@elyracode/ai 0.9.40 → 0.9.42

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -237,6 +237,24 @@ export const MODELS = {
237
237
  contextWindow: 1000000,
238
238
  maxTokens: 128000,
239
239
  },
240
+ "anthropic.claude-opus-5-5": {
241
+ id: "anthropic.claude-opus-5-5",
242
+ name: "Claude Opus 5.5",
243
+ api: "bedrock-converse-stream",
244
+ provider: "amazon-bedrock",
245
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
246
+ reasoning: true,
247
+ thinkingType: "adaptive",
248
+ input: ["text", "image"],
249
+ cost: {
250
+ input: 4,
251
+ output: 20,
252
+ cacheRead: 0.2,
253
+ cacheWrite: 5,
254
+ },
255
+ contextWindow: 1000000,
256
+ maxTokens: 128000,
257
+ },
240
258
  "anthropic.claude-sonnet-4-5-20250929-v1:0": {
241
259
  id: "anthropic.claude-sonnet-4-5-20250929-v1:0",
242
260
  name: "Claude Sonnet 4.5",
@@ -453,6 +471,24 @@ export const MODELS = {
453
471
  contextWindow: 1000000,
454
472
  maxTokens: 128000,
455
473
  },
474
+ "au.anthropic.claude-opus-5-5": {
475
+ id: "au.anthropic.claude-opus-5-5",
476
+ name: "Claude Opus 5.5 (AU)",
477
+ api: "bedrock-converse-stream",
478
+ provider: "amazon-bedrock",
479
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
480
+ reasoning: true,
481
+ thinkingType: "adaptive",
482
+ input: ["text", "image"],
483
+ cost: {
484
+ input: 4.4,
485
+ output: 22,
486
+ cacheRead: 0.22,
487
+ cacheWrite: 5.5,
488
+ },
489
+ contextWindow: 1000000,
490
+ maxTokens: 128000,
491
+ },
456
492
  "au.anthropic.claude-sonnet-4-5-20250929-v1:0": {
457
493
  id: "au.anthropic.claude-sonnet-4-5-20250929-v1:0",
458
494
  name: "Claude Sonnet 4.5 (AU)",
@@ -756,6 +792,24 @@ export const MODELS = {
756
792
  contextWindow: 1000000,
757
793
  maxTokens: 128000,
758
794
  },
795
+ "eu.anthropic.claude-opus-5-5": {
796
+ id: "eu.anthropic.claude-opus-5-5",
797
+ name: "Claude Opus 5.5 (EU)",
798
+ api: "bedrock-converse-stream",
799
+ provider: "amazon-bedrock",
800
+ baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
801
+ reasoning: true,
802
+ thinkingType: "adaptive",
803
+ input: ["text", "image"],
804
+ cost: {
805
+ input: 4.4,
806
+ output: 22,
807
+ cacheRead: 0.22,
808
+ cacheWrite: 5.5,
809
+ },
810
+ contextWindow: 1000000,
811
+ maxTokens: 128000,
812
+ },
759
813
  "eu.anthropic.claude-sonnet-4-20250514-v1:0": {
760
814
  id: "eu.anthropic.claude-sonnet-4-20250514-v1:0",
761
815
  name: "Claude Sonnet 4 (EU)",
@@ -1011,6 +1065,24 @@ export const MODELS = {
1011
1065
  contextWindow: 1000000,
1012
1066
  maxTokens: 128000,
1013
1067
  },
1068
+ "global.anthropic.claude-opus-5-5": {
1069
+ id: "global.anthropic.claude-opus-5-5",
1070
+ name: "Claude Opus 5.5 (Global)",
1071
+ api: "bedrock-converse-stream",
1072
+ provider: "amazon-bedrock",
1073
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1074
+ reasoning: true,
1075
+ thinkingType: "adaptive",
1076
+ input: ["text", "image"],
1077
+ cost: {
1078
+ input: 4,
1079
+ output: 20,
1080
+ cacheRead: 0.2,
1081
+ cacheWrite: 5,
1082
+ },
1083
+ contextWindow: 1000000,
1084
+ maxTokens: 128000,
1085
+ },
1014
1086
  "global.anthropic.claude-sonnet-4-20250514-v1:0": {
1015
1087
  id: "global.anthropic.claude-sonnet-4-20250514-v1:0",
1016
1088
  name: "Claude Sonnet 4 (Global)",
@@ -1344,6 +1416,24 @@ export const MODELS = {
1344
1416
  contextWindow: 1000000,
1345
1417
  maxTokens: 128000,
1346
1418
  },
1419
+ "jp.anthropic.claude-opus-5-5": {
1420
+ id: "jp.anthropic.claude-opus-5-5",
1421
+ name: "Claude Opus 5.5 (JP)",
1422
+ api: "bedrock-converse-stream",
1423
+ provider: "amazon-bedrock",
1424
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1425
+ reasoning: true,
1426
+ thinkingType: "adaptive",
1427
+ input: ["text", "image"],
1428
+ cost: {
1429
+ input: 4.4,
1430
+ output: 22,
1431
+ cacheRead: 0.22,
1432
+ cacheWrite: 5.5,
1433
+ },
1434
+ contextWindow: 1000000,
1435
+ maxTokens: 128000,
1436
+ },
1347
1437
  "jp.anthropic.claude-sonnet-4-5-20250929-v1:0": {
1348
1438
  id: "jp.anthropic.claude-sonnet-4-5-20250929-v1:0",
1349
1439
  name: "Claude Sonnet 4.5 (JP)",
@@ -2400,6 +2490,24 @@ export const MODELS = {
2400
2490
  contextWindow: 1000000,
2401
2491
  maxTokens: 128000,
2402
2492
  },
2493
+ "us.anthropic.claude-opus-5-5": {
2494
+ id: "us.anthropic.claude-opus-5-5",
2495
+ name: "Claude Opus 5.5 (US)",
2496
+ api: "bedrock-converse-stream",
2497
+ provider: "amazon-bedrock",
2498
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2499
+ reasoning: true,
2500
+ thinkingType: "adaptive",
2501
+ input: ["text", "image"],
2502
+ cost: {
2503
+ input: 4.4,
2504
+ output: 22,
2505
+ cacheRead: 0.22,
2506
+ cacheWrite: 5.5,
2507
+ },
2508
+ contextWindow: 1000000,
2509
+ maxTokens: 128000,
2510
+ },
2403
2511
  "us.anthropic.claude-sonnet-4-20250514-v1:0": {
2404
2512
  id: "us.anthropic.claude-sonnet-4-20250514-v1:0",
2405
2513
  name: "Claude Sonnet 4 (US)",
@@ -2999,6 +3107,24 @@ export const MODELS = {
2999
3107
  contextWindow: 1000000,
3000
3108
  maxTokens: 128000,
3001
3109
  },
3110
+ "claude-opus-5-5": {
3111
+ id: "claude-opus-5-5",
3112
+ name: "Claude Opus 5.5",
3113
+ api: "anthropic-messages",
3114
+ provider: "anthropic",
3115
+ baseUrl: "https://api.anthropic.com",
3116
+ reasoning: true,
3117
+ thinkingType: "adaptive",
3118
+ input: ["text", "image"],
3119
+ cost: {
3120
+ input: 4,
3121
+ output: 20,
3122
+ cacheRead: 0.2,
3123
+ cacheWrite: 5,
3124
+ },
3125
+ contextWindow: 1000000,
3126
+ maxTokens: 128000,
3127
+ },
3002
3128
  "claude-sonnet-4-5": {
3003
3129
  id: "claude-sonnet-4-5",
3004
3130
  name: "Claude Sonnet 4.5 (latest)",
@@ -4668,7 +4794,7 @@ export const MODELS = {
4668
4794
  cacheWrite: 0,
4669
4795
  },
4670
4796
  contextWindow: 1310720,
4671
- maxTokens: 1310720,
4797
+ maxTokens: 1048576,
4672
4798
  },
4673
4799
  "@cf/zai-org/glm-5.3-flash": {
4674
4800
  id: "@cf/zai-org/glm-5.3-flash",
@@ -5750,6 +5876,25 @@ export const MODELS = {
5750
5876
  contextWindow: 500000,
5751
5877
  maxTokens: 128000,
5752
5878
  },
5879
+ "grok-4.7": {
5880
+ id: "grok-4.7",
5881
+ name: "Grok 4.7",
5882
+ api: "openai-completions",
5883
+ provider: "github-copilot",
5884
+ baseUrl: "https://api.individual.githubcopilot.com",
5885
+ 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" },
5886
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
5887
+ reasoning: true,
5888
+ input: ["text", "image"],
5889
+ cost: {
5890
+ input: 2,
5891
+ output: 6,
5892
+ cacheRead: 0.5,
5893
+ cacheWrite: 0,
5894
+ },
5895
+ contextWindow: 500000,
5896
+ maxTokens: 128000,
5897
+ },
5753
5898
  "kimi-k2.7-code": {
5754
5899
  id: "kimi-k2.7-code",
5755
5900
  name: "Kimi K2.7 Code",
@@ -7646,6 +7791,24 @@ export const MODELS = {
7646
7791
  contextWindow: 262144,
7647
7792
  maxTokens: 128000,
7648
7793
  },
7794
+ "tencent/Hy4-preview": {
7795
+ id: "tencent/Hy4-preview",
7796
+ name: "Hy4 preview",
7797
+ api: "openai-completions",
7798
+ provider: "huggingface",
7799
+ baseUrl: "https://router.huggingface.co/v1",
7800
+ compat: { "supportsDeveloperRole": false },
7801
+ reasoning: true,
7802
+ input: ["text"],
7803
+ cost: {
7804
+ input: 0.834,
7805
+ output: 2.501,
7806
+ cacheRead: 0,
7807
+ cacheWrite: 0,
7808
+ },
7809
+ contextWindow: 1000000,
7810
+ maxTokens: 64000,
7811
+ },
7649
7812
  "thinkingmachines/Inkling": {
7650
7813
  id: "thinkingmachines/Inkling",
7651
7814
  name: "Inkling",
@@ -9926,6 +10089,25 @@ export const MODELS = {
9926
10089
  contextWindow: 1000000,
9927
10090
  maxTokens: 384000,
9928
10091
  },
10092
+ "deepseek-v4.1-flash": {
10093
+ id: "deepseek-v4.1-flash",
10094
+ name: "DeepSeek V4.1 Flash",
10095
+ api: "openai-completions",
10096
+ provider: "opencode",
10097
+ baseUrl: "https://opencode.ai/zen/v1",
10098
+ compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
10099
+ reasoning: true,
10100
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
10101
+ input: ["text", "image"],
10102
+ cost: {
10103
+ input: 0.3,
10104
+ output: 1.2,
10105
+ cacheRead: 0.006,
10106
+ cacheWrite: 0,
10107
+ },
10108
+ contextWindow: 1000000,
10109
+ maxTokens: 384000,
10110
+ },
9929
10111
  "gemini-3-flash": {
9930
10112
  id: "gemini-3-flash",
9931
10113
  name: "Gemini 3 Flash",
@@ -10632,9 +10814,9 @@ export const MODELS = {
10632
10814
  contextWindow: 262144,
10633
10815
  maxTokens: 32768,
10634
10816
  },
10635
- "mimo-v2.5-free": {
10636
- id: "mimo-v2.5-free",
10637
- name: "MiMo V2.5 Free",
10817
+ "mimo-v2.6-flash-free": {
10818
+ id: "mimo-v2.6-flash-free",
10819
+ name: "MiMo-V2.6-Flash Free",
10638
10820
  api: "openai-completions",
10639
10821
  provider: "opencode",
10640
10822
  baseUrl: "https://opencode.ai/zen/v1",
@@ -10836,6 +11018,23 @@ export const MODELS = {
10836
11018
  contextWindow: 262144,
10837
11019
  maxTokens: 65536,
10838
11020
  },
11021
+ "qwen3.8-flash": {
11022
+ id: "qwen3.8-flash",
11023
+ name: "Qwen3.8 Flash",
11024
+ api: "anthropic-messages",
11025
+ provider: "opencode",
11026
+ baseUrl: "https://opencode.ai/zen",
11027
+ reasoning: true,
11028
+ input: ["text", "image"],
11029
+ cost: {
11030
+ input: 0.15,
11031
+ output: 0.47,
11032
+ cacheRead: 0.016,
11033
+ cacheWrite: 0.2,
11034
+ },
11035
+ contextWindow: 1000000,
11036
+ maxTokens: 131072,
11037
+ },
10839
11038
  },
10840
11039
  "opencode-go": {
10841
11040
  "deepseek-v4-flash": {
@@ -11017,6 +11216,23 @@ export const MODELS = {
11017
11216
  contextWindow: 500000,
11018
11217
  maxTokens: 500000,
11019
11218
  },
11219
+ "grok-4.7": {
11220
+ id: "grok-4.7",
11221
+ name: "Grok 4.7",
11222
+ api: "openai-responses",
11223
+ provider: "opencode-go",
11224
+ baseUrl: "https://opencode.ai/zen/go/v1",
11225
+ reasoning: true,
11226
+ input: ["text", "image"],
11227
+ cost: {
11228
+ input: 2,
11229
+ output: 6,
11230
+ cacheRead: 0.5,
11231
+ cacheWrite: 0,
11232
+ },
11233
+ contextWindow: 500000,
11234
+ maxTokens: 500000,
11235
+ },
11020
11236
  "hy3": {
11021
11237
  id: "hy3",
11022
11238
  name: "Hy3",
@@ -11153,6 +11369,40 @@ export const MODELS = {
11153
11369
  contextWindow: 1048576,
11154
11370
  maxTokens: 128000,
11155
11371
  },
11372
+ "mimo-v2.6-flash": {
11373
+ id: "mimo-v2.6-flash",
11374
+ name: "MiMo-V2.6-Flash",
11375
+ api: "openai-completions",
11376
+ provider: "opencode-go",
11377
+ baseUrl: "https://opencode.ai/zen/go/v1",
11378
+ reasoning: true,
11379
+ input: ["text", "image"],
11380
+ cost: {
11381
+ input: 0.14,
11382
+ output: 0.28,
11383
+ cacheRead: 0.0028,
11384
+ cacheWrite: 0,
11385
+ },
11386
+ contextWindow: 1048576,
11387
+ maxTokens: 131072,
11388
+ },
11389
+ "mimo-v2.6-pro": {
11390
+ id: "mimo-v2.6-pro",
11391
+ name: "MiMo-V2.6-Pro",
11392
+ api: "openai-completions",
11393
+ provider: "opencode-go",
11394
+ baseUrl: "https://opencode.ai/zen/go/v1",
11395
+ reasoning: true,
11396
+ input: ["text", "image"],
11397
+ cost: {
11398
+ input: 0.435,
11399
+ output: 0.87,
11400
+ cacheRead: 0.003625,
11401
+ cacheWrite: 0,
11402
+ },
11403
+ contextWindow: 1048576,
11404
+ maxTokens: 131072,
11405
+ },
11156
11406
  "minimax-m2.7": {
11157
11407
  id: "minimax-m2.7",
11158
11408
  name: "MiniMax-M2.7",
@@ -11165,7 +11415,7 @@ export const MODELS = {
11165
11415
  input: 0.3,
11166
11416
  output: 1.2,
11167
11417
  cacheRead: 0.06,
11168
- cacheWrite: 0,
11418
+ cacheWrite: 0.375,
11169
11419
  },
11170
11420
  contextWindow: 204800,
11171
11421
  maxTokens: 131072,
@@ -11323,7 +11573,7 @@ export const MODELS = {
11323
11573
  cacheRead: 0.19999999999999998,
11324
11574
  cacheWrite: 0,
11325
11575
  },
11326
- contextWindow: 131072,
11576
+ contextWindow: 1048576,
11327
11577
  maxTokens: 32768,
11328
11578
  },
11329
11579
  "aion-labs/aion-3.0": {
@@ -11340,7 +11590,7 @@ export const MODELS = {
11340
11590
  cacheRead: 0.75,
11341
11591
  cacheWrite: 0,
11342
11592
  },
11343
- contextWindow: 131072,
11593
+ contextWindow: 1048576,
11344
11594
  maxTokens: 32768,
11345
11595
  },
11346
11596
  "aion-labs/aion-3.0-mini": {
@@ -11357,7 +11607,7 @@ export const MODELS = {
11357
11607
  cacheRead: 0.18,
11358
11608
  cacheWrite: 0,
11359
11609
  },
11360
- contextWindow: 131072,
11610
+ contextWindow: 1048576,
11361
11611
  maxTokens: 32768,
11362
11612
  },
11363
11613
  "amazon/nova-2-lite-v1": {
@@ -11568,23 +11818,6 @@ export const MODELS = {
11568
11818
  contextWindow: 200000,
11569
11819
  maxTokens: 64000,
11570
11820
  },
11571
- "anthropic/claude-opus-4": {
11572
- id: "anthropic/claude-opus-4",
11573
- name: "Anthropic: Claude Opus 4",
11574
- api: "openai-completions",
11575
- provider: "openrouter",
11576
- baseUrl: "https://openrouter.ai/api/v1",
11577
- reasoning: true,
11578
- input: ["text", "image"],
11579
- cost: {
11580
- input: 15,
11581
- output: 75,
11582
- cacheRead: 1.5,
11583
- cacheWrite: 18.75,
11584
- },
11585
- contextWindow: 200000,
11586
- maxTokens: 32000,
11587
- },
11588
11821
  "anthropic/claude-opus-4.1": {
11589
11822
  id: "anthropic/claude-opus-4.1",
11590
11823
  name: "Anthropic: Claude Opus 4.1",
@@ -11778,38 +12011,72 @@ export const MODELS = {
11778
12011
  contextWindow: 1000000,
11779
12012
  maxTokens: 128000,
11780
12013
  },
11781
- "anthropic/claude-opus-5:batch": {
11782
- id: "anthropic/claude-opus-5:batch",
11783
- name: "Anthropic: Claude Opus 5 (batch)",
12014
+ "anthropic/claude-opus-5.5": {
12015
+ id: "anthropic/claude-opus-5.5",
12016
+ name: "Anthropic: Claude Opus 5.5",
11784
12017
  api: "openai-completions",
11785
12018
  provider: "openrouter",
11786
12019
  baseUrl: "https://openrouter.ai/api/v1",
11787
12020
  reasoning: true,
11788
12021
  input: ["text", "image"],
11789
12022
  cost: {
11790
- input: 2.5,
11791
- output: 12.5,
11792
- cacheRead: 0.25,
11793
- cacheWrite: 3.125,
12023
+ input: 4,
12024
+ output: 20,
12025
+ cacheRead: 0.19999999999999998,
12026
+ cacheWrite: 5,
11794
12027
  },
11795
12028
  contextWindow: 1000000,
11796
12029
  maxTokens: 128000,
11797
12030
  },
11798
- "anthropic/claude-sonnet-4": {
11799
- id: "anthropic/claude-sonnet-4",
11800
- name: "Anthropic: Claude Sonnet 4",
12031
+ "anthropic/claude-opus-5.5:batch": {
12032
+ id: "anthropic/claude-opus-5.5:batch",
12033
+ name: "Anthropic: Claude Opus 5.5 (batch)",
11801
12034
  api: "openai-completions",
11802
12035
  provider: "openrouter",
11803
12036
  baseUrl: "https://openrouter.ai/api/v1",
11804
12037
  reasoning: true,
11805
12038
  input: ["text", "image"],
11806
12039
  cost: {
11807
- input: 3,
11808
- output: 15,
12040
+ input: 2,
12041
+ output: 10,
12042
+ cacheRead: 0.09999999999999999,
12043
+ cacheWrite: 2.5,
12044
+ },
12045
+ contextWindow: 1000000,
12046
+ maxTokens: 128000,
12047
+ },
12048
+ "anthropic/claude-opus-5:batch": {
12049
+ id: "anthropic/claude-opus-5:batch",
12050
+ name: "Anthropic: Claude Opus 5 (batch)",
12051
+ api: "openai-completions",
12052
+ provider: "openrouter",
12053
+ baseUrl: "https://openrouter.ai/api/v1",
12054
+ reasoning: true,
12055
+ input: ["text", "image"],
12056
+ cost: {
12057
+ input: 2.5,
12058
+ output: 12.5,
12059
+ cacheRead: 0.25,
12060
+ cacheWrite: 3.125,
12061
+ },
12062
+ contextWindow: 1000000,
12063
+ maxTokens: 128000,
12064
+ },
12065
+ "anthropic/claude-sonnet-4": {
12066
+ id: "anthropic/claude-sonnet-4",
12067
+ name: "Anthropic: Claude Sonnet 4",
12068
+ api: "openai-completions",
12069
+ provider: "openrouter",
12070
+ baseUrl: "https://openrouter.ai/api/v1",
12071
+ reasoning: true,
12072
+ input: ["text", "image"],
12073
+ cost: {
12074
+ input: 3,
12075
+ output: 15,
11809
12076
  cacheRead: 0.3,
11810
12077
  cacheWrite: 3.75,
11811
12078
  },
11812
- contextWindow: 1000000,
12079
+ contextWindow: 200000,
11813
12080
  maxTokens: 64000,
11814
12081
  },
11815
12082
  "anthropic/claude-sonnet-4.5": {
@@ -12248,9 +12515,9 @@ export const MODELS = {
12248
12515
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12249
12516
  input: ["text"],
12250
12517
  cost: {
12251
- input: 0.048440000000000004,
12252
- output: 0.09688000000000001,
12253
- cacheRead: 0.009688,
12518
+ input: 0.049,
12519
+ output: 0.098,
12520
+ cacheRead: 0.0098,
12254
12521
  cacheWrite: 0,
12255
12522
  },
12256
12523
  contextWindow: 1048576,
@@ -12267,52 +12534,14 @@ export const MODELS = {
12267
12534
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12268
12535
  input: ["text"],
12269
12536
  cost: {
12270
- input: 0.06,
12271
- output: 0.12,
12272
- cacheRead: 0.012,
12537
+ input: 0.04,
12538
+ output: 0.64,
12539
+ cacheRead: 0.016,
12273
12540
  cacheWrite: 0,
12274
12541
  },
12275
12542
  contextWindow: 1310720,
12276
12543
  maxTokens: 943718,
12277
12544
  },
12278
- "deepseek/deepseek-v4-flash-0731:batch": {
12279
- id: "deepseek/deepseek-v4-flash-0731:batch",
12280
- name: "DeepSeek: DeepSeek V4 Flash 0731 (batch)",
12281
- api: "openai-completions",
12282
- provider: "openrouter",
12283
- baseUrl: "https://openrouter.ai/api/v1",
12284
- compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
12285
- reasoning: true,
12286
- thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12287
- input: ["text"],
12288
- cost: {
12289
- input: 0.11,
12290
- output: 0.33,
12291
- cacheRead: 0.0035,
12292
- cacheWrite: 0,
12293
- },
12294
- contextWindow: 1048576,
12295
- maxTokens: 943718,
12296
- },
12297
- "deepseek/deepseek-v4-flash-0731:free": {
12298
- id: "deepseek/deepseek-v4-flash-0731:free",
12299
- name: "DeepSeek: DeepSeek V4 Flash 0731 (free)",
12300
- api: "openai-completions",
12301
- provider: "openrouter",
12302
- baseUrl: "https://openrouter.ai/api/v1",
12303
- compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
12304
- reasoning: true,
12305
- thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12306
- input: ["text"],
12307
- cost: {
12308
- input: 0,
12309
- output: 0,
12310
- cacheRead: 0,
12311
- cacheWrite: 0,
12312
- },
12313
- contextWindow: 1048576,
12314
- maxTokens: 393216,
12315
- },
12316
12545
  "deepseek/deepseek-v4-flash-vision-exp": {
12317
12546
  id: "deepseek/deepseek-v4-flash-vision-exp",
12318
12547
  name: "DeepSeek: DeepSeek V4 Flash Vision Exp",
@@ -12324,28 +12553,9 @@ export const MODELS = {
12324
12553
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12325
12554
  input: ["text", "image"],
12326
12555
  cost: {
12327
- input: 0.21559999999999999,
12328
- output: 0.6468,
12329
- cacheRead: 0.00686,
12330
- cacheWrite: 0,
12331
- },
12332
- contextWindow: 1048576,
12333
- maxTokens: 262144,
12334
- },
12335
- "deepseek/deepseek-v4-flash-vision-exp:batch": {
12336
- id: "deepseek/deepseek-v4-flash-vision-exp:batch",
12337
- name: "DeepSeek: DeepSeek V4 Flash Vision Exp (batch)",
12338
- api: "openai-completions",
12339
- provider: "openrouter",
12340
- baseUrl: "https://openrouter.ai/api/v1",
12341
- compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
12342
- reasoning: true,
12343
- thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12344
- input: ["text", "image"],
12345
- cost: {
12346
- input: 0.11,
12347
- output: 0.33,
12348
- cacheRead: 0.0035,
12556
+ input: 0.22,
12557
+ output: 0.66,
12558
+ cacheRead: 0.007,
12349
12559
  cacheWrite: 0,
12350
12560
  },
12351
12561
  contextWindow: 1048576,
@@ -12362,13 +12572,13 @@ export const MODELS = {
12362
12572
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12363
12573
  input: ["text"],
12364
12574
  cost: {
12365
- input: 1.5999999999999999,
12366
- output: 3.1999999999999997,
12367
- cacheRead: 0.135,
12575
+ input: 0.90741,
12576
+ output: 1.81482,
12577
+ cacheRead: 0.07561749999999999,
12368
12578
  cacheWrite: 0,
12369
12579
  },
12370
12580
  contextWindow: 1048576,
12371
- maxTokens: 393216,
12581
+ maxTokens: 384000,
12372
12582
  },
12373
12583
  "deepseek/deepseek-v4-pro-0813": {
12374
12584
  id: "deepseek/deepseek-v4-pro-0813",
@@ -12381,36 +12591,36 @@ export const MODELS = {
12381
12591
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12382
12592
  input: ["text"],
12383
12593
  cost: {
12384
- input: 0.57816,
12385
- output: 1.73448,
12386
- cacheRead: 0.018396000000000003,
12594
+ input: 0.66,
12595
+ output: 1.9800000000000002,
12596
+ cacheRead: 0.022,
12387
12597
  cacheWrite: 0,
12388
12598
  },
12389
12599
  contextWindow: 1048576,
12390
- maxTokens: 393216,
12600
+ maxTokens: 384000,
12391
12601
  },
12392
- "deepseek/deepseek-v4-pro-0813:batch": {
12393
- id: "deepseek/deepseek-v4-pro-0813:batch",
12394
- name: "DeepSeek: DeepSeek V4 Pro 0813 (batch)",
12602
+ "deepseek/deepseek-v4.1-flash": {
12603
+ id: "deepseek/deepseek-v4.1-flash",
12604
+ name: "DeepSeek: DeepSeek V4.1 Flash",
12395
12605
  api: "openai-completions",
12396
12606
  provider: "openrouter",
12397
12607
  baseUrl: "https://openrouter.ai/api/v1",
12398
12608
  compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
12399
12609
  reasoning: true,
12400
12610
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12401
- input: ["text"],
12611
+ input: ["text", "image"],
12402
12612
  cost: {
12403
- input: 0.66,
12404
- output: 1.9800000000000002,
12405
- cacheRead: 0.022,
12613
+ input: 0.15,
12614
+ output: 0.6,
12615
+ cacheRead: 0.003,
12406
12616
  cacheWrite: 0,
12407
12617
  },
12408
12618
  contextWindow: 1048576,
12409
- maxTokens: 943718,
12619
+ maxTokens: 384000,
12410
12620
  },
12411
- "deepseek/deepseek-v4.1-flash": {
12412
- id: "deepseek/deepseek-v4.1-flash",
12413
- name: "DeepSeek: DeepSeek V4.1 Flash",
12621
+ "deepseek/deepseek-v4.1-flash:batch": {
12622
+ id: "deepseek/deepseek-v4.1-flash:batch",
12623
+ name: "DeepSeek: DeepSeek V4.1 Flash (batch)",
12414
12624
  api: "openai-completions",
12415
12625
  provider: "openrouter",
12416
12626
  baseUrl: "https://openrouter.ai/api/v1",
@@ -12419,13 +12629,13 @@ export const MODELS = {
12419
12629
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12420
12630
  input: ["text", "image"],
12421
12631
  cost: {
12422
- input: 0.15,
12423
- output: 0.6,
12424
- cacheRead: 0.003,
12632
+ input: 0.112,
12633
+ output: 0.33599999999999997,
12634
+ cacheRead: 0.00336,
12425
12635
  cacheWrite: 0,
12426
12636
  },
12427
12637
  contextWindow: 1048576,
12428
- maxTokens: 384000,
12638
+ maxTokens: 131072,
12429
12639
  },
12430
12640
  "dots-studio/dots-3-note-preview:free": {
12431
12641
  id: "dots-studio/dots-3-note-preview:free",
@@ -12934,7 +13144,7 @@ export const MODELS = {
12934
13144
  cacheRead: 0.049999999999999996,
12935
13145
  cacheWrite: 0,
12936
13146
  },
12937
- contextWindow: 1000000,
13147
+ contextWindow: 262144,
12938
13148
  maxTokens: 235929,
12939
13149
  },
12940
13150
  "google/gemma-4-26b-a4b-it:free": {
@@ -13141,23 +13351,6 @@ export const MODELS = {
13141
13351
  contextWindow: 262144,
13142
13352
  maxTokens: 32768,
13143
13353
  },
13144
- "kwaipilot/kat-coder-pro-v2": {
13145
- id: "kwaipilot/kat-coder-pro-v2",
13146
- name: "Kwaipilot: KAT-Coder-Pro V2",
13147
- api: "openai-completions",
13148
- provider: "openrouter",
13149
- baseUrl: "https://openrouter.ai/api/v1",
13150
- reasoning: false,
13151
- input: ["text"],
13152
- cost: {
13153
- input: 0.3,
13154
- output: 1.2,
13155
- cacheRead: 0.06,
13156
- cacheWrite: 0,
13157
- },
13158
- contextWindow: 262144,
13159
- maxTokens: 144000,
13160
- },
13161
13354
  "kwaipilot/kat-coder-pro-v2.5": {
13162
13355
  id: "kwaipilot/kat-coder-pro-v2.5",
13163
13356
  name: "Kwaipilot: KAT-Coder-Pro V2.5",
@@ -13303,30 +13496,13 @@ export const MODELS = {
13303
13496
  reasoning: true,
13304
13497
  input: ["text", "image"],
13305
13498
  cost: {
13306
- input: 0.35,
13307
- output: 1.5,
13499
+ input: 0.3,
13500
+ output: 1.2,
13308
13501
  cacheRead: 0.04,
13309
13502
  cacheWrite: 0,
13310
13503
  },
13311
13504
  contextWindow: 131072,
13312
- maxTokens: 117964,
13313
- },
13314
- "meta/muse-glimmer-30b:batch": {
13315
- id: "meta/muse-glimmer-30b:batch",
13316
- name: "Meta: Muse Glimmer 30B (batch)",
13317
- api: "openai-completions",
13318
- provider: "openrouter",
13319
- baseUrl: "https://openrouter.ai/api/v1",
13320
- reasoning: true,
13321
- input: ["text", "image"],
13322
- cost: {
13323
- input: 0.175,
13324
- output: 0.75,
13325
- cacheRead: 0.02,
13326
- cacheWrite: 0,
13327
- },
13328
- contextWindow: 131072,
13329
- maxTokens: 117964,
13505
+ maxTokens: 16384,
13330
13506
  },
13331
13507
  "meta/muse-spark-1.1": {
13332
13508
  id: "meta/muse-spark-1.1",
@@ -13515,23 +13691,6 @@ export const MODELS = {
13515
13691
  contextWindow: 1048576,
13516
13692
  maxTokens: 512000,
13517
13693
  },
13518
- "minimax/minimax-m3:batch": {
13519
- id: "minimax/minimax-m3:batch",
13520
- name: "MiniMax: MiniMax M3 (batch)",
13521
- api: "openai-completions",
13522
- provider: "openrouter",
13523
- baseUrl: "https://openrouter.ai/api/v1",
13524
- reasoning: true,
13525
- input: ["text", "image"],
13526
- cost: {
13527
- input: 0.3,
13528
- output: 1.2,
13529
- cacheRead: 0.06,
13530
- cacheWrite: 0,
13531
- },
13532
- contextWindow: 524288,
13533
- maxTokens: 471859,
13534
- },
13535
13694
  "mistralai/codestral-2508": {
13536
13695
  id: "mistralai/codestral-2508",
13537
13696
  name: "Mistral: Codestral 2508",
@@ -13855,6 +14014,23 @@ export const MODELS = {
13855
14014
  contextWindow: 262144,
13856
14015
  maxTokens: 209715,
13857
14016
  },
14017
+ "mistralai/mistral-small-3.1-24b-instruct": {
14018
+ id: "mistralai/mistral-small-3.1-24b-instruct",
14019
+ name: "Mistral: Mistral Small 3.1 24B",
14020
+ api: "openai-completions",
14021
+ provider: "openrouter",
14022
+ baseUrl: "https://openrouter.ai/api/v1",
14023
+ reasoning: false,
14024
+ input: ["text", "image"],
14025
+ cost: {
14026
+ input: 0.351,
14027
+ output: 0.5549999999999999,
14028
+ cacheRead: 0,
14029
+ cacheWrite: 0,
14030
+ },
14031
+ contextWindow: 128000,
14032
+ maxTokens: 102400,
14033
+ },
13858
14034
  "mistralai/mistral-small-3.2-24b-instruct": {
13859
14035
  id: "mistralai/mistral-small-3.2-24b-instruct",
13860
14036
  name: "Mistral: Mistral Small 3.2 24B",
@@ -14001,7 +14177,7 @@ export const MODELS = {
14001
14177
  input: ["text", "image"],
14002
14178
  cost: {
14003
14179
  input: 0.7062,
14004
- output: 3.21,
14180
+ output: 3.3000000000000003,
14005
14181
  cacheRead: 0.18,
14006
14182
  cacheWrite: 0,
14007
14183
  },
@@ -14017,9 +14193,9 @@ export const MODELS = {
14017
14193
  reasoning: true,
14018
14194
  input: ["text", "image"],
14019
14195
  cost: {
14020
- input: 1.95,
14021
- output: 10.92,
14022
- cacheRead: 0.2262,
14196
+ input: 3,
14197
+ output: 15,
14198
+ cacheRead: 0.3,
14023
14199
  cacheWrite: 0,
14024
14200
  },
14025
14201
  contextWindow: 1048576,
@@ -14034,13 +14210,13 @@ export const MODELS = {
14034
14210
  reasoning: true,
14035
14211
  input: ["text", "image"],
14036
14212
  cost: {
14037
- input: 3,
14038
- output: 15,
14039
- cacheRead: 0.3,
14213
+ input: 2.2800000000000002,
14214
+ output: 11.399999999999999,
14215
+ cacheRead: 0.228,
14040
14216
  cacheWrite: 0,
14041
14217
  },
14042
14218
  contextWindow: 1048576,
14043
- maxTokens: 943718,
14219
+ maxTokens: 16384,
14044
14220
  },
14045
14221
  "nex-agi/nex-n2.5-mini:free": {
14046
14222
  id: "nex-agi/nex-n2.5-mini:free",
@@ -14059,6 +14235,23 @@ export const MODELS = {
14059
14235
  contextWindow: 262144,
14060
14236
  maxTokens: 235929,
14061
14237
  },
14238
+ "nex-agi/nex-n2.5-pro": {
14239
+ id: "nex-agi/nex-n2.5-pro",
14240
+ name: "Nex AGI: Nex-N2.5-Pro",
14241
+ api: "openai-completions",
14242
+ provider: "openrouter",
14243
+ baseUrl: "https://openrouter.ai/api/v1",
14244
+ reasoning: true,
14245
+ input: ["text", "image"],
14246
+ cost: {
14247
+ input: 0.075,
14248
+ output: 0.25,
14249
+ cacheRead: 0.015,
14250
+ cacheWrite: 0,
14251
+ },
14252
+ contextWindow: 262144,
14253
+ maxTokens: 235929,
14254
+ },
14062
14255
  "nex-agi/nex-n2.5-pro:free": {
14063
14256
  id: "nex-agi/nex-n2.5-pro:free",
14064
14257
  name: "Nex AGI: Nex-N2.5-Pro (free)",
@@ -14085,9 +14278,9 @@ export const MODELS = {
14085
14278
  reasoning: true,
14086
14279
  input: ["text"],
14087
14280
  cost: {
14088
- input: 0.06,
14089
- output: 0.24,
14090
- cacheRead: 0,
14281
+ input: 0.049999999999999996,
14282
+ output: 0.19999999999999998,
14283
+ cacheRead: 0.03,
14091
14284
  cacheWrite: 0,
14092
14285
  },
14093
14286
  contextWindow: 262144,
@@ -14153,13 +14346,13 @@ export const MODELS = {
14153
14346
  reasoning: true,
14154
14347
  input: ["text"],
14155
14348
  cost: {
14156
- input: 0.625,
14157
- output: 3.125,
14158
- cacheRead: 0.1875,
14349
+ input: 0.6,
14350
+ output: 2.4,
14351
+ cacheRead: 0.12,
14159
14352
  cacheWrite: 0,
14160
14353
  },
14161
14354
  contextWindow: 262144,
14162
- maxTokens: 32768,
14355
+ maxTokens: 182520,
14163
14356
  },
14164
14357
  "nvidia/nemotron-3-ultra-550b-a55b:free": {
14165
14358
  id: "nvidia/nemotron-3-ultra-550b-a55b:free",
@@ -14187,13 +14380,13 @@ export const MODELS = {
14187
14380
  reasoning: true,
14188
14381
  input: ["text"],
14189
14382
  cost: {
14190
- input: 0.08,
14383
+ input: 0.07,
14191
14384
  output: 0.19999999999999998,
14192
14385
  cacheRead: 0.04,
14193
14386
  cacheWrite: 0,
14194
14387
  },
14195
14388
  contextWindow: 262144,
14196
- maxTokens: 131072,
14389
+ maxTokens: 235929,
14197
14390
  },
14198
14391
  "nvidia/nemotron-3.5-lightning:free": {
14199
14392
  id: "nvidia/nemotron-3.5-lightning:free",
@@ -15319,39 +15512,90 @@ export const MODELS = {
15319
15512
  contextWindow: 1050000,
15320
15513
  maxTokens: 128000,
15321
15514
  },
15322
- "openai/gpt-audio": {
15323
- id: "openai/gpt-audio",
15324
- name: "OpenAI: GPT Audio",
15515
+ "openai/gpt-6-sol": {
15516
+ id: "openai/gpt-6-sol",
15517
+ name: "OpenAI: GPT-6 Sol",
15325
15518
  api: "openai-completions",
15326
15519
  provider: "openrouter",
15327
15520
  baseUrl: "https://openrouter.ai/api/v1",
15328
- reasoning: false,
15329
- input: ["text"],
15521
+ reasoning: true,
15522
+ input: ["text", "image"],
15330
15523
  cost: {
15331
- input: 2.5,
15524
+ input: 2,
15332
15525
  output: 10,
15333
- cacheRead: 0,
15334
- cacheWrite: 0,
15526
+ cacheRead: 0.19999999999999998,
15527
+ cacheWrite: 2.5,
15335
15528
  },
15336
- contextWindow: 128000,
15337
- maxTokens: 16384,
15529
+ contextWindow: 1050000,
15530
+ maxTokens: 128000,
15338
15531
  },
15339
- "openai/gpt-audio-mini": {
15340
- id: "openai/gpt-audio-mini",
15341
- name: "OpenAI: GPT Audio Mini",
15532
+ "openai/gpt-6-sol-pro": {
15533
+ id: "openai/gpt-6-sol-pro",
15534
+ name: "OpenAI: GPT-6 Sol Pro",
15342
15535
  api: "openai-completions",
15343
15536
  provider: "openrouter",
15344
15537
  baseUrl: "https://openrouter.ai/api/v1",
15345
- reasoning: false,
15346
- input: ["text"],
15538
+ reasoning: true,
15539
+ input: ["text", "image"],
15347
15540
  cost: {
15348
- input: 0.6,
15349
- output: 2.4,
15350
- cacheRead: 0,
15351
- cacheWrite: 0,
15541
+ input: 2,
15542
+ output: 10,
15543
+ cacheRead: 0.19999999999999998,
15544
+ cacheWrite: 2.5,
15352
15545
  },
15353
- contextWindow: 128000,
15354
- maxTokens: 16384,
15546
+ contextWindow: 1050000,
15547
+ maxTokens: 128000,
15548
+ },
15549
+ "openai/gpt-6-sol:batch": {
15550
+ id: "openai/gpt-6-sol:batch",
15551
+ name: "OpenAI: GPT-6 Sol (batch)",
15552
+ api: "openai-completions",
15553
+ provider: "openrouter",
15554
+ baseUrl: "https://openrouter.ai/api/v1",
15555
+ reasoning: true,
15556
+ input: ["text", "image"],
15557
+ cost: {
15558
+ input: 1,
15559
+ output: 5,
15560
+ cacheRead: 0.09999999999999999,
15561
+ cacheWrite: 1.25,
15562
+ },
15563
+ contextWindow: 1050000,
15564
+ maxTokens: 128000,
15565
+ },
15566
+ "openai/gpt-audio": {
15567
+ id: "openai/gpt-audio",
15568
+ name: "OpenAI: GPT Audio",
15569
+ api: "openai-completions",
15570
+ provider: "openrouter",
15571
+ baseUrl: "https://openrouter.ai/api/v1",
15572
+ reasoning: false,
15573
+ input: ["text"],
15574
+ cost: {
15575
+ input: 2.5,
15576
+ output: 10,
15577
+ cacheRead: 0,
15578
+ cacheWrite: 0,
15579
+ },
15580
+ contextWindow: 128000,
15581
+ maxTokens: 16384,
15582
+ },
15583
+ "openai/gpt-audio-mini": {
15584
+ id: "openai/gpt-audio-mini",
15585
+ name: "OpenAI: GPT Audio Mini",
15586
+ api: "openai-completions",
15587
+ provider: "openrouter",
15588
+ baseUrl: "https://openrouter.ai/api/v1",
15589
+ reasoning: false,
15590
+ input: ["text"],
15591
+ cost: {
15592
+ input: 0.6,
15593
+ output: 2.4,
15594
+ cacheRead: 0,
15595
+ cacheWrite: 0,
15596
+ },
15597
+ contextWindow: 128000,
15598
+ maxTokens: 16384,
15355
15599
  },
15356
15600
  "openai/gpt-chat-latest": {
15357
15601
  id: "openai/gpt-chat-latest",
@@ -15387,35 +15631,35 @@ export const MODELS = {
15387
15631
  contextWindow: 131072,
15388
15632
  maxTokens: 65536,
15389
15633
  },
15390
- "openai/gpt-oss-120b:batch": {
15391
- id: "openai/gpt-oss-120b:batch",
15392
- name: "OpenAI: gpt-oss-120b (batch)",
15634
+ "openai/gpt-oss-20b": {
15635
+ id: "openai/gpt-oss-20b",
15636
+ name: "OpenAI: gpt-oss-20b",
15393
15637
  api: "openai-completions",
15394
15638
  provider: "openrouter",
15395
15639
  baseUrl: "https://openrouter.ai/api/v1",
15396
15640
  reasoning: true,
15397
15641
  input: ["text"],
15398
15642
  cost: {
15399
- input: 0.15,
15400
- output: 0.6,
15643
+ input: 0.018,
15644
+ output: 0.09,
15401
15645
  cacheRead: 0,
15402
15646
  cacheWrite: 0,
15403
15647
  },
15404
15648
  contextWindow: 131072,
15405
- maxTokens: 117964,
15649
+ maxTokens: 32768,
15406
15650
  },
15407
- "openai/gpt-oss-20b": {
15408
- id: "openai/gpt-oss-20b",
15409
- name: "OpenAI: gpt-oss-20b",
15651
+ "openai/gpt-oss-20b:batch": {
15652
+ id: "openai/gpt-oss-20b:batch",
15653
+ name: "OpenAI: gpt-oss-20b (batch)",
15410
15654
  api: "openai-completions",
15411
15655
  provider: "openrouter",
15412
15656
  baseUrl: "https://openrouter.ai/api/v1",
15413
15657
  reasoning: true,
15414
15658
  input: ["text"],
15415
15659
  cost: {
15416
- input: 0.03,
15417
- output: 0.13,
15418
- cacheRead: 0.03,
15660
+ input: 0.024,
15661
+ output: 0.112,
15662
+ cacheRead: 0,
15419
15663
  cacheWrite: 0,
15420
15664
  },
15421
15665
  contextWindow: 131072,
@@ -16116,7 +16360,7 @@ export const MODELS = {
16116
16360
  cacheWrite: 0,
16117
16361
  },
16118
16362
  contextWindow: 262144,
16119
- maxTokens: 32768,
16363
+ maxTokens: 235929,
16120
16364
  },
16121
16365
  "qwen/qwen3-vl-235b-a22b-instruct": {
16122
16366
  id: "qwen/qwen3-vl-235b-a22b-instruct",
@@ -16280,13 +16524,13 @@ export const MODELS = {
16280
16524
  reasoning: true,
16281
16525
  input: ["text", "image"],
16282
16526
  cost: {
16283
- input: 0.1625,
16284
- output: 1.3,
16285
- cacheRead: 0,
16527
+ input: 0.3125,
16528
+ output: 1.25,
16529
+ cacheRead: 0.15625,
16286
16530
  cacheWrite: 0,
16287
16531
  },
16288
16532
  contextWindow: 262144,
16289
- maxTokens: 65536,
16533
+ maxTokens: 16384,
16290
16534
  },
16291
16535
  "qwen/qwen3.5-397b-a17b": {
16292
16536
  id: "qwen/qwen3.5-397b-a17b",
@@ -16320,24 +16564,7 @@ export const MODELS = {
16320
16564
  cacheWrite: 0,
16321
16565
  },
16322
16566
  contextWindow: 262144,
16323
- maxTokens: 235929,
16324
- },
16325
- "qwen/qwen3.5-9b:batch": {
16326
- id: "qwen/qwen3.5-9b:batch",
16327
- name: "Qwen: Qwen3.5-9B (batch)",
16328
- api: "openai-completions",
16329
- provider: "openrouter",
16330
- baseUrl: "https://openrouter.ai/api/v1",
16331
- reasoning: true,
16332
- input: ["text", "image"],
16333
- cost: {
16334
- input: 0.16999999999999998,
16335
- output: 0.25,
16336
- cacheRead: 0,
16337
- cacheWrite: 0,
16338
- },
16339
- contextWindow: 262144,
16340
- maxTokens: 235929,
16567
+ maxTokens: 32768,
16341
16568
  },
16342
16569
  "qwen/qwen3.5-flash-02-23": {
16343
16570
  id: "qwen/qwen3.5-flash-02-23",
@@ -16399,13 +16626,13 @@ export const MODELS = {
16399
16626
  reasoning: true,
16400
16627
  input: ["text", "image"],
16401
16628
  cost: {
16402
- input: 0.3,
16403
- output: 2,
16404
- cacheRead: 0.03,
16629
+ input: 0.32,
16630
+ output: 2.7,
16631
+ cacheRead: 0.15,
16405
16632
  cacheWrite: 0,
16406
16633
  },
16407
16634
  contextWindow: 262144,
16408
- maxTokens: 65536,
16635
+ maxTokens: 262140,
16409
16636
  },
16410
16637
  "qwen/qwen3.6-35b-a3b": {
16411
16638
  id: "qwen/qwen3.6-35b-a3b",
@@ -16416,8 +16643,8 @@ export const MODELS = {
16416
16643
  reasoning: true,
16417
16644
  input: ["text", "image"],
16418
16645
  cost: {
16419
- input: 0.09999999999999999,
16420
- output: 0.8999999999999999,
16646
+ input: 0.15,
16647
+ output: 1,
16421
16648
  cacheRead: 0.049999999999999996,
16422
16649
  cacheWrite: 0,
16423
16650
  },
@@ -16543,23 +16770,6 @@ export const MODELS = {
16543
16770
  contextWindow: 1048576,
16544
16771
  maxTokens: 131072,
16545
16772
  },
16546
- "qwen/qwen3.8-2.4t-a95b:batch": {
16547
- id: "qwen/qwen3.8-2.4t-a95b:batch",
16548
- name: "Qwen: Qwen3.8 2.4T A95B (batch)",
16549
- api: "openai-completions",
16550
- provider: "openrouter",
16551
- baseUrl: "https://openrouter.ai/api/v1",
16552
- reasoning: true,
16553
- input: ["text"],
16554
- cost: {
16555
- input: 2,
16556
- output: 6,
16557
- cacheRead: 0.25,
16558
- cacheWrite: 0,
16559
- },
16560
- contextWindow: 1010000,
16561
- maxTokens: 909000,
16562
- },
16563
16773
  "qwen/qwen3.8-27b": {
16564
16774
  id: "qwen/qwen3.8-27b",
16565
16775
  name: "Qwen: Qwen3.8 27B",
@@ -16569,9 +16779,9 @@ export const MODELS = {
16569
16779
  reasoning: true,
16570
16780
  input: ["text", "image"],
16571
16781
  cost: {
16572
- input: 0.21400000000000002,
16573
- output: 2.5500000000000003,
16574
- cacheRead: 0.15,
16782
+ input: 0.42,
16783
+ output: 3,
16784
+ cacheRead: 0.08499999999999999,
16575
16785
  cacheWrite: 0,
16576
16786
  },
16577
16787
  contextWindow: 1000000,
@@ -16866,23 +17076,6 @@ export const MODELS = {
16866
17076
  contextWindow: 1048576,
16867
17077
  maxTokens: 262144,
16868
17078
  },
16869
- "thinkingmachines/inkling:batch": {
16870
- id: "thinkingmachines/inkling:batch",
16871
- name: "Thinking Machines: Inkling (batch)",
16872
- api: "openai-completions",
16873
- provider: "openrouter",
16874
- baseUrl: "https://openrouter.ai/api/v1",
16875
- reasoning: true,
16876
- input: ["text", "image"],
16877
- cost: {
16878
- input: 1,
16879
- output: 4.05,
16880
- cacheRead: 0.16999999999999998,
16881
- cacheWrite: 0,
16882
- },
16883
- contextWindow: 524288,
16884
- maxTokens: 471859,
16885
- },
16886
17079
  "thinkingmachines/inkling:free": {
16887
17080
  id: "thinkingmachines/inkling:free",
16888
17081
  name: "Thinking Machines: Inkling (free)",
@@ -17036,6 +17229,23 @@ export const MODELS = {
17036
17229
  contextWindow: 500000,
17037
17230
  maxTokens: 450000,
17038
17231
  },
17232
+ "x-ai/grok-4.7": {
17233
+ id: "x-ai/grok-4.7",
17234
+ name: "SpaceXAI: Grok 4.7",
17235
+ api: "openai-completions",
17236
+ provider: "openrouter",
17237
+ baseUrl: "https://openrouter.ai/api/v1",
17238
+ reasoning: true,
17239
+ input: ["text", "image"],
17240
+ cost: {
17241
+ input: 1.5999999999999999,
17242
+ output: 4.8,
17243
+ cacheRead: 0.39999999999999997,
17244
+ cacheWrite: 0,
17245
+ },
17246
+ contextWindow: 500000,
17247
+ maxTokens: 450000,
17248
+ },
17039
17249
  "x-ai/grok-build-0.1": {
17040
17250
  id: "x-ai/grok-build-0.1",
17041
17251
  name: "SpaceXAI: Grok Build 0.1",
@@ -17087,6 +17297,57 @@ export const MODELS = {
17087
17297
  contextWindow: 1050000,
17088
17298
  maxTokens: 131072,
17089
17299
  },
17300
+ "xiaomi/mimo-v2.6-flash": {
17301
+ id: "xiaomi/mimo-v2.6-flash",
17302
+ name: "Xiaomi: MiMo-V2.6-Flash",
17303
+ api: "openai-completions",
17304
+ provider: "openrouter",
17305
+ baseUrl: "https://openrouter.ai/api/v1",
17306
+ reasoning: true,
17307
+ input: ["text", "image"],
17308
+ cost: {
17309
+ input: 0.14,
17310
+ output: 0.28,
17311
+ cacheRead: 0.0028,
17312
+ cacheWrite: 0,
17313
+ },
17314
+ contextWindow: 1048576,
17315
+ maxTokens: 131072,
17316
+ },
17317
+ "xiaomi/mimo-v2.6-pro": {
17318
+ id: "xiaomi/mimo-v2.6-pro",
17319
+ name: "Xiaomi: MiMo-V2.6-Pro",
17320
+ api: "openai-completions",
17321
+ provider: "openrouter",
17322
+ baseUrl: "https://openrouter.ai/api/v1",
17323
+ reasoning: true,
17324
+ input: ["text", "image"],
17325
+ cost: {
17326
+ input: 0.435,
17327
+ output: 0.87,
17328
+ cacheRead: 0.0036,
17329
+ cacheWrite: 0,
17330
+ },
17331
+ contextWindow: 1048576,
17332
+ maxTokens: 131072,
17333
+ },
17334
+ "xiaomi/mimo-v2.6-pro-ultraspeed": {
17335
+ id: "xiaomi/mimo-v2.6-pro-ultraspeed",
17336
+ name: "Xiaomi: MiMo-V2.6-Pro-UltraSpeed",
17337
+ api: "openai-completions",
17338
+ provider: "openrouter",
17339
+ baseUrl: "https://openrouter.ai/api/v1",
17340
+ reasoning: true,
17341
+ input: ["text", "image"],
17342
+ cost: {
17343
+ input: 4.35,
17344
+ output: 8.7,
17345
+ cacheRead: 0.036,
17346
+ cacheWrite: 0,
17347
+ },
17348
+ contextWindow: 1048576,
17349
+ maxTokens: 131072,
17350
+ },
17090
17351
  "z-ai/glm-4.5": {
17091
17352
  id: "z-ai/glm-4.5",
17092
17353
  name: "Z.ai: GLM 4.5",
@@ -17266,31 +17527,14 @@ export const MODELS = {
17266
17527
  reasoning: true,
17267
17528
  input: ["text"],
17268
17529
  cost: {
17269
- input: 0.5544,
17270
- output: 1.7424,
17271
- cacheRead: 0.10296000000000001,
17530
+ input: 0.6496,
17531
+ output: 2.0416,
17532
+ cacheRead: 0.12064,
17272
17533
  cacheWrite: 0,
17273
17534
  },
17274
17535
  contextWindow: 1048576,
17275
17536
  maxTokens: 131072,
17276
17537
  },
17277
- "z-ai/glm-5.2:batch": {
17278
- id: "z-ai/glm-5.2:batch",
17279
- name: "Z.ai: GLM 5.2 (batch)",
17280
- api: "openai-completions",
17281
- provider: "openrouter",
17282
- baseUrl: "https://openrouter.ai/api/v1",
17283
- reasoning: true,
17284
- input: ["text"],
17285
- cost: {
17286
- input: 0.7,
17287
- output: 2.2,
17288
- cacheRead: 0.07,
17289
- cacheWrite: 0,
17290
- },
17291
- contextWindow: 1048576,
17292
- maxTokens: 943718,
17293
- },
17294
17538
  "z-ai/glm-5.3": {
17295
17539
  id: "z-ai/glm-5.3",
17296
17540
  name: "Z.ai: GLM 5.3",
@@ -17300,9 +17544,9 @@ export const MODELS = {
17300
17544
  reasoning: true,
17301
17545
  input: ["text"],
17302
17546
  cost: {
17303
- input: 0.9099999999999999,
17304
- output: 2.8600000000000003,
17305
- cacheRead: 0.16899999999999998,
17547
+ input: 0.6537999999999999,
17548
+ output: 2.0547999999999997,
17549
+ cacheRead: 0.12142000000000001,
17306
17550
  cacheWrite: 0,
17307
17551
  },
17308
17552
  contextWindow: 1310720,
@@ -17317,13 +17561,13 @@ export const MODELS = {
17317
17561
  reasoning: true,
17318
17562
  input: ["text", "image"],
17319
17563
  cost: {
17320
- input: 0.09,
17321
- output: 0.3,
17322
- cacheRead: 0.018,
17564
+ input: 0.15,
17565
+ output: 0.5,
17566
+ cacheRead: 0.049999999999999996,
17323
17567
  cacheWrite: 0,
17324
17568
  },
17325
17569
  contextWindow: 1310720,
17326
- maxTokens: 131072,
17570
+ maxTokens: 943718,
17327
17571
  },
17328
17572
  "z-ai/glm-5.3-flash:batch": {
17329
17573
  id: "z-ai/glm-5.3-flash:batch",
@@ -17334,13 +17578,30 @@ export const MODELS = {
17334
17578
  reasoning: true,
17335
17579
  input: ["text", "image"],
17336
17580
  cost: {
17337
- input: 0.075,
17338
- output: 0.25,
17339
- cacheRead: 0.015,
17581
+ input: 0.06,
17582
+ output: 0.19999999999999998,
17583
+ cacheRead: 0.012,
17340
17584
  cacheWrite: 0,
17341
17585
  },
17342
17586
  contextWindow: 1048576,
17343
- maxTokens: 943718,
17587
+ maxTokens: 131072,
17588
+ },
17589
+ "z-ai/glm-5.3-flashx": {
17590
+ id: "z-ai/glm-5.3-flashx",
17591
+ name: "Z.ai: GLM 5.3 FlashX",
17592
+ api: "openai-completions",
17593
+ provider: "openrouter",
17594
+ baseUrl: "https://openrouter.ai/api/v1",
17595
+ reasoning: true,
17596
+ input: ["text", "image"],
17597
+ cost: {
17598
+ input: 0.37,
17599
+ output: 1.25,
17600
+ cacheRead: 0.075,
17601
+ cacheWrite: 0,
17602
+ },
17603
+ contextWindow: 1048576,
17604
+ maxTokens: 131072,
17344
17605
  },
17345
17606
  "z-ai/glm-5.3:batch": {
17346
17607
  id: "z-ai/glm-5.3:batch",
@@ -17351,13 +17612,13 @@ export const MODELS = {
17351
17612
  reasoning: true,
17352
17613
  input: ["text"],
17353
17614
  cost: {
17354
- input: 0.7,
17355
- output: 2.2,
17356
- cacheRead: 0.13,
17615
+ input: 0.72,
17616
+ output: 2.4,
17617
+ cacheRead: 0.12,
17357
17618
  cacheWrite: 0,
17358
17619
  },
17359
17620
  contextWindow: 1048576,
17360
- maxTokens: 943718,
17621
+ maxTokens: 131072,
17361
17622
  },
17362
17623
  "z-ai/glm-5v-turbo": {
17363
17624
  id: "z-ai/glm-5v-turbo",
@@ -17420,10 +17681,10 @@ export const MODELS = {
17420
17681
  reasoning: true,
17421
17682
  input: ["text", "image"],
17422
17683
  cost: {
17423
- input: 5,
17424
- output: 25,
17425
- cacheRead: 0.5,
17426
- cacheWrite: 6.25,
17684
+ input: 4,
17685
+ output: 20,
17686
+ cacheRead: 0.19999999999999998,
17687
+ cacheWrite: 5,
17427
17688
  },
17428
17689
  contextWindow: 1000000,
17429
17690
  maxTokens: 128000,
@@ -17454,13 +17715,13 @@ export const MODELS = {
17454
17715
  reasoning: true,
17455
17716
  input: ["text", "image"],
17456
17717
  cost: {
17457
- input: 0.14,
17458
- output: 0.42,
17459
- cacheRead: 0.004200000000000001,
17718
+ input: 0.12,
17719
+ output: 0.48,
17720
+ cacheRead: 0.0036,
17460
17721
  cacheWrite: 0,
17461
17722
  },
17462
17723
  contextWindow: 1048576,
17463
- maxTokens: 131072,
17724
+ maxTokens: 943718,
17464
17725
  },
17465
17726
  "~deepseek/deepseek-pro-latest": {
17466
17727
  id: "~deepseek/deepseek-pro-latest",
@@ -17471,9 +17732,9 @@ export const MODELS = {
17471
17732
  reasoning: true,
17472
17733
  input: ["text"],
17473
17734
  cost: {
17474
- input: 0.57816,
17475
- output: 1.73448,
17476
- cacheRead: 0.018396000000000003,
17735
+ input: 0.54648,
17736
+ output: 1.63944,
17737
+ cacheRead: 0.017388,
17477
17738
  cacheWrite: 0,
17478
17739
  },
17479
17740
  contextWindow: 1048576,
@@ -17490,13 +17751,13 @@ export const MODELS = {
17490
17751
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
17491
17752
  input: ["text"],
17492
17753
  cost: {
17493
- input: 0.054119999999999994,
17494
- output: 0.16236,
17495
- cacheRead: 0.001722,
17754
+ input: 0.03,
17755
+ output: 1,
17756
+ cacheRead: 0.008,
17496
17757
  cacheWrite: 0,
17497
17758
  },
17498
17759
  contextWindow: 1310720,
17499
- maxTokens: 384000,
17760
+ maxTokens: 943718,
17500
17761
  },
17501
17762
  "~google/gemini-flash-latest": {
17502
17763
  id: "~google/gemini-flash-latest",
@@ -17541,9 +17802,9 @@ export const MODELS = {
17541
17802
  reasoning: true,
17542
17803
  input: ["text", "image"],
17543
17804
  cost: {
17544
- input: 1.95,
17545
- output: 10.92,
17546
- cacheRead: 0.2262,
17805
+ input: 1.5,
17806
+ output: 7.5,
17807
+ cacheRead: 0.15,
17547
17808
  cacheWrite: 0,
17548
17809
  },
17549
17810
  contextWindow: 1048576,
@@ -17643,9 +17904,9 @@ export const MODELS = {
17643
17904
  reasoning: true,
17644
17905
  input: ["text", "image"],
17645
17906
  cost: {
17646
- input: 2,
17647
- output: 6,
17648
- cacheRead: 0.5,
17907
+ input: 1.5999999999999999,
17908
+ output: 4.8,
17909
+ cacheRead: 0.39999999999999997,
17649
17910
  cacheWrite: 0,
17650
17911
  },
17651
17912
  contextWindow: 500000,
@@ -17666,7 +17927,7 @@ export const MODELS = {
17666
17927
  cacheWrite: 0,
17667
17928
  },
17668
17929
  contextWindow: 1310720,
17669
- maxTokens: 131072,
17930
+ maxTokens: 943718,
17670
17931
  },
17671
17932
  "~z-ai/glm-latest": {
17672
17933
  id: "~z-ai/glm-latest",
@@ -17677,9 +17938,9 @@ export const MODELS = {
17677
17938
  reasoning: true,
17678
17939
  input: ["text"],
17679
17940
  cost: {
17680
- input: 0.8917999999999999,
17681
- output: 2.8028,
17682
- cacheRead: 0.16562,
17941
+ input: 0.6537999999999999,
17942
+ output: 2.0547999999999997,
17943
+ cacheRead: 0.12142000000000001,
17683
17944
  cacheWrite: 0,
17684
17945
  },
17685
17946
  contextWindow: 1310720,
@@ -18909,6 +19170,40 @@ export const MODELS = {
18909
19170
  contextWindow: 1000000,
18910
19171
  maxTokens: 128000,
18911
19172
  },
19173
+ "anthropic/claude-opus-5.5": {
19174
+ id: "anthropic/claude-opus-5.5",
19175
+ name: "Claude Opus 5.5",
19176
+ api: "anthropic-messages",
19177
+ provider: "vercel-ai-gateway",
19178
+ baseUrl: "https://ai-gateway.vercel.sh",
19179
+ reasoning: true,
19180
+ input: ["text", "image"],
19181
+ cost: {
19182
+ input: 4,
19183
+ output: 20,
19184
+ cacheRead: 0.19999999999999998,
19185
+ cacheWrite: 5,
19186
+ },
19187
+ contextWindow: 1000000,
19188
+ maxTokens: 128000,
19189
+ },
19190
+ "anthropic/claude-opus-5.5-fast": {
19191
+ id: "anthropic/claude-opus-5.5-fast",
19192
+ name: "Claude Opus 5.5 (Fast)",
19193
+ api: "anthropic-messages",
19194
+ provider: "vercel-ai-gateway",
19195
+ baseUrl: "https://ai-gateway.vercel.sh",
19196
+ reasoning: true,
19197
+ input: ["text", "image"],
19198
+ cost: {
19199
+ input: 8,
19200
+ output: 40,
19201
+ cacheRead: 0.39999999999999997,
19202
+ cacheWrite: 10,
19203
+ },
19204
+ contextWindow: 1000000,
19205
+ maxTokens: 128000,
19206
+ },
18912
19207
  "anthropic/claude-sonnet-4": {
18913
19208
  id: "anthropic/claude-sonnet-4",
18914
19209
  name: "Claude Sonnet 4",
@@ -19243,7 +19538,7 @@ export const MODELS = {
19243
19538
  cost: {
19244
19539
  input: 0.3,
19245
19540
  output: 1.2,
19246
- cacheRead: 0.03,
19541
+ cacheRead: 0.007,
19247
19542
  cacheWrite: 0,
19248
19543
  },
19249
19544
  contextWindow: 1048576,
@@ -20116,6 +20411,23 @@ export const MODELS = {
20116
20411
  contextWindow: 262144,
20117
20412
  maxTokens: 4000,
20118
20413
  },
20414
+ "mixedbread/toast-1": {
20415
+ id: "mixedbread/toast-1",
20416
+ name: "Toast 1",
20417
+ api: "anthropic-messages",
20418
+ provider: "vercel-ai-gateway",
20419
+ baseUrl: "https://ai-gateway.vercel.sh",
20420
+ reasoning: false,
20421
+ input: ["text"],
20422
+ cost: {
20423
+ input: 0.3,
20424
+ output: 0.72,
20425
+ cacheRead: 0.036,
20426
+ cacheWrite: 0,
20427
+ },
20428
+ contextWindow: 131000,
20429
+ maxTokens: 4000,
20430
+ },
20119
20431
  "moonshotai/kimi-k2": {
20120
20432
  id: "moonshotai/kimi-k2",
20121
20433
  name: "Kimi K2 Instruct",
@@ -21058,10 +21370,10 @@ export const MODELS = {
21058
21370
  reasoning: true,
21059
21371
  input: ["text", "image"],
21060
21372
  cost: {
21061
- input: 2,
21062
- output: 10,
21063
- cacheRead: 0.19999999999999998,
21064
- cacheWrite: 2.5,
21373
+ input: 4,
21374
+ output: 20,
21375
+ cacheRead: 0.39999999999999997,
21376
+ cacheWrite: 5,
21065
21377
  },
21066
21378
  contextWindow: 1050000,
21067
21379
  maxTokens: 128000,
@@ -21075,10 +21387,10 @@ export const MODELS = {
21075
21387
  reasoning: true,
21076
21388
  input: ["text", "image"],
21077
21389
  cost: {
21078
- input: 4,
21079
- output: 20,
21080
- cacheRead: 0.39999999999999997,
21081
- cacheWrite: 5,
21390
+ input: 8,
21391
+ output: 40,
21392
+ cacheRead: 0.7999999999999999,
21393
+ cacheWrite: 10,
21082
21394
  },
21083
21395
  contextWindow: 1050000,
21084
21396
  maxTokens: 128000,
@@ -21372,6 +21684,40 @@ export const MODELS = {
21372
21684
  contextWindow: 256000,
21373
21685
  maxTokens: 32768,
21374
21686
  },
21687
+ "quiverai/arrow-2": {
21688
+ id: "quiverai/arrow-2",
21689
+ name: "Arrow 2",
21690
+ api: "anthropic-messages",
21691
+ provider: "vercel-ai-gateway",
21692
+ baseUrl: "https://ai-gateway.vercel.sh",
21693
+ reasoning: true,
21694
+ input: ["text", "image"],
21695
+ cost: {
21696
+ input: 4,
21697
+ output: 20,
21698
+ cacheRead: 0.39999999999999997,
21699
+ cacheWrite: 5,
21700
+ },
21701
+ contextWindow: 131072,
21702
+ maxTokens: 131072,
21703
+ },
21704
+ "quiverai/arrow-2-telos": {
21705
+ id: "quiverai/arrow-2-telos",
21706
+ name: "Arrow 2 Telos",
21707
+ api: "anthropic-messages",
21708
+ provider: "vercel-ai-gateway",
21709
+ baseUrl: "https://ai-gateway.vercel.sh",
21710
+ reasoning: true,
21711
+ input: ["text", "image"],
21712
+ cost: {
21713
+ input: 6,
21714
+ output: 30,
21715
+ cacheRead: 0.6,
21716
+ cacheWrite: 7.5,
21717
+ },
21718
+ contextWindow: 131072,
21719
+ maxTokens: 131072,
21720
+ },
21375
21721
  "sakana/fugu-max": {
21376
21722
  id: "sakana/fugu-max",
21377
21723
  name: "Fugu Max",
@@ -21627,6 +21973,23 @@ export const MODELS = {
21627
21973
  contextWindow: 500000,
21628
21974
  maxTokens: 500000,
21629
21975
  },
21976
+ "spacexai/grok-4.7": {
21977
+ id: "spacexai/grok-4.7",
21978
+ name: "Grok 4.7",
21979
+ api: "anthropic-messages",
21980
+ provider: "vercel-ai-gateway",
21981
+ baseUrl: "https://ai-gateway.vercel.sh",
21982
+ reasoning: true,
21983
+ input: ["text", "image"],
21984
+ cost: {
21985
+ input: 1.2,
21986
+ output: 3.5999999999999996,
21987
+ cacheRead: 0.3,
21988
+ cacheWrite: 0,
21989
+ },
21990
+ contextWindow: 500000,
21991
+ maxTokens: 500000,
21992
+ },
21630
21993
  "spacexai/grok-build-0.1": {
21631
21994
  id: "spacexai/grok-build-0.1",
21632
21995
  name: "Grok Build 0.1",
@@ -21780,6 +22143,57 @@ export const MODELS = {
21780
22143
  contextWindow: 1050000,
21781
22144
  maxTokens: 131000,
21782
22145
  },
22146
+ "xiaomi/mimo-v2.6-flash": {
22147
+ id: "xiaomi/mimo-v2.6-flash",
22148
+ name: "MiMo V2.6 Flash",
22149
+ api: "anthropic-messages",
22150
+ provider: "vercel-ai-gateway",
22151
+ baseUrl: "https://ai-gateway.vercel.sh",
22152
+ reasoning: true,
22153
+ input: ["text", "image"],
22154
+ cost: {
22155
+ input: 0.14,
22156
+ output: 0.28,
22157
+ cacheRead: 0.0028,
22158
+ cacheWrite: 0,
22159
+ },
22160
+ contextWindow: 1048576,
22161
+ maxTokens: 131072,
22162
+ },
22163
+ "xiaomi/mimo-v2.6-pro": {
22164
+ id: "xiaomi/mimo-v2.6-pro",
22165
+ name: "MiMo V2.6 Pro",
22166
+ api: "anthropic-messages",
22167
+ provider: "vercel-ai-gateway",
22168
+ baseUrl: "https://ai-gateway.vercel.sh",
22169
+ reasoning: true,
22170
+ input: ["text", "image"],
22171
+ cost: {
22172
+ input: 0.435,
22173
+ output: 0.87,
22174
+ cacheRead: 0.0036,
22175
+ cacheWrite: 0,
22176
+ },
22177
+ contextWindow: 1048576,
22178
+ maxTokens: 131072,
22179
+ },
22180
+ "xiaomi/mimo-v2.6-pro-ultraspeed": {
22181
+ id: "xiaomi/mimo-v2.6-pro-ultraspeed",
22182
+ name: "MiMo V2.6 Pro UltraSpeed",
22183
+ api: "anthropic-messages",
22184
+ provider: "vercel-ai-gateway",
22185
+ baseUrl: "https://ai-gateway.vercel.sh",
22186
+ reasoning: true,
22187
+ input: ["text", "image"],
22188
+ cost: {
22189
+ input: 4.35,
22190
+ output: 8.7,
22191
+ cacheRead: 0.036,
22192
+ cacheWrite: 0,
22193
+ },
22194
+ contextWindow: 1048576,
22195
+ maxTokens: 131072,
22196
+ },
21783
22197
  "zai/glm-4.5": {
21784
22198
  id: "zai/glm-4.5",
21785
22199
  name: "GLM 4.5",
@@ -22156,6 +22570,23 @@ export const MODELS = {
22156
22570
  contextWindow: 500000,
22157
22571
  maxTokens: 500000,
22158
22572
  },
22573
+ "grok-4.7": {
22574
+ id: "grok-4.7",
22575
+ name: "Grok 4.7",
22576
+ api: "openai-completions",
22577
+ provider: "xai",
22578
+ baseUrl: "https://api.x.ai/v1",
22579
+ reasoning: true,
22580
+ input: ["text", "image"],
22581
+ cost: {
22582
+ input: 2,
22583
+ output: 6,
22584
+ cacheRead: 0.5,
22585
+ cacheWrite: 0,
22586
+ },
22587
+ contextWindow: 500000,
22588
+ maxTokens: 500000,
22589
+ },
22159
22590
  "grok-build-0.1": {
22160
22591
  id: "grok-build-0.1",
22161
22592
  name: "Grok Build 0.1",
@@ -22243,6 +22674,57 @@ export const MODELS = {
22243
22674
  contextWindow: 1048576,
22244
22675
  maxTokens: 131072,
22245
22676
  },
22677
+ "mimo-v2.6-flash": {
22678
+ id: "mimo-v2.6-flash",
22679
+ name: "MiMo-V2.6-Flash",
22680
+ api: "anthropic-messages",
22681
+ provider: "xiaomi",
22682
+ baseUrl: "https://api.xiaomimimo.com/anthropic",
22683
+ reasoning: true,
22684
+ input: ["text", "image"],
22685
+ cost: {
22686
+ input: 0.14,
22687
+ output: 0.28,
22688
+ cacheRead: 0.0028,
22689
+ cacheWrite: 0,
22690
+ },
22691
+ contextWindow: 1048576,
22692
+ maxTokens: 131072,
22693
+ },
22694
+ "mimo-v2.6-pro": {
22695
+ id: "mimo-v2.6-pro",
22696
+ name: "MiMo-V2.6-Pro",
22697
+ api: "anthropic-messages",
22698
+ provider: "xiaomi",
22699
+ baseUrl: "https://api.xiaomimimo.com/anthropic",
22700
+ reasoning: true,
22701
+ input: ["text", "image"],
22702
+ cost: {
22703
+ input: 0.435,
22704
+ output: 0.87,
22705
+ cacheRead: 0.0036,
22706
+ cacheWrite: 0,
22707
+ },
22708
+ contextWindow: 1048576,
22709
+ maxTokens: 131072,
22710
+ },
22711
+ "mimo-v2.6-pro-ultraspeed": {
22712
+ id: "mimo-v2.6-pro-ultraspeed",
22713
+ name: "MiMo-V2.6-Pro-UltraSpeed",
22714
+ api: "anthropic-messages",
22715
+ provider: "xiaomi",
22716
+ baseUrl: "https://api.xiaomimimo.com/anthropic",
22717
+ reasoning: true,
22718
+ input: ["text", "image"],
22719
+ cost: {
22720
+ input: 4.35,
22721
+ output: 8.7,
22722
+ cacheRead: 0.036,
22723
+ cacheWrite: 0,
22724
+ },
22725
+ contextWindow: 1048576,
22726
+ maxTokens: 131072,
22727
+ },
22246
22728
  },
22247
22729
  "xiaomi-token-plan-ams": {
22248
22730
  "mimo-v2.5": {
@@ -22296,6 +22778,57 @@ export const MODELS = {
22296
22778
  contextWindow: 1048576,
22297
22779
  maxTokens: 131072,
22298
22780
  },
22781
+ "mimo-v2.6-flash": {
22782
+ id: "mimo-v2.6-flash",
22783
+ name: "MiMo-V2.6-Flash",
22784
+ api: "anthropic-messages",
22785
+ provider: "xiaomi-token-plan-ams",
22786
+ baseUrl: "https://token-plan-ams.xiaomimimo.com/anthropic",
22787
+ reasoning: true,
22788
+ input: ["text", "image"],
22789
+ cost: {
22790
+ input: 0.14,
22791
+ output: 0.28,
22792
+ cacheRead: 0.0028,
22793
+ cacheWrite: 0,
22794
+ },
22795
+ contextWindow: 1048576,
22796
+ maxTokens: 131072,
22797
+ },
22798
+ "mimo-v2.6-pro": {
22799
+ id: "mimo-v2.6-pro",
22800
+ name: "MiMo-V2.6-Pro",
22801
+ api: "anthropic-messages",
22802
+ provider: "xiaomi-token-plan-ams",
22803
+ baseUrl: "https://token-plan-ams.xiaomimimo.com/anthropic",
22804
+ reasoning: true,
22805
+ input: ["text", "image"],
22806
+ cost: {
22807
+ input: 0.435,
22808
+ output: 0.87,
22809
+ cacheRead: 0.0036,
22810
+ cacheWrite: 0,
22811
+ },
22812
+ contextWindow: 1048576,
22813
+ maxTokens: 131072,
22814
+ },
22815
+ "mimo-v2.6-pro-ultraspeed": {
22816
+ id: "mimo-v2.6-pro-ultraspeed",
22817
+ name: "MiMo-V2.6-Pro-UltraSpeed",
22818
+ api: "anthropic-messages",
22819
+ provider: "xiaomi-token-plan-ams",
22820
+ baseUrl: "https://token-plan-ams.xiaomimimo.com/anthropic",
22821
+ reasoning: true,
22822
+ input: ["text", "image"],
22823
+ cost: {
22824
+ input: 4.35,
22825
+ output: 8.7,
22826
+ cacheRead: 0.036,
22827
+ cacheWrite: 0,
22828
+ },
22829
+ contextWindow: 1048576,
22830
+ maxTokens: 131072,
22831
+ },
22299
22832
  },
22300
22833
  "xiaomi-token-plan-cn": {
22301
22834
  "mimo-v2.5": {
@@ -22349,6 +22882,57 @@ export const MODELS = {
22349
22882
  contextWindow: 1048576,
22350
22883
  maxTokens: 131072,
22351
22884
  },
22885
+ "mimo-v2.6-flash": {
22886
+ id: "mimo-v2.6-flash",
22887
+ name: "MiMo-V2.6-Flash",
22888
+ api: "anthropic-messages",
22889
+ provider: "xiaomi-token-plan-cn",
22890
+ baseUrl: "https://token-plan-cn.xiaomimimo.com/anthropic",
22891
+ reasoning: true,
22892
+ input: ["text", "image"],
22893
+ cost: {
22894
+ input: 0.14,
22895
+ output: 0.28,
22896
+ cacheRead: 0.0028,
22897
+ cacheWrite: 0,
22898
+ },
22899
+ contextWindow: 1048576,
22900
+ maxTokens: 131072,
22901
+ },
22902
+ "mimo-v2.6-pro": {
22903
+ id: "mimo-v2.6-pro",
22904
+ name: "MiMo-V2.6-Pro",
22905
+ api: "anthropic-messages",
22906
+ provider: "xiaomi-token-plan-cn",
22907
+ baseUrl: "https://token-plan-cn.xiaomimimo.com/anthropic",
22908
+ reasoning: true,
22909
+ input: ["text", "image"],
22910
+ cost: {
22911
+ input: 0.435,
22912
+ output: 0.87,
22913
+ cacheRead: 0.0036,
22914
+ cacheWrite: 0,
22915
+ },
22916
+ contextWindow: 1048576,
22917
+ maxTokens: 131072,
22918
+ },
22919
+ "mimo-v2.6-pro-ultraspeed": {
22920
+ id: "mimo-v2.6-pro-ultraspeed",
22921
+ name: "MiMo-V2.6-Pro-UltraSpeed",
22922
+ api: "anthropic-messages",
22923
+ provider: "xiaomi-token-plan-cn",
22924
+ baseUrl: "https://token-plan-cn.xiaomimimo.com/anthropic",
22925
+ reasoning: true,
22926
+ input: ["text", "image"],
22927
+ cost: {
22928
+ input: 4.35,
22929
+ output: 8.7,
22930
+ cacheRead: 0.036,
22931
+ cacheWrite: 0,
22932
+ },
22933
+ contextWindow: 1048576,
22934
+ maxTokens: 131072,
22935
+ },
22352
22936
  },
22353
22937
  "xiaomi-token-plan-sgp": {
22354
22938
  "mimo-v2.5": {
@@ -22402,6 +22986,57 @@ export const MODELS = {
22402
22986
  contextWindow: 1048576,
22403
22987
  maxTokens: 131072,
22404
22988
  },
22989
+ "mimo-v2.6-flash": {
22990
+ id: "mimo-v2.6-flash",
22991
+ name: "MiMo-V2.6-Flash",
22992
+ api: "anthropic-messages",
22993
+ provider: "xiaomi-token-plan-sgp",
22994
+ baseUrl: "https://token-plan-sgp.xiaomimimo.com/anthropic",
22995
+ reasoning: true,
22996
+ input: ["text", "image"],
22997
+ cost: {
22998
+ input: 0.14,
22999
+ output: 0.28,
23000
+ cacheRead: 0.0028,
23001
+ cacheWrite: 0,
23002
+ },
23003
+ contextWindow: 1048576,
23004
+ maxTokens: 131072,
23005
+ },
23006
+ "mimo-v2.6-pro": {
23007
+ id: "mimo-v2.6-pro",
23008
+ name: "MiMo-V2.6-Pro",
23009
+ api: "anthropic-messages",
23010
+ provider: "xiaomi-token-plan-sgp",
23011
+ baseUrl: "https://token-plan-sgp.xiaomimimo.com/anthropic",
23012
+ reasoning: true,
23013
+ input: ["text", "image"],
23014
+ cost: {
23015
+ input: 0.435,
23016
+ output: 0.87,
23017
+ cacheRead: 0.0036,
23018
+ cacheWrite: 0,
23019
+ },
23020
+ contextWindow: 1048576,
23021
+ maxTokens: 131072,
23022
+ },
23023
+ "mimo-v2.6-pro-ultraspeed": {
23024
+ id: "mimo-v2.6-pro-ultraspeed",
23025
+ name: "MiMo-V2.6-Pro-UltraSpeed",
23026
+ api: "anthropic-messages",
23027
+ provider: "xiaomi-token-plan-sgp",
23028
+ baseUrl: "https://token-plan-sgp.xiaomimimo.com/anthropic",
23029
+ reasoning: true,
23030
+ input: ["text", "image"],
23031
+ cost: {
23032
+ input: 4.35,
23033
+ output: 8.7,
23034
+ cacheRead: 0.036,
23035
+ cacheWrite: 0,
23036
+ },
23037
+ contextWindow: 1048576,
23038
+ maxTokens: 131072,
23039
+ },
22405
23040
  },
22406
23041
  "zai": {
22407
23042
  "glm-4.7": {