@dreb/ai 2.34.2 → 2.35.0

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.
@@ -70,6 +70,23 @@ export const MODELS = {
70
70
  contextWindow: 300000,
71
71
  maxTokens: 8192,
72
72
  },
73
+ "anthropic.claude-fable-5": {
74
+ id: "anthropic.claude-fable-5",
75
+ name: "Claude Fable 5",
76
+ api: "bedrock-converse-stream",
77
+ provider: "amazon-bedrock",
78
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
79
+ reasoning: true,
80
+ input: ["text", "image"],
81
+ cost: {
82
+ input: 10,
83
+ output: 50,
84
+ cacheRead: 1,
85
+ cacheWrite: 12.5,
86
+ },
87
+ contextWindow: 1000000,
88
+ maxTokens: 128000,
89
+ },
73
90
  "anthropic.claude-haiku-4-5-20251001-v1:0": {
74
91
  id: "anthropic.claude-haiku-4-5-20251001-v1:0",
75
92
  name: "Claude Haiku 4.5",
@@ -206,6 +223,23 @@ export const MODELS = {
206
223
  contextWindow: 1000000,
207
224
  maxTokens: 64000,
208
225
  },
226
+ "anthropic.claude-sonnet-5": {
227
+ id: "anthropic.claude-sonnet-5",
228
+ name: "Claude Sonnet 5",
229
+ api: "bedrock-converse-stream",
230
+ provider: "amazon-bedrock",
231
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
232
+ reasoning: true,
233
+ input: ["text", "image"],
234
+ cost: {
235
+ input: 2,
236
+ output: 10,
237
+ cacheRead: 0.2,
238
+ cacheWrite: 2.5,
239
+ },
240
+ contextWindow: 1000000,
241
+ maxTokens: 128000,
242
+ },
209
243
  "au.anthropic.claude-haiku-4-5-20251001-v1:0": {
210
244
  id: "au.anthropic.claude-haiku-4-5-20251001-v1:0",
211
245
  name: "Claude Haiku 4.5 (AU)",
@@ -291,6 +325,23 @@ export const MODELS = {
291
325
  contextWindow: 1000000,
292
326
  maxTokens: 128000,
293
327
  },
328
+ "au.anthropic.claude-sonnet-5": {
329
+ id: "au.anthropic.claude-sonnet-5",
330
+ name: "Claude Sonnet 5 (AU)",
331
+ api: "bedrock-converse-stream",
332
+ provider: "amazon-bedrock",
333
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
334
+ reasoning: true,
335
+ input: ["text", "image"],
336
+ cost: {
337
+ input: 2,
338
+ output: 10,
339
+ cacheRead: 0.2,
340
+ cacheWrite: 2.5,
341
+ },
342
+ contextWindow: 1000000,
343
+ maxTokens: 128000,
344
+ },
294
345
  "deepseek.r1-v1:0": {
295
346
  id: "deepseek.r1-v1:0",
296
347
  name: "DeepSeek-R1",
@@ -478,6 +529,23 @@ export const MODELS = {
478
529
  contextWindow: 1000000,
479
530
  maxTokens: 64000,
480
531
  },
532
+ "eu.anthropic.claude-sonnet-5": {
533
+ id: "eu.anthropic.claude-sonnet-5",
534
+ name: "Claude Sonnet 5 (EU)",
535
+ api: "bedrock-converse-stream",
536
+ provider: "amazon-bedrock",
537
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
538
+ reasoning: true,
539
+ input: ["text", "image"],
540
+ cost: {
541
+ input: 2.2,
542
+ output: 11,
543
+ cacheRead: 0.22,
544
+ cacheWrite: 2.75,
545
+ },
546
+ contextWindow: 1000000,
547
+ maxTokens: 128000,
548
+ },
481
549
  "global.anthropic.claude-fable-5": {
482
550
  id: "global.anthropic.claude-fable-5",
483
551
  name: "Claude Fable 5 (Global)",
@@ -614,6 +682,23 @@ export const MODELS = {
614
682
  contextWindow: 1000000,
615
683
  maxTokens: 64000,
616
684
  },
685
+ "global.anthropic.claude-sonnet-5": {
686
+ id: "global.anthropic.claude-sonnet-5",
687
+ name: "Claude Sonnet 5 (Global)",
688
+ api: "bedrock-converse-stream",
689
+ provider: "amazon-bedrock",
690
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
691
+ reasoning: true,
692
+ input: ["text", "image"],
693
+ cost: {
694
+ input: 2,
695
+ output: 10,
696
+ cacheRead: 0.2,
697
+ cacheWrite: 2.5,
698
+ },
699
+ contextWindow: 1000000,
700
+ maxTokens: 128000,
701
+ },
617
702
  "google.gemma-3-27b-it": {
618
703
  id: "google.gemma-3-27b-it",
619
704
  name: "Google Gemma 3 27B Instruct",
@@ -648,6 +733,23 @@ export const MODELS = {
648
733
  contextWindow: 128000,
649
734
  maxTokens: 4096,
650
735
  },
736
+ "jp.anthropic.claude-haiku-4-5-20251001-v1:0": {
737
+ id: "jp.anthropic.claude-haiku-4-5-20251001-v1:0",
738
+ name: "Claude Haiku 4.5 (JP)",
739
+ api: "bedrock-converse-stream",
740
+ provider: "amazon-bedrock",
741
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
742
+ reasoning: true,
743
+ input: ["text", "image"],
744
+ cost: {
745
+ input: 1,
746
+ output: 5,
747
+ cacheRead: 0.1,
748
+ cacheWrite: 1.25,
749
+ },
750
+ contextWindow: 200000,
751
+ maxTokens: 64000,
752
+ },
651
753
  "jp.anthropic.claude-opus-4-7": {
652
754
  id: "jp.anthropic.claude-opus-4-7",
653
755
  name: "Claude Opus 4.7 (JP)",
@@ -716,6 +818,23 @@ export const MODELS = {
716
818
  contextWindow: 1000000,
717
819
  maxTokens: 64000,
718
820
  },
821
+ "jp.anthropic.claude-sonnet-5": {
822
+ id: "jp.anthropic.claude-sonnet-5",
823
+ name: "Claude Sonnet 5 (JP)",
824
+ api: "bedrock-converse-stream",
825
+ provider: "amazon-bedrock",
826
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
827
+ reasoning: true,
828
+ input: ["text", "image"],
829
+ cost: {
830
+ input: 2,
831
+ output: 10,
832
+ cacheRead: 0.2,
833
+ cacheWrite: 2.5,
834
+ },
835
+ contextWindow: 1000000,
836
+ maxTokens: 128000,
837
+ },
719
838
  "meta.llama3-1-70b-instruct-v1:0": {
720
839
  id: "meta.llama3-1-70b-instruct-v1:0",
721
840
  name: "Llama 3.1 70B Instruct",
@@ -1515,6 +1634,23 @@ export const MODELS = {
1515
1634
  contextWindow: 1000000,
1516
1635
  maxTokens: 64000,
1517
1636
  },
1637
+ "us.anthropic.claude-sonnet-5": {
1638
+ id: "us.anthropic.claude-sonnet-5",
1639
+ name: "Claude Sonnet 5 (US)",
1640
+ api: "bedrock-converse-stream",
1641
+ provider: "amazon-bedrock",
1642
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1643
+ reasoning: true,
1644
+ input: ["text", "image"],
1645
+ cost: {
1646
+ input: 2,
1647
+ output: 10,
1648
+ cacheRead: 0.2,
1649
+ cacheWrite: 2.5,
1650
+ },
1651
+ contextWindow: 1000000,
1652
+ maxTokens: 128000,
1653
+ },
1518
1654
  "us.deepseek.r1-v1:0": {
1519
1655
  id: "us.deepseek.r1-v1:0",
1520
1656
  name: "DeepSeek-R1 (US)",
@@ -1600,6 +1736,23 @@ export const MODELS = {
1600
1736
  contextWindow: 1040000,
1601
1737
  maxTokens: 8192,
1602
1738
  },
1739
+ "xai.grok-4.3": {
1740
+ id: "xai.grok-4.3",
1741
+ name: "Grok 4.3",
1742
+ api: "bedrock-converse-stream",
1743
+ provider: "amazon-bedrock",
1744
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1745
+ reasoning: true,
1746
+ input: ["text", "image"],
1747
+ cost: {
1748
+ input: 1.25,
1749
+ output: 2.5,
1750
+ cacheRead: 0.2,
1751
+ cacheWrite: 0,
1752
+ },
1753
+ contextWindow: 1000000,
1754
+ maxTokens: 131072,
1755
+ },
1603
1756
  "zai.glm-4.7": {
1604
1757
  id: "zai.glm-4.7",
1605
1758
  name: "GLM-4.7",
@@ -1653,108 +1806,6 @@ export const MODELS = {
1653
1806
  },
1654
1807
  },
1655
1808
  "anthropic": {
1656
- "claude-3-5-sonnet-20240620": {
1657
- id: "claude-3-5-sonnet-20240620",
1658
- name: "Claude Sonnet 3.5",
1659
- api: "anthropic-messages",
1660
- provider: "anthropic",
1661
- baseUrl: "https://api.anthropic.com",
1662
- reasoning: false,
1663
- input: ["text", "image"],
1664
- cost: {
1665
- input: 3,
1666
- output: 15,
1667
- cacheRead: 0.3,
1668
- cacheWrite: 3.75,
1669
- },
1670
- contextWindow: 200000,
1671
- maxTokens: 8192,
1672
- },
1673
- "claude-3-5-sonnet-20241022": {
1674
- id: "claude-3-5-sonnet-20241022",
1675
- name: "Claude Sonnet 3.5 v2",
1676
- api: "anthropic-messages",
1677
- provider: "anthropic",
1678
- baseUrl: "https://api.anthropic.com",
1679
- reasoning: false,
1680
- input: ["text", "image"],
1681
- cost: {
1682
- input: 3,
1683
- output: 15,
1684
- cacheRead: 0.3,
1685
- cacheWrite: 3.75,
1686
- },
1687
- contextWindow: 200000,
1688
- maxTokens: 8192,
1689
- },
1690
- "claude-3-7-sonnet-20250219": {
1691
- id: "claude-3-7-sonnet-20250219",
1692
- name: "Claude Sonnet 3.7",
1693
- api: "anthropic-messages",
1694
- provider: "anthropic",
1695
- baseUrl: "https://api.anthropic.com",
1696
- reasoning: true,
1697
- input: ["text", "image"],
1698
- cost: {
1699
- input: 3,
1700
- output: 15,
1701
- cacheRead: 0.3,
1702
- cacheWrite: 3.75,
1703
- },
1704
- contextWindow: 200000,
1705
- maxTokens: 64000,
1706
- },
1707
- "claude-3-haiku-20240307": {
1708
- id: "claude-3-haiku-20240307",
1709
- name: "Claude Haiku 3",
1710
- api: "anthropic-messages",
1711
- provider: "anthropic",
1712
- baseUrl: "https://api.anthropic.com",
1713
- reasoning: false,
1714
- input: ["text", "image"],
1715
- cost: {
1716
- input: 0.25,
1717
- output: 1.25,
1718
- cacheRead: 0.03,
1719
- cacheWrite: 0.3,
1720
- },
1721
- contextWindow: 200000,
1722
- maxTokens: 4096,
1723
- },
1724
- "claude-3-opus-20240229": {
1725
- id: "claude-3-opus-20240229",
1726
- name: "Claude Opus 3",
1727
- api: "anthropic-messages",
1728
- provider: "anthropic",
1729
- baseUrl: "https://api.anthropic.com",
1730
- reasoning: false,
1731
- input: ["text", "image"],
1732
- cost: {
1733
- input: 15,
1734
- output: 75,
1735
- cacheRead: 1.5,
1736
- cacheWrite: 18.75,
1737
- },
1738
- contextWindow: 200000,
1739
- maxTokens: 4096,
1740
- },
1741
- "claude-3-sonnet-20240229": {
1742
- id: "claude-3-sonnet-20240229",
1743
- name: "Claude Sonnet 3",
1744
- api: "anthropic-messages",
1745
- provider: "anthropic",
1746
- baseUrl: "https://api.anthropic.com",
1747
- reasoning: false,
1748
- input: ["text", "image"],
1749
- cost: {
1750
- input: 3,
1751
- output: 15,
1752
- cacheRead: 0.3,
1753
- cacheWrite: 0.3,
1754
- },
1755
- contextWindow: 200000,
1756
- maxTokens: 4096,
1757
- },
1758
1809
  "claude-fable-5": {
1759
1810
  id: "claude-fable-5",
1760
1811
  name: "Claude Fable 5",
@@ -1806,23 +1857,6 @@ export const MODELS = {
1806
1857
  contextWindow: 200000,
1807
1858
  maxTokens: 64000,
1808
1859
  },
1809
- "claude-opus-4-0": {
1810
- id: "claude-opus-4-0",
1811
- name: "Claude Opus 4 (latest)",
1812
- api: "anthropic-messages",
1813
- provider: "anthropic",
1814
- baseUrl: "https://api.anthropic.com",
1815
- reasoning: true,
1816
- input: ["text", "image"],
1817
- cost: {
1818
- input: 15,
1819
- output: 75,
1820
- cacheRead: 1.5,
1821
- cacheWrite: 18.75,
1822
- },
1823
- contextWindow: 200000,
1824
- maxTokens: 32000,
1825
- },
1826
1860
  "claude-opus-4-1": {
1827
1861
  id: "claude-opus-4-1",
1828
1862
  name: "Claude Opus 4.1 (latest)",
@@ -1857,23 +1891,6 @@ export const MODELS = {
1857
1891
  contextWindow: 200000,
1858
1892
  maxTokens: 32000,
1859
1893
  },
1860
- "claude-opus-4-20250514": {
1861
- id: "claude-opus-4-20250514",
1862
- name: "Claude Opus 4",
1863
- api: "anthropic-messages",
1864
- provider: "anthropic",
1865
- baseUrl: "https://api.anthropic.com",
1866
- reasoning: true,
1867
- input: ["text", "image"],
1868
- cost: {
1869
- input: 15,
1870
- output: 75,
1871
- cacheRead: 1.5,
1872
- cacheWrite: 18.75,
1873
- },
1874
- contextWindow: 200000,
1875
- maxTokens: 32000,
1876
- },
1877
1894
  "claude-opus-4-5": {
1878
1895
  id: "claude-opus-4-5",
1879
1896
  name: "Claude Opus 4.5 (latest)",
@@ -1959,40 +1976,6 @@ export const MODELS = {
1959
1976
  contextWindow: 1000000,
1960
1977
  maxTokens: 128000,
1961
1978
  },
1962
- "claude-sonnet-4-0": {
1963
- id: "claude-sonnet-4-0",
1964
- name: "Claude Sonnet 4 (latest)",
1965
- api: "anthropic-messages",
1966
- provider: "anthropic",
1967
- baseUrl: "https://api.anthropic.com",
1968
- reasoning: true,
1969
- input: ["text", "image"],
1970
- cost: {
1971
- input: 3,
1972
- output: 15,
1973
- cacheRead: 0.3,
1974
- cacheWrite: 3.75,
1975
- },
1976
- contextWindow: 200000,
1977
- maxTokens: 64000,
1978
- },
1979
- "claude-sonnet-4-20250514": {
1980
- id: "claude-sonnet-4-20250514",
1981
- name: "Claude Sonnet 4",
1982
- api: "anthropic-messages",
1983
- provider: "anthropic",
1984
- baseUrl: "https://api.anthropic.com",
1985
- reasoning: true,
1986
- input: ["text", "image"],
1987
- cost: {
1988
- input: 3,
1989
- output: 15,
1990
- cacheRead: 0.3,
1991
- cacheWrite: 3.75,
1992
- },
1993
- contextWindow: 200000,
1994
- maxTokens: 64000,
1995
- },
1996
1979
  "claude-sonnet-4-5": {
1997
1980
  id: "claude-sonnet-4-5",
1998
1981
  name: "Claude Sonnet 4.5 (latest)",
@@ -2007,7 +1990,7 @@ export const MODELS = {
2007
1990
  cacheRead: 0.3,
2008
1991
  cacheWrite: 3.75,
2009
1992
  },
2010
- contextWindow: 200000,
1993
+ contextWindow: 1000000,
2011
1994
  maxTokens: 64000,
2012
1995
  },
2013
1996
  "claude-sonnet-4-5-20250929": {
@@ -2024,7 +2007,7 @@ export const MODELS = {
2024
2007
  cacheRead: 0.3,
2025
2008
  cacheWrite: 3.75,
2026
2009
  },
2027
- contextWindow: 200000,
2010
+ contextWindow: 1000000,
2028
2011
  maxTokens: 64000,
2029
2012
  },
2030
2013
  "claude-sonnet-4-6": {
@@ -2042,7 +2025,24 @@ export const MODELS = {
2042
2025
  cacheWrite: 3.75,
2043
2026
  },
2044
2027
  contextWindow: 1000000,
2045
- maxTokens: 64000,
2028
+ maxTokens: 128000,
2029
+ },
2030
+ "claude-sonnet-5": {
2031
+ id: "claude-sonnet-5",
2032
+ name: "Claude Sonnet 5",
2033
+ api: "anthropic-messages",
2034
+ provider: "anthropic",
2035
+ baseUrl: "https://api.anthropic.com",
2036
+ reasoning: true,
2037
+ input: ["text", "image"],
2038
+ cost: {
2039
+ input: 2,
2040
+ output: 10,
2041
+ cacheRead: 0.2,
2042
+ cacheWrite: 2.5,
2043
+ },
2044
+ contextWindow: 1000000,
2045
+ maxTokens: 128000,
2046
2046
  },
2047
2047
  },
2048
2048
  "azure-openai-responses": {
@@ -2590,9 +2590,77 @@ export const MODELS = {
2590
2590
  contextWindow: 1050000,
2591
2591
  maxTokens: 128000,
2592
2592
  },
2593
- "gpt-5.5": {
2594
- id: "gpt-5.5",
2595
- name: "GPT-5.5",
2593
+ "gpt-5.5": {
2594
+ id: "gpt-5.5",
2595
+ name: "GPT-5.5",
2596
+ api: "azure-openai-responses",
2597
+ provider: "azure-openai-responses",
2598
+ baseUrl: "",
2599
+ reasoning: true,
2600
+ input: ["text", "image"],
2601
+ cost: {
2602
+ input: 5,
2603
+ output: 30,
2604
+ cacheRead: 0.5,
2605
+ cacheWrite: 0,
2606
+ },
2607
+ contextWindow: 1050000,
2608
+ maxTokens: 128000,
2609
+ },
2610
+ "gpt-5.5-pro": {
2611
+ id: "gpt-5.5-pro",
2612
+ name: "GPT-5.5 Pro",
2613
+ api: "azure-openai-responses",
2614
+ provider: "azure-openai-responses",
2615
+ baseUrl: "",
2616
+ reasoning: true,
2617
+ input: ["text", "image"],
2618
+ cost: {
2619
+ input: 30,
2620
+ output: 180,
2621
+ cacheRead: 0,
2622
+ cacheWrite: 0,
2623
+ },
2624
+ contextWindow: 1050000,
2625
+ maxTokens: 128000,
2626
+ },
2627
+ "gpt-5.6": {
2628
+ id: "gpt-5.6",
2629
+ name: "GPT-5.6",
2630
+ api: "azure-openai-responses",
2631
+ provider: "azure-openai-responses",
2632
+ baseUrl: "",
2633
+ reasoning: true,
2634
+ input: ["text", "image"],
2635
+ cost: {
2636
+ input: 5,
2637
+ output: 30,
2638
+ cacheRead: 0.5,
2639
+ cacheWrite: 6.25,
2640
+ },
2641
+ contextWindow: 1050000,
2642
+ maxTokens: 128000,
2643
+ },
2644
+ "gpt-5.6-luna": {
2645
+ id: "gpt-5.6-luna",
2646
+ name: "GPT-5.6 Luna",
2647
+ api: "azure-openai-responses",
2648
+ provider: "azure-openai-responses",
2649
+ baseUrl: "",
2650
+ reasoning: true,
2651
+ input: ["text", "image"],
2652
+ cost: {
2653
+ input: 1,
2654
+ output: 6,
2655
+ cacheRead: 0.1,
2656
+ cacheWrite: 1.25,
2657
+ },
2658
+ contextWindow: 1050000,
2659
+ maxTokens: 128000,
2660
+ },
2661
+ "gpt-5.6-sol": {
2662
+ id: "gpt-5.6-sol",
2663
+ name: "GPT-5.6 Sol",
2596
2664
  api: "azure-openai-responses",
2597
2665
  provider: "azure-openai-responses",
2598
2666
  baseUrl: "",
@@ -2602,24 +2670,24 @@ export const MODELS = {
2602
2670
  input: 5,
2603
2671
  output: 30,
2604
2672
  cacheRead: 0.5,
2605
- cacheWrite: 0,
2673
+ cacheWrite: 6.25,
2606
2674
  },
2607
2675
  contextWindow: 1050000,
2608
2676
  maxTokens: 128000,
2609
2677
  },
2610
- "gpt-5.5-pro": {
2611
- id: "gpt-5.5-pro",
2612
- name: "GPT-5.5 Pro",
2678
+ "gpt-5.6-terra": {
2679
+ id: "gpt-5.6-terra",
2680
+ name: "GPT-5.6 Terra",
2613
2681
  api: "azure-openai-responses",
2614
2682
  provider: "azure-openai-responses",
2615
2683
  baseUrl: "",
2616
2684
  reasoning: true,
2617
2685
  input: ["text", "image"],
2618
2686
  cost: {
2619
- input: 30,
2620
- output: 180,
2621
- cacheRead: 0,
2622
- cacheWrite: 0,
2687
+ input: 2.5,
2688
+ output: 15,
2689
+ cacheRead: 0.25,
2690
+ cacheWrite: 3.125,
2623
2691
  },
2624
2692
  contextWindow: 1050000,
2625
2693
  maxTokens: 128000,
@@ -2762,6 +2830,23 @@ export const MODELS = {
2762
2830
  },
2763
2831
  },
2764
2832
  "cerebras": {
2833
+ "gemma-4-31b": {
2834
+ id: "gemma-4-31b",
2835
+ name: "Gemma 4 31B IT",
2836
+ api: "openai-completions",
2837
+ provider: "cerebras",
2838
+ baseUrl: "https://api.cerebras.ai/v1",
2839
+ reasoning: true,
2840
+ input: ["text", "image"],
2841
+ cost: {
2842
+ input: 0.99,
2843
+ output: 1.49,
2844
+ cacheRead: 0,
2845
+ cacheWrite: 0,
2846
+ },
2847
+ contextWindow: 131072,
2848
+ maxTokens: 40960,
2849
+ },
2765
2850
  "gpt-oss-120b": {
2766
2851
  id: "gpt-oss-120b",
2767
2852
  name: "GPT OSS 120B",
@@ -2944,6 +3029,25 @@ export const MODELS = {
2944
3029
  contextWindow: 1000000,
2945
3030
  maxTokens: 32000,
2946
3031
  },
3032
+ "claude-sonnet-5": {
3033
+ id: "claude-sonnet-5",
3034
+ name: "Claude Sonnet 5",
3035
+ api: "openai-completions",
3036
+ provider: "github-copilot",
3037
+ baseUrl: "https://api.individual.githubcopilot.com",
3038
+ headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
3039
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
3040
+ reasoning: true,
3041
+ input: ["text", "image"],
3042
+ cost: {
3043
+ input: 2,
3044
+ output: 10,
3045
+ cacheRead: 0.2,
3046
+ cacheWrite: 2.5,
3047
+ },
3048
+ contextWindow: 1000000,
3049
+ maxTokens: 128000,
3050
+ },
2947
3051
  "gemini-2.5-pro": {
2948
3052
  id: "gemini-2.5-pro",
2949
3053
  name: "Gemini 2.5 Pro",
@@ -3183,6 +3287,44 @@ export const MODELS = {
3183
3287
  contextWindow: 400000,
3184
3288
  maxTokens: 128000,
3185
3289
  },
3290
+ "kimi-k2.7-code": {
3291
+ id: "kimi-k2.7-code",
3292
+ name: "Kimi K2.7 Code",
3293
+ api: "openai-completions",
3294
+ provider: "github-copilot",
3295
+ baseUrl: "https://api.individual.githubcopilot.com",
3296
+ headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
3297
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
3298
+ reasoning: true,
3299
+ input: ["text", "image"],
3300
+ cost: {
3301
+ input: 0.95,
3302
+ output: 4,
3303
+ cacheRead: 0.19,
3304
+ cacheWrite: 0,
3305
+ },
3306
+ contextWindow: 256000,
3307
+ maxTokens: 32000,
3308
+ },
3309
+ "mai-code-1-flash-picker": {
3310
+ id: "mai-code-1-flash-picker",
3311
+ name: "MAI-Code-1-Flash",
3312
+ api: "openai-completions",
3313
+ provider: "github-copilot",
3314
+ baseUrl: "https://api.individual.githubcopilot.com",
3315
+ headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
3316
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
3317
+ reasoning: true,
3318
+ input: ["text"],
3319
+ cost: {
3320
+ input: 0.75,
3321
+ output: 4.5,
3322
+ cacheRead: 0.075,
3323
+ cacheWrite: 0,
3324
+ },
3325
+ contextWindow: 256000,
3326
+ maxTokens: 128000,
3327
+ },
3186
3328
  },
3187
3329
  "google": {
3188
3330
  "gemini-2.0-flash": {
@@ -4020,7 +4162,7 @@ export const MODELS = {
4020
4162
  cost: {
4021
4163
  input: 0.075,
4022
4164
  output: 0.3,
4023
- cacheRead: 0.037,
4165
+ cacheRead: 0,
4024
4166
  cacheWrite: 0,
4025
4167
  },
4026
4168
  contextWindow: 131072,
@@ -4693,6 +4835,42 @@ export const MODELS = {
4693
4835
  contextWindow: 262144,
4694
4836
  maxTokens: 262144,
4695
4837
  },
4838
+ "openai/gpt-oss-120b": {
4839
+ id: "openai/gpt-oss-120b",
4840
+ name: "GPT OSS 120B",
4841
+ api: "openai-completions",
4842
+ provider: "huggingface",
4843
+ baseUrl: "https://router.huggingface.co/v1",
4844
+ compat: { "supportsDeveloperRole": false },
4845
+ reasoning: true,
4846
+ input: ["text"],
4847
+ cost: {
4848
+ input: 0.25,
4849
+ output: 0.69,
4850
+ cacheRead: 0,
4851
+ cacheWrite: 0,
4852
+ },
4853
+ contextWindow: 131072,
4854
+ maxTokens: 32768,
4855
+ },
4856
+ "openai/gpt-oss-20b": {
4857
+ id: "openai/gpt-oss-20b",
4858
+ name: "GPT OSS 20B",
4859
+ api: "openai-completions",
4860
+ provider: "huggingface",
4861
+ baseUrl: "https://router.huggingface.co/v1",
4862
+ compat: { "supportsDeveloperRole": false },
4863
+ reasoning: true,
4864
+ input: ["text"],
4865
+ cost: {
4866
+ input: 0.1,
4867
+ output: 0.5,
4868
+ cacheRead: 0,
4869
+ cacheWrite: 0,
4870
+ },
4871
+ contextWindow: 131072,
4872
+ maxTokens: 32768,
4873
+ },
4696
4874
  "stepfun-ai/Step-3.5-Flash": {
4697
4875
  id: "stepfun-ai/Step-3.5-Flash",
4698
4876
  name: "Step 3.5 Flash",
@@ -5367,11 +5545,11 @@ export const MODELS = {
5367
5545
  api: "mistral-conversations",
5368
5546
  provider: "mistral",
5369
5547
  baseUrl: "https://api.mistral.ai",
5370
- reasoning: false,
5548
+ reasoning: true,
5371
5549
  input: ["text", "image"],
5372
5550
  cost: {
5373
- input: 0.4,
5374
- output: 2,
5551
+ input: 1.5,
5552
+ output: 7.5,
5375
5553
  cacheRead: 0,
5376
5554
  cacheWrite: 0,
5377
5555
  },
@@ -6128,6 +6306,74 @@ export const MODELS = {
6128
6306
  contextWindow: 1050000,
6129
6307
  maxTokens: 128000,
6130
6308
  },
6309
+ "gpt-5.6": {
6310
+ id: "gpt-5.6",
6311
+ name: "GPT-5.6",
6312
+ api: "openai-responses",
6313
+ provider: "openai",
6314
+ baseUrl: "https://api.openai.com/v1",
6315
+ reasoning: true,
6316
+ input: ["text", "image"],
6317
+ cost: {
6318
+ input: 5,
6319
+ output: 30,
6320
+ cacheRead: 0.5,
6321
+ cacheWrite: 6.25,
6322
+ },
6323
+ contextWindow: 1050000,
6324
+ maxTokens: 128000,
6325
+ },
6326
+ "gpt-5.6-luna": {
6327
+ id: "gpt-5.6-luna",
6328
+ name: "GPT-5.6 Luna",
6329
+ api: "openai-responses",
6330
+ provider: "openai",
6331
+ baseUrl: "https://api.openai.com/v1",
6332
+ reasoning: true,
6333
+ input: ["text", "image"],
6334
+ cost: {
6335
+ input: 1,
6336
+ output: 6,
6337
+ cacheRead: 0.1,
6338
+ cacheWrite: 1.25,
6339
+ },
6340
+ contextWindow: 1050000,
6341
+ maxTokens: 128000,
6342
+ },
6343
+ "gpt-5.6-sol": {
6344
+ id: "gpt-5.6-sol",
6345
+ name: "GPT-5.6 Sol",
6346
+ api: "openai-responses",
6347
+ provider: "openai",
6348
+ baseUrl: "https://api.openai.com/v1",
6349
+ reasoning: true,
6350
+ input: ["text", "image"],
6351
+ cost: {
6352
+ input: 5,
6353
+ output: 30,
6354
+ cacheRead: 0.5,
6355
+ cacheWrite: 6.25,
6356
+ },
6357
+ contextWindow: 1050000,
6358
+ maxTokens: 128000,
6359
+ },
6360
+ "gpt-5.6-terra": {
6361
+ id: "gpt-5.6-terra",
6362
+ name: "GPT-5.6 Terra",
6363
+ api: "openai-responses",
6364
+ provider: "openai",
6365
+ baseUrl: "https://api.openai.com/v1",
6366
+ reasoning: true,
6367
+ input: ["text", "image"],
6368
+ cost: {
6369
+ input: 2.5,
6370
+ output: 15,
6371
+ cacheRead: 0.25,
6372
+ cacheWrite: 3.125,
6373
+ },
6374
+ contextWindow: 1050000,
6375
+ maxTokens: 128000,
6376
+ },
6131
6377
  "o1": {
6132
6378
  id: "o1",
6133
6379
  name: "o1",
@@ -6421,6 +6667,23 @@ export const MODELS = {
6421
6667
  contextWindow: 200000,
6422
6668
  maxTokens: 32000,
6423
6669
  },
6670
+ "claude-fable-5": {
6671
+ id: "claude-fable-5",
6672
+ name: "Claude Fable 5",
6673
+ api: "anthropic-messages",
6674
+ provider: "opencode",
6675
+ baseUrl: "https://opencode.ai/zen",
6676
+ reasoning: true,
6677
+ input: ["text", "image"],
6678
+ cost: {
6679
+ input: 10,
6680
+ output: 50,
6681
+ cacheRead: 1,
6682
+ cacheWrite: 12.5,
6683
+ },
6684
+ contextWindow: 1000000,
6685
+ maxTokens: 128000,
6686
+ },
6424
6687
  "claude-haiku-4-5": {
6425
6688
  id: "claude-haiku-4-5",
6426
6689
  name: "Claude Haiku 4.5",
@@ -6574,6 +6837,23 @@ export const MODELS = {
6574
6837
  contextWindow: 1000000,
6575
6838
  maxTokens: 64000,
6576
6839
  },
6840
+ "claude-sonnet-5": {
6841
+ id: "claude-sonnet-5",
6842
+ name: "Claude Sonnet 5",
6843
+ api: "anthropic-messages",
6844
+ provider: "opencode",
6845
+ baseUrl: "https://opencode.ai/zen",
6846
+ reasoning: true,
6847
+ input: ["text", "image"],
6848
+ cost: {
6849
+ input: 2,
6850
+ output: 10,
6851
+ cacheRead: 0.2,
6852
+ cacheWrite: 2.5,
6853
+ },
6854
+ contextWindow: 1000000,
6855
+ maxTokens: 128000,
6856
+ },
6577
6857
  "deepseek-v4-flash": {
6578
6858
  id: "deepseek-v4-flash",
6579
6859
  name: "DeepSeek V4 Flash",
@@ -6999,6 +7279,23 @@ export const MODELS = {
6999
7279
  contextWindow: 1050000,
7000
7280
  maxTokens: 128000,
7001
7281
  },
7282
+ "grok-4.5": {
7283
+ id: "grok-4.5",
7284
+ name: "Grok 4.5",
7285
+ api: "openai-completions",
7286
+ provider: "opencode",
7287
+ baseUrl: "https://opencode.ai/zen/v1",
7288
+ reasoning: true,
7289
+ input: ["text", "image"],
7290
+ cost: {
7291
+ input: 2,
7292
+ output: 6,
7293
+ cacheRead: 0.5,
7294
+ cacheWrite: 0,
7295
+ },
7296
+ contextWindow: 500000,
7297
+ maxTokens: 500000,
7298
+ },
7002
7299
  "grok-build-0.1": {
7003
7300
  id: "grok-build-0.1",
7004
7301
  name: "Grok Build 0.1",
@@ -7016,6 +7313,23 @@ export const MODELS = {
7016
7313
  contextWindow: 256000,
7017
7314
  maxTokens: 256000,
7018
7315
  },
7316
+ "hy3-free": {
7317
+ id: "hy3-free",
7318
+ name: "Hy3 Free",
7319
+ api: "openai-completions",
7320
+ provider: "opencode",
7321
+ baseUrl: "https://opencode.ai/zen/v1",
7322
+ reasoning: true,
7323
+ input: ["text"],
7324
+ cost: {
7325
+ input: 0,
7326
+ output: 0,
7327
+ cacheRead: 0,
7328
+ cacheWrite: 0,
7329
+ },
7330
+ contextWindow: 256000,
7331
+ maxTokens: 64000,
7332
+ },
7019
7333
  "kimi-k2.5": {
7020
7334
  id: "kimi-k2.5",
7021
7335
  name: "Kimi K2.5",
@@ -7050,6 +7364,23 @@ export const MODELS = {
7050
7364
  contextWindow: 262144,
7051
7365
  maxTokens: 65536,
7052
7366
  },
7367
+ "kimi-k2.7-code": {
7368
+ id: "kimi-k2.7-code",
7369
+ name: "Kimi K2.7 Code",
7370
+ api: "openai-completions",
7371
+ provider: "opencode",
7372
+ baseUrl: "https://opencode.ai/zen/v1",
7373
+ reasoning: true,
7374
+ input: ["text", "image"],
7375
+ cost: {
7376
+ input: 0.95,
7377
+ output: 4,
7378
+ cacheRead: 0.19,
7379
+ cacheWrite: 0,
7380
+ },
7381
+ contextWindow: 262144,
7382
+ maxTokens: 262144,
7383
+ },
7053
7384
  "mimo-v2.5-free": {
7054
7385
  id: "mimo-v2.5-free",
7055
7386
  name: "MiMo V2.5 Free",
@@ -7069,7 +7400,7 @@ export const MODELS = {
7069
7400
  },
7070
7401
  "minimax-m2.5": {
7071
7402
  id: "minimax-m2.5",
7072
- name: "MiniMax M2.5",
7403
+ name: "MiniMax-M2.5",
7073
7404
  api: "openai-completions",
7074
7405
  provider: "opencode",
7075
7406
  baseUrl: "https://opencode.ai/zen/v1",
@@ -7086,7 +7417,7 @@ export const MODELS = {
7086
7417
  },
7087
7418
  "minimax-m2.7": {
7088
7419
  id: "minimax-m2.7",
7089
- name: "MiniMax M2.7",
7420
+ name: "MiniMax-M2.7",
7090
7421
  api: "openai-completions",
7091
7422
  provider: "opencode",
7092
7423
  baseUrl: "https://opencode.ai/zen/v1",
@@ -7101,6 +7432,23 @@ export const MODELS = {
7101
7432
  contextWindow: 204800,
7102
7433
  maxTokens: 131072,
7103
7434
  },
7435
+ "minimax-m3": {
7436
+ id: "minimax-m3",
7437
+ name: "MiniMax-M3",
7438
+ api: "openai-completions",
7439
+ provider: "opencode",
7440
+ baseUrl: "https://opencode.ai/zen/v1",
7441
+ reasoning: true,
7442
+ input: ["text", "image"],
7443
+ cost: {
7444
+ input: 0.3,
7445
+ output: 1.2,
7446
+ cacheRead: 0.06,
7447
+ cacheWrite: 0,
7448
+ },
7449
+ contextWindow: 512000,
7450
+ maxTokens: 128000,
7451
+ },
7104
7452
  "nemotron-3-ultra-free": {
7105
7453
  id: "nemotron-3-ultra-free",
7106
7454
  name: "Nemotron 3 Ultra Free",
@@ -7309,7 +7657,7 @@ export const MODELS = {
7309
7657
  },
7310
7658
  "minimax-m2.7": {
7311
7659
  id: "minimax-m2.7",
7312
- name: "MiniMax M2.7",
7660
+ name: "MiniMax-M2.7",
7313
7661
  api: "anthropic-messages",
7314
7662
  provider: "opencode-go",
7315
7663
  baseUrl: "https://opencode.ai/zen/go",
@@ -7326,16 +7674,16 @@ export const MODELS = {
7326
7674
  },
7327
7675
  "minimax-m3": {
7328
7676
  id: "minimax-m3",
7329
- name: "MiniMax M3 (3x usage)",
7677
+ name: "MiniMax-M3",
7330
7678
  api: "anthropic-messages",
7331
7679
  provider: "opencode-go",
7332
7680
  baseUrl: "https://opencode.ai/zen/go",
7333
7681
  reasoning: true,
7334
7682
  input: ["text", "image"],
7335
7683
  cost: {
7336
- input: 0.1,
7337
- output: 0.4,
7338
- cacheRead: 0.02,
7684
+ input: 0.3,
7685
+ output: 1.2,
7686
+ cacheRead: 0.06,
7339
7687
  cacheWrite: 0,
7340
7688
  },
7341
7689
  contextWindow: 1000000,
@@ -7411,6 +7759,57 @@ export const MODELS = {
7411
7759
  contextWindow: 256000,
7412
7760
  maxTokens: 4096,
7413
7761
  },
7762
+ "aion-labs/aion-2.0": {
7763
+ id: "aion-labs/aion-2.0",
7764
+ name: "AionLabs: Aion-2.0",
7765
+ api: "openai-completions",
7766
+ provider: "openrouter",
7767
+ baseUrl: "https://openrouter.ai/api/v1",
7768
+ reasoning: true,
7769
+ input: ["text"],
7770
+ cost: {
7771
+ input: 0.7999999999999999,
7772
+ output: 1.5999999999999999,
7773
+ cacheRead: 0.19999999999999998,
7774
+ cacheWrite: 0,
7775
+ },
7776
+ contextWindow: 131072,
7777
+ maxTokens: 32768,
7778
+ },
7779
+ "aion-labs/aion-3.0": {
7780
+ id: "aion-labs/aion-3.0",
7781
+ name: "AionLabs: Aion-3.0",
7782
+ api: "openai-completions",
7783
+ provider: "openrouter",
7784
+ baseUrl: "https://openrouter.ai/api/v1",
7785
+ reasoning: true,
7786
+ input: ["text"],
7787
+ cost: {
7788
+ input: 3,
7789
+ output: 6,
7790
+ cacheRead: 0.75,
7791
+ cacheWrite: 0,
7792
+ },
7793
+ contextWindow: 131072,
7794
+ maxTokens: 32768,
7795
+ },
7796
+ "aion-labs/aion-3.0-mini": {
7797
+ id: "aion-labs/aion-3.0-mini",
7798
+ name: "AionLabs: Aion-3.0-Mini",
7799
+ api: "openai-completions",
7800
+ provider: "openrouter",
7801
+ baseUrl: "https://openrouter.ai/api/v1",
7802
+ reasoning: true,
7803
+ input: ["text"],
7804
+ cost: {
7805
+ input: 0.7,
7806
+ output: 1.4,
7807
+ cacheRead: 0.18,
7808
+ cacheWrite: 0,
7809
+ },
7810
+ contextWindow: 131072,
7811
+ maxTokens: 32768,
7812
+ },
7414
7813
  "amazon/nova-2-lite-v1": {
7415
7814
  id: "amazon/nova-2-lite-v1",
7416
7815
  name: "Amazon: Nova 2 Lite",
@@ -7615,23 +8014,6 @@ export const MODELS = {
7615
8014
  contextWindow: 1000000,
7616
8015
  maxTokens: 128000,
7617
8016
  },
7618
- "anthropic/claude-opus-4.6-fast": {
7619
- id: "anthropic/claude-opus-4.6-fast",
7620
- name: "Anthropic: Claude Opus 4.6 (Fast)",
7621
- api: "openai-completions",
7622
- provider: "openrouter",
7623
- baseUrl: "https://openrouter.ai/api/v1",
7624
- reasoning: true,
7625
- input: ["text", "image"],
7626
- cost: {
7627
- input: 30,
7628
- output: 150,
7629
- cacheRead: 3,
7630
- cacheWrite: 37.5,
7631
- },
7632
- contextWindow: 1000000,
7633
- maxTokens: 128000,
7634
- },
7635
8017
  "anthropic/claude-opus-4.7": {
7636
8018
  id: "anthropic/claude-opus-4.7",
7637
8019
  name: "Anthropic: Claude Opus 4.7",
@@ -7751,6 +8133,23 @@ export const MODELS = {
7751
8133
  contextWindow: 1000000,
7752
8134
  maxTokens: 128000,
7753
8135
  },
8136
+ "anthropic/claude-sonnet-5": {
8137
+ id: "anthropic/claude-sonnet-5",
8138
+ name: "Anthropic: Claude Sonnet 5",
8139
+ api: "openai-completions",
8140
+ provider: "openrouter",
8141
+ baseUrl: "https://openrouter.ai/api/v1",
8142
+ reasoning: true,
8143
+ input: ["text", "image"],
8144
+ cost: {
8145
+ input: 2,
8146
+ output: 10,
8147
+ cacheRead: 0.19999999999999998,
8148
+ cacheWrite: 2.5,
8149
+ },
8150
+ contextWindow: 1000000,
8151
+ maxTokens: 128000,
8152
+ },
7754
8153
  "arcee-ai/trinity-large-thinking": {
7755
8154
  id: "arcee-ai/trinity-large-thinking",
7756
8155
  name: "Arcee AI: Trinity Large Thinking",
@@ -7964,8 +8363,8 @@ export const MODELS = {
7964
8363
  reasoning: false,
7965
8364
  input: ["text"],
7966
8365
  cost: {
7967
- input: 0.19999999999999998,
7968
- output: 0.77,
8366
+ input: 0.24,
8367
+ output: 0.8999999999999999,
7969
8368
  cacheRead: 0.135,
7970
8369
  cacheWrite: 0,
7971
8370
  },
@@ -8085,7 +8484,7 @@ export const MODELS = {
8085
8484
  cost: {
8086
8485
  input: 0.09,
8087
8486
  output: 0.18,
8088
- cacheRead: 0.02,
8487
+ cacheRead: 0.018,
8089
8488
  cacheWrite: 0,
8090
8489
  },
8091
8490
  contextWindow: 1048576,
@@ -8142,23 +8541,6 @@ export const MODELS = {
8142
8541
  contextWindow: 1048576,
8143
8542
  maxTokens: 65535,
8144
8543
  },
8145
- "google/gemini-2.5-flash-lite-preview-09-2025": {
8146
- id: "google/gemini-2.5-flash-lite-preview-09-2025",
8147
- name: "Google: Gemini 2.5 Flash Lite Preview 09-2025",
8148
- api: "openai-completions",
8149
- provider: "openrouter",
8150
- baseUrl: "https://openrouter.ai/api/v1",
8151
- reasoning: true,
8152
- input: ["text", "image"],
8153
- cost: {
8154
- input: 0.09999999999999999,
8155
- output: 0.39999999999999997,
8156
- cacheRead: 0.01,
8157
- cacheWrite: 0.08333333333333334,
8158
- },
8159
- contextWindow: 1048576,
8160
- maxTokens: 65535,
8161
- },
8162
8544
  "google/gemini-2.5-pro": {
8163
8545
  id: "google/gemini-2.5-pro",
8164
8546
  name: "Google: Gemini 2.5 Pro",
@@ -8679,12 +9061,12 @@ export const MODELS = {
8679
9061
  input: ["text"],
8680
9062
  cost: {
8681
9063
  input: 0.255,
8682
- output: 1,
8683
- cacheRead: 0.03,
9064
+ output: 1.02,
9065
+ cacheRead: 0,
8684
9066
  cacheWrite: 0,
8685
9067
  },
8686
9068
  contextWindow: 204800,
8687
- maxTokens: 196608,
9069
+ maxTokens: 131072,
8688
9070
  },
8689
9071
  "minimax/minimax-m2.1": {
8690
9072
  id: "minimax/minimax-m2.1",
@@ -8695,13 +9077,13 @@ export const MODELS = {
8695
9077
  reasoning: true,
8696
9078
  input: ["text"],
8697
9079
  cost: {
8698
- input: 0.29,
8699
- output: 0.95,
9080
+ input: 0.3,
9081
+ output: 1.2,
8700
9082
  cacheRead: 0.03,
8701
9083
  cacheWrite: 0,
8702
9084
  },
8703
9085
  contextWindow: 204800,
8704
- maxTokens: 196608,
9086
+ maxTokens: 131072,
8705
9087
  },
8706
9088
  "minimax/minimax-m2.5": {
8707
9089
  id: "minimax/minimax-m2.5",
@@ -8712,9 +9094,9 @@ export const MODELS = {
8712
9094
  reasoning: true,
8713
9095
  input: ["text"],
8714
9096
  cost: {
8715
- input: 0.12,
8716
- output: 0.48,
8717
- cacheRead: 0,
9097
+ input: 0.15,
9098
+ output: 0.8999999999999999,
9099
+ cacheRead: 0.049999999999999996,
8718
9100
  cacheWrite: 0,
8719
9101
  },
8720
9102
  contextWindow: 204800,
@@ -8729,8 +9111,8 @@ export const MODELS = {
8729
9111
  reasoning: true,
8730
9112
  input: ["text"],
8731
9113
  cost: {
8732
- input: 0.18,
8733
- output: 0.72,
9114
+ input: 0.24,
9115
+ output: 0.96,
8734
9116
  cacheRead: 0,
8735
9117
  cacheWrite: 0,
8736
9118
  },
@@ -8752,7 +9134,7 @@ export const MODELS = {
8752
9134
  cacheWrite: 0,
8753
9135
  },
8754
9136
  contextWindow: 1048576,
8755
- maxTokens: 512000,
9137
+ maxTokens: 131072,
8756
9138
  },
8757
9139
  "mistralai/codestral-2508": {
8758
9140
  id: "mistralai/codestral-2508",
@@ -9058,7 +9440,7 @@ export const MODELS = {
9058
9440
  cacheWrite: 0,
9059
9441
  },
9060
9442
  contextWindow: 131072,
9061
- maxTokens: 32768,
9443
+ maxTokens: 100352,
9062
9444
  },
9063
9445
  "moonshotai/kimi-k2-0905": {
9064
9446
  id: "moonshotai/kimi-k2-0905",
@@ -9075,7 +9457,7 @@ export const MODELS = {
9075
9457
  cacheWrite: 0,
9076
9458
  },
9077
9459
  contextWindow: 262144,
9078
- maxTokens: 262144,
9460
+ maxTokens: 100352,
9079
9461
  },
9080
9462
  "moonshotai/kimi-k2-thinking": {
9081
9463
  id: "moonshotai/kimi-k2-thinking",
@@ -9088,11 +9470,11 @@ export const MODELS = {
9088
9470
  cost: {
9089
9471
  input: 0.6,
9090
9472
  output: 2.5,
9091
- cacheRead: 0.6,
9473
+ cacheRead: 0.15,
9092
9474
  cacheWrite: 0,
9093
9475
  },
9094
9476
  contextWindow: 262144,
9095
- maxTokens: 262144,
9477
+ maxTokens: 100352,
9096
9478
  },
9097
9479
  "moonshotai/kimi-k2.5": {
9098
9480
  id: "moonshotai/kimi-k2.5",
@@ -9122,7 +9504,7 @@ export const MODELS = {
9122
9504
  cost: {
9123
9505
  input: 0.66,
9124
9506
  output: 3.41,
9125
- cacheRead: 0.144,
9507
+ cacheRead: 0.15,
9126
9508
  cacheWrite: 0,
9127
9509
  },
9128
9510
  contextWindow: 262144,
@@ -9137,13 +9519,47 @@ export const MODELS = {
9137
9519
  reasoning: true,
9138
9520
  input: ["text", "image"],
9139
9521
  cost: {
9140
- input: 0.74,
9141
- output: 3.5,
9142
- cacheRead: 0.15,
9522
+ input: 0.72,
9523
+ output: 3.49,
9524
+ cacheRead: 0.159,
9143
9525
  cacheWrite: 0,
9144
9526
  },
9145
9527
  contextWindow: 262144,
9146
- maxTokens: 16384,
9528
+ maxTokens: 262144,
9529
+ },
9530
+ "nex-agi/nex-n2-mini": {
9531
+ id: "nex-agi/nex-n2-mini",
9532
+ name: "Nex AGI: Nex-N2-Mini",
9533
+ api: "openai-completions",
9534
+ provider: "openrouter",
9535
+ baseUrl: "https://openrouter.ai/api/v1",
9536
+ reasoning: true,
9537
+ input: ["text", "image"],
9538
+ cost: {
9539
+ input: 0.024999999999999998,
9540
+ output: 0.09999999999999999,
9541
+ cacheRead: 0.0025,
9542
+ cacheWrite: 0,
9543
+ },
9544
+ contextWindow: 262144,
9545
+ maxTokens: 262144,
9546
+ },
9547
+ "nex-agi/nex-n2-pro": {
9548
+ id: "nex-agi/nex-n2-pro",
9549
+ name: "Nex AGI: Nex-N2-Pro",
9550
+ api: "openai-completions",
9551
+ provider: "openrouter",
9552
+ baseUrl: "https://openrouter.ai/api/v1",
9553
+ reasoning: true,
9554
+ input: ["text", "image"],
9555
+ cost: {
9556
+ input: 0.25,
9557
+ output: 1,
9558
+ cacheRead: 0.024999999999999998,
9559
+ cacheWrite: 0,
9560
+ },
9561
+ contextWindow: 262144,
9562
+ maxTokens: 262144,
9147
9563
  },
9148
9564
  "nvidia/llama-3.3-nemotron-super-49b-v1.5": {
9149
9565
  id: "nvidia/llama-3.3-nemotron-super-49b-v1.5",
@@ -9222,13 +9638,13 @@ export const MODELS = {
9222
9638
  reasoning: true,
9223
9639
  input: ["text"],
9224
9640
  cost: {
9225
- input: 0.08499999999999999,
9226
- output: 0.39999999999999997,
9641
+ input: 0.08,
9642
+ output: 0.44999999999999996,
9227
9643
  cacheRead: 0,
9228
9644
  cacheWrite: 0,
9229
9645
  },
9230
9646
  contextWindow: 1000000,
9231
- maxTokens: 16384,
9647
+ maxTokens: 4096,
9232
9648
  },
9233
9649
  "nvidia/nemotron-3-super-120b-a12b:free": {
9234
9650
  id: "nvidia/nemotron-3-super-120b-a12b:free",
@@ -9936,10 +10352,112 @@ export const MODELS = {
9936
10352
  reasoning: true,
9937
10353
  input: ["text", "image"],
9938
10354
  cost: {
9939
- input: 30,
9940
- output: 180,
9941
- cacheRead: 0,
9942
- cacheWrite: 0,
10355
+ input: 30,
10356
+ output: 180,
10357
+ cacheRead: 0,
10358
+ cacheWrite: 0,
10359
+ },
10360
+ contextWindow: 1050000,
10361
+ maxTokens: 128000,
10362
+ },
10363
+ "openai/gpt-5.6-luna": {
10364
+ id: "openai/gpt-5.6-luna",
10365
+ name: "OpenAI: GPT-5.6 Luna",
10366
+ api: "openai-completions",
10367
+ provider: "openrouter",
10368
+ baseUrl: "https://openrouter.ai/api/v1",
10369
+ reasoning: true,
10370
+ input: ["text", "image"],
10371
+ cost: {
10372
+ input: 1,
10373
+ output: 6,
10374
+ cacheRead: 0.09999999999999999,
10375
+ cacheWrite: 1.25,
10376
+ },
10377
+ contextWindow: 1050000,
10378
+ maxTokens: 128000,
10379
+ },
10380
+ "openai/gpt-5.6-luna-pro": {
10381
+ id: "openai/gpt-5.6-luna-pro",
10382
+ name: "OpenAI: GPT-5.6 Luna Pro",
10383
+ api: "openai-completions",
10384
+ provider: "openrouter",
10385
+ baseUrl: "https://openrouter.ai/api/v1",
10386
+ reasoning: true,
10387
+ input: ["text", "image"],
10388
+ cost: {
10389
+ input: 1,
10390
+ output: 6,
10391
+ cacheRead: 0.09999999999999999,
10392
+ cacheWrite: 1.25,
10393
+ },
10394
+ contextWindow: 1050000,
10395
+ maxTokens: 128000,
10396
+ },
10397
+ "openai/gpt-5.6-sol": {
10398
+ id: "openai/gpt-5.6-sol",
10399
+ name: "OpenAI: GPT-5.6 Sol",
10400
+ api: "openai-completions",
10401
+ provider: "openrouter",
10402
+ baseUrl: "https://openrouter.ai/api/v1",
10403
+ reasoning: true,
10404
+ input: ["text", "image"],
10405
+ cost: {
10406
+ input: 5,
10407
+ output: 30,
10408
+ cacheRead: 0.5,
10409
+ cacheWrite: 6.25,
10410
+ },
10411
+ contextWindow: 1050000,
10412
+ maxTokens: 128000,
10413
+ },
10414
+ "openai/gpt-5.6-sol-pro": {
10415
+ id: "openai/gpt-5.6-sol-pro",
10416
+ name: "OpenAI: GPT-5.6 Sol Pro",
10417
+ api: "openai-completions",
10418
+ provider: "openrouter",
10419
+ baseUrl: "https://openrouter.ai/api/v1",
10420
+ reasoning: true,
10421
+ input: ["text", "image"],
10422
+ cost: {
10423
+ input: 5,
10424
+ output: 30,
10425
+ cacheRead: 0.5,
10426
+ cacheWrite: 6.25,
10427
+ },
10428
+ contextWindow: 1050000,
10429
+ maxTokens: 128000,
10430
+ },
10431
+ "openai/gpt-5.6-terra": {
10432
+ id: "openai/gpt-5.6-terra",
10433
+ name: "OpenAI: GPT-5.6 Terra",
10434
+ api: "openai-completions",
10435
+ provider: "openrouter",
10436
+ baseUrl: "https://openrouter.ai/api/v1",
10437
+ reasoning: true,
10438
+ input: ["text", "image"],
10439
+ cost: {
10440
+ input: 2.5,
10441
+ output: 15,
10442
+ cacheRead: 0.25,
10443
+ cacheWrite: 3.125,
10444
+ },
10445
+ contextWindow: 1050000,
10446
+ maxTokens: 128000,
10447
+ },
10448
+ "openai/gpt-5.6-terra-pro": {
10449
+ id: "openai/gpt-5.6-terra-pro",
10450
+ name: "OpenAI: GPT-5.6 Terra Pro",
10451
+ api: "openai-completions",
10452
+ provider: "openrouter",
10453
+ baseUrl: "https://openrouter.ai/api/v1",
10454
+ reasoning: true,
10455
+ input: ["text", "image"],
10456
+ cost: {
10457
+ input: 2.5,
10458
+ output: 15,
10459
+ cacheRead: 0.25,
10460
+ cacheWrite: 3.125,
9943
10461
  },
9944
10462
  contextWindow: 1050000,
9945
10463
  maxTokens: 128000,
@@ -10004,13 +10522,13 @@ export const MODELS = {
10004
10522
  reasoning: true,
10005
10523
  input: ["text"],
10006
10524
  cost: {
10007
- input: 0.03,
10008
- output: 0.15,
10525
+ input: 0.036,
10526
+ output: 0.18,
10009
10527
  cacheRead: 0,
10010
10528
  cacheWrite: 0,
10011
10529
  },
10012
10530
  contextWindow: 131072,
10013
- maxTokens: 131072,
10531
+ maxTokens: 4096,
10014
10532
  },
10015
10533
  "openai/gpt-oss-120b:free": {
10016
10534
  id: "openai/gpt-oss-120b:free",
@@ -10267,23 +10785,6 @@ export const MODELS = {
10267
10785
  contextWindow: 200000,
10268
10786
  maxTokens: 4096,
10269
10787
  },
10270
- "openrouter/owl-alpha": {
10271
- id: "openrouter/owl-alpha",
10272
- name: "Owl Alpha",
10273
- api: "openai-completions",
10274
- provider: "openrouter",
10275
- baseUrl: "https://openrouter.ai/api/v1",
10276
- reasoning: false,
10277
- input: ["text"],
10278
- cost: {
10279
- input: 0,
10280
- output: 0,
10281
- cacheRead: 0,
10282
- cacheWrite: 0,
10283
- },
10284
- contextWindow: 1048756,
10285
- maxTokens: 262144,
10286
- },
10287
10788
  "poolside/laguna-m.1": {
10288
10789
  id: "poolside/laguna-m.1",
10289
10790
  name: "Poolside: Laguna M.1",
@@ -10318,26 +10819,26 @@ export const MODELS = {
10318
10819
  contextWindow: 262144,
10319
10820
  maxTokens: 32768,
10320
10821
  },
10321
- "poolside/laguna-xs.2": {
10322
- id: "poolside/laguna-xs.2",
10323
- name: "Poolside: Laguna XS.2",
10822
+ "poolside/laguna-xs-2.1": {
10823
+ id: "poolside/laguna-xs-2.1",
10824
+ name: "Poolside: Laguna XS 2.1",
10324
10825
  api: "openai-completions",
10325
10826
  provider: "openrouter",
10326
10827
  baseUrl: "https://openrouter.ai/api/v1",
10327
10828
  reasoning: true,
10328
10829
  input: ["text"],
10329
10830
  cost: {
10330
- input: 0.09999999999999999,
10331
- output: 0.19999999999999998,
10332
- cacheRead: 0.049999999999999996,
10831
+ input: 0.06,
10832
+ output: 0.12,
10833
+ cacheRead: 0.03,
10333
10834
  cacheWrite: 0,
10334
10835
  },
10335
10836
  contextWindow: 262144,
10336
10837
  maxTokens: 32768,
10337
10838
  },
10338
- "poolside/laguna-xs.2:free": {
10339
- id: "poolside/laguna-xs.2:free",
10340
- name: "Poolside: Laguna XS.2 (free)",
10839
+ "poolside/laguna-xs-2.1:free": {
10840
+ id: "poolside/laguna-xs-2.1:free",
10841
+ name: "Poolside: Laguna XS 2.1 (free)",
10341
10842
  api: "openai-completions",
10342
10843
  provider: "openrouter",
10343
10844
  baseUrl: "https://openrouter.ai/api/v1",
@@ -10497,13 +10998,13 @@ export const MODELS = {
10497
10998
  reasoning: true,
10498
10999
  input: ["text"],
10499
11000
  cost: {
10500
- input: 0.09999999999999999,
10501
- output: 0.09999999999999999,
10502
- cacheRead: 0.09999999999999999,
11001
+ input: 0.14950000000000002,
11002
+ output: 1.495,
11003
+ cacheRead: 0,
10503
11004
  cacheWrite: 0,
10504
11005
  },
10505
11006
  contextWindow: 262144,
10506
- maxTokens: 262144,
11007
+ maxTokens: 4096,
10507
11008
  },
10508
11009
  "qwen/qwen3-30b-a3b": {
10509
11010
  id: "qwen/qwen3-30b-a3b",
@@ -10548,13 +11049,13 @@ export const MODELS = {
10548
11049
  reasoning: true,
10549
11050
  input: ["text"],
10550
11051
  cost: {
10551
- input: 0.08,
10552
- output: 0.39999999999999997,
10553
- cacheRead: 0.08,
11052
+ input: 0.13,
11053
+ output: 1.56,
11054
+ cacheRead: 0,
10554
11055
  cacheWrite: 0,
10555
11056
  },
10556
11057
  contextWindow: 131072,
10557
- maxTokens: 131072,
11058
+ maxTokens: 32768,
10558
11059
  },
10559
11060
  "qwen/qwen3-32b": {
10560
11061
  id: "qwen/qwen3-32b",
@@ -10582,9 +11083,9 @@ export const MODELS = {
10582
11083
  reasoning: true,
10583
11084
  input: ["text"],
10584
11085
  cost: {
10585
- input: 0.049999999999999996,
10586
- output: 0.39999999999999997,
10587
- cacheRead: 0.049999999999999996,
11086
+ input: 0.117,
11087
+ output: 0.45499999999999996,
11088
+ cacheRead: 0,
10588
11089
  cacheWrite: 0,
10589
11090
  },
10590
11091
  contextWindow: 131072,
@@ -10871,8 +11372,8 @@ export const MODELS = {
10871
11372
  reasoning: false,
10872
11373
  input: ["text", "image"],
10873
11374
  cost: {
10874
- input: 0.08,
10875
- output: 0.5,
11375
+ input: 0.117,
11376
+ output: 0.45499999999999996,
10876
11377
  cacheRead: 0,
10877
11378
  cacheWrite: 0,
10878
11379
  },
@@ -10958,7 +11459,7 @@ export const MODELS = {
10958
11459
  cost: {
10959
11460
  input: 0.385,
10960
11461
  output: 2.4499999999999997,
10961
- cacheRead: 0,
11462
+ cacheRead: 0.111,
10962
11463
  cacheWrite: 0,
10963
11464
  },
10964
11465
  contextWindow: 256000,
@@ -11041,9 +11542,9 @@ export const MODELS = {
11041
11542
  reasoning: true,
11042
11543
  input: ["text", "image"],
11043
11544
  cost: {
11044
- input: 0.28850000000000003,
11045
- output: 2.65,
11046
- cacheRead: 0,
11545
+ input: 0.28500000000000003,
11546
+ output: 2.4,
11547
+ cacheRead: 0.15,
11047
11548
  cacheWrite: 0,
11048
11549
  },
11049
11550
  contextWindow: 262144,
@@ -11228,13 +11729,13 @@ export const MODELS = {
11228
11729
  reasoning: true,
11229
11730
  input: ["text"],
11230
11731
  cost: {
11231
- input: 0.09,
11732
+ input: 0.09999999999999999,
11232
11733
  output: 0.3,
11233
- cacheRead: 0.02,
11734
+ cacheRead: 0,
11234
11735
  cacheWrite: 0,
11235
11736
  },
11236
11737
  contextWindow: 262144,
11237
- maxTokens: 16384,
11738
+ maxTokens: 65536,
11238
11739
  },
11239
11740
  "stepfun/step-3.7-flash": {
11240
11741
  id: "stepfun/step-3.7-flash",
@@ -11253,6 +11754,23 @@ export const MODELS = {
11253
11754
  contextWindow: 256000,
11254
11755
  maxTokens: 256000,
11255
11756
  },
11757
+ "tencent/hy3": {
11758
+ id: "tencent/hy3",
11759
+ name: "Tencent: Hy3",
11760
+ api: "openai-completions",
11761
+ provider: "openrouter",
11762
+ baseUrl: "https://openrouter.ai/api/v1",
11763
+ reasoning: true,
11764
+ input: ["text"],
11765
+ cost: {
11766
+ input: 0.14,
11767
+ output: 0.58,
11768
+ cacheRead: 0.035,
11769
+ cacheWrite: 0,
11770
+ },
11771
+ contextWindow: 262144,
11772
+ maxTokens: 4096,
11773
+ },
11256
11774
  "tencent/hy3-preview": {
11257
11775
  id: "tencent/hy3-preview",
11258
11776
  name: "Tencent: Hy3 preview",
@@ -11270,6 +11788,23 @@ export const MODELS = {
11270
11788
  contextWindow: 262144,
11271
11789
  maxTokens: 4096,
11272
11790
  },
11791
+ "tencent/hy3:free": {
11792
+ id: "tencent/hy3:free",
11793
+ name: "Tencent: Hy3 (free)",
11794
+ api: "openai-completions",
11795
+ provider: "openrouter",
11796
+ baseUrl: "https://openrouter.ai/api/v1",
11797
+ reasoning: true,
11798
+ input: ["text"],
11799
+ cost: {
11800
+ input: 0,
11801
+ output: 0,
11802
+ cacheRead: 0,
11803
+ cacheWrite: 0,
11804
+ },
11805
+ contextWindow: 262144,
11806
+ maxTokens: 262144,
11807
+ },
11273
11808
  "thedrummer/unslopnemo-12b": {
11274
11809
  id: "thedrummer/unslopnemo-12b",
11275
11810
  name: "TheDrummer: UnslopNemo 12B",
@@ -11338,6 +11873,23 @@ export const MODELS = {
11338
11873
  contextWindow: 1000000,
11339
11874
  maxTokens: 4096,
11340
11875
  },
11876
+ "x-ai/grok-4.5": {
11877
+ id: "x-ai/grok-4.5",
11878
+ name: "xAI: Grok 4.5",
11879
+ api: "openai-completions",
11880
+ provider: "openrouter",
11881
+ baseUrl: "https://openrouter.ai/api/v1",
11882
+ reasoning: true,
11883
+ input: ["text", "image"],
11884
+ cost: {
11885
+ input: 2,
11886
+ output: 6,
11887
+ cacheRead: 0.5,
11888
+ cacheWrite: 0,
11889
+ },
11890
+ contextWindow: 500000,
11891
+ maxTokens: 4096,
11892
+ },
11341
11893
  "x-ai/grok-build-0.1": {
11342
11894
  id: "x-ai/grok-build-0.1",
11343
11895
  name: "xAI: Grok Build 0.1",
@@ -11366,7 +11918,7 @@ export const MODELS = {
11366
11918
  cost: {
11367
11919
  input: 0.105,
11368
11920
  output: 0.28,
11369
- cacheRead: 0,
11921
+ cacheRead: 0.028,
11370
11922
  cacheWrite: 0,
11371
11923
  },
11372
11924
  contextWindow: 1048576,
@@ -11551,13 +12103,13 @@ export const MODELS = {
11551
12103
  reasoning: true,
11552
12104
  input: ["text"],
11553
12105
  cost: {
11554
- input: 0.98,
11555
- output: 3.08,
11556
- cacheRead: 0.182,
12106
+ input: 0.966,
12107
+ output: 3.036,
12108
+ cacheRead: 0.1794,
11557
12109
  cacheWrite: 0,
11558
12110
  },
11559
12111
  contextWindow: 202752,
11560
- maxTokens: 4096,
12112
+ maxTokens: 128000,
11561
12113
  },
11562
12114
  "z-ai/glm-5.2": {
11563
12115
  id: "z-ai/glm-5.2",
@@ -11568,13 +12120,13 @@ export const MODELS = {
11568
12120
  reasoning: true,
11569
12121
  input: ["text"],
11570
12122
  cost: {
11571
- input: 0.95,
11572
- output: 3,
11573
- cacheRead: 0.18,
12123
+ input: 0.54,
12124
+ output: 1.76,
12125
+ cacheRead: 0.09999999999999999,
11574
12126
  cacheWrite: 0,
11575
12127
  },
11576
12128
  contextWindow: 1048576,
11577
- maxTokens: 32768,
12129
+ maxTokens: 101376,
11578
12130
  },
11579
12131
  "z-ai/glm-5v-turbo": {
11580
12132
  id: "z-ai/glm-5v-turbo",
@@ -11653,10 +12205,10 @@ export const MODELS = {
11653
12205
  reasoning: true,
11654
12206
  input: ["text", "image"],
11655
12207
  cost: {
11656
- input: 3,
11657
- output: 15,
11658
- cacheRead: 0.3,
11659
- cacheWrite: 3.75,
12208
+ input: 2,
12209
+ output: 10,
12210
+ cacheRead: 0.19999999999999998,
12211
+ cacheWrite: 2.5,
11660
12212
  },
11661
12213
  contextWindow: 1000000,
11662
12214
  maxTokens: 128000,
@@ -11706,7 +12258,7 @@ export const MODELS = {
11706
12258
  cost: {
11707
12259
  input: 0.66,
11708
12260
  output: 3.41,
11709
- cacheRead: 0.144,
12261
+ cacheRead: 0.15,
11710
12262
  cacheWrite: 0,
11711
12263
  },
11712
12264
  contextWindow: 262144,
@@ -11724,7 +12276,7 @@ export const MODELS = {
11724
12276
  input: 5,
11725
12277
  output: 30,
11726
12278
  cacheRead: 0.5,
11727
- cacheWrite: 0,
12279
+ cacheWrite: 6.25,
11728
12280
  },
11729
12281
  contextWindow: 1050000,
11730
12282
  maxTokens: 128000,
@@ -11746,6 +12298,23 @@ export const MODELS = {
11746
12298
  contextWindow: 400000,
11747
12299
  maxTokens: 128000,
11748
12300
  },
12301
+ "~x-ai/grok-latest": {
12302
+ id: "~x-ai/grok-latest",
12303
+ name: "xAI: Grok Latest",
12304
+ api: "openai-completions",
12305
+ provider: "openrouter",
12306
+ baseUrl: "https://openrouter.ai/api/v1",
12307
+ reasoning: true,
12308
+ input: ["text", "image"],
12309
+ cost: {
12310
+ input: 2,
12311
+ output: 6,
12312
+ cacheRead: 0.5,
12313
+ cacheWrite: 0,
12314
+ },
12315
+ contextWindow: 500000,
12316
+ maxTokens: 4096,
12317
+ },
11749
12318
  },
11750
12319
  "vercel-ai-gateway": {
11751
12320
  "alibaba/qwen-3-14b": {
@@ -12258,6 +12827,23 @@ export const MODELS = {
12258
12827
  contextWindow: 200000,
12259
12828
  maxTokens: 8192,
12260
12829
  },
12830
+ "anthropic/claude-fable-5": {
12831
+ id: "anthropic/claude-fable-5",
12832
+ name: "Claude Fable 5",
12833
+ api: "anthropic-messages",
12834
+ provider: "vercel-ai-gateway",
12835
+ baseUrl: "https://ai-gateway.vercel.sh",
12836
+ reasoning: true,
12837
+ input: ["text", "image"],
12838
+ cost: {
12839
+ input: 10,
12840
+ output: 50,
12841
+ cacheRead: 1,
12842
+ cacheWrite: 12.5,
12843
+ },
12844
+ contextWindow: 1000000,
12845
+ maxTokens: 128000,
12846
+ },
12261
12847
  "anthropic/claude-haiku-4.5": {
12262
12848
  id: "anthropic/claude-haiku-4.5",
12263
12849
  name: "Claude Haiku 4.5",
@@ -12428,6 +13014,23 @@ export const MODELS = {
12428
13014
  contextWindow: 1000000,
12429
13015
  maxTokens: 128000,
12430
13016
  },
13017
+ "anthropic/claude-sonnet-5": {
13018
+ id: "anthropic/claude-sonnet-5",
13019
+ name: "Claude Sonnet 5",
13020
+ api: "anthropic-messages",
13021
+ provider: "vercel-ai-gateway",
13022
+ baseUrl: "https://ai-gateway.vercel.sh",
13023
+ reasoning: true,
13024
+ input: ["text", "image"],
13025
+ cost: {
13026
+ input: 2,
13027
+ output: 10,
13028
+ cacheRead: 0.19999999999999998,
13029
+ cacheWrite: 2.5,
13030
+ },
13031
+ contextWindow: 1000000,
13032
+ maxTokens: 128000,
13033
+ },
12431
13034
  "arcee-ai/trinity-large-preview": {
12432
13035
  id: "arcee-ai/trinity-large-preview",
12433
13036
  name: "Trinity Large Preview",
@@ -12643,7 +13246,7 @@ export const MODELS = {
12643
13246
  cost: {
12644
13247
  input: 0.14,
12645
13248
  output: 0.28,
12646
- cacheRead: 0.0028,
13249
+ cacheRead: 0.028,
12647
13250
  cacheWrite: 0,
12648
13251
  },
12649
13252
  contextWindow: 1000000,
@@ -13091,6 +13694,23 @@ export const MODELS = {
13091
13694
  contextWindow: 128000,
13092
13695
  maxTokens: 8192,
13093
13696
  },
13697
+ "meta/muse-spark-1.1": {
13698
+ id: "meta/muse-spark-1.1",
13699
+ name: "Muse Spark 1.1",
13700
+ api: "anthropic-messages",
13701
+ provider: "vercel-ai-gateway",
13702
+ baseUrl: "https://ai-gateway.vercel.sh",
13703
+ reasoning: true,
13704
+ input: ["text", "image"],
13705
+ cost: {
13706
+ input: 1.25,
13707
+ output: 4.25,
13708
+ cacheRead: 0.15,
13709
+ cacheWrite: 0,
13710
+ },
13711
+ contextWindow: 1048576,
13712
+ maxTokens: 1048576,
13713
+ },
13094
13714
  "minimax/minimax-m2": {
13095
13715
  id: "minimax/minimax-m2",
13096
13716
  name: "MiniMax M2",
@@ -14196,6 +14816,57 @@ export const MODELS = {
14196
14816
  contextWindow: 1000000,
14197
14817
  maxTokens: 128000,
14198
14818
  },
14819
+ "openai/gpt-5.6-luna": {
14820
+ id: "openai/gpt-5.6-luna",
14821
+ name: "GPT 5.6 Luna",
14822
+ api: "anthropic-messages",
14823
+ provider: "vercel-ai-gateway",
14824
+ baseUrl: "https://ai-gateway.vercel.sh",
14825
+ reasoning: true,
14826
+ input: ["text", "image"],
14827
+ cost: {
14828
+ input: 1,
14829
+ output: 6,
14830
+ cacheRead: 0.09999999999999999,
14831
+ cacheWrite: 1.25,
14832
+ },
14833
+ contextWindow: 1050000,
14834
+ maxTokens: 128000,
14835
+ },
14836
+ "openai/gpt-5.6-sol": {
14837
+ id: "openai/gpt-5.6-sol",
14838
+ name: "GPT 5.6 Sol",
14839
+ api: "anthropic-messages",
14840
+ provider: "vercel-ai-gateway",
14841
+ baseUrl: "https://ai-gateway.vercel.sh",
14842
+ reasoning: true,
14843
+ input: ["text", "image"],
14844
+ cost: {
14845
+ input: 5,
14846
+ output: 30,
14847
+ cacheRead: 0.5,
14848
+ cacheWrite: 6.25,
14849
+ },
14850
+ contextWindow: 1050000,
14851
+ maxTokens: 128000,
14852
+ },
14853
+ "openai/gpt-5.6-terra": {
14854
+ id: "openai/gpt-5.6-terra",
14855
+ name: "GPT 5.6 Terra",
14856
+ api: "anthropic-messages",
14857
+ provider: "vercel-ai-gateway",
14858
+ baseUrl: "https://ai-gateway.vercel.sh",
14859
+ reasoning: true,
14860
+ input: ["text", "image"],
14861
+ cost: {
14862
+ input: 2.5,
14863
+ output: 15,
14864
+ cacheRead: 0.25,
14865
+ cacheWrite: 3.125,
14866
+ },
14867
+ contextWindow: 1050000,
14868
+ maxTokens: 128000,
14869
+ },
14199
14870
  "openai/gpt-oss-120b": {
14200
14871
  id: "openai/gpt-oss-120b",
14201
14872
  name: "GPT OSS 120B",
@@ -14553,6 +15224,23 @@ export const MODELS = {
14553
15224
  contextWindow: 1000000,
14554
15225
  maxTokens: 1000000,
14555
15226
  },
15227
+ "xai/grok-4.5": {
15228
+ id: "xai/grok-4.5",
15229
+ name: "Grok 4.5",
15230
+ api: "anthropic-messages",
15231
+ provider: "vercel-ai-gateway",
15232
+ baseUrl: "https://ai-gateway.vercel.sh",
15233
+ reasoning: true,
15234
+ input: ["text", "image"],
15235
+ cost: {
15236
+ input: 2,
15237
+ output: 6,
15238
+ cacheRead: 0.5,
15239
+ cacheWrite: 0,
15240
+ },
15241
+ contextWindow: 500000,
15242
+ maxTokens: 500000,
15243
+ },
14556
15244
  "xai/grok-build-0.1": {
14557
15245
  id: "xai/grok-build-0.1",
14558
15246
  name: "Grok Build 0.1",
@@ -14640,7 +15328,7 @@ export const MODELS = {
14640
15328
  },
14641
15329
  "zai/glm-4.5": {
14642
15330
  id: "zai/glm-4.5",
14643
- name: "GLM-4.5",
15331
+ name: "GLM 4.5",
14644
15332
  api: "anthropic-messages",
14645
15333
  provider: "vercel-ai-gateway",
14646
15334
  baseUrl: "https://ai-gateway.vercel.sh",
@@ -14851,12 +15539,12 @@ export const MODELS = {
14851
15539
  reasoning: true,
14852
15540
  input: ["text"],
14853
15541
  cost: {
14854
- input: 1.5,
14855
- output: 4.5,
14856
- cacheRead: 0.3,
15542
+ input: 1.4,
15543
+ output: 4.4,
15544
+ cacheRead: 0.26,
14857
15545
  cacheWrite: 0,
14858
15546
  },
14859
- contextWindow: 1000000,
15547
+ contextWindow: 1040000,
14860
15548
  maxTokens: 128000,
14861
15549
  },
14862
15550
  "zai/glm-5.2-fast": {
@@ -14946,6 +15634,23 @@ export const MODELS = {
14946
15634
  contextWindow: 1000000,
14947
15635
  maxTokens: 30000,
14948
15636
  },
15637
+ "grok-4.5": {
15638
+ id: "grok-4.5",
15639
+ name: "Grok 4.5",
15640
+ api: "openai-completions",
15641
+ provider: "xai",
15642
+ baseUrl: "https://api.x.ai/v1",
15643
+ reasoning: true,
15644
+ input: ["text", "image"],
15645
+ cost: {
15646
+ input: 2,
15647
+ output: 6,
15648
+ cacheRead: 0.5,
15649
+ cacheWrite: 0,
15650
+ },
15651
+ contextWindow: 500000,
15652
+ maxTokens: 500000,
15653
+ },
14949
15654
  "grok-build-0.1": {
14950
15655
  id: "grok-build-0.1",
14951
15656
  name: "Grok Build 0.1",