@elyracode/ai 0.9.41 → 0.9.43

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.
@@ -237,6 +237,24 @@ export const MODELS = {
237
237
  contextWindow: 1000000,
238
238
  maxTokens: 128000,
239
239
  },
240
+ "anthropic.claude-opus-5-5": {
241
+ id: "anthropic.claude-opus-5-5",
242
+ name: "Claude Opus 5.5",
243
+ api: "bedrock-converse-stream",
244
+ provider: "amazon-bedrock",
245
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
246
+ reasoning: true,
247
+ thinkingType: "adaptive",
248
+ input: ["text", "image"],
249
+ cost: {
250
+ input: 4,
251
+ output: 20,
252
+ cacheRead: 0.2,
253
+ cacheWrite: 5,
254
+ },
255
+ contextWindow: 1000000,
256
+ maxTokens: 128000,
257
+ },
240
258
  "anthropic.claude-sonnet-4-5-20250929-v1:0": {
241
259
  id: "anthropic.claude-sonnet-4-5-20250929-v1:0",
242
260
  name: "Claude Sonnet 4.5",
@@ -453,6 +471,24 @@ export const MODELS = {
453
471
  contextWindow: 1000000,
454
472
  maxTokens: 128000,
455
473
  },
474
+ "au.anthropic.claude-opus-5-5": {
475
+ id: "au.anthropic.claude-opus-5-5",
476
+ name: "Claude Opus 5.5 (AU)",
477
+ api: "bedrock-converse-stream",
478
+ provider: "amazon-bedrock",
479
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
480
+ reasoning: true,
481
+ thinkingType: "adaptive",
482
+ input: ["text", "image"],
483
+ cost: {
484
+ input: 4.4,
485
+ output: 22,
486
+ cacheRead: 0.22,
487
+ cacheWrite: 5.5,
488
+ },
489
+ contextWindow: 1000000,
490
+ maxTokens: 128000,
491
+ },
456
492
  "au.anthropic.claude-sonnet-4-5-20250929-v1:0": {
457
493
  id: "au.anthropic.claude-sonnet-4-5-20250929-v1:0",
458
494
  name: "Claude Sonnet 4.5 (AU)",
@@ -756,6 +792,24 @@ export const MODELS = {
756
792
  contextWindow: 1000000,
757
793
  maxTokens: 128000,
758
794
  },
795
+ "eu.anthropic.claude-opus-5-5": {
796
+ id: "eu.anthropic.claude-opus-5-5",
797
+ name: "Claude Opus 5.5 (EU)",
798
+ api: "bedrock-converse-stream",
799
+ provider: "amazon-bedrock",
800
+ baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
801
+ reasoning: true,
802
+ thinkingType: "adaptive",
803
+ input: ["text", "image"],
804
+ cost: {
805
+ input: 4.4,
806
+ output: 22,
807
+ cacheRead: 0.22,
808
+ cacheWrite: 5.5,
809
+ },
810
+ contextWindow: 1000000,
811
+ maxTokens: 128000,
812
+ },
759
813
  "eu.anthropic.claude-sonnet-4-20250514-v1:0": {
760
814
  id: "eu.anthropic.claude-sonnet-4-20250514-v1:0",
761
815
  name: "Claude Sonnet 4 (EU)",
@@ -1011,6 +1065,24 @@ export const MODELS = {
1011
1065
  contextWindow: 1000000,
1012
1066
  maxTokens: 128000,
1013
1067
  },
1068
+ "global.anthropic.claude-opus-5-5": {
1069
+ id: "global.anthropic.claude-opus-5-5",
1070
+ name: "Claude Opus 5.5 (Global)",
1071
+ api: "bedrock-converse-stream",
1072
+ provider: "amazon-bedrock",
1073
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1074
+ reasoning: true,
1075
+ thinkingType: "adaptive",
1076
+ input: ["text", "image"],
1077
+ cost: {
1078
+ input: 4,
1079
+ output: 20,
1080
+ cacheRead: 0.2,
1081
+ cacheWrite: 5,
1082
+ },
1083
+ contextWindow: 1000000,
1084
+ maxTokens: 128000,
1085
+ },
1014
1086
  "global.anthropic.claude-sonnet-4-20250514-v1:0": {
1015
1087
  id: "global.anthropic.claude-sonnet-4-20250514-v1:0",
1016
1088
  name: "Claude Sonnet 4 (Global)",
@@ -1083,6 +1155,23 @@ export const MODELS = {
1083
1155
  contextWindow: 1000000,
1084
1156
  maxTokens: 128000,
1085
1157
  },
1158
+ "global.moonshotai.kimi-k3": {
1159
+ id: "global.moonshotai.kimi-k3",
1160
+ name: "Kimi K3 (Global)",
1161
+ api: "bedrock-converse-stream",
1162
+ provider: "amazon-bedrock",
1163
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1164
+ reasoning: true,
1165
+ input: ["text", "image"],
1166
+ cost: {
1167
+ input: 3,
1168
+ output: 15,
1169
+ cacheRead: 0.3,
1170
+ cacheWrite: 3.75,
1171
+ },
1172
+ contextWindow: 1048576,
1173
+ maxTokens: 128000,
1174
+ },
1086
1175
  "global.openai.gpt-5.6-luna": {
1087
1176
  id: "global.openai.gpt-5.6-luna",
1088
1177
  name: "GPT-5.6 Luna (Global)",
@@ -1151,6 +1240,40 @@ export const MODELS = {
1151
1240
  contextWindow: 1050000,
1152
1241
  maxTokens: 128000,
1153
1242
  },
1243
+ "global.openai.gpt-6-luna": {
1244
+ id: "global.openai.gpt-6-luna",
1245
+ name: "GPT-6 Luna (Global)",
1246
+ api: "bedrock-converse-stream",
1247
+ provider: "amazon-bedrock",
1248
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1249
+ reasoning: true,
1250
+ input: ["text", "image"],
1251
+ cost: {
1252
+ input: 0.1,
1253
+ output: 0.5,
1254
+ cacheRead: 0.01,
1255
+ cacheWrite: 0.125,
1256
+ },
1257
+ contextWindow: 1050000,
1258
+ maxTokens: 128000,
1259
+ },
1260
+ "global.openai.gpt-6-sol": {
1261
+ id: "global.openai.gpt-6-sol",
1262
+ name: "GPT-6 Sol (Global)",
1263
+ api: "bedrock-converse-stream",
1264
+ provider: "amazon-bedrock",
1265
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1266
+ reasoning: true,
1267
+ input: ["text", "image"],
1268
+ cost: {
1269
+ input: 2,
1270
+ output: 10,
1271
+ cacheRead: 0.2,
1272
+ cacheWrite: 2.5,
1273
+ },
1274
+ contextWindow: 1050000,
1275
+ maxTokens: 128000,
1276
+ },
1154
1277
  "global.xai.grok-4.6": {
1155
1278
  id: "global.xai.grok-4.6",
1156
1279
  name: "Grok 4.6 (Global)",
@@ -1344,6 +1467,24 @@ export const MODELS = {
1344
1467
  contextWindow: 1000000,
1345
1468
  maxTokens: 128000,
1346
1469
  },
1470
+ "jp.anthropic.claude-opus-5-5": {
1471
+ id: "jp.anthropic.claude-opus-5-5",
1472
+ name: "Claude Opus 5.5 (JP)",
1473
+ api: "bedrock-converse-stream",
1474
+ provider: "amazon-bedrock",
1475
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1476
+ reasoning: true,
1477
+ thinkingType: "adaptive",
1478
+ input: ["text", "image"],
1479
+ cost: {
1480
+ input: 4.4,
1481
+ output: 22,
1482
+ cacheRead: 0.22,
1483
+ cacheWrite: 5.5,
1484
+ },
1485
+ contextWindow: 1000000,
1486
+ maxTokens: 128000,
1487
+ },
1347
1488
  "jp.anthropic.claude-sonnet-4-5-20250929-v1:0": {
1348
1489
  id: "jp.anthropic.claude-sonnet-4-5-20250929-v1:0",
1349
1490
  name: "Claude Sonnet 4.5 (JP)",
@@ -1514,7 +1655,7 @@ export const MODELS = {
1514
1655
  cacheRead: 0,
1515
1656
  cacheWrite: 0,
1516
1657
  },
1517
- contextWindow: 204800,
1658
+ contextWindow: 196608,
1518
1659
  maxTokens: 131072,
1519
1660
  },
1520
1661
  "minimax.minimax-m2.5": {
@@ -1548,7 +1689,7 @@ export const MODELS = {
1548
1689
  cacheRead: 0,
1549
1690
  cacheWrite: 0,
1550
1691
  },
1551
- contextWindow: 256000,
1692
+ contextWindow: 262144,
1552
1693
  maxTokens: 8192,
1553
1694
  },
1554
1695
  "mistral.magistral-small-2509": {
@@ -1633,7 +1774,7 @@ export const MODELS = {
1633
1774
  cacheRead: 0,
1634
1775
  cacheWrite: 0,
1635
1776
  },
1636
- contextWindow: 256000,
1777
+ contextWindow: 262144,
1637
1778
  maxTokens: 8192,
1638
1779
  },
1639
1780
  "mistral.pixtral-large-2502-v1:0": {
@@ -1701,7 +1842,7 @@ export const MODELS = {
1701
1842
  cacheRead: 0,
1702
1843
  cacheWrite: 0,
1703
1844
  },
1704
- contextWindow: 262143,
1845
+ contextWindow: 262144,
1705
1846
  maxTokens: 16000,
1706
1847
  },
1707
1848
  "moonshotai.kimi-k2.5": {
@@ -1718,7 +1859,7 @@ export const MODELS = {
1718
1859
  cacheRead: 0,
1719
1860
  cacheWrite: 0,
1720
1861
  },
1721
- contextWindow: 262143,
1862
+ contextWindow: 262144,
1722
1863
  maxTokens: 16384,
1723
1864
  },
1724
1865
  "nvidia.nemotron-nano-12b-v2": {
@@ -1735,7 +1876,7 @@ export const MODELS = {
1735
1876
  cacheRead: 0,
1736
1877
  cacheWrite: 0,
1737
1878
  },
1738
- contextWindow: 128000,
1879
+ contextWindow: 131072,
1739
1880
  maxTokens: 8192,
1740
1881
  },
1741
1882
  "nvidia.nemotron-nano-3-30b": {
@@ -1804,7 +1945,7 @@ export const MODELS = {
1804
1945
  cacheRead: 0.275,
1805
1946
  cacheWrite: 0,
1806
1947
  },
1807
- contextWindow: 272000,
1948
+ contextWindow: 1000000,
1808
1949
  maxTokens: 128000,
1809
1950
  },
1810
1951
  "openai.gpt-5.5": {
@@ -1822,7 +1963,7 @@ export const MODELS = {
1822
1963
  cacheRead: 0.55,
1823
1964
  cacheWrite: 0,
1824
1965
  },
1825
- contextWindow: 272000,
1966
+ contextWindow: 1000000,
1826
1967
  maxTokens: 128000,
1827
1968
  },
1828
1969
  "openai.gpt-5.6-luna": {
@@ -1893,6 +2034,40 @@ export const MODELS = {
1893
2034
  contextWindow: 1050000,
1894
2035
  maxTokens: 128000,
1895
2036
  },
2037
+ "openai.gpt-6-luna": {
2038
+ id: "openai.gpt-6-luna",
2039
+ name: "GPT-6 Luna",
2040
+ api: "bedrock-converse-stream",
2041
+ provider: "amazon-bedrock",
2042
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2043
+ reasoning: true,
2044
+ input: ["text", "image"],
2045
+ cost: {
2046
+ input: 0.11,
2047
+ output: 0.55,
2048
+ cacheRead: 0.011,
2049
+ cacheWrite: 0.1375,
2050
+ },
2051
+ contextWindow: 1050000,
2052
+ maxTokens: 128000,
2053
+ },
2054
+ "openai.gpt-6-sol": {
2055
+ id: "openai.gpt-6-sol",
2056
+ name: "GPT-6 Sol",
2057
+ api: "bedrock-converse-stream",
2058
+ provider: "amazon-bedrock",
2059
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2060
+ reasoning: true,
2061
+ input: ["text", "image"],
2062
+ cost: {
2063
+ input: 2.2,
2064
+ output: 11,
2065
+ cacheRead: 0.22,
2066
+ cacheWrite: 2.75,
2067
+ },
2068
+ contextWindow: 1050000,
2069
+ maxTokens: 128000,
2070
+ },
1896
2071
  "openai.gpt-oss-120b": {
1897
2072
  id: "openai.gpt-oss-120b",
1898
2073
  name: "gpt-oss-120b",
@@ -1907,8 +2082,8 @@ export const MODELS = {
1907
2082
  cacheRead: 0,
1908
2083
  cacheWrite: 0,
1909
2084
  },
1910
- contextWindow: 128000,
1911
- maxTokens: 16384,
2085
+ contextWindow: 131072,
2086
+ maxTokens: 131072,
1912
2087
  },
1913
2088
  "openai.gpt-oss-120b-1:0": {
1914
2089
  id: "openai.gpt-oss-120b-1:0",
@@ -1924,8 +2099,8 @@ export const MODELS = {
1924
2099
  cacheRead: 0,
1925
2100
  cacheWrite: 0,
1926
2101
  },
1927
- contextWindow: 128000,
1928
- maxTokens: 16384,
2102
+ contextWindow: 131072,
2103
+ maxTokens: 128000,
1929
2104
  },
1930
2105
  "openai.gpt-oss-20b": {
1931
2106
  id: "openai.gpt-oss-20b",
@@ -1941,8 +2116,8 @@ export const MODELS = {
1941
2116
  cacheRead: 0,
1942
2117
  cacheWrite: 0,
1943
2118
  },
1944
- contextWindow: 128000,
1945
- maxTokens: 16384,
2119
+ contextWindow: 131072,
2120
+ maxTokens: 131072,
1946
2121
  },
1947
2122
  "openai.gpt-oss-20b-1:0": {
1948
2123
  id: "openai.gpt-oss-20b-1:0",
@@ -1958,8 +2133,8 @@ export const MODELS = {
1958
2133
  cacheRead: 0,
1959
2134
  cacheWrite: 0,
1960
2135
  },
1961
- contextWindow: 128000,
1962
- maxTokens: 16384,
2136
+ contextWindow: 131072,
2137
+ maxTokens: 128000,
1963
2138
  },
1964
2139
  "openai.gpt-oss-safeguard-120b": {
1965
2140
  id: "openai.gpt-oss-safeguard-120b",
@@ -2400,6 +2575,24 @@ export const MODELS = {
2400
2575
  contextWindow: 1000000,
2401
2576
  maxTokens: 128000,
2402
2577
  },
2578
+ "us.anthropic.claude-opus-5-5": {
2579
+ id: "us.anthropic.claude-opus-5-5",
2580
+ name: "Claude Opus 5.5 (US)",
2581
+ api: "bedrock-converse-stream",
2582
+ provider: "amazon-bedrock",
2583
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2584
+ reasoning: true,
2585
+ thinkingType: "adaptive",
2586
+ input: ["text", "image"],
2587
+ cost: {
2588
+ input: 4.4,
2589
+ output: 22,
2590
+ cacheRead: 0.22,
2591
+ cacheWrite: 5.5,
2592
+ },
2593
+ contextWindow: 1000000,
2594
+ maxTokens: 128000,
2595
+ },
2403
2596
  "us.anthropic.claude-sonnet-4-20250514-v1:0": {
2404
2597
  id: "us.anthropic.claude-sonnet-4-20250514-v1:0",
2405
2598
  name: "Claude Sonnet 4 (US)",
@@ -2574,6 +2767,23 @@ export const MODELS = {
2574
2767
  contextWindow: 128000,
2575
2768
  maxTokens: 8192,
2576
2769
  },
2770
+ "us.moonshotai.kimi-k3": {
2771
+ id: "us.moonshotai.kimi-k3",
2772
+ name: "Kimi K3 (US)",
2773
+ api: "bedrock-converse-stream",
2774
+ provider: "amazon-bedrock",
2775
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2776
+ reasoning: true,
2777
+ input: ["text", "image"],
2778
+ cost: {
2779
+ input: 3.3,
2780
+ output: 16.5,
2781
+ cacheRead: 0.33,
2782
+ cacheWrite: 4.125,
2783
+ },
2784
+ contextWindow: 1048576,
2785
+ maxTokens: 128000,
2786
+ },
2577
2787
  "us.openai.gpt-5.6-luna": {
2578
2788
  id: "us.openai.gpt-5.6-luna",
2579
2789
  name: "GPT-5.6 Luna (US)",
@@ -2642,6 +2852,40 @@ export const MODELS = {
2642
2852
  contextWindow: 1050000,
2643
2853
  maxTokens: 128000,
2644
2854
  },
2855
+ "us.openai.gpt-6-luna": {
2856
+ id: "us.openai.gpt-6-luna",
2857
+ name: "GPT-6 Luna (US)",
2858
+ api: "bedrock-converse-stream",
2859
+ provider: "amazon-bedrock",
2860
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2861
+ reasoning: true,
2862
+ input: ["text", "image"],
2863
+ cost: {
2864
+ input: 0.11,
2865
+ output: 0.55,
2866
+ cacheRead: 0.011,
2867
+ cacheWrite: 0.1375,
2868
+ },
2869
+ contextWindow: 1050000,
2870
+ maxTokens: 128000,
2871
+ },
2872
+ "us.openai.gpt-6-sol": {
2873
+ id: "us.openai.gpt-6-sol",
2874
+ name: "GPT-6 Sol (US)",
2875
+ api: "bedrock-converse-stream",
2876
+ provider: "amazon-bedrock",
2877
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2878
+ reasoning: true,
2879
+ input: ["text", "image"],
2880
+ cost: {
2881
+ input: 2.2,
2882
+ output: 11,
2883
+ cacheRead: 0.22,
2884
+ cacheWrite: 2.75,
2885
+ },
2886
+ contextWindow: 1050000,
2887
+ maxTokens: 128000,
2888
+ },
2645
2889
  "us.writer.palmyra-x4-v1:0": {
2646
2890
  id: "us.writer.palmyra-x4-v1:0",
2647
2891
  name: "Palmyra X4 (US)",
@@ -2775,7 +3019,7 @@ export const MODELS = {
2775
3019
  cacheRead: 0,
2776
3020
  cacheWrite: 0,
2777
3021
  },
2778
- contextWindow: 204800,
3022
+ contextWindow: 202752,
2779
3023
  maxTokens: 131072,
2780
3024
  },
2781
3025
  "zai.glm-4.7-flash": {
@@ -2792,7 +3036,7 @@ export const MODELS = {
2792
3036
  cacheRead: 0,
2793
3037
  cacheWrite: 0,
2794
3038
  },
2795
- contextWindow: 200000,
3039
+ contextWindow: 202752,
2796
3040
  maxTokens: 131072,
2797
3041
  },
2798
3042
  "zai.glm-5": {
@@ -2999,6 +3243,24 @@ export const MODELS = {
2999
3243
  contextWindow: 1000000,
3000
3244
  maxTokens: 128000,
3001
3245
  },
3246
+ "claude-opus-5-5": {
3247
+ id: "claude-opus-5-5",
3248
+ name: "Claude Opus 5.5",
3249
+ api: "anthropic-messages",
3250
+ provider: "anthropic",
3251
+ baseUrl: "https://api.anthropic.com",
3252
+ reasoning: true,
3253
+ thinkingType: "adaptive",
3254
+ input: ["text", "image"],
3255
+ cost: {
3256
+ input: 4,
3257
+ output: 20,
3258
+ cacheRead: 0.2,
3259
+ cacheWrite: 5,
3260
+ },
3261
+ contextWindow: 1000000,
3262
+ maxTokens: 128000,
3263
+ },
3002
3264
  "claude-sonnet-4-5": {
3003
3265
  id: "claude-sonnet-4-5",
3004
3266
  name: "Claude Sonnet 4.5 (latest)",
@@ -3624,19 +3886,53 @@ export const MODELS = {
3624
3886
  contextWindow: 1050000,
3625
3887
  maxTokens: 128000,
3626
3888
  },
3627
- "gpt-realtime-2.1": {
3628
- id: "gpt-realtime-2.1",
3629
- name: "GPT-Realtime-2.1",
3889
+ "gpt-6-luna": {
3890
+ id: "gpt-6-luna",
3891
+ name: "GPT-6 Luna",
3630
3892
  api: "azure-openai-responses",
3631
3893
  provider: "azure-openai-responses",
3632
3894
  baseUrl: "",
3633
3895
  reasoning: true,
3634
3896
  input: ["text", "image"],
3635
3897
  cost: {
3636
- input: 4,
3637
- output: 24,
3638
- cacheRead: 0.4,
3639
- cacheWrite: 0,
3898
+ input: 0.1,
3899
+ output: 0.5,
3900
+ cacheRead: 0.01,
3901
+ cacheWrite: 0.125,
3902
+ },
3903
+ contextWindow: 1050000,
3904
+ maxTokens: 128000,
3905
+ },
3906
+ "gpt-6-sol": {
3907
+ id: "gpt-6-sol",
3908
+ name: "GPT-6 Sol",
3909
+ api: "azure-openai-responses",
3910
+ provider: "azure-openai-responses",
3911
+ baseUrl: "",
3912
+ reasoning: true,
3913
+ input: ["text", "image"],
3914
+ cost: {
3915
+ input: 2,
3916
+ output: 10,
3917
+ cacheRead: 0.2,
3918
+ cacheWrite: 2.5,
3919
+ },
3920
+ contextWindow: 1050000,
3921
+ maxTokens: 128000,
3922
+ },
3923
+ "gpt-realtime-2.1": {
3924
+ id: "gpt-realtime-2.1",
3925
+ name: "GPT-Realtime-2.1",
3926
+ api: "azure-openai-responses",
3927
+ provider: "azure-openai-responses",
3928
+ baseUrl: "",
3929
+ reasoning: true,
3930
+ input: ["text", "image"],
3931
+ cost: {
3932
+ input: 4,
3933
+ output: 24,
3934
+ cacheRead: 0.4,
3935
+ cacheWrite: 0,
3640
3936
  },
3641
3937
  contextWindow: 128000,
3642
3938
  maxTokens: 32000,
@@ -3922,6 +4218,23 @@ export const MODELS = {
3922
4218
  contextWindow: 1000000,
3923
4219
  maxTokens: 128000,
3924
4220
  },
4221
+ "claude-opus-5.5": {
4222
+ id: "claude-opus-5.5",
4223
+ name: "Claude Opus 5.5",
4224
+ api: "anthropic-messages",
4225
+ provider: "cloudflare-ai-gateway",
4226
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
4227
+ reasoning: true,
4228
+ input: ["text", "image"],
4229
+ cost: {
4230
+ input: 4,
4231
+ output: 20,
4232
+ cacheRead: 0.2,
4233
+ cacheWrite: 5,
4234
+ },
4235
+ contextWindow: 1000000,
4236
+ maxTokens: 128000,
4237
+ },
3925
4238
  "claude-sonnet-4.5": {
3926
4239
  id: "claude-sonnet-4.5",
3927
4240
  name: "Claude Sonnet 4.5 (latest)",
@@ -4309,6 +4622,40 @@ export const MODELS = {
4309
4622
  contextWindow: 1050000,
4310
4623
  maxTokens: 128000,
4311
4624
  },
4625
+ "gpt-6-luna": {
4626
+ id: "gpt-6-luna",
4627
+ name: "GPT-6 Luna",
4628
+ api: "openai-responses",
4629
+ provider: "cloudflare-ai-gateway",
4630
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
4631
+ reasoning: true,
4632
+ input: ["text", "image"],
4633
+ cost: {
4634
+ input: 0.1,
4635
+ output: 0.5,
4636
+ cacheRead: 0.01,
4637
+ cacheWrite: 0.125,
4638
+ },
4639
+ contextWindow: 1050000,
4640
+ maxTokens: 128000,
4641
+ },
4642
+ "gpt-6-sol": {
4643
+ id: "gpt-6-sol",
4644
+ name: "GPT-6 Sol",
4645
+ api: "openai-responses",
4646
+ provider: "cloudflare-ai-gateway",
4647
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
4648
+ reasoning: true,
4649
+ input: ["text", "image"],
4650
+ cost: {
4651
+ input: 2,
4652
+ output: 10,
4653
+ cacheRead: 0.2,
4654
+ cacheWrite: 2.5,
4655
+ },
4656
+ contextWindow: 1050000,
4657
+ maxTokens: 128000,
4658
+ },
4312
4659
  "o3": {
4313
4660
  id: "o3",
4314
4661
  name: "o3",
@@ -4668,7 +5015,7 @@ export const MODELS = {
4668
5015
  cacheWrite: 0,
4669
5016
  },
4670
5017
  contextWindow: 1310720,
4671
- maxTokens: 1310720,
5018
+ maxTokens: 1048576,
4672
5019
  },
4673
5020
  "@cf/zai-org/glm-5.3-flash": {
4674
5021
  id: "@cf/zai-org/glm-5.3-flash",
@@ -4815,6 +5162,23 @@ export const MODELS = {
4815
5162
  contextWindow: 1000000,
4816
5163
  maxTokens: 384000,
4817
5164
  },
5165
+ "accounts/fireworks/models/ember-1": {
5166
+ id: "accounts/fireworks/models/ember-1",
5167
+ name: "Ember-1",
5168
+ api: "anthropic-messages",
5169
+ provider: "fireworks",
5170
+ baseUrl: "https://api.fireworks.ai/inference",
5171
+ reasoning: true,
5172
+ input: ["text", "image"],
5173
+ cost: {
5174
+ input: 3,
5175
+ output: 15,
5176
+ cacheRead: 0.3,
5177
+ cacheWrite: 0,
5178
+ },
5179
+ contextWindow: 1048576,
5180
+ maxTokens: 131072,
5181
+ },
4818
5182
  "accounts/fireworks/models/glm-5p2": {
4819
5183
  id: "accounts/fireworks/models/glm-5p2",
4820
5184
  name: "GLM 5.2",
@@ -5409,6 +5773,25 @@ export const MODELS = {
5409
5773
  contextWindow: 1000000,
5410
5774
  maxTokens: 64000,
5411
5775
  },
5776
+ "claude-opus-5.5": {
5777
+ id: "claude-opus-5.5",
5778
+ name: "Claude Opus 5.5",
5779
+ api: "openai-completions",
5780
+ provider: "github-copilot",
5781
+ baseUrl: "https://api.individual.githubcopilot.com",
5782
+ 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" },
5783
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
5784
+ reasoning: true,
5785
+ input: ["text", "image"],
5786
+ cost: {
5787
+ input: 4,
5788
+ output: 20,
5789
+ cacheRead: 0.2,
5790
+ cacheWrite: 5,
5791
+ },
5792
+ contextWindow: 1000000,
5793
+ maxTokens: 128000,
5794
+ },
5412
5795
  "claude-sonnet-4.6": {
5413
5796
  id: "claude-sonnet-4.6",
5414
5797
  name: "Claude Sonnet 4.6",
@@ -5712,6 +6095,44 @@ export const MODELS = {
5712
6095
  contextWindow: 1050000,
5713
6096
  maxTokens: 128000,
5714
6097
  },
6098
+ "gpt-6-luna": {
6099
+ id: "gpt-6-luna",
6100
+ name: "GPT-6 Luna",
6101
+ api: "openai-completions",
6102
+ provider: "github-copilot",
6103
+ baseUrl: "https://api.individual.githubcopilot.com",
6104
+ 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" },
6105
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
6106
+ reasoning: true,
6107
+ input: ["text", "image"],
6108
+ cost: {
6109
+ input: 0.1,
6110
+ output: 0.5,
6111
+ cacheRead: 0.01,
6112
+ cacheWrite: 0.125,
6113
+ },
6114
+ contextWindow: 1050000,
6115
+ maxTokens: 128000,
6116
+ },
6117
+ "gpt-6-sol": {
6118
+ id: "gpt-6-sol",
6119
+ name: "GPT-6 Sol",
6120
+ api: "openai-completions",
6121
+ provider: "github-copilot",
6122
+ baseUrl: "https://api.individual.githubcopilot.com",
6123
+ 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" },
6124
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
6125
+ reasoning: true,
6126
+ input: ["text", "image"],
6127
+ cost: {
6128
+ input: 2,
6129
+ output: 10,
6130
+ cacheRead: 0.2,
6131
+ cacheWrite: 2.5,
6132
+ },
6133
+ contextWindow: 1050000,
6134
+ maxTokens: 128000,
6135
+ },
5715
6136
  "grok-4.5": {
5716
6137
  id: "grok-4.5",
5717
6138
  name: "Grok 4.5",
@@ -5750,6 +6171,25 @@ export const MODELS = {
5750
6171
  contextWindow: 500000,
5751
6172
  maxTokens: 128000,
5752
6173
  },
6174
+ "grok-4.7": {
6175
+ id: "grok-4.7",
6176
+ name: "Grok 4.7",
6177
+ api: "openai-completions",
6178
+ provider: "github-copilot",
6179
+ baseUrl: "https://api.individual.githubcopilot.com",
6180
+ 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" },
6181
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
6182
+ reasoning: true,
6183
+ input: ["text", "image"],
6184
+ cost: {
6185
+ input: 2,
6186
+ output: 6,
6187
+ cacheRead: 0.5,
6188
+ cacheWrite: 0,
6189
+ },
6190
+ contextWindow: 500000,
6191
+ maxTokens: 128000,
6192
+ },
5753
6193
  "kimi-k2.7-code": {
5754
6194
  id: "kimi-k2.7-code",
5755
6195
  name: "Kimi K2.7 Code",
@@ -5876,8 +6316,8 @@ export const MODELS = {
5876
6316
  cacheRead: 0,
5877
6317
  cacheWrite: 0,
5878
6318
  },
5879
- contextWindow: 131072,
5880
- maxTokens: 65536,
6319
+ contextWindow: 128000,
6320
+ maxTokens: 64000,
5881
6321
  },
5882
6322
  "gemini-2.5-flash": {
5883
6323
  id: "gemini-2.5-flash",
@@ -5982,7 +6422,7 @@ export const MODELS = {
5982
6422
  cacheWrite: 0,
5983
6423
  },
5984
6424
  contextWindow: 65536,
5985
- maxTokens: 65536,
6425
+ maxTokens: 4096,
5986
6426
  },
5987
6427
  "gemini-3.1-flash-lite-preview": {
5988
6428
  id: "gemini-3.1-flash-lite-preview",
@@ -7646,6 +8086,24 @@ export const MODELS = {
7646
8086
  contextWindow: 262144,
7647
8087
  maxTokens: 128000,
7648
8088
  },
8089
+ "tencent/Hy4-preview": {
8090
+ id: "tencent/Hy4-preview",
8091
+ name: "Hy4 preview",
8092
+ api: "openai-completions",
8093
+ provider: "huggingface",
8094
+ baseUrl: "https://router.huggingface.co/v1",
8095
+ compat: { "supportsDeveloperRole": false },
8096
+ reasoning: true,
8097
+ input: ["text"],
8098
+ cost: {
8099
+ input: 0.834,
8100
+ output: 2.501,
8101
+ cacheRead: 0,
8102
+ cacheWrite: 0,
8103
+ },
8104
+ contextWindow: 1000000,
8105
+ maxTokens: 64000,
8106
+ },
7649
8107
  "thinkingmachines/Inkling": {
7650
8108
  id: "thinkingmachines/Inkling",
7651
8109
  name: "Inkling",
@@ -8022,7 +8480,7 @@ export const MODELS = {
8022
8480
  cacheRead: 0.06,
8023
8481
  cacheWrite: 0,
8024
8482
  },
8025
- contextWindow: 1048576,
8483
+ contextWindow: 1000000,
8026
8484
  maxTokens: 512000,
8027
8485
  },
8028
8486
  },
@@ -8075,7 +8533,7 @@ export const MODELS = {
8075
8533
  cacheRead: 0.06,
8076
8534
  cacheWrite: 0,
8077
8535
  },
8078
- contextWindow: 1048576,
8536
+ contextWindow: 1000000,
8079
8537
  maxTokens: 512000,
8080
8538
  },
8081
8539
  },
@@ -8713,7 +9171,7 @@ export const MODELS = {
8713
9171
  cacheWrite: 0,
8714
9172
  },
8715
9173
  contextWindow: 1048576,
8716
- maxTokens: 131072,
9174
+ maxTokens: 1048576,
8717
9175
  },
8718
9176
  },
8719
9177
  "moonshotai-cn": {
@@ -8787,7 +9245,7 @@ export const MODELS = {
8787
9245
  cacheWrite: 0,
8788
9246
  },
8789
9247
  contextWindow: 1048576,
8790
- maxTokens: 131072,
9248
+ maxTokens: 1048576,
8791
9249
  },
8792
9250
  },
8793
9251
  "openai": {
@@ -9342,6 +9800,40 @@ export const MODELS = {
9342
9800
  contextWindow: 1050000,
9343
9801
  maxTokens: 128000,
9344
9802
  },
9803
+ "gpt-6-luna": {
9804
+ id: "gpt-6-luna",
9805
+ name: "GPT-6 Luna",
9806
+ api: "openai-responses",
9807
+ provider: "openai",
9808
+ baseUrl: "https://api.openai.com/v1",
9809
+ reasoning: true,
9810
+ input: ["text", "image"],
9811
+ cost: {
9812
+ input: 0.1,
9813
+ output: 0.5,
9814
+ cacheRead: 0.01,
9815
+ cacheWrite: 0.125,
9816
+ },
9817
+ contextWindow: 1050000,
9818
+ maxTokens: 128000,
9819
+ },
9820
+ "gpt-6-sol": {
9821
+ id: "gpt-6-sol",
9822
+ name: "GPT-6 Sol",
9823
+ api: "openai-responses",
9824
+ provider: "openai",
9825
+ baseUrl: "https://api.openai.com/v1",
9826
+ reasoning: true,
9827
+ input: ["text", "image"],
9828
+ cost: {
9829
+ input: 2,
9830
+ output: 10,
9831
+ cacheRead: 0.2,
9832
+ cacheWrite: 2.5,
9833
+ },
9834
+ contextWindow: 1050000,
9835
+ maxTokens: 128000,
9836
+ },
9345
9837
  "gpt-realtime-2.1": {
9346
9838
  id: "gpt-realtime-2.1",
9347
9839
  name: "GPT-Realtime-2.1",
@@ -9801,6 +10293,23 @@ export const MODELS = {
9801
10293
  contextWindow: 1000000,
9802
10294
  maxTokens: 128000,
9803
10295
  },
10296
+ "claude-opus-5-5": {
10297
+ id: "claude-opus-5-5",
10298
+ name: "Claude Opus 5.5",
10299
+ api: "anthropic-messages",
10300
+ provider: "opencode",
10301
+ baseUrl: "https://opencode.ai/zen",
10302
+ reasoning: true,
10303
+ input: ["text", "image"],
10304
+ cost: {
10305
+ input: 4,
10306
+ output: 20,
10307
+ cacheRead: 0.2,
10308
+ cacheWrite: 5,
10309
+ },
10310
+ contextWindow: 1000000,
10311
+ maxTokens: 128000,
10312
+ },
9804
10313
  "claude-sonnet-4": {
9805
10314
  id: "claude-sonnet-4",
9806
10315
  name: "Claude Sonnet 4",
@@ -10515,6 +11024,40 @@ export const MODELS = {
10515
11024
  contextWindow: 1050000,
10516
11025
  maxTokens: 128000,
10517
11026
  },
11027
+ "gpt-6-luna": {
11028
+ id: "gpt-6-luna",
11029
+ name: "GPT-6 Luna",
11030
+ api: "openai-responses",
11031
+ provider: "opencode",
11032
+ baseUrl: "https://opencode.ai/zen/v1",
11033
+ reasoning: true,
11034
+ input: ["text", "image"],
11035
+ cost: {
11036
+ input: 0.1,
11037
+ output: 0.5,
11038
+ cacheRead: 0.01,
11039
+ cacheWrite: 0.125,
11040
+ },
11041
+ contextWindow: 1050000,
11042
+ maxTokens: 128000,
11043
+ },
11044
+ "gpt-6-sol": {
11045
+ id: "gpt-6-sol",
11046
+ name: "GPT-6 Sol",
11047
+ api: "openai-responses",
11048
+ provider: "opencode",
11049
+ baseUrl: "https://opencode.ai/zen/v1",
11050
+ reasoning: true,
11051
+ input: ["text", "image"],
11052
+ cost: {
11053
+ input: 2,
11054
+ output: 10,
11055
+ cacheRead: 0.2,
11056
+ cacheWrite: 2.5,
11057
+ },
11058
+ contextWindow: 1050000,
11059
+ maxTokens: 128000,
11060
+ },
10518
11061
  "grok-4.5": {
10519
11062
  id: "grok-4.5",
10520
11063
  name: "Grok 4.5",
@@ -10549,16 +11092,33 @@ export const MODELS = {
10549
11092
  contextWindow: 500000,
10550
11093
  maxTokens: 500000,
10551
11094
  },
10552
- "grok-build-0.1": {
10553
- id: "grok-build-0.1",
10554
- name: "Grok Build 0.1",
11095
+ "grok-4.7": {
11096
+ id: "grok-4.7",
11097
+ name: "Grok 4.7 (30% Off)",
10555
11098
  api: "openai-responses",
10556
11099
  provider: "opencode",
10557
11100
  baseUrl: "https://opencode.ai/zen/v1",
10558
11101
  reasoning: true,
10559
11102
  input: ["text", "image"],
10560
11103
  cost: {
10561
- input: 1,
11104
+ input: 1.4,
11105
+ output: 4.2,
11106
+ cacheRead: 0.35,
11107
+ cacheWrite: 0,
11108
+ },
11109
+ contextWindow: 500000,
11110
+ maxTokens: 500000,
11111
+ },
11112
+ "grok-build-0.1": {
11113
+ id: "grok-build-0.1",
11114
+ name: "Grok Build 0.1",
11115
+ api: "openai-responses",
11116
+ provider: "opencode",
11117
+ baseUrl: "https://opencode.ai/zen/v1",
11118
+ reasoning: true,
11119
+ input: ["text", "image"],
11120
+ cost: {
11121
+ input: 1,
10562
11122
  output: 2,
10563
11123
  cacheRead: 0.2,
10564
11124
  cacheWrite: 0,
@@ -10651,9 +11211,9 @@ export const MODELS = {
10651
11211
  contextWindow: 262144,
10652
11212
  maxTokens: 32768,
10653
11213
  },
10654
- "mimo-v2.5-free": {
10655
- id: "mimo-v2.5-free",
10656
- name: "MiMo V2.5 Free",
11214
+ "mimo-v2.6-flash-free": {
11215
+ id: "mimo-v2.6-flash-free",
11216
+ name: "MiMo-V2.6-Flash Free",
10657
11217
  api: "openai-completions",
10658
11218
  provider: "opencode",
10659
11219
  baseUrl: "https://opencode.ai/zen/v1",
@@ -10872,6 +11432,23 @@ export const MODELS = {
10872
11432
  contextWindow: 1000000,
10873
11433
  maxTokens: 131072,
10874
11434
  },
11435
+ "space-bunny-free": {
11436
+ id: "space-bunny-free",
11437
+ name: "Space Bunny Free",
11438
+ api: "openai-completions",
11439
+ provider: "opencode",
11440
+ baseUrl: "https://opencode.ai/zen/v1",
11441
+ reasoning: true,
11442
+ input: ["text", "image"],
11443
+ cost: {
11444
+ input: 0,
11445
+ output: 0,
11446
+ cacheRead: 0,
11447
+ cacheWrite: 0,
11448
+ },
11449
+ contextWindow: 1048576,
11450
+ maxTokens: 524288,
11451
+ },
10875
11452
  },
10876
11453
  "opencode-go": {
10877
11454
  "deepseek-v4-flash": {
@@ -11036,6 +11613,23 @@ export const MODELS = {
11036
11613
  contextWindow: 1050000,
11037
11614
  maxTokens: 128000,
11038
11615
  },
11616
+ "gpt-6-luna": {
11617
+ id: "gpt-6-luna",
11618
+ name: "GPT-6 Luna",
11619
+ api: "openai-responses",
11620
+ provider: "opencode-go",
11621
+ baseUrl: "https://opencode.ai/zen/go/v1",
11622
+ reasoning: true,
11623
+ input: ["text", "image"],
11624
+ cost: {
11625
+ input: 0.1,
11626
+ output: 0.5,
11627
+ cacheRead: 0.01,
11628
+ cacheWrite: 0.125,
11629
+ },
11630
+ contextWindow: 1050000,
11631
+ maxTokens: 128000,
11632
+ },
11039
11633
  "grok-4.6": {
11040
11634
  id: "grok-4.6",
11041
11635
  name: "Grok 4.6",
@@ -11053,6 +11647,23 @@ export const MODELS = {
11053
11647
  contextWindow: 500000,
11054
11648
  maxTokens: 500000,
11055
11649
  },
11650
+ "grok-4.7": {
11651
+ id: "grok-4.7",
11652
+ name: "Grok 4.7",
11653
+ api: "openai-responses",
11654
+ provider: "opencode-go",
11655
+ baseUrl: "https://opencode.ai/zen/go/v1",
11656
+ reasoning: true,
11657
+ input: ["text", "image"],
11658
+ cost: {
11659
+ input: 2,
11660
+ output: 6,
11661
+ cacheRead: 0.5,
11662
+ cacheWrite: 0,
11663
+ },
11664
+ contextWindow: 500000,
11665
+ maxTokens: 500000,
11666
+ },
11056
11667
  "hy3": {
11057
11668
  id: "hy3",
11058
11669
  name: "Hy3",
@@ -11189,6 +11800,40 @@ export const MODELS = {
11189
11800
  contextWindow: 1048576,
11190
11801
  maxTokens: 128000,
11191
11802
  },
11803
+ "mimo-v2.6-flash": {
11804
+ id: "mimo-v2.6-flash",
11805
+ name: "MiMo-V2.6-Flash",
11806
+ api: "openai-completions",
11807
+ provider: "opencode-go",
11808
+ baseUrl: "https://opencode.ai/zen/go/v1",
11809
+ reasoning: true,
11810
+ input: ["text", "image"],
11811
+ cost: {
11812
+ input: 0.14,
11813
+ output: 0.28,
11814
+ cacheRead: 0.0028,
11815
+ cacheWrite: 0,
11816
+ },
11817
+ contextWindow: 1048576,
11818
+ maxTokens: 131072,
11819
+ },
11820
+ "mimo-v2.6-pro": {
11821
+ id: "mimo-v2.6-pro",
11822
+ name: "MiMo-V2.6-Pro",
11823
+ api: "openai-completions",
11824
+ provider: "opencode-go",
11825
+ baseUrl: "https://opencode.ai/zen/go/v1",
11826
+ reasoning: true,
11827
+ input: ["text", "image"],
11828
+ cost: {
11829
+ input: 0.435,
11830
+ output: 0.87,
11831
+ cacheRead: 0.003625,
11832
+ cacheWrite: 0,
11833
+ },
11834
+ contextWindow: 1048576,
11835
+ maxTokens: 131072,
11836
+ },
11192
11837
  "minimax-m2.7": {
11193
11838
  id: "minimax-m2.7",
11194
11839
  name: "MiniMax-M2.7",
@@ -11201,7 +11846,7 @@ export const MODELS = {
11201
11846
  input: 0.3,
11202
11847
  output: 1.2,
11203
11848
  cacheRead: 0.06,
11204
- cacheWrite: 0,
11849
+ cacheWrite: 0.375,
11205
11850
  },
11206
11851
  contextWindow: 204800,
11207
11852
  maxTokens: 131072,
@@ -11343,6 +11988,23 @@ export const MODELS = {
11343
11988
  contextWindow: 1000000,
11344
11989
  maxTokens: 131072,
11345
11990
  },
11991
+ "space-bunny-free": {
11992
+ id: "space-bunny-free",
11993
+ name: "Space Bunny Free",
11994
+ api: "openai-completions",
11995
+ provider: "opencode-go",
11996
+ baseUrl: "https://opencode.ai/zen/go/v1",
11997
+ reasoning: true,
11998
+ input: ["text", "image"],
11999
+ cost: {
12000
+ input: 0,
12001
+ output: 0,
12002
+ cacheRead: 0,
12003
+ cacheWrite: 0,
12004
+ },
12005
+ contextWindow: 1048576,
12006
+ maxTokens: 524288,
12007
+ },
11346
12008
  },
11347
12009
  "openrouter": {
11348
12010
  "aion-labs/aion-2.0": {
@@ -11396,6 +12058,40 @@ export const MODELS = {
11396
12058
  contextWindow: 131072,
11397
12059
  maxTokens: 32768,
11398
12060
  },
12061
+ "aion-labs/aion-3.5": {
12062
+ id: "aion-labs/aion-3.5",
12063
+ name: "AionLabs: Aion 3.5",
12064
+ api: "openai-completions",
12065
+ provider: "openrouter",
12066
+ baseUrl: "https://openrouter.ai/api/v1",
12067
+ reasoning: true,
12068
+ input: ["text"],
12069
+ cost: {
12070
+ input: 3,
12071
+ output: 6,
12072
+ cacheRead: 0.75,
12073
+ cacheWrite: 0,
12074
+ },
12075
+ contextWindow: 262144,
12076
+ maxTokens: 32768,
12077
+ },
12078
+ "aion-labs/aion-3.5-mini": {
12079
+ id: "aion-labs/aion-3.5-mini",
12080
+ name: "AionLabs: Aion 3.5 Mini",
12081
+ api: "openai-completions",
12082
+ provider: "openrouter",
12083
+ baseUrl: "https://openrouter.ai/api/v1",
12084
+ reasoning: true,
12085
+ input: ["text"],
12086
+ cost: {
12087
+ input: 0.7,
12088
+ output: 1.4,
12089
+ cacheRead: 0.18,
12090
+ cacheWrite: 0,
12091
+ },
12092
+ contextWindow: 262144,
12093
+ maxTokens: 32768,
12094
+ },
11399
12095
  "amazon/nova-2-lite-v1": {
11400
12096
  id: "amazon/nova-2-lite-v1",
11401
12097
  name: "Amazon: Nova 2 Lite",
@@ -11604,23 +12300,6 @@ export const MODELS = {
11604
12300
  contextWindow: 200000,
11605
12301
  maxTokens: 64000,
11606
12302
  },
11607
- "anthropic/claude-opus-4": {
11608
- id: "anthropic/claude-opus-4",
11609
- name: "Anthropic: Claude Opus 4",
11610
- api: "openai-completions",
11611
- provider: "openrouter",
11612
- baseUrl: "https://openrouter.ai/api/v1",
11613
- reasoning: true,
11614
- input: ["text", "image"],
11615
- cost: {
11616
- input: 15,
11617
- output: 75,
11618
- cacheRead: 1.5,
11619
- cacheWrite: 18.75,
11620
- },
11621
- contextWindow: 200000,
11622
- maxTokens: 32000,
11623
- },
11624
12303
  "anthropic/claude-opus-4.1": {
11625
12304
  id: "anthropic/claude-opus-4.1",
11626
12305
  name: "Anthropic: Claude Opus 4.1",
@@ -11814,6 +12493,40 @@ export const MODELS = {
11814
12493
  contextWindow: 1000000,
11815
12494
  maxTokens: 128000,
11816
12495
  },
12496
+ "anthropic/claude-opus-5.5": {
12497
+ id: "anthropic/claude-opus-5.5",
12498
+ name: "Anthropic: Claude Opus 5.5",
12499
+ api: "openai-completions",
12500
+ provider: "openrouter",
12501
+ baseUrl: "https://openrouter.ai/api/v1",
12502
+ reasoning: true,
12503
+ input: ["text", "image"],
12504
+ cost: {
12505
+ input: 4,
12506
+ output: 20,
12507
+ cacheRead: 0.19999999999999998,
12508
+ cacheWrite: 5,
12509
+ },
12510
+ contextWindow: 1000000,
12511
+ maxTokens: 128000,
12512
+ },
12513
+ "anthropic/claude-opus-5.5:batch": {
12514
+ id: "anthropic/claude-opus-5.5:batch",
12515
+ name: "Anthropic: Claude Opus 5.5 (batch)",
12516
+ api: "openai-completions",
12517
+ provider: "openrouter",
12518
+ baseUrl: "https://openrouter.ai/api/v1",
12519
+ reasoning: true,
12520
+ input: ["text", "image"],
12521
+ cost: {
12522
+ input: 2,
12523
+ output: 10,
12524
+ cacheRead: 0.09999999999999999,
12525
+ cacheWrite: 2.5,
12526
+ },
12527
+ contextWindow: 1000000,
12528
+ maxTokens: 128000,
12529
+ },
11817
12530
  "anthropic/claude-opus-5:batch": {
11818
12531
  id: "anthropic/claude-opus-5:batch",
11819
12532
  name: "Anthropic: Claude Opus 5 (batch)",
@@ -11845,7 +12558,7 @@ export const MODELS = {
11845
12558
  cacheRead: 0.3,
11846
12559
  cacheWrite: 3.75,
11847
12560
  },
11848
- contextWindow: 1000000,
12561
+ contextWindow: 200000,
11849
12562
  maxTokens: 64000,
11850
12563
  },
11851
12564
  "anthropic/claude-sonnet-4.5": {
@@ -12086,6 +12799,23 @@ export const MODELS = {
12086
12799
  contextWindow: 262144,
12087
12800
  maxTokens: 131072,
12088
12801
  },
12802
+ "cohere/command-a-plus": {
12803
+ id: "cohere/command-a-plus",
12804
+ name: "Cohere: Command A+",
12805
+ api: "openai-completions",
12806
+ provider: "openrouter",
12807
+ baseUrl: "https://openrouter.ai/api/v1",
12808
+ reasoning: true,
12809
+ input: ["text", "image"],
12810
+ cost: {
12811
+ input: 0.3,
12812
+ output: 1.5,
12813
+ cacheRead: 0.15,
12814
+ cacheWrite: 0,
12815
+ },
12816
+ contextWindow: 192000,
12817
+ maxTokens: 64000,
12818
+ },
12089
12819
  "cohere/command-r-08-2024": {
12090
12820
  id: "cohere/command-r-08-2024",
12091
12821
  name: "Cohere: Command R (08-2024)",
@@ -12284,9 +13014,9 @@ export const MODELS = {
12284
13014
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12285
13015
  input: ["text"],
12286
13016
  cost: {
12287
- input: 0.0364,
12288
- output: 0.0728,
12289
- cacheRead: 0.00728,
13017
+ input: 0.088606,
13018
+ output: 0.177212,
13019
+ cacheRead: 0.017721200000000003,
12290
13020
  cacheWrite: 0,
12291
13021
  },
12292
13022
  contextWindow: 1048576,
@@ -12303,33 +13033,14 @@ export const MODELS = {
12303
13033
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12304
13034
  input: ["text"],
12305
13035
  cost: {
12306
- input: 0.04,
12307
- output: 0.08,
13036
+ input: 0.03,
13037
+ output: 0.32,
12308
13038
  cacheRead: 0.016,
12309
13039
  cacheWrite: 0,
12310
13040
  },
12311
13041
  contextWindow: 1310720,
12312
13042
  maxTokens: 943718,
12313
13043
  },
12314
- "deepseek/deepseek-v4-flash-0731:batch": {
12315
- id: "deepseek/deepseek-v4-flash-0731:batch",
12316
- name: "DeepSeek: DeepSeek V4 Flash 0731 (batch)",
12317
- api: "openai-completions",
12318
- provider: "openrouter",
12319
- baseUrl: "https://openrouter.ai/api/v1",
12320
- compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
12321
- reasoning: true,
12322
- thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12323
- input: ["text"],
12324
- cost: {
12325
- input: 0.11,
12326
- output: 0.33,
12327
- cacheRead: 0.0035,
12328
- cacheWrite: 0,
12329
- },
12330
- contextWindow: 1048576,
12331
- maxTokens: 943718,
12332
- },
12333
13044
  "deepseek/deepseek-v4-flash-vision-exp": {
12334
13045
  id: "deepseek/deepseek-v4-flash-vision-exp",
12335
13046
  name: "DeepSeek: DeepSeek V4 Flash Vision Exp",
@@ -12341,28 +13052,9 @@ export const MODELS = {
12341
13052
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12342
13053
  input: ["text", "image"],
12343
13054
  cost: {
12344
- input: 0.21559999999999999,
12345
- output: 0.6468,
12346
- cacheRead: 0.00686,
12347
- cacheWrite: 0,
12348
- },
12349
- contextWindow: 1048576,
12350
- maxTokens: 262144,
12351
- },
12352
- "deepseek/deepseek-v4-flash-vision-exp:batch": {
12353
- id: "deepseek/deepseek-v4-flash-vision-exp:batch",
12354
- name: "DeepSeek: DeepSeek V4 Flash Vision Exp (batch)",
12355
- api: "openai-completions",
12356
- provider: "openrouter",
12357
- baseUrl: "https://openrouter.ai/api/v1",
12358
- compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
12359
- reasoning: true,
12360
- thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12361
- input: ["text", "image"],
12362
- cost: {
12363
- input: 0.11,
12364
- output: 0.33,
12365
- cacheRead: 0.0035,
13055
+ input: 0.22,
13056
+ output: 0.66,
13057
+ cacheRead: 0.007,
12366
13058
  cacheWrite: 0,
12367
13059
  },
12368
13060
  contextWindow: 1048576,
@@ -12379,9 +13071,9 @@ export const MODELS = {
12379
13071
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12380
13072
  input: ["text"],
12381
13073
  cost: {
12382
- input: 0.422298,
12383
- output: 0.844596,
12384
- cacheRead: 0.0351915,
13074
+ input: 0.9396,
13075
+ output: 1.8792,
13076
+ cacheRead: 0.07830000000000001,
12385
13077
  cacheWrite: 0,
12386
13078
  },
12387
13079
  contextWindow: 1048576,
@@ -12398,36 +13090,36 @@ export const MODELS = {
12398
13090
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12399
13091
  input: ["text"],
12400
13092
  cost: {
12401
- input: 0.66,
12402
- output: 1.9800000000000002,
12403
- cacheRead: 0.022,
13093
+ input: 0.46199999999999997,
13094
+ output: 1.386,
13095
+ cacheRead: 0.015399999999999999,
12404
13096
  cacheWrite: 0,
12405
13097
  },
12406
13098
  contextWindow: 1048576,
12407
13099
  maxTokens: 384000,
12408
13100
  },
12409
- "deepseek/deepseek-v4-pro-0813:batch": {
12410
- id: "deepseek/deepseek-v4-pro-0813:batch",
12411
- name: "DeepSeek: DeepSeek V4 Pro 0813 (batch)",
13101
+ "deepseek/deepseek-v4.1-flash": {
13102
+ id: "deepseek/deepseek-v4.1-flash",
13103
+ name: "DeepSeek: DeepSeek V4.1 Flash",
12412
13104
  api: "openai-completions",
12413
13105
  provider: "openrouter",
12414
13106
  baseUrl: "https://openrouter.ai/api/v1",
12415
13107
  compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
12416
13108
  reasoning: true,
12417
13109
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12418
- input: ["text"],
13110
+ input: ["text", "image"],
12419
13111
  cost: {
12420
- input: 0.66,
12421
- output: 1.9800000000000002,
12422
- cacheRead: 0.022,
13112
+ input: 0.14,
13113
+ output: 0.42,
13114
+ cacheRead: 0.004200000000000001,
12423
13115
  cacheWrite: 0,
12424
13116
  },
12425
13117
  contextWindow: 1048576,
12426
- maxTokens: 943718,
13118
+ maxTokens: 131072,
12427
13119
  },
12428
- "deepseek/deepseek-v4.1-flash": {
12429
- id: "deepseek/deepseek-v4.1-flash",
12430
- name: "DeepSeek: DeepSeek V4.1 Flash",
13120
+ "deepseek/deepseek-v4.1-flash:batch": {
13121
+ id: "deepseek/deepseek-v4.1-flash:batch",
13122
+ name: "DeepSeek: DeepSeek V4.1 Flash (batch)",
12431
13123
  api: "openai-completions",
12432
13124
  provider: "openrouter",
12433
13125
  baseUrl: "https://openrouter.ai/api/v1",
@@ -12436,13 +13128,13 @@ export const MODELS = {
12436
13128
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12437
13129
  input: ["text", "image"],
12438
13130
  cost: {
12439
- input: 0.15,
12440
- output: 0.6,
12441
- cacheRead: 0.003,
13131
+ input: 0.112,
13132
+ output: 0.33599999999999997,
13133
+ cacheRead: 0.00336,
12442
13134
  cacheWrite: 0,
12443
13135
  },
12444
13136
  contextWindow: 1048576,
12445
- maxTokens: 384000,
13137
+ maxTokens: 131072,
12446
13138
  },
12447
13139
  "dots-studio/dots-3-note-preview:free": {
12448
13140
  id: "dots-studio/dots-3-note-preview:free",
@@ -12461,22 +13153,39 @@ export const MODELS = {
12461
13153
  contextWindow: 512000,
12462
13154
  maxTokens: 460800,
12463
13155
  },
12464
- "google/gemini-2.5-flash": {
12465
- id: "google/gemini-2.5-flash",
12466
- name: "Google: Gemini 2.5 Flash",
13156
+ "fireworks/ember-1": {
13157
+ id: "fireworks/ember-1",
13158
+ name: "Fireworks: Ember-1",
12467
13159
  api: "openai-completions",
12468
13160
  provider: "openrouter",
12469
13161
  baseUrl: "https://openrouter.ai/api/v1",
12470
13162
  reasoning: true,
12471
13163
  input: ["text", "image"],
12472
13164
  cost: {
12473
- input: 0.3,
12474
- output: 2.5,
12475
- cacheRead: 0.03,
12476
- cacheWrite: 0.0833333333333333,
12477
- },
12478
- contextWindow: 1048576,
12479
- maxTokens: 65535,
13165
+ input: 3,
13166
+ output: 15,
13167
+ cacheRead: 0.3,
13168
+ cacheWrite: 0,
13169
+ },
13170
+ contextWindow: 1048576,
13171
+ maxTokens: 943718,
13172
+ },
13173
+ "google/gemini-2.5-flash": {
13174
+ id: "google/gemini-2.5-flash",
13175
+ name: "Google: Gemini 2.5 Flash",
13176
+ api: "openai-completions",
13177
+ provider: "openrouter",
13178
+ baseUrl: "https://openrouter.ai/api/v1",
13179
+ reasoning: true,
13180
+ input: ["text", "image"],
13181
+ cost: {
13182
+ input: 0.3,
13183
+ output: 2.5,
13184
+ cacheRead: 0.03,
13185
+ cacheWrite: 0.0833333333333333,
13186
+ },
13187
+ contextWindow: 1048576,
13188
+ maxTokens: 65535,
12480
13189
  },
12481
13190
  "google/gemini-2.5-flash-lite": {
12482
13191
  id: "google/gemini-2.5-flash-lite",
@@ -13138,43 +13847,9 @@ export const MODELS = {
13138
13847
  cacheRead: 0.012,
13139
13848
  cacheWrite: 0,
13140
13849
  },
13141
- contextWindow: 131072,
13142
- maxTokens: 32768,
13143
- },
13144
- "inclusionai/ling-3.0-flash-vl:free": {
13145
- id: "inclusionai/ling-3.0-flash-vl:free",
13146
- name: "inclusionAI: Ling 3.0 Flash VL (free)",
13147
- api: "openai-completions",
13148
- provider: "openrouter",
13149
- baseUrl: "https://openrouter.ai/api/v1",
13150
- reasoning: true,
13151
- input: ["text", "image"],
13152
- cost: {
13153
- input: 0,
13154
- output: 0,
13155
- cacheRead: 0,
13156
- cacheWrite: 0,
13157
- },
13158
13850
  contextWindow: 262144,
13159
13851
  maxTokens: 32768,
13160
13852
  },
13161
- "kwaipilot/kat-coder-pro-v2": {
13162
- id: "kwaipilot/kat-coder-pro-v2",
13163
- name: "Kwaipilot: KAT-Coder-Pro V2",
13164
- api: "openai-completions",
13165
- provider: "openrouter",
13166
- baseUrl: "https://openrouter.ai/api/v1",
13167
- reasoning: false,
13168
- input: ["text"],
13169
- cost: {
13170
- input: 0.3,
13171
- output: 1.2,
13172
- cacheRead: 0.06,
13173
- cacheWrite: 0,
13174
- },
13175
- contextWindow: 262144,
13176
- maxTokens: 144000,
13177
- },
13178
13853
  "kwaipilot/kat-coder-pro-v2.5": {
13179
13854
  id: "kwaipilot/kat-coder-pro-v2.5",
13180
13855
  name: "Kwaipilot: KAT-Coder-Pro V2.5",
@@ -13328,23 +14003,6 @@ export const MODELS = {
13328
14003
  contextWindow: 131072,
13329
14004
  maxTokens: 16384,
13330
14005
  },
13331
- "meta/muse-glimmer-30b:batch": {
13332
- id: "meta/muse-glimmer-30b:batch",
13333
- name: "Meta: Muse Glimmer 30B (batch)",
13334
- api: "openai-completions",
13335
- provider: "openrouter",
13336
- baseUrl: "https://openrouter.ai/api/v1",
13337
- reasoning: true,
13338
- input: ["text", "image"],
13339
- cost: {
13340
- input: 0.175,
13341
- output: 0.75,
13342
- cacheRead: 0.02,
13343
- cacheWrite: 0,
13344
- },
13345
- contextWindow: 131072,
13346
- maxTokens: 117964,
13347
- },
13348
14006
  "meta/muse-spark-1.1": {
13349
14007
  id: "meta/muse-spark-1.1",
13350
14008
  name: "Meta: Muse Spark 1.1",
@@ -13456,13 +14114,13 @@ export const MODELS = {
13456
14114
  reasoning: true,
13457
14115
  input: ["text"],
13458
14116
  cost: {
13459
- input: 0.255,
13460
- output: 1.02,
14117
+ input: 0.3,
14118
+ output: 1.2,
13461
14119
  cacheRead: 0,
13462
14120
  cacheWrite: 0,
13463
14121
  },
13464
14122
  contextWindow: 204800,
13465
- maxTokens: 131072,
14123
+ maxTokens: 176947,
13466
14124
  },
13467
14125
  "minimax/minimax-m2.1": {
13468
14126
  id: "minimax/minimax-m2.1",
@@ -13532,23 +14190,6 @@ export const MODELS = {
13532
14190
  contextWindow: 1048576,
13533
14191
  maxTokens: 512000,
13534
14192
  },
13535
- "minimax/minimax-m3:batch": {
13536
- id: "minimax/minimax-m3:batch",
13537
- name: "MiniMax: MiniMax M3 (batch)",
13538
- api: "openai-completions",
13539
- provider: "openrouter",
13540
- baseUrl: "https://openrouter.ai/api/v1",
13541
- reasoning: true,
13542
- input: ["text", "image"],
13543
- cost: {
13544
- input: 0.3,
13545
- output: 1.2,
13546
- cacheRead: 0.06,
13547
- cacheWrite: 0,
13548
- },
13549
- contextWindow: 524288,
13550
- maxTokens: 471859,
13551
- },
13552
14193
  "mistralai/codestral-2508": {
13553
14194
  id: "mistralai/codestral-2508",
13554
14195
  name: "Mistral: Codestral 2508",
@@ -13583,23 +14224,6 @@ export const MODELS = {
13583
14224
  contextWindow: 256000,
13584
14225
  maxTokens: 204800,
13585
14226
  },
13586
- "mistralai/devstral-2512": {
13587
- id: "mistralai/devstral-2512",
13588
- name: "Mistral: Devstral 2 2512",
13589
- api: "openai-completions",
13590
- provider: "openrouter",
13591
- baseUrl: "https://openrouter.ai/api/v1",
13592
- reasoning: false,
13593
- input: ["text"],
13594
- cost: {
13595
- input: 0.39999999999999997,
13596
- output: 2,
13597
- cacheRead: 0.04,
13598
- cacheWrite: 0,
13599
- },
13600
- contextWindow: 262144,
13601
- maxTokens: 209715,
13602
- },
13603
14227
  "mistralai/ministral-14b-2512": {
13604
14228
  id: "mistralai/ministral-14b-2512",
13605
14229
  name: "Mistral: Ministral 3 14B 2512",
@@ -14034,8 +14658,8 @@ export const MODELS = {
14034
14658
  reasoning: true,
14035
14659
  input: ["text", "image"],
14036
14660
  cost: {
14037
- input: 0.7062,
14038
- output: 3.21,
14661
+ input: 0.6562,
14662
+ output: 3.3000000000000003,
14039
14663
  cacheRead: 0.18,
14040
14664
  cacheWrite: 0,
14041
14665
  },
@@ -14051,9 +14675,9 @@ export const MODELS = {
14051
14675
  reasoning: true,
14052
14676
  input: ["text", "image"],
14053
14677
  cost: {
14054
- input: 1.7,
14055
- output: 8.5,
14056
- cacheRead: 0.16999999999999998,
14678
+ input: 3,
14679
+ output: 15,
14680
+ cacheRead: 0.3,
14057
14681
  cacheWrite: 0,
14058
14682
  },
14059
14683
  contextWindow: 1048576,
@@ -14068,13 +14692,13 @@ export const MODELS = {
14068
14692
  reasoning: true,
14069
14693
  input: ["text", "image"],
14070
14694
  cost: {
14071
- input: 3,
14072
- output: 15,
14073
- cacheRead: 0.3,
14695
+ input: 2.2800000000000002,
14696
+ output: 11.399999999999999,
14697
+ cacheRead: 0.228,
14074
14698
  cacheWrite: 0,
14075
14699
  },
14076
14700
  contextWindow: 1048576,
14077
- maxTokens: 943718,
14701
+ maxTokens: 16384,
14078
14702
  },
14079
14703
  "nex-agi/nex-n2.5-mini:free": {
14080
14704
  id: "nex-agi/nex-n2.5-mini:free",
@@ -14119,9 +14743,9 @@ export const MODELS = {
14119
14743
  reasoning: true,
14120
14744
  input: ["text"],
14121
14745
  cost: {
14122
- input: 0.06,
14123
- output: 0.24,
14124
- cacheRead: 0,
14746
+ input: 0.049999999999999996,
14747
+ output: 0.19999999999999998,
14748
+ cacheRead: 0.03,
14125
14749
  cacheWrite: 0,
14126
14750
  },
14127
14751
  contextWindow: 262144,
@@ -14221,13 +14845,13 @@ export const MODELS = {
14221
14845
  reasoning: true,
14222
14846
  input: ["text"],
14223
14847
  cost: {
14224
- input: 0.07,
14848
+ input: 0.08,
14225
14849
  output: 0.19999999999999998,
14226
14850
  cacheRead: 0.04,
14227
14851
  cacheWrite: 0,
14228
14852
  },
14229
14853
  contextWindow: 262144,
14230
- maxTokens: 235929,
14854
+ maxTokens: 131072,
14231
14855
  },
14232
14856
  "nvidia/nemotron-3.5-lightning:free": {
14233
14857
  id: "nvidia/nemotron-3.5-lightning:free",
@@ -15353,6 +15977,142 @@ export const MODELS = {
15353
15977
  contextWindow: 1050000,
15354
15978
  maxTokens: 128000,
15355
15979
  },
15980
+ "openai/gpt-6-luna": {
15981
+ id: "openai/gpt-6-luna",
15982
+ name: "OpenAI: GPT-6 Luna",
15983
+ api: "openai-completions",
15984
+ provider: "openrouter",
15985
+ baseUrl: "https://openrouter.ai/api/v1",
15986
+ reasoning: true,
15987
+ input: ["text", "image"],
15988
+ cost: {
15989
+ input: 0.09999999999999999,
15990
+ output: 0.5,
15991
+ cacheRead: 0.01,
15992
+ cacheWrite: 0.125,
15993
+ },
15994
+ contextWindow: 1050000,
15995
+ maxTokens: 128000,
15996
+ },
15997
+ "openai/gpt-6-luna-pro": {
15998
+ id: "openai/gpt-6-luna-pro",
15999
+ name: "OpenAI: GPT-6 Luna Pro",
16000
+ api: "openai-completions",
16001
+ provider: "openrouter",
16002
+ baseUrl: "https://openrouter.ai/api/v1",
16003
+ reasoning: true,
16004
+ input: ["text", "image"],
16005
+ cost: {
16006
+ input: 0.09999999999999999,
16007
+ output: 0.5,
16008
+ cacheRead: 0.01,
16009
+ cacheWrite: 0.125,
16010
+ },
16011
+ contextWindow: 1050000,
16012
+ maxTokens: 128000,
16013
+ },
16014
+ "openai/gpt-6-luna-pro:batch": {
16015
+ id: "openai/gpt-6-luna-pro:batch",
16016
+ name: "OpenAI: GPT-6 Luna Pro (batch)",
16017
+ api: "openai-completions",
16018
+ provider: "openrouter",
16019
+ baseUrl: "https://openrouter.ai/api/v1",
16020
+ reasoning: true,
16021
+ input: ["text", "image"],
16022
+ cost: {
16023
+ input: 0.049999999999999996,
16024
+ output: 0.25,
16025
+ cacheRead: 0.005,
16026
+ cacheWrite: 0.0625,
16027
+ },
16028
+ contextWindow: 1050000,
16029
+ maxTokens: 128000,
16030
+ },
16031
+ "openai/gpt-6-luna:batch": {
16032
+ id: "openai/gpt-6-luna:batch",
16033
+ name: "OpenAI: GPT-6 Luna (batch)",
16034
+ api: "openai-completions",
16035
+ provider: "openrouter",
16036
+ baseUrl: "https://openrouter.ai/api/v1",
16037
+ reasoning: true,
16038
+ input: ["text", "image"],
16039
+ cost: {
16040
+ input: 0.049999999999999996,
16041
+ output: 0.25,
16042
+ cacheRead: 0.005,
16043
+ cacheWrite: 0.0625,
16044
+ },
16045
+ contextWindow: 1050000,
16046
+ maxTokens: 128000,
16047
+ },
16048
+ "openai/gpt-6-sol": {
16049
+ id: "openai/gpt-6-sol",
16050
+ name: "OpenAI: GPT-6 Sol",
16051
+ api: "openai-completions",
16052
+ provider: "openrouter",
16053
+ baseUrl: "https://openrouter.ai/api/v1",
16054
+ reasoning: true,
16055
+ input: ["text", "image"],
16056
+ cost: {
16057
+ input: 2,
16058
+ output: 10,
16059
+ cacheRead: 0.19999999999999998,
16060
+ cacheWrite: 2.5,
16061
+ },
16062
+ contextWindow: 1050000,
16063
+ maxTokens: 128000,
16064
+ },
16065
+ "openai/gpt-6-sol-pro": {
16066
+ id: "openai/gpt-6-sol-pro",
16067
+ name: "OpenAI: GPT-6 Sol Pro",
16068
+ api: "openai-completions",
16069
+ provider: "openrouter",
16070
+ baseUrl: "https://openrouter.ai/api/v1",
16071
+ reasoning: true,
16072
+ input: ["text", "image"],
16073
+ cost: {
16074
+ input: 2,
16075
+ output: 10,
16076
+ cacheRead: 0.19999999999999998,
16077
+ cacheWrite: 2.5,
16078
+ },
16079
+ contextWindow: 1050000,
16080
+ maxTokens: 128000,
16081
+ },
16082
+ "openai/gpt-6-sol-pro:batch": {
16083
+ id: "openai/gpt-6-sol-pro:batch",
16084
+ name: "OpenAI: GPT-6 Sol Pro (batch)",
16085
+ api: "openai-completions",
16086
+ provider: "openrouter",
16087
+ baseUrl: "https://openrouter.ai/api/v1",
16088
+ reasoning: true,
16089
+ input: ["text", "image"],
16090
+ cost: {
16091
+ input: 1,
16092
+ output: 5,
16093
+ cacheRead: 0.09999999999999999,
16094
+ cacheWrite: 1.25,
16095
+ },
16096
+ contextWindow: 1050000,
16097
+ maxTokens: 128000,
16098
+ },
16099
+ "openai/gpt-6-sol:batch": {
16100
+ id: "openai/gpt-6-sol:batch",
16101
+ name: "OpenAI: GPT-6 Sol (batch)",
16102
+ api: "openai-completions",
16103
+ provider: "openrouter",
16104
+ baseUrl: "https://openrouter.ai/api/v1",
16105
+ reasoning: true,
16106
+ input: ["text", "image"],
16107
+ cost: {
16108
+ input: 1,
16109
+ output: 5,
16110
+ cacheRead: 0.09999999999999999,
16111
+ cacheWrite: 1.25,
16112
+ },
16113
+ contextWindow: 1050000,
16114
+ maxTokens: 128000,
16115
+ },
15356
16116
  "openai/gpt-audio": {
15357
16117
  id: "openai/gpt-audio",
15358
16118
  name: "OpenAI: GPT Audio",
@@ -15430,8 +16190,8 @@ export const MODELS = {
15430
16190
  reasoning: true,
15431
16191
  input: ["text"],
15432
16192
  cost: {
15433
- input: 0.15,
15434
- output: 0.6,
16193
+ input: 0.0296,
16194
+ output: 0.136,
15435
16195
  cacheRead: 0,
15436
16196
  cacheWrite: 0,
15437
16197
  },
@@ -15447,9 +16207,26 @@ export const MODELS = {
15447
16207
  reasoning: true,
15448
16208
  input: ["text"],
15449
16209
  cost: {
15450
- input: 0.03,
15451
- output: 0.13,
15452
- cacheRead: 0.03,
16210
+ input: 0.018,
16211
+ output: 0.09,
16212
+ cacheRead: 0,
16213
+ cacheWrite: 0,
16214
+ },
16215
+ contextWindow: 131072,
16216
+ maxTokens: 32768,
16217
+ },
16218
+ "openai/gpt-oss-20b:batch": {
16219
+ id: "openai/gpt-oss-20b:batch",
16220
+ name: "OpenAI: gpt-oss-20b (batch)",
16221
+ api: "openai-completions",
16222
+ provider: "openrouter",
16223
+ baseUrl: "https://openrouter.ai/api/v1",
16224
+ reasoning: true,
16225
+ input: ["text"],
16226
+ cost: {
16227
+ input: 0.024,
16228
+ output: 0.112,
16229
+ cacheRead: 0,
15453
16230
  cacheWrite: 0,
15454
16231
  },
15455
16232
  contextWindow: 131072,
@@ -15940,13 +16717,13 @@ export const MODELS = {
15940
16717
  reasoning: false,
15941
16718
  input: ["text"],
15942
16719
  cost: {
15943
- input: 0.04815,
15944
- output: 0.19305,
16720
+ input: 0.09999999999999999,
16721
+ output: 0.3,
15945
16722
  cacheRead: 0,
15946
16723
  cacheWrite: 0,
15947
16724
  },
15948
16725
  contextWindow: 262144,
15949
- maxTokens: 32000,
16726
+ maxTokens: 235929,
15950
16727
  },
15951
16728
  "qwen/qwen3-30b-a3b-thinking-2507": {
15952
16729
  id: "qwen/qwen3-30b-a3b-thinking-2507",
@@ -16127,13 +16904,13 @@ export const MODELS = {
16127
16904
  reasoning: false,
16128
16905
  input: ["text"],
16129
16906
  cost: {
16130
- input: 0.09,
16907
+ input: 0.09999999999999999,
16131
16908
  output: 1.1,
16132
- cacheRead: 0,
16909
+ cacheRead: 0.07,
16133
16910
  cacheWrite: 0,
16134
16911
  },
16135
16912
  contextWindow: 262144,
16136
- maxTokens: 16384,
16913
+ maxTokens: 235929,
16137
16914
  },
16138
16915
  "qwen/qwen3-next-80b-a3b-thinking": {
16139
16916
  id: "qwen/qwen3-next-80b-a3b-thinking",
@@ -16150,7 +16927,7 @@ export const MODELS = {
16150
16927
  cacheWrite: 0,
16151
16928
  },
16152
16929
  contextWindow: 262144,
16153
- maxTokens: 32768,
16930
+ maxTokens: 235929,
16154
16931
  },
16155
16932
  "qwen/qwen3-vl-235b-a22b-instruct": {
16156
16933
  id: "qwen/qwen3-vl-235b-a22b-instruct",
@@ -16195,8 +16972,8 @@ export const MODELS = {
16195
16972
  reasoning: false,
16196
16973
  input: ["text", "image"],
16197
16974
  cost: {
16198
- input: 0.19999999999999998,
16199
- output: 0.7,
16975
+ input: 0.13,
16976
+ output: 0.52,
16200
16977
  cacheRead: 0,
16201
16978
  cacheWrite: 0,
16202
16979
  },
@@ -16356,23 +17133,6 @@ export const MODELS = {
16356
17133
  contextWindow: 262144,
16357
17134
  maxTokens: 32768,
16358
17135
  },
16359
- "qwen/qwen3.5-9b:batch": {
16360
- id: "qwen/qwen3.5-9b:batch",
16361
- name: "Qwen: Qwen3.5-9B (batch)",
16362
- api: "openai-completions",
16363
- provider: "openrouter",
16364
- baseUrl: "https://openrouter.ai/api/v1",
16365
- reasoning: true,
16366
- input: ["text", "image"],
16367
- cost: {
16368
- input: 0.16999999999999998,
16369
- output: 0.25,
16370
- cacheRead: 0,
16371
- cacheWrite: 0,
16372
- },
16373
- contextWindow: 262144,
16374
- maxTokens: 235929,
16375
- },
16376
17136
  "qwen/qwen3.5-flash-02-23": {
16377
17137
  id: "qwen/qwen3.5-flash-02-23",
16378
17138
  name: "Qwen: Qwen3.5-Flash",
@@ -16433,13 +17193,13 @@ export const MODELS = {
16433
17193
  reasoning: true,
16434
17194
  input: ["text", "image"],
16435
17195
  cost: {
16436
- input: 0.3,
16437
- output: 2,
16438
- cacheRead: 0.03,
17196
+ input: 0.32,
17197
+ output: 2.7,
17198
+ cacheRead: 0.15,
16439
17199
  cacheWrite: 0,
16440
17200
  },
16441
17201
  contextWindow: 262144,
16442
- maxTokens: 65536,
17202
+ maxTokens: 262140,
16443
17203
  },
16444
17204
  "qwen/qwen3.6-35b-a3b": {
16445
17205
  id: "qwen/qwen3.6-35b-a3b",
@@ -16450,8 +17210,8 @@ export const MODELS = {
16450
17210
  reasoning: true,
16451
17211
  input: ["text", "image"],
16452
17212
  cost: {
16453
- input: 0.09999999999999999,
16454
- output: 0.8999999999999999,
17213
+ input: 0.15,
17214
+ output: 1,
16455
17215
  cacheRead: 0.049999999999999996,
16456
17216
  cacheWrite: 0,
16457
17217
  },
@@ -16577,23 +17337,6 @@ export const MODELS = {
16577
17337
  contextWindow: 1048576,
16578
17338
  maxTokens: 131072,
16579
17339
  },
16580
- "qwen/qwen3.8-2.4t-a95b:batch": {
16581
- id: "qwen/qwen3.8-2.4t-a95b:batch",
16582
- name: "Qwen: Qwen3.8 2.4T A95B (batch)",
16583
- api: "openai-completions",
16584
- provider: "openrouter",
16585
- baseUrl: "https://openrouter.ai/api/v1",
16586
- reasoning: true,
16587
- input: ["text"],
16588
- cost: {
16589
- input: 2,
16590
- output: 6,
16591
- cacheRead: 0.25,
16592
- cacheWrite: 0,
16593
- },
16594
- contextWindow: 1010000,
16595
- maxTokens: 909000,
16596
- },
16597
17340
  "qwen/qwen3.8-27b": {
16598
17341
  id: "qwen/qwen3.8-27b",
16599
17342
  name: "Qwen: Qwen3.8 27B",
@@ -16662,6 +17405,40 @@ export const MODELS = {
16662
17405
  contextWindow: 1000000,
16663
17406
  maxTokens: 131072,
16664
17407
  },
17408
+ "qwen/qwen3.8-max-prime": {
17409
+ id: "qwen/qwen3.8-max-prime",
17410
+ name: "Qwen: Qwen3.8 Max Prime",
17411
+ api: "openai-completions",
17412
+ provider: "openrouter",
17413
+ baseUrl: "https://openrouter.ai/api/v1",
17414
+ reasoning: true,
17415
+ input: ["text", "image"],
17416
+ cost: {
17417
+ input: 4,
17418
+ output: 12,
17419
+ cacheRead: 0.5,
17420
+ cacheWrite: 0,
17421
+ },
17422
+ contextWindow: 1000000,
17423
+ maxTokens: 131072,
17424
+ },
17425
+ "qwen/qwen3.8-omni-flash": {
17426
+ id: "qwen/qwen3.8-omni-flash",
17427
+ name: "Qwen: Qwen3.8 Omni Flash",
17428
+ api: "openai-completions",
17429
+ provider: "openrouter",
17430
+ baseUrl: "https://openrouter.ai/api/v1",
17431
+ reasoning: true,
17432
+ input: ["text", "image"],
17433
+ cost: {
17434
+ input: 0.15,
17435
+ output: 0.47,
17436
+ cacheRead: 0.016,
17437
+ cacheWrite: 0,
17438
+ },
17439
+ contextWindow: 1000000,
17440
+ maxTokens: 131072,
17441
+ },
16665
17442
  "rekaai/reka-edge": {
16666
17443
  id: "rekaai/reka-edge",
16667
17444
  name: "Reka Edge",
@@ -16781,6 +17558,23 @@ export const MODELS = {
16781
17558
  contextWindow: 131072,
16782
17559
  maxTokens: 16384,
16783
17560
  },
17561
+ "stealth/space-bunny-alpha": {
17562
+ id: "stealth/space-bunny-alpha",
17563
+ name: "Space Bunny Alpha",
17564
+ api: "openai-completions",
17565
+ provider: "openrouter",
17566
+ baseUrl: "https://openrouter.ai/api/v1",
17567
+ reasoning: true,
17568
+ input: ["text", "image"],
17569
+ cost: {
17570
+ input: 0,
17571
+ output: 0,
17572
+ cacheRead: 0,
17573
+ cacheWrite: 0,
17574
+ },
17575
+ contextWindow: 1000000,
17576
+ maxTokens: 524288,
17577
+ },
16784
17578
  "stepfun/step-3.5-flash": {
16785
17579
  id: "stepfun/step-3.5-flash",
16786
17580
  name: "StepFun: Step 3.5 Flash",
@@ -16900,23 +17694,6 @@ export const MODELS = {
16900
17694
  contextWindow: 1048576,
16901
17695
  maxTokens: 262144,
16902
17696
  },
16903
- "thinkingmachines/inkling:batch": {
16904
- id: "thinkingmachines/inkling:batch",
16905
- name: "Thinking Machines: Inkling (batch)",
16906
- api: "openai-completions",
16907
- provider: "openrouter",
16908
- baseUrl: "https://openrouter.ai/api/v1",
16909
- reasoning: true,
16910
- input: ["text", "image"],
16911
- cost: {
16912
- input: 1,
16913
- output: 4.05,
16914
- cacheRead: 0.16999999999999998,
16915
- cacheWrite: 0,
16916
- },
16917
- contextWindow: 524288,
16918
- maxTokens: 471859,
16919
- },
16920
17697
  "thinkingmachines/inkling:free": {
16921
17698
  id: "thinkingmachines/inkling:free",
16922
17699
  name: "Thinking Machines: Inkling (free)",
@@ -16951,6 +17728,23 @@ export const MODELS = {
16951
17728
  contextWindow: 262144,
16952
17729
  maxTokens: 131072,
16953
17730
  },
17731
+ "upstage/solar-mini4": {
17732
+ id: "upstage/solar-mini4",
17733
+ name: "Upstage: Solar Mini 4",
17734
+ api: "openai-completions",
17735
+ provider: "openrouter",
17736
+ baseUrl: "https://openrouter.ai/api/v1",
17737
+ reasoning: true,
17738
+ input: ["text"],
17739
+ cost: {
17740
+ input: 0.049999999999999996,
17741
+ output: 0.19999999999999998,
17742
+ cacheRead: 0.005,
17743
+ cacheWrite: 0,
17744
+ },
17745
+ contextWindow: 524288,
17746
+ maxTokens: 131072,
17747
+ },
16954
17748
  "upstage/solar-pro-3": {
16955
17749
  id: "upstage/solar-pro-3",
16956
17750
  name: "Upstage: Solar Pro 3",
@@ -17070,6 +17864,23 @@ export const MODELS = {
17070
17864
  contextWindow: 500000,
17071
17865
  maxTokens: 450000,
17072
17866
  },
17867
+ "x-ai/grok-4.7": {
17868
+ id: "x-ai/grok-4.7",
17869
+ name: "SpaceXAI: Grok 4.7",
17870
+ api: "openai-completions",
17871
+ provider: "openrouter",
17872
+ baseUrl: "https://openrouter.ai/api/v1",
17873
+ reasoning: true,
17874
+ input: ["text", "image"],
17875
+ cost: {
17876
+ input: 1.5999999999999999,
17877
+ output: 4.8,
17878
+ cacheRead: 0.39999999999999997,
17879
+ cacheWrite: 0,
17880
+ },
17881
+ contextWindow: 500000,
17882
+ maxTokens: 450000,
17883
+ },
17073
17884
  "x-ai/grok-build-0.1": {
17074
17885
  id: "x-ai/grok-build-0.1",
17075
17886
  name: "SpaceXAI: Grok Build 0.1",
@@ -17121,6 +17932,57 @@ export const MODELS = {
17121
17932
  contextWindow: 1050000,
17122
17933
  maxTokens: 131072,
17123
17934
  },
17935
+ "xiaomi/mimo-v2.6-flash": {
17936
+ id: "xiaomi/mimo-v2.6-flash",
17937
+ name: "Xiaomi: MiMo-V2.6-Flash",
17938
+ api: "openai-completions",
17939
+ provider: "openrouter",
17940
+ baseUrl: "https://openrouter.ai/api/v1",
17941
+ reasoning: true,
17942
+ input: ["text", "image"],
17943
+ cost: {
17944
+ input: 0.14,
17945
+ output: 0.28,
17946
+ cacheRead: 0.0028,
17947
+ cacheWrite: 0,
17948
+ },
17949
+ contextWindow: 1048576,
17950
+ maxTokens: 131072,
17951
+ },
17952
+ "xiaomi/mimo-v2.6-pro": {
17953
+ id: "xiaomi/mimo-v2.6-pro",
17954
+ name: "Xiaomi: MiMo-V2.6-Pro",
17955
+ api: "openai-completions",
17956
+ provider: "openrouter",
17957
+ baseUrl: "https://openrouter.ai/api/v1",
17958
+ reasoning: true,
17959
+ input: ["text", "image"],
17960
+ cost: {
17961
+ input: 0.435,
17962
+ output: 0.87,
17963
+ cacheRead: 0.0036,
17964
+ cacheWrite: 0,
17965
+ },
17966
+ contextWindow: 1048576,
17967
+ maxTokens: 131072,
17968
+ },
17969
+ "xiaomi/mimo-v2.6-pro-ultraspeed": {
17970
+ id: "xiaomi/mimo-v2.6-pro-ultraspeed",
17971
+ name: "Xiaomi: MiMo-V2.6-Pro-UltraSpeed",
17972
+ api: "openai-completions",
17973
+ provider: "openrouter",
17974
+ baseUrl: "https://openrouter.ai/api/v1",
17975
+ reasoning: true,
17976
+ input: ["text", "image"],
17977
+ cost: {
17978
+ input: 4.35,
17979
+ output: 8.7,
17980
+ cacheRead: 0.036,
17981
+ cacheWrite: 0,
17982
+ },
17983
+ contextWindow: 1048576,
17984
+ maxTokens: 131072,
17985
+ },
17124
17986
  "z-ai/glm-4.5": {
17125
17987
  id: "z-ai/glm-4.5",
17126
17988
  name: "Z.ai: GLM 4.5",
@@ -17308,23 +18170,6 @@ export const MODELS = {
17308
18170
  contextWindow: 1048576,
17309
18171
  maxTokens: 131072,
17310
18172
  },
17311
- "z-ai/glm-5.2:batch": {
17312
- id: "z-ai/glm-5.2:batch",
17313
- name: "Z.ai: GLM 5.2 (batch)",
17314
- api: "openai-completions",
17315
- provider: "openrouter",
17316
- baseUrl: "https://openrouter.ai/api/v1",
17317
- reasoning: true,
17318
- input: ["text"],
17319
- cost: {
17320
- input: 0.7,
17321
- output: 2.2,
17322
- cacheRead: 0.07,
17323
- cacheWrite: 0,
17324
- },
17325
- contextWindow: 1048576,
17326
- maxTokens: 943718,
17327
- },
17328
18173
  "z-ai/glm-5.3": {
17329
18174
  id: "z-ai/glm-5.3",
17330
18175
  name: "Z.ai: GLM 5.3",
@@ -17334,9 +18179,9 @@ export const MODELS = {
17334
18179
  reasoning: true,
17335
18180
  input: ["text"],
17336
18181
  cost: {
17337
- input: 0.896,
17338
- output: 2.816,
17339
- cacheRead: 0.16640000000000002,
18182
+ input: 0.84,
18183
+ output: 2.64,
18184
+ cacheRead: 0.156,
17340
18185
  cacheWrite: 0,
17341
18186
  },
17342
18187
  contextWindow: 1310720,
@@ -17351,13 +18196,13 @@ export const MODELS = {
17351
18196
  reasoning: true,
17352
18197
  input: ["text", "image"],
17353
18198
  cost: {
17354
- input: 0.09,
17355
- output: 0.3,
17356
- cacheRead: 0.018,
18199
+ input: 0.15,
18200
+ output: 0.5,
18201
+ cacheRead: 0.049999999999999996,
17357
18202
  cacheWrite: 0,
17358
18203
  },
17359
18204
  contextWindow: 1310720,
17360
- maxTokens: 131072,
18205
+ maxTokens: 943718,
17361
18206
  },
17362
18207
  "z-ai/glm-5.3-flash:batch": {
17363
18208
  id: "z-ai/glm-5.3-flash:batch",
@@ -17368,13 +18213,13 @@ export const MODELS = {
17368
18213
  reasoning: true,
17369
18214
  input: ["text", "image"],
17370
18215
  cost: {
17371
- input: 0.075,
17372
- output: 0.25,
17373
- cacheRead: 0.015,
18216
+ input: 0.06,
18217
+ output: 0.19999999999999998,
18218
+ cacheRead: 0.012,
17374
18219
  cacheWrite: 0,
17375
18220
  },
17376
18221
  contextWindow: 1048576,
17377
- maxTokens: 943718,
18222
+ maxTokens: 131072,
17378
18223
  },
17379
18224
  "z-ai/glm-5.3-flashx": {
17380
18225
  id: "z-ai/glm-5.3-flashx",
@@ -17387,12 +18232,29 @@ export const MODELS = {
17387
18232
  cost: {
17388
18233
  input: 0.37,
17389
18234
  output: 1.25,
17390
- cacheRead: 0.075,
18235
+ cacheRead: 0.09,
17391
18236
  cacheWrite: 0,
17392
18237
  },
17393
18238
  contextWindow: 1048576,
17394
18239
  maxTokens: 131072,
17395
18240
  },
18241
+ "z-ai/glm-5.3-prime": {
18242
+ id: "z-ai/glm-5.3-prime",
18243
+ name: "Z.ai: GLM 5.3 Prime",
18244
+ api: "openai-completions",
18245
+ provider: "openrouter",
18246
+ baseUrl: "https://openrouter.ai/api/v1",
18247
+ reasoning: true,
18248
+ input: ["text"],
18249
+ cost: {
18250
+ input: 2.8,
18251
+ output: 8.8,
18252
+ cacheRead: 0.56,
18253
+ cacheWrite: 0,
18254
+ },
18255
+ contextWindow: 1000000,
18256
+ maxTokens: 131072,
18257
+ },
17396
18258
  "z-ai/glm-5.3:batch": {
17397
18259
  id: "z-ai/glm-5.3:batch",
17398
18260
  name: "Z.ai: GLM 5.3 (batch)",
@@ -17402,13 +18264,13 @@ export const MODELS = {
17402
18264
  reasoning: true,
17403
18265
  input: ["text"],
17404
18266
  cost: {
17405
- input: 0.7,
17406
- output: 2.2,
17407
- cacheRead: 0.13,
18267
+ input: 0.44999999999999996,
18268
+ output: 2,
18269
+ cacheRead: 0.09999999999999999,
17408
18270
  cacheWrite: 0,
17409
18271
  },
17410
18272
  contextWindow: 1048576,
17411
- maxTokens: 943718,
18273
+ maxTokens: 131072,
17412
18274
  },
17413
18275
  "z-ai/glm-5v-turbo": {
17414
18276
  id: "z-ai/glm-5v-turbo",
@@ -17471,10 +18333,10 @@ export const MODELS = {
17471
18333
  reasoning: true,
17472
18334
  input: ["text", "image"],
17473
18335
  cost: {
17474
- input: 5,
17475
- output: 25,
17476
- cacheRead: 0.5,
17477
- cacheWrite: 6.25,
18336
+ input: 4,
18337
+ output: 20,
18338
+ cacheRead: 0.19999999999999998,
18339
+ cacheWrite: 5,
17478
18340
  },
17479
18341
  contextWindow: 1000000,
17480
18342
  maxTokens: 128000,
@@ -17505,9 +18367,9 @@ export const MODELS = {
17505
18367
  reasoning: true,
17506
18368
  input: ["text", "image"],
17507
18369
  cost: {
17508
- input: 0.13,
17509
- output: 0.52,
17510
- cacheRead: 0.0026000000000000003,
18370
+ input: 0.04,
18371
+ output: 1,
18372
+ cacheRead: 0.01,
17511
18373
  cacheWrite: 0,
17512
18374
  },
17513
18375
  contextWindow: 1048576,
@@ -17522,13 +18384,13 @@ export const MODELS = {
17522
18384
  reasoning: true,
17523
18385
  input: ["text"],
17524
18386
  cost: {
17525
- input: 0.56496,
17526
- output: 1.69488,
17527
- cacheRead: 0.017976000000000002,
18387
+ input: 0.39,
18388
+ output: 2.9000000000000004,
18389
+ cacheRead: 0.25,
17528
18390
  cacheWrite: 0,
17529
18391
  },
17530
18392
  contextWindow: 1048576,
17531
- maxTokens: 393216,
18393
+ maxTokens: 943718,
17532
18394
  },
17533
18395
  "~deepseek/deepseek-v4-flash-latest": {
17534
18396
  id: "~deepseek/deepseek-v4-flash-latest",
@@ -17541,8 +18403,8 @@ export const MODELS = {
17541
18403
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
17542
18404
  input: ["text"],
17543
18405
  cost: {
17544
- input: 0.04,
17545
- output: 0.08,
18406
+ input: 0.03,
18407
+ output: 0.32,
17546
18408
  cacheRead: 0.016,
17547
18409
  cacheWrite: 0,
17548
18410
  },
@@ -17592,9 +18454,9 @@ export const MODELS = {
17592
18454
  reasoning: true,
17593
18455
  input: ["text", "image"],
17594
18456
  cost: {
17595
- input: 1.7,
17596
- output: 8.5,
17597
- cacheRead: 0.16999999999999998,
18457
+ input: 1.4,
18458
+ output: 10.75,
18459
+ cacheRead: 0.3,
17598
18460
  cacheWrite: 0,
17599
18461
  },
17600
18462
  contextWindow: 1048576,
@@ -17626,10 +18488,10 @@ export const MODELS = {
17626
18488
  reasoning: true,
17627
18489
  input: ["text", "image"],
17628
18490
  cost: {
17629
- input: 0.19999999999999998,
17630
- output: 1.2,
17631
- cacheRead: 0.02,
17632
- cacheWrite: 0.25,
18491
+ input: 0.09999999999999999,
18492
+ output: 0.5,
18493
+ cacheRead: 0.01,
18494
+ cacheWrite: 0.125,
17633
18495
  },
17634
18496
  contextWindow: 1050000,
17635
18497
  maxTokens: 128000,
@@ -17694,9 +18556,9 @@ export const MODELS = {
17694
18556
  reasoning: true,
17695
18557
  input: ["text", "image"],
17696
18558
  cost: {
17697
- input: 2,
17698
- output: 6,
17699
- cacheRead: 0.5,
18559
+ input: 1.5999999999999999,
18560
+ output: 4.8,
18561
+ cacheRead: 0.39999999999999997,
17700
18562
  cacheWrite: 0,
17701
18563
  },
17702
18564
  contextWindow: 500000,
@@ -17711,13 +18573,13 @@ export const MODELS = {
17711
18573
  reasoning: true,
17712
18574
  input: ["text", "image"],
17713
18575
  cost: {
17714
- input: 0.075,
17715
- output: 0.25,
17716
- cacheRead: 0.015,
18576
+ input: 0.045,
18577
+ output: 0.14,
18578
+ cacheRead: 0.01,
17717
18579
  cacheWrite: 0,
17718
18580
  },
17719
18581
  contextWindow: 1310720,
17720
- maxTokens: 943718,
18582
+ maxTokens: 128000,
17721
18583
  },
17722
18584
  "~z-ai/glm-latest": {
17723
18585
  id: "~z-ai/glm-latest",
@@ -17728,9 +18590,9 @@ export const MODELS = {
17728
18590
  reasoning: true,
17729
18591
  input: ["text"],
17730
18592
  cost: {
17731
- input: 0.8442,
17732
- output: 2.6532,
17733
- cacheRead: 0.15678,
18593
+ input: 0.5625,
18594
+ output: 2.5,
18595
+ cacheRead: 0.125,
17734
18596
  cacheWrite: 0,
17735
18597
  },
17736
18598
  contextWindow: 1310720,
@@ -17754,7 +18616,7 @@ export const MODELS = {
17754
18616
  cacheRead: 0.06,
17755
18617
  cacheWrite: 0,
17756
18618
  },
17757
- contextWindow: 202752,
18619
+ contextWindow: 196608,
17758
18620
  maxTokens: 131072,
17759
18621
  },
17760
18622
  "MiniMaxAI/MiniMax-M3": {
@@ -17866,7 +18728,7 @@ export const MODELS = {
17866
18728
  cacheRead: 0.03,
17867
18729
  cacheWrite: 0,
17868
18730
  },
17869
- contextWindow: 1000000,
18731
+ contextWindow: 1048576,
17870
18732
  maxTokens: 384000,
17871
18733
  },
17872
18734
  "deepseek-ai/DeepSeek-V4-Pro": {
@@ -18112,7 +18974,7 @@ export const MODELS = {
18112
18974
  cacheRead: 0.26,
18113
18975
  cacheWrite: 0,
18114
18976
  },
18115
- contextWindow: 512000,
18977
+ contextWindow: 1048575,
18116
18978
  maxTokens: 164000,
18117
18979
  },
18118
18980
  "zai-org/GLM-5.3": {
@@ -18665,6 +19527,23 @@ export const MODELS = {
18665
19527
  contextWindow: 991000,
18666
19528
  maxTokens: 128000,
18667
19529
  },
19530
+ "alibaba/qwen3.8-max-prime": {
19531
+ id: "alibaba/qwen3.8-max-prime",
19532
+ name: "Qwen 3.8 Max Prime",
19533
+ api: "anthropic-messages",
19534
+ provider: "vercel-ai-gateway",
19535
+ baseUrl: "https://ai-gateway.vercel.sh",
19536
+ reasoning: true,
19537
+ input: ["text", "image"],
19538
+ cost: {
19539
+ input: 4,
19540
+ output: 12,
19541
+ cacheRead: 0.5,
19542
+ cacheWrite: 0,
19543
+ },
19544
+ contextWindow: 1000000,
19545
+ maxTokens: 131072,
19546
+ },
18668
19547
  "alibaba/qwen3.8-omni-flash": {
18669
19548
  id: "alibaba/qwen3.8-omni-flash",
18670
19549
  name: "Qwen 3.8 Omni Flash",
@@ -18835,7 +19714,7 @@ export const MODELS = {
18835
19714
  cacheWrite: 18.75,
18836
19715
  },
18837
19716
  contextWindow: 200000,
18838
- maxTokens: 8192,
19717
+ maxTokens: 32000,
18839
19718
  },
18840
19719
  "anthropic/claude-opus-4.5": {
18841
19720
  id: "anthropic/claude-opus-4.5",
@@ -18960,6 +19839,40 @@ export const MODELS = {
18960
19839
  contextWindow: 1000000,
18961
19840
  maxTokens: 128000,
18962
19841
  },
19842
+ "anthropic/claude-opus-5.5": {
19843
+ id: "anthropic/claude-opus-5.5",
19844
+ name: "Claude Opus 5.5",
19845
+ api: "anthropic-messages",
19846
+ provider: "vercel-ai-gateway",
19847
+ baseUrl: "https://ai-gateway.vercel.sh",
19848
+ reasoning: true,
19849
+ input: ["text", "image"],
19850
+ cost: {
19851
+ input: 4,
19852
+ output: 20,
19853
+ cacheRead: 0.19999999999999998,
19854
+ cacheWrite: 5,
19855
+ },
19856
+ contextWindow: 1000000,
19857
+ maxTokens: 128000,
19858
+ },
19859
+ "anthropic/claude-opus-5.5-fast": {
19860
+ id: "anthropic/claude-opus-5.5-fast",
19861
+ name: "Claude Opus 5.5 (Fast)",
19862
+ api: "anthropic-messages",
19863
+ provider: "vercel-ai-gateway",
19864
+ baseUrl: "https://ai-gateway.vercel.sh",
19865
+ reasoning: true,
19866
+ input: ["text", "image"],
19867
+ cost: {
19868
+ input: 8,
19869
+ output: 40,
19870
+ cacheRead: 0.39999999999999997,
19871
+ cacheWrite: 10,
19872
+ },
19873
+ contextWindow: 1000000,
19874
+ maxTokens: 128000,
19875
+ },
18963
19876
  "anthropic/claude-sonnet-4": {
18964
19877
  id: "anthropic/claude-sonnet-4",
18965
19878
  name: "Claude Sonnet 4",
@@ -18975,7 +19888,7 @@ export const MODELS = {
18975
19888
  cacheWrite: 3.75,
18976
19889
  },
18977
19890
  contextWindow: 1000000,
18978
- maxTokens: 8192,
19891
+ maxTokens: 64000,
18979
19892
  },
18980
19893
  "anthropic/claude-sonnet-4.5": {
18981
19894
  id: "anthropic/claude-sonnet-4.5",
@@ -19294,7 +20207,7 @@ export const MODELS = {
19294
20207
  cost: {
19295
20208
  input: 0.3,
19296
20209
  output: 1.2,
19297
- cacheRead: 0.03,
20210
+ cacheRead: 0.007,
19298
20211
  cacheWrite: 0,
19299
20212
  },
19300
20213
  contextWindow: 1048576,
@@ -19315,7 +20228,7 @@ export const MODELS = {
19315
20228
  cacheWrite: 0,
19316
20229
  },
19317
20230
  contextWindow: 1000000,
19318
- maxTokens: 65536,
20231
+ maxTokens: 65535,
19319
20232
  },
19320
20233
  "google/gemini-2.5-flash-lite": {
19321
20234
  id: "google/gemini-2.5-flash-lite",
@@ -19332,7 +20245,7 @@ export const MODELS = {
19332
20245
  cacheWrite: 0,
19333
20246
  },
19334
20247
  contextWindow: 1048576,
19335
- maxTokens: 65536,
20248
+ maxTokens: 65535,
19336
20249
  },
19337
20250
  "google/gemini-2.5-pro": {
19338
20251
  id: "google/gemini-2.5-pro",
@@ -19349,7 +20262,7 @@ export const MODELS = {
19349
20262
  cacheWrite: 0,
19350
20263
  },
19351
20264
  contextWindow: 1048576,
19352
- maxTokens: 65536,
20265
+ maxTokens: 65535,
19353
20266
  },
19354
20267
  "google/gemini-3-flash": {
19355
20268
  id: "google/gemini-3-flash",
@@ -19468,7 +20381,7 @@ export const MODELS = {
19468
20381
  cacheWrite: 0,
19469
20382
  },
19470
20383
  contextWindow: 1000000,
19471
- maxTokens: 65536,
20384
+ maxTokens: 65535,
19472
20385
  },
19473
20386
  "google/gemini-3.8-flash": {
19474
20387
  id: "google/gemini-3.8-flash",
@@ -19485,7 +20398,7 @@ export const MODELS = {
19485
20398
  cacheWrite: 0,
19486
20399
  },
19487
20400
  contextWindow: 1000000,
19488
- maxTokens: 65536,
20401
+ maxTokens: 65535,
19489
20402
  },
19490
20403
  "google/gemma-4-26b-a4b-it": {
19491
20404
  id: "google/gemma-4-26b-a4b-it",
@@ -19666,26 +20579,9 @@ export const MODELS = {
19666
20579
  reasoning: true,
19667
20580
  input: ["text", "image"],
19668
20581
  cost: {
19669
- input: 0,
19670
- output: 0,
19671
- cacheRead: 0,
19672
- cacheWrite: 0,
19673
- },
19674
- contextWindow: 256000,
19675
- maxTokens: 32000,
19676
- },
19677
- "inclusionai/ling-3.0-flash-vl-free": {
19678
- id: "inclusionai/ling-3.0-flash-vl-free",
19679
- name: "Ling 3.0 Flash VL (Free)",
19680
- api: "anthropic-messages",
19681
- provider: "vercel-ai-gateway",
19682
- baseUrl: "https://ai-gateway.vercel.sh",
19683
- reasoning: true,
19684
- input: ["text", "image"],
19685
- cost: {
19686
- input: 0,
19687
- output: 0,
19688
- cacheRead: 0,
20582
+ input: 0.075,
20583
+ output: 0.22,
20584
+ cacheRead: 0.015,
19689
20585
  cacheWrite: 0,
19690
20586
  },
19691
20587
  contextWindow: 256000,
@@ -21219,6 +22115,74 @@ export const MODELS = {
21219
22115
  contextWindow: 1050000,
21220
22116
  maxTokens: 128000,
21221
22117
  },
22118
+ "openai/gpt-6-luna": {
22119
+ id: "openai/gpt-6-luna",
22120
+ name: "GPT-6 Luna",
22121
+ api: "anthropic-messages",
22122
+ provider: "vercel-ai-gateway",
22123
+ baseUrl: "https://ai-gateway.vercel.sh",
22124
+ reasoning: true,
22125
+ input: ["text", "image"],
22126
+ cost: {
22127
+ input: 0.09999999999999999,
22128
+ output: 0.5,
22129
+ cacheRead: 0.01,
22130
+ cacheWrite: 0.125,
22131
+ },
22132
+ contextWindow: 1050000,
22133
+ maxTokens: 128000,
22134
+ },
22135
+ "openai/gpt-6-luna-fast": {
22136
+ id: "openai/gpt-6-luna-fast",
22137
+ name: "GPT-6 Luna (Fast)",
22138
+ api: "anthropic-messages",
22139
+ provider: "vercel-ai-gateway",
22140
+ baseUrl: "https://ai-gateway.vercel.sh",
22141
+ reasoning: true,
22142
+ input: ["text", "image"],
22143
+ cost: {
22144
+ input: 0.19999999999999998,
22145
+ output: 1,
22146
+ cacheRead: 0.02,
22147
+ cacheWrite: 0.25,
22148
+ },
22149
+ contextWindow: 1050000,
22150
+ maxTokens: 128000,
22151
+ },
22152
+ "openai/gpt-6-sol": {
22153
+ id: "openai/gpt-6-sol",
22154
+ name: "GPT-6 Sol",
22155
+ api: "anthropic-messages",
22156
+ provider: "vercel-ai-gateway",
22157
+ baseUrl: "https://ai-gateway.vercel.sh",
22158
+ reasoning: true,
22159
+ input: ["text", "image"],
22160
+ cost: {
22161
+ input: 2,
22162
+ output: 10,
22163
+ cacheRead: 0.19999999999999998,
22164
+ cacheWrite: 2.5,
22165
+ },
22166
+ contextWindow: 1050000,
22167
+ maxTokens: 128000,
22168
+ },
22169
+ "openai/gpt-6-sol-fast": {
22170
+ id: "openai/gpt-6-sol-fast",
22171
+ name: "GPT-6 Sol (Fast)",
22172
+ api: "anthropic-messages",
22173
+ provider: "vercel-ai-gateway",
22174
+ baseUrl: "https://ai-gateway.vercel.sh",
22175
+ reasoning: true,
22176
+ input: ["text", "image"],
22177
+ cost: {
22178
+ input: 4,
22179
+ output: 20,
22180
+ cacheRead: 0.39999999999999997,
22181
+ cacheWrite: 5,
22182
+ },
22183
+ contextWindow: 1050000,
22184
+ maxTokens: 128000,
22185
+ },
21222
22186
  "openai/gpt-oss-120b": {
21223
22187
  id: "openai/gpt-oss-120b",
21224
22188
  name: "GPT OSS 120B",
@@ -21230,7 +22194,7 @@ export const MODELS = {
21230
22194
  cost: {
21231
22195
  input: 0.09999999999999999,
21232
22196
  output: 0.5,
21233
- cacheRead: 0,
22197
+ cacheRead: 0.09999999999999999,
21234
22198
  cacheWrite: 0,
21235
22199
  },
21236
22200
  contextWindow: 131072,
@@ -21729,6 +22693,23 @@ export const MODELS = {
21729
22693
  contextWindow: 500000,
21730
22694
  maxTokens: 500000,
21731
22695
  },
22696
+ "spacexai/grok-4.7": {
22697
+ id: "spacexai/grok-4.7",
22698
+ name: "Grok 4.7",
22699
+ api: "anthropic-messages",
22700
+ provider: "vercel-ai-gateway",
22701
+ baseUrl: "https://ai-gateway.vercel.sh",
22702
+ reasoning: true,
22703
+ input: ["text", "image"],
22704
+ cost: {
22705
+ input: 1.2,
22706
+ output: 3.5999999999999996,
22707
+ cacheRead: 0.3,
22708
+ cacheWrite: 0,
22709
+ },
22710
+ contextWindow: 500000,
22711
+ maxTokens: 500000,
22712
+ },
21732
22713
  "spacexai/grok-build-0.1": {
21733
22714
  id: "spacexai/grok-build-0.1",
21734
22715
  name: "Grok Build 0.1",
@@ -21882,6 +22863,57 @@ export const MODELS = {
21882
22863
  contextWindow: 1050000,
21883
22864
  maxTokens: 131000,
21884
22865
  },
22866
+ "xiaomi/mimo-v2.6-flash": {
22867
+ id: "xiaomi/mimo-v2.6-flash",
22868
+ name: "MiMo V2.6 Flash",
22869
+ api: "anthropic-messages",
22870
+ provider: "vercel-ai-gateway",
22871
+ baseUrl: "https://ai-gateway.vercel.sh",
22872
+ reasoning: true,
22873
+ input: ["text", "image"],
22874
+ cost: {
22875
+ input: 0.14,
22876
+ output: 0.28,
22877
+ cacheRead: 0.0028,
22878
+ cacheWrite: 0,
22879
+ },
22880
+ contextWindow: 1048576,
22881
+ maxTokens: 131072,
22882
+ },
22883
+ "xiaomi/mimo-v2.6-pro": {
22884
+ id: "xiaomi/mimo-v2.6-pro",
22885
+ name: "MiMo V2.6 Pro",
22886
+ api: "anthropic-messages",
22887
+ provider: "vercel-ai-gateway",
22888
+ baseUrl: "https://ai-gateway.vercel.sh",
22889
+ reasoning: true,
22890
+ input: ["text", "image"],
22891
+ cost: {
22892
+ input: 0.435,
22893
+ output: 0.87,
22894
+ cacheRead: 0.0036,
22895
+ cacheWrite: 0,
22896
+ },
22897
+ contextWindow: 1048576,
22898
+ maxTokens: 131072,
22899
+ },
22900
+ "xiaomi/mimo-v2.6-pro-ultraspeed": {
22901
+ id: "xiaomi/mimo-v2.6-pro-ultraspeed",
22902
+ name: "MiMo V2.6 Pro UltraSpeed",
22903
+ api: "anthropic-messages",
22904
+ provider: "vercel-ai-gateway",
22905
+ baseUrl: "https://ai-gateway.vercel.sh",
22906
+ reasoning: true,
22907
+ input: ["text", "image"],
22908
+ cost: {
22909
+ input: 4.35,
22910
+ output: 8.7,
22911
+ cacheRead: 0.036,
22912
+ cacheWrite: 0,
22913
+ },
22914
+ contextWindow: 1048576,
22915
+ maxTokens: 131072,
22916
+ },
21885
22917
  "zai/glm-4.5": {
21886
22918
  id: "zai/glm-4.5",
21887
22919
  name: "GLM 4.5",
@@ -22258,6 +23290,23 @@ export const MODELS = {
22258
23290
  contextWindow: 500000,
22259
23291
  maxTokens: 500000,
22260
23292
  },
23293
+ "grok-4.7": {
23294
+ id: "grok-4.7",
23295
+ name: "Grok 4.7",
23296
+ api: "openai-completions",
23297
+ provider: "xai",
23298
+ baseUrl: "https://api.x.ai/v1",
23299
+ reasoning: true,
23300
+ input: ["text", "image"],
23301
+ cost: {
23302
+ input: 2,
23303
+ output: 6,
23304
+ cacheRead: 0.5,
23305
+ cacheWrite: 0,
23306
+ },
23307
+ contextWindow: 500000,
23308
+ maxTokens: 500000,
23309
+ },
22261
23310
  "grok-build-0.1": {
22262
23311
  id: "grok-build-0.1",
22263
23312
  name: "Grok Build 0.1",
@@ -22345,6 +23394,57 @@ export const MODELS = {
22345
23394
  contextWindow: 1048576,
22346
23395
  maxTokens: 131072,
22347
23396
  },
23397
+ "mimo-v2.6-flash": {
23398
+ id: "mimo-v2.6-flash",
23399
+ name: "MiMo-V2.6-Flash",
23400
+ api: "anthropic-messages",
23401
+ provider: "xiaomi",
23402
+ baseUrl: "https://api.xiaomimimo.com/anthropic",
23403
+ reasoning: true,
23404
+ input: ["text", "image"],
23405
+ cost: {
23406
+ input: 0.14,
23407
+ output: 0.28,
23408
+ cacheRead: 0.0028,
23409
+ cacheWrite: 0,
23410
+ },
23411
+ contextWindow: 1048576,
23412
+ maxTokens: 131072,
23413
+ },
23414
+ "mimo-v2.6-pro": {
23415
+ id: "mimo-v2.6-pro",
23416
+ name: "MiMo-V2.6-Pro",
23417
+ api: "anthropic-messages",
23418
+ provider: "xiaomi",
23419
+ baseUrl: "https://api.xiaomimimo.com/anthropic",
23420
+ reasoning: true,
23421
+ input: ["text", "image"],
23422
+ cost: {
23423
+ input: 0.435,
23424
+ output: 0.87,
23425
+ cacheRead: 0.0036,
23426
+ cacheWrite: 0,
23427
+ },
23428
+ contextWindow: 1048576,
23429
+ maxTokens: 131072,
23430
+ },
23431
+ "mimo-v2.6-pro-ultraspeed": {
23432
+ id: "mimo-v2.6-pro-ultraspeed",
23433
+ name: "MiMo-V2.6-Pro-UltraSpeed",
23434
+ api: "anthropic-messages",
23435
+ provider: "xiaomi",
23436
+ baseUrl: "https://api.xiaomimimo.com/anthropic",
23437
+ reasoning: true,
23438
+ input: ["text", "image"],
23439
+ cost: {
23440
+ input: 4.35,
23441
+ output: 8.7,
23442
+ cacheRead: 0.036,
23443
+ cacheWrite: 0,
23444
+ },
23445
+ contextWindow: 1048576,
23446
+ maxTokens: 131072,
23447
+ },
22348
23448
  },
22349
23449
  "xiaomi-token-plan-ams": {
22350
23450
  "mimo-v2.5": {
@@ -22398,6 +23498,57 @@ export const MODELS = {
22398
23498
  contextWindow: 1048576,
22399
23499
  maxTokens: 131072,
22400
23500
  },
23501
+ "mimo-v2.6-flash": {
23502
+ id: "mimo-v2.6-flash",
23503
+ name: "MiMo-V2.6-Flash",
23504
+ api: "anthropic-messages",
23505
+ provider: "xiaomi-token-plan-ams",
23506
+ baseUrl: "https://token-plan-ams.xiaomimimo.com/anthropic",
23507
+ reasoning: true,
23508
+ input: ["text", "image"],
23509
+ cost: {
23510
+ input: 0.14,
23511
+ output: 0.28,
23512
+ cacheRead: 0.0028,
23513
+ cacheWrite: 0,
23514
+ },
23515
+ contextWindow: 1048576,
23516
+ maxTokens: 131072,
23517
+ },
23518
+ "mimo-v2.6-pro": {
23519
+ id: "mimo-v2.6-pro",
23520
+ name: "MiMo-V2.6-Pro",
23521
+ api: "anthropic-messages",
23522
+ provider: "xiaomi-token-plan-ams",
23523
+ baseUrl: "https://token-plan-ams.xiaomimimo.com/anthropic",
23524
+ reasoning: true,
23525
+ input: ["text", "image"],
23526
+ cost: {
23527
+ input: 0.435,
23528
+ output: 0.87,
23529
+ cacheRead: 0.0036,
23530
+ cacheWrite: 0,
23531
+ },
23532
+ contextWindow: 1048576,
23533
+ maxTokens: 131072,
23534
+ },
23535
+ "mimo-v2.6-pro-ultraspeed": {
23536
+ id: "mimo-v2.6-pro-ultraspeed",
23537
+ name: "MiMo-V2.6-Pro-UltraSpeed",
23538
+ api: "anthropic-messages",
23539
+ provider: "xiaomi-token-plan-ams",
23540
+ baseUrl: "https://token-plan-ams.xiaomimimo.com/anthropic",
23541
+ reasoning: true,
23542
+ input: ["text", "image"],
23543
+ cost: {
23544
+ input: 4.35,
23545
+ output: 8.7,
23546
+ cacheRead: 0.036,
23547
+ cacheWrite: 0,
23548
+ },
23549
+ contextWindow: 1048576,
23550
+ maxTokens: 131072,
23551
+ },
22401
23552
  },
22402
23553
  "xiaomi-token-plan-cn": {
22403
23554
  "mimo-v2.5": {
@@ -22451,6 +23602,57 @@ export const MODELS = {
22451
23602
  contextWindow: 1048576,
22452
23603
  maxTokens: 131072,
22453
23604
  },
23605
+ "mimo-v2.6-flash": {
23606
+ id: "mimo-v2.6-flash",
23607
+ name: "MiMo-V2.6-Flash",
23608
+ api: "anthropic-messages",
23609
+ provider: "xiaomi-token-plan-cn",
23610
+ baseUrl: "https://token-plan-cn.xiaomimimo.com/anthropic",
23611
+ reasoning: true,
23612
+ input: ["text", "image"],
23613
+ cost: {
23614
+ input: 0.14,
23615
+ output: 0.28,
23616
+ cacheRead: 0.0028,
23617
+ cacheWrite: 0,
23618
+ },
23619
+ contextWindow: 1048576,
23620
+ maxTokens: 131072,
23621
+ },
23622
+ "mimo-v2.6-pro": {
23623
+ id: "mimo-v2.6-pro",
23624
+ name: "MiMo-V2.6-Pro",
23625
+ api: "anthropic-messages",
23626
+ provider: "xiaomi-token-plan-cn",
23627
+ baseUrl: "https://token-plan-cn.xiaomimimo.com/anthropic",
23628
+ reasoning: true,
23629
+ input: ["text", "image"],
23630
+ cost: {
23631
+ input: 0.435,
23632
+ output: 0.87,
23633
+ cacheRead: 0.0036,
23634
+ cacheWrite: 0,
23635
+ },
23636
+ contextWindow: 1048576,
23637
+ maxTokens: 131072,
23638
+ },
23639
+ "mimo-v2.6-pro-ultraspeed": {
23640
+ id: "mimo-v2.6-pro-ultraspeed",
23641
+ name: "MiMo-V2.6-Pro-UltraSpeed",
23642
+ api: "anthropic-messages",
23643
+ provider: "xiaomi-token-plan-cn",
23644
+ baseUrl: "https://token-plan-cn.xiaomimimo.com/anthropic",
23645
+ reasoning: true,
23646
+ input: ["text", "image"],
23647
+ cost: {
23648
+ input: 4.35,
23649
+ output: 8.7,
23650
+ cacheRead: 0.036,
23651
+ cacheWrite: 0,
23652
+ },
23653
+ contextWindow: 1048576,
23654
+ maxTokens: 131072,
23655
+ },
22454
23656
  },
22455
23657
  "xiaomi-token-plan-sgp": {
22456
23658
  "mimo-v2.5": {
@@ -22504,6 +23706,57 @@ export const MODELS = {
22504
23706
  contextWindow: 1048576,
22505
23707
  maxTokens: 131072,
22506
23708
  },
23709
+ "mimo-v2.6-flash": {
23710
+ id: "mimo-v2.6-flash",
23711
+ name: "MiMo-V2.6-Flash",
23712
+ api: "anthropic-messages",
23713
+ provider: "xiaomi-token-plan-sgp",
23714
+ baseUrl: "https://token-plan-sgp.xiaomimimo.com/anthropic",
23715
+ reasoning: true,
23716
+ input: ["text", "image"],
23717
+ cost: {
23718
+ input: 0.14,
23719
+ output: 0.28,
23720
+ cacheRead: 0.0028,
23721
+ cacheWrite: 0,
23722
+ },
23723
+ contextWindow: 1048576,
23724
+ maxTokens: 131072,
23725
+ },
23726
+ "mimo-v2.6-pro": {
23727
+ id: "mimo-v2.6-pro",
23728
+ name: "MiMo-V2.6-Pro",
23729
+ api: "anthropic-messages",
23730
+ provider: "xiaomi-token-plan-sgp",
23731
+ baseUrl: "https://token-plan-sgp.xiaomimimo.com/anthropic",
23732
+ reasoning: true,
23733
+ input: ["text", "image"],
23734
+ cost: {
23735
+ input: 0.435,
23736
+ output: 0.87,
23737
+ cacheRead: 0.0036,
23738
+ cacheWrite: 0,
23739
+ },
23740
+ contextWindow: 1048576,
23741
+ maxTokens: 131072,
23742
+ },
23743
+ "mimo-v2.6-pro-ultraspeed": {
23744
+ id: "mimo-v2.6-pro-ultraspeed",
23745
+ name: "MiMo-V2.6-Pro-UltraSpeed",
23746
+ api: "anthropic-messages",
23747
+ provider: "xiaomi-token-plan-sgp",
23748
+ baseUrl: "https://token-plan-sgp.xiaomimimo.com/anthropic",
23749
+ reasoning: true,
23750
+ input: ["text", "image"],
23751
+ cost: {
23752
+ input: 4.35,
23753
+ output: 8.7,
23754
+ cacheRead: 0.036,
23755
+ cacheWrite: 0,
23756
+ },
23757
+ contextWindow: 1048576,
23758
+ maxTokens: 131072,
23759
+ },
22507
23760
  },
22508
23761
  "zai": {
22509
23762
  "glm-4.7": {