@elyracode/ai 0.9.43 → 0.9.45

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.
@@ -309,6 +309,24 @@ export const MODELS = {
309
309
  contextWindow: 1000000,
310
310
  maxTokens: 128000,
311
311
  },
312
+ "anthropic.claude-sonnet-5-5": {
313
+ id: "anthropic.claude-sonnet-5-5",
314
+ name: "Claude Sonnet 5.5",
315
+ api: "bedrock-converse-stream",
316
+ provider: "amazon-bedrock",
317
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
318
+ reasoning: true,
319
+ thinkingType: "adaptive",
320
+ input: ["text", "image"],
321
+ cost: {
322
+ input: 2,
323
+ output: 10,
324
+ cacheRead: 0.2,
325
+ cacheWrite: 2.5,
326
+ },
327
+ contextWindow: 1000000,
328
+ maxTokens: 128000,
329
+ },
312
330
  "apac.amazon.nova-lite-v1:0": {
313
331
  id: "apac.amazon.nova-lite-v1:0",
314
332
  name: "Nova Lite (APAC)",
@@ -1155,6 +1173,24 @@ export const MODELS = {
1155
1173
  contextWindow: 1000000,
1156
1174
  maxTokens: 128000,
1157
1175
  },
1176
+ "global.anthropic.claude-sonnet-5-5": {
1177
+ id: "global.anthropic.claude-sonnet-5-5",
1178
+ name: "Claude Sonnet 5.5 (Global)",
1179
+ api: "bedrock-converse-stream",
1180
+ provider: "amazon-bedrock",
1181
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1182
+ reasoning: true,
1183
+ thinkingType: "adaptive",
1184
+ input: ["text", "image"],
1185
+ cost: {
1186
+ input: 2,
1187
+ output: 10,
1188
+ cacheRead: 0.2,
1189
+ cacheWrite: 2.5,
1190
+ },
1191
+ contextWindow: 1000000,
1192
+ maxTokens: 128000,
1193
+ },
1158
1194
  "global.moonshotai.kimi-k3": {
1159
1195
  id: "global.moonshotai.kimi-k3",
1160
1196
  name: "Kimi K3 (Global)",
@@ -1291,6 +1327,23 @@ export const MODELS = {
1291
1327
  contextWindow: 500000,
1292
1328
  maxTokens: 500000,
1293
1329
  },
1330
+ "global.xai.grok-4.7": {
1331
+ id: "global.xai.grok-4.7",
1332
+ name: "Grok 4.7 (Global)",
1333
+ api: "bedrock-converse-stream",
1334
+ provider: "amazon-bedrock",
1335
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1336
+ reasoning: true,
1337
+ input: ["text", "image"],
1338
+ cost: {
1339
+ input: 2,
1340
+ output: 6,
1341
+ cacheRead: 0.5,
1342
+ cacheWrite: 0,
1343
+ },
1344
+ contextWindow: 500000,
1345
+ maxTokens: 500000,
1346
+ },
1294
1347
  "google.gemma-4-26b-a4b": {
1295
1348
  id: "google.gemma-4-26b-a4b",
1296
1349
  name: "Gemma 4 26B A4B IT",
@@ -2937,6 +2990,23 @@ export const MODELS = {
2937
2990
  contextWindow: 500000,
2938
2991
  maxTokens: 500000,
2939
2992
  },
2993
+ "us.xai.grok-4.7": {
2994
+ id: "us.xai.grok-4.7",
2995
+ name: "Grok 4.7 (US)",
2996
+ api: "bedrock-converse-stream",
2997
+ provider: "amazon-bedrock",
2998
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2999
+ reasoning: true,
3000
+ input: ["text", "image"],
3001
+ cost: {
3002
+ input: 2.2,
3003
+ output: 6.6,
3004
+ cacheRead: 0.55,
3005
+ cacheWrite: 0,
3006
+ },
3007
+ contextWindow: 500000,
3008
+ maxTokens: 500000,
3009
+ },
2940
3010
  "writer.palmyra-x4-v1:0": {
2941
3011
  id: "writer.palmyra-x4-v1:0",
2942
3012
  name: "Palmyra X4",
@@ -3333,6 +3403,24 @@ export const MODELS = {
3333
3403
  contextWindow: 1000000,
3334
3404
  maxTokens: 128000,
3335
3405
  },
3406
+ "claude-sonnet-5-5": {
3407
+ id: "claude-sonnet-5-5",
3408
+ name: "Claude Sonnet 5.5",
3409
+ api: "anthropic-messages",
3410
+ provider: "anthropic",
3411
+ baseUrl: "https://api.anthropic.com",
3412
+ reasoning: true,
3413
+ thinkingType: "adaptive",
3414
+ input: ["text", "image"],
3415
+ cost: {
3416
+ input: 2,
3417
+ output: 10,
3418
+ cacheRead: 0.2,
3419
+ cacheWrite: 2.5,
3420
+ },
3421
+ contextWindow: 1000000,
3422
+ maxTokens: 128000,
3423
+ },
3336
3424
  },
3337
3425
  "azure-openai-responses": {
3338
3426
  "gpt-4": {
@@ -3920,6 +4008,57 @@ export const MODELS = {
3920
4008
  contextWindow: 1050000,
3921
4009
  maxTokens: 128000,
3922
4010
  },
4011
+ "gpt-6.1-sol": {
4012
+ id: "gpt-6.1-sol",
4013
+ name: "GPT-6.1 Sol",
4014
+ api: "azure-openai-responses",
4015
+ provider: "azure-openai-responses",
4016
+ baseUrl: "",
4017
+ reasoning: true,
4018
+ input: ["text", "image"],
4019
+ cost: {
4020
+ input: 2,
4021
+ output: 10,
4022
+ cacheRead: 0.1,
4023
+ cacheWrite: 2.5,
4024
+ },
4025
+ contextWindow: 1050000,
4026
+ maxTokens: 128000,
4027
+ },
4028
+ "gpt-daybreak-blue-latest": {
4029
+ id: "gpt-daybreak-blue-latest",
4030
+ name: "Daybreak Blue",
4031
+ api: "azure-openai-responses",
4032
+ provider: "azure-openai-responses",
4033
+ baseUrl: "",
4034
+ reasoning: true,
4035
+ input: ["text", "image"],
4036
+ cost: {
4037
+ input: 4,
4038
+ output: 20,
4039
+ cacheRead: 0.4,
4040
+ cacheWrite: 5,
4041
+ },
4042
+ contextWindow: 1050000,
4043
+ maxTokens: 128000,
4044
+ },
4045
+ "gpt-daybreak-red-latest": {
4046
+ id: "gpt-daybreak-red-latest",
4047
+ name: "Daybreak Red",
4048
+ api: "azure-openai-responses",
4049
+ provider: "azure-openai-responses",
4050
+ baseUrl: "",
4051
+ reasoning: true,
4052
+ input: ["text", "image"],
4053
+ cost: {
4054
+ input: 12.5,
4055
+ output: 75,
4056
+ cacheRead: 1.25,
4057
+ cacheWrite: 15.625,
4058
+ },
4059
+ contextWindow: 400000,
4060
+ maxTokens: 128000,
4061
+ },
3923
4062
  "gpt-realtime-2.1": {
3924
4063
  id: "gpt-realtime-2.1",
3925
4064
  name: "GPT-Realtime-2.1",
@@ -4069,11 +4208,11 @@ export const MODELS = {
4069
4208
  cost: {
4070
4209
  input: 0.99,
4071
4210
  output: 1.49,
4072
- cacheRead: 0,
4211
+ cacheRead: 0.99,
4073
4212
  cacheWrite: 0,
4074
4213
  },
4075
- contextWindow: 65536,
4076
- maxTokens: 32768,
4214
+ contextWindow: 131072,
4215
+ maxTokens: 40960,
4077
4216
  },
4078
4217
  },
4079
4218
  "cloudflare-ai-gateway": {
@@ -4249,7 +4388,7 @@ export const MODELS = {
4249
4388
  cacheRead: 0.3,
4250
4389
  cacheWrite: 3.75,
4251
4390
  },
4252
- contextWindow: 1000000,
4391
+ contextWindow: 200000,
4253
4392
  maxTokens: 64000,
4254
4393
  },
4255
4394
  "claude-sonnet-4.6": {
@@ -4725,7 +4864,7 @@ export const MODELS = {
4725
4864
  cacheRead: 0.014,
4726
4865
  cacheWrite: 0,
4727
4866
  },
4728
- contextWindow: 1310720,
4867
+ contextWindow: 1048576,
4729
4868
  maxTokens: 1048576,
4730
4869
  },
4731
4870
  "@cf/deepseek-ai/deepseek-v4-pro-0813": {
@@ -5014,7 +5153,7 @@ export const MODELS = {
5014
5153
  cacheRead: 0.26,
5015
5154
  cacheWrite: 0,
5016
5155
  },
5017
- contextWindow: 1310720,
5156
+ contextWindow: 1048576,
5018
5157
  maxTokens: 1048576,
5019
5158
  },
5020
5159
  "@cf/zai-org/glm-5.3-flash": {
@@ -5032,7 +5171,7 @@ export const MODELS = {
5032
5171
  cacheRead: 0.03,
5033
5172
  cacheWrite: 0,
5034
5173
  },
5035
- contextWindow: 1310720,
5174
+ contextWindow: 1048576,
5036
5175
  maxTokens: 1048576,
5037
5176
  },
5038
5177
  },
@@ -5077,74 +5216,6 @@ export const MODELS = {
5077
5216
  },
5078
5217
  },
5079
5218
  "fireworks": {
5080
- "accounts/fireworks/models/deepseek-v4-flash-0731": {
5081
- id: "accounts/fireworks/models/deepseek-v4-flash-0731",
5082
- name: "DeepSeek V4 Flash 0731",
5083
- api: "anthropic-messages",
5084
- provider: "fireworks",
5085
- baseUrl: "https://api.fireworks.ai/inference",
5086
- reasoning: true,
5087
- input: ["text"],
5088
- cost: {
5089
- input: 0.22,
5090
- output: 0.66,
5091
- cacheRead: 0.007,
5092
- cacheWrite: 0,
5093
- },
5094
- contextWindow: 1000000,
5095
- maxTokens: 384000,
5096
- },
5097
- "accounts/fireworks/models/deepseek-v4-flash-vision-exp": {
5098
- id: "accounts/fireworks/models/deepseek-v4-flash-vision-exp",
5099
- name: "DeepSeek V4 Flash Vision Exp",
5100
- api: "anthropic-messages",
5101
- provider: "fireworks",
5102
- baseUrl: "https://api.fireworks.ai/inference",
5103
- reasoning: true,
5104
- input: ["text", "image"],
5105
- cost: {
5106
- input: 0.22,
5107
- output: 0.66,
5108
- cacheRead: 0.007,
5109
- cacheWrite: 0,
5110
- },
5111
- contextWindow: 1000000,
5112
- maxTokens: 384000,
5113
- },
5114
- "accounts/fireworks/models/deepseek-v4-pro": {
5115
- id: "accounts/fireworks/models/deepseek-v4-pro",
5116
- name: "DeepSeek V4 Pro",
5117
- api: "anthropic-messages",
5118
- provider: "fireworks",
5119
- baseUrl: "https://api.fireworks.ai/inference",
5120
- reasoning: true,
5121
- input: ["text"],
5122
- cost: {
5123
- input: 1.2,
5124
- output: 1.2,
5125
- cacheRead: 0.6,
5126
- cacheWrite: 0,
5127
- },
5128
- contextWindow: 1000000,
5129
- maxTokens: 384000,
5130
- },
5131
- "accounts/fireworks/models/deepseek-v4-pro-0813": {
5132
- id: "accounts/fireworks/models/deepseek-v4-pro-0813",
5133
- name: "DeepSeek V4 Pro 0813",
5134
- api: "anthropic-messages",
5135
- provider: "fireworks",
5136
- baseUrl: "https://api.fireworks.ai/inference",
5137
- reasoning: true,
5138
- input: ["text"],
5139
- cost: {
5140
- input: 1.32,
5141
- output: 3.96,
5142
- cacheRead: 0.044,
5143
- cacheWrite: 0,
5144
- },
5145
- contextWindow: 1000000,
5146
- maxTokens: 384000,
5147
- },
5148
5219
  "accounts/fireworks/models/deepseek-v4p1-flash": {
5149
5220
  id: "accounts/fireworks/models/deepseek-v4p1-flash",
5150
5221
  name: "DeepSeek V4.1 Flash",
@@ -5179,23 +5250,6 @@ export const MODELS = {
5179
5250
  contextWindow: 1048576,
5180
5251
  maxTokens: 131072,
5181
5252
  },
5182
- "accounts/fireworks/models/glm-5p2": {
5183
- id: "accounts/fireworks/models/glm-5p2",
5184
- name: "GLM 5.2",
5185
- api: "anthropic-messages",
5186
- provider: "fireworks",
5187
- baseUrl: "https://api.fireworks.ai/inference",
5188
- reasoning: true,
5189
- input: ["text"],
5190
- cost: {
5191
- input: 1.4,
5192
- output: 4.4,
5193
- cacheRead: 0.14,
5194
- cacheWrite: 0,
5195
- },
5196
- contextWindow: 1048575,
5197
- maxTokens: 131072,
5198
- },
5199
5253
  "accounts/fireworks/models/glm-5p3": {
5200
5254
  id: "accounts/fireworks/models/glm-5p3",
5201
5255
  name: "GLM 5.3",
@@ -5264,40 +5318,6 @@ export const MODELS = {
5264
5318
  contextWindow: 1048576,
5265
5319
  maxTokens: 1048576,
5266
5320
  },
5267
- "accounts/fireworks/models/kimi-k2p6": {
5268
- id: "accounts/fireworks/models/kimi-k2p6",
5269
- name: "Kimi K2.6",
5270
- api: "anthropic-messages",
5271
- provider: "fireworks",
5272
- baseUrl: "https://api.fireworks.ai/inference",
5273
- reasoning: true,
5274
- input: ["text", "image"],
5275
- cost: {
5276
- input: 0.95,
5277
- output: 4,
5278
- cacheRead: 0.16,
5279
- cacheWrite: 0,
5280
- },
5281
- contextWindow: 262000,
5282
- maxTokens: 262000,
5283
- },
5284
- "accounts/fireworks/models/kimi-k2p7-code": {
5285
- id: "accounts/fireworks/models/kimi-k2p7-code",
5286
- name: "Kimi K2.7 Code",
5287
- api: "anthropic-messages",
5288
- provider: "fireworks",
5289
- baseUrl: "https://api.fireworks.ai/inference",
5290
- reasoning: true,
5291
- input: ["text", "image"],
5292
- cost: {
5293
- input: 0.95,
5294
- output: 4,
5295
- cacheRead: 0.19,
5296
- cacheWrite: 0,
5297
- },
5298
- contextWindow: 262000,
5299
- maxTokens: 262000,
5300
- },
5301
5321
  "accounts/fireworks/models/kimi-k3": {
5302
5322
  id: "accounts/fireworks/models/kimi-k3",
5303
5323
  name: "Kimi K3",
@@ -5315,23 +5335,6 @@ export const MODELS = {
5315
5335
  contextWindow: 1048576,
5316
5336
  maxTokens: 131072,
5317
5337
  },
5318
- "accounts/fireworks/models/minimax-m2p7": {
5319
- id: "accounts/fireworks/models/minimax-m2p7",
5320
- name: "MiniMax-M2.7",
5321
- api: "anthropic-messages",
5322
- provider: "fireworks",
5323
- baseUrl: "https://api.fireworks.ai/inference",
5324
- reasoning: true,
5325
- input: ["text"],
5326
- cost: {
5327
- input: 1.2,
5328
- output: 1.2,
5329
- cacheRead: 0.6,
5330
- cacheWrite: 0,
5331
- },
5332
- contextWindow: 196608,
5333
- maxTokens: 131072,
5334
- },
5335
5338
  "accounts/fireworks/models/minimax-m3": {
5336
5339
  id: "accounts/fireworks/models/minimax-m3",
5337
5340
  name: "MiniMax-M3",
@@ -5349,31 +5352,14 @@ export const MODELS = {
5349
5352
  contextWindow: 512000,
5350
5353
  maxTokens: 512000,
5351
5354
  },
5352
- "accounts/fireworks/models/muse-glimmer-30b": {
5353
- id: "accounts/fireworks/models/muse-glimmer-30b",
5354
- name: "Muse Glimmer 30B",
5355
+ "accounts/fireworks/models/nemotron-3-ultra-nvfp4": {
5356
+ id: "accounts/fireworks/models/nemotron-3-ultra-nvfp4",
5357
+ name: "Nemotron 3 Ultra 550B A55B",
5355
5358
  api: "anthropic-messages",
5356
5359
  provider: "fireworks",
5357
5360
  baseUrl: "https://api.fireworks.ai/inference",
5358
5361
  reasoning: true,
5359
- input: ["text", "image"],
5360
- cost: {
5361
- input: 0.35,
5362
- output: 1.5,
5363
- cacheRead: 0.04,
5364
- cacheWrite: 0,
5365
- },
5366
- contextWindow: 131072,
5367
- maxTokens: 131072,
5368
- },
5369
- "accounts/fireworks/models/nemotron-3-ultra-nvfp4": {
5370
- id: "accounts/fireworks/models/nemotron-3-ultra-nvfp4",
5371
- name: "Nemotron 3 Ultra 550B A55B",
5372
- api: "anthropic-messages",
5373
- provider: "fireworks",
5374
- baseUrl: "https://api.fireworks.ai/inference",
5375
- reasoning: true,
5376
- input: ["text"],
5362
+ input: ["text"],
5377
5363
  cost: {
5378
5364
  input: 0.6,
5379
5365
  output: 2.4,
@@ -5400,23 +5386,6 @@ export const MODELS = {
5400
5386
  contextWindow: 262144,
5401
5387
  maxTokens: 262144,
5402
5388
  },
5403
- "accounts/fireworks/models/qwen3p7-plus": {
5404
- id: "accounts/fireworks/models/qwen3p7-plus",
5405
- name: "Qwen 3.7 Plus",
5406
- api: "anthropic-messages",
5407
- provider: "fireworks",
5408
- baseUrl: "https://api.fireworks.ai/inference",
5409
- reasoning: true,
5410
- input: ["text", "image"],
5411
- cost: {
5412
- input: 0.4,
5413
- output: 1.6,
5414
- cacheRead: 0.08,
5415
- cacheWrite: 0,
5416
- },
5417
- contextWindow: 262144,
5418
- maxTokens: 65536,
5419
- },
5420
5389
  "accounts/fireworks/models/qwen3p8-2p4t-a95b": {
5421
5390
  id: "accounts/fireworks/models/qwen3p8-2p4t-a95b",
5422
5391
  name: "Qwen3.8 2.4T A95B",
@@ -5468,40 +5437,6 @@ export const MODELS = {
5468
5437
  contextWindow: 1000000,
5469
5438
  maxTokens: 384000,
5470
5439
  },
5471
- "accounts/fireworks/routers/deepseek-pro-latest": {
5472
- id: "accounts/fireworks/routers/deepseek-pro-latest",
5473
- name: "DeepSeek Pro Latest",
5474
- api: "anthropic-messages",
5475
- provider: "fireworks",
5476
- baseUrl: "https://api.fireworks.ai/inference",
5477
- reasoning: true,
5478
- input: ["text"],
5479
- cost: {
5480
- input: 1.32,
5481
- output: 3.96,
5482
- cacheRead: 0.044,
5483
- cacheWrite: 0,
5484
- },
5485
- contextWindow: 1000000,
5486
- maxTokens: 384000,
5487
- },
5488
- "accounts/fireworks/routers/glm-5p2-fast": {
5489
- id: "accounts/fireworks/routers/glm-5p2-fast",
5490
- name: "GLM 5.2 Fast",
5491
- api: "anthropic-messages",
5492
- provider: "fireworks",
5493
- baseUrl: "https://api.fireworks.ai/inference",
5494
- reasoning: true,
5495
- input: ["text"],
5496
- cost: {
5497
- input: 2.1,
5498
- output: 6.6,
5499
- cacheRead: 0.21,
5500
- cacheWrite: 0,
5501
- },
5502
- contextWindow: 1048575,
5503
- maxTokens: 131072,
5504
- },
5505
5440
  "accounts/fireworks/routers/glm-5p3-fast": {
5506
5441
  id: "accounts/fireworks/routers/glm-5p3-fast",
5507
5442
  name: "GLM 5.3 Fast",
@@ -5829,6 +5764,25 @@ export const MODELS = {
5829
5764
  contextWindow: 1000000,
5830
5765
  maxTokens: 128000,
5831
5766
  },
5767
+ "claude-sonnet-5.5": {
5768
+ id: "claude-sonnet-5.5",
5769
+ name: "Claude Sonnet 5.5",
5770
+ api: "openai-completions",
5771
+ provider: "github-copilot",
5772
+ baseUrl: "https://api.individual.githubcopilot.com",
5773
+ 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" },
5774
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
5775
+ reasoning: true,
5776
+ input: ["text", "image"],
5777
+ cost: {
5778
+ input: 2,
5779
+ output: 10,
5780
+ cacheRead: 0.2,
5781
+ cacheWrite: 2.5,
5782
+ },
5783
+ contextWindow: 1000000,
5784
+ maxTokens: 128000,
5785
+ },
5832
5786
  "gemini-3.5-flash": {
5833
5787
  id: "gemini-3.5-flash",
5834
5788
  name: "Gemini 3.5 Flash",
@@ -6133,6 +6087,25 @@ export const MODELS = {
6133
6087
  contextWindow: 1050000,
6134
6088
  maxTokens: 128000,
6135
6089
  },
6090
+ "gpt-6.1-sol": {
6091
+ id: "gpt-6.1-sol",
6092
+ name: "GPT-6.1 Sol",
6093
+ api: "openai-completions",
6094
+ provider: "github-copilot",
6095
+ baseUrl: "https://api.individual.githubcopilot.com",
6096
+ 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" },
6097
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
6098
+ reasoning: true,
6099
+ input: ["text", "image"],
6100
+ cost: {
6101
+ input: 2,
6102
+ output: 10,
6103
+ cacheRead: 0.1,
6104
+ cacheWrite: 2.5,
6105
+ },
6106
+ contextWindow: 1050000,
6107
+ maxTokens: 128000,
6108
+ },
6136
6109
  "grok-4.5": {
6137
6110
  id: "grok-4.5",
6138
6111
  name: "Grok 4.5",
@@ -8549,7 +8522,7 @@ export const MODELS = {
8549
8522
  cost: {
8550
8523
  input: 0.3,
8551
8524
  output: 0.9,
8552
- cacheRead: 0,
8525
+ cacheRead: 0.03,
8553
8526
  cacheWrite: 0,
8554
8527
  },
8555
8528
  contextWindow: 256000,
@@ -8691,23 +8664,6 @@ export const MODELS = {
8691
8664
  contextWindow: 128000,
8692
8665
  maxTokens: 16384,
8693
8666
  },
8694
- "magistral-small": {
8695
- id: "magistral-small",
8696
- name: "Magistral Small",
8697
- api: "mistral-conversations",
8698
- provider: "mistral",
8699
- baseUrl: "https://api.mistral.ai",
8700
- reasoning: true,
8701
- input: ["text"],
8702
- cost: {
8703
- input: 0.5,
8704
- output: 1.5,
8705
- cacheRead: 0,
8706
- cacheWrite: 0,
8707
- },
8708
- contextWindow: 128000,
8709
- maxTokens: 128000,
8710
- },
8711
8667
  "ministral-3b-latest": {
8712
8668
  id: "ministral-3b-latest",
8713
8669
  name: "Ministral 3B (latest)",
@@ -8770,7 +8726,7 @@ export const MODELS = {
8770
8726
  cost: {
8771
8727
  input: 0.5,
8772
8728
  output: 1.5,
8773
- cacheRead: 0,
8729
+ cacheRead: 0.05,
8774
8730
  cacheWrite: 0,
8775
8731
  },
8776
8732
  contextWindow: 262144,
@@ -8787,7 +8743,7 @@ export const MODELS = {
8787
8743
  cost: {
8788
8744
  input: 0.5,
8789
8745
  output: 1.5,
8790
- cacheRead: 0,
8746
+ cacheRead: 0.05,
8791
8747
  cacheWrite: 0,
8792
8748
  },
8793
8749
  contextWindow: 262144,
@@ -8838,7 +8794,7 @@ export const MODELS = {
8838
8794
  cost: {
8839
8795
  input: 1.5,
8840
8796
  output: 7.5,
8841
- cacheRead: 0,
8797
+ cacheRead: 0.15,
8842
8798
  cacheWrite: 0,
8843
8799
  },
8844
8800
  contextWindow: 262144,
@@ -8872,7 +8828,7 @@ export const MODELS = {
8872
8828
  cost: {
8873
8829
  input: 1.5,
8874
8830
  output: 7.5,
8875
- cacheRead: 0,
8831
+ cacheRead: 0.15,
8876
8832
  cacheWrite: 0,
8877
8833
  },
8878
8834
  contextWindow: 262144,
@@ -8923,7 +8879,7 @@ export const MODELS = {
8923
8879
  cost: {
8924
8880
  input: 0.15,
8925
8881
  output: 0.6,
8926
- cacheRead: 0,
8882
+ cacheRead: 0.015,
8927
8883
  cacheWrite: 0,
8928
8884
  },
8929
8885
  contextWindow: 256000,
@@ -8940,7 +8896,7 @@ export const MODELS = {
8940
8896
  cost: {
8941
8897
  input: 0.15,
8942
8898
  output: 0.6,
8943
- cacheRead: 0,
8899
+ cacheRead: 0.015,
8944
8900
  cacheWrite: 0,
8945
8901
  },
8946
8902
  contextWindow: 256000,
@@ -9834,6 +9790,57 @@ export const MODELS = {
9834
9790
  contextWindow: 1050000,
9835
9791
  maxTokens: 128000,
9836
9792
  },
9793
+ "gpt-6.1-sol": {
9794
+ id: "gpt-6.1-sol",
9795
+ name: "GPT-6.1 Sol",
9796
+ api: "openai-responses",
9797
+ provider: "openai",
9798
+ baseUrl: "https://api.openai.com/v1",
9799
+ reasoning: true,
9800
+ input: ["text", "image"],
9801
+ cost: {
9802
+ input: 2,
9803
+ output: 10,
9804
+ cacheRead: 0.1,
9805
+ cacheWrite: 2.5,
9806
+ },
9807
+ contextWindow: 1050000,
9808
+ maxTokens: 128000,
9809
+ },
9810
+ "gpt-daybreak-blue-latest": {
9811
+ id: "gpt-daybreak-blue-latest",
9812
+ name: "Daybreak Blue",
9813
+ api: "openai-responses",
9814
+ provider: "openai",
9815
+ baseUrl: "https://api.openai.com/v1",
9816
+ reasoning: true,
9817
+ input: ["text", "image"],
9818
+ cost: {
9819
+ input: 4,
9820
+ output: 20,
9821
+ cacheRead: 0.4,
9822
+ cacheWrite: 5,
9823
+ },
9824
+ contextWindow: 1050000,
9825
+ maxTokens: 128000,
9826
+ },
9827
+ "gpt-daybreak-red-latest": {
9828
+ id: "gpt-daybreak-red-latest",
9829
+ name: "Daybreak Red",
9830
+ api: "openai-responses",
9831
+ provider: "openai",
9832
+ baseUrl: "https://api.openai.com/v1",
9833
+ reasoning: true,
9834
+ input: ["text", "image"],
9835
+ cost: {
9836
+ input: 12.5,
9837
+ output: 75,
9838
+ cacheRead: 1.25,
9839
+ cacheWrite: 15.625,
9840
+ },
9841
+ contextWindow: 400000,
9842
+ maxTokens: 128000,
9843
+ },
9837
9844
  "gpt-realtime-2.1": {
9838
9845
  id: "gpt-realtime-2.1",
9839
9846
  name: "GPT-Realtime-2.1",
@@ -10378,6 +10385,23 @@ export const MODELS = {
10378
10385
  contextWindow: 1000000,
10379
10386
  maxTokens: 128000,
10380
10387
  },
10388
+ "claude-sonnet-5-5": {
10389
+ id: "claude-sonnet-5-5",
10390
+ name: "Claude Sonnet 5.5",
10391
+ api: "anthropic-messages",
10392
+ provider: "opencode",
10393
+ baseUrl: "https://opencode.ai/zen",
10394
+ reasoning: true,
10395
+ input: ["text", "image"],
10396
+ cost: {
10397
+ input: 2,
10398
+ output: 10,
10399
+ cacheRead: 0.2,
10400
+ cacheWrite: 2.5,
10401
+ },
10402
+ contextWindow: 1000000,
10403
+ maxTokens: 128000,
10404
+ },
10381
10405
  "deepseek-v4-flash": {
10382
10406
  id: "deepseek-v4-flash",
10383
10407
  name: "DeepSeek V4 Flash",
@@ -11058,6 +11082,23 @@ export const MODELS = {
11058
11082
  contextWindow: 1050000,
11059
11083
  maxTokens: 128000,
11060
11084
  },
11085
+ "gpt-6.1-sol": {
11086
+ id: "gpt-6.1-sol",
11087
+ name: "GPT-6.1 Sol",
11088
+ api: "openai-responses",
11089
+ provider: "opencode",
11090
+ baseUrl: "https://opencode.ai/zen/v1",
11091
+ reasoning: true,
11092
+ input: ["text", "image"],
11093
+ cost: {
11094
+ input: 2,
11095
+ output: 10,
11096
+ cacheRead: 0.1,
11097
+ cacheWrite: 2.5,
11098
+ },
11099
+ contextWindow: 1050000,
11100
+ maxTokens: 128000,
11101
+ },
11061
11102
  "grok-4.5": {
11062
11103
  id: "grok-4.5",
11063
11104
  name: "Grok 4.5",
@@ -11094,16 +11135,16 @@ export const MODELS = {
11094
11135
  },
11095
11136
  "grok-4.7": {
11096
11137
  id: "grok-4.7",
11097
- name: "Grok 4.7 (30% Off)",
11138
+ name: "Grok 4.7",
11098
11139
  api: "openai-responses",
11099
11140
  provider: "opencode",
11100
11141
  baseUrl: "https://opencode.ai/zen/v1",
11101
11142
  reasoning: true,
11102
11143
  input: ["text", "image"],
11103
11144
  cost: {
11104
- input: 1.4,
11105
- output: 4.2,
11106
- cacheRead: 0.35,
11145
+ input: 2,
11146
+ output: 6,
11147
+ cacheRead: 0.5,
11107
11148
  cacheWrite: 0,
11108
11149
  },
11109
11150
  contextWindow: 500000,
@@ -11211,6 +11252,23 @@ export const MODELS = {
11211
11252
  contextWindow: 262144,
11212
11253
  maxTokens: 32768,
11213
11254
  },
11255
+ "longcat-2.5-preview-free": {
11256
+ id: "longcat-2.5-preview-free",
11257
+ name: "LongCat 2.5 Preview Free",
11258
+ api: "openai-completions",
11259
+ provider: "opencode",
11260
+ baseUrl: "https://opencode.ai/zen/v1",
11261
+ reasoning: true,
11262
+ input: ["text", "image"],
11263
+ cost: {
11264
+ input: 0,
11265
+ output: 0,
11266
+ cacheRead: 0,
11267
+ cacheWrite: 0,
11268
+ },
11269
+ contextWindow: 1000000,
11270
+ maxTokens: 131072,
11271
+ },
11214
11272
  "mimo-v2.6-flash-free": {
11215
11273
  id: "mimo-v2.6-flash-free",
11216
11274
  name: "MiMo-V2.6-Flash Free",
@@ -11296,23 +11354,6 @@ export const MODELS = {
11296
11354
  contextWindow: 1048576,
11297
11355
  maxTokens: 131072,
11298
11356
  },
11299
- "muse-spark-1.2-contributor-free": {
11300
- id: "muse-spark-1.2-contributor-free",
11301
- name: "Muse Spark 1.2 Free",
11302
- api: "openai-responses",
11303
- provider: "opencode",
11304
- baseUrl: "https://opencode.ai/zen/v1",
11305
- reasoning: true,
11306
- input: ["text", "image"],
11307
- cost: {
11308
- input: 0,
11309
- output: 0,
11310
- cacheRead: 0,
11311
- cacheWrite: 0,
11312
- },
11313
- contextWindow: 1048576,
11314
- maxTokens: 131072,
11315
- },
11316
11357
  "muse-spark-1.3": {
11317
11358
  id: "muse-spark-1.3",
11318
11359
  name: "Muse Spark 1.3",
@@ -11432,6 +11473,23 @@ export const MODELS = {
11432
11473
  contextWindow: 1000000,
11433
11474
  maxTokens: 131072,
11434
11475
  },
11476
+ "qwen3.8-max": {
11477
+ id: "qwen3.8-max",
11478
+ name: "Qwen3.8 Max",
11479
+ api: "openai-completions",
11480
+ provider: "opencode",
11481
+ baseUrl: "https://opencode.ai/zen/v1",
11482
+ reasoning: true,
11483
+ input: ["text", "image"],
11484
+ cost: {
11485
+ input: 2,
11486
+ output: 6,
11487
+ cacheRead: 0.25,
11488
+ cacheWrite: 2.5,
11489
+ },
11490
+ contextWindow: 262144,
11491
+ maxTokens: 131072,
11492
+ },
11435
11493
  "space-bunny-free": {
11436
11494
  id: "space-bunny-free",
11437
11495
  name: "Space Bunny Free",
@@ -11527,23 +11585,6 @@ export const MODELS = {
11527
11585
  contextWindow: 1000000,
11528
11586
  maxTokens: 384000,
11529
11587
  },
11530
- "glm-5.1": {
11531
- id: "glm-5.1",
11532
- name: "GLM-5.1",
11533
- api: "openai-completions",
11534
- provider: "opencode-go",
11535
- baseUrl: "https://opencode.ai/zen/go/v1",
11536
- reasoning: true,
11537
- input: ["text"],
11538
- cost: {
11539
- input: 1.4,
11540
- output: 4.4,
11541
- cacheRead: 0.26,
11542
- cacheWrite: 0,
11543
- },
11544
- contextWindow: 202752,
11545
- maxTokens: 32768,
11546
- },
11547
11588
  "glm-5.2": {
11548
11589
  id: "glm-5.2",
11549
11590
  name: "GLM-5.2",
@@ -11698,23 +11739,6 @@ export const MODELS = {
11698
11739
  contextWindow: 1024000,
11699
11740
  maxTokens: 64000,
11700
11741
  },
11701
- "kimi-k2.6": {
11702
- id: "kimi-k2.6",
11703
- name: "Kimi K2.6",
11704
- api: "openai-completions",
11705
- provider: "opencode-go",
11706
- baseUrl: "https://opencode.ai/zen/go/v1",
11707
- reasoning: true,
11708
- input: ["text", "image"],
11709
- cost: {
11710
- input: 0.95,
11711
- output: 4,
11712
- cacheRead: 0.16,
11713
- cacheWrite: 0,
11714
- },
11715
- contextWindow: 262144,
11716
- maxTokens: 65536,
11717
- },
11718
11742
  "kimi-k2.7-code": {
11719
11743
  id: "kimi-k2.7-code",
11720
11744
  name: "Kimi K2.7 Code",
@@ -11766,6 +11790,23 @@ export const MODELS = {
11766
11790
  contextWindow: 1000000,
11767
11791
  maxTokens: 131072,
11768
11792
  },
11793
+ "longcat-2.5-preview-free": {
11794
+ id: "longcat-2.5-preview-free",
11795
+ name: "LongCat 2.5 Preview Free",
11796
+ api: "openai-completions",
11797
+ provider: "opencode-go",
11798
+ baseUrl: "https://opencode.ai/zen/go/v1",
11799
+ reasoning: true,
11800
+ input: ["text", "image"],
11801
+ cost: {
11802
+ input: 0,
11803
+ output: 0,
11804
+ cacheRead: 0,
11805
+ cacheWrite: 0,
11806
+ },
11807
+ contextWindow: 1000000,
11808
+ maxTokens: 131072,
11809
+ },
11769
11810
  "mimo-v2.5": {
11770
11811
  id: "mimo-v2.5",
11771
11812
  name: "MiMo V2.5",
@@ -11902,41 +11943,6 @@ export const MODELS = {
11902
11943
  contextWindow: 1048576,
11903
11944
  maxTokens: 131072,
11904
11945
  },
11905
- "qwen3.6-plus": {
11906
- id: "qwen3.6-plus",
11907
- name: "Qwen3.6 Plus",
11908
- api: "openai-completions",
11909
- provider: "opencode-go",
11910
- baseUrl: "https://opencode.ai/zen/go/v1",
11911
- compat: { "thinkingFormat": "qwen" },
11912
- reasoning: true,
11913
- input: ["text", "image"],
11914
- cost: {
11915
- input: 0.5,
11916
- output: 3,
11917
- cacheRead: 0.05,
11918
- cacheWrite: 0.625,
11919
- },
11920
- contextWindow: 1000000,
11921
- maxTokens: 65536,
11922
- },
11923
- "qwen3.7-max": {
11924
- id: "qwen3.7-max",
11925
- name: "Qwen3.7 Max",
11926
- api: "openai-completions",
11927
- provider: "opencode-go",
11928
- baseUrl: "https://opencode.ai/zen/go/v1",
11929
- reasoning: true,
11930
- input: ["text"],
11931
- cost: {
11932
- input: 2.5,
11933
- output: 7.5,
11934
- cacheRead: 0.5,
11935
- cacheWrite: 3.125,
11936
- },
11937
- contextWindow: 1000000,
11938
- maxTokens: 65536,
11939
- },
11940
11946
  "qwen3.7-plus": {
11941
11947
  id: "qwen3.7-plus",
11942
11948
  name: "Qwen3.7 Plus",
@@ -12177,23 +12183,6 @@ export const MODELS = {
12177
12183
  contextWindow: 300000,
12178
12184
  maxTokens: 5120,
12179
12185
  },
12180
- "anthropic/claude-3-haiku": {
12181
- id: "anthropic/claude-3-haiku",
12182
- name: "Anthropic: Claude 3 Haiku",
12183
- api: "openai-completions",
12184
- provider: "openrouter",
12185
- baseUrl: "https://openrouter.ai/api/v1",
12186
- reasoning: false,
12187
- input: ["text", "image"],
12188
- cost: {
12189
- input: 0.25,
12190
- output: 1.25,
12191
- cacheRead: 0.03,
12192
- cacheWrite: 0.3,
12193
- },
12194
- contextWindow: 200000,
12195
- maxTokens: 4096,
12196
- },
12197
12186
  "anthropic/claude-fable-5": {
12198
12187
  id: "anthropic/claude-fable-5",
12199
12188
  name: "Anthropic: Claude Fable 5",
@@ -12646,6 +12635,40 @@ export const MODELS = {
12646
12635
  contextWindow: 1000000,
12647
12636
  maxTokens: 128000,
12648
12637
  },
12638
+ "anthropic/claude-sonnet-5.5": {
12639
+ id: "anthropic/claude-sonnet-5.5",
12640
+ name: "Anthropic: Claude Sonnet 5.5",
12641
+ api: "openai-completions",
12642
+ provider: "openrouter",
12643
+ baseUrl: "https://openrouter.ai/api/v1",
12644
+ reasoning: true,
12645
+ input: ["text", "image"],
12646
+ cost: {
12647
+ input: 2,
12648
+ output: 10,
12649
+ cacheRead: 0.19999999999999998,
12650
+ cacheWrite: 2.5,
12651
+ },
12652
+ contextWindow: 1000000,
12653
+ maxTokens: 128000,
12654
+ },
12655
+ "anthropic/claude-sonnet-5.5:batch": {
12656
+ id: "anthropic/claude-sonnet-5.5:batch",
12657
+ name: "Anthropic: Claude Sonnet 5.5 (batch)",
12658
+ api: "openai-completions",
12659
+ provider: "openrouter",
12660
+ baseUrl: "https://openrouter.ai/api/v1",
12661
+ reasoning: true,
12662
+ input: ["text", "image"],
12663
+ cost: {
12664
+ input: 1,
12665
+ output: 5,
12666
+ cacheRead: 0.09999999999999999,
12667
+ cacheWrite: 1.25,
12668
+ },
12669
+ contextWindow: 1000000,
12670
+ maxTokens: 128000,
12671
+ },
12649
12672
  "anthropic/claude-sonnet-5:batch": {
12650
12673
  id: "anthropic/claude-sonnet-5:batch",
12651
12674
  name: "Anthropic: Claude Sonnet 5 (batch)",
@@ -12876,13 +12899,13 @@ export const MODELS = {
12876
12899
  reasoning: false,
12877
12900
  input: ["text"],
12878
12901
  cost: {
12879
- input: 0.32,
12880
- output: 0.8899999999999999,
12902
+ input: 0.2574,
12903
+ output: 1.0287,
12881
12904
  cacheRead: 0,
12882
12905
  cacheWrite: 0,
12883
12906
  },
12884
12907
  contextWindow: 163840,
12885
- maxTokens: 16384,
12908
+ maxTokens: 16000,
12886
12909
  },
12887
12910
  "deepseek/deepseek-chat-v3-0324": {
12888
12911
  id: "deepseek/deepseek-chat-v3-0324",
@@ -12893,9 +12916,9 @@ export const MODELS = {
12893
12916
  reasoning: false,
12894
12917
  input: ["text"],
12895
12918
  cost: {
12896
- input: 0.25,
12897
- output: 1,
12898
- cacheRead: 0,
12919
+ input: 0.29,
12920
+ output: 1.1400000000000001,
12921
+ cacheRead: 0.11,
12899
12922
  cacheWrite: 0,
12900
12923
  },
12901
12924
  contextWindow: 163840,
@@ -12961,13 +12984,13 @@ export const MODELS = {
12961
12984
  reasoning: true,
12962
12985
  input: ["text"],
12963
12986
  cost: {
12964
- input: 0.27,
12987
+ input: 0.3,
12965
12988
  output: 1,
12966
12989
  cacheRead: 0.135,
12967
12990
  cacheWrite: 0,
12968
12991
  },
12969
12992
  contextWindow: 163840,
12970
- maxTokens: 32768,
12993
+ maxTokens: 65536,
12971
12994
  },
12972
12995
  "deepseek/deepseek-v3.2": {
12973
12996
  id: "deepseek/deepseek-v3.2",
@@ -12978,9 +13001,9 @@ export const MODELS = {
12978
13001
  reasoning: true,
12979
13002
  input: ["text"],
12980
13003
  cost: {
12981
- input: 0.26899999999999996,
12982
- output: 0.39999999999999997,
12983
- cacheRead: 0.13449999999999998,
13004
+ input: 0.28,
13005
+ output: 0.42,
13006
+ cacheRead: 0.028,
12984
13007
  cacheWrite: 0,
12985
13008
  },
12986
13009
  contextWindow: 163840,
@@ -13001,7 +13024,7 @@ export const MODELS = {
13001
13024
  cacheWrite: 0,
13002
13025
  },
13003
13026
  contextWindow: 163840,
13004
- maxTokens: 65536,
13027
+ maxTokens: 147456,
13005
13028
  },
13006
13029
  "deepseek/deepseek-v4-flash": {
13007
13030
  id: "deepseek/deepseek-v4-flash",
@@ -13014,13 +13037,13 @@ export const MODELS = {
13014
13037
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13015
13038
  input: ["text"],
13016
13039
  cost: {
13017
- input: 0.088606,
13018
- output: 0.177212,
13019
- cacheRead: 0.017721200000000003,
13040
+ input: 0.14,
13041
+ output: 0.28,
13042
+ cacheRead: 0.028,
13020
13043
  cacheWrite: 0,
13021
13044
  },
13022
13045
  contextWindow: 1048576,
13023
- maxTokens: 384000,
13046
+ maxTokens: 131072,
13024
13047
  },
13025
13048
  "deepseek/deepseek-v4-flash-0731": {
13026
13049
  id: "deepseek/deepseek-v4-flash-0731",
@@ -13033,12 +13056,12 @@ export const MODELS = {
13033
13056
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13034
13057
  input: ["text"],
13035
13058
  cost: {
13036
- input: 0.03,
13037
- output: 0.32,
13038
- cacheRead: 0.016,
13059
+ input: 0.01,
13060
+ output: 1.28,
13061
+ cacheRead: 0.01,
13039
13062
  cacheWrite: 0,
13040
13063
  },
13041
- contextWindow: 1310720,
13064
+ contextWindow: 1048576,
13042
13065
  maxTokens: 943718,
13043
13066
  },
13044
13067
  "deepseek/deepseek-v4-flash-vision-exp": {
@@ -13052,13 +13075,13 @@ export const MODELS = {
13052
13075
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13053
13076
  input: ["text", "image"],
13054
13077
  cost: {
13055
- input: 0.22,
13056
- output: 0.66,
13057
- cacheRead: 0.007,
13078
+ input: 0.21559999999999999,
13079
+ output: 0.6468,
13080
+ cacheRead: 0.00686,
13058
13081
  cacheWrite: 0,
13059
13082
  },
13060
13083
  contextWindow: 1048576,
13061
- maxTokens: 943718,
13084
+ maxTokens: 262144,
13062
13085
  },
13063
13086
  "deepseek/deepseek-v4-pro": {
13064
13087
  id: "deepseek/deepseek-v4-pro",
@@ -13071,9 +13094,9 @@ export const MODELS = {
13071
13094
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13072
13095
  input: ["text"],
13073
13096
  cost: {
13074
- input: 0.9396,
13075
- output: 1.8792,
13076
- cacheRead: 0.07830000000000001,
13097
+ input: 0.9552599999999999,
13098
+ output: 1.9105199999999998,
13099
+ cacheRead: 0.07960500000000001,
13077
13100
  cacheWrite: 0,
13078
13101
  },
13079
13102
  contextWindow: 1048576,
@@ -13090,13 +13113,13 @@ export const MODELS = {
13090
13113
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13091
13114
  input: ["text"],
13092
13115
  cost: {
13093
- input: 0.46199999999999997,
13094
- output: 1.386,
13095
- cacheRead: 0.015399999999999999,
13116
+ input: 1.32,
13117
+ output: 3.9600000000000004,
13118
+ cacheRead: 0.044,
13096
13119
  cacheWrite: 0,
13097
13120
  },
13098
13121
  contextWindow: 1048576,
13099
- maxTokens: 384000,
13122
+ maxTokens: 393216,
13100
13123
  },
13101
13124
  "deepseek/deepseek-v4.1-flash": {
13102
13125
  id: "deepseek/deepseek-v4.1-flash",
@@ -13109,13 +13132,13 @@ export const MODELS = {
13109
13132
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13110
13133
  input: ["text", "image"],
13111
13134
  cost: {
13112
- input: 0.14,
13113
- output: 0.42,
13114
- cacheRead: 0.004200000000000001,
13135
+ input: 0.019799999999999998,
13136
+ output: 0.396,
13137
+ cacheRead: 0.0029100000000000003,
13115
13138
  cacheWrite: 0,
13116
13139
  },
13117
13140
  contextWindow: 1048576,
13118
- maxTokens: 131072,
13141
+ maxTokens: 943718,
13119
13142
  },
13120
13143
  "deepseek/deepseek-v4.1-flash:batch": {
13121
13144
  id: "deepseek/deepseek-v4.1-flash:batch",
@@ -13799,23 +13822,6 @@ export const MODELS = {
13799
13822
  contextWindow: 262144,
13800
13823
  maxTokens: 235929,
13801
13824
  },
13802
- "inclusionai/ling-3.0-flash-fin:free": {
13803
- id: "inclusionai/ling-3.0-flash-fin:free",
13804
- name: "inclusionAI: Ling 3.0 Flash Fin (free)",
13805
- api: "openai-completions",
13806
- provider: "openrouter",
13807
- baseUrl: "https://openrouter.ai/api/v1",
13808
- reasoning: true,
13809
- input: ["text"],
13810
- cost: {
13811
- input: 0,
13812
- output: 0,
13813
- cacheRead: 0,
13814
- cacheWrite: 0,
13815
- },
13816
- contextWindow: 262144,
13817
- maxTokens: 32768,
13818
- },
13819
13825
  "inclusionai/ling-3.0-flash-sante:free": {
13820
13826
  id: "inclusionai/ling-3.0-flash-sante:free",
13821
13827
  name: "inclusionAI: Ling 3.0 Flash Sante (free)",
@@ -13842,9 +13848,9 @@ export const MODELS = {
13842
13848
  reasoning: true,
13843
13849
  input: ["text", "image"],
13844
13850
  cost: {
13845
- input: 0.06,
13846
- output: 0.18,
13847
- cacheRead: 0.012,
13851
+ input: 0.020999999999999998,
13852
+ output: 0.061599999999999995,
13853
+ cacheRead: 0.004200000000000001,
13848
13854
  cacheWrite: 0,
13849
13855
  },
13850
13856
  contextWindow: 262144,
@@ -13995,13 +14001,13 @@ export const MODELS = {
13995
14001
  reasoning: true,
13996
14002
  input: ["text", "image"],
13997
14003
  cost: {
13998
- input: 0.3,
13999
- output: 1.2,
14004
+ input: 0.35,
14005
+ output: 1.5,
14000
14006
  cacheRead: 0.04,
14001
14007
  cacheWrite: 0,
14002
14008
  },
14003
14009
  contextWindow: 131072,
14004
- maxTokens: 16384,
14010
+ maxTokens: 117964,
14005
14011
  },
14006
14012
  "meta/muse-spark-1.1": {
14007
14013
  id: "meta/muse-spark-1.1",
@@ -14165,13 +14171,13 @@ export const MODELS = {
14165
14171
  reasoning: true,
14166
14172
  input: ["text"],
14167
14173
  cost: {
14168
- input: 0.3,
14169
- output: 1.2,
14170
- cacheRead: 0.06,
14174
+ input: 0.21,
14175
+ output: 0.84,
14176
+ cacheRead: 0.041999999999999996,
14171
14177
  cacheWrite: 0,
14172
14178
  },
14173
14179
  contextWindow: 204800,
14174
- maxTokens: 131072,
14180
+ maxTokens: 176947,
14175
14181
  },
14176
14182
  "minimax/minimax-m3": {
14177
14183
  id: "minimax/minimax-m3",
@@ -14224,6 +14230,23 @@ export const MODELS = {
14224
14230
  contextWindow: 256000,
14225
14231
  maxTokens: 204800,
14226
14232
  },
14233
+ "mistralai/devstral-2512": {
14234
+ id: "mistralai/devstral-2512",
14235
+ name: "Mistral: Devstral 2 2512",
14236
+ api: "openai-completions",
14237
+ provider: "openrouter",
14238
+ baseUrl: "https://openrouter.ai/api/v1",
14239
+ reasoning: false,
14240
+ input: ["text"],
14241
+ cost: {
14242
+ input: 0.39999999999999997,
14243
+ output: 2,
14244
+ cacheRead: 0.04,
14245
+ cacheWrite: 0,
14246
+ },
14247
+ contextWindow: 262144,
14248
+ maxTokens: 209715,
14249
+ },
14227
14250
  "mistralai/ministral-14b-2512": {
14228
14251
  id: "mistralai/ministral-14b-2512",
14229
14252
  name: "Mistral: Ministral 3 14B 2512",
@@ -14326,6 +14349,23 @@ export const MODELS = {
14326
14349
  contextWindow: 131072,
14327
14350
  maxTokens: 104857,
14328
14351
  },
14352
+ "mistralai/mistral-large-2512": {
14353
+ id: "mistralai/mistral-large-2512",
14354
+ name: "Mistral: Mistral Large 3 2512",
14355
+ api: "openai-completions",
14356
+ provider: "openrouter",
14357
+ baseUrl: "https://openrouter.ai/api/v1",
14358
+ reasoning: false,
14359
+ input: ["text", "image"],
14360
+ cost: {
14361
+ input: 0.5,
14362
+ output: 1.5,
14363
+ cacheRead: 0.049999999999999996,
14364
+ cacheWrite: 0,
14365
+ },
14366
+ contextWindow: 262144,
14367
+ maxTokens: 209715,
14368
+ },
14329
14369
  "mistralai/mistral-large-2512:batch": {
14330
14370
  id: "mistralai/mistral-large-2512:batch",
14331
14371
  name: "Mistral: Mistral Large 3 2512 (batch)",
@@ -14641,9 +14681,9 @@ export const MODELS = {
14641
14681
  reasoning: true,
14642
14682
  input: ["text", "image"],
14643
14683
  cost: {
14644
- input: 0.95,
14645
- output: 4,
14646
- cacheRead: 0.16,
14684
+ input: 0.65,
14685
+ output: 3.41,
14686
+ cacheRead: 0.15,
14647
14687
  cacheWrite: 0,
14648
14688
  },
14649
14689
  contextWindow: 262144,
@@ -14658,8 +14698,8 @@ export const MODELS = {
14658
14698
  reasoning: true,
14659
14699
  input: ["text", "image"],
14660
14700
  cost: {
14661
- input: 0.6562,
14662
- output: 3.3000000000000003,
14701
+ input: 0.6712,
14702
+ output: 3.35,
14663
14703
  cacheRead: 0.18,
14664
14704
  cacheWrite: 0,
14665
14705
  },
@@ -14700,35 +14740,18 @@ export const MODELS = {
14700
14740
  contextWindow: 1048576,
14701
14741
  maxTokens: 16384,
14702
14742
  },
14703
- "nex-agi/nex-n2.5-mini:free": {
14704
- id: "nex-agi/nex-n2.5-mini:free",
14705
- name: "Nex AGI: Nex-N2.5-Mini (free)",
14706
- api: "openai-completions",
14707
- provider: "openrouter",
14708
- baseUrl: "https://openrouter.ai/api/v1",
14709
- reasoning: true,
14710
- input: ["text", "image"],
14711
- cost: {
14712
- input: 0,
14713
- output: 0,
14714
- cacheRead: 0,
14715
- cacheWrite: 0,
14716
- },
14717
- contextWindow: 262144,
14718
- maxTokens: 235929,
14719
- },
14720
- "nex-agi/nex-n2.5-pro:free": {
14721
- id: "nex-agi/nex-n2.5-pro:free",
14722
- name: "Nex AGI: Nex-N2.5-Pro (free)",
14743
+ "nex-agi/nex-n2.5-pro": {
14744
+ id: "nex-agi/nex-n2.5-pro",
14745
+ name: "Nex AGI: Nex-N2.5-Pro",
14723
14746
  api: "openai-completions",
14724
14747
  provider: "openrouter",
14725
14748
  baseUrl: "https://openrouter.ai/api/v1",
14726
14749
  reasoning: true,
14727
14750
  input: ["text", "image"],
14728
14751
  cost: {
14729
- input: 0,
14730
- output: 0,
14731
- cacheRead: 0,
14752
+ input: 0.075,
14753
+ output: 0.25,
14754
+ cacheRead: 0.015,
14732
14755
  cacheWrite: 0,
14733
14756
  },
14734
14757
  contextWindow: 262144,
@@ -14845,13 +14868,13 @@ export const MODELS = {
14845
14868
  reasoning: true,
14846
14869
  input: ["text"],
14847
14870
  cost: {
14848
- input: 0.08,
14849
- output: 0.19999999999999998,
14850
- cacheRead: 0.04,
14871
+ input: 0.06,
14872
+ output: 0.16,
14873
+ cacheRead: 0.03,
14851
14874
  cacheWrite: 0,
14852
14875
  },
14853
14876
  contextWindow: 262144,
14854
- maxTokens: 131072,
14877
+ maxTokens: 32768,
14855
14878
  },
14856
14879
  "nvidia/nemotron-3.5-lightning:free": {
14857
14880
  id: "nvidia/nemotron-3.5-lightning:free",
@@ -15782,10 +15805,10 @@ export const MODELS = {
15782
15805
  reasoning: true,
15783
15806
  input: ["text", "image"],
15784
15807
  cost: {
15785
- input: 2,
15786
- output: 10,
15787
- cacheRead: 0.19999999999999998,
15788
- cacheWrite: 2.5,
15808
+ input: 4,
15809
+ output: 20,
15810
+ cacheRead: 0.39999999999999997,
15811
+ cacheWrite: 5,
15789
15812
  },
15790
15813
  contextWindow: 1050000,
15791
15814
  maxTokens: 128000,
@@ -16113,6 +16136,74 @@ export const MODELS = {
16113
16136
  contextWindow: 1050000,
16114
16137
  maxTokens: 128000,
16115
16138
  },
16139
+ "openai/gpt-6.1-sol": {
16140
+ id: "openai/gpt-6.1-sol",
16141
+ name: "OpenAI: GPT-6.1 Sol",
16142
+ api: "openai-completions",
16143
+ provider: "openrouter",
16144
+ baseUrl: "https://openrouter.ai/api/v1",
16145
+ reasoning: true,
16146
+ input: ["text", "image"],
16147
+ cost: {
16148
+ input: 2,
16149
+ output: 10,
16150
+ cacheRead: 0.09999999999999999,
16151
+ cacheWrite: 2.5,
16152
+ },
16153
+ contextWindow: 1050000,
16154
+ maxTokens: 128000,
16155
+ },
16156
+ "openai/gpt-6.1-sol-pro": {
16157
+ id: "openai/gpt-6.1-sol-pro",
16158
+ name: "OpenAI: GPT-6.1 Sol Pro",
16159
+ api: "openai-completions",
16160
+ provider: "openrouter",
16161
+ baseUrl: "https://openrouter.ai/api/v1",
16162
+ reasoning: true,
16163
+ input: ["text", "image"],
16164
+ cost: {
16165
+ input: 2,
16166
+ output: 10,
16167
+ cacheRead: 0.09999999999999999,
16168
+ cacheWrite: 2.5,
16169
+ },
16170
+ contextWindow: 1050000,
16171
+ maxTokens: 128000,
16172
+ },
16173
+ "openai/gpt-6.1-sol-pro:batch": {
16174
+ id: "openai/gpt-6.1-sol-pro:batch",
16175
+ name: "OpenAI: GPT-6.1 Sol Pro (batch)",
16176
+ api: "openai-completions",
16177
+ provider: "openrouter",
16178
+ baseUrl: "https://openrouter.ai/api/v1",
16179
+ reasoning: true,
16180
+ input: ["text", "image"],
16181
+ cost: {
16182
+ input: 1,
16183
+ output: 5,
16184
+ cacheRead: 0.049999999999999996,
16185
+ cacheWrite: 1.25,
16186
+ },
16187
+ contextWindow: 1050000,
16188
+ maxTokens: 128000,
16189
+ },
16190
+ "openai/gpt-6.1-sol:batch": {
16191
+ id: "openai/gpt-6.1-sol:batch",
16192
+ name: "OpenAI: GPT-6.1 Sol (batch)",
16193
+ api: "openai-completions",
16194
+ provider: "openrouter",
16195
+ baseUrl: "https://openrouter.ai/api/v1",
16196
+ reasoning: true,
16197
+ input: ["text", "image"],
16198
+ cost: {
16199
+ input: 1,
16200
+ output: 5,
16201
+ cacheRead: 0.049999999999999996,
16202
+ cacheWrite: 1.25,
16203
+ },
16204
+ contextWindow: 1050000,
16205
+ maxTokens: 128000,
16206
+ },
16116
16207
  "openai/gpt-audio": {
16117
16208
  id: "openai/gpt-audio",
16118
16209
  name: "OpenAI: GPT Audio",
@@ -16173,13 +16264,13 @@ export const MODELS = {
16173
16264
  reasoning: true,
16174
16265
  input: ["text"],
16175
16266
  cost: {
16176
- input: 0.15,
16177
- output: 0.6,
16178
- cacheRead: 0.075,
16267
+ input: 0.037,
16268
+ output: 0.16999999999999998,
16269
+ cacheRead: 0,
16179
16270
  cacheWrite: 0,
16180
16271
  },
16181
16272
  contextWindow: 131072,
16182
- maxTokens: 65536,
16273
+ maxTokens: 117964,
16183
16274
  },
16184
16275
  "openai/gpt-oss-120b:batch": {
16185
16276
  id: "openai/gpt-oss-120b:batch",
@@ -16209,7 +16300,7 @@ export const MODELS = {
16209
16300
  cost: {
16210
16301
  input: 0.018,
16211
16302
  output: 0.09,
16212
- cacheRead: 0,
16303
+ cacheRead: 0.009,
16213
16304
  cacheWrite: 0,
16214
16305
  },
16215
16306
  contextWindow: 131072,
@@ -16470,6 +16561,23 @@ export const MODELS = {
16470
16561
  contextWindow: 200000,
16471
16562
  maxTokens: 4096,
16472
16563
  },
16564
+ "perceptron/perceptron-mk1.5": {
16565
+ id: "perceptron/perceptron-mk1.5",
16566
+ name: "Perceptron: Perceptron Mk1.5",
16567
+ api: "openai-completions",
16568
+ provider: "openrouter",
16569
+ baseUrl: "https://openrouter.ai/api/v1",
16570
+ reasoning: true,
16571
+ input: ["text", "image"],
16572
+ cost: {
16573
+ input: 0.15,
16574
+ output: 1.5,
16575
+ cacheRead: 0,
16576
+ cacheWrite: 0,
16577
+ },
16578
+ contextWindow: 36864,
16579
+ maxTokens: 8192,
16580
+ },
16473
16581
  "poolside/laguna-s-2.1": {
16474
16582
  id: "poolside/laguna-s-2.1",
16475
16583
  name: "Poolside: Laguna S 2.1",
@@ -16549,7 +16657,7 @@ export const MODELS = {
16549
16657
  cost: {
16550
16658
  input: 0.075,
16551
16659
  output: 0.5,
16552
- cacheRead: 0,
16660
+ cacheRead: 0.0375,
16553
16661
  cacheWrite: 0,
16554
16662
  },
16555
16663
  contextWindow: 262144,
@@ -16700,13 +16808,13 @@ export const MODELS = {
16700
16808
  reasoning: true,
16701
16809
  input: ["text"],
16702
16810
  cost: {
16703
- input: 0.12,
16704
- output: 0.5,
16811
+ input: 0.13,
16812
+ output: 0.52,
16705
16813
  cacheRead: 0,
16706
16814
  cacheWrite: 0,
16707
16815
  },
16708
16816
  contextWindow: 131072,
16709
- maxTokens: 16384,
16817
+ maxTokens: 8192,
16710
16818
  },
16711
16819
  "qwen/qwen3-30b-a3b-instruct-2507": {
16712
16820
  id: "qwen/qwen3-30b-a3b-instruct-2507",
@@ -16717,13 +16825,13 @@ export const MODELS = {
16717
16825
  reasoning: false,
16718
16826
  input: ["text"],
16719
16827
  cost: {
16720
- input: 0.09999999999999999,
16721
- output: 0.3,
16828
+ input: 0.04815,
16829
+ output: 0.19305,
16722
16830
  cacheRead: 0,
16723
16831
  cacheWrite: 0,
16724
16832
  },
16725
16833
  contextWindow: 262144,
16726
- maxTokens: 235929,
16834
+ maxTokens: 32000,
16727
16835
  },
16728
16836
  "qwen/qwen3-30b-a3b-thinking-2507": {
16729
16837
  id: "qwen/qwen3-30b-a3b-thinking-2507",
@@ -16972,13 +17080,13 @@ export const MODELS = {
16972
17080
  reasoning: false,
16973
17081
  input: ["text", "image"],
16974
17082
  cost: {
16975
- input: 0.13,
16976
- output: 0.52,
17083
+ input: 0.15,
17084
+ output: 0.6,
16977
17085
  cacheRead: 0,
16978
17086
  cacheWrite: 0,
16979
17087
  },
16980
17088
  contextWindow: 262144,
16981
- maxTokens: 32768,
17089
+ maxTokens: 16384,
16982
17090
  },
16983
17091
  "qwen/qwen3-vl-30b-a3b-thinking": {
16984
17092
  id: "qwen/qwen3-vl-30b-a3b-thinking",
@@ -17091,13 +17199,13 @@ export const MODELS = {
17091
17199
  reasoning: true,
17092
17200
  input: ["text", "image"],
17093
17201
  cost: {
17094
- input: 0.3125,
17095
- output: 1.25,
17096
- cacheRead: 0.15625,
17202
+ input: 0.1625,
17203
+ output: 1.3,
17204
+ cacheRead: 0,
17097
17205
  cacheWrite: 0,
17098
17206
  },
17099
17207
  contextWindow: 262144,
17100
- maxTokens: 16384,
17208
+ maxTokens: 65536,
17101
17209
  },
17102
17210
  "qwen/qwen3.5-397b-a17b": {
17103
17211
  id: "qwen/qwen3.5-397b-a17b",
@@ -17194,12 +17302,12 @@ export const MODELS = {
17194
17302
  input: ["text", "image"],
17195
17303
  cost: {
17196
17304
  input: 0.32,
17197
- output: 2.7,
17198
- cacheRead: 0.15,
17305
+ output: 3.1999999999999997,
17306
+ cacheRead: 0,
17199
17307
  cacheWrite: 0,
17200
17308
  },
17201
17309
  contextWindow: 262144,
17202
- maxTokens: 262140,
17310
+ maxTokens: 81920,
17203
17311
  },
17204
17312
  "qwen/qwen3.6-35b-a3b": {
17205
17313
  id: "qwen/qwen3.6-35b-a3b",
@@ -17657,7 +17765,7 @@ export const MODELS = {
17657
17765
  cacheRead: 0.16999999999999998,
17658
17766
  cacheWrite: 0,
17659
17767
  },
17660
- contextWindow: 1048576,
17768
+ contextWindow: 524288,
17661
17769
  maxTokens: 471859,
17662
17770
  },
17663
17771
  "thinkingmachines/inkling-small": {
@@ -17674,7 +17782,7 @@ export const MODELS = {
17674
17782
  cacheRead: 0.09999999999999999,
17675
17783
  cacheWrite: 0,
17676
17784
  },
17677
- contextWindow: 1048576,
17785
+ contextWindow: 524288,
17678
17786
  maxTokens: 262144,
17679
17787
  },
17680
17788
  "thinkingmachines/inkling-small:free": {
@@ -17873,9 +17981,9 @@ export const MODELS = {
17873
17981
  reasoning: true,
17874
17982
  input: ["text", "image"],
17875
17983
  cost: {
17876
- input: 1.5999999999999999,
17877
- output: 4.8,
17878
- cacheRead: 0.39999999999999997,
17984
+ input: 2,
17985
+ output: 6,
17986
+ cacheRead: 0.5,
17879
17987
  cacheWrite: 0,
17880
17988
  },
17881
17989
  contextWindow: 500000,
@@ -17963,7 +18071,7 @@ export const MODELS = {
17963
18071
  cacheRead: 0.0036,
17964
18072
  cacheWrite: 0,
17965
18073
  },
17966
- contextWindow: 1048576,
18074
+ contextWindow: 1050000,
17967
18075
  maxTokens: 131072,
17968
18076
  },
17969
18077
  "xiaomi/mimo-v2.6-pro-ultraspeed": {
@@ -18077,9 +18185,9 @@ export const MODELS = {
18077
18185
  reasoning: true,
18078
18186
  input: ["text"],
18079
18187
  cost: {
18080
- input: 0.39999999999999997,
18081
- output: 1.75,
18082
- cacheRead: 0.08,
18188
+ input: 0.6,
18189
+ output: 2.2,
18190
+ cacheRead: 0.11,
18083
18191
  cacheWrite: 0,
18084
18192
  },
18085
18193
  contextWindow: 204800,
@@ -18145,13 +18253,13 @@ export const MODELS = {
18145
18253
  reasoning: true,
18146
18254
  input: ["text"],
18147
18255
  cost: {
18148
- input: 0.966,
18149
- output: 3.036,
18150
- cacheRead: 0.1794,
18256
+ input: 1.4,
18257
+ output: 4.4,
18258
+ cacheRead: 0.26,
18151
18259
  cacheWrite: 0,
18152
18260
  },
18153
18261
  contextWindow: 204800,
18154
- maxTokens: 128000,
18262
+ maxTokens: 131072,
18155
18263
  },
18156
18264
  "z-ai/glm-5.2": {
18157
18265
  id: "z-ai/glm-5.2",
@@ -18162,13 +18270,13 @@ export const MODELS = {
18162
18270
  reasoning: true,
18163
18271
  input: ["text"],
18164
18272
  cost: {
18165
- input: 0.6496,
18166
- output: 2.0416,
18167
- cacheRead: 0.12064,
18273
+ input: 0.36,
18274
+ output: 3.9899999999999998,
18275
+ cacheRead: 0.26,
18168
18276
  cacheWrite: 0,
18169
18277
  },
18170
18278
  contextWindow: 1048576,
18171
- maxTokens: 131072,
18279
+ maxTokens: 943718,
18172
18280
  },
18173
18281
  "z-ai/glm-5.3": {
18174
18282
  id: "z-ai/glm-5.3",
@@ -18179,13 +18287,13 @@ export const MODELS = {
18179
18287
  reasoning: true,
18180
18288
  input: ["text"],
18181
18289
  cost: {
18182
- input: 0.84,
18183
- output: 2.64,
18184
- cacheRead: 0.156,
18290
+ input: 1.4,
18291
+ output: 4.4,
18292
+ cacheRead: 0.26,
18185
18293
  cacheWrite: 0,
18186
18294
  },
18187
- contextWindow: 1310720,
18188
- maxTokens: 131072,
18295
+ contextWindow: 1048576,
18296
+ maxTokens: 943717,
18189
18297
  },
18190
18298
  "z-ai/glm-5.3-flash": {
18191
18299
  id: "z-ai/glm-5.3-flash",
@@ -18198,11 +18306,11 @@ export const MODELS = {
18198
18306
  cost: {
18199
18307
  input: 0.15,
18200
18308
  output: 0.5,
18201
- cacheRead: 0.049999999999999996,
18309
+ cacheRead: 0.03,
18202
18310
  cacheWrite: 0,
18203
18311
  },
18204
- contextWindow: 1310720,
18205
- maxTokens: 943718,
18312
+ contextWindow: 1048576,
18313
+ maxTokens: 943717,
18206
18314
  },
18207
18315
  "z-ai/glm-5.3-flash:batch": {
18208
18316
  id: "z-ai/glm-5.3-flash:batch",
@@ -18367,9 +18475,9 @@ export const MODELS = {
18367
18475
  reasoning: true,
18368
18476
  input: ["text", "image"],
18369
18477
  cost: {
18370
- input: 0.04,
18371
- output: 1,
18372
- cacheRead: 0.01,
18478
+ input: 0.019799999999999998,
18479
+ output: 0.396,
18480
+ cacheRead: 0.0029100000000000003,
18373
18481
  cacheWrite: 0,
18374
18482
  },
18375
18483
  contextWindow: 1048576,
@@ -18384,13 +18492,13 @@ export const MODELS = {
18384
18492
  reasoning: true,
18385
18493
  input: ["text"],
18386
18494
  cost: {
18387
- input: 0.39,
18388
- output: 2.9000000000000004,
18389
- cacheRead: 0.25,
18495
+ input: 0.15,
18496
+ output: 3.5,
18497
+ cacheRead: 0.15,
18390
18498
  cacheWrite: 0,
18391
18499
  },
18392
18500
  contextWindow: 1048576,
18393
- maxTokens: 943718,
18501
+ maxTokens: 393216,
18394
18502
  },
18395
18503
  "~deepseek/deepseek-v4-flash-latest": {
18396
18504
  id: "~deepseek/deepseek-v4-flash-latest",
@@ -18403,12 +18511,12 @@ export const MODELS = {
18403
18511
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
18404
18512
  input: ["text"],
18405
18513
  cost: {
18406
- input: 0.03,
18407
- output: 0.32,
18408
- cacheRead: 0.016,
18514
+ input: 0.009899999999999999,
18515
+ output: 0.13068,
18516
+ cacheRead: 0.0013859999999999999,
18409
18517
  cacheWrite: 0,
18410
18518
  },
18411
- contextWindow: 1310720,
18519
+ contextWindow: 1048576,
18412
18520
  maxTokens: 943718,
18413
18521
  },
18414
18522
  "~google/gemini-flash-latest": {
@@ -18454,9 +18562,9 @@ export const MODELS = {
18454
18562
  reasoning: true,
18455
18563
  input: ["text", "image"],
18456
18564
  cost: {
18457
- input: 1.4,
18458
- output: 10.75,
18459
- cacheRead: 0.3,
18565
+ input: 0.3654,
18566
+ output: 9.1343,
18567
+ cacheRead: 0.39999999999999997,
18460
18568
  cacheWrite: 0,
18461
18569
  },
18462
18570
  contextWindow: 1048576,
@@ -18524,7 +18632,7 @@ export const MODELS = {
18524
18632
  cost: {
18525
18633
  input: 2,
18526
18634
  output: 10,
18527
- cacheRead: 0.19999999999999998,
18635
+ cacheRead: 0.09999999999999999,
18528
18636
  cacheWrite: 2.5,
18529
18637
  },
18530
18638
  contextWindow: 1050000,
@@ -18556,9 +18664,9 @@ export const MODELS = {
18556
18664
  reasoning: true,
18557
18665
  input: ["text", "image"],
18558
18666
  cost: {
18559
- input: 1.5999999999999999,
18560
- output: 4.8,
18561
- cacheRead: 0.39999999999999997,
18667
+ input: 2,
18668
+ output: 6,
18669
+ cacheRead: 0.5,
18562
18670
  cacheWrite: 0,
18563
18671
  },
18564
18672
  contextWindow: 500000,
@@ -18573,13 +18681,13 @@ export const MODELS = {
18573
18681
  reasoning: true,
18574
18682
  input: ["text", "image"],
18575
18683
  cost: {
18576
- input: 0.045,
18577
- output: 0.14,
18684
+ input: 0.02,
18685
+ output: 0.24750000000000003,
18578
18686
  cacheRead: 0.01,
18579
18687
  cacheWrite: 0,
18580
18688
  },
18581
- contextWindow: 1310720,
18582
- maxTokens: 128000,
18689
+ contextWindow: 1048576,
18690
+ maxTokens: 943718,
18583
18691
  },
18584
18692
  "~z-ai/glm-latest": {
18585
18693
  id: "~z-ai/glm-latest",
@@ -18590,12 +18698,12 @@ export const MODELS = {
18590
18698
  reasoning: true,
18591
18699
  input: ["text"],
18592
18700
  cost: {
18593
- input: 0.5625,
18594
- output: 2.5,
18595
- cacheRead: 0.125,
18701
+ input: 0.13,
18702
+ output: 4,
18703
+ cacheRead: 0.13,
18596
18704
  cacheWrite: 0,
18597
18705
  },
18598
- contextWindow: 1310720,
18706
+ contextWindow: 1048576,
18599
18707
  maxTokens: 131072,
18600
18708
  },
18601
18709
  },
@@ -18825,44 +18933,6 @@ export const MODELS = {
18825
18933
  contextWindow: 131072,
18826
18934
  maxTokens: 131072,
18827
18935
  },
18828
- "moonshotai/Kimi-K2.6": {
18829
- id: "moonshotai/Kimi-K2.6",
18830
- name: "Kimi K2.6",
18831
- api: "openai-completions",
18832
- provider: "together",
18833
- baseUrl: "https://api.together.ai/v1",
18834
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
18835
- reasoning: true,
18836
- thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
18837
- input: ["text", "image"],
18838
- cost: {
18839
- input: 1.2,
18840
- output: 4.5,
18841
- cacheRead: 0.2,
18842
- cacheWrite: 0,
18843
- },
18844
- contextWindow: 262144,
18845
- maxTokens: 131000,
18846
- },
18847
- "moonshotai/Kimi-K2.7-Code": {
18848
- id: "moonshotai/Kimi-K2.7-Code",
18849
- name: "Kimi K2.7 Code",
18850
- api: "openai-completions",
18851
- provider: "together",
18852
- baseUrl: "https://api.together.ai/v1",
18853
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
18854
- reasoning: true,
18855
- thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
18856
- input: ["text"],
18857
- cost: {
18858
- input: 0.95,
18859
- output: 4,
18860
- cacheRead: 0.19,
18861
- cacheWrite: 0,
18862
- },
18863
- contextWindow: 262144,
18864
- maxTokens: 131072,
18865
- },
18866
18936
  "moonshotai/Kimi-K3": {
18867
18937
  id: "moonshotai/Kimi-K3",
18868
18938
  name: "Kimi K3",
@@ -19350,7 +19420,7 @@ export const MODELS = {
19350
19420
  input: ["text", "image"],
19351
19421
  cost: {
19352
19422
  input: 0.39999999999999997,
19353
- output: 2.5,
19423
+ output: 2.4,
19354
19424
  cacheRead: 0.04,
19355
19425
  cacheWrite: 0.5,
19356
19426
  },
@@ -19539,7 +19609,7 @@ export const MODELS = {
19539
19609
  input: 4,
19540
19610
  output: 12,
19541
19611
  cacheRead: 0.5,
19542
- cacheWrite: 0,
19612
+ cacheWrite: 5,
19543
19613
  },
19544
19614
  contextWindow: 1000000,
19545
19615
  maxTokens: 131072,
@@ -19941,6 +20011,23 @@ export const MODELS = {
19941
20011
  contextWindow: 1000000,
19942
20012
  maxTokens: 128000,
19943
20013
  },
20014
+ "anthropic/claude-sonnet-5.5": {
20015
+ id: "anthropic/claude-sonnet-5.5",
20016
+ name: "Claude Sonnet 5.5",
20017
+ api: "anthropic-messages",
20018
+ provider: "vercel-ai-gateway",
20019
+ baseUrl: "https://ai-gateway.vercel.sh",
20020
+ reasoning: true,
20021
+ input: ["text", "image"],
20022
+ cost: {
20023
+ input: 2,
20024
+ output: 10,
20025
+ cacheRead: 0.19999999999999998,
20026
+ cacheWrite: 2.5,
20027
+ },
20028
+ contextWindow: 1000000,
20029
+ maxTokens: 128000,
20030
+ },
19944
20031
  "arcee-ai/trinity-large-thinking": {
19945
20032
  id: "arcee-ai/trinity-large-thinking",
19946
20033
  name: "Trinity Large Thinking",
@@ -20154,9 +20241,9 @@ export const MODELS = {
20154
20241
  reasoning: true,
20155
20242
  input: ["text", "image"],
20156
20243
  cost: {
20157
- input: 0.22,
20158
- output: 0.66,
20159
- cacheRead: 0.007,
20244
+ input: 0.21559999999999999,
20245
+ output: 0.6468,
20246
+ cacheRead: 0.0068,
20160
20247
  cacheWrite: 0,
20161
20248
  },
20162
20249
  contextWindow: 1048576,
@@ -20213,6 +20300,23 @@ export const MODELS = {
20213
20300
  contextWindow: 1048576,
20214
20301
  maxTokens: 32768,
20215
20302
  },
20303
+ "fireworks/ember-1": {
20304
+ id: "fireworks/ember-1",
20305
+ name: "Ember-1",
20306
+ api: "anthropic-messages",
20307
+ provider: "vercel-ai-gateway",
20308
+ baseUrl: "https://ai-gateway.vercel.sh",
20309
+ reasoning: true,
20310
+ input: ["text", "image"],
20311
+ cost: {
20312
+ input: 3,
20313
+ output: 15,
20314
+ cacheRead: 0.3,
20315
+ cacheWrite: 0,
20316
+ },
20317
+ contextWindow: 1048576,
20318
+ maxTokens: 1048576,
20319
+ },
20216
20320
  "google/gemini-2.5-flash": {
20217
20321
  id: "google/gemini-2.5-flash",
20218
20322
  name: "Gemini 2.5 Flash",
@@ -20511,26 +20615,9 @@ export const MODELS = {
20511
20615
  reasoning: true,
20512
20616
  input: ["text"],
20513
20617
  cost: {
20514
- input: 0,
20515
- output: 0,
20516
- cacheRead: 0,
20517
- cacheWrite: 0,
20518
- },
20519
- contextWindow: 256000,
20520
- maxTokens: 32000,
20521
- },
20522
- "inclusionai/ling-3.0-flash-fin-free": {
20523
- id: "inclusionai/ling-3.0-flash-fin-free",
20524
- name: "Ling 3.0 Flash Fin (Free)",
20525
- api: "anthropic-messages",
20526
- provider: "vercel-ai-gateway",
20527
- baseUrl: "https://ai-gateway.vercel.sh",
20528
- reasoning: true,
20529
- input: ["text"],
20530
- cost: {
20531
- input: 0,
20532
- output: 0,
20533
- cacheRead: 0,
20618
+ input: 0.075,
20619
+ output: 0.22,
20620
+ cacheRead: 0.015,
20534
20621
  cacheWrite: 0,
20535
20622
  },
20536
20623
  contextWindow: 256000,
@@ -20587,6 +20674,40 @@ export const MODELS = {
20587
20674
  contextWindow: 256000,
20588
20675
  maxTokens: 32000,
20589
20676
  },
20677
+ "inclusionai/ling-3.1-flash": {
20678
+ id: "inclusionai/ling-3.1-flash",
20679
+ name: "Ling 3.1 Flash",
20680
+ api: "anthropic-messages",
20681
+ provider: "vercel-ai-gateway",
20682
+ baseUrl: "https://ai-gateway.vercel.sh",
20683
+ reasoning: true,
20684
+ input: ["text"],
20685
+ cost: {
20686
+ input: 0,
20687
+ output: 0,
20688
+ cacheRead: 0,
20689
+ cacheWrite: 0,
20690
+ },
20691
+ contextWindow: 262144,
20692
+ maxTokens: 32768,
20693
+ },
20694
+ "inclusionai/ling-3.1-flash-free": {
20695
+ id: "inclusionai/ling-3.1-flash-free",
20696
+ name: "Ling 3.1 Flash (Free)",
20697
+ api: "anthropic-messages",
20698
+ provider: "vercel-ai-gateway",
20699
+ baseUrl: "https://ai-gateway.vercel.sh",
20700
+ reasoning: true,
20701
+ input: ["text"],
20702
+ cost: {
20703
+ input: 0,
20704
+ output: 0,
20705
+ cacheRead: 0,
20706
+ cacheWrite: 0,
20707
+ },
20708
+ contextWindow: 262144,
20709
+ maxTokens: 32768,
20710
+ },
20590
20711
  "interfaze/interfaze-beta": {
20591
20712
  id: "interfaze/interfaze-beta",
20592
20713
  name: "Interfaze Beta",
@@ -20604,6 +20725,23 @@ export const MODELS = {
20604
20725
  contextWindow: 1000000,
20605
20726
  maxTokens: 32000,
20606
20727
  },
20728
+ "meituan/longcat-2.5-preview": {
20729
+ id: "meituan/longcat-2.5-preview",
20730
+ name: "LongCat 2.5 Preview",
20731
+ api: "anthropic-messages",
20732
+ provider: "vercel-ai-gateway",
20733
+ baseUrl: "https://ai-gateway.vercel.sh",
20734
+ reasoning: true,
20735
+ input: ["text", "image"],
20736
+ cost: {
20737
+ input: 0.3,
20738
+ output: 1.2,
20739
+ cacheRead: 0.006,
20740
+ cacheWrite: 0,
20741
+ },
20742
+ contextWindow: 1048576,
20743
+ maxTokens: 131072,
20744
+ },
20607
20745
  "meta/llama-3.1-70b": {
20608
20746
  id: "meta/llama-3.1-70b",
20609
20747
  name: "Llama 3.1 70B Instruct",
@@ -21159,7 +21297,7 @@ export const MODELS = {
21159
21297
  cost: {
21160
21298
  input: 0.95,
21161
21299
  output: 4,
21162
- cacheRead: 0.16,
21300
+ cacheRead: 0.19,
21163
21301
  cacheWrite: 0,
21164
21302
  },
21165
21303
  contextWindow: 256000,
@@ -22183,6 +22321,40 @@ export const MODELS = {
22183
22321
  contextWindow: 1050000,
22184
22322
  maxTokens: 128000,
22185
22323
  },
22324
+ "openai/gpt-6.1-sol": {
22325
+ id: "openai/gpt-6.1-sol",
22326
+ name: "GPT-6.1 Sol",
22327
+ api: "anthropic-messages",
22328
+ provider: "vercel-ai-gateway",
22329
+ baseUrl: "https://ai-gateway.vercel.sh",
22330
+ reasoning: true,
22331
+ input: ["text", "image"],
22332
+ cost: {
22333
+ input: 2,
22334
+ output: 10,
22335
+ cacheRead: 0.09999999999999999,
22336
+ cacheWrite: 2.5,
22337
+ },
22338
+ contextWindow: 1050000,
22339
+ maxTokens: 128000,
22340
+ },
22341
+ "openai/gpt-6.1-sol-fast": {
22342
+ id: "openai/gpt-6.1-sol-fast",
22343
+ name: "GPT-6.1 Sol (Fast)",
22344
+ api: "anthropic-messages",
22345
+ provider: "vercel-ai-gateway",
22346
+ baseUrl: "https://ai-gateway.vercel.sh",
22347
+ reasoning: true,
22348
+ input: ["text", "image"],
22349
+ cost: {
22350
+ input: 4,
22351
+ output: 20,
22352
+ cacheRead: 0.19999999999999998,
22353
+ cacheWrite: 5,
22354
+ },
22355
+ contextWindow: 1050000,
22356
+ maxTokens: 128000,
22357
+ },
22186
22358
  "openai/gpt-oss-120b": {
22187
22359
  id: "openai/gpt-oss-120b",
22188
22360
  name: "GPT OSS 120B",
@@ -22702,9 +22874,9 @@ export const MODELS = {
22702
22874
  reasoning: true,
22703
22875
  input: ["text", "image"],
22704
22876
  cost: {
22705
- input: 1.2,
22706
- output: 3.5999999999999996,
22707
- cacheRead: 0.3,
22877
+ input: 2,
22878
+ output: 6,
22879
+ cacheRead: 0.5,
22708
22880
  cacheWrite: 0,
22709
22881
  },
22710
22882
  contextWindow: 500000,
@@ -22821,7 +22993,7 @@ export const MODELS = {
22821
22993
  reasoning: true,
22822
22994
  input: ["text", "image"],
22823
22995
  cost: {
22824
- input: 0.5,
22996
+ input: 0.44999999999999996,
22825
22997
  output: 1.2,
22826
22998
  cacheRead: 0.09999999999999999,
22827
22999
  cacheWrite: 0,
@@ -22993,7 +23165,7 @@ export const MODELS = {
22993
23165
  cost: {
22994
23166
  input: 0.6,
22995
23167
  output: 2.2,
22996
- cacheRead: 0.12,
23168
+ cacheRead: 0,
22997
23169
  cacheWrite: 0,
22998
23170
  },
22999
23171
  contextWindow: 200000,
@@ -23110,9 +23282,9 @@ export const MODELS = {
23110
23282
  reasoning: true,
23111
23283
  input: ["text"],
23112
23284
  cost: {
23113
- input: 2.0999999999999996,
23114
- output: 6.6000000000000005,
23115
- cacheRead: 0.21,
23285
+ input: 2.8,
23286
+ output: 8.8,
23287
+ cacheRead: 0.56,
23116
23288
  cacheWrite: 0,
23117
23289
  },
23118
23290
  contextWindow: 1000000,