@elyracode/ai 0.9.35 → 0.9.37

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.
@@ -13,11 +13,11 @@ export const MODELS = {
13
13
  cost: {
14
14
  input: 0.33,
15
15
  output: 2.75,
16
- cacheRead: 0,
17
- cacheWrite: 0,
16
+ cacheRead: 0.0825,
17
+ cacheWrite: 0.33,
18
18
  },
19
- contextWindow: 128000,
20
- maxTokens: 4096,
19
+ contextWindow: 1000000,
20
+ maxTokens: 65535,
21
21
  },
22
22
  "amazon.nova-lite-v1:0": {
23
23
  id: "amazon.nova-lite-v1:0",
@@ -31,10 +31,10 @@ export const MODELS = {
31
31
  input: 0.06,
32
32
  output: 0.24,
33
33
  cacheRead: 0.015,
34
- cacheWrite: 0,
34
+ cacheWrite: 0.06,
35
35
  },
36
36
  contextWindow: 300000,
37
- maxTokens: 8192,
37
+ maxTokens: 10000,
38
38
  },
39
39
  "amazon.nova-micro-v1:0": {
40
40
  id: "amazon.nova-micro-v1:0",
@@ -48,10 +48,10 @@ export const MODELS = {
48
48
  input: 0.035,
49
49
  output: 0.14,
50
50
  cacheRead: 0.00875,
51
- cacheWrite: 0,
51
+ cacheWrite: 0.035,
52
52
  },
53
53
  contextWindow: 128000,
54
- maxTokens: 8192,
54
+ maxTokens: 10000,
55
55
  },
56
56
  "amazon.nova-pro-v1:0": {
57
57
  id: "amazon.nova-pro-v1:0",
@@ -65,10 +65,10 @@ export const MODELS = {
65
65
  input: 0.8,
66
66
  output: 3.2,
67
67
  cacheRead: 0.2,
68
- cacheWrite: 0,
68
+ cacheWrite: 0.8,
69
69
  },
70
70
  contextWindow: 300000,
71
- maxTokens: 8192,
71
+ maxTokens: 10000,
72
72
  },
73
73
  "anthropic.claude-fable-5": {
74
74
  id: "anthropic.claude-fable-5",
@@ -291,6 +291,57 @@ export const MODELS = {
291
291
  contextWindow: 1000000,
292
292
  maxTokens: 128000,
293
293
  },
294
+ "apac.amazon.nova-lite-v1:0": {
295
+ id: "apac.amazon.nova-lite-v1:0",
296
+ name: "Nova Lite (APAC)",
297
+ api: "bedrock-converse-stream",
298
+ provider: "amazon-bedrock",
299
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
300
+ reasoning: false,
301
+ input: ["text", "image"],
302
+ cost: {
303
+ input: 0.063,
304
+ output: 0.252,
305
+ cacheRead: 0.01575,
306
+ cacheWrite: 0.063,
307
+ },
308
+ contextWindow: 300000,
309
+ maxTokens: 10000,
310
+ },
311
+ "apac.amazon.nova-micro-v1:0": {
312
+ id: "apac.amazon.nova-micro-v1:0",
313
+ name: "Nova Micro (APAC)",
314
+ api: "bedrock-converse-stream",
315
+ provider: "amazon-bedrock",
316
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
317
+ reasoning: false,
318
+ input: ["text"],
319
+ cost: {
320
+ input: 0.037,
321
+ output: 0.148,
322
+ cacheRead: 0.00925,
323
+ cacheWrite: 0.037,
324
+ },
325
+ contextWindow: 128000,
326
+ maxTokens: 10000,
327
+ },
328
+ "apac.amazon.nova-pro-v1:0": {
329
+ id: "apac.amazon.nova-pro-v1:0",
330
+ name: "Nova Pro (APAC)",
331
+ api: "bedrock-converse-stream",
332
+ provider: "amazon-bedrock",
333
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
334
+ reasoning: false,
335
+ input: ["text", "image"],
336
+ cost: {
337
+ input: 0.84,
338
+ output: 3.36,
339
+ cacheRead: 0.21,
340
+ cacheWrite: 0.84,
341
+ },
342
+ contextWindow: 300000,
343
+ maxTokens: 10000,
344
+ },
294
345
  "au.anthropic.claude-haiku-4-5-20251001-v1:0": {
295
346
  id: "au.anthropic.claude-haiku-4-5-20251001-v1:0",
296
347
  name: "Claude Haiku 4.5 (AU)",
@@ -328,6 +379,25 @@ export const MODELS = {
328
379
  contextWindow: 1000000,
329
380
  maxTokens: 128000,
330
381
  },
382
+ "au.anthropic.claude-opus-4-7": {
383
+ id: "au.anthropic.claude-opus-4-7",
384
+ name: "Claude Opus 4.7 (AU)",
385
+ api: "bedrock-converse-stream",
386
+ provider: "amazon-bedrock",
387
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
388
+ reasoning: true,
389
+ thinkingType: "adaptive",
390
+ thinkingLevelMap: { "xhigh": "xhigh" },
391
+ input: ["text", "image"],
392
+ cost: {
393
+ input: 5.5,
394
+ output: 27.5,
395
+ cacheRead: 0.55,
396
+ cacheWrite: 6.875,
397
+ },
398
+ contextWindow: 1000000,
399
+ maxTokens: 128000,
400
+ },
331
401
  "au.anthropic.claude-opus-4-8": {
332
402
  id: "au.anthropic.claude-opus-4-8",
333
403
  name: "Claude Opus 4.8 (AU)",
@@ -419,6 +489,23 @@ export const MODELS = {
419
489
  contextWindow: 1000000,
420
490
  maxTokens: 128000,
421
491
  },
492
+ "ca.amazon.nova-lite-v1:0": {
493
+ id: "ca.amazon.nova-lite-v1:0",
494
+ name: "Nova Lite (CA)",
495
+ api: "bedrock-converse-stream",
496
+ provider: "amazon-bedrock",
497
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
498
+ reasoning: false,
499
+ input: ["text", "image"],
500
+ cost: {
501
+ input: 0.064,
502
+ output: 0.256,
503
+ cacheRead: 0.016,
504
+ cacheWrite: 0.064,
505
+ },
506
+ contextWindow: 300000,
507
+ maxTokens: 10000,
508
+ },
422
509
  "deepseek.r1-v1:0": {
423
510
  id: "deepseek.r1-v1:0",
424
511
  name: "DeepSeek-R1",
@@ -470,6 +557,74 @@ export const MODELS = {
470
557
  contextWindow: 163840,
471
558
  maxTokens: 81920,
472
559
  },
560
+ "eu.amazon.nova-2-lite-v1:0": {
561
+ id: "eu.amazon.nova-2-lite-v1:0",
562
+ name: "Nova 2 Lite (EU)",
563
+ api: "bedrock-converse-stream",
564
+ provider: "amazon-bedrock",
565
+ baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
566
+ reasoning: true,
567
+ input: ["text", "image"],
568
+ cost: {
569
+ input: 0.374,
570
+ output: 3.157,
571
+ cacheRead: 0.0935,
572
+ cacheWrite: 0.374,
573
+ },
574
+ contextWindow: 1000000,
575
+ maxTokens: 65535,
576
+ },
577
+ "eu.amazon.nova-lite-v1:0": {
578
+ id: "eu.amazon.nova-lite-v1:0",
579
+ name: "Nova Lite (EU)",
580
+ api: "bedrock-converse-stream",
581
+ provider: "amazon-bedrock",
582
+ baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
583
+ reasoning: false,
584
+ input: ["text", "image"],
585
+ cost: {
586
+ input: 0.069,
587
+ output: 0.276,
588
+ cacheRead: 0.01725,
589
+ cacheWrite: 0.069,
590
+ },
591
+ contextWindow: 300000,
592
+ maxTokens: 10000,
593
+ },
594
+ "eu.amazon.nova-micro-v1:0": {
595
+ id: "eu.amazon.nova-micro-v1:0",
596
+ name: "Nova Micro (EU)",
597
+ api: "bedrock-converse-stream",
598
+ provider: "amazon-bedrock",
599
+ baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
600
+ reasoning: false,
601
+ input: ["text"],
602
+ cost: {
603
+ input: 0.04,
604
+ output: 0.16,
605
+ cacheRead: 0.01,
606
+ cacheWrite: 0.04,
607
+ },
608
+ contextWindow: 128000,
609
+ maxTokens: 10000,
610
+ },
611
+ "eu.amazon.nova-pro-v1:0": {
612
+ id: "eu.amazon.nova-pro-v1:0",
613
+ name: "Nova Pro (EU)",
614
+ api: "bedrock-converse-stream",
615
+ provider: "amazon-bedrock",
616
+ baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
617
+ reasoning: false,
618
+ input: ["text", "image"],
619
+ cost: {
620
+ input: 0.92,
621
+ output: 3.68,
622
+ cacheRead: 0.23,
623
+ cacheWrite: 0.92,
624
+ },
625
+ contextWindow: 300000,
626
+ maxTokens: 10000,
627
+ },
473
628
  "eu.anthropic.claude-fable-5": {
474
629
  id: "eu.anthropic.claude-fable-5",
475
630
  name: "Claude Fable 5 (EU)",
@@ -654,6 +809,40 @@ export const MODELS = {
654
809
  contextWindow: 1000000,
655
810
  maxTokens: 128000,
656
811
  },
812
+ "eu.mistral.pixtral-large-2502-v1:0": {
813
+ id: "eu.mistral.pixtral-large-2502-v1:0",
814
+ name: "Pixtral Large (25.02) (EU)",
815
+ api: "bedrock-converse-stream",
816
+ provider: "amazon-bedrock",
817
+ baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
818
+ reasoning: false,
819
+ input: ["text", "image"],
820
+ cost: {
821
+ input: 2,
822
+ output: 6,
823
+ cacheRead: 0,
824
+ cacheWrite: 0,
825
+ },
826
+ contextWindow: 128000,
827
+ maxTokens: 8192,
828
+ },
829
+ "global.amazon.nova-2-lite-v1:0": {
830
+ id: "global.amazon.nova-2-lite-v1:0",
831
+ name: "Nova 2 Lite (Global)",
832
+ api: "bedrock-converse-stream",
833
+ provider: "amazon-bedrock",
834
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
835
+ reasoning: true,
836
+ input: ["text", "image"],
837
+ cost: {
838
+ input: 0.3,
839
+ output: 2.5,
840
+ cacheRead: 0.075,
841
+ cacheWrite: 0.3,
842
+ },
843
+ contextWindow: 1000000,
844
+ maxTokens: 65535,
845
+ },
657
846
  "global.anthropic.claude-fable-5": {
658
847
  id: "global.anthropic.claude-fable-5",
659
848
  name: "Claude Fable 5 (Global)",
@@ -908,30 +1097,81 @@ export const MODELS = {
908
1097
  contextWindow: 1050000,
909
1098
  maxTokens: 128000,
910
1099
  },
911
- "google.gemma-3-27b-it": {
912
- id: "google.gemma-3-27b-it",
913
- name: "Google Gemma 3 27B Instruct",
1100
+ "global.openai.gpt-6-astra": {
1101
+ id: "global.openai.gpt-6-astra",
1102
+ name: "GPT-6 Astra (Global)",
914
1103
  api: "bedrock-converse-stream",
915
1104
  provider: "amazon-bedrock",
916
1105
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
917
- reasoning: false,
1106
+ reasoning: true,
918
1107
  input: ["text", "image"],
919
1108
  cost: {
920
- input: 0.12,
921
- output: 0.2,
1109
+ input: 10,
1110
+ output: 50,
1111
+ cacheRead: 1,
1112
+ cacheWrite: 12.5,
1113
+ },
1114
+ contextWindow: 1050000,
1115
+ maxTokens: 128000,
1116
+ },
1117
+ "global.xai.grok-4.6": {
1118
+ id: "global.xai.grok-4.6",
1119
+ name: "Grok 4.6 (Global)",
1120
+ api: "bedrock-converse-stream",
1121
+ provider: "amazon-bedrock",
1122
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1123
+ reasoning: true,
1124
+ input: ["text", "image"],
1125
+ cost: {
1126
+ input: 2,
1127
+ output: 6,
1128
+ cacheRead: 0.5,
1129
+ cacheWrite: 0,
1130
+ },
1131
+ contextWindow: 500000,
1132
+ maxTokens: 500000,
1133
+ },
1134
+ "google.gemma-4-26b-a4b": {
1135
+ id: "google.gemma-4-26b-a4b",
1136
+ name: "Gemma 4 26B A4B IT",
1137
+ api: "bedrock-converse-stream",
1138
+ provider: "amazon-bedrock",
1139
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1140
+ reasoning: true,
1141
+ input: ["text", "image"],
1142
+ cost: {
1143
+ input: 0.13,
1144
+ output: 0.4,
922
1145
  cacheRead: 0,
923
1146
  cacheWrite: 0,
924
1147
  },
925
- contextWindow: 202752,
926
- maxTokens: 8192,
1148
+ contextWindow: 262144,
1149
+ maxTokens: 32768,
927
1150
  },
928
- "google.gemma-3-4b-it": {
929
- id: "google.gemma-3-4b-it",
930
- name: "Gemma 3 4B IT",
1151
+ "google.gemma-4-31b": {
1152
+ id: "google.gemma-4-31b",
1153
+ name: "Gemma 4 31B IT",
931
1154
  api: "bedrock-converse-stream",
932
1155
  provider: "amazon-bedrock",
933
1156
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
934
- reasoning: false,
1157
+ reasoning: true,
1158
+ input: ["text", "image"],
1159
+ cost: {
1160
+ input: 0.14,
1161
+ output: 0.4,
1162
+ cacheRead: 0,
1163
+ cacheWrite: 0,
1164
+ },
1165
+ contextWindow: 262144,
1166
+ maxTokens: 32768,
1167
+ },
1168
+ "google.gemma-4-e2b": {
1169
+ id: "google.gemma-4-e2b",
1170
+ name: "Gemma 4 E2B IT",
1171
+ api: "bedrock-converse-stream",
1172
+ provider: "amazon-bedrock",
1173
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1174
+ reasoning: true,
935
1175
  input: ["text", "image"],
936
1176
  cost: {
937
1177
  input: 0.04,
@@ -939,8 +1179,59 @@ export const MODELS = {
939
1179
  cacheRead: 0,
940
1180
  cacheWrite: 0,
941
1181
  },
942
- contextWindow: 128000,
943
- maxTokens: 4096,
1182
+ contextWindow: 131072,
1183
+ maxTokens: 8192,
1184
+ },
1185
+ "in.openai.gpt-5.6-luna": {
1186
+ id: "in.openai.gpt-5.6-luna",
1187
+ name: "GPT-5.6 Luna (India)",
1188
+ api: "bedrock-converse-stream",
1189
+ provider: "amazon-bedrock",
1190
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1191
+ reasoning: true,
1192
+ input: ["text", "image"],
1193
+ cost: {
1194
+ input: 0.22,
1195
+ output: 1.32,
1196
+ cacheRead: 0.022,
1197
+ cacheWrite: 0.275,
1198
+ },
1199
+ contextWindow: 1050000,
1200
+ maxTokens: 128000,
1201
+ },
1202
+ "in.openai.gpt-5.6-terra": {
1203
+ id: "in.openai.gpt-5.6-terra",
1204
+ name: "GPT-5.6 Terra (India)",
1205
+ api: "bedrock-converse-stream",
1206
+ provider: "amazon-bedrock",
1207
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1208
+ reasoning: true,
1209
+ input: ["text", "image"],
1210
+ cost: {
1211
+ input: 2.2,
1212
+ output: 13.2,
1213
+ cacheRead: 0.22,
1214
+ cacheWrite: 2.75,
1215
+ },
1216
+ contextWindow: 1050000,
1217
+ maxTokens: 128000,
1218
+ },
1219
+ "jp.amazon.nova-2-lite-v1:0": {
1220
+ id: "jp.amazon.nova-2-lite-v1:0",
1221
+ name: "Nova 2 Lite (JP)",
1222
+ api: "bedrock-converse-stream",
1223
+ provider: "amazon-bedrock",
1224
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1225
+ reasoning: true,
1226
+ input: ["text", "image"],
1227
+ cost: {
1228
+ input: 0.396,
1229
+ output: 3.311,
1230
+ cacheRead: 0.099,
1231
+ cacheWrite: 0.396,
1232
+ },
1233
+ contextWindow: 1000000,
1234
+ maxTokens: 65535,
944
1235
  },
945
1236
  "jp.anthropic.claude-haiku-4-5-20251001-v1:0": {
946
1237
  id: "jp.anthropic.claude-haiku-4-5-20251001-v1:0",
@@ -1548,6 +1839,23 @@ export const MODELS = {
1548
1839
  contextWindow: 1050000,
1549
1840
  maxTokens: 128000,
1550
1841
  },
1842
+ "openai.gpt-6-astra": {
1843
+ id: "openai.gpt-6-astra",
1844
+ name: "GPT-6 Astra",
1845
+ api: "bedrock-converse-stream",
1846
+ provider: "amazon-bedrock",
1847
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1848
+ reasoning: true,
1849
+ input: ["text", "image"],
1850
+ cost: {
1851
+ input: 11,
1852
+ output: 55,
1853
+ cacheRead: 1.1,
1854
+ cacheWrite: 13.75,
1855
+ },
1856
+ contextWindow: 1050000,
1857
+ maxTokens: 128000,
1858
+ },
1551
1859
  "openai.gpt-oss-120b": {
1552
1860
  id: "openai.gpt-oss-120b",
1553
1861
  name: "gpt-oss-120b",
@@ -1622,7 +1930,7 @@ export const MODELS = {
1622
1930
  api: "bedrock-converse-stream",
1623
1931
  provider: "amazon-bedrock",
1624
1932
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1625
- reasoning: false,
1933
+ reasoning: true,
1626
1934
  input: ["text"],
1627
1935
  cost: {
1628
1936
  input: 0.15,
@@ -1639,7 +1947,7 @@ export const MODELS = {
1639
1947
  api: "bedrock-converse-stream",
1640
1948
  provider: "amazon-bedrock",
1641
1949
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1642
- reasoning: false,
1950
+ reasoning: true,
1643
1951
  input: ["text"],
1644
1952
  cost: {
1645
1953
  input: 0.07,
@@ -1769,14 +2077,133 @@ export const MODELS = {
1769
2077
  contextWindow: 262000,
1770
2078
  maxTokens: 262000,
1771
2079
  },
1772
- "us.anthropic.claude-fable-5": {
1773
- id: "us.anthropic.claude-fable-5",
1774
- name: "Claude Fable 5 (US)",
2080
+ "us-gov.openai.gpt-oss-120b-1:0": {
2081
+ id: "us-gov.openai.gpt-oss-120b-1:0",
2082
+ name: "gpt-oss-120b (GovCloud)",
1775
2083
  api: "bedrock-converse-stream",
1776
2084
  provider: "amazon-bedrock",
1777
2085
  baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1778
2086
  reasoning: true,
1779
- thinkingType: "adaptive",
2087
+ input: ["text"],
2088
+ cost: {
2089
+ input: 0.18,
2090
+ output: 0.72,
2091
+ cacheRead: 0,
2092
+ cacheWrite: 0,
2093
+ },
2094
+ contextWindow: 128000,
2095
+ maxTokens: 16384,
2096
+ },
2097
+ "us-gov.openai.gpt-oss-20b-1:0": {
2098
+ id: "us-gov.openai.gpt-oss-20b-1:0",
2099
+ name: "gpt-oss-20b (GovCloud)",
2100
+ api: "bedrock-converse-stream",
2101
+ provider: "amazon-bedrock",
2102
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2103
+ reasoning: true,
2104
+ input: ["text"],
2105
+ cost: {
2106
+ input: 0.084,
2107
+ output: 0.36,
2108
+ cacheRead: 0,
2109
+ cacheWrite: 0,
2110
+ },
2111
+ contextWindow: 128000,
2112
+ maxTokens: 16384,
2113
+ },
2114
+ "us.amazon.nova-2-lite-v1:0": {
2115
+ id: "us.amazon.nova-2-lite-v1:0",
2116
+ name: "Nova 2 Lite (US)",
2117
+ api: "bedrock-converse-stream",
2118
+ provider: "amazon-bedrock",
2119
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2120
+ reasoning: true,
2121
+ input: ["text", "image"],
2122
+ cost: {
2123
+ input: 0.33,
2124
+ output: 2.75,
2125
+ cacheRead: 0.0825,
2126
+ cacheWrite: 0.33,
2127
+ },
2128
+ contextWindow: 1000000,
2129
+ maxTokens: 65535,
2130
+ },
2131
+ "us.amazon.nova-lite-v1:0": {
2132
+ id: "us.amazon.nova-lite-v1:0",
2133
+ name: "Nova Lite (US)",
2134
+ api: "bedrock-converse-stream",
2135
+ provider: "amazon-bedrock",
2136
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2137
+ reasoning: false,
2138
+ input: ["text", "image"],
2139
+ cost: {
2140
+ input: 0.06,
2141
+ output: 0.24,
2142
+ cacheRead: 0.015,
2143
+ cacheWrite: 0.06,
2144
+ },
2145
+ contextWindow: 300000,
2146
+ maxTokens: 10000,
2147
+ },
2148
+ "us.amazon.nova-micro-v1:0": {
2149
+ id: "us.amazon.nova-micro-v1:0",
2150
+ name: "Nova Micro (US)",
2151
+ api: "bedrock-converse-stream",
2152
+ provider: "amazon-bedrock",
2153
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2154
+ reasoning: false,
2155
+ input: ["text"],
2156
+ cost: {
2157
+ input: 0.035,
2158
+ output: 0.14,
2159
+ cacheRead: 0.00875,
2160
+ cacheWrite: 0.035,
2161
+ },
2162
+ contextWindow: 128000,
2163
+ maxTokens: 10000,
2164
+ },
2165
+ "us.amazon.nova-premier-v1:0": {
2166
+ id: "us.amazon.nova-premier-v1:0",
2167
+ name: "Nova Premier (US)",
2168
+ api: "bedrock-converse-stream",
2169
+ provider: "amazon-bedrock",
2170
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2171
+ reasoning: false,
2172
+ input: ["text", "image"],
2173
+ cost: {
2174
+ input: 2.5,
2175
+ output: 12.5,
2176
+ cacheRead: 0.625,
2177
+ cacheWrite: 2.5,
2178
+ },
2179
+ contextWindow: 1000000,
2180
+ maxTokens: 10000,
2181
+ },
2182
+ "us.amazon.nova-pro-v1:0": {
2183
+ id: "us.amazon.nova-pro-v1:0",
2184
+ name: "Nova Pro (US)",
2185
+ api: "bedrock-converse-stream",
2186
+ provider: "amazon-bedrock",
2187
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2188
+ reasoning: false,
2189
+ input: ["text", "image"],
2190
+ cost: {
2191
+ input: 0.8,
2192
+ output: 3.2,
2193
+ cacheRead: 0.2,
2194
+ cacheWrite: 0.8,
2195
+ },
2196
+ contextWindow: 300000,
2197
+ maxTokens: 10000,
2198
+ },
2199
+ "us.anthropic.claude-fable-5": {
2200
+ id: "us.anthropic.claude-fable-5",
2201
+ name: "Claude Fable 5 (US)",
2202
+ api: "bedrock-converse-stream",
2203
+ provider: "amazon-bedrock",
2204
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2205
+ reasoning: true,
2206
+ thinkingType: "adaptive",
1780
2207
  thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
1781
2208
  input: ["text", "image"],
1782
2209
  cost: {
@@ -2007,6 +2434,57 @@ export const MODELS = {
2007
2434
  contextWindow: 128000,
2008
2435
  maxTokens: 32768,
2009
2436
  },
2437
+ "us.meta.llama3-1-70b-instruct-v1:0": {
2438
+ id: "us.meta.llama3-1-70b-instruct-v1:0",
2439
+ name: "Llama 3.1 70B Instruct (US)",
2440
+ api: "bedrock-converse-stream",
2441
+ provider: "amazon-bedrock",
2442
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2443
+ reasoning: false,
2444
+ input: ["text"],
2445
+ cost: {
2446
+ input: 0.72,
2447
+ output: 0.72,
2448
+ cacheRead: 0,
2449
+ cacheWrite: 0,
2450
+ },
2451
+ contextWindow: 128000,
2452
+ maxTokens: 4096,
2453
+ },
2454
+ "us.meta.llama3-1-8b-instruct-v1:0": {
2455
+ id: "us.meta.llama3-1-8b-instruct-v1:0",
2456
+ name: "Llama 3.1 8B Instruct (US)",
2457
+ api: "bedrock-converse-stream",
2458
+ provider: "amazon-bedrock",
2459
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2460
+ reasoning: false,
2461
+ input: ["text"],
2462
+ cost: {
2463
+ input: 0.22,
2464
+ output: 0.22,
2465
+ cacheRead: 0,
2466
+ cacheWrite: 0,
2467
+ },
2468
+ contextWindow: 128000,
2469
+ maxTokens: 4096,
2470
+ },
2471
+ "us.meta.llama3-3-70b-instruct-v1:0": {
2472
+ id: "us.meta.llama3-3-70b-instruct-v1:0",
2473
+ name: "Llama 3.3 70B Instruct (US)",
2474
+ api: "bedrock-converse-stream",
2475
+ provider: "amazon-bedrock",
2476
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2477
+ reasoning: false,
2478
+ input: ["text"],
2479
+ cost: {
2480
+ input: 0.72,
2481
+ output: 0.72,
2482
+ cacheRead: 0,
2483
+ cacheWrite: 0,
2484
+ },
2485
+ contextWindow: 128000,
2486
+ maxTokens: 4096,
2487
+ },
2010
2488
  "us.meta.llama4-maverick-17b-instruct-v1:0": {
2011
2489
  id: "us.meta.llama4-maverick-17b-instruct-v1:0",
2012
2490
  name: "Llama 4 Maverick 17B Instruct (US)",
@@ -2041,6 +2519,142 @@ export const MODELS = {
2041
2519
  contextWindow: 3500000,
2042
2520
  maxTokens: 16384,
2043
2521
  },
2522
+ "us.mistral.pixtral-large-2502-v1:0": {
2523
+ id: "us.mistral.pixtral-large-2502-v1:0",
2524
+ name: "Pixtral Large (25.02) (US)",
2525
+ api: "bedrock-converse-stream",
2526
+ provider: "amazon-bedrock",
2527
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2528
+ reasoning: false,
2529
+ input: ["text", "image"],
2530
+ cost: {
2531
+ input: 2,
2532
+ output: 6,
2533
+ cacheRead: 0,
2534
+ cacheWrite: 0,
2535
+ },
2536
+ contextWindow: 128000,
2537
+ maxTokens: 8192,
2538
+ },
2539
+ "us.openai.gpt-5.6-luna": {
2540
+ id: "us.openai.gpt-5.6-luna",
2541
+ name: "GPT-5.6 Luna (US)",
2542
+ api: "bedrock-converse-stream",
2543
+ provider: "amazon-bedrock",
2544
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2545
+ reasoning: true,
2546
+ input: ["text", "image"],
2547
+ cost: {
2548
+ input: 0.22,
2549
+ output: 1.32,
2550
+ cacheRead: 0.022,
2551
+ cacheWrite: 0.275,
2552
+ },
2553
+ contextWindow: 1050000,
2554
+ maxTokens: 128000,
2555
+ },
2556
+ "us.openai.gpt-5.6-sol": {
2557
+ id: "us.openai.gpt-5.6-sol",
2558
+ name: "GPT-5.6 Sol (US)",
2559
+ api: "bedrock-converse-stream",
2560
+ provider: "amazon-bedrock",
2561
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2562
+ reasoning: true,
2563
+ input: ["text", "image"],
2564
+ cost: {
2565
+ input: 4.4,
2566
+ output: 22,
2567
+ cacheRead: 0.44,
2568
+ cacheWrite: 5.5,
2569
+ },
2570
+ contextWindow: 1050000,
2571
+ maxTokens: 128000,
2572
+ },
2573
+ "us.openai.gpt-5.6-terra": {
2574
+ id: "us.openai.gpt-5.6-terra",
2575
+ name: "GPT-5.6 Terra (US)",
2576
+ api: "bedrock-converse-stream",
2577
+ provider: "amazon-bedrock",
2578
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2579
+ reasoning: true,
2580
+ input: ["text", "image"],
2581
+ cost: {
2582
+ input: 2.2,
2583
+ output: 13.2,
2584
+ cacheRead: 0.22,
2585
+ cacheWrite: 2.75,
2586
+ },
2587
+ contextWindow: 1050000,
2588
+ maxTokens: 128000,
2589
+ },
2590
+ "us.openai.gpt-6-astra": {
2591
+ id: "us.openai.gpt-6-astra",
2592
+ name: "GPT-6 Astra (US)",
2593
+ api: "bedrock-converse-stream",
2594
+ provider: "amazon-bedrock",
2595
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2596
+ reasoning: true,
2597
+ input: ["text", "image"],
2598
+ cost: {
2599
+ input: 11,
2600
+ output: 55,
2601
+ cacheRead: 1.1,
2602
+ cacheWrite: 13.75,
2603
+ },
2604
+ contextWindow: 1050000,
2605
+ maxTokens: 128000,
2606
+ },
2607
+ "us.writer.palmyra-x4-v1:0": {
2608
+ id: "us.writer.palmyra-x4-v1:0",
2609
+ name: "Palmyra X4 (US)",
2610
+ api: "bedrock-converse-stream",
2611
+ provider: "amazon-bedrock",
2612
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2613
+ reasoning: true,
2614
+ input: ["text"],
2615
+ cost: {
2616
+ input: 2.5,
2617
+ output: 10,
2618
+ cacheRead: 0,
2619
+ cacheWrite: 0,
2620
+ },
2621
+ contextWindow: 122880,
2622
+ maxTokens: 8192,
2623
+ },
2624
+ "us.writer.palmyra-x5-v1:0": {
2625
+ id: "us.writer.palmyra-x5-v1:0",
2626
+ name: "Palmyra X5 (US)",
2627
+ api: "bedrock-converse-stream",
2628
+ provider: "amazon-bedrock",
2629
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2630
+ reasoning: true,
2631
+ input: ["text"],
2632
+ cost: {
2633
+ input: 0.6,
2634
+ output: 6,
2635
+ cacheRead: 0,
2636
+ cacheWrite: 0,
2637
+ },
2638
+ contextWindow: 1040000,
2639
+ maxTokens: 8192,
2640
+ },
2641
+ "us.xai.grok-4.6": {
2642
+ id: "us.xai.grok-4.6",
2643
+ name: "Grok 4.6 (US)",
2644
+ api: "bedrock-converse-stream",
2645
+ provider: "amazon-bedrock",
2646
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2647
+ reasoning: true,
2648
+ input: ["text", "image"],
2649
+ cost: {
2650
+ input: 2.2,
2651
+ output: 6.6,
2652
+ cacheRead: 0.55,
2653
+ cacheWrite: 0,
2654
+ },
2655
+ contextWindow: 500000,
2656
+ maxTokens: 500000,
2657
+ },
2044
2658
  "writer.palmyra-x4-v1:0": {
2045
2659
  id: "writer.palmyra-x4-v1:0",
2046
2660
  name: "Palmyra X4",
@@ -2955,6 +3569,23 @@ export const MODELS = {
2955
3569
  contextWindow: 1050000,
2956
3570
  maxTokens: 128000,
2957
3571
  },
3572
+ "gpt-6-astra": {
3573
+ id: "gpt-6-astra",
3574
+ name: "GPT-6 Astra",
3575
+ api: "azure-openai-responses",
3576
+ provider: "azure-openai-responses",
3577
+ baseUrl: "",
3578
+ reasoning: true,
3579
+ input: ["text", "image"],
3580
+ cost: {
3581
+ input: 10,
3582
+ output: 50,
3583
+ cacheRead: 1,
3584
+ cacheWrite: 12.5,
3585
+ },
3586
+ contextWindow: 1050000,
3587
+ maxTokens: 128000,
3588
+ },
2958
3589
  "gpt-realtime-2.1": {
2959
3590
  id: "gpt-realtime-2.1",
2960
3591
  name: "GPT-Realtime-2.1",
@@ -3076,45 +3707,63 @@ export const MODELS = {
3076
3707
  },
3077
3708
  },
3078
3709
  "cerebras": {
3079
- "gemma-4-31b": {
3080
- id: "gemma-4-31b",
3081
- name: "Gemma 4 31B IT",
3710
+ "gpt-oss-120b": {
3711
+ id: "gpt-oss-120b",
3712
+ name: "GPT OSS 120B",
3082
3713
  api: "openai-completions",
3083
3714
  provider: "cerebras",
3084
3715
  baseUrl: "https://api.cerebras.ai/v1",
3085
3716
  reasoning: true,
3086
- input: ["text", "image"],
3717
+ input: ["text"],
3087
3718
  cost: {
3088
- input: 0.99,
3089
- output: 1.49,
3719
+ input: 0.35,
3720
+ output: 0.75,
3090
3721
  cacheRead: 0,
3091
3722
  cacheWrite: 0,
3092
3723
  },
3093
3724
  contextWindow: 131072,
3094
3725
  maxTokens: 40960,
3095
3726
  },
3096
- "gpt-oss-120b": {
3097
- id: "gpt-oss-120b",
3098
- name: "GPT OSS 120B",
3727
+ "qwen-3.8-27b": {
3728
+ id: "qwen-3.8-27b",
3729
+ name: "Qwen3.8 27B",
3099
3730
  api: "openai-completions",
3100
3731
  provider: "cerebras",
3101
3732
  baseUrl: "https://api.cerebras.ai/v1",
3102
3733
  reasoning: true,
3103
- input: ["text"],
3734
+ input: ["text", "image"],
3104
3735
  cost: {
3105
- input: 0.35,
3106
- output: 0.75,
3736
+ input: 0.99,
3737
+ output: 1.49,
3107
3738
  cacheRead: 0,
3108
3739
  cacheWrite: 0,
3109
3740
  },
3110
- contextWindow: 131072,
3111
- maxTokens: 40960,
3741
+ contextWindow: 65536,
3742
+ maxTokens: 32768,
3743
+ },
3744
+ },
3745
+ "cloudflare-ai-gateway": {
3746
+ "claude-fable-5": {
3747
+ id: "claude-fable-5",
3748
+ name: "Claude Fable 5",
3749
+ api: "anthropic-messages",
3750
+ provider: "cloudflare-ai-gateway",
3751
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
3752
+ reasoning: true,
3753
+ thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
3754
+ input: ["text", "image"],
3755
+ cost: {
3756
+ input: 10,
3757
+ output: 50,
3758
+ cacheRead: 1,
3759
+ cacheWrite: 12.5,
3760
+ },
3761
+ contextWindow: 1000000,
3762
+ maxTokens: 128000,
3112
3763
  },
3113
- },
3114
- "cloudflare-ai-gateway": {
3115
- "claude-fable-5": {
3116
- id: "claude-fable-5",
3117
- name: "Claude Fable 5",
3764
+ "claude-fable-5.1": {
3765
+ id: "claude-fable-5.1",
3766
+ name: "Claude Fable 5.1",
3118
3767
  api: "anthropic-messages",
3119
3768
  provider: "cloudflare-ai-gateway",
3120
3769
  baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
@@ -3124,7 +3773,7 @@ export const MODELS = {
3124
3773
  cost: {
3125
3774
  input: 10,
3126
3775
  output: 50,
3127
- cacheRead: 1,
3776
+ cacheRead: 0.25,
3128
3777
  cacheWrite: 12.5,
3129
3778
  },
3130
3779
  contextWindow: 1000000,
@@ -4077,6 +4726,23 @@ export const MODELS = {
4077
4726
  contextWindow: 1000000,
4078
4727
  maxTokens: 384000,
4079
4728
  },
4729
+ "accounts/fireworks/models/deepseek-v4p1-flash": {
4730
+ id: "accounts/fireworks/models/deepseek-v4p1-flash",
4731
+ name: "DeepSeek V4.1 Flash",
4732
+ api: "anthropic-messages",
4733
+ provider: "fireworks",
4734
+ baseUrl: "https://api.fireworks.ai/inference",
4735
+ reasoning: true,
4736
+ input: ["text", "image"],
4737
+ cost: {
4738
+ input: 0.22,
4739
+ output: 0.66,
4740
+ cacheRead: 0.007,
4741
+ cacheWrite: 0,
4742
+ },
4743
+ contextWindow: 1000000,
4744
+ maxTokens: 384000,
4745
+ },
4080
4746
  "accounts/fireworks/models/glm-5p2": {
4081
4747
  id: "accounts/fireworks/models/glm-5p2",
4082
4748
  name: "GLM 5.2",
@@ -4108,8 +4774,8 @@ export const MODELS = {
4108
4774
  cacheRead: 0.26,
4109
4775
  cacheWrite: 0,
4110
4776
  },
4111
- contextWindow: 1000000,
4112
- maxTokens: 131072,
4777
+ contextWindow: 1048573,
4778
+ maxTokens: 262144,
4113
4779
  },
4114
4780
  "accounts/fireworks/models/glm-5p3-flash": {
4115
4781
  id: "accounts/fireworks/models/glm-5p3-flash",
@@ -4125,7 +4791,7 @@ export const MODELS = {
4125
4791
  cacheRead: 0.03,
4126
4792
  cacheWrite: 0,
4127
4793
  },
4128
- contextWindow: 1000000,
4794
+ contextWindow: 1048573,
4129
4795
  maxTokens: 131072,
4130
4796
  },
4131
4797
  "accounts/fireworks/models/gpt-oss-120b": {
@@ -4230,6 +4896,23 @@ export const MODELS = {
4230
4896
  contextWindow: 512000,
4231
4897
  maxTokens: 512000,
4232
4898
  },
4899
+ "accounts/fireworks/models/mistral-large-3-fp8": {
4900
+ id: "accounts/fireworks/models/mistral-large-3-fp8",
4901
+ name: "Mistral Large 3 675B Instruct 2512",
4902
+ api: "anthropic-messages",
4903
+ provider: "fireworks",
4904
+ baseUrl: "https://api.fireworks.ai/inference",
4905
+ reasoning: false,
4906
+ input: ["text", "image"],
4907
+ cost: {
4908
+ input: 0,
4909
+ output: 0,
4910
+ cacheRead: 0,
4911
+ cacheWrite: 0,
4912
+ },
4913
+ contextWindow: 262144,
4914
+ maxTokens: 262144,
4915
+ },
4233
4916
  "accounts/fireworks/models/muse-glimmer-30b": {
4234
4917
  id: "accounts/fireworks/models/muse-glimmer-30b",
4235
4918
  name: "Muse Glimmer 30B",
@@ -4298,6 +4981,23 @@ export const MODELS = {
4298
4981
  contextWindow: 262144,
4299
4982
  maxTokens: 65536,
4300
4983
  },
4984
+ "accounts/fireworks/models/qwen3p8-2p4t-a95b": {
4985
+ id: "accounts/fireworks/models/qwen3p8-2p4t-a95b",
4986
+ name: "Qwen3.8 2.4T A95B",
4987
+ api: "anthropic-messages",
4988
+ provider: "fireworks",
4989
+ baseUrl: "https://api.fireworks.ai/inference",
4990
+ reasoning: true,
4991
+ input: ["text"],
4992
+ cost: {
4993
+ input: 2,
4994
+ output: 6,
4995
+ cacheRead: 0.25,
4996
+ cacheWrite: 0,
4997
+ },
4998
+ contextWindow: 262144,
4999
+ maxTokens: 131072,
5000
+ },
4301
5001
  "accounts/fireworks/models/qwen3p8-max": {
4302
5002
  id: "accounts/fireworks/models/qwen3p8-max",
4303
5003
  name: "Qwen3.8 Max",
@@ -4332,6 +5032,23 @@ export const MODELS = {
4332
5032
  contextWindow: 1048575,
4333
5033
  maxTokens: 131072,
4334
5034
  },
5035
+ "accounts/fireworks/routers/glm-5p3-fast": {
5036
+ id: "accounts/fireworks/routers/glm-5p3-fast",
5037
+ name: "GLM 5.3 Fast",
5038
+ api: "anthropic-messages",
5039
+ provider: "fireworks",
5040
+ baseUrl: "https://api.fireworks.ai/inference",
5041
+ reasoning: true,
5042
+ input: ["text"],
5043
+ cost: {
5044
+ input: 2.1,
5045
+ output: 6.6,
5046
+ cacheRead: 0.39,
5047
+ cacheWrite: 0,
5048
+ },
5049
+ contextWindow: 1048572,
5050
+ maxTokens: 262144,
5051
+ },
4335
5052
  "accounts/fireworks/routers/kimi-k3-fast": {
4336
5053
  id: "accounts/fireworks/routers/kimi-k3-fast",
4337
5054
  name: "Kimi K3 Fast",
@@ -4371,6 +5088,26 @@ export const MODELS = {
4371
5088
  contextWindow: 1000000,
4372
5089
  maxTokens: 128000,
4373
5090
  },
5091
+ "claude-fable-5.1": {
5092
+ id: "claude-fable-5.1",
5093
+ name: "Claude Fable 5.1",
5094
+ api: "openai-completions",
5095
+ provider: "github-copilot",
5096
+ baseUrl: "https://api.individual.githubcopilot.com",
5097
+ 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" },
5098
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
5099
+ reasoning: true,
5100
+ thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
5101
+ input: ["text", "image"],
5102
+ cost: {
5103
+ input: 10,
5104
+ output: 50,
5105
+ cacheRead: 0.25,
5106
+ cacheWrite: 12.5,
5107
+ },
5108
+ contextWindow: 1000000,
5109
+ maxTokens: 128000,
5110
+ },
4374
5111
  "claude-haiku-4.5": {
4375
5112
  id: "claude-haiku-4.5",
4376
5113
  name: "Claude Haiku 4.5 (latest)",
@@ -4390,43 +5127,6 @@ export const MODELS = {
4390
5127
  contextWindow: 200000,
4391
5128
  maxTokens: 64000,
4392
5129
  },
4393
- "claude-opus-4.5": {
4394
- id: "claude-opus-4.5",
4395
- name: "Claude Opus 4.5 (latest)",
4396
- api: "anthropic-messages",
4397
- provider: "github-copilot",
4398
- baseUrl: "https://api.individual.githubcopilot.com",
4399
- 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" },
4400
- reasoning: true,
4401
- input: ["text", "image"],
4402
- cost: {
4403
- input: 5,
4404
- output: 25,
4405
- cacheRead: 0.5,
4406
- cacheWrite: 6.25,
4407
- },
4408
- contextWindow: 200000,
4409
- maxTokens: 32000,
4410
- },
4411
- "claude-opus-4.6": {
4412
- id: "claude-opus-4.6",
4413
- name: "Claude Opus 4.6",
4414
- api: "anthropic-messages",
4415
- provider: "github-copilot",
4416
- baseUrl: "https://api.individual.githubcopilot.com",
4417
- 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" },
4418
- reasoning: true,
4419
- thinkingLevelMap: { "xhigh": "max" },
4420
- input: ["text", "image"],
4421
- cost: {
4422
- input: 5,
4423
- output: 25,
4424
- cacheRead: 0.5,
4425
- cacheWrite: 6.25,
4426
- },
4427
- contextWindow: 1000000,
4428
- maxTokens: 32000,
4429
- },
4430
5130
  "claude-opus-4.7": {
4431
5131
  id: "claude-opus-4.7",
4432
5132
  name: "Claude Opus 4.7",
@@ -4484,44 +5184,6 @@ export const MODELS = {
4484
5184
  contextWindow: 1000000,
4485
5185
  maxTokens: 64000,
4486
5186
  },
4487
- "claude-sonnet-4": {
4488
- id: "claude-sonnet-4",
4489
- name: "Claude Sonnet 4 (latest)",
4490
- api: "anthropic-messages",
4491
- provider: "github-copilot",
4492
- baseUrl: "https://api.individual.githubcopilot.com",
4493
- 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" },
4494
- compat: { "supportsEagerToolInputStreaming": false },
4495
- reasoning: true,
4496
- input: ["text", "image"],
4497
- cost: {
4498
- input: 3,
4499
- output: 15,
4500
- cacheRead: 0.3,
4501
- cacheWrite: 3.75,
4502
- },
4503
- contextWindow: 216000,
4504
- maxTokens: 16000,
4505
- },
4506
- "claude-sonnet-4.5": {
4507
- id: "claude-sonnet-4.5",
4508
- name: "Claude Sonnet 4.5 (latest)",
4509
- api: "anthropic-messages",
4510
- provider: "github-copilot",
4511
- baseUrl: "https://api.individual.githubcopilot.com",
4512
- 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" },
4513
- compat: { "supportsEagerToolInputStreaming": false },
4514
- reasoning: true,
4515
- input: ["text", "image"],
4516
- cost: {
4517
- input: 3,
4518
- output: 15,
4519
- cacheRead: 0.3,
4520
- cacheWrite: 3.75,
4521
- },
4522
- contextWindow: 200000,
4523
- maxTokens: 32000,
4524
- },
4525
5187
  "claude-sonnet-4.6": {
4526
5188
  id: "claude-sonnet-4.6",
4527
5189
  name: "Claude Sonnet 4.6",
@@ -4559,25 +5221,6 @@ export const MODELS = {
4559
5221
  contextWindow: 1000000,
4560
5222
  maxTokens: 128000,
4561
5223
  },
4562
- "gemini-3.1-pro-preview": {
4563
- id: "gemini-3.1-pro-preview",
4564
- name: "Gemini 3.1 Pro Preview",
4565
- api: "openai-completions",
4566
- provider: "github-copilot",
4567
- baseUrl: "https://api.individual.githubcopilot.com",
4568
- 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" },
4569
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
4570
- reasoning: true,
4571
- input: ["text", "image"],
4572
- cost: {
4573
- input: 2,
4574
- output: 12,
4575
- cacheRead: 0.2,
4576
- cacheWrite: 0,
4577
- },
4578
- contextWindow: 1000000,
4579
- maxTokens: 64000,
4580
- },
4581
5224
  "gemini-3.5-flash": {
4582
5225
  id: "gemini-3.5-flash",
4583
5226
  name: "Gemini 3.5 Flash",
@@ -4635,24 +5278,24 @@ export const MODELS = {
4635
5278
  contextWindow: 1000000,
4636
5279
  maxTokens: 64000,
4637
5280
  },
4638
- "gpt-4.1": {
4639
- id: "gpt-4.1",
4640
- name: "GPT-4.1",
5281
+ "gemini-3.8-flash": {
5282
+ id: "gemini-3.8-flash",
5283
+ name: "Gemini 3.8 Flash",
4641
5284
  api: "openai-completions",
4642
5285
  provider: "github-copilot",
4643
5286
  baseUrl: "https://api.individual.githubcopilot.com",
4644
5287
  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" },
4645
5288
  compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
4646
- reasoning: false,
5289
+ reasoning: true,
4647
5290
  input: ["text", "image"],
4648
5291
  cost: {
4649
- input: 2,
4650
- output: 8,
4651
- cacheRead: 0.5,
5292
+ input: 0.75,
5293
+ output: 3.75,
5294
+ cacheRead: 0.075,
4652
5295
  cacheWrite: 0,
4653
5296
  },
4654
- contextWindow: 128000,
4655
- maxTokens: 16384,
5297
+ contextWindow: 1000000,
5298
+ maxTokens: 64000,
4656
5299
  },
4657
5300
  "gpt-5-mini": {
4658
5301
  id: "gpt-5-mini",
@@ -4673,44 +5316,6 @@ export const MODELS = {
4673
5316
  contextWindow: 264000,
4674
5317
  maxTokens: 64000,
4675
5318
  },
4676
- "gpt-5.2": {
4677
- id: "gpt-5.2",
4678
- name: "GPT-5.2",
4679
- api: "openai-responses",
4680
- provider: "github-copilot",
4681
- baseUrl: "https://api.individual.githubcopilot.com",
4682
- 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" },
4683
- reasoning: true,
4684
- thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
4685
- input: ["text", "image"],
4686
- cost: {
4687
- input: 1.75,
4688
- output: 14,
4689
- cacheRead: 0.175,
4690
- cacheWrite: 0,
4691
- },
4692
- contextWindow: 400000,
4693
- maxTokens: 128000,
4694
- },
4695
- "gpt-5.2-codex": {
4696
- id: "gpt-5.2-codex",
4697
- name: "GPT-5.2 Codex",
4698
- api: "openai-responses",
4699
- provider: "github-copilot",
4700
- baseUrl: "https://api.individual.githubcopilot.com",
4701
- 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" },
4702
- reasoning: true,
4703
- thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
4704
- input: ["text", "image"],
4705
- cost: {
4706
- input: 1.75,
4707
- output: 14,
4708
- cacheRead: 0.175,
4709
- cacheWrite: 0,
4710
- },
4711
- contextWindow: 400000,
4712
- maxTokens: 128000,
4713
- },
4714
5319
  "gpt-5.3-codex": {
4715
5320
  id: "gpt-5.3-codex",
4716
5321
  name: "GPT-5.3 Codex",
@@ -4836,10 +5441,10 @@ export const MODELS = {
4836
5441
  thinkingLevelMap: { "off": null },
4837
5442
  input: ["text", "image"],
4838
5443
  cost: {
4839
- input: 2,
4840
- output: 10,
4841
- cacheRead: 0.2,
4842
- cacheWrite: 2.5,
5444
+ input: 4,
5445
+ output: 20,
5446
+ cacheRead: 0.4,
5447
+ cacheWrite: 5,
4843
5448
  },
4844
5449
  contextWindow: 1050000,
4845
5450
  maxTokens: 128000,
@@ -4863,6 +5468,25 @@ export const MODELS = {
4863
5468
  contextWindow: 1050000,
4864
5469
  maxTokens: 128000,
4865
5470
  },
5471
+ "gpt-6-astra": {
5472
+ id: "gpt-6-astra",
5473
+ name: "GPT-6 Astra",
5474
+ api: "openai-completions",
5475
+ provider: "github-copilot",
5476
+ baseUrl: "https://api.individual.githubcopilot.com",
5477
+ 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" },
5478
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
5479
+ reasoning: true,
5480
+ input: ["text", "image"],
5481
+ cost: {
5482
+ input: 10,
5483
+ output: 50,
5484
+ cacheRead: 1,
5485
+ cacheWrite: 12.5,
5486
+ },
5487
+ contextWindow: 1050000,
5488
+ maxTokens: 128000,
5489
+ },
4866
5490
  "grok-4.5": {
4867
5491
  id: "grok-4.5",
4868
5492
  name: "Grok 4.5",
@@ -6437,6 +7061,78 @@ export const MODELS = {
6437
7061
  contextWindow: 1000000,
6438
7062
  maxTokens: 384000,
6439
7063
  },
7064
+ "deepseek-ai/DeepSeek-V4.1-Flash": {
7065
+ id: "deepseek-ai/DeepSeek-V4.1-Flash",
7066
+ name: "DeepSeek V4.1 Flash",
7067
+ api: "openai-completions",
7068
+ provider: "huggingface",
7069
+ baseUrl: "https://router.huggingface.co/v1",
7070
+ compat: { "supportsDeveloperRole": false },
7071
+ reasoning: true,
7072
+ input: ["text", "image"],
7073
+ cost: {
7074
+ input: 0.3,
7075
+ output: 1.2,
7076
+ cacheRead: 0,
7077
+ cacheWrite: 0,
7078
+ },
7079
+ contextWindow: 1048576,
7080
+ maxTokens: 384000,
7081
+ },
7082
+ "google/gemma-3-12b-it": {
7083
+ id: "google/gemma-3-12b-it",
7084
+ name: "Gemma 3 12B IT",
7085
+ api: "openai-completions",
7086
+ provider: "huggingface",
7087
+ baseUrl: "https://router.huggingface.co/v1",
7088
+ compat: { "supportsDeveloperRole": false },
7089
+ reasoning: false,
7090
+ input: ["text", "image"],
7091
+ cost: {
7092
+ input: 0.05,
7093
+ output: 0.15,
7094
+ cacheRead: 0,
7095
+ cacheWrite: 0,
7096
+ },
7097
+ contextWindow: 131072,
7098
+ maxTokens: 131072,
7099
+ },
7100
+ "google/gemma-3-27b-it": {
7101
+ id: "google/gemma-3-27b-it",
7102
+ name: "Gemma 3 27B IT",
7103
+ api: "openai-completions",
7104
+ provider: "huggingface",
7105
+ baseUrl: "https://router.huggingface.co/v1",
7106
+ compat: { "supportsDeveloperRole": false },
7107
+ reasoning: false,
7108
+ input: ["text", "image"],
7109
+ cost: {
7110
+ input: 0.08,
7111
+ output: 0.16,
7112
+ cacheRead: 0,
7113
+ cacheWrite: 0,
7114
+ },
7115
+ contextWindow: 131072,
7116
+ maxTokens: 131072,
7117
+ },
7118
+ "google/gemma-3-4b-it": {
7119
+ id: "google/gemma-3-4b-it",
7120
+ name: "Gemma 3 4B IT",
7121
+ api: "openai-completions",
7122
+ provider: "huggingface",
7123
+ baseUrl: "https://router.huggingface.co/v1",
7124
+ compat: { "supportsDeveloperRole": false },
7125
+ reasoning: false,
7126
+ input: ["text", "image"],
7127
+ cost: {
7128
+ input: 0.05,
7129
+ output: 0.1,
7130
+ cacheRead: 0,
7131
+ cacheWrite: 0,
7132
+ },
7133
+ contextWindow: 131072,
7134
+ maxTokens: 131072,
7135
+ },
6440
7136
  "google/gemma-4-26B-A4B-it": {
6441
7137
  id: "google/gemma-4-26B-A4B-it",
6442
7138
  name: "Gemma 4 26B A4B IT",
@@ -7705,114 +8401,6 @@ export const MODELS = {
7705
8401
  },
7706
8402
  },
7707
8403
  "moonshotai": {
7708
- "kimi-k2-0711-preview": {
7709
- id: "kimi-k2-0711-preview",
7710
- name: "Kimi K2 0711",
7711
- api: "openai-completions",
7712
- provider: "moonshotai",
7713
- baseUrl: "https://api.moonshot.ai/v1",
7714
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
7715
- reasoning: false,
7716
- input: ["text"],
7717
- cost: {
7718
- input: 0.6,
7719
- output: 2.5,
7720
- cacheRead: 0.15,
7721
- cacheWrite: 0,
7722
- },
7723
- contextWindow: 131072,
7724
- maxTokens: 16384,
7725
- },
7726
- "kimi-k2-0905-preview": {
7727
- id: "kimi-k2-0905-preview",
7728
- name: "Kimi K2 0905",
7729
- api: "openai-completions",
7730
- provider: "moonshotai",
7731
- baseUrl: "https://api.moonshot.ai/v1",
7732
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
7733
- reasoning: false,
7734
- input: ["text"],
7735
- cost: {
7736
- input: 0.6,
7737
- output: 2.5,
7738
- cacheRead: 0.15,
7739
- cacheWrite: 0,
7740
- },
7741
- contextWindow: 262144,
7742
- maxTokens: 262144,
7743
- },
7744
- "kimi-k2-thinking": {
7745
- id: "kimi-k2-thinking",
7746
- name: "Kimi K2 Thinking",
7747
- api: "openai-completions",
7748
- provider: "moonshotai",
7749
- baseUrl: "https://api.moonshot.ai/v1",
7750
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
7751
- reasoning: true,
7752
- input: ["text"],
7753
- cost: {
7754
- input: 0.6,
7755
- output: 2.5,
7756
- cacheRead: 0.15,
7757
- cacheWrite: 0,
7758
- },
7759
- contextWindow: 262144,
7760
- maxTokens: 262144,
7761
- },
7762
- "kimi-k2-thinking-turbo": {
7763
- id: "kimi-k2-thinking-turbo",
7764
- name: "Kimi K2 Thinking Turbo",
7765
- api: "openai-completions",
7766
- provider: "moonshotai",
7767
- baseUrl: "https://api.moonshot.ai/v1",
7768
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
7769
- reasoning: true,
7770
- input: ["text"],
7771
- cost: {
7772
- input: 1.15,
7773
- output: 8,
7774
- cacheRead: 0.15,
7775
- cacheWrite: 0,
7776
- },
7777
- contextWindow: 262144,
7778
- maxTokens: 262144,
7779
- },
7780
- "kimi-k2-turbo-preview": {
7781
- id: "kimi-k2-turbo-preview",
7782
- name: "Kimi K2 Turbo",
7783
- api: "openai-completions",
7784
- provider: "moonshotai",
7785
- baseUrl: "https://api.moonshot.ai/v1",
7786
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
7787
- reasoning: false,
7788
- input: ["text"],
7789
- cost: {
7790
- input: 2.4,
7791
- output: 10,
7792
- cacheRead: 0.6,
7793
- cacheWrite: 0,
7794
- },
7795
- contextWindow: 262144,
7796
- maxTokens: 262144,
7797
- },
7798
- "kimi-k2.5": {
7799
- id: "kimi-k2.5",
7800
- name: "Kimi K2.5",
7801
- api: "openai-completions",
7802
- provider: "moonshotai",
7803
- baseUrl: "https://api.moonshot.ai/v1",
7804
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
7805
- reasoning: true,
7806
- input: ["text", "image"],
7807
- cost: {
7808
- input: 0.6,
7809
- output: 3,
7810
- cacheRead: 0.1,
7811
- cacheWrite: 0,
7812
- },
7813
- contextWindow: 262144,
7814
- maxTokens: 262144,
7815
- },
7816
8404
  "kimi-k2.6": {
7817
8405
  id: "kimi-k2.6",
7818
8406
  name: "Kimi K2.6",
@@ -7871,130 +8459,22 @@ export const MODELS = {
7871
8459
  id: "kimi-k3",
7872
8460
  name: "Kimi K3",
7873
8461
  api: "openai-completions",
7874
- provider: "moonshotai",
7875
- baseUrl: "https://api.moonshot.ai/v1",
7876
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
7877
- reasoning: true,
7878
- input: ["text", "image"],
7879
- cost: {
7880
- input: 3,
7881
- output: 15,
7882
- cacheRead: 0.3,
7883
- cacheWrite: 0,
7884
- },
7885
- contextWindow: 1048576,
7886
- maxTokens: 131072,
7887
- },
7888
- },
7889
- "moonshotai-cn": {
7890
- "kimi-k2-0711-preview": {
7891
- id: "kimi-k2-0711-preview",
7892
- name: "Kimi K2 0711",
7893
- api: "openai-completions",
7894
- provider: "moonshotai-cn",
7895
- baseUrl: "https://api.moonshot.cn/v1",
7896
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
7897
- reasoning: false,
7898
- input: ["text"],
7899
- cost: {
7900
- input: 0.6,
7901
- output: 2.5,
7902
- cacheRead: 0.15,
7903
- cacheWrite: 0,
7904
- },
7905
- contextWindow: 131072,
7906
- maxTokens: 16384,
7907
- },
7908
- "kimi-k2-0905-preview": {
7909
- id: "kimi-k2-0905-preview",
7910
- name: "Kimi K2 0905",
7911
- api: "openai-completions",
7912
- provider: "moonshotai-cn",
7913
- baseUrl: "https://api.moonshot.cn/v1",
7914
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
7915
- reasoning: false,
7916
- input: ["text"],
7917
- cost: {
7918
- input: 0.6,
7919
- output: 2.5,
7920
- cacheRead: 0.15,
7921
- cacheWrite: 0,
7922
- },
7923
- contextWindow: 262144,
7924
- maxTokens: 262144,
7925
- },
7926
- "kimi-k2-thinking": {
7927
- id: "kimi-k2-thinking",
7928
- name: "Kimi K2 Thinking",
7929
- api: "openai-completions",
7930
- provider: "moonshotai-cn",
7931
- baseUrl: "https://api.moonshot.cn/v1",
7932
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
7933
- reasoning: true,
7934
- input: ["text"],
7935
- cost: {
7936
- input: 0.6,
7937
- output: 2.5,
7938
- cacheRead: 0.15,
7939
- cacheWrite: 0,
7940
- },
7941
- contextWindow: 262144,
7942
- maxTokens: 262144,
7943
- },
7944
- "kimi-k2-thinking-turbo": {
7945
- id: "kimi-k2-thinking-turbo",
7946
- name: "Kimi K2 Thinking Turbo",
7947
- api: "openai-completions",
7948
- provider: "moonshotai-cn",
7949
- baseUrl: "https://api.moonshot.cn/v1",
7950
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
7951
- reasoning: true,
7952
- input: ["text"],
7953
- cost: {
7954
- input: 1.15,
7955
- output: 8,
7956
- cacheRead: 0.15,
7957
- cacheWrite: 0,
7958
- },
7959
- contextWindow: 262144,
7960
- maxTokens: 262144,
7961
- },
7962
- "kimi-k2-turbo-preview": {
7963
- id: "kimi-k2-turbo-preview",
7964
- name: "Kimi K2 Turbo",
7965
- api: "openai-completions",
7966
- provider: "moonshotai-cn",
7967
- baseUrl: "https://api.moonshot.cn/v1",
7968
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
7969
- reasoning: false,
7970
- input: ["text"],
7971
- cost: {
7972
- input: 2.4,
7973
- output: 10,
7974
- cacheRead: 0.6,
7975
- cacheWrite: 0,
7976
- },
7977
- contextWindow: 262144,
7978
- maxTokens: 262144,
7979
- },
7980
- "kimi-k2.5": {
7981
- id: "kimi-k2.5",
7982
- name: "Kimi K2.5",
7983
- api: "openai-completions",
7984
- provider: "moonshotai-cn",
7985
- baseUrl: "https://api.moonshot.cn/v1",
8462
+ provider: "moonshotai",
8463
+ baseUrl: "https://api.moonshot.ai/v1",
7986
8464
  compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
7987
8465
  reasoning: true,
7988
8466
  input: ["text", "image"],
7989
8467
  cost: {
7990
- input: 0.6,
7991
- output: 3,
7992
- cacheRead: 0.1,
8468
+ input: 3,
8469
+ output: 15,
8470
+ cacheRead: 0.3,
7993
8471
  cacheWrite: 0,
7994
8472
  },
7995
- contextWindow: 262144,
7996
- maxTokens: 262144,
8473
+ contextWindow: 1048576,
8474
+ maxTokens: 131072,
7997
8475
  },
8476
+ },
8477
+ "moonshotai-cn": {
7998
8478
  "kimi-k2.6": {
7999
8479
  id: "kimi-k2.6",
8000
8480
  name: "Kimi K2.6",
@@ -8603,6 +9083,23 @@ export const MODELS = {
8603
9083
  contextWindow: 1050000,
8604
9084
  maxTokens: 128000,
8605
9085
  },
9086
+ "gpt-6-astra": {
9087
+ id: "gpt-6-astra",
9088
+ name: "GPT-6 Astra",
9089
+ api: "openai-responses",
9090
+ provider: "openai",
9091
+ baseUrl: "https://api.openai.com/v1",
9092
+ reasoning: true,
9093
+ input: ["text", "image"],
9094
+ cost: {
9095
+ input: 10,
9096
+ output: 50,
9097
+ cacheRead: 1,
9098
+ cacheWrite: 12.5,
9099
+ },
9100
+ contextWindow: 1050000,
9101
+ maxTokens: 128000,
9102
+ },
8606
9103
  "gpt-realtime-2.1": {
8607
9104
  id: "gpt-realtime-2.1",
8608
9105
  name: "GPT-Realtime-2.1",
@@ -9149,6 +9646,25 @@ export const MODELS = {
9149
9646
  contextWindow: 1000000,
9150
9647
  maxTokens: 384000,
9151
9648
  },
9649
+ "deepseek-v4-flash-vision-exp": {
9650
+ id: "deepseek-v4-flash-vision-exp",
9651
+ name: "DeepSeek V4 Flash Vision Exp",
9652
+ api: "openai-completions",
9653
+ provider: "opencode",
9654
+ baseUrl: "https://opencode.ai/zen/v1",
9655
+ compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
9656
+ reasoning: true,
9657
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
9658
+ input: ["text", "image"],
9659
+ cost: {
9660
+ input: 0.14,
9661
+ output: 0.28,
9662
+ cacheRead: 0.028,
9663
+ cacheWrite: 0,
9664
+ },
9665
+ contextWindow: 1000000,
9666
+ maxTokens: 384000,
9667
+ },
9152
9668
  "deepseek-v4-pro": {
9153
9669
  id: "deepseek-v4-pro",
9154
9670
  name: "DeepSeek V4 Pro",
@@ -9345,6 +9861,40 @@ export const MODELS = {
9345
9861
  contextWindow: 1000000,
9346
9862
  maxTokens: 131072,
9347
9863
  },
9864
+ "glm-5.3": {
9865
+ id: "glm-5.3",
9866
+ name: "GLM-5.3",
9867
+ api: "openai-completions",
9868
+ provider: "opencode",
9869
+ baseUrl: "https://opencode.ai/zen/v1",
9870
+ reasoning: true,
9871
+ input: ["text"],
9872
+ cost: {
9873
+ input: 1.4,
9874
+ output: 4.4,
9875
+ cacheRead: 0.26,
9876
+ cacheWrite: 0,
9877
+ },
9878
+ contextWindow: 1000000,
9879
+ maxTokens: 131072,
9880
+ },
9881
+ "glm-5.3-flash": {
9882
+ id: "glm-5.3-flash",
9883
+ name: "GLM-5.3-Flash",
9884
+ api: "openai-completions",
9885
+ provider: "opencode",
9886
+ baseUrl: "https://opencode.ai/zen/v1",
9887
+ reasoning: true,
9888
+ input: ["text", "image"],
9889
+ cost: {
9890
+ input: 0.15,
9891
+ output: 0.5,
9892
+ cacheRead: 0.03,
9893
+ cacheWrite: 0,
9894
+ },
9895
+ contextWindow: 1000000,
9896
+ maxTokens: 131072,
9897
+ },
9348
9898
  "gpt-5": {
9349
9899
  id: "gpt-5",
9350
9900
  name: "GPT-5",
@@ -9687,6 +10237,23 @@ export const MODELS = {
9687
10237
  contextWindow: 1050000,
9688
10238
  maxTokens: 128000,
9689
10239
  },
10240
+ "gpt-6-astra": {
10241
+ id: "gpt-6-astra",
10242
+ name: "GPT-6 Astra",
10243
+ api: "openai-responses",
10244
+ provider: "opencode",
10245
+ baseUrl: "https://opencode.ai/zen/v1",
10246
+ reasoning: true,
10247
+ input: ["text", "image"],
10248
+ cost: {
10249
+ input: 10,
10250
+ output: 50,
10251
+ cacheRead: 1,
10252
+ cacheWrite: 12.5,
10253
+ },
10254
+ contextWindow: 1050000,
10255
+ maxTokens: 128000,
10256
+ },
9690
10257
  "grok-4.5": {
9691
10258
  id: "grok-4.5",
9692
10259
  name: "Grok 4.5",
@@ -9925,6 +10492,23 @@ export const MODELS = {
9925
10492
  contextWindow: 1048576,
9926
10493
  maxTokens: 131072,
9927
10494
  },
10495
+ "muse-spark-1.3": {
10496
+ id: "muse-spark-1.3",
10497
+ name: "Muse Spark 1.3",
10498
+ api: "openai-responses",
10499
+ provider: "opencode",
10500
+ baseUrl: "https://opencode.ai/zen/v1",
10501
+ reasoning: true,
10502
+ input: ["text", "image"],
10503
+ cost: {
10504
+ input: 1.25,
10505
+ output: 4.25,
10506
+ cacheRead: 0.15,
10507
+ cacheWrite: 0,
10508
+ },
10509
+ contextWindow: 1048576,
10510
+ maxTokens: 131072,
10511
+ },
9928
10512
  "muse-spark-1.3-contributor-free": {
9929
10513
  id: "muse-spark-1.3-contributor-free",
9930
10514
  name: "Muse Spark 1.3 Free",
@@ -10023,9 +10607,9 @@ export const MODELS = {
10023
10607
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
10024
10608
  input: ["text"],
10025
10609
  cost: {
10026
- input: 0.22,
10027
- output: 0.66,
10028
- cacheRead: 0.007,
10610
+ input: 0.15,
10611
+ output: 0.6,
10612
+ cacheRead: 0.003,
10029
10613
  cacheWrite: 0,
10030
10614
  },
10031
10615
  contextWindow: 1000000,
@@ -10042,9 +10626,9 @@ export const MODELS = {
10042
10626
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
10043
10627
  input: ["text", "image"],
10044
10628
  cost: {
10045
- input: 0.22,
10046
- output: 0.66,
10047
- cacheRead: 0.007,
10629
+ input: 0.15,
10630
+ output: 0.6,
10631
+ cacheRead: 0.003,
10048
10632
  cacheWrite: 0,
10049
10633
  },
10050
10634
  contextWindow: 1000000,
@@ -10069,6 +10653,25 @@ export const MODELS = {
10069
10653
  contextWindow: 1000000,
10070
10654
  maxTokens: 384000,
10071
10655
  },
10656
+ "deepseek-v4.1-flash": {
10657
+ id: "deepseek-v4.1-flash",
10658
+ name: "DeepSeek V4.1 Flash",
10659
+ api: "openai-completions",
10660
+ provider: "opencode-go",
10661
+ baseUrl: "https://opencode.ai/zen/go/v1",
10662
+ compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
10663
+ reasoning: true,
10664
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
10665
+ input: ["text", "image"],
10666
+ cost: {
10667
+ input: 0.15,
10668
+ output: 0.6,
10669
+ cacheRead: 0.003,
10670
+ cacheWrite: 0,
10671
+ },
10672
+ contextWindow: 1000000,
10673
+ maxTokens: 384000,
10674
+ },
10072
10675
  "glm-5.1": {
10073
10676
  id: "glm-5.1",
10074
10677
  name: "GLM-5.1",
@@ -10122,16 +10725,16 @@ export const MODELS = {
10122
10725
  },
10123
10726
  "glm-5.3-flash": {
10124
10727
  id: "glm-5.3-flash",
10125
- name: "GLM-5.3-Flash (2x usage)",
10728
+ name: "GLM-5.3-Flash",
10126
10729
  api: "openai-completions",
10127
10730
  provider: "opencode-go",
10128
10731
  baseUrl: "https://opencode.ai/zen/go/v1",
10129
10732
  reasoning: true,
10130
10733
  input: ["text", "image"],
10131
10734
  cost: {
10132
- input: 0.075,
10133
- output: 0.25,
10134
- cacheRead: 0.015,
10735
+ input: 0.15,
10736
+ output: 0.5,
10737
+ cacheRead: 0.03,
10135
10738
  cacheWrite: 0,
10136
10739
  },
10137
10740
  contextWindow: 1000000,
@@ -11265,13 +11868,13 @@ export const MODELS = {
11265
11868
  reasoning: false,
11266
11869
  input: ["text"],
11267
11870
  cost: {
11268
- input: 0.32,
11269
- output: 0.8899999999999999,
11871
+ input: 0.2574,
11872
+ output: 1.0287,
11270
11873
  cacheRead: 0,
11271
11874
  cacheWrite: 0,
11272
11875
  },
11273
11876
  contextWindow: 163840,
11274
- maxTokens: 16384,
11877
+ maxTokens: 16000,
11275
11878
  },
11276
11879
  "deepseek/deepseek-chat-v3-0324": {
11277
11880
  id: "deepseek/deepseek-chat-v3-0324",
@@ -11299,13 +11902,13 @@ export const MODELS = {
11299
11902
  reasoning: true,
11300
11903
  input: ["text"],
11301
11904
  cost: {
11302
- input: 0.55,
11303
- output: 1.6500000000000001,
11304
- cacheRead: 0.55,
11905
+ input: 0.25,
11906
+ output: 0.95,
11907
+ cacheRead: 0.13,
11305
11908
  cacheWrite: 0,
11306
11909
  },
11307
11910
  contextWindow: 163840,
11308
- maxTokens: 144900,
11911
+ maxTokens: 32768,
11309
11912
  },
11310
11913
  "deepseek/deepseek-r1": {
11311
11914
  id: "deepseek/deepseek-r1",
@@ -11403,9 +12006,9 @@ export const MODELS = {
11403
12006
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
11404
12007
  input: ["text"],
11405
12008
  cost: {
11406
- input: 0.07784,
11407
- output: 0.15568,
11408
- cacheRead: 0.015568,
12009
+ input: 0.088606,
12010
+ output: 0.177212,
12011
+ cacheRead: 0.017721200000000003,
11409
12012
  cacheWrite: 0,
11410
12013
  },
11411
12014
  contextWindow: 1048576,
@@ -11441,9 +12044,9 @@ export const MODELS = {
11441
12044
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
11442
12045
  input: ["text"],
11443
12046
  cost: {
11444
- input: 0.14,
11445
- output: 0.28,
11446
- cacheRead: 0.03,
12047
+ input: 0.11,
12048
+ output: 0.33,
12049
+ cacheRead: 0.0035,
11447
12050
  cacheWrite: 0,
11448
12051
  },
11449
12052
  contextWindow: 1048576,
@@ -11466,7 +12069,26 @@ export const MODELS = {
11466
12069
  cacheWrite: 0,
11467
12070
  },
11468
12071
  contextWindow: 1048576,
11469
- maxTokens: 384000,
12072
+ maxTokens: 943718,
12073
+ },
12074
+ "deepseek/deepseek-v4-flash-vision-exp:batch": {
12075
+ id: "deepseek/deepseek-v4-flash-vision-exp:batch",
12076
+ name: "DeepSeek: DeepSeek V4 Flash Vision Exp (batch)",
12077
+ api: "openai-completions",
12078
+ provider: "openrouter",
12079
+ baseUrl: "https://openrouter.ai/api/v1",
12080
+ compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
12081
+ reasoning: true,
12082
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12083
+ input: ["text", "image"],
12084
+ cost: {
12085
+ input: 0.11,
12086
+ output: 0.33,
12087
+ cacheRead: 0.0035,
12088
+ cacheWrite: 0,
12089
+ },
12090
+ contextWindow: 1048576,
12091
+ maxTokens: 943718,
11470
12092
  },
11471
12093
  "deepseek/deepseek-v4-pro": {
11472
12094
  id: "deepseek/deepseek-v4-pro",
@@ -11479,9 +12101,9 @@ export const MODELS = {
11479
12101
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
11480
12102
  input: ["text"],
11481
12103
  cost: {
11482
- input: 1.030776,
11483
- output: 2.061552,
11484
- cacheRead: 0.085898,
12104
+ input: 0.9552599999999999,
12105
+ output: 1.9105199999999998,
12106
+ cacheRead: 0.07960500000000001,
11485
12107
  cacheWrite: 0,
11486
12108
  },
11487
12109
  contextWindow: 1048576,
@@ -11500,11 +12122,11 @@ export const MODELS = {
11500
12122
  cost: {
11501
12123
  input: 0.66,
11502
12124
  output: 1.9800000000000002,
11503
- cacheRead: 0.022,
12125
+ cacheRead: 0.06599999999999999,
11504
12126
  cacheWrite: 0,
11505
12127
  },
11506
12128
  contextWindow: 1048576,
11507
- maxTokens: 384000,
12129
+ maxTokens: 943718,
11508
12130
  },
11509
12131
  "deepseek/deepseek-v4-pro-0813:batch": {
11510
12132
  id: "deepseek/deepseek-v4-pro-0813:batch",
@@ -11517,14 +12139,33 @@ export const MODELS = {
11517
12139
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
11518
12140
  input: ["text"],
11519
12141
  cost: {
11520
- input: 1.32,
11521
- output: 3.9600000000000004,
11522
- cacheRead: 0.13,
12142
+ input: 0.66,
12143
+ output: 1.9800000000000002,
12144
+ cacheRead: 0.022,
11523
12145
  cacheWrite: 0,
11524
12146
  },
11525
12147
  contextWindow: 1048576,
11526
12148
  maxTokens: 943718,
11527
12149
  },
12150
+ "deepseek/deepseek-v4.1-flash": {
12151
+ id: "deepseek/deepseek-v4.1-flash",
12152
+ name: "DeepSeek: DeepSeek V4.1 Flash",
12153
+ api: "openai-completions",
12154
+ provider: "openrouter",
12155
+ baseUrl: "https://openrouter.ai/api/v1",
12156
+ compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
12157
+ reasoning: true,
12158
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12159
+ input: ["text", "image"],
12160
+ cost: {
12161
+ input: 0.15,
12162
+ output: 0.6,
12163
+ cacheRead: 0.003,
12164
+ cacheWrite: 0,
12165
+ },
12166
+ contextWindow: 1048576,
12167
+ maxTokens: 384000,
12168
+ },
11528
12169
  "dots-studio/dots-3-note-preview:free": {
11529
12170
  id: "dots-studio/dots-3-note-preview:free",
11530
12171
  name: "Dots Studio: Dots3-Note Preview (free)",
@@ -12044,13 +12685,13 @@ export const MODELS = {
12044
12685
  reasoning: true,
12045
12686
  input: ["text", "image"],
12046
12687
  cost: {
12047
- input: 0.07,
12048
- output: 0.33999999999999997,
12688
+ input: 0.041999999999999996,
12689
+ output: 0.22,
12049
12690
  cacheRead: 0,
12050
12691
  cacheWrite: 0,
12051
12692
  },
12052
12693
  contextWindow: 262144,
12053
- maxTokens: 16384,
12694
+ maxTokens: 32768,
12054
12695
  },
12055
12696
  "google/gemma-4-26b-a4b-it:free": {
12056
12697
  id: "google/gemma-4-26b-a4b-it:free",
@@ -12120,23 +12761,6 @@ export const MODELS = {
12120
12761
  contextWindow: 262144,
12121
12762
  maxTokens: 32768,
12122
12763
  },
12123
- "ibm-granite/granite-4.1-8b": {
12124
- id: "ibm-granite/granite-4.1-8b",
12125
- name: "IBM: Granite 4.1 8B",
12126
- api: "openai-completions",
12127
- provider: "openrouter",
12128
- baseUrl: "https://openrouter.ai/api/v1",
12129
- reasoning: false,
12130
- input: ["text"],
12131
- cost: {
12132
- input: 0.049999999999999996,
12133
- output: 0.09999999999999999,
12134
- cacheRead: 0.049999999999999996,
12135
- cacheWrite: 0,
12136
- },
12137
- contextWindow: 131072,
12138
- maxTokens: 117964,
12139
- },
12140
12764
  "ibm-granite/granite-4.2-8b": {
12141
12765
  id: "ibm-granite/granite-4.2-8b",
12142
12766
  name: "IBM: Granite 4.2 8B",
@@ -12146,9 +12770,9 @@ export const MODELS = {
12146
12770
  reasoning: true,
12147
12771
  input: ["text"],
12148
12772
  cost: {
12149
- input: 0.09999999999999999,
12150
- output: 0.15,
12151
- cacheRead: 0.049999999999999996,
12773
+ input: 0.06,
12774
+ output: 0.25,
12775
+ cacheRead: 0.015,
12152
12776
  cacheWrite: 0,
12153
12777
  },
12154
12778
  contextWindow: 131072,
@@ -12171,9 +12795,9 @@ export const MODELS = {
12171
12795
  contextWindow: 128000,
12172
12796
  maxTokens: 50000,
12173
12797
  },
12174
- "inception/mercury-2.5-preview": {
12175
- id: "inception/mercury-2.5-preview",
12176
- name: "Inception: Mercury 2.5 Preview",
12798
+ "inception/mercury-2.5": {
12799
+ id: "inception/mercury-2.5",
12800
+ name: "Inception: Mercury 2.5",
12177
12801
  api: "openai-completions",
12178
12802
  provider: "openrouter",
12179
12803
  baseUrl: "https://openrouter.ai/api/v1",
@@ -12190,7 +12814,7 @@ export const MODELS = {
12190
12814
  },
12191
12815
  "inclusionai/ling-3.0-flash": {
12192
12816
  id: "inclusionai/ling-3.0-flash",
12193
- name: "Ling-3.0-flash",
12817
+ name: "inclusionAI: Ling 3.0 Flash",
12194
12818
  api: "openai-completions",
12195
12819
  provider: "openrouter",
12196
12820
  baseUrl: "https://openrouter.ai/api/v1",
@@ -12207,7 +12831,7 @@ export const MODELS = {
12207
12831
  },
12208
12832
  "inclusionai/ling-3.0-flash-fin": {
12209
12833
  id: "inclusionai/ling-3.0-flash-fin",
12210
- name: "Ling 3.0 Flash Fin",
12834
+ name: "inclusionAI: Ling 3.0 Flash Fin",
12211
12835
  api: "openai-completions",
12212
12836
  provider: "openrouter",
12213
12837
  baseUrl: "https://openrouter.ai/api/v1",
@@ -12224,7 +12848,24 @@ export const MODELS = {
12224
12848
  },
12225
12849
  "inclusionai/ling-3.0-flash-fin:free": {
12226
12850
  id: "inclusionai/ling-3.0-flash-fin:free",
12227
- name: "Ling 3.0 Flash Fin (free)",
12851
+ name: "inclusionAI: Ling 3.0 Flash Fin (free)",
12852
+ api: "openai-completions",
12853
+ provider: "openrouter",
12854
+ baseUrl: "https://openrouter.ai/api/v1",
12855
+ reasoning: true,
12856
+ input: ["text"],
12857
+ cost: {
12858
+ input: 0,
12859
+ output: 0,
12860
+ cacheRead: 0,
12861
+ cacheWrite: 0,
12862
+ },
12863
+ contextWindow: 262144,
12864
+ maxTokens: 32768,
12865
+ },
12866
+ "inclusionai/ling-3.0-flash-sante:free": {
12867
+ id: "inclusionai/ling-3.0-flash-sante:free",
12868
+ name: "inclusionAI: Ling 3.0 Flash Sante (free)",
12228
12869
  api: "openai-completions",
12229
12870
  provider: "openrouter",
12230
12871
  baseUrl: "https://openrouter.ai/api/v1",
@@ -12239,6 +12880,23 @@ export const MODELS = {
12239
12880
  contextWindow: 262144,
12240
12881
  maxTokens: 32768,
12241
12882
  },
12883
+ "inclusionai/ling-3.0-flash-vl:free": {
12884
+ id: "inclusionai/ling-3.0-flash-vl:free",
12885
+ name: "inclusionAI: Ling 3.0 Flash VL (free)",
12886
+ api: "openai-completions",
12887
+ provider: "openrouter",
12888
+ baseUrl: "https://openrouter.ai/api/v1",
12889
+ reasoning: true,
12890
+ input: ["text", "image"],
12891
+ cost: {
12892
+ input: 0,
12893
+ output: 0,
12894
+ cacheRead: 0,
12895
+ cacheWrite: 0,
12896
+ },
12897
+ contextWindow: 262144,
12898
+ maxTokens: 32768,
12899
+ },
12242
12900
  "kwaipilot/kat-coder-pro-v2": {
12243
12901
  id: "kwaipilot/kat-coder-pro-v2",
12244
12902
  name: "Kwaipilot: KAT-Coder-Pro V2",
@@ -12416,11 +13074,11 @@ export const MODELS = {
12416
13074
  provider: "openrouter",
12417
13075
  baseUrl: "https://openrouter.ai/api/v1",
12418
13076
  reasoning: true,
12419
- input: ["text", "image"],
12420
- cost: {
12421
- input: 0.35,
12422
- output: 1.5,
12423
- cacheRead: 0.04,
13077
+ input: ["text", "image"],
13078
+ cost: {
13079
+ input: 0.175,
13080
+ output: 0.75,
13081
+ cacheRead: 0.02,
12424
13082
  cacheWrite: 0,
12425
13083
  },
12426
13084
  contextWindow: 131072,
@@ -12571,13 +13229,13 @@ export const MODELS = {
12571
13229
  reasoning: true,
12572
13230
  input: ["text"],
12573
13231
  cost: {
12574
- input: 0.27,
12575
- output: 1.08,
12576
- cacheRead: 0.027,
13232
+ input: 0.3,
13233
+ output: 1.2,
13234
+ cacheRead: 0.03,
12577
13235
  cacheWrite: 0,
12578
13236
  },
12579
13237
  contextWindow: 204800,
12580
- maxTokens: 128000,
13238
+ maxTokens: 131072,
12581
13239
  },
12582
13240
  "minimax/minimax-m2.7": {
12583
13241
  id: "minimax/minimax-m2.7",
@@ -12596,23 +13254,6 @@ export const MODELS = {
12596
13254
  contextWindow: 204800,
12597
13255
  maxTokens: 131072,
12598
13256
  },
12599
- "minimax/minimax-m2.7:free": {
12600
- id: "minimax/minimax-m2.7:free",
12601
- name: "MiniMax: MiniMax M2.7 (free)",
12602
- api: "openai-completions",
12603
- provider: "openrouter",
12604
- baseUrl: "https://openrouter.ai/api/v1",
12605
- reasoning: true,
12606
- input: ["text"],
12607
- cost: {
12608
- input: 0,
12609
- output: 0,
12610
- cacheRead: 0,
12611
- cacheWrite: 0,
12612
- },
12613
- contextWindow: 196608,
12614
- maxTokens: 176947,
12615
- },
12616
13257
  "minimax/minimax-m3": {
12617
13258
  id: "minimax/minimax-m3",
12618
13259
  name: "MiniMax: MiniMax M3",
@@ -12647,35 +13288,35 @@ export const MODELS = {
12647
13288
  contextWindow: 524288,
12648
13289
  maxTokens: 471859,
12649
13290
  },
12650
- "minimax/minimax-m3:free": {
12651
- id: "minimax/minimax-m3:free",
12652
- name: "MiniMax: MiniMax M3 (free)",
13291
+ "mistralai/codestral-2508": {
13292
+ id: "mistralai/codestral-2508",
13293
+ name: "Mistral: Codestral 2508",
12653
13294
  api: "openai-completions",
12654
13295
  provider: "openrouter",
12655
13296
  baseUrl: "https://openrouter.ai/api/v1",
12656
- reasoning: true,
12657
- input: ["text", "image"],
13297
+ reasoning: false,
13298
+ input: ["text"],
12658
13299
  cost: {
12659
- input: 0,
12660
- output: 0,
12661
- cacheRead: 0,
13300
+ input: 0.3,
13301
+ output: 0.8999999999999999,
13302
+ cacheRead: 0.03,
12662
13303
  cacheWrite: 0,
12663
13304
  },
12664
- contextWindow: 1048576,
12665
- maxTokens: 943718,
13305
+ contextWindow: 256000,
13306
+ maxTokens: 204800,
12666
13307
  },
12667
- "mistralai/codestral-2508": {
12668
- id: "mistralai/codestral-2508",
12669
- name: "Mistral: Codestral 2508",
13308
+ "mistralai/codestral-2508:batch": {
13309
+ id: "mistralai/codestral-2508:batch",
13310
+ name: "Mistral: Codestral 2508 (batch)",
12670
13311
  api: "openai-completions",
12671
13312
  provider: "openrouter",
12672
13313
  baseUrl: "https://openrouter.ai/api/v1",
12673
13314
  reasoning: false,
12674
13315
  input: ["text"],
12675
13316
  cost: {
12676
- input: 0.3,
12677
- output: 0.8999999999999999,
12678
- cacheRead: 0.03,
13317
+ input: 0.15,
13318
+ output: 0.44999999999999996,
13319
+ cacheRead: 0.015,
12679
13320
  cacheWrite: 0,
12680
13321
  },
12681
13322
  contextWindow: 256000,
@@ -12749,6 +13390,23 @@ export const MODELS = {
12749
13390
  contextWindow: 262144,
12750
13391
  maxTokens: 209715,
12751
13392
  },
13393
+ "mistralai/ministral-8b-2512:batch": {
13394
+ id: "mistralai/ministral-8b-2512:batch",
13395
+ name: "Mistral: Ministral 3 8B 2512 (batch)",
13396
+ api: "openai-completions",
13397
+ provider: "openrouter",
13398
+ baseUrl: "https://openrouter.ai/api/v1",
13399
+ reasoning: false,
13400
+ input: ["text", "image"],
13401
+ cost: {
13402
+ input: 0.075,
13403
+ output: 0.075,
13404
+ cacheRead: 0.0075,
13405
+ cacheWrite: 0,
13406
+ },
13407
+ contextWindow: 262144,
13408
+ maxTokens: 209715,
13409
+ },
12752
13410
  "mistralai/mistral-large": {
12753
13411
  id: "mistralai/mistral-large",
12754
13412
  name: "Mistral Large",
@@ -12800,6 +13458,23 @@ export const MODELS = {
12800
13458
  contextWindow: 262144,
12801
13459
  maxTokens: 209715,
12802
13460
  },
13461
+ "mistralai/mistral-large-2512:batch": {
13462
+ id: "mistralai/mistral-large-2512:batch",
13463
+ name: "Mistral: Mistral Large 3 2512 (batch)",
13464
+ api: "openai-completions",
13465
+ provider: "openrouter",
13466
+ baseUrl: "https://openrouter.ai/api/v1",
13467
+ reasoning: false,
13468
+ input: ["text", "image"],
13469
+ cost: {
13470
+ input: 0.25,
13471
+ output: 0.75,
13472
+ cacheRead: 0.024999999999999998,
13473
+ cacheWrite: 0,
13474
+ },
13475
+ contextWindow: 262144,
13476
+ maxTokens: 209715,
13477
+ },
12803
13478
  "mistralai/mistral-medium-3": {
12804
13479
  id: "mistralai/mistral-medium-3",
12805
13480
  name: "Mistral: Mistral Medium 3",
@@ -12868,6 +13543,23 @@ export const MODELS = {
12868
13543
  contextWindow: 131072,
12869
13544
  maxTokens: 104857,
12870
13545
  },
13546
+ "mistralai/mistral-medium-3.1:batch": {
13547
+ id: "mistralai/mistral-medium-3.1:batch",
13548
+ name: "Mistral: Mistral Medium 3.1 (batch)",
13549
+ api: "openai-completions",
13550
+ provider: "openrouter",
13551
+ baseUrl: "https://openrouter.ai/api/v1",
13552
+ reasoning: false,
13553
+ input: ["text", "image"],
13554
+ cost: {
13555
+ input: 0.19999999999999998,
13556
+ output: 1,
13557
+ cacheRead: 0.02,
13558
+ cacheWrite: 0,
13559
+ },
13560
+ contextWindow: 131072,
13561
+ maxTokens: 104857,
13562
+ },
12871
13563
  "mistralai/mistral-nemo": {
12872
13564
  id: "mistralai/mistral-nemo",
12873
13565
  name: "Mistral: Mistral Nemo",
@@ -12919,6 +13611,23 @@ export const MODELS = {
12919
13611
  contextWindow: 262144,
12920
13612
  maxTokens: 209715,
12921
13613
  },
13614
+ "mistralai/mistral-small-2603:batch": {
13615
+ id: "mistralai/mistral-small-2603:batch",
13616
+ name: "Mistral: Mistral Small 4 (batch)",
13617
+ api: "openai-completions",
13618
+ provider: "openrouter",
13619
+ baseUrl: "https://openrouter.ai/api/v1",
13620
+ reasoning: true,
13621
+ input: ["text", "image"],
13622
+ cost: {
13623
+ input: 0.075,
13624
+ output: 0.3,
13625
+ cacheRead: 0.0075,
13626
+ cacheWrite: 0,
13627
+ },
13628
+ contextWindow: 262144,
13629
+ maxTokens: 209715,
13630
+ },
12922
13631
  "mistralai/mistral-small-3.2-24b-instruct": {
12923
13632
  id: "mistralai/mistral-small-3.2-24b-instruct",
12924
13633
  name: "Mistral: Mistral Small 3.2 24B",
@@ -13064,9 +13773,9 @@ export const MODELS = {
13064
13773
  reasoning: true,
13065
13774
  input: ["text", "image"],
13066
13775
  cost: {
13067
- input: 0.66,
13068
- output: 3.4,
13069
- cacheRead: 0.18,
13776
+ input: 0.71,
13777
+ output: 3.5,
13778
+ cacheRead: 0.15,
13070
13779
  cacheWrite: 0,
13071
13780
  },
13072
13781
  contextWindow: 262144,
@@ -13081,9 +13790,9 @@ export const MODELS = {
13081
13790
  reasoning: true,
13082
13791
  input: ["text", "image"],
13083
13792
  cost: {
13084
- input: 3,
13085
- output: 15,
13086
- cacheRead: 0.3,
13793
+ input: 2.34,
13794
+ output: 11.7,
13795
+ cacheRead: 0.261,
13087
13796
  cacheWrite: 0,
13088
13797
  },
13089
13798
  contextWindow: 1048576,
@@ -13106,35 +13815,35 @@ export const MODELS = {
13106
13815
  contextWindow: 1048576,
13107
13816
  maxTokens: 943718,
13108
13817
  },
13109
- "nex-agi/nex-n2-mini": {
13110
- id: "nex-agi/nex-n2-mini",
13111
- name: "Nex AGI: Nex-N2-Mini",
13818
+ "nex-agi/nex-n2.5-mini:free": {
13819
+ id: "nex-agi/nex-n2.5-mini:free",
13820
+ name: "Nex AGI: Nex-N2.5-Mini (free)",
13112
13821
  api: "openai-completions",
13113
13822
  provider: "openrouter",
13114
13823
  baseUrl: "https://openrouter.ai/api/v1",
13115
13824
  reasoning: true,
13116
13825
  input: ["text", "image"],
13117
13826
  cost: {
13118
- input: 0.024999999999999998,
13119
- output: 0.09999999999999999,
13120
- cacheRead: 0.0025,
13827
+ input: 0,
13828
+ output: 0,
13829
+ cacheRead: 0,
13121
13830
  cacheWrite: 0,
13122
13831
  },
13123
13832
  contextWindow: 262144,
13124
13833
  maxTokens: 235929,
13125
13834
  },
13126
- "nex-agi/nex-n2-pro": {
13127
- id: "nex-agi/nex-n2-pro",
13128
- name: "Nex AGI: Nex-N2-Pro",
13835
+ "nex-agi/nex-n2.5-pro:free": {
13836
+ id: "nex-agi/nex-n2.5-pro:free",
13837
+ name: "Nex AGI: Nex-N2.5-Pro (free)",
13129
13838
  api: "openai-completions",
13130
13839
  provider: "openrouter",
13131
13840
  baseUrl: "https://openrouter.ai/api/v1",
13132
13841
  reasoning: true,
13133
13842
  input: ["text", "image"],
13134
13843
  cost: {
13135
- input: 0.25,
13136
- output: 1,
13137
- cacheRead: 0.024999999999999998,
13844
+ input: 0,
13845
+ output: 0,
13846
+ cacheRead: 0,
13138
13847
  cacheWrite: 0,
13139
13848
  },
13140
13849
  contextWindow: 262144,
@@ -13188,7 +13897,7 @@ export const MODELS = {
13188
13897
  cacheRead: 0,
13189
13898
  cacheWrite: 0,
13190
13899
  },
13191
- contextWindow: 1000000,
13900
+ contextWindow: 262144,
13192
13901
  maxTokens: 16384,
13193
13902
  },
13194
13903
  "nvidia/nemotron-3-super-120b-a12b:free": {
@@ -13217,13 +13926,13 @@ export const MODELS = {
13217
13926
  reasoning: true,
13218
13927
  input: ["text"],
13219
13928
  cost: {
13220
- input: 0.6,
13221
- output: 2.4,
13222
- cacheRead: 0.12,
13929
+ input: 0.625,
13930
+ output: 3.125,
13931
+ cacheRead: 0.1875,
13223
13932
  cacheWrite: 0,
13224
13933
  },
13225
13934
  contextWindow: 262144,
13226
- maxTokens: 182520,
13935
+ maxTokens: 32768,
13227
13936
  },
13228
13937
  "nvidia/nemotron-3-ultra-550b-a55b:free": {
13229
13938
  id: "nvidia/nemotron-3-ultra-550b-a55b:free",
@@ -14315,6 +15024,74 @@ export const MODELS = {
14315
15024
  contextWindow: 400000,
14316
15025
  maxTokens: 128000,
14317
15026
  },
15027
+ "openai/gpt-6-astra": {
15028
+ id: "openai/gpt-6-astra",
15029
+ name: "OpenAI: GPT-6 Astra",
15030
+ api: "openai-completions",
15031
+ provider: "openrouter",
15032
+ baseUrl: "https://openrouter.ai/api/v1",
15033
+ reasoning: true,
15034
+ input: ["text", "image"],
15035
+ cost: {
15036
+ input: 10,
15037
+ output: 50,
15038
+ cacheRead: 1,
15039
+ cacheWrite: 12.5,
15040
+ },
15041
+ contextWindow: 1050000,
15042
+ maxTokens: 128000,
15043
+ },
15044
+ "openai/gpt-6-astra-pro": {
15045
+ id: "openai/gpt-6-astra-pro",
15046
+ name: "OpenAI: GPT-6 Astra Pro",
15047
+ api: "openai-completions",
15048
+ provider: "openrouter",
15049
+ baseUrl: "https://openrouter.ai/api/v1",
15050
+ reasoning: true,
15051
+ input: ["text", "image"],
15052
+ cost: {
15053
+ input: 10,
15054
+ output: 50,
15055
+ cacheRead: 1,
15056
+ cacheWrite: 12.5,
15057
+ },
15058
+ contextWindow: 1050000,
15059
+ maxTokens: 128000,
15060
+ },
15061
+ "openai/gpt-6-astra-pro:batch": {
15062
+ id: "openai/gpt-6-astra-pro:batch",
15063
+ name: "OpenAI: GPT-6 Astra Pro (batch)",
15064
+ api: "openai-completions",
15065
+ provider: "openrouter",
15066
+ baseUrl: "https://openrouter.ai/api/v1",
15067
+ reasoning: true,
15068
+ input: ["text", "image"],
15069
+ cost: {
15070
+ input: 5,
15071
+ output: 25,
15072
+ cacheRead: 0.5,
15073
+ cacheWrite: 6.25,
15074
+ },
15075
+ contextWindow: 1050000,
15076
+ maxTokens: 128000,
15077
+ },
15078
+ "openai/gpt-6-astra:batch": {
15079
+ id: "openai/gpt-6-astra:batch",
15080
+ name: "OpenAI: GPT-6 Astra (batch)",
15081
+ api: "openai-completions",
15082
+ provider: "openrouter",
15083
+ baseUrl: "https://openrouter.ai/api/v1",
15084
+ reasoning: true,
15085
+ input: ["text", "image"],
15086
+ cost: {
15087
+ input: 5,
15088
+ output: 25,
15089
+ cacheRead: 0.5,
15090
+ cacheWrite: 6.25,
15091
+ },
15092
+ contextWindow: 1050000,
15093
+ maxTokens: 128000,
15094
+ },
14318
15095
  "openai/gpt-audio": {
14319
15096
  id: "openai/gpt-audio",
14320
15097
  name: "OpenAI: GPT Audio",
@@ -14800,13 +15577,13 @@ export const MODELS = {
14800
15577
  reasoning: true,
14801
15578
  input: ["text"],
14802
15579
  cost: {
14803
- input: 0.12,
14804
- output: 0.24,
15580
+ input: 0.22749999999999998,
15581
+ output: 0.9099999999999999,
14805
15582
  cacheRead: 0,
14806
15583
  cacheWrite: 0,
14807
15584
  },
14808
15585
  contextWindow: 131072,
14809
- maxTokens: 16384,
15586
+ maxTokens: 8192,
14810
15587
  },
14811
15588
  "qwen/qwen3-235b-a22b": {
14812
15589
  id: "qwen/qwen3-235b-a22b",
@@ -14834,13 +15611,13 @@ export const MODELS = {
14834
15611
  reasoning: false,
14835
15612
  input: ["text"],
14836
15613
  cost: {
14837
- input: 0.0875,
14838
- output: 0.35,
14839
- cacheRead: 0.0175,
15614
+ input: 0.22,
15615
+ output: 0.88,
15616
+ cacheRead: 0,
14840
15617
  cacheWrite: 0,
14841
15618
  },
14842
15619
  contextWindow: 262144,
14843
- maxTokens: 235929,
15620
+ maxTokens: 16384,
14844
15621
  },
14845
15622
  "qwen/qwen3-235b-a22b-thinking-2507": {
14846
15623
  id: "qwen/qwen3-235b-a22b-thinking-2507",
@@ -14885,13 +15662,13 @@ export const MODELS = {
14885
15662
  reasoning: false,
14886
15663
  input: ["text"],
14887
15664
  cost: {
14888
- input: 0.04815,
14889
- output: 0.19305,
15665
+ input: 0.09,
15666
+ output: 0.3,
14890
15667
  cacheRead: 0,
14891
15668
  cacheWrite: 0,
14892
15669
  },
14893
15670
  contextWindow: 262144,
14894
- maxTokens: 32000,
15671
+ maxTokens: 235929,
14895
15672
  },
14896
15673
  "qwen/qwen3-30b-a3b-thinking-2507": {
14897
15674
  id: "qwen/qwen3-30b-a3b-thinking-2507",
@@ -15072,13 +15849,13 @@ export const MODELS = {
15072
15849
  reasoning: false,
15073
15850
  input: ["text"],
15074
15851
  cost: {
15075
- input: 0.09999999999999999,
15852
+ input: 0.09,
15076
15853
  output: 1.1,
15077
- cacheRead: 0.07,
15854
+ cacheRead: 0,
15078
15855
  cacheWrite: 0,
15079
15856
  },
15080
15857
  contextWindow: 262144,
15081
- maxTokens: 235929,
15858
+ maxTokens: 16384,
15082
15859
  },
15083
15860
  "qwen/qwen3-next-80b-a3b-thinking": {
15084
15861
  id: "qwen/qwen3-next-80b-a3b-thinking",
@@ -15095,7 +15872,7 @@ export const MODELS = {
15095
15872
  cacheWrite: 0,
15096
15873
  },
15097
15874
  contextWindow: 262144,
15098
- maxTokens: 32768,
15875
+ maxTokens: 235929,
15099
15876
  },
15100
15877
  "qwen/qwen3-vl-235b-a22b-instruct": {
15101
15878
  id: "qwen/qwen3-vl-235b-a22b-instruct",
@@ -15225,13 +16002,13 @@ export const MODELS = {
15225
16002
  reasoning: true,
15226
16003
  input: ["text", "image"],
15227
16004
  cost: {
15228
- input: 0.29,
15229
- output: 2.4,
16005
+ input: 0.26,
16006
+ output: 2.08,
15230
16007
  cacheRead: 0,
15231
16008
  cacheWrite: 0,
15232
16009
  },
15233
16010
  contextWindow: 262144,
15234
- maxTokens: 81920,
16011
+ maxTokens: 65536,
15235
16012
  },
15236
16013
  "qwen/qwen3.5-27b": {
15237
16014
  id: "qwen/qwen3.5-27b",
@@ -15259,13 +16036,13 @@ export const MODELS = {
15259
16036
  reasoning: true,
15260
16037
  input: ["text", "image"],
15261
16038
  cost: {
15262
- input: 0.25,
16039
+ input: 0.3125,
15263
16040
  output: 1.25,
15264
- cacheRead: 0.25,
16041
+ cacheRead: 0.15625,
15265
16042
  cacheWrite: 0,
15266
16043
  },
15267
16044
  contextWindow: 262144,
15268
- maxTokens: 235929,
16045
+ maxTokens: 16384,
15269
16046
  },
15270
16047
  "qwen/qwen3.5-397b-a17b": {
15271
16048
  id: "qwen/qwen3.5-397b-a17b",
@@ -15378,13 +16155,13 @@ export const MODELS = {
15378
16155
  reasoning: true,
15379
16156
  input: ["text", "image"],
15380
16157
  cost: {
15381
- input: 0.6,
15382
- output: 3.5999999999999996,
15383
- cacheRead: 0.12,
16158
+ input: 0.3,
16159
+ output: 2,
16160
+ cacheRead: 0.03,
15384
16161
  cacheWrite: 0,
15385
16162
  },
15386
16163
  contextWindow: 262144,
15387
- maxTokens: 235929,
16164
+ maxTokens: 65536,
15388
16165
  },
15389
16166
  "qwen/qwen3.6-35b-a3b": {
15390
16167
  id: "qwen/qwen3.6-35b-a3b",
@@ -15520,7 +16297,7 @@ export const MODELS = {
15520
16297
  cacheWrite: 0,
15521
16298
  },
15522
16299
  contextWindow: 1048576,
15523
- maxTokens: 262144,
16300
+ maxTokens: 131072,
15524
16301
  },
15525
16302
  "qwen/qwen3.8-2.4t-a95b:batch": {
15526
16303
  id: "qwen/qwen3.8-2.4t-a95b:batch",
@@ -15573,9 +16350,9 @@ export const MODELS = {
15573
16350
  contextWindow: 1000000,
15574
16351
  maxTokens: 131072,
15575
16352
  },
15576
- "qwen/qwen3.8-max": {
15577
- id: "qwen/qwen3.8-max",
15578
- name: "Qwen: Qwen3.8 Max",
16353
+ "qwen/qwen3.8-max-0902": {
16354
+ id: "qwen/qwen3.8-max-0902",
16355
+ name: "Qwen: Qwen3.8 Max (0902)",
15579
16356
  api: "openai-completions",
15580
16357
  provider: "openrouter",
15581
16358
  baseUrl: "https://openrouter.ai/api/v1",
@@ -15621,12 +16398,46 @@ export const MODELS = {
15621
16398
  cacheRead: 0,
15622
16399
  cacheWrite: 0,
15623
16400
  },
15624
- contextWindow: 256000,
16401
+ contextWindow: 256000,
16402
+ maxTokens: 128000,
16403
+ },
16404
+ "sakana/fugu-max": {
16405
+ id: "sakana/fugu-max",
16406
+ name: "Sakana: Fugu Max",
16407
+ api: "openai-completions",
16408
+ provider: "openrouter",
16409
+ baseUrl: "https://openrouter.ai/api/v1",
16410
+ reasoning: true,
16411
+ input: ["text", "image"],
16412
+ cost: {
16413
+ input: 2,
16414
+ output: 6,
16415
+ cacheRead: 0.25,
16416
+ cacheWrite: 0,
16417
+ },
16418
+ contextWindow: 1000000,
16419
+ maxTokens: 128000,
16420
+ },
16421
+ "sakana/fugu-ultra": {
16422
+ id: "sakana/fugu-ultra",
16423
+ name: "Sakana: Fugu Ultra",
16424
+ api: "openai-completions",
16425
+ provider: "openrouter",
16426
+ baseUrl: "https://openrouter.ai/api/v1",
16427
+ reasoning: true,
16428
+ input: ["text", "image"],
16429
+ cost: {
16430
+ input: 5,
16431
+ output: 30,
16432
+ cacheRead: 0.5,
16433
+ cacheWrite: 0,
16434
+ },
16435
+ contextWindow: 1000000,
15625
16436
  maxTokens: 128000,
15626
16437
  },
15627
- "sakana/fugu-ultra": {
15628
- id: "sakana/fugu-ultra",
15629
- name: "Sakana: Fugu Ultra",
16438
+ "sakana/fugu-ultra-v2": {
16439
+ id: "sakana/fugu-ultra-v2",
16440
+ name: "Sakana: Fugu Ultra v2",
15630
16441
  api: "openai-completions",
15631
16442
  provider: "openrouter",
15632
16443
  baseUrl: "https://openrouter.ai/api/v1",
@@ -15718,9 +16529,9 @@ export const MODELS = {
15718
16529
  reasoning: true,
15719
16530
  input: ["text"],
15720
16531
  cost: {
15721
- input: 0.0825,
15722
- output: 0.33,
15723
- cacheRead: 0.020625,
16532
+ input: 0.13199999999999998,
16533
+ output: 0.5279999999999999,
16534
+ cacheRead: 0.032999999999999995,
15724
16535
  cacheWrite: 0,
15725
16536
  },
15726
16537
  contextWindow: 262144,
@@ -15758,7 +16569,7 @@ export const MODELS = {
15758
16569
  cacheWrite: 0,
15759
16570
  },
15760
16571
  contextWindow: 1024000,
15761
- maxTokens: 26214,
16572
+ maxTokens: 819200,
15762
16573
  },
15763
16574
  "thinkingmachines/inkling": {
15764
16575
  id: "thinkingmachines/inkling",
@@ -15775,7 +16586,7 @@ export const MODELS = {
15775
16586
  cacheWrite: 0,
15776
16587
  },
15777
16588
  contextWindow: 1048576,
15778
- maxTokens: 471859,
16589
+ maxTokens: 32768,
15779
16590
  },
15780
16591
  "thinkingmachines/inkling-small": {
15781
16592
  id: "thinkingmachines/inkling-small",
@@ -15888,9 +16699,9 @@ export const MODELS = {
15888
16699
  reasoning: true,
15889
16700
  input: ["text"],
15890
16701
  cost: {
15891
- input: 0.03,
15892
- output: 0.12,
15893
- cacheRead: 0.006,
16702
+ input: 0.09,
16703
+ output: 0.36,
16704
+ cacheRead: 0.018,
15894
16705
  cacheWrite: 0,
15895
16706
  },
15896
16707
  contextWindow: 524288,
@@ -15930,6 +16741,23 @@ export const MODELS = {
15930
16741
  contextWindow: 1000000,
15931
16742
  maxTokens: 900000,
15932
16743
  },
16744
+ "x-ai/grok-4.3:batch": {
16745
+ id: "x-ai/grok-4.3:batch",
16746
+ name: "SpaceXAI: Grok 4.3 (batch)",
16747
+ api: "openai-completions",
16748
+ provider: "openrouter",
16749
+ baseUrl: "https://openrouter.ai/api/v1",
16750
+ reasoning: true,
16751
+ input: ["text", "image"],
16752
+ cost: {
16753
+ input: 1,
16754
+ output: 2,
16755
+ cacheRead: 0.16,
16756
+ cacheWrite: 0,
16757
+ },
16758
+ contextWindow: 1000000,
16759
+ maxTokens: 900000,
16760
+ },
15933
16761
  "x-ai/grok-4.5": {
15934
16762
  id: "x-ai/grok-4.5",
15935
16763
  name: "SpaceXAI: Grok 4.5",
@@ -16075,13 +16903,13 @@ export const MODELS = {
16075
16903
  reasoning: true,
16076
16904
  input: ["text"],
16077
16905
  cost: {
16078
- input: 0.55,
16079
- output: 2.2,
16080
- cacheRead: 0.11,
16906
+ input: 0.43,
16907
+ output: 1.75,
16908
+ cacheRead: 0.08,
16081
16909
  cacheWrite: 0,
16082
16910
  },
16083
16911
  contextWindow: 204800,
16084
- maxTokens: 131072,
16912
+ maxTokens: 16384,
16085
16913
  },
16086
16914
  "z-ai/glm-4.6v": {
16087
16915
  id: "z-ai/glm-4.6v",
@@ -16126,13 +16954,13 @@ export const MODELS = {
16126
16954
  reasoning: true,
16127
16955
  input: ["text"],
16128
16956
  cost: {
16129
- input: 0.06,
16957
+ input: 0.060500000000000005,
16130
16958
  output: 0.39999999999999997,
16131
- cacheRead: 0.01,
16959
+ cacheRead: 0,
16132
16960
  cacheWrite: 0,
16133
16961
  },
16134
- contextWindow: 202752,
16135
- maxTokens: 16384,
16962
+ contextWindow: 200000,
16963
+ maxTokens: 117964,
16136
16964
  },
16137
16965
  "z-ai/glm-5": {
16138
16966
  id: "z-ai/glm-5",
@@ -16202,22 +17030,22 @@ export const MODELS = {
16202
17030
  contextWindow: 1048576,
16203
17031
  maxTokens: 131072,
16204
17032
  },
16205
- "z-ai/glm-5.2:free": {
16206
- id: "z-ai/glm-5.2:free",
16207
- name: "Z.ai: GLM 5.2 (free)",
17033
+ "z-ai/glm-5.2:batch": {
17034
+ id: "z-ai/glm-5.2:batch",
17035
+ name: "Z.ai: GLM 5.2 (batch)",
16208
17036
  api: "openai-completions",
16209
17037
  provider: "openrouter",
16210
17038
  baseUrl: "https://openrouter.ai/api/v1",
16211
17039
  reasoning: true,
16212
17040
  input: ["text"],
16213
17041
  cost: {
16214
- input: 0,
16215
- output: 0,
16216
- cacheRead: 0,
17042
+ input: 0.7,
17043
+ output: 2.2,
17044
+ cacheRead: 0.07,
16217
17045
  cacheWrite: 0,
16218
17046
  },
16219
- contextWindow: 256000,
16220
- maxTokens: 230400,
17047
+ contextWindow: 1048576,
17048
+ maxTokens: 943718,
16221
17049
  },
16222
17050
  "z-ai/glm-5.3": {
16223
17051
  id: "z-ai/glm-5.3",
@@ -16230,11 +17058,11 @@ export const MODELS = {
16230
17058
  cost: {
16231
17059
  input: 1.4,
16232
17060
  output: 4.4,
16233
- cacheRead: 0.14,
17061
+ cacheRead: 0.26,
16234
17062
  cacheWrite: 0,
16235
17063
  },
16236
17064
  contextWindow: 1310720,
16237
- maxTokens: 262144,
17065
+ maxTokens: 943718,
16238
17066
  },
16239
17067
  "z-ai/glm-5.3-flash": {
16240
17068
  id: "z-ai/glm-5.3-flash",
@@ -16245,9 +17073,9 @@ export const MODELS = {
16245
17073
  reasoning: true,
16246
17074
  input: ["text", "image"],
16247
17075
  cost: {
16248
- input: 0.075,
16249
- output: 0.25,
16250
- cacheRead: 0.015,
17076
+ input: 0.15,
17077
+ output: 0.5,
17078
+ cacheRead: 0.03,
16251
17079
  cacheWrite: 0,
16252
17080
  },
16253
17081
  contextWindow: 1310720,
@@ -16262,13 +17090,30 @@ export const MODELS = {
16262
17090
  reasoning: true,
16263
17091
  input: ["text", "image"],
16264
17092
  cost: {
16265
- input: 0.15,
16266
- output: 0.5,
16267
- cacheRead: 0.03,
17093
+ input: 0.075,
17094
+ output: 0.25,
17095
+ cacheRead: 0.015,
16268
17096
  cacheWrite: 0,
16269
17097
  },
16270
- contextWindow: 1048575,
16271
- maxTokens: 943717,
17098
+ contextWindow: 1048576,
17099
+ maxTokens: 943718,
17100
+ },
17101
+ "z-ai/glm-5.3:batch": {
17102
+ id: "z-ai/glm-5.3:batch",
17103
+ name: "Z.ai: GLM 5.3 (batch)",
17104
+ api: "openai-completions",
17105
+ provider: "openrouter",
17106
+ baseUrl: "https://openrouter.ai/api/v1",
17107
+ reasoning: true,
17108
+ input: ["text"],
17109
+ cost: {
17110
+ input: 0.7,
17111
+ output: 2.2,
17112
+ cacheRead: 0.13,
17113
+ cacheWrite: 0,
17114
+ },
17115
+ contextWindow: 1048576,
17116
+ maxTokens: 943718,
16272
17117
  },
16273
17118
  "z-ai/glm-5v-turbo": {
16274
17119
  id: "z-ai/glm-5v-turbo",
@@ -16418,9 +17263,9 @@ export const MODELS = {
16418
17263
  reasoning: true,
16419
17264
  input: ["text", "image"],
16420
17265
  cost: {
16421
- input: 2.5,
16422
- output: 14,
16423
- cacheRead: 0.29,
17266
+ input: 2.34,
17267
+ output: 11.7,
17268
+ cacheRead: 0.261,
16424
17269
  cacheWrite: 0,
16425
17270
  },
16426
17271
  contextWindow: 1048576,
@@ -16486,9 +17331,9 @@ export const MODELS = {
16486
17331
  reasoning: true,
16487
17332
  input: ["text", "image"],
16488
17333
  cost: {
16489
- input: 0.07125000000000001,
16490
- output: 0.2375,
16491
- cacheRead: 0.01425,
17334
+ input: 0.075,
17335
+ output: 0.25,
17336
+ cacheRead: 0.015,
16492
17337
  cacheWrite: 0,
16493
17338
  },
16494
17339
  contextWindow: 1310720,
@@ -16503,9 +17348,9 @@ export const MODELS = {
16503
17348
  reasoning: true,
16504
17349
  input: ["text"],
16505
17350
  cost: {
16506
- input: 1.1480000000000001,
16507
- output: 3.608,
16508
- cacheRead: 0.18860000000000002,
17351
+ input: 0.9700000000000001,
17352
+ output: 3.3077,
17353
+ cacheRead: 0.19399999999999998,
16509
17354
  cacheWrite: 0,
16510
17355
  },
16511
17356
  contextWindow: 1310720,
@@ -17387,23 +18232,6 @@ export const MODELS = {
17387
18232
  contextWindow: 991000,
17388
18233
  maxTokens: 128000,
17389
18234
  },
17390
- "alibaba/qwen3.8-flash-next": {
17391
- id: "alibaba/qwen3.8-flash-next",
17392
- name: "Qwen 3.8 Flash Next",
17393
- api: "anthropic-messages",
17394
- provider: "vercel-ai-gateway",
17395
- baseUrl: "https://ai-gateway.vercel.sh",
17396
- reasoning: true,
17397
- input: ["text", "image"],
17398
- cost: {
17399
- input: 0.12,
17400
- output: 0.39999999999999997,
17401
- cacheRead: 0.01,
17402
- cacheWrite: 0,
17403
- },
17404
- contextWindow: 1048576,
17405
- maxTokens: 1048576,
17406
- },
17407
18235
  "alibaba/qwen3.8-max": {
17408
18236
  id: "alibaba/qwen3.8-max",
17409
18237
  name: "Qwen 3.8 Max",
@@ -17912,9 +18740,9 @@ export const MODELS = {
17912
18740
  reasoning: false,
17913
18741
  input: ["text"],
17914
18742
  cost: {
17915
- input: 0.28,
17916
- output: 0.42,
17917
- cacheRead: 0.028,
18743
+ input: 0.62,
18744
+ output: 1.85,
18745
+ cacheRead: 0,
17918
18746
  cacheWrite: 0,
17919
18747
  },
17920
18748
  contextWindow: 128000,
@@ -18022,6 +18850,23 @@ export const MODELS = {
18022
18850
  contextWindow: 1000000,
18023
18851
  maxTokens: 384000,
18024
18852
  },
18853
+ "deepseek/deepseek-v4.1-flash": {
18854
+ id: "deepseek/deepseek-v4.1-flash",
18855
+ name: "DeepSeek V4.1 Flash",
18856
+ api: "anthropic-messages",
18857
+ provider: "vercel-ai-gateway",
18858
+ baseUrl: "https://ai-gateway.vercel.sh",
18859
+ reasoning: true,
18860
+ input: ["text", "image"],
18861
+ cost: {
18862
+ input: 0.3,
18863
+ output: 1.2,
18864
+ cacheRead: 0.03,
18865
+ cacheWrite: 0,
18866
+ },
18867
+ contextWindow: 1048576,
18868
+ maxTokens: 32768,
18869
+ },
18025
18870
  "google/gemini-2.5-flash": {
18026
18871
  id: "google/gemini-2.5-flash",
18027
18872
  name: "Gemini 2.5 Flash",
@@ -18260,6 +19105,23 @@ export const MODELS = {
18260
19105
  contextWindow: 128000,
18261
19106
  maxTokens: 128000,
18262
19107
  },
19108
+ "inception/mercury-2.5": {
19109
+ id: "inception/mercury-2.5",
19110
+ name: "Mercury 2.5",
19111
+ api: "anthropic-messages",
19112
+ provider: "vercel-ai-gateway",
19113
+ baseUrl: "https://ai-gateway.vercel.sh",
19114
+ reasoning: true,
19115
+ input: ["text"],
19116
+ cost: {
19117
+ input: 0.04,
19118
+ output: 0.15,
19119
+ cacheRead: 0.004,
19120
+ cacheWrite: 0,
19121
+ },
19122
+ contextWindow: 260000,
19123
+ maxTokens: 65536,
19124
+ },
18263
19125
  "inception/mercury-coder-small": {
18264
19126
  id: "inception/mercury-coder-small",
18265
19127
  name: "Mercury Coder Small Beta",
@@ -18328,6 +19190,40 @@ export const MODELS = {
18328
19190
  contextWindow: 256000,
18329
19191
  maxTokens: 32000,
18330
19192
  },
19193
+ "inclusionai/ling-3.0-flash-sante": {
19194
+ id: "inclusionai/ling-3.0-flash-sante",
19195
+ name: "Ling 3.0 Flash Sante",
19196
+ api: "anthropic-messages",
19197
+ provider: "vercel-ai-gateway",
19198
+ baseUrl: "https://ai-gateway.vercel.sh",
19199
+ reasoning: true,
19200
+ input: ["text"],
19201
+ cost: {
19202
+ input: 0,
19203
+ output: 0,
19204
+ cacheRead: 0,
19205
+ cacheWrite: 0,
19206
+ },
19207
+ contextWindow: 256000,
19208
+ maxTokens: 32000,
19209
+ },
19210
+ "inclusionai/ling-3.0-flash-sante-free": {
19211
+ id: "inclusionai/ling-3.0-flash-sante-free",
19212
+ name: "Ling 3.0 Flash Sante (Free)",
19213
+ api: "anthropic-messages",
19214
+ provider: "vercel-ai-gateway",
19215
+ baseUrl: "https://ai-gateway.vercel.sh",
19216
+ reasoning: true,
19217
+ input: ["text"],
19218
+ cost: {
19219
+ input: 0,
19220
+ output: 0,
19221
+ cacheRead: 0,
19222
+ cacheWrite: 0,
19223
+ },
19224
+ contextWindow: 256000,
19225
+ maxTokens: 32000,
19226
+ },
18331
19227
  "interfaze/interfaze-beta": {
18332
19228
  id: "interfaze/interfaze-beta",
18333
19229
  name: "Interfaze Beta",
@@ -18702,23 +19598,6 @@ export const MODELS = {
18702
19598
  contextWindow: 204800,
18703
19599
  maxTokens: 131000,
18704
19600
  },
18705
- "minimax/minimax-m2.7-free": {
18706
- id: "minimax/minimax-m2.7-free",
18707
- name: "MiniMax M2.7 (Free)",
18708
- api: "anthropic-messages",
18709
- provider: "vercel-ai-gateway",
18710
- baseUrl: "https://ai-gateway.vercel.sh",
18711
- reasoning: true,
18712
- input: ["text"],
18713
- cost: {
18714
- input: 0,
18715
- output: 0,
18716
- cacheRead: 0,
18717
- cacheWrite: 0,
18718
- },
18719
- contextWindow: 196608,
18720
- maxTokens: 196608,
18721
- },
18722
19601
  "minimax/minimax-m2.7-highspeed": {
18723
19602
  id: "minimax/minimax-m2.7-highspeed",
18724
19603
  name: "MiniMax M2.7 High Speed",
@@ -18753,23 +19632,6 @@ export const MODELS = {
18753
19632
  contextWindow: 512000,
18754
19633
  maxTokens: 512000,
18755
19634
  },
18756
- "minimax/minimax-m3-free": {
18757
- id: "minimax/minimax-m3-free",
18758
- name: "MiniMax M3 (Free)",
18759
- api: "anthropic-messages",
18760
- provider: "vercel-ai-gateway",
18761
- baseUrl: "https://ai-gateway.vercel.sh",
18762
- reasoning: true,
18763
- input: ["text", "image"],
18764
- cost: {
18765
- input: 0,
18766
- output: 0,
18767
- cacheRead: 0,
18768
- cacheWrite: 0,
18769
- },
18770
- contextWindow: 1048576,
18771
- maxTokens: 1048576,
18772
- },
18773
19635
  "mistral/codestral": {
18774
19636
  id: "mistral/codestral",
18775
19637
  name: "Mistral Codestral",
@@ -19902,7 +20764,7 @@ export const MODELS = {
19902
20764
  input: 0.39999999999999997,
19903
20765
  output: 2.4,
19904
20766
  cacheRead: 0.04,
19905
- cacheWrite: 0.25,
20767
+ cacheWrite: 0.5,
19906
20768
  },
19907
20769
  contextWindow: 1050000,
19908
20770
  maxTokens: 128000,
@@ -19936,7 +20798,7 @@ export const MODELS = {
19936
20798
  input: 4,
19937
20799
  output: 20,
19938
20800
  cacheRead: 0.39999999999999997,
19939
- cacheWrite: 2.5,
20801
+ cacheWrite: 5,
19940
20802
  },
19941
20803
  contextWindow: 1050000,
19942
20804
  maxTokens: 128000,
@@ -19970,7 +20832,41 @@ export const MODELS = {
19970
20832
  input: 4,
19971
20833
  output: 24,
19972
20834
  cacheRead: 0.39999999999999997,
19973
- cacheWrite: 2.5,
20835
+ cacheWrite: 5,
20836
+ },
20837
+ contextWindow: 1050000,
20838
+ maxTokens: 128000,
20839
+ },
20840
+ "openai/gpt-6-astra": {
20841
+ id: "openai/gpt-6-astra",
20842
+ name: "GPT-6 Astra",
20843
+ api: "anthropic-messages",
20844
+ provider: "vercel-ai-gateway",
20845
+ baseUrl: "https://ai-gateway.vercel.sh",
20846
+ reasoning: true,
20847
+ input: ["text", "image"],
20848
+ cost: {
20849
+ input: 10,
20850
+ output: 50,
20851
+ cacheRead: 1,
20852
+ cacheWrite: 12.5,
20853
+ },
20854
+ contextWindow: 1050000,
20855
+ maxTokens: 128000,
20856
+ },
20857
+ "openai/gpt-6-astra-fast": {
20858
+ id: "openai/gpt-6-astra-fast",
20859
+ name: "GPT-6 Astra (Fast)",
20860
+ api: "anthropic-messages",
20861
+ provider: "vercel-ai-gateway",
20862
+ baseUrl: "https://ai-gateway.vercel.sh",
20863
+ reasoning: true,
20864
+ input: ["text", "image"],
20865
+ cost: {
20866
+ input: 20,
20867
+ output: 100,
20868
+ cacheRead: 2,
20869
+ cacheWrite: 25,
19974
20870
  },
19975
20871
  contextWindow: 1050000,
19976
20872
  maxTokens: 128000,
@@ -20570,23 +21466,6 @@ export const MODELS = {
20570
21466
  contextWindow: 1050000,
20571
21467
  maxTokens: 131000,
20572
21468
  },
20573
- "xiaomi/mimo-v2.5-pro-ultraspeed": {
20574
- id: "xiaomi/mimo-v2.5-pro-ultraspeed",
20575
- name: "MiMo V2.5 Pro UltraSpeed",
20576
- api: "anthropic-messages",
20577
- provider: "vercel-ai-gateway",
20578
- baseUrl: "https://ai-gateway.vercel.sh",
20579
- reasoning: true,
20580
- input: ["text"],
20581
- cost: {
20582
- input: 1.305,
20583
- output: 2.61,
20584
- cacheRead: 0.0108,
20585
- cacheWrite: 0,
20586
- },
20587
- contextWindow: 1048576,
20588
- maxTokens: 131072,
20589
- },
20590
21469
  "zai/glm-4.5": {
20591
21470
  id: "zai/glm-4.5",
20592
21471
  name: "GLM 4.5",
@@ -20800,9 +21679,9 @@ export const MODELS = {
20800
21679
  reasoning: true,
20801
21680
  input: ["text"],
20802
21681
  cost: {
20803
- input: 0.7,
20804
- output: 2.2,
20805
- cacheRead: 0.13,
21682
+ input: 1.4,
21683
+ output: 4.4,
21684
+ cacheRead: 0.14,
20806
21685
  cacheWrite: 0,
20807
21686
  },
20808
21687
  contextWindow: 1000000,
@@ -20842,23 +21721,6 @@ export const MODELS = {
20842
21721
  contextWindow: 1000000,
20843
21722
  maxTokens: 131000,
20844
21723
  },
20845
- "zai/glm-5.3-promo-50": {
20846
- id: "zai/glm-5.3-promo-50",
20847
- name: "GLM 5.3 (50% off)",
20848
- api: "anthropic-messages",
20849
- provider: "vercel-ai-gateway",
20850
- baseUrl: "https://ai-gateway.vercel.sh",
20851
- reasoning: true,
20852
- input: ["text"],
20853
- cost: {
20854
- input: 0.7,
20855
- output: 2.2,
20856
- cacheRead: 0.13,
20857
- cacheWrite: 0,
20858
- },
20859
- contextWindow: 1048576,
20860
- maxTokens: 1048576,
20861
- },
20862
21724
  "zai/glm-5v-turbo": {
20863
21725
  id: "zai/glm-5v-turbo",
20864
21726
  name: "GLM 5V Turbo",