 272001,
7076
+ "usd_per_token": "0.0001"
7077
+ },
7078
+ {
7079
+ "meter": "output",
7080
+ "minimum_input_tokens": 272001,
7081
+ "usd_per_token": "0.00015"
7082
+ },
7083
+ {
7084
+ "meter": "input_cache_read",
7085
+ "minimum_input_tokens": 0,
7086
+ "maximum_input_tokens": 272001,
7087
+ "usd_per_token": "0.000002"
7088
+ },
7089
+ {
7090
+ "meter": "input_cache_read",
7091
+ "minimum_input_tokens": 272001,
7092
+ "usd_per_token": "0.000004"
7093
+ },
7094
+ {
7095
+ "meter": "input_cache_write",
7096
+ "minimum_input_tokens": 0,
7097
+ "maximum_input_tokens": 272001,
7098
+ "usd_per_token": "0.000025"
7099
+ },
7100
+ {
7101
+ "meter": "input_cache_write",
7102
+ "minimum_input_tokens": 272001,
7103
+ "usd_per_token": "0.00005"
7104
+ }
7105
+ ]
7106
+ }
7107
+ }
6008
7108
  }
6009
7109
  },
6010
7110
  "openai": {
@@ -6086,6 +7186,80 @@
6086
7186
  "source_url": "https://developers.openai.com/api/docs/models/gpt-6-astra",
6087
7187
  "context_tokens": 1050000,
6088
7188
  "max_output_tokens": 128000
7189
+ },
7190
+ "modes": {
7191
+ "fast": {
7192
+ "source_url": "https://developers.openai.com/api/docs/guides/fast-mode",
7193
+ "request": {
7194
+ "service_tier": "fast"
7195
+ },
7196
+ "qualifications": [
7197
+ {
7198
+ "source_url": "https://developers.openai.com/api/docs/pricing.md#fast-pricing-data",
7199
+ "notes": "OpenAI separately publishes 12-hour cache-write rates of $50.00 in the short-context band and $100.00 in the long-context band per million tokens."
7200
+ }
7201
+ ],
7202
+ "limits": {
7203
+ "source_url": "https://developers.openai.com/api/docs/models/gpt-6-astra",
7204
+ "context_tokens": 1050000,
7205
+ "max_output_tokens": 128000
7206
+ },
7207
+ "token_pricing": {
7208
+ "source_url": "https://developers.openai.com/api/docs/pricing.md#fast-pricing-data",
7209
+ "unit": "usd_per_token",
7210
+ "scope": "Regular global Fast token rates, including 30-minute cache writes. Long-context rates apply to the entire request above 272,000 input tokens.",
7211
+ "input": "0.00002",
7212
+ "output": "0.0001",
7213
+ "input_cache_read": "0.000002",
7214
+ "input_cache_write": "0.000025",
7215
+ "tiers": [
7216
+ {
7217
+ "meter": "input",
7218
+ "minimum_input_tokens": 0,
7219
+ "maximum_input_tokens": 272001,
7220
+ "usd_per_token": "0.00002"
7221
+ },
7222
+ {
7223
+ "meter": "input",
7224
+ "minimum_input_tokens": 272001,
7225
+ "usd_per_token": "0.00004"
7226
+ },
7227
+ {
7228
+ "meter": "output",
7229
+ "minimum_input_tokens": 0,
7230
+ "maximum_input_tokens": 272001,
7231
+ "usd_per_token": "0.0001"
7232
+ },
7233
+ {
7234
+ "meter": "output",
7235
+ "minimum_input_tokens": 272001,
7236
+ "usd_per_token": "0.00015"
7237
+ },
7238
+ {
7239
+ "meter": "input_cache_read",
7240
+ "minimum_input_tokens": 0,
7241
+ "maximum_input_tokens": 272001,
7242
+ "usd_per_token": "0.000002"
7243
+ },
7244
+ {
7245
+ "meter": "input_cache_read",
7246
+ "minimum_input_tokens": 272001,
7247
+ "usd_per_token": "0.000004"
7248
+ },
7249
+ {
7250
+ "meter": "input_cache_write",
7251
+ "minimum_input_tokens": 0,
7252
+ "maximum_input_tokens": 272001,
7253
+ "usd_per_token": "0.000025"
7254
+ },
7255
+ {
7256
+ "meter": "input_cache_write",
7257
+ "minimum_input_tokens": 272001,
7258
+ "usd_per_token": "0.00005"
7259
+ }
7260
+ ]
7261
+ }
7262
+ }
6089
7263
  }
6090
7264
  },
6091
7265
  "openrouter": {
@@ -6166,6 +7340,95 @@
6166
7340
  "source_url": "https://openrouter.ai/api/v1/models",
6167
7341
  "context_tokens": 1050000,
6168
7342
  "max_output_tokens": 128000
7343
+ },
7344
+ "modes": {
7345
+ "fast": {
7346
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-6-astra/endpoints",
7347
+ "request": {
7348
+ "service_tier": "fast",
7349
+ "provider": {
7350
+ "only": [
7351
+ "openai/fast"
7352
+ ]
7353
+ }
7354
+ },
7355
+ "qualifications": [
7356
+ {
7357
+ "source_url": "https://openrouter.ai/docs/guides/features/service-tiers",
7358
+ "notes": "The provider.only tag selects the openai/fast endpoint. OpenRouter reports the tier that actually served the request."
7359
+ },
7360
+ {
7361
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-6-astra/endpoints",
7362
+ "notes": "The Fast endpoint publishes a separate maximum of 922,000 prompt tokens."
7363
+ }
7364
+ ],
7365
+ "limits": {
7366
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-6-astra/endpoints",
7367
+ "context_tokens": 1050000,
7368
+ "max_output_tokens": 128000
7369
+ },
7370
+ "capabilities": {
7371
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-6-astra/endpoints",
7372
+ "tools": true,
7373
+ "reasoning": true,
7374
+ "structured_output": true
7375
+ },
7376
+ "token_pricing": {
7377
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-6-astra/endpoints",
7378
+ "unit": "usd_per_token",
7379
+ "scope": "Regular token rates for requests served on the OpenRouter Fast endpoint. Optional tools and regional premiums are excluded.",
7380
+ "input": "0.00002",
7381
+ "output": "0.0001",
7382
+ "input_cache_read": "0.000002",
7383
+ "input_cache_write": "0.000025",
7384
+ "tiers": [
7385
+ {
7386
+ "meter": "input",
7387
+ "minimum_input_tokens": 0,
7388
+ "maximum_input_tokens": 272000,
7389
+ "usd_per_token": "0.00002"
7390
+ },
7391
+ {
7392
+ "meter": "input",
7393
+ "minimum_input_tokens": 272000,
7394
+ "usd_per_token": "0.00004"
7395
+ },
7396
+ {
7397
+ "meter": "output",
7398
+ "minimum_input_tokens": 0,
7399
+ "maximum_input_tokens": 272000,
7400
+ "usd_per_token": "0.0001"
7401
+ },
7402
+ {
7403
+ "meter": "output",
7404
+ "minimum_input_tokens": 272000,
7405
+ "usd_per_token": "0.00015"
7406
+ },
7407
+ {
7408
+ "meter": "input_cache_read",
7409
+ "minimum_input_tokens": 0,
7410
+ "maximum_input_tokens": 272000,
7411
+ "usd_per_token": "0.000002"
7412
+ },
7413
+ {
7414
+ "meter": "input_cache_read",
7415
+ "minimum_input_tokens": 272000,
7416
+ "usd_per_token": "0.000004"
7417
+ },
7418
+ {
7419
+ "meter": "input_cache_write",
7420
+ "minimum_input_tokens": 0,
7421
+ "maximum_input_tokens": 272000,
7422
+ "usd_per_token": "0.000025"
7423
+ },
7424
+ {
7425
+ "meter": "input_cache_write",
7426
+ "minimum_input_tokens": 272000,
7427
+ "usd_per_token": "0.00005"
7428
+ }
7429
+ ]
7430
+ }
7431
+ }
6169
7432
  }
6170
7433
  },
6171
7434
  "grida": {
@@ -6506,7 +7769,81 @@
6506
7769
  }
6507
7770
  }
6508
7771
  }
6509
- ]
7772
+ ],
7773
+ "modes": {
7774
+ "fast": {
7775
+ "source_url": "https://developers.openai.com/api/docs/guides/fast-mode",
7776
+ "request": {
7777
+ "service_tier": "fast"
7778
+ },
7779
+ "qualifications": [
7780
+ {
7781
+ "source_url": "https://developers.openai.com/api/docs/pricing.md#fast-pricing-data",
7782
+ "notes": "OpenAI separately publishes 12-hour cache-write rates of $0.50 in the short-context band and $1.00 in the long-context band per million tokens."
7783
+ }
7784
+ ],
7785
+ "limits": {
7786
+ "source_url": "https://developers.openai.com/api/docs/models/gpt-6-luna",
7787
+ "context_tokens": 1050000,
7788
+ "max_output_tokens": 128000
7789
+ },
7790
+ "token_pricing": {
7791
+ "source_url": "https://developers.openai.com/api/docs/pricing.md#fast-pricing-data",
7792
+ "unit": "usd_per_token",
7793
+ "scope": "Regular global Fast token rates, including 30-minute cache writes. Long-context rates apply to the entire request above 272,000 input tokens.",
7794
+ "input": "0.0000002",
7795
+ "output": "0.000001",
7796
+ "input_cache_read": "0.00000002",
7797
+ "input_cache_write": "0.00000025",
7798
+ "tiers": [
7799
+ {
7800
+ "meter": "input",
7801
+ "minimum_input_tokens": 0,
7802
+ "maximum_input_tokens": 272001,
7803
+ "usd_per_token": "0.0000002"
7804
+ },
7805
+ {
7806
+ "meter": "input",
7807
+ "minimum_input_tokens": 272001,
7808
+ "usd_per_token": "0.0000004"
7809
+ },
7810
+ {
7811
+ "meter": "output",
7812
+ "minimum_input_tokens": 0,
7813
+ "maximum_input_tokens": 272001,
7814
+ "usd_per_token": "0.000001"
7815
+ },
7816
+ {
7817
+ "meter": "output",
7818
+ "minimum_input_tokens": 272001,
7819
+ "usd_per_token": "0.0000015"
7820
+ },
7821
+ {
7822
+ "meter": "input_cache_read",
7823
+ "minimum_input_tokens": 0,
7824
+ "maximum_input_tokens": 272001,
7825
+ "usd_per_token": "0.00000002"
7826
+ },
7827
+ {
7828
+ "meter": "input_cache_read",
7829
+ "minimum_input_tokens": 272001,
7830
+ "usd_per_token": "0.00000004"
7831
+ },
7832
+ {
7833
+ "meter": "input_cache_write",
7834
+ "minimum_input_tokens": 0,
7835
+ "maximum_input_tokens": 272001,
7836
+ "usd_per_token": "0.00000025"
7837
+ },
7838
+ {
7839
+ "meter": "input_cache_write",
7840
+ "minimum_input_tokens": 272001,
7841
+ "usd_per_token": "0.0000005"
7842
+ }
7843
+ ]
7844
+ }
7845
+ }
7846
+ }
6510
7847
  },
6511
7848
  "openrouter": {
6512
7849
  "provider": "openrouter",
@@ -6593,18 +7930,107 @@
6593
7930
  "input": "text",
6594
7931
  "source_url": "https://openrouter.ai/openai/gpt-6-luna"
6595
7932
  }
6596
- ]
6597
- },
6598
- "vercel": {
6599
- "provider": "vercel",
6600
- "id": "openai/gpt-6-luna",
6601
- "url": "https://vercel.com/ai-gateway/models/gpt-6-luna",
6602
- "source_url": "https://vercel.com/ai-gateway/models/gpt-6-luna",
6603
- "token_pricing": {
6604
- "source_url": "https://vercel.com/ai-gateway/models/gpt-6-luna",
6605
- "unit": "usd_per_token",
6606
- "scope": "Standard synchronous global token rates; optional tools, regional processing and alternate service tiers are excluded. Cache writes use the default duration.",
6607
- "input": "0.0000001",
7933
+ ],
7934
+ "modes": {
7935
+ "fast": {
7936
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-6-luna/endpoints",
7937
+ "request": {
7938
+ "service_tier": "fast",
7939
+ "provider": {
7940
+ "only": [
7941
+ "openai/fast"
7942
+ ]
7943
+ }
7944
+ },
7945
+ "qualifications": [
7946
+ {
7947
+ "source_url": "https://openrouter.ai/docs/guides/features/service-tiers",
7948
+ "notes": "The provider.only tag selects the openai/fast endpoint. OpenRouter reports the tier that actually served the request."
7949
+ },
7950
+ {
7951
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-6-luna/endpoints",
7952
+ "notes": "The Fast endpoint publishes a separate maximum of 922,000 prompt tokens."
7953
+ }
7954
+ ],
7955
+ "limits": {
7956
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-6-luna/endpoints",
7957
+ "context_tokens": 1050000,
7958
+ "max_output_tokens": 128000
7959
+ },
7960
+ "capabilities": {
7961
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-6-luna/endpoints",
7962
+ "tools": true,
7963
+ "reasoning": true,
7964
+ "structured_output": true
7965
+ },
7966
+ "token_pricing": {
7967
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-6-luna/endpoints",
7968
+ "unit": "usd_per_token",
7969
+ "scope": "Regular token rates for requests served on the OpenRouter Fast endpoint. Optional tools and regional premiums are excluded.",
7970
+ "input": "0.0000002",
7971
+ "output": "0.000001",
7972
+ "input_cache_read": "0.00000002",
7973
+ "input_cache_write": "0.00000025",
7974
+ "tiers": [
7975
+ {
7976
+ "meter": "input",
7977
+ "minimum_input_tokens": 0,
7978
+ "maximum_input_tokens": 272000,
7979
+ "usd_per_token": "0.0000002"
7980
+ },
7981
+ {
7982
+ "meter": "input",
7983
+ "minimum_input_tokens": 272000,
7984
+ "usd_per_token": "0.0000004"
7985
+ },
7986
+ {
7987
+ "meter": "output",
7988
+ "minimum_input_tokens": 0,
7989
+ "maximum_input_tokens": 272000,
7990
+ "usd_per_token": "0.000001"
7991
+ },
7992
+ {
7993
+ "meter": "output",
7994
+ "minimum_input_tokens": 272000,
7995
+ "usd_per_token": "0.0000015"
7996
+ },
7997
+ {
7998
+ "meter": "input_cache_read",
7999
+ "minimum_input_tokens": 0,
8000
+ "maximum_input_tokens": 272000,
8001
+ "usd_per_token": "0.00000002"
8002
+ },
8003
+ {
8004
+ "meter": "input_cache_read",
8005
+ "minimum_input_tokens": 272000,
8006
+ "usd_per_token": "0.00000004"
8007
+ },
8008
+ {
8009
+ "meter": "input_cache_write",
8010
+ "minimum_input_tokens": 0,
8011
+ "maximum_input_tokens": 272000,
8012
+ "usd_per_token": "0.00000025"
8013
+ },
8014
+ {
8015
+ "meter": "input_cache_write",
8016
+ "minimum_input_tokens": 272000,
8017
+ "usd_per_token": "0.0000005"
8018
+ }
8019
+ ]
8020
+ }
8021
+ }
8022
+ }
8023
+ },
8024
+ "vercel": {
8025
+ "provider": "vercel",
8026
+ "id": "openai/gpt-6-luna",
8027
+ "url": "https://vercel.com/ai-gateway/models/gpt-6-luna",
8028
+ "source_url": "https://vercel.com/ai-gateway/models/gpt-6-luna",
8029
+ "token_pricing": {
8030
+ "source_url": "https://vercel.com/ai-gateway/models/gpt-6-luna",
8031
+ "unit": "usd_per_token",
8032
+ "scope": "Standard synchronous global token rates; optional tools, regional processing and alternate service tiers are excluded. Cache writes use the default duration.",
8033
+ "input": "0.0000001",
6608
8034
  "output": "0.0000005",
6609
8035
  "input_cache_read": "0.00000001",
6610
8036
  "input_cache_write": "0.000000125",
@@ -6674,7 +8100,89 @@
6674
8100
  "input": "text",
6675
8101
  "source_url": "https://vercel.com/ai-gateway/models/gpt-6-luna"
6676
8102
  }
6677
- ]
8103
+ ],
8104
+ "offerings": {
8105
+ "openai/gpt-6-luna-fast": {
8106
+ "id": "openai/gpt-6-luna-fast",
8107
+ "canonical_model_id": "openai/gpt-6-luna",
8108
+ "mode": "fast",
8109
+ "label": "GPT-6 Luna (Fast)",
8110
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-6-luna-fast/endpoints",
8111
+ "qualifications": [
8112
+ {
8113
+ "source_url": "https://vercel.com/docs/ai-gateway/models-and-providers/fast-mode",
8114
+ "notes": "Vercel can serve the base route at Standard speed when Fast capacity is unavailable. Fast prices apply when the request was served Fast."
8115
+ }
8116
+ ],
8117
+ "limits": {
8118
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-6-luna-fast/endpoints",
8119
+ "context_tokens": 1050000,
8120
+ "max_output_tokens": 128000
8121
+ },
8122
+ "capabilities": {
8123
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-6-luna-fast/endpoints",
8124
+ "image_input": true,
8125
+ "tools": true,
8126
+ "reasoning": true,
8127
+ "structured_output": true
8128
+ },
8129
+ "token_pricing": {
8130
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-6-luna-fast/endpoints",
8131
+ "unit": "usd_per_token",
8132
+ "scope": "Regular global token rates for requests served on the Vercel Fast endpoint. Optional tools and regional premiums are excluded.",
8133
+ "input": "0.0000002",
8134
+ "output": "0.000001",
8135
+ "input_cache_read": "0.00000002",
8136
+ "input_cache_write": "0.00000025",
8137
+ "tiers": [
8138
+ {
8139
+ "meter": "input",
8140
+ "minimum_input_tokens": 0,
8141
+ "maximum_input_tokens": 272001,
8142
+ "usd_per_token": "0.0000002"
8143
+ },
8144
+ {
8145
+ "meter": "input",
8146
+ "minimum_input_tokens": 272001,
8147
+ "usd_per_token": "0.0000004"
8148
+ },
8149
+ {
8150
+ "meter": "output",
8151
+ "minimum_input_tokens": 0,
8152
+ "maximum_input_tokens": 272001,
8153
+ "usd_per_token": "0.000001"
8154
+ },
8155
+ {
8156
+ "meter": "output",
8157
+ "minimum_input_tokens": 272001,
8158
+ "usd_per_token": "0.0000015"
8159
+ },
8160
+ {
8161
+ "meter": "input_cache_read",
8162
+ "minimum_input_tokens": 0,
8163
+ "maximum_input_tokens": 272001,
8164
+ "usd_per_token": "0.00000002"
8165
+ },
8166
+ {
8167
+ "meter": "input_cache_read",
8168
+ "minimum_input_tokens": 272001,
8169
+ "usd_per_token": "0.00000004"
8170
+ },
8171
+ {
8172
+ "meter": "input_cache_write",
8173
+ "minimum_input_tokens": 0,
8174
+ "maximum_input_tokens": 272001,
8175
+ "usd_per_token": "0.00000025"
8176
+ },
8177
+ {
8178
+ "meter": "input_cache_write",
8179
+ "minimum_input_tokens": 272001,
8180
+ "usd_per_token": "0.0000005"
8181
+ }
8182
+ ]
8183
+ }
8184
+ }
8185
+ }
6678
8186
  },
6679
8187
  "grida": {
6680
8188
  "provider": "grida",
@@ -6998,7 +8506,81 @@
6998
8506
  }
6999
8507
  }
7000
8508
  }
7001
- ]
8509
+ ],
8510
+ "modes": {
8511
+ "fast": {
8512
+ "source_url": "https://developers.openai.com/api/docs/guides/fast-mode",
8513
+ "request": {
8514
+ "service_tier": "fast"
8515
+ },
8516
+ "qualifications": [
8517
+ {
8518
+ "source_url": "https://developers.openai.com/api/docs/pricing.md#fast-pricing-data",
8519
+ "notes": "OpenAI separately publishes 12-hour cache-write rates of $10.00 in the short-context band and $20.00 in the long-context band per million tokens."
8520
+ }
8521
+ ],
8522
+ "limits": {
8523
+ "source_url": "https://developers.openai.com/api/docs/models/gpt-6-sol",
8524
+ "context_tokens": 1050000,
8525
+ "max_output_tokens": 128000
8526
+ },
8527
+ "token_pricing": {
8528
+ "source_url": "https://developers.openai.com/api/docs/pricing.md#fast-pricing-data",
8529
+ "unit": "usd_per_token",
8530
+ "scope": "Regular global Fast token rates, including 30-minute cache writes. Long-context rates apply to the entire request above 272,000 input tokens.",
8531
+ "input": "0.000004",
8532
+ "output": "0.00002",
8533
+ "input_cache_read": "0.0000004",
8534
+ "input_cache_write": "0.000005",
8535
+ "tiers": [
8536
+ {
8537
+ "meter": "input",
8538
+ "minimum_input_tokens": 0,
8539
+ "maximum_input_tokens": 272001,
8540
+ "usd_per_token": "0.000004"
8541
+ },
8542
+ {
8543
+ "meter": "input",
8544
+ "minimum_input_tokens": 272001,
8545
+ "usd_per_token": "0.000008"
8546
+ },
8547
+ {
8548
+ "meter": "output",
8549
+ "minimum_input_tokens": 0,
8550
+ "maximum_input_tokens": 272001,
8551
+ "usd_per_token": "0.00002"
8552
+ },
8553
+ {
8554
+ "meter": "output",
8555
+ "minimum_input_tokens": 272001,
8556
+ "usd_per_token": "0.00003"
8557
+ },
8558
+ {
8559
+ "meter": "input_cache_read",
8560
+ "minimum_input_tokens": 0,
8561
+ "maximum_input_tokens": 272001,
8562
+ "usd_per_token": "0.0000004"
8563
+ },
8564
+ {
8565
+ "meter": "input_cache_read",
8566
+ "minimum_input_tokens": 272001,
8567
+ "usd_per_token": "0.0000008"
8568
+ },
8569
+ {
8570
+ "meter": "input_cache_write",
8571
+ "minimum_input_tokens": 0,
8572
+ "maximum_input_tokens": 272001,
8573
+ "usd_per_token": "0.000005"
8574
+ },
8575
+ {
8576
+ "meter": "input_cache_write",
8577
+ "minimum_input_tokens": 272001,
8578
+ "usd_per_token": "0.00001"
8579
+ }
8580
+ ]
8581
+ }
8582
+ }
8583
+ }
7002
8584
  },
7003
8585
  "openrouter": {
7004
8586
  "provider": "openrouter",
@@ -7085,7 +8667,96 @@
7085
8667
  "input": "text",
7086
8668
  "source_url": "https://openrouter.ai/openai/gpt-6-sol"
7087
8669
  }
7088
- ]
8670
+ ],
8671
+ "modes": {
8672
+ "fast": {
8673
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-6-sol/endpoints",
8674
+ "request": {
8675
+ "service_tier": "fast",
8676
+ "provider": {
8677
+ "only": [
8678
+ "openai/fast"
8679
+ ]
8680
+ }
8681
+ },
8682
+ "qualifications": [
8683
+ {
8684
+ "source_url": "https://openrouter.ai/docs/guides/features/service-tiers",
8685
+ "notes": "The provider.only tag selects the openai/fast endpoint. OpenRouter reports the tier that actually served the request."
8686
+ },
8687
+ {
8688
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-6-sol/endpoints",
8689
+ "notes": "The Fast endpoint publishes a separate maximum of 922,000 prompt tokens."
8690
+ }
8691
+ ],
8692
+ "limits": {
8693
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-6-sol/endpoints",
8694
+ "context_tokens": 1050000,
8695
+ "max_output_tokens": 128000
8696
+ },
8697
+ "capabilities": {
8698
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-6-sol/endpoints",
8699
+ "tools": true,
8700
+ "reasoning": true,
8701
+ "structured_output": true
8702
+ },
8703
+ "token_pricing": {
8704
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-6-sol/endpoints",
8705
+ "unit": "usd_per_token",
8706
+ "scope": "Regular token rates for requests served on the OpenRouter Fast endpoint. Optional tools and regional premiums are excluded.",
8707
+ "input": "0.000004",
8708
+ "output": "0.00002",
8709
+ "input_cache_read": "0.0000004",
8710
+ "input_cache_write": "0.000005",
8711
+ "tiers": [
8712
+ {
8713
+ "meter": "input",
8714
+ "minimum_input_tokens": 0,
8715
+ "maximum_input_tokens": 272000,
8716
+ "usd_per_token": "0.000004"
8717
+ },
8718
+ {
8719
+ "meter": "input",
8720
+ "minimum_input_tokens": 272000,
8721
+ "usd_per_token": "0.000008"
8722
+ },
8723
+ {
8724
+ "meter": "output",
8725
+ "minimum_input_tokens": 0,
8726
+ "maximum_input_tokens": 272000,
8727
+ "usd_per_token": "0.00002"
8728
+ },
8729
+ {
8730
+ "meter": "output",
8731
+ "minimum_input_tokens": 272000,
8732
+ "usd_per_token": "0.00003"
8733
+ },
8734
+ {
8735
+ "meter": "input_cache_read",
8736
+ "minimum_input_tokens": 0,
8737
+ "maximum_input_tokens": 272000,
8738
+ "usd_per_token": "0.0000004"
8739
+ },
8740
+ {
8741
+ "meter": "input_cache_read",
8742
+ "minimum_input_tokens": 272000,
8743
+ "usd_per_token": "0.0000008"
8744
+ },
8745
+ {
8746
+ "meter": "input_cache_write",
8747
+ "minimum_input_tokens": 0,
8748
+ "maximum_input_tokens": 272000,
8749
+ "usd_per_token": "0.000005"
8750
+ },
8751
+ {
8752
+ "meter": "input_cache_write",
8753
+ "minimum_input_tokens": 272000,
8754
+ "usd_per_token": "0.00001"
8755
+ }
8756
+ ]
8757
+ }
8758
+ }
8759
+ }
7089
8760
  },
7090
8761
  "vercel": {
7091
8762
  "provider": "vercel",
@@ -7166,7 +8837,89 @@
7166
8837
  "input": "text",
7167
8838
  "source_url": "https://vercel.com/ai-gateway/models/gpt-6-sol"
7168
8839
  }
7169
- ]
8840
+ ],
8841
+ "offerings": {
8842
+ "openai/gpt-6-sol-fast": {
8843
+ "id": "openai/gpt-6-sol-fast",
8844
+ "canonical_model_id": "openai/gpt-6-sol",
8845
+ "mode": "fast",
8846
+ "label": "GPT-6 Sol (Fast)",
8847
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-6-sol-fast/endpoints",
8848
+ "qualifications": [
8849
+ {
8850
+ "source_url": "https://vercel.com/docs/ai-gateway/models-and-providers/fast-mode",
8851
+ "notes": "Vercel can serve the base route at Standard speed when Fast capacity is unavailable. Fast prices apply when the request was served Fast."
8852
+ }
8853
+ ],
8854
+ "limits": {
8855
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-6-sol-fast/endpoints",
8856
+ "context_tokens": 1050000,
8857
+ "max_output_tokens": 128000
8858
+ },
8859
+ "capabilities": {
8860
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-6-sol-fast/endpoints",
8861
+ "image_input": true,
8862
+ "tools": true,
8863
+ "reasoning": true,
8864
+ "structured_output": true
8865
+ },
8866
+ "token_pricing": {
8867
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-6-sol-fast/endpoints",
8868
+ "unit": "usd_per_token",
8869
+ "scope": "Regular global token rates for requests served on the Vercel Fast endpoint. Optional tools and regional premiums are excluded.",
8870
+ "input": "0.000004",
8871
+ "output": "0.00002",
8872
+ "input_cache_read": "0.0000004",
8873
+ "input_cache_write": "0.000005",
8874
+ "tiers": [
8875
+ {
8876
+ "meter": "input",
8877
+ "minimum_input_tokens": 0,
8878
+ "maximum_input_tokens": 272001,
8879
+ "usd_per_token": "0.000004"
8880
+ },
8881
+ {
8882
+ "meter": "input",
8883
+ "minimum_input_tokens": 272001,
8884
+ "usd_per_token": "0.000008"
8885
+ },
8886
+ {
8887
+ "meter": "output",
8888
+ "minimum_input_tokens": 0,
8889
+ "maximum_input_tokens": 272001,
8890
+ "usd_per_token": "0.00002"
8891
+ },
8892
+ {
8893
+ "meter": "output",
8894
+ "minimum_input_tokens": 272001,
8895
+ "usd_per_token": "0.00003"
8896
+ },
8897
+ {
8898
+ "meter": "input_cache_read",
8899
+ "minimum_input_tokens": 0,
8900
+ "maximum_input_tokens": 272001,
8901
+ "usd_per_token": "0.0000004"
8902
+ },
8903
+ {
8904
+ "meter": "input_cache_read",
8905
+ "minimum_input_tokens": 272001,
8906
+ "usd_per_token": "0.0000008"
8907
+ },
8908
+ {
8909
+ "meter": "input_cache_write",
8910
+ "minimum_input_tokens": 0,
8911
+ "maximum_input_tokens": 272001,
8912
+ "usd_per_token": "0.000005"
8913
+ },
8914
+ {
8915
+ "meter": "input_cache_write",
8916
+ "minimum_input_tokens": 272001,
8917
+ "usd_per_token": "0.00001"
8918
+ }
8919
+ ]
8920
+ }
8921
+ }
8922
+ }
7170
8923
  },
7171
8924
  "grida": {
7172
8925
  "provider": "grida",
@@ -7489,7 +9242,81 @@
7489
9242
  }
7490
9243
  }
7491
9244
  }
7492
- ]
9245
+ ],
9246
+ "modes": {
9247
+ "fast": {
9248
+ "source_url": "https://developers.openai.com/api/docs/guides/fast-mode",
9249
+ "request": {
9250
+ "service_tier": "fast"
9251
+ },
9252
+ "qualifications": [
9253
+ {
9254
+ "source_url": "https://developers.openai.com/api/docs/pricing.md#fast-pricing-data",
9255
+ "notes": "OpenAI separately publishes 12-hour cache-write rates of $10.00 in the short-context band and $20.00 in the long-context band per million tokens."
9256
+ }
9257
+ ],
9258
+ "limits": {
9259
+ "source_url": "https://developers.openai.com/api/docs/models/gpt-6.1-sol",
9260
+ "context_tokens": 1050000,
9261
+ "max_output_tokens": 128000
9262
+ },
9263
+ "token_pricing": {
9264
+ "source_url": "https://developers.openai.com/api/docs/pricing.md#fast-pricing-data",
9265
+ "unit": "usd_per_token",
9266
+ "scope": "Regular global Fast token rates, including 30-minute cache writes. Long-context rates apply to the entire request above 272,000 input tokens.",
9267
+ "input": "0.000004",
9268
+ "output": "0.00002",
9269
+ "input_cache_read": "0.0000002",
9270
+ "input_cache_write": "0.000005",
9271
+ "tiers": [
9272
+ {
9273
+ "meter": "input",
9274
+ "minimum_input_tokens": 0,
9275
+ "maximum_input_tokens": 272001,
9276
+ "usd_per_token": "0.000004"
9277
+ },
9278
+ {
9279
+ "meter": "input",
9280
+ "minimum_input_tokens": 272001,
9281
+ "usd_per_token": "0.000008"
9282
+ },
9283
+ {
9284
+ "meter": "output",
9285
+ "minimum_input_tokens": 0,
9286
+ "maximum_input_tokens": 272001,
9287
+ "usd_per_token": "0.00002"
9288
+ },
9289
+ {
9290
+ "meter": "output",
9291
+ "minimum_input_tokens": 272001,
9292
+ "usd_per_token": "0.00003"
9293
+ },
9294
+ {
9295
+ "meter": "input_cache_read",
9296
+ "minimum_input_tokens": 0,
9297
+ "maximum_input_tokens": 272001,
9298
+ "usd_per_token": "0.0000002"
9299
+ },
9300
+ {
9301
+ "meter": "input_cache_read",
9302
+ "minimum_input_tokens": 272001,
9303
+ "usd_per_token": "0.0000004"
9304
+ },
9305
+ {
9306
+ "meter": "input_cache_write",
9307
+ "minimum_input_tokens": 0,
9308
+ "maximum_input_tokens": 272001,
9309
+ "usd_per_token": "0.000005"
9310
+ },
9311
+ {
9312
+ "meter": "input_cache_write",
9313
+ "minimum_input_tokens": 272001,
9314
+ "usd_per_token": "0.00001"
9315
+ }
9316
+ ]
9317
+ }
9318
+ }
9319
+ }
7493
9320
  },
7494
9321
  "openrouter": {
7495
9322
  "provider": "openrouter",
@@ -7576,7 +9403,96 @@
7576
9403
  "input": "text",
7577
9404
  "source_url": "https://openrouter.ai/openai/gpt-6.1-sol"
7578
9405
  }
7579
- ]
9406
+ ],
9407
+ "modes": {
9408
+ "fast": {
9409
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-6.1-sol/endpoints",
9410
+ "request": {
9411
+ "service_tier": "fast",
9412
+ "provider": {
9413
+ "only": [
9414
+ "openai/fast"
9415
+ ]
9416
+ }
9417
+ },
9418
+ "qualifications": [
9419
+ {
9420
+ "source_url": "https://openrouter.ai/docs/guides/features/service-tiers",
9421
+ "notes": "The provider.only tag selects the openai/fast endpoint. OpenRouter reports the tier that actually served the request."
9422
+ },
9423
+ {
9424
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-6.1-sol/endpoints",
9425
+ "notes": "The Fast endpoint publishes a separate maximum of 922,000 prompt tokens."
9426
+ }
9427
+ ],
9428
+ "limits": {
9429
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-6.1-sol/endpoints",
9430
+ "context_tokens": 1050000,
9431
+ "max_output_tokens": 128000
9432
+ },
9433
+ "capabilities": {
9434
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-6.1-sol/endpoints",
9435
+ "tools": true,
9436
+ "reasoning": true,
9437
+ "structured_output": true
9438
+ },
9439
+ "token_pricing": {
9440
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-6.1-sol/endpoints",
9441
+ "unit": "usd_per_token",
9442
+ "scope": "Regular token rates for requests served on the OpenRouter Fast endpoint. Optional tools and regional premiums are excluded.",
9443
+ "input": "0.000004",
9444
+ "output": "0.00002",
9445
+ "input_cache_read": "0.0000002",
9446
+ "input_cache_write": "0.000005",
9447
+ "tiers": [
9448
+ {
9449
+ "meter": "input",
9450
+ "minimum_input_tokens": 0,
9451
+ "maximum_input_tokens": 272000,
9452
+ "usd_per_token": "0.000004"
9453
+ },
9454
+ {
9455
+ "meter": "input",
9456
+ "minimum_input_tokens": 272000,
9457
+ "usd_per_token": "0.000008"
9458
+ },
9459
+ {
9460
+ "meter": "output",
9461
+ "minimum_input_tokens": 0,
9462
+ "maximum_input_tokens": 272000,
9463
+ "usd_per_token": "0.00002"
9464
+ },
9465
+ {
9466
+ "meter": "output",
9467
+ "minimum_input_tokens": 272000,
9468
+ "usd_per_token": "0.00003"
9469
+ },
9470
+ {
9471
+ "meter": "input_cache_read",
9472
+ "minimum_input_tokens": 0,
9473
+ "maximum_input_tokens": 272000,
9474
+ "usd_per_token": "0.0000002"
9475
+ },
9476
+ {
9477
+ "meter": "input_cache_read",
9478
+ "minimum_input_tokens": 272000,
9479
+ "usd_per_token": "0.0000004"
9480
+ },
9481
+ {
9482
+ "meter": "input_cache_write",
9483
+ "minimum_input_tokens": 0,
9484
+ "maximum_input_tokens": 272000,
9485
+ "usd_per_token": "0.000005"
9486
+ },
9487
+ {
9488
+ "meter": "input_cache_write",
9489
+ "minimum_input_tokens": 272000,
9490
+ "usd_per_token": "0.00001"
9491
+ }
9492
+ ]
9493
+ }
9494
+ }
9495
+ }
7580
9496
  },
7581
9497
  "vercel": {
7582
9498
  "provider": "vercel",
@@ -7657,7 +9573,89 @@
7657
9573
  "input": "text",
7658
9574
  "source_url": "https://vercel.com/ai-gateway/models/gpt-6.1-sol"
7659
9575
  }
7660
- ]
9576
+ ],
9577
+ "offerings": {
9578
+ "openai/gpt-6.1-sol-fast": {
9579
+ "id": "openai/gpt-6.1-sol-fast",
9580
+ "canonical_model_id": "openai/gpt-6.1-sol",
9581
+ "mode": "fast",
9582
+ "label": "GPT-6.1 Sol (Fast)",
9583
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-6.1-sol-fast/endpoints",
9584
+ "qualifications": [
9585
+ {
9586
+ "source_url": "https://vercel.com/docs/ai-gateway/models-and-providers/fast-mode",
9587
+ "notes": "Vercel can serve the base route at Standard speed when Fast capacity is unavailable. Fast prices apply when the request was served Fast."
9588
+ }
9589
+ ],
9590
+ "limits": {
9591
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-6.1-sol-fast/endpoints",
9592
+ "context_tokens": 1050000,
9593
+ "max_output_tokens": 128000
9594
+ },
9595
+ "capabilities": {
9596
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-6.1-sol-fast/endpoints",
9597
+ "image_input": true,
9598
+ "tools": true,
9599
+ "reasoning": true,
9600
+ "structured_output": true
9601
+ },
9602
+ "token_pricing": {
9603
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-6.1-sol-fast/endpoints",
9604
+ "unit": "usd_per_token",
9605
+ "scope": "Regular global token rates for requests served on the Vercel Fast endpoint. Optional tools and regional premiums are excluded.",
9606
+ "input": "0.000004",
9607
+ "output": "0.00002",
9608
+ "input_cache_read": "0.0000002",
9609
+ "input_cache_write": "0.000005",
9610
+ "tiers": [
9611
+ {
9612
+ "meter": "input",
9613
+ "minimum_input_tokens": 0,
9614
+ "maximum_input_tokens": 272001,
9615
+ "usd_per_token": "0.000004"
9616
+ },
9617
+ {
9618
+ "meter": "input",
9619
+ "minimum_input_tokens": 272001,
9620
+ "usd_per_token": "0.000008"
9621
+ },
9622
+ {
9623
+ "meter": "output",
9624
+ "minimum_input_tokens": 0,
9625
+ "maximum_input_tokens": 272001,
9626
+ "usd_per_token": "0.00002"
9627
+ },
9628
+ {
9629
+ "meter": "output",
9630
+ "minimum_input_tokens": 272001,
9631
+ "usd_per_token": "0.00003"
9632
+ },
9633
+ {
9634
+ "meter": "input_cache_read",
9635
+ "minimum_input_tokens": 0,
9636
+ "maximum_input_tokens": 272001,
9637
+ "usd_per_token": "0.0000002"
9638
+ },
9639
+ {
9640
+ "meter": "input_cache_read",
9641
+ "minimum_input_tokens": 272001,
9642
+ "usd_per_token": "0.0000004"
9643
+ },
9644
+ {
9645
+ "meter": "input_cache_write",
9646
+ "minimum_input_tokens": 0,
9647
+ "maximum_input_tokens": 272001,
9648
+ "usd_per_token": "0.000005"
9649
+ },
9650
+ {
9651
+ "meter": "input_cache_write",
9652
+ "minimum_input_tokens": 272001,
9653
+ "usd_per_token": "0.00001"
9654
+ }
9655
+ ]
9656
+ }
9657
+ }
9658
+ }
7661
9659
  },
7662
9660
  "grida": {
7663
9661
  "provider": "grida",
@@ -7985,6 +9983,80 @@
7985
9983
  "source_url": "https://developers.openai.com/api/docs/models/gpt-6.1-terra",
7986
9984
  "context_tokens": 1050000,
7987
9985
  "max_output_tokens": 128000
9986
+ },
9987
+ "modes": {
9988
+ "fast": {
9989
+ "source_url": "https://developers.openai.com/api/docs/guides/fast-mode",
9990
+ "request": {
9991
+ "service_tier": "fast"
9992
+ },
9993
+ "qualifications": [
9994
+ {
9995
+ "source_url": "https://developers.openai.com/api/docs/pricing.md#fast-pricing-data",
9996
+ "notes": "OpenAI separately publishes 12-hour cache-write rates of $5.00 in the short-context band and $10.00 in the long-context band per million tokens."
9997
+ }
9998
+ ],
9999
+ "limits": {
10000
+ "source_url": "https://developers.openai.com/api/docs/models/gpt-6.1-terra",
10001
+ "context_tokens": 1050000,
10002
+ "max_output_tokens": 128000
10003
+ },
10004
+ "token_pricing": {
10005
+ "source_url": "https://developers.openai.com/api/docs/pricing.md#fast-pricing-data",
10006
+ "unit": "usd_per_token",
10007
+ "scope": "Regular global Fast token rates, including 30-minute cache writes. Long-context rates apply to the entire request above 272,000 input tokens.",
10008
+ "input": "0.000002",
10009
+ "output": "0.00001",
10010
+ "input_cache_read": "0.0000001",
10011
+ "input_cache_write": "0.0000025",
10012
+ "tiers": [
10013
+ {
10014
+ "meter": "input",
10015
+ "minimum_input_tokens": 0,
10016
+ "maximum_input_tokens": 272001,
10017
+ "usd_per_token": "0.000002"
10018
+ },
10019
+ {
10020
+ "meter": "input",
10021
+ "minimum_input_tokens": 272001,
10022
+ "usd_per_token": "0.000004"
10023
+ },
10024
+ {
10025
+ "meter": "output",
10026
+ "minimum_input_tokens": 0,
10027
+ "maximum_input_tokens": 272001,
10028
+ "usd_per_token": "0.00001"
10029
+ },
10030
+ {
10031
+ "meter": "output",
10032
+ "minimum_input_tokens": 272001,
10033
+ "usd_per_token": "0.000015"
10034
+ },
10035
+ {
10036
+ "meter": "input_cache_read",
10037
+ "minimum_input_tokens": 0,
10038
+ "maximum_input_tokens": 272001,
10039
+ "usd_per_token": "0.0000001"
10040
+ },
10041
+ {
10042
+ "meter": "input_cache_read",
10043
+ "minimum_input_tokens": 272001,
10044
+ "usd_per_token": "0.0000002"
10045
+ },
10046
+ {
10047
+ "meter": "input_cache_write",
10048
+ "minimum_input_tokens": 0,
10049
+ "maximum_input_tokens": 272001,
10050
+ "usd_per_token": "0.0000025"
10051
+ },
10052
+ {
10053
+ "meter": "input_cache_write",
10054
+ "minimum_input_tokens": 272001,
10055
+ "usd_per_token": "0.000005"
10056
+ }
10057
+ ]
10058
+ }
10059
+ }
7988
10060
  }
7989
10061
  },
7990
10062
  "openrouter": {
@@ -8072,6 +10144,95 @@
8072
10144
  "source_url": "https://openrouter.ai/openai/gpt-6.1-terra",
8073
10145
  "context_tokens": 1050000,
8074
10146
  "max_output_tokens": 128000
10147
+ },
10148
+ "modes": {
10149
+ "fast": {
10150
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-6.1-terra/endpoints",
10151
+ "request": {
10152
+ "service_tier": "fast",
10153
+ "provider": {
10154
+ "only": [
10155
+ "openai/fast"
10156
+ ]
10157
+ }
10158
+ },
10159
+ "qualifications": [
10160
+ {
10161
+ "source_url": "https://openrouter.ai/docs/guides/features/service-tiers",
10162
+ "notes": "The provider.only tag selects the openai/fast endpoint. OpenRouter reports the tier that actually served the request."
10163
+ },
10164
+ {
10165
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-6.1-terra/endpoints",
10166
+ "notes": "The Fast endpoint publishes a separate maximum of 922,000 prompt tokens."
10167
+ }
10168
+ ],
10169
+ "limits": {
10170
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-6.1-terra/endpoints",
10171
+ "context_tokens": 1050000,
10172
+ "max_output_tokens": 128000
10173
+ },
10174
+ "capabilities": {
10175
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-6.1-terra/endpoints",
10176
+ "tools": true,
10177
+ "reasoning": true,
10178
+ "structured_output": true
10179
+ },
10180
+ "token_pricing": {
10181
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-6.1-terra/endpoints",
10182
+ "unit": "usd_per_token",
10183
+ "scope": "Regular token rates for requests served on the OpenRouter Fast endpoint. Optional tools and regional premiums are excluded.",
10184
+ "input": "0.000002",
10185
+ "output": "0.00001",
10186
+ "input_cache_read": "0.0000001",
10187
+ "input_cache_write": "0.0000025",
10188
+ "tiers": [
10189
+ {
10190
+ "meter": "input",
10191
+ "minimum_input_tokens": 0,
10192
+ "maximum_input_tokens": 272000,
10193
+ "usd_per_token": "0.000002"
10194
+ },
10195
+ {
10196
+ "meter": "input",
10197
+ "minimum_input_tokens": 272000,
10198
+ "usd_per_token": "0.000004"
10199
+ },
10200
+ {
10201
+ "meter": "output",
10202
+ "minimum_input_tokens": 0,
10203
+ "maximum_input_tokens": 272000,
10204
+ "usd_per_token": "0.00001"
10205
+ },
10206
+ {
10207
+ "meter": "output",
10208
+ "minimum_input_tokens": 272000,
10209
+ "usd_per_token": "0.000015"
10210
+ },
10211
+ {
10212
+ "meter": "input_cache_read",
10213
+ "minimum_input_tokens": 0,
10214
+ "maximum_input_tokens": 272000,
10215
+ "usd_per_token": "0.0000001"
10216
+ },
10217
+ {
10218
+ "meter": "input_cache_read",
10219
+ "minimum_input_tokens": 272000,
10220
+ "usd_per_token": "0.0000002"
10221
+ },
10222
+ {
10223
+ "meter": "input_cache_write",
10224
+ "minimum_input_tokens": 0,
10225
+ "maximum_input_tokens": 272000,
10226
+ "usd_per_token": "0.0000025"
10227
+ },
10228
+ {
10229
+ "meter": "input_cache_write",
10230
+ "minimum_input_tokens": 272000,
10231
+ "usd_per_token": "0.000005"
10232
+ }
10233
+ ]
10234
+ }
10235
+ }
8075
10236
  }
8076
10237
  },
8077
10238
  "vercel": {
@@ -8153,6 +10314,88 @@
8153
10314
  "source_url": "https://vercel.com/ai-gateway/models/gpt-6.1-terra",
8154
10315
  "context_tokens": 1050000,
8155
10316
  "max_output_tokens": 128000
10317
+ },
10318
+ "offerings": {
10319
+ "openai/gpt-6.1-terra-fast": {
10320
+ "id": "openai/gpt-6.1-terra-fast",
10321
+ "canonical_model_id": "openai/gpt-6.1-terra",
10322
+ "mode": "fast",
10323
+ "label": "GPT-6.1 Terra (Fast)",
10324
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-6.1-terra-fast/endpoints",
10325
+ "qualifications": [
10326
+ {
10327
+ "source_url": "https://vercel.com/docs/ai-gateway/models-and-providers/fast-mode",
10328
+ "notes": "Vercel can serve the base route at Standard speed when Fast capacity is unavailable. Fast prices apply when the request was served Fast."
10329
+ }
10330
+ ],
10331
+ "limits": {
10332
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-6.1-terra-fast/endpoints",
10333
+ "context_tokens": 1050000,
10334
+ "max_output_tokens": 128000
10335
+ },
10336
+ "capabilities": {
10337
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-6.1-terra-fast/endpoints",
10338
+ "image_input": true,
10339
+ "tools": true,
10340
+ "reasoning": true,
10341
+ "structured_output": true
10342
+ },
10343
+ "token_pricing": {
10344
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-6.1-terra-fast/endpoints",
10345
+ "unit": "usd_per_token",
10346
+ "scope": "Regular global token rates for requests served on the Vercel Fast endpoint. Optional tools and regional premiums are excluded.",
10347
+ "input": "0.000002",
10348
+ "output": "0.00001",
10349
+ "input_cache_read": "0.0000001",
10350
+ "input_cache_write": "0.0000025",
10351
+ "tiers": [
10352
+ {
10353
+ "meter": "input",
10354
+ "minimum_input_tokens": 0,
10355
+ "maximum_input_tokens": 272001,
10356
+ "usd_per_token": "0.000002"
10357
+ },
10358
+ {
10359
+ "meter": "input",
10360
+ "minimum_input_tokens": 272001,
10361
+ "usd_per_token": "0.000004"
10362
+ },
10363
+ {
10364
+ "meter": "output",
10365
+ "minimum_input_tokens": 0,
10366
+ "maximum_input_tokens": 272001,
10367
+ "usd_per_token": "0.00001"
10368
+ },
10369
+ {
10370
+ "meter": "output",
10371
+ "minimum_input_tokens": 272001,
10372
+ "usd_per_token": "0.000015"
10373
+ },
10374
+ {
10375
+ "meter": "input_cache_read",
10376
+ "minimum_input_tokens": 0,
10377
+ "maximum_input_tokens": 272001,
10378
+ "usd_per_token": "0.0000001"
10379
+ },
10380
+ {
10381
+ "meter": "input_cache_read",
10382
+ "minimum_input_tokens": 272001,
10383
+ "usd_per_token": "0.0000002"
10384
+ },
10385
+ {
10386
+ "meter": "input_cache_write",
10387
+ "minimum_input_tokens": 0,
10388
+ "maximum_input_tokens": 272001,
10389
+ "usd_per_token": "0.0000025"
10390
+ },
10391
+ {
10392
+ "meter": "input_cache_write",
10393
+ "minimum_input_tokens": 272001,
10394
+ "usd_per_token": "0.000005"
10395
+ }
10396
+ ]
10397
+ }
10398
+ }
8156
10399
  }
8157
10400
  },
8158
10401
  "grida": {
@@ -8484,7 +10727,85 @@
8484
10727
  }
8485
10728
  }
8486
10729
  }
8487
- ]
10730
+ ],
10731
+ "modes": {
10732
+ "fast": {
10733
+ "source_url": "https://developers.openai.com/api/docs/guides/fast-mode",
10734
+ "request": {
10735
+ "service_tier": "fast"
10736
+ },
10737
+ "qualifications": [
10738
+ {
10739
+ "source_url": "https://developers.openai.com/api/docs/pricing.md#fast-pricing-data",
10740
+ "notes": "OpenAI separately publishes 12-hour cache-write rates of $40.00 in the short-context band and $80.00 in the long-context band per million tokens."
10741
+ },
10742
+ {
10743
+ "source_url": "https://developers.openai.com/api/docs/models/gpt-6.2-astra",
10744
+ "notes": "The model publishes a separate maximum of 922,000 input tokens."
10745
+ }
10746
+ ],
10747
+ "limits": {
10748
+ "source_url": "https://developers.openai.com/api/docs/models/gpt-6.2-astra",
10749
+ "context_tokens": 1050000,
10750
+ "max_output_tokens": 128000
10751
+ },
10752
+ "token_pricing": {
10753
+ "source_url": "https://developers.openai.com/api/docs/pricing.md#fast-pricing-data",
10754
+ "unit": "usd_per_token",
10755
+ "scope": "Regular global Fast token rates, including 30-minute cache writes. Long-context rates apply to the entire request above 272,000 input tokens.",
10756
+ "input": "0.000016",
10757
+ "output": "0.00008",
10758
+ "input_cache_read": "0.0000008",
10759
+ "input_cache_write": "0.00002",
10760
+ "tiers": [
10761
+ {
10762
+ "meter": "input",
10763
+ "minimum_input_tokens": 0,
10764
+ "maximum_input_tokens": 272001,
10765
+ "usd_per_token": "0.000016"
10766
+ },
10767
+ {
10768
+ "meter": "input",
10769
+ "minimum_input_tokens": 272001,
10770
+ "usd_per_token": "0.000032"
10771
+ },
10772
+ {
10773
+ "meter": "output",
10774
+ "minimum_input_tokens": 0,
10775
+ "maximum_input_tokens": 272001,
10776
+ "usd_per_token": "0.00008"
10777
+ },
10778
+ {
10779
+ "meter": "output",
10780
+ "minimum_input_tokens": 272001,
10781
+ "usd_per_token": "0.00012"
10782
+ },
10783
+ {
10784
+ "meter": "input_cache_read",
10785
+ "minimum_input_tokens": 0,
10786
+ "maximum_input_tokens": 272001,
10787
+ "usd_per_token": "0.0000008"
10788
+ },
10789
+ {
10790
+ "meter": "input_cache_read",
10791
+ "minimum_input_tokens": 272001,
10792
+ "usd_per_token": "0.0000016"
10793
+ },
10794
+ {
10795
+ "meter": "input_cache_write",
10796
+ "minimum_input_tokens": 0,
10797
+ "maximum_input_tokens": 272001,
10798
+ "usd_per_token": "0.00002"
10799
+ },
10800
+ {
10801
+ "meter": "input_cache_write",
10802
+ "minimum_input_tokens": 272001,
10803
+ "usd_per_token": "0.00004"
10804
+ }
10805
+ ]
10806
+ }
10807
+ }
10808
+ }
8488
10809
  },
8489
10810
  "openrouter": {
8490
10811
  "provider": "openrouter",
@@ -8570,7 +10891,96 @@
8570
10891
  "input": "text",
8571
10892
  "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-6.2-astra/endpoints"
8572
10893
  }
8573
- ]
10894
+ ],
10895
+ "modes": {
10896
+ "fast": {
10897
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-6.2-astra/endpoints",
10898
+ "request": {
10899
+ "service_tier": "fast",
10900
+ "provider": {
10901
+ "only": [
10902
+ "openai/fast"
10903
+ ]
10904
+ }
10905
+ },
10906
+ "qualifications": [
10907
+ {
10908
+ "source_url": "https://openrouter.ai/docs/guides/features/service-tiers",
10909
+ "notes": "The provider.only tag selects the openai/fast endpoint. OpenRouter reports the tier that actually served the request."
10910
+ },
10911
+ {
10912
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-6.2-astra/endpoints",
10913
+ "notes": "The Fast endpoint publishes a separate maximum of 922,000 prompt tokens."
10914
+ }
10915
+ ],
10916
+ "limits": {
10917
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-6.2-astra/endpoints",
10918
+ "context_tokens": 1050000,
10919
+ "max_output_tokens": 128000
10920
+ },
10921
+ "capabilities": {
10922
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-6.2-astra/endpoints",
10923
+ "tools": true,
10924
+ "reasoning": true,
10925
+ "structured_output": true
10926
+ },
10927
+ "token_pricing": {
10928
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-6.2-astra/endpoints",
10929
+ "unit": "usd_per_token",
10930
+ "scope": "Regular token rates for requests served on the OpenRouter Fast endpoint. Optional tools and regional premiums are excluded.",
10931
+ "input": "0.000016",
10932
+ "output": "0.00008",
10933
+ "input_cache_read": "0.0000008",
10934
+ "input_cache_write": "0.00002",
10935
+ "tiers": [
10936
+ {
10937
+ "meter": "input",
10938
+ "minimum_input_tokens": 0,
10939
+ "maximum_input_tokens": 272000,
10940
+ "usd_per_token": "0.000016"
10941
+ },
10942
+ {
10943
+ "meter": "input",
10944
+ "minimum_input_tokens": 272000,
10945
+ "usd_per_token": "0.000032"
10946
+ },
10947
+ {
10948
+ "meter": "output",
10949
+ "minimum_input_tokens": 0,
10950
+ "maximum_input_tokens": 272000,
10951
+ "usd_per_token": "0.00008"
10952
+ },
10953
+ {
10954
+ "meter": "output",
10955
+ "minimum_input_tokens": 272000,
10956
+ "usd_per_token": "0.00012"
10957
+ },
10958
+ {
10959
+ "meter": "input_cache_read",
10960
+ "minimum_input_tokens": 0,
10961
+ "maximum_input_tokens": 272000,
10962
+ "usd_per_token": "0.0000008"
10963
+ },
10964
+ {
10965
+ "meter": "input_cache_read",
10966
+ "minimum_input_tokens": 272000,
10967
+ "usd_per_token": "0.0000016"
10968
+ },
10969
+ {
10970
+ "meter": "input_cache_write",
10971
+ "minimum_input_tokens": 0,
10972
+ "maximum_input_tokens": 272000,
10973
+ "usd_per_token": "0.00002"
10974
+ },
10975
+ {
10976
+ "meter": "input_cache_write",
10977
+ "minimum_input_tokens": 272000,
10978
+ "usd_per_token": "0.00004"
10979
+ }
10980
+ ]
10981
+ }
10982
+ }
10983
+ }
8574
10984
  },
8575
10985
  "vercel": {
8576
10986
  "provider": "vercel",
@@ -8656,7 +11066,89 @@
8656
11066
  "input": "text",
8657
11067
  "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-6.2-astra/endpoints"
8658
11068
  }
8659
- ]
11069
+ ],
11070
+ "offerings": {
11071
+ "openai/gpt-6.2-astra-fast": {
11072
+ "id": "openai/gpt-6.2-astra-fast",
11073
+ "canonical_model_id": "openai/gpt-6.2-astra",
11074
+ "mode": "fast",
11075
+ "label": "GPT-6.2 Astra (Fast)",
11076
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-6.2-astra-fast/endpoints",
11077
+ "qualifications": [
11078
+ {
11079
+ "source_url": "https://vercel.com/docs/ai-gateway/models-and-providers/fast-mode",
11080
+ "notes": "Vercel can serve the base route at Standard speed when Fast capacity is unavailable. Fast prices apply when the request was served Fast."
11081
+ }
11082
+ ],
11083
+ "limits": {
11084
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-6.2-astra-fast/endpoints",
11085
+ "context_tokens": 1050000,
11086
+ "max_output_tokens": 128000
11087
+ },
11088
+ "capabilities": {
11089
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-6.2-astra-fast/endpoints",
11090
+ "image_input": true,
11091
+ "tools": true,
11092
+ "reasoning": true,
11093
+ "structured_output": true
11094
+ },
11095
+ "token_pricing": {
11096
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-6.2-astra-fast/endpoints",
11097
+ "unit": "usd_per_token",
11098
+ "scope": "Regular global token rates for requests served on the Vercel Fast endpoint. Optional tools and regional premiums are excluded.",
11099
+ "input": "0.000016",
11100
+ "output": "0.00008",
11101
+ "input_cache_read": "0.0000008",
11102
+ "input_cache_write": "0.00002",
11103
+ "tiers": [
11104
+ {
11105
+ "meter": "input",
11106
+ "minimum_input_tokens": 0,
11107
+ "maximum_input_tokens": 272001,
11108
+ "usd_per_token": "0.000016"
11109
+ },
11110
+ {
11111
+ "meter": "input",
11112
+ "minimum_input_tokens": 272001,
11113
+ "usd_per_token": "0.000032"
11114
+ },
11115
+ {
11116
+ "meter": "output",
11117
+ "minimum_input_tokens": 0,
11118
+ "maximum_input_tokens": 272001,
11119
+ "usd_per_token": "0.00008"
11120
+ },
11121
+ {
11122
+ "meter": "output",
11123
+ "minimum_input_tokens": 272001,
11124
+ "usd_per_token": "0.00012"
11125
+ },
11126
+ {
11127
+ "meter": "input_cache_read",
11128
+ "minimum_input_tokens": 0,
11129
+ "maximum_input_tokens": 272001,
11130
+ "usd_per_token": "0.0000008"
11131
+ },
11132
+ {
11133
+ "meter": "input_cache_read",
11134
+ "minimum_input_tokens": 272001,
11135
+ "usd_per_token": "0.0000016"
11136
+ },
11137
+ {
11138
+ "meter": "input_cache_write",
11139
+ "minimum_input_tokens": 0,
11140
+ "maximum_input_tokens": 272001,
11141
+ "usd_per_token": "0.00002"
11142
+ },
11143
+ {
11144
+ "meter": "input_cache_write",
11145
+ "minimum_input_tokens": 272001,
11146
+ "usd_per_token": "0.00004"
11147
+ }
11148
+ ]
11149
+ }
11150
+ }
11151
+ }
8660
11152
  },
8661
11153
  "grida": {
8662
11154
  "provider": "grida",
@@ -8987,7 +11479,85 @@
8987
11479
  }
8988
11480
  }
8989
11481
  }
8990
- ]
11482
+ ],
11483
+ "modes": {
11484
+ "fast": {
11485
+ "source_url": "https://developers.openai.com/api/docs/guides/fast-mode",
11486
+ "request": {
11487
+ "service_tier": "fast"
11488
+ },
11489
+ "qualifications": [
11490
+ {
11491
+ "source_url": "https://developers.openai.com/api/docs/pricing.md#fast-pricing-data",
11492
+ "notes": "OpenAI separately publishes 12-hour cache-write rates of $10.00 in the short-context band and $20.00 in the long-context band per million tokens."
11493
+ },
11494
+ {
11495
+ "source_url": "https://developers.openai.com/api/docs/models/gpt-6.2-sol",
11496
+ "notes": "The model publishes a separate maximum of 922,000 input tokens."
11497
+ }
11498
+ ],
11499
+ "limits": {
11500
+ "source_url": "https://developers.openai.com/api/docs/models/gpt-6.2-sol",
11501
+ "context_tokens": 1050000,
11502
+ "max_output_tokens": 128000
11503
+ },
11504
+ "token_pricing": {
11505
+ "source_url": "https://developers.openai.com/api/docs/pricing.md#fast-pricing-data",
11506
+ "unit": "usd_per_token",
11507
+ "scope": "Regular global Fast token rates, including 30-minute cache writes. Long-context rates apply to the entire request above 272,000 input tokens.",
11508
+ "input": "0.000004",
11509
+ "output": "0.00002",
11510
+ "input_cache_read": "0.0000002",
11511
+ "input_cache_write": "0.000005",
11512
+ "tiers": [
11513
+ {
11514
+ "meter": "input",
11515
+ "minimum_input_tokens": 0,
11516
+ "maximum_input_tokens": 272001,
11517
+ "usd_per_token": "0.000004"
11518
+ },
11519
+ {
11520
+ "meter": "input",
11521
+ "minimum_input_tokens": 272001,
11522
+ "usd_per_token": "0.000008"
11523
+ },
11524
+ {
11525
+ "meter": "output",
11526
+ "minimum_input_tokens": 0,
11527
+ "maximum_input_tokens": 272001,
11528
+ "usd_per_token": "0.00002"
11529
+ },
11530
+ {
11531
+ "meter": "output",
11532
+ "minimum_input_tokens": 272001,
11533
+ "usd_per_token": "0.00003"
11534
+ },
11535
+ {
11536
+ "meter": "input_cache_read",
11537
+ "minimum_input_tokens": 0,
11538
+ "maximum_input_tokens": 272001,
11539
+ "usd_per_token": "0.0000002"
11540
+ },
11541
+ {
11542
+ "meter": "input_cache_read",
11543
+ "minimum_input_tokens": 272001,
11544
+ "usd_per_token": "0.0000004"
11545
+ },
11546
+ {
11547
+ "meter": "input_cache_write",
11548
+ "minimum_input_tokens": 0,
11549
+ "maximum_input_tokens": 272001,
11550
+ "usd_per_token": "0.000005"
11551
+ },
11552
+ {
11553
+ "meter": "input_cache_write",
11554
+ "minimum_input_tokens": 272001,
11555
+ "usd_per_token": "0.00001"
11556
+ }
11557
+ ]
11558
+ }
11559
+ }
11560
+ }
8991
11561
  },
8992
11562
  "openrouter": {
8993
11563
  "provider": "openrouter",
@@ -9073,7 +11643,96 @@
9073
11643
  "input": "text",
9074
11644
  "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-6.2-sol/endpoints"
9075
11645
  }
9076
- ]
11646
+ ],
11647
+ "modes": {
11648
+ "fast": {
11649
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-6.2-sol/endpoints",
11650
+ "request": {
11651
+ "service_tier": "fast",
11652
+ "provider": {
11653
+ "only": [
11654
+ "openai/fast"
11655
+ ]
11656
+ }
11657
+ },
11658
+ "qualifications": [
11659
+ {
11660
+ "source_url": "https://openrouter.ai/docs/guides/features/service-tiers",
11661
+ "notes": "The provider.only tag selects the openai/fast endpoint. OpenRouter reports the tier that actually served the request."
11662
+ },
11663
+ {
11664
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-6.2-sol/endpoints",
11665
+ "notes": "The Fast endpoint publishes a separate maximum of 922,000 prompt tokens."
11666
+ }
11667
+ ],
11668
+ "limits": {
11669
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-6.2-sol/endpoints",
11670
+ "context_tokens": 1050000,
11671
+ "max_output_tokens": 128000
11672
+ },
11673
+ "capabilities": {
11674
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-6.2-sol/endpoints",
11675
+ "tools": true,
11676
+ "reasoning": true,
11677
+ "structured_output": true
11678
+ },
11679
+ "token_pricing": {
11680
+ "source_url": "https://openrouter.ai/api/v1/models/openai/gpt-6.2-sol/endpoints",
11681
+ "unit": "usd_per_token",
11682
+ "scope": "Regular token rates for requests served on the OpenRouter Fast endpoint. Optional tools and regional premiums are excluded.",
11683
+ "input": "0.000004",
11684
+ "output": "0.00002",
11685
+ "input_cache_read": "0.0000002",
11686
+ "input_cache_write": "0.000005",
11687
+ "tiers": [
11688
+ {
11689
+ "meter": "input",
11690
+ "minimum_input_tokens": 0,
11691
+ "maximum_input_tokens": 272000,
11692
+ "usd_per_token": "0.000004"
11693
+ },
11694
+ {
11695
+ "meter": "input",
11696
+ "minimum_input_tokens": 272000,
11697
+ "usd_per_token": "0.000008"
11698
+ },
11699
+ {
11700
+ "meter": "output",
11701
+ "minimum_input_tokens": 0,
11702
+ "maximum_input_tokens": 272000,
11703
+ "usd_per_token": "0.00002"
11704
+ },
11705
+ {
11706
+ "meter": "output",
11707
+ "minimum_input_tokens": 272000,
11708
+ "usd_per_token": "0.00003"
11709
+ },
11710
+ {
11711
+ "meter": "input_cache_read",
11712
+ "minimum_input_tokens": 0,
11713
+ "maximum_input_tokens": 272000,
11714
+ "usd_per_token": "0.0000002"
11715
+ },
11716
+ {
11717
+ "meter": "input_cache_read",
11718
+ "minimum_input_tokens": 272000,
11719
+ "usd_per_token": "0.0000004"
11720
+ },
11721
+ {
11722
+ "meter": "input_cache_write",
11723
+ "minimum_input_tokens": 0,
11724
+ "maximum_input_tokens": 272000,
11725
+ "usd_per_token": "0.000005"
11726
+ },
11727
+ {
11728
+ "meter": "input_cache_write",
11729
+ "minimum_input_tokens": 272000,
11730
+ "usd_per_token": "0.00001"
11731
+ }
11732
+ ]
11733
+ }
11734
+ }
11735
+ }
9077
11736
  },
9078
11737
  "vercel": {
9079
11738
  "provider": "vercel",
@@ -9159,7 +11818,89 @@
9159
11818
  "input": "text",
9160
11819
  "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-6.2-sol/endpoints"
9161
11820
  }
9162
- ]
11821
+ ],
11822
+ "offerings": {
11823
+ "openai/gpt-6.2-sol-fast": {
11824
+ "id": "openai/gpt-6.2-sol-fast",
11825
+ "canonical_model_id": "openai/gpt-6.2-sol",
11826
+ "mode": "fast",
11827
+ "label": "GPT-6.2 Sol (Fast)",
11828
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-6.2-sol-fast/endpoints",
11829
+ "qualifications": [
11830
+ {
11831
+ "source_url": "https://vercel.com/docs/ai-gateway/models-and-providers/fast-mode",
11832
+ "notes": "Vercel can serve the base route at Standard speed when Fast capacity is unavailable. Fast prices apply when the request was served Fast."
11833
+ }
11834
+ ],
11835
+ "limits": {
11836
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-6.2-sol-fast/endpoints",
11837
+ "context_tokens": 1050000,
11838
+ "max_output_tokens": 128000
11839
+ },
11840
+ "capabilities": {
11841
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-6.2-sol-fast/endpoints",
11842
+ "image_input": true,
11843
+ "tools": true,
11844
+ "reasoning": true,
11845
+ "structured_output": true
11846
+ },
11847
+ "token_pricing": {
11848
+ "source_url": "https://ai-gateway.vercel.sh/v1/models/openai/gpt-6.2-sol-fast/endpoints",
11849
+ "unit": "usd_per_token",
11850
+ "scope": "Regular global token rates for requests served on the Vercel Fast endpoint. Optional tools and regional premiums are excluded.",
11851
+ "input": "0.000004",
11852
+ "output": "0.00002",
11853
+ "input_cache_read": "0.0000002",
11854
+ "input_cache_write": "0.000005",
11855
+ "tiers": [
11856
+ {
11857
+ "meter": "input",
11858
+ "minimum_input_tokens": 0,
11859
+ "maximum_input_tokens": 272001,
11860
+ "usd_per_token": "0.000004"
11861
+ },
11862
+ {
11863
+ "meter": "input",
11864
+ "minimum_input_tokens": 272001,
11865
+ "usd_per_token": "0.000008"
11866
+ },
11867
+ {
11868
+ "meter": "output",
11869
+ "minimum_input_tokens": 0,
11870
+ "maximum_input_tokens": 272001,
11871
+ "usd_per_token": "0.00002"
11872
+ },
11873
+ {
11874
+ "meter": "output",
11875
+ "minimum_input_tokens": 272001,
11876
+ "usd_per_token": "0.00003"
11877
+ },
11878
+ {
11879
+ "meter": "input_cache_read",
11880
+ "minimum_input_tokens": 0,
11881
+ "maximum_input_tokens": 272001,
11882
+ "usd_per_token": "0.0000002"
11883
+ },
11884
+ {
11885
+ "meter": "input_cache_read",
11886
+ "minimum_input_tokens": 272001,
11887
+ "usd_per_token": "0.0000004"
11888
+ },
11889
+ {
11890
+ "meter": "input_cache_write",
11891
+ "minimum_input_tokens": 0,
11892
+ "maximum_input_tokens": 272001,
11893
+ "usd_per_token": "0.000005"
11894
+ },
11895
+ {
11896
+ "meter": "input_cache_write",
11897
+ "minimum_input_tokens": 272001,
11898
+ "usd_per_token": "0.00001"
11899
+ }
11900
+ ]
11901
+ }
11902
+ }
11903
+ }
9163
11904
  },
9164
11905
  "grida": {
9165
11906
  "provider": "grida",