@elyracode/ai 0.9.54 → 0.9.56

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.
@@ -597,6 +597,24 @@ export const MODELS = {
597
597
  contextWindow: 1000000,
598
598
  maxTokens: 128000,
599
599
  },
600
+ "au.anthropic.claude-sonnet-5-5": {
601
+ id: "au.anthropic.claude-sonnet-5-5",
602
+ name: "Claude Sonnet 5.5 (AU)",
603
+ api: "bedrock-converse-stream",
604
+ provider: "amazon-bedrock",
605
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
606
+ reasoning: true,
607
+ thinkingType: "adaptive",
608
+ input: ["text", "image"],
609
+ cost: {
610
+ input: 2.2,
611
+ output: 11,
612
+ cacheRead: 0.11,
613
+ cacheWrite: 2.75,
614
+ },
615
+ contextWindow: 1000000,
616
+ maxTokens: 128000,
617
+ },
600
618
  "ca.amazon.nova-lite-v1:0": {
601
619
  id: "ca.amazon.nova-lite-v1:0",
602
620
  name: "Nova Lite (CA)",
@@ -1417,6 +1435,23 @@ export const MODELS = {
1417
1435
  contextWindow: 1050000,
1418
1436
  maxTokens: 128000,
1419
1437
  },
1438
+ "global.openai.gpt-6.1-terra": {
1439
+ id: "global.openai.gpt-6.1-terra",
1440
+ name: "GPT-6.1 Terra (Global)",
1441
+ api: "bedrock-converse-stream",
1442
+ provider: "amazon-bedrock",
1443
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1444
+ reasoning: true,
1445
+ input: ["text", "image"],
1446
+ cost: {
1447
+ input: 1,
1448
+ output: 5,
1449
+ cacheRead: 0.05,
1450
+ cacheWrite: 1.25,
1451
+ },
1452
+ contextWindow: 1050000,
1453
+ maxTokens: 128000,
1454
+ },
1420
1455
  "global.xai.grok-4.6": {
1421
1456
  id: "global.xai.grok-4.6",
1422
1457
  name: "Grok 4.6 (Global)",
@@ -2334,6 +2369,23 @@ export const MODELS = {
2334
2369
  contextWindow: 1050000,
2335
2370
  maxTokens: 128000,
2336
2371
  },
2372
+ "openai.gpt-6.1-terra": {
2373
+ id: "openai.gpt-6.1-terra",
2374
+ name: "GPT-6.1 Terra",
2375
+ api: "bedrock-converse-stream",
2376
+ provider: "amazon-bedrock",
2377
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2378
+ reasoning: true,
2379
+ input: ["text", "image"],
2380
+ cost: {
2381
+ input: 1.1,
2382
+ output: 5.5,
2383
+ cacheRead: 0.055,
2384
+ cacheWrite: 1.375,
2385
+ },
2386
+ contextWindow: 1050000,
2387
+ maxTokens: 128000,
2388
+ },
2337
2389
  "openai.gpt-oss-120b": {
2338
2390
  id: "openai.gpt-oss-120b",
2339
2391
  name: "gpt-oss-120b",
@@ -3205,6 +3257,23 @@ export const MODELS = {
3205
3257
  contextWindow: 1050000,
3206
3258
  maxTokens: 128000,
3207
3259
  },
3260
+ "us.openai.gpt-6.1-terra": {
3261
+ id: "us.openai.gpt-6.1-terra",
3262
+ name: "GPT-6.1 Terra (US)",
3263
+ api: "bedrock-converse-stream",
3264
+ provider: "amazon-bedrock",
3265
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
3266
+ reasoning: true,
3267
+ input: ["text", "image"],
3268
+ cost: {
3269
+ input: 1.1,
3270
+ output: 5.5,
3271
+ cacheRead: 0.055,
3272
+ cacheWrite: 1.375,
3273
+ },
3274
+ contextWindow: 1050000,
3275
+ maxTokens: 128000,
3276
+ },
3208
3277
  "us.writer.palmyra-x4-v1:0": {
3209
3278
  id: "us.writer.palmyra-x4-v1:0",
3210
3279
  name: "Palmyra X4 (US)",
@@ -3988,24 +4057,6 @@ export const MODELS = {
3988
4057
  contextWindow: 400000,
3989
4058
  maxTokens: 128000,
3990
4059
  },
3991
- "gpt-5.2-chat-latest": {
3992
- id: "gpt-5.2-chat-latest",
3993
- name: "GPT-5.2 Chat",
3994
- api: "azure-openai-responses",
3995
- provider: "azure-openai-responses",
3996
- baseUrl: "",
3997
- reasoning: true,
3998
- thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
3999
- input: ["text", "image"],
4000
- cost: {
4001
- input: 1.75,
4002
- output: 14,
4003
- cacheRead: 0.175,
4004
- cacheWrite: 0,
4005
- },
4006
- contextWindow: 128000,
4007
- maxTokens: 16384,
4008
- },
4009
4060
  "gpt-5.2-pro": {
4010
4061
  id: "gpt-5.2-pro",
4011
4062
  name: "GPT-5.2 Pro",
@@ -4024,24 +4075,6 @@ export const MODELS = {
4024
4075
  contextWindow: 400000,
4025
4076
  maxTokens: 128000,
4026
4077
  },
4027
- "gpt-5.3-chat-latest": {
4028
- id: "gpt-5.3-chat-latest",
4029
- name: "GPT-5.3 Chat (latest)",
4030
- api: "azure-openai-responses",
4031
- provider: "azure-openai-responses",
4032
- baseUrl: "",
4033
- reasoning: false,
4034
- thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
4035
- input: ["text", "image"],
4036
- cost: {
4037
- input: 1.75,
4038
- output: 14,
4039
- cacheRead: 0.175,
4040
- cacheWrite: 0,
4041
- },
4042
- contextWindow: 128000,
4043
- maxTokens: 16384,
4044
- },
4045
4078
  "gpt-5.3-codex": {
4046
4079
  id: "gpt-5.3-codex",
4047
4080
  name: "GPT-5.3 Codex",
@@ -4326,6 +4359,23 @@ export const MODELS = {
4326
4359
  contextWindow: 1050000,
4327
4360
  maxTokens: 128000,
4328
4361
  },
4362
+ "gpt-6.1-terra": {
4363
+ id: "gpt-6.1-terra",
4364
+ name: "GPT-6.1 Terra",
4365
+ api: "azure-openai-responses",
4366
+ provider: "azure-openai-responses",
4367
+ baseUrl: "",
4368
+ reasoning: true,
4369
+ input: ["text", "image"],
4370
+ cost: {
4371
+ input: 1,
4372
+ output: 5,
4373
+ cacheRead: 0.05,
4374
+ cacheWrite: 1.25,
4375
+ },
4376
+ contextWindow: 1050000,
4377
+ maxTokens: 128000,
4378
+ },
4329
4379
  "gpt-daybreak-blue-latest": {
4330
4380
  id: "gpt-daybreak-blue-latest",
4331
4381
  name: "Daybreak Blue",
@@ -4492,7 +4542,7 @@ export const MODELS = {
4492
4542
  cost: {
4493
4543
  input: 0.35,
4494
4544
  output: 0.75,
4495
- cacheRead: 0,
4545
+ cacheRead: 0.35,
4496
4546
  cacheWrite: 0,
4497
4547
  },
4498
4548
  contextWindow: 131072,
@@ -4754,7 +4804,7 @@ export const MODELS = {
4754
4804
  cost: {
4755
4805
  input: 2,
4756
4806
  output: 10,
4757
- cacheRead: 0.2,
4807
+ cacheRead: 0.1,
4758
4808
  cacheWrite: 2.5,
4759
4809
  },
4760
4810
  contextWindow: 1000000,
@@ -5053,10 +5103,10 @@ export const MODELS = {
5053
5103
  thinkingLevelMap: { "off": null },
5054
5104
  input: ["text", "image"],
5055
5105
  cost: {
5056
- input: 2,
5057
- output: 10,
5058
- cacheRead: 0.25,
5059
- cacheWrite: 3.125,
5106
+ input: 4,
5107
+ output: 20,
5108
+ cacheRead: 0.4,
5109
+ cacheWrite: 5,
5060
5110
  },
5061
5111
  contextWindow: 1050000,
5062
5112
  maxTokens: 128000,
@@ -5147,6 +5197,23 @@ export const MODELS = {
5147
5197
  contextWindow: 1050000,
5148
5198
  maxTokens: 128000,
5149
5199
  },
5200
+ "gpt-6.1-terra": {
5201
+ id: "gpt-6.1-terra",
5202
+ name: "GPT-6.1 Terra",
5203
+ api: "openai-responses",
5204
+ provider: "cloudflare-ai-gateway",
5205
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
5206
+ reasoning: true,
5207
+ input: ["text", "image"],
5208
+ cost: {
5209
+ input: 1,
5210
+ output: 5,
5211
+ cacheRead: 0.05,
5212
+ cacheWrite: 1.25,
5213
+ },
5214
+ contextWindow: 1050000,
5215
+ maxTokens: 128000,
5216
+ },
5150
5217
  "o3": {
5151
5218
  id: "o3",
5152
5219
  name: "o3",
@@ -5238,6 +5305,25 @@ export const MODELS = {
5238
5305
  contextWindow: 1048576,
5239
5306
  maxTokens: 1048576,
5240
5307
  },
5308
+ "@cf/deepseek-ai/deepseek-v4.1-flash-1017": {
5309
+ id: "@cf/deepseek-ai/deepseek-v4.1-flash-1017",
5310
+ name: "DeepSeek V4.1 Flash 1017",
5311
+ api: "openai-completions",
5312
+ provider: "cloudflare-workers-ai",
5313
+ baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
5314
+ compat: { "sendSessionAffinityHeaders": true, "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
5315
+ reasoning: true,
5316
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
5317
+ input: ["text", "image"],
5318
+ cost: {
5319
+ input: 0.3,
5320
+ output: 1.2,
5321
+ cacheRead: 0.006,
5322
+ cacheWrite: 0,
5323
+ },
5324
+ contextWindow: 1048576,
5325
+ maxTokens: 1048576,
5326
+ },
5241
5327
  "@cf/google/gemma-4-26b-a4b-it": {
5242
5328
  id: "@cf/google/gemma-4-26b-a4b-it",
5243
5329
  name: "Gemma 4 26B A4B IT",
@@ -5585,6 +5671,23 @@ export const MODELS = {
5585
5671
  contextWindow: 1000000,
5586
5672
  maxTokens: 384000,
5587
5673
  },
5674
+ "accounts/fireworks/models/deepseek-v4p1-flash-1017": {
5675
+ id: "accounts/fireworks/models/deepseek-v4p1-flash-1017",
5676
+ name: "DeepSeek V4.1 Flash 1017",
5677
+ api: "anthropic-messages",
5678
+ provider: "fireworks",
5679
+ baseUrl: "https://api.fireworks.ai/inference",
5680
+ reasoning: true,
5681
+ input: ["text", "image"],
5682
+ cost: {
5683
+ input: 0.3,
5684
+ output: 1.2,
5685
+ cacheRead: 0.006,
5686
+ cacheWrite: 0,
5687
+ },
5688
+ contextWindow: 1000000,
5689
+ maxTokens: 384000,
5690
+ },
5588
5691
  "accounts/fireworks/models/ember-1": {
5589
5692
  id: "accounts/fireworks/models/ember-1",
5590
5693
  name: "Ember-1",
@@ -5704,6 +5807,40 @@ export const MODELS = {
5704
5807
  contextWindow: 512000,
5705
5808
  maxTokens: 512000,
5706
5809
  },
5810
+ "accounts/fireworks/models/minimax-m3p1-flash": {
5811
+ id: "accounts/fireworks/models/minimax-m3p1-flash",
5812
+ name: "MiniMax-M3.1-Flash",
5813
+ api: "anthropic-messages",
5814
+ provider: "fireworks",
5815
+ baseUrl: "https://api.fireworks.ai/inference",
5816
+ reasoning: true,
5817
+ input: ["text", "image"],
5818
+ cost: {
5819
+ input: 0.15,
5820
+ output: 0.6,
5821
+ cacheRead: 0.015,
5822
+ cacheWrite: 0,
5823
+ },
5824
+ contextWindow: 1000000,
5825
+ maxTokens: 512000,
5826
+ },
5827
+ "accounts/fireworks/models/muse-spark-open": {
5828
+ id: "accounts/fireworks/models/muse-spark-open",
5829
+ name: "Muse Spark Open",
5830
+ api: "anthropic-messages",
5831
+ provider: "fireworks",
5832
+ baseUrl: "https://api.fireworks.ai/inference",
5833
+ reasoning: true,
5834
+ input: ["text", "image"],
5835
+ cost: {
5836
+ input: 1.25,
5837
+ output: 4.25,
5838
+ cacheRead: 0.15,
5839
+ cacheWrite: 0,
5840
+ },
5841
+ contextWindow: 1048576,
5842
+ maxTokens: 131072,
5843
+ },
5707
5844
  "accounts/fireworks/models/nemotron-3-ultra-nvfp4": {
5708
5845
  id: "accounts/fireworks/models/nemotron-3-ultra-nvfp4",
5709
5846
  name: "Nemotron 3 Ultra 550B A55B",
@@ -5789,6 +5926,40 @@ export const MODELS = {
5789
5926
  contextWindow: 1000000,
5790
5927
  maxTokens: 384000,
5791
5928
  },
5929
+ "accounts/fireworks/routers/deepseek-v4p1-flash-1017-spot": {
5930
+ id: "accounts/fireworks/routers/deepseek-v4p1-flash-1017-spot",
5931
+ name: "DeepSeek V4.1 Flash 1017 Spot",
5932
+ api: "anthropic-messages",
5933
+ provider: "fireworks",
5934
+ baseUrl: "https://api.fireworks.ai/inference",
5935
+ reasoning: true,
5936
+ input: ["text", "image"],
5937
+ cost: {
5938
+ input: 0.21,
5939
+ output: 0.84,
5940
+ cacheRead: 0.0042,
5941
+ cacheWrite: 0,
5942
+ },
5943
+ contextWindow: 1000000,
5944
+ maxTokens: 384000,
5945
+ },
5946
+ "accounts/fireworks/routers/deepseek-v4p1-flash-spot": {
5947
+ id: "accounts/fireworks/routers/deepseek-v4p1-flash-spot",
5948
+ name: "DeepSeek V4.1 Flash Spot",
5949
+ api: "anthropic-messages",
5950
+ provider: "fireworks",
5951
+ baseUrl: "https://api.fireworks.ai/inference",
5952
+ reasoning: true,
5953
+ input: ["text", "image"],
5954
+ cost: {
5955
+ input: 0.21,
5956
+ output: 0.84,
5957
+ cacheRead: 0.0042,
5958
+ cacheWrite: 0,
5959
+ },
5960
+ contextWindow: 1000000,
5961
+ maxTokens: 384000,
5962
+ },
5792
5963
  "accounts/fireworks/routers/glm-5p3-fast": {
5793
5964
  id: "accounts/fireworks/routers/glm-5p3-fast",
5794
5965
  name: "GLM 5.3 Fast",
@@ -5806,6 +5977,23 @@ export const MODELS = {
5806
5977
  contextWindow: 1048572,
5807
5978
  maxTokens: 262144,
5808
5979
  },
5980
+ "accounts/fireworks/routers/glm-5p3-spot": {
5981
+ id: "accounts/fireworks/routers/glm-5p3-spot",
5982
+ name: "GLM 5.3 Spot",
5983
+ api: "anthropic-messages",
5984
+ provider: "fireworks",
5985
+ baseUrl: "https://api.fireworks.ai/inference",
5986
+ reasoning: true,
5987
+ input: ["text"],
5988
+ cost: {
5989
+ input: 0.98,
5990
+ output: 3.08,
5991
+ cacheRead: 0.182,
5992
+ cacheWrite: 0,
5993
+ },
5994
+ contextWindow: 1048573,
5995
+ maxTokens: 262144,
5996
+ },
5809
5997
  "accounts/fireworks/routers/glm-fast-latest": {
5810
5998
  id: "accounts/fireworks/routers/glm-fast-latest",
5811
5999
  name: "GLM 5.3 Fast (Latest)",
@@ -5891,6 +6079,23 @@ export const MODELS = {
5891
6079
  contextWindow: 1048576,
5892
6080
  maxTokens: 131072,
5893
6081
  },
6082
+ "accounts/fireworks/routers/kimi-k3-spot": {
6083
+ id: "accounts/fireworks/routers/kimi-k3-spot",
6084
+ name: "Kimi K3 Spot",
6085
+ api: "anthropic-messages",
6086
+ provider: "fireworks",
6087
+ baseUrl: "https://api.fireworks.ai/inference",
6088
+ reasoning: true,
6089
+ input: ["text", "image"],
6090
+ cost: {
6091
+ input: 2.1,
6092
+ output: 10.5,
6093
+ cacheRead: 0.21,
6094
+ cacheWrite: 0,
6095
+ },
6096
+ contextWindow: 1048576,
6097
+ maxTokens: 131072,
6098
+ },
5894
6099
  "accounts/fireworks/routers/kimi-latest": {
5895
6100
  id: "accounts/fireworks/routers/kimi-latest",
5896
6101
  name: "Kimi Latest",
@@ -6022,25 +6227,6 @@ export const MODELS = {
6022
6227
  contextWindow: 1000000,
6023
6228
  maxTokens: 128000,
6024
6229
  },
6025
- "claude-opus-4.7": {
6026
- id: "claude-opus-4.7",
6027
- name: "Claude Opus 4.7",
6028
- api: "anthropic-messages",
6029
- provider: "github-copilot",
6030
- baseUrl: "https://api.individual.githubcopilot.com",
6031
- 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" },
6032
- reasoning: true,
6033
- thinkingLevelMap: { "xhigh": "xhigh" },
6034
- input: ["text", "image"],
6035
- cost: {
6036
- input: 5,
6037
- output: 25,
6038
- cacheRead: 0.5,
6039
- cacheWrite: 6.25,
6040
- },
6041
- contextWindow: 200000,
6042
- maxTokens: 32000,
6043
- },
6044
6230
  "claude-opus-4.8": {
6045
6231
  id: "claude-opus-4.8",
6046
6232
  name: "Claude Opus 4.8",
@@ -6154,63 +6340,6 @@ export const MODELS = {
6154
6340
  contextWindow: 1000000,
6155
6341
  maxTokens: 128000,
6156
6342
  },
6157
- "gemini-3.5-flash": {
6158
- id: "gemini-3.5-flash",
6159
- name: "Gemini 3.5 Flash",
6160
- api: "openai-completions",
6161
- provider: "github-copilot",
6162
- baseUrl: "https://api.individual.githubcopilot.com",
6163
- 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" },
6164
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
6165
- reasoning: true,
6166
- input: ["text", "image"],
6167
- cost: {
6168
- input: 1.5,
6169
- output: 9,
6170
- cacheRead: 0.15,
6171
- cacheWrite: 0,
6172
- },
6173
- contextWindow: 200000,
6174
- maxTokens: 64000,
6175
- },
6176
- "gemini-3.6-flash": {
6177
- id: "gemini-3.6-flash",
6178
- name: "Gemini 3.6 Flash",
6179
- api: "openai-completions",
6180
- provider: "github-copilot",
6181
- baseUrl: "https://api.individual.githubcopilot.com",
6182
- 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" },
6183
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
6184
- reasoning: true,
6185
- input: ["text", "image"],
6186
- cost: {
6187
- input: 0.75,
6188
- output: 3.75,
6189
- cacheRead: 0.075,
6190
- cacheWrite: 0,
6191
- },
6192
- contextWindow: 1000000,
6193
- maxTokens: 64000,
6194
- },
6195
- "gemini-3.7-flash": {
6196
- id: "gemini-3.7-flash",
6197
- name: "Gemini 3.7 Flash",
6198
- api: "openai-completions",
6199
- provider: "github-copilot",
6200
- baseUrl: "https://api.individual.githubcopilot.com",
6201
- 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" },
6202
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
6203
- reasoning: true,
6204
- input: ["text", "image"],
6205
- cost: {
6206
- input: 0.75,
6207
- output: 3.75,
6208
- cacheRead: 0.075,
6209
- cacheWrite: 0,
6210
- },
6211
- contextWindow: 1000000,
6212
- maxTokens: 64000,
6213
- },
6214
6343
  "gemini-3.8-flash": {
6215
6344
  id: "gemini-3.8-flash",
6216
6345
  name: "Gemini 3.8 Flash",
@@ -6249,25 +6378,6 @@ export const MODELS = {
6249
6378
  contextWindow: 1048576,
6250
6379
  maxTokens: 65536,
6251
6380
  },
6252
- "gpt-5-mini": {
6253
- id: "gpt-5-mini",
6254
- name: "GPT-5 Mini",
6255
- api: "openai-responses",
6256
- provider: "github-copilot",
6257
- baseUrl: "https://api.individual.githubcopilot.com",
6258
- 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" },
6259
- reasoning: true,
6260
- thinkingLevelMap: { "off": null },
6261
- input: ["text", "image"],
6262
- cost: {
6263
- input: 0.25,
6264
- output: 2,
6265
- cacheRead: 0.025,
6266
- cacheWrite: 0,
6267
- },
6268
- contextWindow: 264000,
6269
- maxTokens: 64000,
6270
- },
6271
6381
  "gpt-5.3-codex": {
6272
6382
  id: "gpt-5.3-codex",
6273
6383
  name: "GPT-5.3 Codex",
@@ -6287,44 +6397,6 @@ export const MODELS = {
6287
6397
  contextWindow: 400000,
6288
6398
  maxTokens: 128000,
6289
6399
  },
6290
- "gpt-5.4": {
6291
- id: "gpt-5.4",
6292
- name: "GPT-5.4",
6293
- api: "openai-responses",
6294
- provider: "github-copilot",
6295
- baseUrl: "https://api.individual.githubcopilot.com",
6296
- 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" },
6297
- reasoning: true,
6298
- thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
6299
- input: ["text", "image"],
6300
- cost: {
6301
- input: 2.5,
6302
- output: 15,
6303
- cacheRead: 0.25,
6304
- cacheWrite: 0,
6305
- },
6306
- contextWindow: 1050000,
6307
- maxTokens: 128000,
6308
- },
6309
- "gpt-5.4-mini": {
6310
- id: "gpt-5.4-mini",
6311
- name: "GPT-5.4 mini",
6312
- api: "openai-responses",
6313
- provider: "github-copilot",
6314
- baseUrl: "https://api.individual.githubcopilot.com",
6315
- 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" },
6316
- reasoning: true,
6317
- thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
6318
- input: ["text", "image"],
6319
- cost: {
6320
- input: 0.75,
6321
- output: 4.5,
6322
- cacheRead: 0.075,
6323
- cacheWrite: 0,
6324
- },
6325
- contextWindow: 400000,
6326
- maxTokens: 128000,
6327
- },
6328
6400
  "gpt-5.4-nano": {
6329
6401
  id: "gpt-5.4-nano",
6330
6402
  name: "GPT-5.4 nano",
@@ -6344,25 +6416,6 @@ export const MODELS = {
6344
6416
  contextWindow: 400000,
6345
6417
  maxTokens: 128000,
6346
6418
  },
6347
- "gpt-5.5": {
6348
- id: "gpt-5.5",
6349
- name: "GPT-5.5",
6350
- api: "openai-responses",
6351
- provider: "github-copilot",
6352
- baseUrl: "https://api.individual.githubcopilot.com",
6353
- 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" },
6354
- reasoning: true,
6355
- thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
6356
- input: ["text", "image"],
6357
- cost: {
6358
- input: 5,
6359
- output: 30,
6360
- cacheRead: 0.5,
6361
- cacheWrite: 0,
6362
- },
6363
- contextWindow: 1050000,
6364
- maxTokens: 128000,
6365
- },
6366
6419
  "gpt-5.6-luna": {
6367
6420
  id: "gpt-5.6-luna",
6368
6421
  name: "GPT-5.6 Luna",
@@ -6496,6 +6549,25 @@ export const MODELS = {
6496
6549
  contextWindow: 1050000,
6497
6550
  maxTokens: 128000,
6498
6551
  },
6552
+ "gpt-6.1-terra": {
6553
+ id: "gpt-6.1-terra",
6554
+ name: "GPT-6.1 Terra",
6555
+ api: "openai-completions",
6556
+ provider: "github-copilot",
6557
+ baseUrl: "https://api.individual.githubcopilot.com",
6558
+ 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" },
6559
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
6560
+ reasoning: true,
6561
+ input: ["text", "image"],
6562
+ cost: {
6563
+ input: 1,
6564
+ output: 5,
6565
+ cacheRead: 0.05,
6566
+ cacheWrite: 1.25,
6567
+ },
6568
+ contextWindow: 1050000,
6569
+ maxTokens: 128000,
6570
+ },
6499
6571
  "grok-4.5": {
6500
6572
  id: "grok-4.5",
6501
6573
  name: "Grok 4.5",
@@ -6553,25 +6625,6 @@ export const MODELS = {
6553
6625
  contextWindow: 500000,
6554
6626
  maxTokens: 128000,
6555
6627
  },
6556
- "kimi-k2.7-code": {
6557
- id: "kimi-k2.7-code",
6558
- name: "Kimi K2.7 Code",
6559
- api: "openai-completions",
6560
- provider: "github-copilot",
6561
- baseUrl: "https://api.individual.githubcopilot.com",
6562
- 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" },
6563
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
6564
- reasoning: true,
6565
- input: ["text", "image"],
6566
- cost: {
6567
- input: 0.95,
6568
- output: 4,
6569
- cacheRead: 0.19,
6570
- cacheWrite: 0,
6571
- },
6572
- contextWindow: 256000,
6573
- maxTokens: 32000,
6574
- },
6575
6628
  "kimi-k3": {
6576
6629
  id: "kimi-k3",
6577
6630
  name: "Kimi K3",
@@ -6591,25 +6644,6 @@ export const MODELS = {
6591
6644
  contextWindow: 1048576,
6592
6645
  maxTokens: 131072,
6593
6646
  },
6594
- "mai-code-1-flash-picker": {
6595
- id: "mai-code-1-flash-picker",
6596
- name: "MAI-Code-1-Flash",
6597
- api: "openai-completions",
6598
- provider: "github-copilot",
6599
- baseUrl: "https://api.individual.githubcopilot.com",
6600
- 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" },
6601
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
6602
- reasoning: true,
6603
- input: ["text"],
6604
- cost: {
6605
- input: 0.75,
6606
- output: 4.5,
6607
- cacheRead: 0.075,
6608
- cacheWrite: 0,
6609
- },
6610
- contextWindow: 256000,
6611
- maxTokens: 128000,
6612
- },
6613
6647
  "mai-code-1.1-flash": {
6614
6648
  id: "mai-code-1.1-flash",
6615
6649
  name: "MAI-Code-1.1-Flash",
@@ -7003,6 +7037,24 @@ export const MODELS = {
7003
7037
  contextWindow: 1048576,
7004
7038
  maxTokens: 65536,
7005
7039
  },
7040
+ "gemini-pro-latest": {
7041
+ id: "gemini-pro-latest",
7042
+ name: "Gemini Pro Latest",
7043
+ api: "google-generative-ai",
7044
+ provider: "google",
7045
+ baseUrl: "https://generativelanguage.googleapis.com/v1beta",
7046
+ reasoning: true,
7047
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "LOW", "medium": "MEDIUM", "high": "HIGH" },
7048
+ input: ["text", "image"],
7049
+ cost: {
7050
+ input: 2,
7051
+ output: 12,
7052
+ cacheRead: 0.2,
7053
+ cacheWrite: 0,
7054
+ },
7055
+ contextWindow: 1048576,
7056
+ maxTokens: 65536,
7057
+ },
7006
7058
  "gemma-4-26b-a4b-it": {
7007
7059
  id: "gemma-4-26b-a4b-it",
7008
7060
  name: "Gemma 4 26B A4B IT",
@@ -7491,7 +7543,7 @@ export const MODELS = {
7491
7543
  cost: {
7492
7544
  input: 0.075,
7493
7545
  output: 0.3,
7494
- cacheRead: 0,
7546
+ cacheRead: 0.0375,
7495
7547
  cacheWrite: 0,
7496
7548
  },
7497
7549
  contextWindow: 131072,
@@ -7528,7 +7580,7 @@ export const MODELS = {
7528
7580
  cacheRead: 0,
7529
7581
  cacheWrite: 0,
7530
7582
  },
7531
- contextWindow: 131042,
7583
+ contextWindow: 131072,
7532
7584
  maxTokens: 16384,
7533
7585
  },
7534
7586
  },
@@ -7641,6 +7693,24 @@ export const MODELS = {
7641
7693
  contextWindow: 524288,
7642
7694
  maxTokens: 512000,
7643
7695
  },
7696
+ "MiniMaxAI/MiniMax-M3.1-Flash": {
7697
+ id: "MiniMaxAI/MiniMax-M3.1-Flash",
7698
+ name: "MiniMax-M3.1-Flash",
7699
+ api: "openai-completions",
7700
+ provider: "huggingface",
7701
+ baseUrl: "https://router.huggingface.co/v1",
7702
+ compat: { "supportsDeveloperRole": false },
7703
+ reasoning: true,
7704
+ input: ["text", "image"],
7705
+ cost: {
7706
+ input: 0.15,
7707
+ output: 0.6,
7708
+ cacheRead: 0,
7709
+ cacheWrite: 0,
7710
+ },
7711
+ contextWindow: 1000000,
7712
+ maxTokens: 512000,
7713
+ },
7644
7714
  "Qwen/Qwen2.5-Coder-32B-Instruct": {
7645
7715
  id: "Qwen/Qwen2.5-Coder-32B-Instruct",
7646
7716
  name: "Qwen2.5-Coder-32B-Instruct",
@@ -7711,7 +7781,7 @@ export const MODELS = {
7711
7781
  cacheWrite: 0,
7712
7782
  },
7713
7783
  contextWindow: 262144,
7714
- maxTokens: 131072,
7784
+ maxTokens: 81920,
7715
7785
  },
7716
7786
  "Qwen/Qwen3-30B-A3B": {
7717
7787
  id: "Qwen/Qwen3-30B-A3B",
@@ -7749,6 +7819,24 @@ export const MODELS = {
7749
7819
  contextWindow: 131072,
7750
7820
  maxTokens: 16384,
7751
7821
  },
7822
+ "Qwen/Qwen3-8B": {
7823
+ id: "Qwen/Qwen3-8B",
7824
+ name: "Qwen3 8B",
7825
+ api: "openai-completions",
7826
+ provider: "huggingface",
7827
+ baseUrl: "https://router.huggingface.co/v1",
7828
+ compat: { "supportsDeveloperRole": false },
7829
+ reasoning: true,
7830
+ input: ["text"],
7831
+ cost: {
7832
+ input: 0.07,
7833
+ output: 0.18,
7834
+ cacheRead: 0,
7835
+ cacheWrite: 0,
7836
+ },
7837
+ contextWindow: 40960,
7838
+ maxTokens: 32768,
7839
+ },
7752
7840
  "Qwen/Qwen3-Coder-30B-A3B-Instruct": {
7753
7841
  id: "Qwen/Qwen3-Coder-30B-A3B-Instruct",
7754
7842
  name: "Qwen3-Coder 30B-A3B Instruct",
@@ -7783,7 +7871,7 @@ export const MODELS = {
7783
7871
  cacheWrite: 0,
7784
7872
  },
7785
7873
  contextWindow: 262144,
7786
- maxTokens: 66536,
7874
+ maxTokens: 65536,
7787
7875
  },
7788
7876
  "Qwen/Qwen3-Coder-Next": {
7789
7877
  id: "Qwen/Qwen3-Coder-Next",
@@ -7819,25 +7907,7 @@ export const MODELS = {
7819
7907
  cacheWrite: 0,
7820
7908
  },
7821
7909
  contextWindow: 262144,
7822
- maxTokens: 66536,
7823
- },
7824
- "Qwen/Qwen3-Next-80B-A3B-Thinking": {
7825
- id: "Qwen/Qwen3-Next-80B-A3B-Thinking",
7826
- name: "Qwen3-Next-80B-A3B-Thinking",
7827
- api: "openai-completions",
7828
- provider: "huggingface",
7829
- baseUrl: "https://router.huggingface.co/v1",
7830
- compat: { "supportsDeveloperRole": false },
7831
- reasoning: false,
7832
- input: ["text"],
7833
- cost: {
7834
- input: 0.3,
7835
- output: 2,
7836
- cacheRead: 0,
7837
- cacheWrite: 0,
7838
- },
7839
- contextWindow: 262144,
7840
- maxTokens: 131072,
7910
+ maxTokens: 32768,
7841
7911
  },
7842
7912
  "Qwen/Qwen3-VL-235B-A22B-Instruct": {
7843
7913
  id: "Qwen/Qwen3-VL-235B-A22B-Instruct",
@@ -8125,7 +8195,7 @@ export const MODELS = {
8125
8195
  cacheWrite: 0,
8126
8196
  },
8127
8197
  contextWindow: 163840,
8128
- maxTokens: 163840,
8198
+ maxTokens: 32768,
8129
8199
  },
8130
8200
  "deepseek-ai/DeepSeek-V3": {
8131
8201
  id: "deepseek-ai/DeepSeek-V3",
@@ -8307,18 +8377,36 @@ export const MODELS = {
8307
8377
  contextWindow: 1048576,
8308
8378
  maxTokens: 384000,
8309
8379
  },
8310
- "google/gemma-3-12b-it": {
8311
- id: "google/gemma-3-12b-it",
8312
- name: "Gemma 3 12B IT",
8380
+ "deepseek-ai/DeepSeek-V4.1-Flash-1017": {
8381
+ id: "deepseek-ai/DeepSeek-V4.1-Flash-1017",
8382
+ name: "DeepSeek V4.1 Flash 1017",
8313
8383
  api: "openai-completions",
8314
8384
  provider: "huggingface",
8315
8385
  baseUrl: "https://router.huggingface.co/v1",
8316
8386
  compat: { "supportsDeveloperRole": false },
8317
- reasoning: false,
8387
+ reasoning: true,
8318
8388
  input: ["text", "image"],
8319
8389
  cost: {
8320
- input: 0.05,
8321
- output: 0.15,
8390
+ input: 0.3,
8391
+ output: 1.2,
8392
+ cacheRead: 0,
8393
+ cacheWrite: 0,
8394
+ },
8395
+ contextWindow: 1048576,
8396
+ maxTokens: 384000,
8397
+ },
8398
+ "google/gemma-3-12b-it": {
8399
+ id: "google/gemma-3-12b-it",
8400
+ name: "Gemma 3 12B IT",
8401
+ api: "openai-completions",
8402
+ provider: "huggingface",
8403
+ baseUrl: "https://router.huggingface.co/v1",
8404
+ compat: { "supportsDeveloperRole": false },
8405
+ reasoning: false,
8406
+ input: ["text", "image"],
8407
+ cost: {
8408
+ input: 0.05,
8409
+ output: 0.15,
8322
8410
  cacheRead: 0,
8323
8411
  cacheWrite: 0,
8324
8412
  },
@@ -8703,24 +8791,6 @@ export const MODELS = {
8703
8791
  contextWindow: 524288,
8704
8792
  maxTokens: 1048576,
8705
8793
  },
8706
- "zai-org/GLM-4.5": {
8707
- id: "zai-org/GLM-4.5",
8708
- name: "GLM-4.5",
8709
- api: "openai-completions",
8710
- provider: "huggingface",
8711
- baseUrl: "https://router.huggingface.co/v1",
8712
- compat: { "supportsDeveloperRole": false },
8713
- reasoning: true,
8714
- input: ["text"],
8715
- cost: {
8716
- input: 0.6,
8717
- output: 2.2,
8718
- cacheRead: 0,
8719
- cacheWrite: 0,
8720
- },
8721
- contextWindow: 131072,
8722
- maxTokens: 98304,
8723
- },
8724
8794
  "zai-org/GLM-4.5-Air": {
8725
8795
  id: "zai-org/GLM-4.5-Air",
8726
8796
  name: "GLM-4.5-Air",
@@ -8957,9 +9027,45 @@ export const MODELS = {
8957
9027
  contextWindow: 262144,
8958
9028
  maxTokens: 131072,
8959
9029
  },
9030
+ "k3.1-pro": {
9031
+ id: "k3.1-pro",
9032
+ name: "Kimi K3.1 Pro",
9033
+ api: "anthropic-messages",
9034
+ provider: "kimi-coding",
9035
+ baseUrl: "https://api.kimi.com/coding",
9036
+ headers: { "User-Agent": "KimiCLI/1.5" },
9037
+ reasoning: true,
9038
+ input: ["text", "image"],
9039
+ cost: {
9040
+ input: 0,
9041
+ output: 0,
9042
+ cacheRead: 0,
9043
+ cacheWrite: 0,
9044
+ },
9045
+ contextWindow: 1048576,
9046
+ maxTokens: 131072,
9047
+ },
9048
+ "k3.1-pro-highspeed": {
9049
+ id: "k3.1-pro-highspeed",
9050
+ name: "Kimi K3.1 Pro Highspeed",
9051
+ api: "anthropic-messages",
9052
+ provider: "kimi-coding",
9053
+ baseUrl: "https://api.kimi.com/coding",
9054
+ headers: { "User-Agent": "KimiCLI/1.5" },
9055
+ reasoning: true,
9056
+ input: ["text", "image"],
9057
+ cost: {
9058
+ input: 0,
9059
+ output: 0,
9060
+ cacheRead: 0,
9061
+ cacheWrite: 0,
9062
+ },
9063
+ contextWindow: 1048576,
9064
+ maxTokens: 131072,
9065
+ },
8960
9066
  "kimi-for-coding": {
8961
9067
  id: "kimi-for-coding",
8962
- name: "kimi-for-coding",
9068
+ name: "Kimi K2.8 Preview",
8963
9069
  api: "anthropic-messages",
8964
9070
  provider: "kimi-coding",
8965
9071
  baseUrl: "https://api.kimi.com/coding",
@@ -9044,7 +9150,7 @@ export const MODELS = {
9044
9150
  cacheWrite: 0,
9045
9151
  },
9046
9152
  contextWindow: 1000000,
9047
- maxTokens: 512000,
9153
+ maxTokens: 524288,
9048
9154
  },
9049
9155
  },
9050
9156
  "minimax-cn": {
@@ -9057,10 +9163,10 @@ export const MODELS = {
9057
9163
  reasoning: true,
9058
9164
  input: ["text"],
9059
9165
  cost: {
9060
- input: 0.3,
9061
- output: 1.2,
9062
- cacheRead: 0.06,
9063
- cacheWrite: 0.375,
9166
+ input: 0.3137,
9167
+ output: 1.2549,
9168
+ cacheRead: 0.0627,
9169
+ cacheWrite: 0.3922,
9064
9170
  },
9065
9171
  contextWindow: 204800,
9066
9172
  maxTokens: 131072,
@@ -9074,10 +9180,10 @@ export const MODELS = {
9074
9180
  reasoning: true,
9075
9181
  input: ["text"],
9076
9182
  cost: {
9077
- input: 0.6,
9078
- output: 2.4,
9079
- cacheRead: 0.06,
9080
- cacheWrite: 0.375,
9183
+ input: 0.6275,
9184
+ output: 2.5098,
9185
+ cacheRead: 0.0627,
9186
+ cacheWrite: 0.3922,
9081
9187
  },
9082
9188
  contextWindow: 204800,
9083
9189
  maxTokens: 131072,
@@ -9091,13 +9197,13 @@ export const MODELS = {
9091
9197
  reasoning: true,
9092
9198
  input: ["text", "image"],
9093
9199
  cost: {
9094
- input: 0.3,
9095
- output: 1.2,
9096
- cacheRead: 0.06,
9200
+ input: 0.3137,
9201
+ output: 1.2549,
9202
+ cacheRead: 0.0627,
9097
9203
  cacheWrite: 0,
9098
9204
  },
9099
9205
  contextWindow: 1000000,
9100
- maxTokens: 512000,
9206
+ maxTokens: 524288,
9101
9207
  },
9102
9208
  },
9103
9209
  "mistral": {
@@ -9135,25 +9241,25 @@ export const MODELS = {
9135
9241
  contextWindow: 256000,
9136
9242
  maxTokens: 4096,
9137
9243
  },
9138
- "devstral-2512": {
9139
- id: "devstral-2512",
9140
- name: "Devstral 2",
9244
+ "deepseek-v4-1-flash-1017": {
9245
+ id: "deepseek-v4-1-flash-1017",
9246
+ name: "DeepSeek V4.1 Flash 1017",
9141
9247
  api: "mistral-conversations",
9142
9248
  provider: "mistral",
9143
9249
  baseUrl: "https://api.mistral.ai",
9144
- reasoning: false,
9250
+ reasoning: true,
9145
9251
  input: ["text"],
9146
9252
  cost: {
9147
- input: 0.4,
9148
- output: 2,
9149
- cacheRead: 0,
9253
+ input: 0.3,
9254
+ output: 1.2,
9255
+ cacheRead: 0.007,
9150
9256
  cacheWrite: 0,
9151
9257
  },
9152
- contextWindow: 262144,
9153
- maxTokens: 262144,
9258
+ contextWindow: 1048576,
9259
+ maxTokens: 128000,
9154
9260
  },
9155
- "devstral-latest": {
9156
- id: "devstral-latest",
9261
+ "devstral-2512": {
9262
+ id: "devstral-2512",
9157
9263
  name: "Devstral 2",
9158
9264
  api: "mistral-conversations",
9159
9265
  provider: "mistral",
@@ -9169,9 +9275,9 @@ export const MODELS = {
9169
9275
  contextWindow: 262144,
9170
9276
  maxTokens: 262144,
9171
9277
  },
9172
- "devstral-medium-2507": {
9173
- id: "devstral-medium-2507",
9174
- name: "Devstral Medium",
9278
+ "devstral-latest": {
9279
+ id: "devstral-latest",
9280
+ name: "Devstral 2",
9175
9281
  api: "mistral-conversations",
9176
9282
  provider: "mistral",
9177
9283
  baseUrl: "https://api.mistral.ai",
@@ -9183,8 +9289,8 @@ export const MODELS = {
9183
9289
  cacheRead: 0,
9184
9290
  cacheWrite: 0,
9185
9291
  },
9186
- contextWindow: 128000,
9187
- maxTokens: 128000,
9292
+ contextWindow: 262144,
9293
+ maxTokens: 262144,
9188
9294
  },
9189
9295
  "devstral-medium-latest": {
9190
9296
  id: "devstral-medium-latest",
@@ -9203,40 +9309,6 @@ export const MODELS = {
9203
9309
  contextWindow: 262144,
9204
9310
  maxTokens: 262144,
9205
9311
  },
9206
- "devstral-small-2505": {
9207
- id: "devstral-small-2505",
9208
- name: "Devstral Small 2505",
9209
- api: "mistral-conversations",
9210
- provider: "mistral",
9211
- baseUrl: "https://api.mistral.ai",
9212
- reasoning: false,
9213
- input: ["text"],
9214
- cost: {
9215
- input: 0.1,
9216
- output: 0.3,
9217
- cacheRead: 0,
9218
- cacheWrite: 0,
9219
- },
9220
- contextWindow: 128000,
9221
- maxTokens: 128000,
9222
- },
9223
- "devstral-small-2507": {
9224
- id: "devstral-small-2507",
9225
- name: "Devstral Small",
9226
- api: "mistral-conversations",
9227
- provider: "mistral",
9228
- baseUrl: "https://api.mistral.ai",
9229
- reasoning: false,
9230
- input: ["text"],
9231
- cost: {
9232
- input: 0.1,
9233
- output: 0.3,
9234
- cacheRead: 0,
9235
- cacheWrite: 0,
9236
- },
9237
- contextWindow: 128000,
9238
- maxTokens: 128000,
9239
- },
9240
9312
  "glm-5-2": {
9241
9313
  id: "glm-5-2",
9242
9314
  name: "GLM-5.2",
@@ -9348,9 +9420,9 @@ export const MODELS = {
9348
9420
  reasoning: false,
9349
9421
  input: ["text", "image"],
9350
9422
  cost: {
9351
- input: 0.04,
9352
- output: 0.04,
9353
- cacheRead: 0,
9423
+ input: 0.1,
9424
+ output: 0.1,
9425
+ cacheRead: 0.01,
9354
9426
  cacheWrite: 0,
9355
9427
  },
9356
9428
  contextWindow: 131072,
@@ -9382,31 +9454,14 @@ export const MODELS = {
9382
9454
  reasoning: false,
9383
9455
  input: ["text", "image"],
9384
9456
  cost: {
9385
- input: 0.1,
9386
- output: 0.1,
9387
- cacheRead: 0,
9457
+ input: 0.15,
9458
+ output: 0.15,
9459
+ cacheRead: 0.015,
9388
9460
  cacheWrite: 0,
9389
9461
  },
9390
9462
  contextWindow: 262144,
9391
9463
  maxTokens: 128000,
9392
9464
  },
9393
- "mistral-large-2411": {
9394
- id: "mistral-large-2411",
9395
- name: "Mistral Large 2.1",
9396
- api: "mistral-conversations",
9397
- provider: "mistral",
9398
- baseUrl: "https://api.mistral.ai",
9399
- reasoning: false,
9400
- input: ["text"],
9401
- cost: {
9402
- input: 2,
9403
- output: 6,
9404
- cacheRead: 0,
9405
- cacheWrite: 0,
9406
- },
9407
- contextWindow: 131072,
9408
- maxTokens: 16384,
9409
- },
9410
9465
  "mistral-large-2512": {
9411
9466
  id: "mistral-large-2512",
9412
9467
  name: "Mistral Large 3",
@@ -9433,8 +9488,25 @@ export const MODELS = {
9433
9488
  reasoning: true,
9434
9489
  input: ["text", "image"],
9435
9490
  cost: {
9436
- input: 0.68,
9437
- output: 2.09,
9491
+ input: 0.7,
9492
+ output: 2.1,
9493
+ cacheRead: 0.07,
9494
+ cacheWrite: 0,
9495
+ },
9496
+ contextWindow: 1048576,
9497
+ maxTokens: 262144,
9498
+ },
9499
+ "mistral-large-4-0-8": {
9500
+ id: "mistral-large-4-0-8",
9501
+ name: "Mistral Large 4.0.8",
9502
+ api: "mistral-conversations",
9503
+ provider: "mistral",
9504
+ baseUrl: "https://api.mistral.ai",
9505
+ reasoning: true,
9506
+ input: ["text", "image"],
9507
+ cost: {
9508
+ input: 0.7,
9509
+ output: 2.1,
9438
9510
  cacheRead: 0.07,
9439
9511
  cacheWrite: 0,
9440
9512
  },
@@ -9543,23 +9615,6 @@ export const MODELS = {
9543
9615
  contextWindow: 262144,
9544
9616
  maxTokens: 262144,
9545
9617
  },
9546
- "mistral-nemo": {
9547
- id: "mistral-nemo",
9548
- name: "Mistral Nemo",
9549
- api: "mistral-conversations",
9550
- provider: "mistral",
9551
- baseUrl: "https://api.mistral.ai",
9552
- reasoning: false,
9553
- input: ["text"],
9554
- cost: {
9555
- input: 0.15,
9556
- output: 0.15,
9557
- cacheRead: 0,
9558
- cacheWrite: 0,
9559
- },
9560
- contextWindow: 128000,
9561
- maxTokens: 128000,
9562
- },
9563
9618
  "mistral-small-2506": {
9564
9619
  id: "mistral-small-2506",
9565
9620
  name: "Mistral Small 3.2",
@@ -9611,23 +9666,6 @@ export const MODELS = {
9611
9666
  contextWindow: 262144,
9612
9667
  maxTokens: 256000,
9613
9668
  },
9614
- "open-mistral-7b": {
9615
- id: "open-mistral-7b",
9616
- name: "Mistral 7B",
9617
- api: "mistral-conversations",
9618
- provider: "mistral",
9619
- baseUrl: "https://api.mistral.ai",
9620
- reasoning: false,
9621
- input: ["text"],
9622
- cost: {
9623
- input: 0.25,
9624
- output: 0.25,
9625
- cacheRead: 0,
9626
- cacheWrite: 0,
9627
- },
9628
- contextWindow: 8000,
9629
- maxTokens: 8000,
9630
- },
9631
9669
  "open-mistral-nemo": {
9632
9670
  id: "open-mistral-nemo",
9633
9671
  name: "Open Mistral Nemo",
@@ -9645,40 +9683,6 @@ export const MODELS = {
9645
9683
  contextWindow: 128000,
9646
9684
  maxTokens: 128000,
9647
9685
  },
9648
- "open-mixtral-8x22b": {
9649
- id: "open-mixtral-8x22b",
9650
- name: "Mixtral 8x22B",
9651
- api: "mistral-conversations",
9652
- provider: "mistral",
9653
- baseUrl: "https://api.mistral.ai",
9654
- reasoning: false,
9655
- input: ["text"],
9656
- cost: {
9657
- input: 2,
9658
- output: 6,
9659
- cacheRead: 0,
9660
- cacheWrite: 0,
9661
- },
9662
- contextWindow: 64000,
9663
- maxTokens: 64000,
9664
- },
9665
- "open-mixtral-8x7b": {
9666
- id: "open-mixtral-8x7b",
9667
- name: "Mixtral 8x7B",
9668
- api: "mistral-conversations",
9669
- provider: "mistral",
9670
- baseUrl: "https://api.mistral.ai",
9671
- reasoning: false,
9672
- input: ["text"],
9673
- cost: {
9674
- input: 0.7,
9675
- output: 0.7,
9676
- cacheRead: 0,
9677
- cacheWrite: 0,
9678
- },
9679
- contextWindow: 32000,
9680
- maxTokens: 32000,
9681
- },
9682
9686
  "pixtral-12b": {
9683
9687
  id: "pixtral-12b",
9684
9688
  name: "Pixtral 12B",
@@ -9696,23 +9700,6 @@ export const MODELS = {
9696
9700
  contextWindow: 128000,
9697
9701
  maxTokens: 128000,
9698
9702
  },
9699
- "pixtral-large-latest": {
9700
- id: "pixtral-large-latest",
9701
- name: "Pixtral Large (latest)",
9702
- api: "mistral-conversations",
9703
- provider: "mistral",
9704
- baseUrl: "https://api.mistral.ai",
9705
- reasoning: false,
9706
- input: ["text", "image"],
9707
- cost: {
9708
- input: 2,
9709
- output: 6,
9710
- cacheRead: 0,
9711
- cacheWrite: 0,
9712
- },
9713
- contextWindow: 128000,
9714
- maxTokens: 128000,
9715
- },
9716
9703
  "voxtral-small-2507": {
9717
9704
  id: "voxtral-small-2507",
9718
9705
  name: "Voxtral Small",
@@ -9740,7 +9727,7 @@ export const MODELS = {
9740
9727
  input: ["text"],
9741
9728
  cost: {
9742
9729
  input: 0.1,
9743
- output: 0.3,
9730
+ output: 0.4,
9744
9731
  cacheRead: 0,
9745
9732
  cacheWrite: 0,
9746
9733
  },
@@ -9781,6 +9768,23 @@ export const MODELS = {
9781
9768
  contextWindow: 1048576,
9782
9769
  maxTokens: 131072,
9783
9770
  },
9771
+ "zai-glm-5-3-flash": {
9772
+ id: "zai-glm-5-3-flash",
9773
+ name: "GLM-5.3-Flash",
9774
+ api: "mistral-conversations",
9775
+ provider: "mistral",
9776
+ baseUrl: "https://api.mistral.ai",
9777
+ reasoning: true,
9778
+ input: ["text", "image"],
9779
+ cost: {
9780
+ input: 0.15,
9781
+ output: 0.5,
9782
+ cacheRead: 0.03,
9783
+ cacheWrite: 0,
9784
+ },
9785
+ contextWindow: 1048576,
9786
+ maxTokens: 131072,
9787
+ },
9784
9788
  },
9785
9789
  "moonshotai": {
9786
9790
  "kimi-k2.6": {
@@ -9855,6 +9859,42 @@ export const MODELS = {
9855
9859
  contextWindow: 1048576,
9856
9860
  maxTokens: 1048576,
9857
9861
  },
9862
+ "kimi-k3.1-pro": {
9863
+ id: "kimi-k3.1-pro",
9864
+ name: "Kimi K3.1 Pro",
9865
+ api: "openai-completions",
9866
+ provider: "moonshotai",
9867
+ baseUrl: "https://api.moonshot.ai/v1",
9868
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
9869
+ reasoning: true,
9870
+ input: ["text", "image"],
9871
+ cost: {
9872
+ input: 2,
9873
+ output: 10,
9874
+ cacheRead: 0.2,
9875
+ cacheWrite: 2,
9876
+ },
9877
+ contextWindow: 1048576,
9878
+ maxTokens: 1048576,
9879
+ },
9880
+ "kimi-k3.1-pro-highspeed": {
9881
+ id: "kimi-k3.1-pro-highspeed",
9882
+ name: "Kimi K3.1 Pro Highspeed",
9883
+ api: "openai-completions",
9884
+ provider: "moonshotai",
9885
+ baseUrl: "https://api.moonshot.ai/v1",
9886
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
9887
+ reasoning: true,
9888
+ input: ["text", "image"],
9889
+ cost: {
9890
+ input: 4,
9891
+ output: 20,
9892
+ cacheRead: 0.2,
9893
+ cacheWrite: 4,
9894
+ },
9895
+ contextWindow: 1048576,
9896
+ maxTokens: 1048576,
9897
+ },
9858
9898
  },
9859
9899
  "moonshotai-cn": {
9860
9900
  "kimi-k2.6": {
@@ -9867,9 +9907,9 @@ export const MODELS = {
9867
9907
  reasoning: true,
9868
9908
  input: ["text", "image"],
9869
9909
  cost: {
9870
- input: 0.95,
9871
- output: 4,
9872
- cacheRead: 0.16,
9910
+ input: 0.9711,
9911
+ output: 4.0337,
9912
+ cacheRead: 0.1643,
9873
9913
  cacheWrite: 0,
9874
9914
  },
9875
9915
  contextWindow: 262144,
@@ -9885,9 +9925,9 @@ export const MODELS = {
9885
9925
  reasoning: true,
9886
9926
  input: ["text", "image"],
9887
9927
  cost: {
9888
- input: 0.95,
9889
- output: 4,
9890
- cacheRead: 0.19,
9928
+ input: 0.9711,
9929
+ output: 4.0337,
9930
+ cacheRead: 0.1942,
9891
9931
  cacheWrite: 0,
9892
9932
  },
9893
9933
  contextWindow: 262144,
@@ -9903,9 +9943,9 @@ export const MODELS = {
9903
9943
  reasoning: true,
9904
9944
  input: ["text", "image"],
9905
9945
  cost: {
9906
- input: 1.9,
9907
- output: 8,
9908
- cacheRead: 0.38,
9946
+ input: 1.9421,
9947
+ output: 8.0673,
9948
+ cacheRead: 0.3884,
9909
9949
  cacheWrite: 0,
9910
9950
  },
9911
9951
  contextWindow: 262144,
@@ -9921,10 +9961,46 @@ export const MODELS = {
9921
9961
  reasoning: true,
9922
9962
  input: ["text", "image"],
9923
9963
  cost: {
9924
- input: 3,
9925
- output: 15,
9926
- cacheRead: 0.3,
9927
- cacheWrite: 3,
9964
+ input: 2.9879,
9965
+ output: 14.9395,
9966
+ cacheRead: 0.2988,
9967
+ cacheWrite: 2.9879,
9968
+ },
9969
+ contextWindow: 1048576,
9970
+ maxTokens: 1048576,
9971
+ },
9972
+ "kimi-k3.1-pro": {
9973
+ id: "kimi-k3.1-pro",
9974
+ name: "Kimi K3.1 Pro",
9975
+ api: "openai-completions",
9976
+ provider: "moonshotai-cn",
9977
+ baseUrl: "https://api.moonshot.cn/v1",
9978
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
9979
+ reasoning: true,
9980
+ input: ["text", "image"],
9981
+ cost: {
9982
+ input: 1.9437,
9983
+ output: 10.1671,
9984
+ cacheRead: 0.1944,
9985
+ cacheWrite: 1.9437,
9986
+ },
9987
+ contextWindow: 1048576,
9988
+ maxTokens: 1048576,
9989
+ },
9990
+ "kimi-k3.1-pro-highspeed": {
9991
+ id: "kimi-k3.1-pro-highspeed",
9992
+ name: "Kimi K3.1 Pro Highspeed",
9993
+ api: "openai-completions",
9994
+ provider: "moonshotai-cn",
9995
+ baseUrl: "https://api.moonshot.cn/v1",
9996
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
9997
+ reasoning: true,
9998
+ input: ["text", "image"],
9999
+ cost: {
10000
+ input: 3.8874,
10001
+ output: 20.3342,
10002
+ cacheRead: 0.1944,
10003
+ cacheWrite: 3.8874,
9928
10004
  },
9929
10005
  contextWindow: 1048576,
9930
10006
  maxTokens: 1048576,
@@ -10195,24 +10271,6 @@ export const MODELS = {
10195
10271
  contextWindow: 400000,
10196
10272
  maxTokens: 128000,
10197
10273
  },
10198
- "gpt-5.2-chat-latest": {
10199
- id: "gpt-5.2-chat-latest",
10200
- name: "GPT-5.2 Chat",
10201
- api: "openai-responses",
10202
- provider: "openai",
10203
- baseUrl: "https://api.openai.com/v1",
10204
- reasoning: true,
10205
- thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
10206
- input: ["text", "image"],
10207
- cost: {
10208
- input: 1.75,
10209
- output: 14,
10210
- cacheRead: 0.175,
10211
- cacheWrite: 0,
10212
- },
10213
- contextWindow: 128000,
10214
- maxTokens: 16384,
10215
- },
10216
10274
  "gpt-5.2-pro": {
10217
10275
  id: "gpt-5.2-pro",
10218
10276
  name: "GPT-5.2 Pro",
@@ -10231,24 +10289,6 @@ export const MODELS = {
10231
10289
  contextWindow: 400000,
10232
10290
  maxTokens: 128000,
10233
10291
  },
10234
- "gpt-5.3-chat-latest": {
10235
- id: "gpt-5.3-chat-latest",
10236
- name: "GPT-5.3 Chat (latest)",
10237
- api: "openai-responses",
10238
- provider: "openai",
10239
- baseUrl: "https://api.openai.com/v1",
10240
- reasoning: false,
10241
- thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
10242
- input: ["text", "image"],
10243
- cost: {
10244
- input: 1.75,
10245
- output: 14,
10246
- cacheRead: 0.175,
10247
- cacheWrite: 0,
10248
- },
10249
- contextWindow: 128000,
10250
- maxTokens: 16384,
10251
- },
10252
10292
  "gpt-5.3-codex": {
10253
10293
  id: "gpt-5.3-codex",
10254
10294
  name: "GPT-5.3 Codex",
@@ -10533,6 +10573,23 @@ export const MODELS = {
10533
10573
  contextWindow: 1050000,
10534
10574
  maxTokens: 128000,
10535
10575
  },
10576
+ "gpt-6.1-terra": {
10577
+ id: "gpt-6.1-terra",
10578
+ name: "GPT-6.1 Terra",
10579
+ api: "openai-responses",
10580
+ provider: "openai",
10581
+ baseUrl: "https://api.openai.com/v1",
10582
+ reasoning: true,
10583
+ input: ["text", "image"],
10584
+ cost: {
10585
+ input: 1,
10586
+ output: 5,
10587
+ cacheRead: 0.05,
10588
+ cacheWrite: 1.25,
10589
+ },
10590
+ contextWindow: 1050000,
10591
+ maxTokens: 128000,
10592
+ },
10536
10593
  "gpt-daybreak-blue-latest": {
10537
10594
  id: "gpt-daybreak-blue-latest",
10538
10595
  name: "Daybreak Blue",
@@ -10868,9 +10925,9 @@ export const MODELS = {
10868
10925
  },
10869
10926
  },
10870
10927
  "opencode": {
10871
- "big-pickle": {
10872
- id: "big-pickle",
10873
- name: "Big Pickle",
10928
+ "beam-free": {
10929
+ id: "beam-free",
10930
+ name: "Beam Free",
10874
10931
  api: "openai-completions",
10875
10932
  provider: "opencode",
10876
10933
  baseUrl: "https://opencode.ai/zen/v1",
@@ -10882,12 +10939,12 @@ export const MODELS = {
10882
10939
  cacheRead: 0,
10883
10940
  cacheWrite: 0,
10884
10941
  },
10885
- contextWindow: 200000,
10886
- maxTokens: 32000,
10942
+ contextWindow: 1048576,
10943
+ maxTokens: 131072,
10887
10944
  },
10888
- "cat-jam-free": {
10889
- id: "cat-jam-free",
10890
- name: "Cat Jam Free",
10945
+ "big-pickle": {
10946
+ id: "big-pickle",
10947
+ name: "Big Pickle",
10891
10948
  api: "openai-completions",
10892
10949
  provider: "opencode",
10893
10950
  baseUrl: "https://opencode.ai/zen/v1",
@@ -10899,8 +10956,8 @@ export const MODELS = {
10899
10956
  cacheRead: 0,
10900
10957
  cacheWrite: 0,
10901
10958
  },
10902
- contextWindow: 262144,
10903
- maxTokens: 131072,
10959
+ contextWindow: 200000,
10960
+ maxTokens: 32000,
10904
10961
  },
10905
10962
  "claude-fable-5": {
10906
10963
  id: "claude-fable-5",
@@ -11077,23 +11134,6 @@ export const MODELS = {
11077
11134
  contextWindow: 1000000,
11078
11135
  maxTokens: 128000,
11079
11136
  },
11080
- "claude-sonnet-4": {
11081
- id: "claude-sonnet-4",
11082
- name: "Claude Sonnet 4",
11083
- api: "anthropic-messages",
11084
- provider: "opencode",
11085
- baseUrl: "https://opencode.ai/zen",
11086
- reasoning: true,
11087
- input: ["text", "image"],
11088
- cost: {
11089
- input: 3,
11090
- output: 15,
11091
- cacheRead: 0.3,
11092
- cacheWrite: 3.75,
11093
- },
11094
- contextWindow: 200000,
11095
- maxTokens: 64000,
11096
- },
11097
11137
  "claude-sonnet-4-5": {
11098
11138
  id: "claude-sonnet-4-5",
11099
11139
  name: "Claude Sonnet 4.5",
@@ -11162,44 +11202,6 @@ export const MODELS = {
11162
11202
  contextWindow: 1000000,
11163
11203
  maxTokens: 128000,
11164
11204
  },
11165
- "deepseek-v4-flash": {
11166
- id: "deepseek-v4-flash",
11167
- name: "DeepSeek V4 Flash",
11168
- api: "openai-completions",
11169
- provider: "opencode",
11170
- baseUrl: "https://opencode.ai/zen/v1",
11171
- compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
11172
- reasoning: true,
11173
- thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
11174
- input: ["text"],
11175
- cost: {
11176
- input: 0.14,
11177
- output: 0.28,
11178
- cacheRead: 0.028,
11179
- cacheWrite: 0,
11180
- },
11181
- contextWindow: 1000000,
11182
- maxTokens: 384000,
11183
- },
11184
- "deepseek-v4-flash-vision-exp": {
11185
- id: "deepseek-v4-flash-vision-exp",
11186
- name: "DeepSeek V4 Flash Vision Exp",
11187
- api: "openai-completions",
11188
- provider: "opencode",
11189
- baseUrl: "https://opencode.ai/zen/v1",
11190
- compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
11191
- reasoning: true,
11192
- thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
11193
- input: ["text", "image"],
11194
- cost: {
11195
- input: 0.14,
11196
- output: 0.28,
11197
- cacheRead: 0.028,
11198
- cacheWrite: 0,
11199
- },
11200
- contextWindow: 1000000,
11201
- maxTokens: 384000,
11202
- },
11203
11205
  "deepseek-v4-pro": {
11204
11206
  id: "deepseek-v4-pro",
11205
11207
  name: "DeepSeek V4 Pro",
@@ -11212,7 +11214,7 @@ export const MODELS = {
11212
11214
  input: ["text"],
11213
11215
  cost: {
11214
11216
  input: 1.74,
11215
- output: 3.84,
11217
+ output: 3.48,
11216
11218
  cacheRead: 0.145,
11217
11219
  cacheWrite: 0,
11218
11220
  },
@@ -11238,13 +11240,15 @@ export const MODELS = {
11238
11240
  contextWindow: 1000000,
11239
11241
  maxTokens: 384000,
11240
11242
  },
11241
- "exo-free": {
11242
- id: "exo-free",
11243
- name: "Exo Free",
11243
+ "deepseek-v4.1-flash-free": {
11244
+ id: "deepseek-v4.1-flash-free",
11245
+ name: "DeepSeek V4.1 Flash Free",
11244
11246
  api: "openai-completions",
11245
11247
  provider: "opencode",
11246
11248
  baseUrl: "https://opencode.ai/zen/v1",
11249
+ compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
11247
11250
  reasoning: true,
11251
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
11248
11252
  input: ["text", "image"],
11249
11253
  cost: {
11250
11254
  input: 0,
@@ -11252,8 +11256,25 @@ export const MODELS = {
11252
11256
  cacheRead: 0,
11253
11257
  cacheWrite: 0,
11254
11258
  },
11255
- contextWindow: 1048576,
11256
- maxTokens: 131072,
11259
+ contextWindow: 200000,
11260
+ maxTokens: 32000,
11261
+ },
11262
+ "flint-40b-free": {
11263
+ id: "flint-40b-free",
11264
+ name: "Flint 40B Free",
11265
+ api: "openai-completions",
11266
+ provider: "opencode",
11267
+ baseUrl: "https://opencode.ai/zen/v1",
11268
+ reasoning: true,
11269
+ input: ["text"],
11270
+ cost: {
11271
+ input: 0,
11272
+ output: 0,
11273
+ cacheRead: 0,
11274
+ cacheWrite: 0,
11275
+ },
11276
+ contextWindow: 262144,
11277
+ maxTokens: 65536,
11257
11278
  },
11258
11279
  "gemini-3-flash": {
11259
11280
  id: "gemini-3-flash",
@@ -11483,6 +11504,23 @@ export const MODELS = {
11483
11504
  contextWindow: 1000000,
11484
11505
  maxTokens: 131072,
11485
11506
  },
11507
+ "glm-5.3-flash-free": {
11508
+ id: "glm-5.3-flash-free",
11509
+ name: "GLM-5.3-Flash Free",
11510
+ api: "openai-completions",
11511
+ provider: "opencode",
11512
+ baseUrl: "https://opencode.ai/zen/v1",
11513
+ reasoning: true,
11514
+ input: ["text", "image"],
11515
+ cost: {
11516
+ input: 0,
11517
+ output: 0,
11518
+ cacheRead: 0,
11519
+ cacheWrite: 0,
11520
+ },
11521
+ contextWindow: 200000,
11522
+ maxTokens: 32000,
11523
+ },
11486
11524
  "gpt-5": {
11487
11525
  id: "gpt-5",
11488
11526
  name: "GPT-5",
@@ -11817,10 +11855,10 @@ export const MODELS = {
11817
11855
  thinkingLevelMap: { "off": null },
11818
11856
  input: ["text", "image"],
11819
11857
  cost: {
11820
- input: 2.5,
11821
- output: 15,
11822
- cacheRead: 0.25,
11823
- cacheWrite: 3.125,
11858
+ input: 2,
11859
+ output: 12,
11860
+ cacheRead: 0.2,
11861
+ cacheWrite: 2.5,
11824
11862
  },
11825
11863
  contextWindow: 1050000,
11826
11864
  maxTokens: 128000,
@@ -11972,7 +12010,7 @@ export const MODELS = {
11972
12010
  cost: {
11973
12011
  input: 0.6,
11974
12012
  output: 3,
11975
- cacheRead: 0.08,
12013
+ cacheRead: 0.1,
11976
12014
  cacheWrite: 0,
11977
12015
  },
11978
12016
  contextWindow: 262144,
@@ -12020,30 +12058,13 @@ export const MODELS = {
12020
12058
  baseUrl: "https://opencode.ai/zen/v1",
12021
12059
  reasoning: true,
12022
12060
  input: ["text", "image"],
12023
- cost: {
12024
- input: 3,
12025
- output: 15,
12026
- cacheRead: 0.3,
12027
- cacheWrite: 0,
12028
- },
12029
- contextWindow: 1048576,
12030
- maxTokens: 131072,
12031
- },
12032
- "longcat-2.5-preview-free": {
12033
- id: "longcat-2.5-preview-free",
12034
- name: "LongCat 2.5 Preview Free",
12035
- api: "openai-completions",
12036
- provider: "opencode",
12037
- baseUrl: "https://opencode.ai/zen/v1",
12038
- reasoning: true,
12039
- input: ["text", "image"],
12040
- cost: {
12041
- input: 0,
12042
- output: 0,
12043
- cacheRead: 0,
12044
- cacheWrite: 0,
12061
+ cost: {
12062
+ input: 3,
12063
+ output: 15,
12064
+ cacheRead: 0.3,
12065
+ cacheWrite: 3,
12045
12066
  },
12046
- contextWindow: 1000000,
12067
+ contextWindow: 1048576,
12047
12068
  maxTokens: 131072,
12048
12069
  },
12049
12070
  "mimo-v2.6-flash-free": {
@@ -12165,26 +12186,26 @@ export const MODELS = {
12165
12186
  contextWindow: 1048576,
12166
12187
  maxTokens: 131072,
12167
12188
  },
12168
- "muse-spark-1.3-contributor-free": {
12169
- id: "muse-spark-1.3-contributor-free",
12170
- name: "Muse Spark 1.3 Free",
12189
+ "muse-wonder-1.0": {
12190
+ id: "muse-wonder-1.0",
12191
+ name: "Muse Wonder",
12171
12192
  api: "openai-responses",
12172
12193
  provider: "opencode",
12173
12194
  baseUrl: "https://opencode.ai/zen/v1",
12174
12195
  reasoning: true,
12175
12196
  input: ["text", "image"],
12176
12197
  cost: {
12177
- input: 0,
12178
- output: 0,
12179
- cacheRead: 0,
12198
+ input: 4,
12199
+ output: 20,
12200
+ cacheRead: 0.2,
12180
12201
  cacheWrite: 0,
12181
12202
  },
12182
12203
  contextWindow: 1048576,
12183
12204
  maxTokens: 131072,
12184
12205
  },
12185
- "nemotron-3-ultra-free": {
12186
- id: "nemotron-3-ultra-free",
12187
- name: "Nemotron 3 Ultra Free",
12206
+ "nemotron-3.5-lightning-free": {
12207
+ id: "nemotron-3.5-lightning-free",
12208
+ name: "Nemotron 3.5 Lightning Free",
12188
12209
  api: "openai-completions",
12189
12210
  provider: "opencode",
12190
12211
  baseUrl: "https://opencode.ai/zen/v1",
@@ -12196,25 +12217,25 @@ export const MODELS = {
12196
12217
  cacheRead: 0,
12197
12218
  cacheWrite: 0,
12198
12219
  },
12199
- contextWindow: 1000000,
12200
- maxTokens: 128000,
12220
+ contextWindow: 262144,
12221
+ maxTokens: 262144,
12201
12222
  },
12202
- "nemotron-3.5-lightning-free": {
12203
- id: "nemotron-3.5-lightning-free",
12204
- name: "Nemotron 3.5 Lightning Free",
12223
+ "nemotron-3.5-super-vl-free": {
12224
+ id: "nemotron-3.5-super-vl-free",
12225
+ name: "Nemotron 3.5 Super VL Free",
12205
12226
  api: "openai-completions",
12206
12227
  provider: "opencode",
12207
12228
  baseUrl: "https://opencode.ai/zen/v1",
12208
12229
  reasoning: true,
12209
- input: ["text"],
12230
+ input: ["text", "image"],
12210
12231
  cost: {
12211
12232
  input: 0,
12212
12233
  output: 0,
12213
12234
  cacheRead: 0,
12214
12235
  cacheWrite: 0,
12215
12236
  },
12216
- contextWindow: 262144,
12217
- maxTokens: 262144,
12237
+ contextWindow: 1048576,
12238
+ maxTokens: 131072,
12218
12239
  },
12219
12240
  "qwen3.5-plus": {
12220
12241
  id: "qwen3.5-plus",
@@ -12284,45 +12305,11 @@ export const MODELS = {
12284
12305
  contextWindow: 262144,
12285
12306
  maxTokens: 131072,
12286
12307
  },
12287
- "space-bunny-free": {
12288
- id: "space-bunny-free",
12289
- name: "Space Bunny Free",
12290
- api: "openai-completions",
12291
- provider: "opencode",
12292
- baseUrl: "https://opencode.ai/zen/v1",
12293
- reasoning: true,
12294
- input: ["text", "image"],
12295
- cost: {
12296
- input: 0,
12297
- output: 0,
12298
- cacheRead: 0,
12299
- cacheWrite: 0,
12300
- },
12301
- contextWindow: 1048576,
12302
- maxTokens: 524288,
12303
- },
12304
- "step-5-preview-free": {
12305
- id: "step-5-preview-free",
12306
- name: "Step 5 Preview Free",
12307
- api: "openai-completions",
12308
- provider: "opencode",
12309
- baseUrl: "https://opencode.ai/zen/v1",
12310
- reasoning: true,
12311
- input: ["text", "image"],
12312
- cost: {
12313
- input: 0,
12314
- output: 0,
12315
- cacheRead: 0,
12316
- cacheWrite: 0,
12317
- },
12318
- contextWindow: 1000000,
12319
- maxTokens: 65536,
12320
- },
12321
12308
  },
12322
12309
  "opencode-go": {
12323
- "cat-jam-free": {
12324
- id: "cat-jam-free",
12325
- name: "Cat Jam Free",
12310
+ "beam-free": {
12311
+ id: "beam-free",
12312
+ name: "Beam Free",
12326
12313
  api: "openai-completions",
12327
12314
  provider: "opencode-go",
12328
12315
  baseUrl: "https://opencode.ai/zen/go/v1",
@@ -12334,7 +12321,7 @@ export const MODELS = {
12334
12321
  cacheRead: 0,
12335
12322
  cacheWrite: 0,
12336
12323
  },
12337
- contextWindow: 262144,
12324
+ contextWindow: 1048576,
12338
12325
  maxTokens: 131072,
12339
12326
  },
12340
12327
  "claude-haiku-5-5": {
@@ -12392,18 +12379,18 @@ export const MODELS = {
12392
12379
  contextWindow: 1000000,
12393
12380
  maxTokens: 384000,
12394
12381
  },
12395
- "gemini-4-argon-contributor": {
12396
- id: "gemini-4-argon-contributor",
12397
- name: "Gemini 4 Argon Contributor",
12382
+ "gemini-4-argon": {
12383
+ id: "gemini-4-argon",
12384
+ name: "Gemini 4 Argon",
12398
12385
  api: "google-generative-ai",
12399
12386
  provider: "opencode-go",
12400
12387
  baseUrl: "https://opencode.ai/zen/go/v1",
12401
12388
  reasoning: true,
12402
12389
  input: ["text", "image"],
12403
12390
  cost: {
12404
- input: 4,
12405
- output: 20,
12406
- cacheRead: 0.2,
12391
+ input: 2,
12392
+ output: 10,
12393
+ cacheRead: 0.1,
12407
12394
  cacheWrite: 0,
12408
12395
  },
12409
12396
  contextWindow: 1048576,
@@ -12495,23 +12482,6 @@ export const MODELS = {
12495
12482
  contextWindow: 1050000,
12496
12483
  maxTokens: 128000,
12497
12484
  },
12498
- "grok-4.6": {
12499
- id: "grok-4.6",
12500
- name: "Grok 4.6",
12501
- api: "openai-responses",
12502
- provider: "opencode-go",
12503
- baseUrl: "https://opencode.ai/zen/go/v1",
12504
- reasoning: true,
12505
- input: ["text", "image"],
12506
- cost: {
12507
- input: 2,
12508
- output: 6,
12509
- cacheRead: 0.5,
12510
- cacheWrite: 0,
12511
- },
12512
- contextWindow: 500000,
12513
- maxTokens: 500000,
12514
- },
12515
12485
  "grok-4.7": {
12516
12486
  id: "grok-4.7",
12517
12487
  name: "Grok 4.7",
@@ -12563,6 +12533,23 @@ export const MODELS = {
12563
12533
  contextWindow: 1024000,
12564
12534
  maxTokens: 64000,
12565
12535
  },
12536
+ "iceman-contributor-free": {
12537
+ id: "iceman-contributor-free",
12538
+ name: "Iceman Contributor Free",
12539
+ api: "openai-completions",
12540
+ provider: "opencode-go",
12541
+ baseUrl: "https://opencode.ai/zen/go/v1",
12542
+ reasoning: true,
12543
+ input: ["text"],
12544
+ cost: {
12545
+ input: 0,
12546
+ output: 0,
12547
+ cacheRead: 0,
12548
+ cacheWrite: 0,
12549
+ },
12550
+ contextWindow: 262144,
12551
+ maxTokens: 131072,
12552
+ },
12566
12553
  "kimi-k2.7-code": {
12567
12554
  id: "kimi-k2.7-code",
12568
12555
  name: "Kimi K2.7 Code",
@@ -12592,40 +12579,40 @@ export const MODELS = {
12592
12579
  input: 3,
12593
12580
  output: 15,
12594
12581
  cacheRead: 0.3,
12595
- cacheWrite: 0,
12582
+ cacheWrite: 3,
12596
12583
  },
12597
12584
  contextWindow: 1048576,
12598
12585
  maxTokens: 131072,
12599
12586
  },
12600
- "longcat-2.0": {
12601
- id: "longcat-2.0",
12602
- name: "LongCat-2.0",
12587
+ "kimi-k3.1-pro": {
12588
+ id: "kimi-k3.1-pro",
12589
+ name: "Kimi K3.1 Pro",
12603
12590
  api: "openai-completions",
12604
12591
  provider: "opencode-go",
12605
12592
  baseUrl: "https://opencode.ai/zen/go/v1",
12606
12593
  reasoning: true,
12607
- input: ["text"],
12594
+ input: ["text", "image"],
12608
12595
  cost: {
12609
- input: 0.3,
12610
- output: 1.2,
12611
- cacheRead: 0.006,
12612
- cacheWrite: 0,
12596
+ input: 2,
12597
+ output: 10,
12598
+ cacheRead: 0.2,
12599
+ cacheWrite: 2,
12613
12600
  },
12614
- contextWindow: 1000000,
12601
+ contextWindow: 1048576,
12615
12602
  maxTokens: 131072,
12616
12603
  },
12617
- "longcat-2.5-preview-free": {
12618
- id: "longcat-2.5-preview-free",
12619
- name: "LongCat 2.5 Preview Free",
12604
+ "longcat-2.0": {
12605
+ id: "longcat-2.0",
12606
+ name: "LongCat-2.0",
12620
12607
  api: "openai-completions",
12621
12608
  provider: "opencode-go",
12622
12609
  baseUrl: "https://opencode.ai/zen/go/v1",
12623
12610
  reasoning: true,
12624
- input: ["text", "image"],
12611
+ input: ["text"],
12625
12612
  cost: {
12626
- input: 0,
12627
- output: 0,
12628
- cacheRead: 0,
12613
+ input: 0.3,
12614
+ output: 1.2,
12615
+ cacheRead: 0.006,
12629
12616
  cacheWrite: 0,
12630
12617
  },
12631
12618
  contextWindow: 1000000,
@@ -12699,23 +12686,6 @@ export const MODELS = {
12699
12686
  contextWindow: 1048576,
12700
12687
  maxTokens: 131072,
12701
12688
  },
12702
- "minimax-m2.7": {
12703
- id: "minimax-m2.7",
12704
- name: "MiniMax-M2.7",
12705
- api: "openai-completions",
12706
- provider: "opencode-go",
12707
- baseUrl: "https://opencode.ai/zen/go/v1",
12708
- reasoning: true,
12709
- input: ["text"],
12710
- cost: {
12711
- input: 0.3,
12712
- output: 1.2,
12713
- cacheRead: 0.06,
12714
- cacheWrite: 0.375,
12715
- },
12716
- contextWindow: 204800,
12717
- maxTokens: 131072,
12718
- },
12719
12689
  "minimax-m3": {
12720
12690
  id: "minimax-m3",
12721
12691
  name: "MiniMax-M3",
@@ -12733,6 +12703,23 @@ export const MODELS = {
12733
12703
  contextWindow: 1000000,
12734
12704
  maxTokens: 131072,
12735
12705
  },
12706
+ "minimax-m3.1-flash": {
12707
+ id: "minimax-m3.1-flash",
12708
+ name: "MiniMax M3.1 Flash",
12709
+ api: "openai-completions",
12710
+ provider: "opencode-go",
12711
+ baseUrl: "https://opencode.ai/zen/go/v1",
12712
+ reasoning: true,
12713
+ input: ["text", "image"],
12714
+ cost: {
12715
+ input: 0.15,
12716
+ output: 0.6,
12717
+ cacheRead: 0.015,
12718
+ cacheWrite: 0,
12719
+ },
12720
+ contextWindow: 1000000,
12721
+ maxTokens: 512000,
12722
+ },
12736
12723
  "muse-spark-1.2-contributor": {
12737
12724
  id: "muse-spark-1.2-contributor",
12738
12725
  name: "Muse Spark 1.2 Contributor",
@@ -12818,35 +12805,18 @@ export const MODELS = {
12818
12805
  contextWindow: 1000000,
12819
12806
  maxTokens: 131072,
12820
12807
  },
12821
- "space-bunny": {
12822
- id: "space-bunny",
12823
- name: "Space Bunny",
12824
- api: "openai-completions",
12825
- provider: "opencode-go",
12826
- baseUrl: "https://opencode.ai/zen/go/v1",
12827
- reasoning: true,
12828
- input: ["text", "image"],
12829
- cost: {
12830
- input: 0.15,
12831
- output: 0.6,
12832
- cacheRead: 0.03,
12833
- cacheWrite: 0,
12834
- },
12835
- contextWindow: 1048576,
12836
- maxTokens: 524288,
12837
- },
12838
- "step-5-preview-free": {
12839
- id: "step-5-preview-free",
12840
- name: "Step 5 Preview Free",
12808
+ "step-5-preview": {
12809
+ id: "step-5-preview",
12810
+ name: "Step 5 Preview",
12841
12811
  api: "openai-completions",
12842
12812
  provider: "opencode-go",
12843
12813
  baseUrl: "https://opencode.ai/zen/go/v1",
12844
12814
  reasoning: true,
12845
12815
  input: ["text", "image"],
12846
12816
  cost: {
12847
- input: 0,
12848
- output: 0,
12849
- cacheRead: 0,
12817
+ input: 1,
12818
+ output: 2.7,
12819
+ cacheRead: 0.1,
12850
12820
  cacheWrite: 0,
12851
12821
  },
12852
12822
  contextWindow: 1000000,
@@ -13408,23 +13378,6 @@ export const MODELS = {
13408
13378
  contextWindow: 1000000,
13409
13379
  maxTokens: 128000,
13410
13380
  },
13411
- "anthropic/claude-sonnet-4": {
13412
- id: "anthropic/claude-sonnet-4",
13413
- name: "Anthropic: Claude Sonnet 4",
13414
- api: "openai-completions",
13415
- provider: "openrouter",
13416
- baseUrl: "https://openrouter.ai/api/v1",
13417
- reasoning: true,
13418
- input: ["text", "image"],
13419
- cost: {
13420
- input: 3,
13421
- output: 15,
13422
- cacheRead: 0.3,
13423
- cacheWrite: 3.75,
13424
- },
13425
- contextWindow: 200000,
13426
- maxTokens: 64000,
13427
- },
13428
13381
  "anthropic/claude-sonnet-4.5": {
13429
13382
  id: "anthropic/claude-sonnet-4.5",
13430
13383
  name: "Anthropic: Claude Sonnet 4.5",
@@ -13561,23 +13514,6 @@ export const MODELS = {
13561
13514
  contextWindow: 1000000,
13562
13515
  maxTokens: 128000,
13563
13516
  },
13564
- "arcee-ai/trinity-large-thinking": {
13565
- id: "arcee-ai/trinity-large-thinking",
13566
- name: "Arcee AI: Trinity Large Thinking",
13567
- api: "openai-completions",
13568
- provider: "openrouter",
13569
- baseUrl: "https://openrouter.ai/api/v1",
13570
- reasoning: true,
13571
- input: ["text"],
13572
- cost: {
13573
- input: 0.25,
13574
- output: 0.7999999999999999,
13575
- cacheRead: 0.06,
13576
- cacheWrite: 0,
13577
- },
13578
- contextWindow: 262144,
13579
- maxTokens: 80000,
13580
- },
13581
13517
  "auto": {
13582
13518
  id: "auto",
13583
13519
  name: "Auto",
@@ -13774,13 +13710,13 @@ export const MODELS = {
13774
13710
  reasoning: false,
13775
13711
  input: ["text"],
13776
13712
  cost: {
13777
- input: 0.32,
13778
- output: 0.8899999999999999,
13713
+ input: 0.2574,
13714
+ output: 1.0287,
13779
13715
  cacheRead: 0,
13780
13716
  cacheWrite: 0,
13781
13717
  },
13782
13718
  contextWindow: 163840,
13783
- maxTokens: 16384,
13719
+ maxTokens: 16000,
13784
13720
  },
13785
13721
  "deepseek/deepseek-chat-v3-0324": {
13786
13722
  id: "deepseek/deepseek-chat-v3-0324",
@@ -13814,24 +13750,7 @@ export const MODELS = {
13814
13750
  cacheWrite: 0,
13815
13751
  },
13816
13752
  contextWindow: 163840,
13817
- maxTokens: 32768,
13818
- },
13819
- "deepseek/deepseek-r1": {
13820
- id: "deepseek/deepseek-r1",
13821
- name: "DeepSeek: R1",
13822
- api: "openai-completions",
13823
- provider: "openrouter",
13824
- baseUrl: "https://openrouter.ai/api/v1",
13825
- reasoning: true,
13826
- input: ["text"],
13827
- cost: {
13828
- input: 0.7,
13829
- output: 2.5,
13830
- cacheRead: 0,
13831
- cacheWrite: 0,
13832
- },
13833
- contextWindow: 64000,
13834
- maxTokens: 16000,
13753
+ maxTokens: 147456,
13835
13754
  },
13836
13755
  "deepseek/deepseek-r1-0528": {
13837
13756
  id: "deepseek/deepseek-r1-0528",
@@ -13876,9 +13795,9 @@ export const MODELS = {
13876
13795
  reasoning: true,
13877
13796
  input: ["text"],
13878
13797
  cost: {
13879
- input: 0.25899999999999995,
13880
- output: 0.7999999999999999,
13881
- cacheRead: 0.14,
13798
+ input: 0.26,
13799
+ output: 0.38,
13800
+ cacheRead: 0.13,
13882
13801
  cacheWrite: 0,
13883
13802
  },
13884
13803
  contextWindow: 163840,
@@ -13931,9 +13850,9 @@ export const MODELS = {
13931
13850
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13932
13851
  input: ["text"],
13933
13852
  cost: {
13934
- input: 0.016,
13935
- output: 0.64,
13936
- cacheRead: 0.016,
13853
+ input: 0.119,
13854
+ output: 0.238,
13855
+ cacheRead: 0.0238,
13937
13856
  cacheWrite: 0,
13938
13857
  },
13939
13858
  contextWindow: 1048576,
@@ -13969,13 +13888,13 @@ export const MODELS = {
13969
13888
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13970
13889
  input: ["text"],
13971
13890
  cost: {
13972
- input: 0.43934999999999996,
13973
- output: 0.8786999999999999,
13974
- cacheRead: 0.0366125,
13891
+ input: 1.5999999999999999,
13892
+ output: 3.1999999999999997,
13893
+ cacheRead: 0.135,
13975
13894
  cacheWrite: 0,
13976
13895
  },
13977
13896
  contextWindow: 1048576,
13978
- maxTokens: 384000,
13897
+ maxTokens: 393216,
13979
13898
  },
13980
13899
  "deepseek/deepseek-v4-pro-0813": {
13981
13900
  id: "deepseek/deepseek-v4-pro-0813",
@@ -13988,17 +13907,36 @@ export const MODELS = {
13988
13907
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13989
13908
  input: ["text"],
13990
13909
  cost: {
13991
- input: 0.66,
13992
- output: 1.9800000000000002,
13993
- cacheRead: 0.022,
13910
+ input: 0.11499999999999999,
13911
+ output: 4,
13912
+ cacheRead: 0.11,
13913
+ cacheWrite: 0,
13914
+ },
13915
+ contextWindow: 1048576,
13916
+ maxTokens: 943718,
13917
+ },
13918
+ "deepseek/deepseek-v4.1-flash": {
13919
+ id: "deepseek/deepseek-v4.1-flash",
13920
+ name: "DeepSeek: DeepSeek V4.1 Flash",
13921
+ api: "openai-completions",
13922
+ provider: "openrouter",
13923
+ baseUrl: "https://openrouter.ai/api/v1",
13924
+ compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
13925
+ reasoning: true,
13926
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13927
+ input: ["text", "image"],
13928
+ cost: {
13929
+ input: 0.045,
13930
+ output: 0.5,
13931
+ cacheRead: 0.006,
13994
13932
  cacheWrite: 0,
13995
13933
  },
13996
13934
  contextWindow: 1048576,
13997
- maxTokens: 393216,
13935
+ maxTokens: 943718,
13998
13936
  },
13999
- "deepseek/deepseek-v4.1-flash": {
14000
- id: "deepseek/deepseek-v4.1-flash",
14001
- name: "DeepSeek: DeepSeek V4.1 Flash",
13937
+ "deepseek/deepseek-v4.1-flash-1017": {
13938
+ id: "deepseek/deepseek-v4.1-flash-1017",
13939
+ name: "DeepSeek: DeepSeek V4.1 Flash 1017",
14002
13940
  api: "openai-completions",
14003
13941
  provider: "openrouter",
14004
13942
  baseUrl: "https://openrouter.ai/api/v1",
@@ -14007,13 +13945,13 @@ export const MODELS = {
14007
13945
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
14008
13946
  input: ["text", "image"],
14009
13947
  cost: {
14010
- input: 0.02016,
14011
- output: 0.891,
14012
- cacheRead: 0.0054,
13948
+ input: 0.15,
13949
+ output: 0.6,
13950
+ cacheRead: 0.003,
14013
13951
  cacheWrite: 0,
14014
13952
  },
14015
13953
  contextWindow: 1048576,
14016
- maxTokens: 943718,
13954
+ maxTokens: 393216,
14017
13955
  },
14018
13956
  "deepseek/deepseek-v4.1-flash:batch": {
14019
13957
  id: "deepseek/deepseek-v4.1-flash:batch",
@@ -14026,13 +13964,13 @@ export const MODELS = {
14026
13964
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
14027
13965
  input: ["text", "image"],
14028
13966
  cost: {
14029
- input: 0.112,
14030
- output: 0.33599999999999997,
14031
- cacheRead: 0.00336,
13967
+ input: 0.049999999999999996,
13968
+ output: 0.15,
13969
+ cacheRead: 0.004,
14032
13970
  cacheWrite: 0,
14033
13971
  },
14034
13972
  contextWindow: 1048576,
14035
- maxTokens: 131072,
13973
+ maxTokens: 384000,
14036
13974
  },
14037
13975
  "dots-studio/dots-3-note-preview:free": {
14038
13976
  id: "dots-studio/dots-3-note-preview:free",
@@ -14051,6 +13989,23 @@ export const MODELS = {
14051
13989
  contextWindow: 512000,
14052
13990
  maxTokens: 460800,
14053
13991
  },
13992
+ "elorian/glimpse": {
13993
+ id: "elorian/glimpse",
13994
+ name: "Elorian: Glimpse",
13995
+ api: "openai-completions",
13996
+ provider: "openrouter",
13997
+ baseUrl: "https://openrouter.ai/api/v1",
13998
+ reasoning: true,
13999
+ input: ["text", "image"],
14000
+ cost: {
14001
+ input: 0.6,
14002
+ output: 3,
14003
+ cacheRead: 0.06,
14004
+ cacheWrite: 0,
14005
+ },
14006
+ contextWindow: 262144,
14007
+ maxTokens: 256000,
14008
+ },
14054
14009
  "fireworks/ember-1": {
14055
14010
  id: "fireworks/ember-1",
14056
14011
  name: "Fireworks: Ember-1",
@@ -14102,40 +14057,6 @@ export const MODELS = {
14102
14057
  contextWindow: 1048576,
14103
14058
  maxTokens: 65535,
14104
14059
  },
14105
- "google/gemini-2.5-flash-lite:batch": {
14106
- id: "google/gemini-2.5-flash-lite:batch",
14107
- name: "Google: Gemini 2.5 Flash Lite (batch)",
14108
- api: "openai-completions",
14109
- provider: "openrouter",
14110
- baseUrl: "https://openrouter.ai/api/v1",
14111
- reasoning: true,
14112
- input: ["text", "image"],
14113
- cost: {
14114
- input: 0.049999999999999996,
14115
- output: 0.19999999999999998,
14116
- cacheRead: 0.01,
14117
- cacheWrite: 0,
14118
- },
14119
- contextWindow: 1048576,
14120
- maxTokens: 65535,
14121
- },
14122
- "google/gemini-2.5-flash:batch": {
14123
- id: "google/gemini-2.5-flash:batch",
14124
- name: "Google: Gemini 2.5 Flash (batch)",
14125
- api: "openai-completions",
14126
- provider: "openrouter",
14127
- baseUrl: "https://openrouter.ai/api/v1",
14128
- reasoning: true,
14129
- input: ["text", "image"],
14130
- cost: {
14131
- input: 0.15,
14132
- output: 1.25,
14133
- cacheRead: 0.03,
14134
- cacheWrite: 0,
14135
- },
14136
- contextWindow: 1048576,
14137
- maxTokens: 65535,
14138
- },
14139
14060
  "google/gemini-2.5-pro": {
14140
14061
  id: "google/gemini-2.5-pro",
14141
14062
  name: "Google: Gemini 2.5 Pro",
@@ -14170,23 +14091,6 @@ export const MODELS = {
14170
14091
  contextWindow: 1048576,
14171
14092
  maxTokens: 65536,
14172
14093
  },
14173
- "google/gemini-2.5-pro:batch": {
14174
- id: "google/gemini-2.5-pro:batch",
14175
- name: "Google: Gemini 2.5 Pro (batch)",
14176
- api: "openai-completions",
14177
- provider: "openrouter",
14178
- baseUrl: "https://openrouter.ai/api/v1",
14179
- reasoning: true,
14180
- input: ["text", "image"],
14181
- cost: {
14182
- input: 0.625,
14183
- output: 5,
14184
- cacheRead: 0.125,
14185
- cacheWrite: 0,
14186
- },
14187
- contextWindow: 1048576,
14188
- maxTokens: 65536,
14189
- },
14190
14094
  "google/gemini-3-flash-preview": {
14191
14095
  id: "google/gemini-3-flash-preview",
14192
14096
  name: "Google: Gemini 3 Flash Preview",
@@ -14485,9 +14389,9 @@ export const MODELS = {
14485
14389
  reasoning: true,
14486
14390
  input: ["text", "image"],
14487
14391
  cost: {
14488
- input: 0.75,
14489
- output: 3.75,
14490
- cacheRead: 0.075,
14392
+ input: 0.8250000000000001,
14393
+ output: 4.125,
14394
+ cacheRead: 0.0825,
14491
14395
  cacheWrite: 0.0416666666666667,
14492
14396
  },
14493
14397
  contextWindow: 1048576,
@@ -14525,7 +14429,7 @@ export const MODELS = {
14525
14429
  cacheWrite: 0.1875,
14526
14430
  },
14527
14431
  contextWindow: 1048576,
14528
- maxTokens: 65536,
14432
+ maxTokens: 943718,
14529
14433
  },
14530
14434
  "google/gemini-4-argon:batch": {
14531
14435
  id: "google/gemini-4-argon:batch",
@@ -14588,7 +14492,7 @@ export const MODELS = {
14588
14492
  input: ["text", "image"],
14589
14493
  cost: {
14590
14494
  input: 0.08,
14591
- output: 0.44999999999999996,
14495
+ output: 0.35,
14592
14496
  cacheRead: 0.04,
14593
14497
  cacheWrite: 0,
14594
14498
  },
@@ -14604,9 +14508,9 @@ export const MODELS = {
14604
14508
  reasoning: true,
14605
14509
  input: ["text", "image"],
14606
14510
  cost: {
14607
- input: 0.09,
14608
- output: 0.3,
14609
- cacheRead: 0.049999999999999996,
14511
+ input: 0.0675,
14512
+ output: 0.22499999999999998,
14513
+ cacheRead: 0.0375,
14610
14514
  cacheWrite: 0,
14611
14515
  },
14612
14516
  contextWindow: 262144,
@@ -14638,9 +14542,9 @@ export const MODELS = {
14638
14542
  reasoning: true,
14639
14543
  input: ["text", "image"],
14640
14544
  cost: {
14641
- input: 0.09,
14642
- output: 0.33999999999999997,
14643
- cacheRead: 0.049999999999999996,
14545
+ input: 0.19999999999999998,
14546
+ output: 0.39999999999999997,
14547
+ cacheRead: 0,
14644
14548
  cacheWrite: 0,
14645
14549
  },
14646
14550
  contextWindow: 262144,
@@ -14673,7 +14577,7 @@ export const MODELS = {
14673
14577
  input: ["text"],
14674
14578
  cost: {
14675
14579
  input: 0.06,
14676
- output: 0.25,
14580
+ output: 0.15,
14677
14581
  cacheRead: 0.015,
14678
14582
  cacheWrite: 0,
14679
14583
  },
@@ -14714,6 +14618,23 @@ export const MODELS = {
14714
14618
  contextWindow: 260000,
14715
14619
  maxTokens: 65536,
14716
14620
  },
14621
+ "inception/mercury-3": {
14622
+ id: "inception/mercury-3",
14623
+ name: "Inception: Mercury 3",
14624
+ api: "openai-completions",
14625
+ provider: "openrouter",
14626
+ baseUrl: "https://openrouter.ai/api/v1",
14627
+ reasoning: true,
14628
+ input: ["text"],
14629
+ cost: {
14630
+ input: 0.09999999999999999,
14631
+ output: 0.35,
14632
+ cacheRead: 0.01,
14633
+ cacheWrite: 0,
14634
+ },
14635
+ contextWindow: 1000000,
14636
+ maxTokens: 131072,
14637
+ },
14717
14638
  "inclusionai/ling-3.0-flash": {
14718
14639
  id: "inclusionai/ling-3.0-flash",
14719
14640
  name: "inclusionAI: Ling 3.0 Flash",
@@ -14762,8 +14683,25 @@ export const MODELS = {
14762
14683
  cacheRead: 0.015,
14763
14684
  cacheWrite: 0,
14764
14685
  },
14765
- contextWindow: 262144,
14766
- maxTokens: 235929,
14686
+ contextWindow: 1000000,
14687
+ maxTokens: 262144,
14688
+ },
14689
+ "liquid/lfm-2.5-2.6b": {
14690
+ id: "liquid/lfm-2.5-2.6b",
14691
+ name: "LiquidAI: LFM2.5-2.6B",
14692
+ api: "openai-completions",
14693
+ provider: "openrouter",
14694
+ baseUrl: "https://openrouter.ai/api/v1",
14695
+ reasoning: true,
14696
+ input: ["text"],
14697
+ cost: {
14698
+ input: 0.35,
14699
+ output: 0.5,
14700
+ cacheRead: 0.04,
14701
+ cacheWrite: 0,
14702
+ },
14703
+ contextWindow: 128000,
14704
+ maxTokens: 8192,
14767
14705
  },
14768
14706
  "liquid/lfm-2.5-2.6b:free": {
14769
14707
  id: "liquid/lfm-2.5-2.6b:free",
@@ -14859,13 +14797,13 @@ export const MODELS = {
14859
14797
  reasoning: false,
14860
14798
  input: ["text"],
14861
14799
  cost: {
14862
- input: 0.59,
14863
- output: 0.7899999999999999,
14864
- cacheRead: 0.295,
14800
+ input: 0.09999999999999999,
14801
+ output: 0.32,
14802
+ cacheRead: 0,
14865
14803
  cacheWrite: 0,
14866
14804
  },
14867
14805
  contextWindow: 131072,
14868
- maxTokens: 32768,
14806
+ maxTokens: 16384,
14869
14807
  },
14870
14808
  "meta-llama/llama-4-maverick": {
14871
14809
  id: "meta-llama/llama-4-maverick",
@@ -14881,7 +14819,7 @@ export const MODELS = {
14881
14819
  cacheRead: 0.049999999999999996,
14882
14820
  cacheWrite: 0,
14883
14821
  },
14884
- contextWindow: 1048576,
14822
+ contextWindow: 524288,
14885
14823
  maxTokens: 16384,
14886
14824
  },
14887
14825
  "meta-llama/llama-4-scout": {
@@ -14893,13 +14831,13 @@ export const MODELS = {
14893
14831
  reasoning: false,
14894
14832
  input: ["text", "image"],
14895
14833
  cost: {
14896
- input: 0.18,
14897
- output: 0.59,
14834
+ input: 0.09999999999999999,
14835
+ output: 0.3,
14898
14836
  cacheRead: 0,
14899
14837
  cacheWrite: 0,
14900
14838
  },
14901
14839
  contextWindow: 1310720,
14902
- maxTokens: 117964,
14840
+ maxTokens: 16384,
14903
14841
  },
14904
14842
  "meta/muse-glimmer-30b": {
14905
14843
  id: "meta/muse-glimmer-30b",
@@ -15003,6 +14941,23 @@ export const MODELS = {
15003
14941
  contextWindow: 1048576,
15004
14942
  maxTokens: 943718,
15005
14943
  },
14944
+ "meta/muse-spark-open": {
14945
+ id: "meta/muse-spark-open",
14946
+ name: "Meta: Muse Spark Open",
14947
+ api: "openai-completions",
14948
+ provider: "openrouter",
14949
+ baseUrl: "https://openrouter.ai/api/v1",
14950
+ reasoning: true,
14951
+ input: ["text", "image"],
14952
+ cost: {
14953
+ input: 1.25,
14954
+ output: 4.25,
14955
+ cacheRead: 0.15,
14956
+ cacheWrite: 0,
14957
+ },
14958
+ contextWindow: 1048576,
14959
+ maxTokens: 131072,
14960
+ },
15006
14961
  "meta/muse-wonder": {
15007
14962
  id: "meta/muse-wonder",
15008
14963
  name: "Meta: Muse Wonder",
@@ -15081,12 +15036,12 @@ export const MODELS = {
15081
15036
  input: ["text"],
15082
15037
  cost: {
15083
15038
  input: 0.27,
15084
- output: 1.08,
15085
- cacheRead: 0.027,
15039
+ output: 0.95,
15040
+ cacheRead: 0.03,
15086
15041
  cacheWrite: 0,
15087
15042
  },
15088
15043
  contextWindow: 204800,
15089
- maxTokens: 128000,
15044
+ maxTokens: 32768,
15090
15045
  },
15091
15046
  "minimax/minimax-m2.7": {
15092
15047
  id: "minimax/minimax-m2.7",
@@ -15122,35 +15077,35 @@ export const MODELS = {
15122
15077
  contextWindow: 1048576,
15123
15078
  maxTokens: 512000,
15124
15079
  },
15125
- "mistralai/codestral-2508": {
15126
- id: "mistralai/codestral-2508",
15127
- name: "Mistral: Codestral 2508",
15080
+ "minimax/minimax-m3.1-flash": {
15081
+ id: "minimax/minimax-m3.1-flash",
15082
+ name: "MiniMax: MiniMax M3.1 Flash",
15128
15083
  api: "openai-completions",
15129
15084
  provider: "openrouter",
15130
15085
  baseUrl: "https://openrouter.ai/api/v1",
15131
- reasoning: false,
15132
- input: ["text"],
15086
+ reasoning: true,
15087
+ input: ["text", "image"],
15133
15088
  cost: {
15134
- input: 0.3,
15135
- output: 0.8999999999999999,
15136
- cacheRead: 0.03,
15089
+ input: 0.075,
15090
+ output: 0.3,
15091
+ cacheRead: 0.0075,
15137
15092
  cacheWrite: 0,
15138
15093
  },
15139
- contextWindow: 256000,
15140
- maxTokens: 204800,
15094
+ contextWindow: 1048576,
15095
+ maxTokens: 524288,
15141
15096
  },
15142
- "mistralai/codestral-2508:batch": {
15143
- id: "mistralai/codestral-2508:batch",
15144
- name: "Mistral: Codestral 2508 (batch)",
15097
+ "mistralai/codestral-2508": {
15098
+ id: "mistralai/codestral-2508",
15099
+ name: "Mistral: Codestral 2508",
15145
15100
  api: "openai-completions",
15146
15101
  provider: "openrouter",
15147
15102
  baseUrl: "https://openrouter.ai/api/v1",
15148
15103
  reasoning: false,
15149
15104
  input: ["text"],
15150
15105
  cost: {
15151
- input: 0.15,
15152
- output: 0.44999999999999996,
15153
- cacheRead: 0.015,
15106
+ input: 0.3,
15107
+ output: 0.8999999999999999,
15108
+ cacheRead: 0.03,
15154
15109
  cacheWrite: 0,
15155
15110
  },
15156
15111
  contextWindow: 256000,
@@ -15224,23 +15179,6 @@ export const MODELS = {
15224
15179
  contextWindow: 262144,
15225
15180
  maxTokens: 209715,
15226
15181
  },
15227
- "mistralai/ministral-8b-2512:batch": {
15228
- id: "mistralai/ministral-8b-2512:batch",
15229
- name: "Mistral: Ministral 3 8B 2512 (batch)",
15230
- api: "openai-completions",
15231
- provider: "openrouter",
15232
- baseUrl: "https://openrouter.ai/api/v1",
15233
- reasoning: false,
15234
- input: ["text", "image"],
15235
- cost: {
15236
- input: 0.075,
15237
- output: 0.075,
15238
- cacheRead: 0.0075,
15239
- cacheWrite: 0,
15240
- },
15241
- contextWindow: 262144,
15242
- maxTokens: 209715,
15243
- },
15244
15182
  "mistralai/mistral-large": {
15245
15183
  id: "mistralai/mistral-large",
15246
15184
  name: "Mistral Large",
@@ -15292,23 +15230,6 @@ export const MODELS = {
15292
15230
  contextWindow: 262144,
15293
15231
  maxTokens: 209715,
15294
15232
  },
15295
- "mistralai/mistral-large-2512:batch": {
15296
- id: "mistralai/mistral-large-2512:batch",
15297
- name: "Mistral: Mistral Large 3 2512 (batch)",
15298
- api: "openai-completions",
15299
- provider: "openrouter",
15300
- baseUrl: "https://openrouter.ai/api/v1",
15301
- reasoning: false,
15302
- input: ["text", "image"],
15303
- cost: {
15304
- input: 0.25,
15305
- output: 0.75,
15306
- cacheRead: 0.024999999999999998,
15307
- cacheWrite: 0,
15308
- },
15309
- contextWindow: 262144,
15310
- maxTokens: 209715,
15311
- },
15312
15233
  "mistralai/mistral-large-4-0": {
15313
15234
  id: "mistralai/mistral-large-4-0",
15314
15235
  name: "Mistral: Mistral Large 4",
@@ -15318,8 +15239,8 @@ export const MODELS = {
15318
15239
  reasoning: true,
15319
15240
  input: ["text", "image"],
15320
15241
  cost: {
15321
- input: 0.6799999999999999,
15322
- output: 2.09,
15242
+ input: 0.7,
15243
+ output: 2.0999999999999996,
15323
15244
  cacheRead: 0.07,
15324
15245
  cacheWrite: 0,
15325
15246
  },
@@ -15394,23 +15315,6 @@ export const MODELS = {
15394
15315
  contextWindow: 131072,
15395
15316
  maxTokens: 104857,
15396
15317
  },
15397
- "mistralai/mistral-medium-3.1:batch": {
15398
- id: "mistralai/mistral-medium-3.1:batch",
15399
- name: "Mistral: Mistral Medium 3.1 (batch)",
15400
- api: "openai-completions",
15401
- provider: "openrouter",
15402
- baseUrl: "https://openrouter.ai/api/v1",
15403
- reasoning: false,
15404
- input: ["text", "image"],
15405
- cost: {
15406
- input: 0.19999999999999998,
15407
- output: 1,
15408
- cacheRead: 0.02,
15409
- cacheWrite: 0,
15410
- },
15411
- contextWindow: 131072,
15412
- maxTokens: 104857,
15413
- },
15414
15318
  "mistralai/mistral-nemo": {
15415
15319
  id: "mistralai/mistral-nemo",
15416
15320
  name: "Mistral: Mistral Nemo",
@@ -15462,23 +15366,6 @@ export const MODELS = {
15462
15366
  contextWindow: 262144,
15463
15367
  maxTokens: 209715,
15464
15368
  },
15465
- "mistralai/mistral-small-2603:batch": {
15466
- id: "mistralai/mistral-small-2603:batch",
15467
- name: "Mistral: Mistral Small 4 (batch)",
15468
- api: "openai-completions",
15469
- provider: "openrouter",
15470
- baseUrl: "https://openrouter.ai/api/v1",
15471
- reasoning: true,
15472
- input: ["text", "image"],
15473
- cost: {
15474
- input: 0.075,
15475
- output: 0.3,
15476
- cacheRead: 0.0075,
15477
- cacheWrite: 0,
15478
- },
15479
- contextWindow: 262144,
15480
- maxTokens: 209715,
15481
- },
15482
15369
  "mistralai/mistral-small-3.1-24b-instruct": {
15483
15370
  id: "mistralai/mistral-small-3.1-24b-instruct",
15484
15371
  name: "Mistral: Mistral Small 3.1 24B",
@@ -15505,8 +15392,8 @@ export const MODELS = {
15505
15392
  reasoning: false,
15506
15393
  input: ["text", "image"],
15507
15394
  cost: {
15508
- input: 0.09375,
15509
- output: 0.25,
15395
+ input: 0.075,
15396
+ output: 0.19999999999999998,
15510
15397
  cacheRead: 0,
15511
15398
  cacheWrite: 0,
15512
15399
  },
@@ -15641,26 +15528,43 @@ export const MODELS = {
15641
15528
  reasoning: true,
15642
15529
  input: ["text", "image"],
15643
15530
  cost: {
15644
- input: 0.6712,
15645
- output: 3.35,
15646
- cacheRead: 0.18,
15531
+ input: 0.6,
15532
+ output: 3.5,
15533
+ cacheRead: 0.15,
15647
15534
  cacheWrite: 0,
15648
15535
  },
15649
15536
  contextWindow: 262144,
15650
15537
  maxTokens: 235929,
15651
15538
  },
15652
- "moonshotai/kimi-k3": {
15653
- id: "moonshotai/kimi-k3",
15654
- name: "MoonshotAI: Kimi K3",
15539
+ "moonshotai/kimi-k3": {
15540
+ id: "moonshotai/kimi-k3",
15541
+ name: "MoonshotAI: Kimi K3",
15542
+ api: "openai-completions",
15543
+ provider: "openrouter",
15544
+ baseUrl: "https://openrouter.ai/api/v1",
15545
+ reasoning: true,
15546
+ input: ["text", "image"],
15547
+ cost: {
15548
+ input: 0.192,
15549
+ output: 15,
15550
+ cacheRead: 0.182,
15551
+ cacheWrite: 0,
15552
+ },
15553
+ contextWindow: 1048576,
15554
+ maxTokens: 943718,
15555
+ },
15556
+ "moonshotai/kimi-k3.1-pro": {
15557
+ id: "moonshotai/kimi-k3.1-pro",
15558
+ name: "MoonshotAI: Kimi K3.1 Pro",
15655
15559
  api: "openai-completions",
15656
15560
  provider: "openrouter",
15657
15561
  baseUrl: "https://openrouter.ai/api/v1",
15658
15562
  reasoning: true,
15659
15563
  input: ["text", "image"],
15660
15564
  cost: {
15661
- input: 0.7,
15662
- output: 15,
15663
- cacheRead: 0.32,
15565
+ input: 2,
15566
+ output: 10,
15567
+ cacheRead: 0.19999999999999998,
15664
15568
  cacheWrite: 0,
15665
15569
  },
15666
15570
  contextWindow: 1048576,
@@ -15711,7 +15615,7 @@ export const MODELS = {
15711
15615
  cost: {
15712
15616
  input: 0.06,
15713
15617
  output: 0.24,
15714
- cacheRead: 0,
15618
+ cacheRead: 0.012,
15715
15619
  cacheWrite: 0,
15716
15620
  },
15717
15621
  contextWindow: 262144,
@@ -15743,30 +15647,13 @@ export const MODELS = {
15743
15647
  reasoning: true,
15744
15648
  input: ["text"],
15745
15649
  cost: {
15746
- input: 0.08,
15747
- output: 0.44999999999999996,
15748
- cacheRead: 0,
15749
- cacheWrite: 0,
15750
- },
15751
- contextWindow: 262144,
15752
- maxTokens: 235929,
15753
- },
15754
- "nvidia/nemotron-3-super-120b-a12b:free": {
15755
- id: "nvidia/nemotron-3-super-120b-a12b:free",
15756
- name: "NVIDIA: Nemotron 3 Super (free)",
15757
- api: "openai-completions",
15758
- provider: "openrouter",
15759
- baseUrl: "https://openrouter.ai/api/v1",
15760
- reasoning: true,
15761
- input: ["text"],
15762
- cost: {
15763
- input: 0,
15764
- output: 0,
15765
- cacheRead: 0,
15650
+ input: 0.3,
15651
+ output: 2.4,
15652
+ cacheRead: 0.15,
15766
15653
  cacheWrite: 0,
15767
15654
  },
15768
- contextWindow: 262144,
15769
- maxTokens: 235929,
15655
+ contextWindow: 1048576,
15656
+ maxTokens: 262144,
15770
15657
  },
15771
15658
  "nvidia/nemotron-3-ultra-550b-a55b": {
15772
15659
  id: "nvidia/nemotron-3-ultra-550b-a55b",
@@ -15836,22 +15723,39 @@ export const MODELS = {
15836
15723
  contextWindow: 1000000,
15837
15724
  maxTokens: 65536,
15838
15725
  },
15839
- "openai/gpt-3.5-turbo": {
15840
- id: "openai/gpt-3.5-turbo",
15841
- name: "OpenAI: GPT-3.5 Turbo",
15726
+ "nvidia/nemotron-3.5-super-vl": {
15727
+ id: "nvidia/nemotron-3.5-super-vl",
15728
+ name: "NVIDIA: Nemotron 3.5 Super VL",
15842
15729
  api: "openai-completions",
15843
15730
  provider: "openrouter",
15844
15731
  baseUrl: "https://openrouter.ai/api/v1",
15845
- reasoning: false,
15846
- input: ["text"],
15732
+ reasoning: true,
15733
+ input: ["text", "image"],
15847
15734
  cost: {
15848
- input: 0.5,
15849
- output: 1.5,
15735
+ input: 0.15,
15736
+ output: 0.5,
15737
+ cacheRead: 0.02,
15738
+ cacheWrite: 0,
15739
+ },
15740
+ contextWindow: 1048576,
15741
+ maxTokens: 235929,
15742
+ },
15743
+ "nvidia/nemotron-3.5-super-vl:free": {
15744
+ id: "nvidia/nemotron-3.5-super-vl:free",
15745
+ name: "NVIDIA: Nemotron 3.5 Super VL (free)",
15746
+ api: "openai-completions",
15747
+ provider: "openrouter",
15748
+ baseUrl: "https://openrouter.ai/api/v1",
15749
+ reasoning: true,
15750
+ input: ["text", "image"],
15751
+ cost: {
15752
+ input: 0,
15753
+ output: 0,
15850
15754
  cacheRead: 0,
15851
15755
  cacheWrite: 0,
15852
15756
  },
15853
- contextWindow: 16385,
15854
- maxTokens: 4096,
15757
+ contextWindow: 1000000,
15758
+ maxTokens: 131072,
15855
15759
  },
15856
15760
  "openai/gpt-3.5-turbo-0613": {
15857
15761
  id: "openai/gpt-3.5-turbo-0613",
@@ -15887,23 +15791,6 @@ export const MODELS = {
15887
15791
  contextWindow: 16385,
15888
15792
  maxTokens: 4096,
15889
15793
  },
15890
- "openai/gpt-3.5-turbo:batch": {
15891
- id: "openai/gpt-3.5-turbo:batch",
15892
- name: "OpenAI: GPT-3.5 Turbo (batch)",
15893
- api: "openai-completions",
15894
- provider: "openrouter",
15895
- baseUrl: "https://openrouter.ai/api/v1",
15896
- reasoning: false,
15897
- input: ["text"],
15898
- cost: {
15899
- input: 0.25,
15900
- output: 0.75,
15901
- cacheRead: 0,
15902
- cacheWrite: 0,
15903
- },
15904
- contextWindow: 16385,
15905
- maxTokens: 4096,
15906
- },
15907
15794
  "openai/gpt-4": {
15908
15795
  id: "openai/gpt-4",
15909
15796
  name: "OpenAI: GPT-4",
@@ -16000,11 +15887,11 @@ export const MODELS = {
16000
15887
  cost: {
16001
15888
  input: 0.09999999999999999,
16002
15889
  output: 0.39999999999999997,
16003
- cacheRead: 0.024999999999999998,
15890
+ cacheRead: 0.03,
16004
15891
  cacheWrite: 0,
16005
15892
  },
16006
15893
  contextWindow: 1047576,
16007
- maxTokens: 32768,
15894
+ maxTokens: 942818,
16008
15895
  },
16009
15896
  "openai/gpt-4.1-nano:batch": {
16010
15897
  id: "openai/gpt-4.1-nano:batch",
@@ -16731,10 +16618,10 @@ export const MODELS = {
16731
16618
  reasoning: true,
16732
16619
  input: ["text", "image"],
16733
16620
  cost: {
16734
- input: 2,
16735
- output: 10,
16736
- cacheRead: 0.19999999999999998,
16737
- cacheWrite: 2.5,
16621
+ input: 4,
16622
+ output: 20,
16623
+ cacheRead: 0.39999999999999997,
16624
+ cacheWrite: 5,
16738
16625
  },
16739
16626
  contextWindow: 1050000,
16740
16627
  maxTokens: 128000,
@@ -16748,10 +16635,10 @@ export const MODELS = {
16748
16635
  reasoning: true,
16749
16636
  input: ["text", "image"],
16750
16637
  cost: {
16751
- input: 2,
16752
- output: 10,
16753
- cacheRead: 0.19999999999999998,
16754
- cacheWrite: 2.5,
16638
+ input: 4,
16639
+ output: 20,
16640
+ cacheRead: 0.39999999999999997,
16641
+ cacheWrite: 5,
16755
16642
  },
16756
16643
  contextWindow: 1050000,
16757
16644
  maxTokens: 128000,
@@ -16765,10 +16652,10 @@ export const MODELS = {
16765
16652
  reasoning: true,
16766
16653
  input: ["text", "image"],
16767
16654
  cost: {
16768
- input: 1,
16769
- output: 5,
16770
- cacheRead: 0.09999999999999999,
16771
- cacheWrite: 1.25,
16655
+ input: 2,
16656
+ output: 10,
16657
+ cacheRead: 0.19999999999999998,
16658
+ cacheWrite: 2.5,
16772
16659
  },
16773
16660
  contextWindow: 1050000,
16774
16661
  maxTokens: 128000,
@@ -16782,10 +16669,10 @@ export const MODELS = {
16782
16669
  reasoning: true,
16783
16670
  input: ["text", "image"],
16784
16671
  cost: {
16785
- input: 1,
16786
- output: 5,
16787
- cacheRead: 0.09999999999999999,
16788
- cacheWrite: 1.25,
16672
+ input: 2,
16673
+ output: 10,
16674
+ cacheRead: 0.19999999999999998,
16675
+ cacheWrite: 2.5,
16789
16676
  },
16790
16677
  contextWindow: 1050000,
16791
16678
  maxTokens: 128000,
@@ -17147,6 +17034,74 @@ export const MODELS = {
17147
17034
  contextWindow: 1050000,
17148
17035
  maxTokens: 128000,
17149
17036
  },
17037
+ "openai/gpt-6.1-terra": {
17038
+ id: "openai/gpt-6.1-terra",
17039
+ name: "OpenAI: GPT-6.1 Terra",
17040
+ api: "openai-completions",
17041
+ provider: "openrouter",
17042
+ baseUrl: "https://openrouter.ai/api/v1",
17043
+ reasoning: true,
17044
+ input: ["text", "image"],
17045
+ cost: {
17046
+ input: 1,
17047
+ output: 5,
17048
+ cacheRead: 0.049999999999999996,
17049
+ cacheWrite: 1.25,
17050
+ },
17051
+ contextWindow: 1050000,
17052
+ maxTokens: 128000,
17053
+ },
17054
+ "openai/gpt-6.1-terra-pro": {
17055
+ id: "openai/gpt-6.1-terra-pro",
17056
+ name: "OpenAI: GPT-6.1 Terra Pro",
17057
+ api: "openai-completions",
17058
+ provider: "openrouter",
17059
+ baseUrl: "https://openrouter.ai/api/v1",
17060
+ reasoning: true,
17061
+ input: ["text", "image"],
17062
+ cost: {
17063
+ input: 1,
17064
+ output: 5,
17065
+ cacheRead: 0.049999999999999996,
17066
+ cacheWrite: 1.25,
17067
+ },
17068
+ contextWindow: 1050000,
17069
+ maxTokens: 128000,
17070
+ },
17071
+ "openai/gpt-6.1-terra-pro:batch": {
17072
+ id: "openai/gpt-6.1-terra-pro:batch",
17073
+ name: "OpenAI: GPT-6.1 Terra Pro (batch)",
17074
+ api: "openai-completions",
17075
+ provider: "openrouter",
17076
+ baseUrl: "https://openrouter.ai/api/v1",
17077
+ reasoning: true,
17078
+ input: ["text", "image"],
17079
+ cost: {
17080
+ input: 0.5,
17081
+ output: 2.5,
17082
+ cacheRead: 0.024999999999999998,
17083
+ cacheWrite: 0.625,
17084
+ },
17085
+ contextWindow: 1050000,
17086
+ maxTokens: 128000,
17087
+ },
17088
+ "openai/gpt-6.1-terra:batch": {
17089
+ id: "openai/gpt-6.1-terra:batch",
17090
+ name: "OpenAI: GPT-6.1 Terra (batch)",
17091
+ api: "openai-completions",
17092
+ provider: "openrouter",
17093
+ baseUrl: "https://openrouter.ai/api/v1",
17094
+ reasoning: true,
17095
+ input: ["text", "image"],
17096
+ cost: {
17097
+ input: 0.5,
17098
+ output: 2.5,
17099
+ cacheRead: 0.024999999999999998,
17100
+ cacheWrite: 0.625,
17101
+ },
17102
+ contextWindow: 1050000,
17103
+ maxTokens: 128000,
17104
+ },
17150
17105
  "openai/gpt-audio": {
17151
17106
  id: "openai/gpt-audio",
17152
17107
  name: "OpenAI: GPT Audio",
@@ -17207,13 +17162,13 @@ export const MODELS = {
17207
17162
  reasoning: true,
17208
17163
  input: ["text"],
17209
17164
  cost: {
17210
- input: 0.037,
17211
- output: 0.16999999999999998,
17165
+ input: 0.014,
17166
+ output: 0.051,
17212
17167
  cacheRead: 0,
17213
17168
  cacheWrite: 0,
17214
17169
  },
17215
17170
  contextWindow: 131072,
17216
- maxTokens: 117964,
17171
+ maxTokens: 65536,
17217
17172
  },
17218
17173
  "openai/gpt-oss-120b:batch": {
17219
17174
  id: "openai/gpt-oss-120b:batch",
@@ -17241,13 +17196,13 @@ export const MODELS = {
17241
17196
  reasoning: true,
17242
17197
  input: ["text"],
17243
17198
  cost: {
17244
- input: 0.018,
17245
- output: 0.09,
17246
- cacheRead: 0.009,
17199
+ input: 0.03,
17200
+ output: 0.13,
17201
+ cacheRead: 0.03,
17247
17202
  cacheWrite: 0,
17248
17203
  },
17249
17204
  contextWindow: 131072,
17250
- maxTokens: 32768,
17205
+ maxTokens: 117964,
17251
17206
  },
17252
17207
  "openai/gpt-oss-20b:batch": {
17253
17208
  id: "openai/gpt-oss-20b:batch",
@@ -17283,23 +17238,6 @@ export const MODELS = {
17283
17238
  contextWindow: 131072,
17284
17239
  maxTokens: 65536,
17285
17240
  },
17286
- "openai/o1": {
17287
- id: "openai/o1",
17288
- name: "OpenAI: o1",
17289
- api: "openai-completions",
17290
- provider: "openrouter",
17291
- baseUrl: "https://openrouter.ai/api/v1",
17292
- reasoning: true,
17293
- input: ["text", "image"],
17294
- cost: {
17295
- input: 15,
17296
- output: 60,
17297
- cacheRead: 7.5,
17298
- cacheWrite: 0,
17299
- },
17300
- contextWindow: 200000,
17301
- maxTokens: 100000,
17302
- },
17303
17241
  "openai/o3": {
17304
17242
  id: "openai/o3",
17305
17243
  name: "OpenAI: o3",
@@ -17317,40 +17255,6 @@ export const MODELS = {
17317
17255
  contextWindow: 200000,
17318
17256
  maxTokens: 100000,
17319
17257
  },
17320
- "openai/o3-mini": {
17321
- id: "openai/o3-mini",
17322
- name: "OpenAI: o3 Mini",
17323
- api: "openai-completions",
17324
- provider: "openrouter",
17325
- baseUrl: "https://openrouter.ai/api/v1",
17326
- reasoning: true,
17327
- input: ["text"],
17328
- cost: {
17329
- input: 1.1,
17330
- output: 4.4,
17331
- cacheRead: 0.55,
17332
- cacheWrite: 0,
17333
- },
17334
- contextWindow: 200000,
17335
- maxTokens: 100000,
17336
- },
17337
- "openai/o3-mini-high": {
17338
- id: "openai/o3-mini-high",
17339
- name: "OpenAI: o3 Mini High",
17340
- api: "openai-completions",
17341
- provider: "openrouter",
17342
- baseUrl: "https://openrouter.ai/api/v1",
17343
- reasoning: true,
17344
- input: ["text"],
17345
- cost: {
17346
- input: 1.1,
17347
- output: 4.4,
17348
- cacheRead: 0.55,
17349
- cacheWrite: 0,
17350
- },
17351
- contextWindow: 200000,
17352
- maxTokens: 100000,
17353
- },
17354
17258
  "openai/o3-mini:batch": {
17355
17259
  id: "openai/o3-mini:batch",
17356
17260
  name: "OpenAI: o3 Mini (batch)",
@@ -17369,68 +17273,34 @@ export const MODELS = {
17369
17273
  maxTokens: 100000,
17370
17274
  },
17371
17275
  "openai/o3-pro": {
17372
- id: "openai/o3-pro",
17373
- name: "OpenAI: o3 Pro",
17374
- api: "openai-completions",
17375
- provider: "openrouter",
17376
- baseUrl: "https://openrouter.ai/api/v1",
17377
- reasoning: true,
17378
- input: ["text", "image"],
17379
- cost: {
17380
- input: 20,
17381
- output: 80,
17382
- cacheRead: 0,
17383
- cacheWrite: 0,
17384
- },
17385
- contextWindow: 200000,
17386
- maxTokens: 100000,
17387
- },
17388
- "openai/o3:batch": {
17389
- id: "openai/o3:batch",
17390
- name: "OpenAI: o3 (batch)",
17391
- api: "openai-completions",
17392
- provider: "openrouter",
17393
- baseUrl: "https://openrouter.ai/api/v1",
17394
- reasoning: true,
17395
- input: ["text", "image"],
17396
- cost: {
17397
- input: 1,
17398
- output: 4,
17399
- cacheRead: 0.25,
17400
- cacheWrite: 0,
17401
- },
17402
- contextWindow: 200000,
17403
- maxTokens: 100000,
17404
- },
17405
- "openai/o4-mini": {
17406
- id: "openai/o4-mini",
17407
- name: "OpenAI: o4 Mini",
17276
+ id: "openai/o3-pro",
17277
+ name: "OpenAI: o3 Pro",
17408
17278
  api: "openai-completions",
17409
17279
  provider: "openrouter",
17410
17280
  baseUrl: "https://openrouter.ai/api/v1",
17411
17281
  reasoning: true,
17412
17282
  input: ["text", "image"],
17413
17283
  cost: {
17414
- input: 1.1,
17415
- output: 4.4,
17416
- cacheRead: 0.275,
17284
+ input: 20,
17285
+ output: 80,
17286
+ cacheRead: 0,
17417
17287
  cacheWrite: 0,
17418
17288
  },
17419
17289
  contextWindow: 200000,
17420
17290
  maxTokens: 100000,
17421
17291
  },
17422
- "openai/o4-mini-high": {
17423
- id: "openai/o4-mini-high",
17424
- name: "OpenAI: o4 Mini High",
17292
+ "openai/o3:batch": {
17293
+ id: "openai/o3:batch",
17294
+ name: "OpenAI: o3 (batch)",
17425
17295
  api: "openai-completions",
17426
17296
  provider: "openrouter",
17427
17297
  baseUrl: "https://openrouter.ai/api/v1",
17428
17298
  reasoning: true,
17429
17299
  input: ["text", "image"],
17430
17300
  cost: {
17431
- input: 1.1,
17432
- output: 4.4,
17433
- cacheRead: 0.275,
17301
+ input: 1,
17302
+ output: 4,
17303
+ cacheRead: 0.25,
17434
17304
  cacheWrite: 0,
17435
17305
  },
17436
17306
  contextWindow: 200000,
@@ -17485,7 +17355,7 @@ export const MODELS = {
17485
17355
  cacheWrite: 0,
17486
17356
  },
17487
17357
  contextWindow: 2000000,
17488
- maxTokens: 4096,
17358
+ maxTokens: 65536,
17489
17359
  },
17490
17360
  "openrouter/free": {
17491
17361
  id: "openrouter/free",
@@ -17521,107 +17391,73 @@ export const MODELS = {
17521
17391
  contextWindow: 2000000,
17522
17392
  maxTokens: 4096,
17523
17393
  },
17524
- "perceptron/perceptron-mk1.5": {
17525
- id: "perceptron/perceptron-mk1.5",
17526
- name: "Perceptron: Perceptron Mk1.5",
17394
+ "particle-ai/particle-1": {
17395
+ id: "particle-ai/particle-1",
17396
+ name: "Particle AI: Particle-1",
17527
17397
  api: "openai-completions",
17528
17398
  provider: "openrouter",
17529
17399
  baseUrl: "https://openrouter.ai/api/v1",
17530
17400
  reasoning: true,
17531
17401
  input: ["text", "image"],
17532
17402
  cost: {
17533
- input: 0.15,
17534
- output: 1.5,
17535
- cacheRead: 0,
17536
- cacheWrite: 0,
17537
- },
17538
- contextWindow: 36864,
17539
- maxTokens: 8192,
17540
- },
17541
- "poolside/laguna-s-2.1": {
17542
- id: "poolside/laguna-s-2.1",
17543
- name: "Poolside: Laguna S 2.1",
17544
- api: "openai-completions",
17545
- provider: "openrouter",
17546
- baseUrl: "https://openrouter.ai/api/v1",
17547
- reasoning: true,
17548
- input: ["text"],
17549
- cost: {
17550
- input: 0.09,
17551
- output: 0.18,
17552
- cacheRead: 0.009,
17403
+ input: 0.049999999999999996,
17404
+ output: 0.5,
17405
+ cacheRead: 0.003,
17553
17406
  cacheWrite: 0,
17554
17407
  },
17555
17408
  contextWindow: 1048576,
17556
17409
  maxTokens: 131072,
17557
17410
  },
17558
- "poolside/laguna-s-2.1:free": {
17559
- id: "poolside/laguna-s-2.1:free",
17560
- name: "Poolside: Laguna S 2.1 (free)",
17411
+ "perceptron/perceptron-mk1.5": {
17412
+ id: "perceptron/perceptron-mk1.5",
17413
+ name: "Perceptron: Perceptron Mk1.5",
17561
17414
  api: "openai-completions",
17562
17415
  provider: "openrouter",
17563
17416
  baseUrl: "https://openrouter.ai/api/v1",
17564
17417
  reasoning: true,
17565
- input: ["text"],
17418
+ input: ["text", "image"],
17566
17419
  cost: {
17567
- input: 0,
17568
- output: 0,
17420
+ input: 0.15,
17421
+ output: 1.5,
17569
17422
  cacheRead: 0,
17570
17423
  cacheWrite: 0,
17571
17424
  },
17572
- contextWindow: 262144,
17573
- maxTokens: 32768,
17574
- },
17575
- "poolside/laguna-xs-2.1": {
17576
- id: "poolside/laguna-xs-2.1",
17577
- name: "Poolside: Laguna XS 2.1",
17578
- api: "openai-completions",
17579
- provider: "openrouter",
17580
- baseUrl: "https://openrouter.ai/api/v1",
17581
- reasoning: true,
17582
- input: ["text"],
17583
- cost: {
17584
- input: 0.06,
17585
- output: 0.12,
17586
- cacheRead: 0.03,
17587
- cacheWrite: 0,
17588
- },
17589
- contextWindow: 262144,
17590
- maxTokens: 32768,
17425
+ contextWindow: 36864,
17426
+ maxTokens: 8192,
17591
17427
  },
17592
- "poolside/laguna-xs-2.1:free": {
17593
- id: "poolside/laguna-xs-2.1:free",
17594
- name: "Poolside: Laguna XS 2.1 (free)",
17428
+ "prism-ml/ternary-bonsai-2-27b": {
17429
+ id: "prism-ml/ternary-bonsai-2-27b",
17430
+ name: "PrismML: Ternary Bonsai 2 27B",
17595
17431
  api: "openai-completions",
17596
17432
  provider: "openrouter",
17597
17433
  baseUrl: "https://openrouter.ai/api/v1",
17598
17434
  reasoning: true,
17599
- input: ["text"],
17435
+ input: ["text", "image"],
17600
17436
  cost: {
17601
- input: 0,
17602
- output: 0,
17603
- cacheRead: 0,
17437
+ input: 0.075,
17438
+ output: 0.5,
17439
+ cacheRead: 0.0375,
17604
17440
  cacheWrite: 0,
17605
17441
  },
17606
17442
  contextWindow: 262144,
17607
17443
  maxTokens: 32768,
17608
17444
  },
17609
- "prism-ml/ternary-bonsai-2-27b": {
17610
- id: "prism-ml/ternary-bonsai-2-27b",
17611
- name: "PrismML: Ternary Bonsai 2 27B",
17445
+ "prism-ml/ternary-bonsai-2-9b": {
17446
+ id: "prism-ml/ternary-bonsai-2-9b",
17447
+ name: "PrismML: Ternary Bonsai 2 9B",
17612
17448
  api: "openai-completions",
17613
17449
  provider: "openrouter",
17614
17450
  baseUrl: "https://openrouter.ai/api/v1",
17615
17451
  reasoning: true,
17616
17452
  input: ["text", "image"],
17617
17453
  cost: {
17618
- input: 0.075,
17619
- output: 0.5,
17620
- cacheRead: 0.0375,
17454
+ input: 0.08,
17455
+ output: 0.13,
17456
+ cacheRead: 0.04,
17621
17457
  cacheWrite: 0,
17622
17458
  },
17623
17459
  contextWindow: 262144,
17624
- maxTokens: 32768,
17460
+ maxTokens: 65536,
17625
17461
  },
17626
17462
  "qwen/qwen-2.5-72b-instruct": {
17627
17463
  id: "qwen/qwen-2.5-72b-instruct",
@@ -17753,7 +17589,7 @@ export const MODELS = {
17753
17589
  cost: {
17754
17590
  input: 0.09999999999999999,
17755
17591
  output: 0.3,
17756
- cacheRead: 0,
17592
+ cacheRead: 0.09999999999999999,
17757
17593
  cacheWrite: 0,
17758
17594
  },
17759
17595
  contextWindow: 262144,
@@ -17853,30 +17689,13 @@ export const MODELS = {
17853
17689
  reasoning: false,
17854
17690
  input: ["text"],
17855
17691
  cost: {
17856
- input: 0.09999999999999999,
17692
+ input: 0.09,
17857
17693
  output: 1.1,
17858
- cacheRead: 0.07,
17859
- cacheWrite: 0,
17860
- },
17861
- contextWindow: 262144,
17862
- maxTokens: 235929,
17863
- },
17864
- "qwen/qwen3-next-80b-a3b-thinking": {
17865
- id: "qwen/qwen3-next-80b-a3b-thinking",
17866
- name: "Qwen: Qwen3 Next 80B A3B Thinking",
17867
- api: "openai-completions",
17868
- provider: "openrouter",
17869
- baseUrl: "https://openrouter.ai/api/v1",
17870
- reasoning: true,
17871
- input: ["text"],
17872
- cost: {
17873
- input: 0.15,
17874
- output: 1.2,
17875
17694
  cacheRead: 0,
17876
17695
  cacheWrite: 0,
17877
17696
  },
17878
17697
  contextWindow: 262144,
17879
- maxTokens: 235929,
17698
+ maxTokens: 16384,
17880
17699
  },
17881
17700
  "qwen/qwen3-vl-235b-a22b-instruct": {
17882
17701
  id: "qwen/qwen3-vl-235b-a22b-instruct",
@@ -17989,13 +17808,13 @@ export const MODELS = {
17989
17808
  reasoning: true,
17990
17809
  input: ["text", "image"],
17991
17810
  cost: {
17992
- input: 0.15,
17811
+ input: 0.14,
17993
17812
  output: 1,
17994
17813
  cacheRead: 0.049999999999999996,
17995
17814
  cacheWrite: 0,
17996
17815
  },
17997
17816
  contextWindow: 262144,
17998
- maxTokens: 16384,
17817
+ maxTokens: 81920,
17999
17818
  },
18000
17819
  "qwen/qwen3.5-397b-a17b": {
18001
17820
  id: "qwen/qwen3.5-397b-a17b",
@@ -18023,13 +17842,13 @@ export const MODELS = {
18023
17842
  reasoning: true,
18024
17843
  input: ["text", "image"],
18025
17844
  cost: {
18026
- input: 0.09999999999999999,
18027
- output: 0.15,
17845
+ input: 0.16999999999999998,
17846
+ output: 0.25,
18028
17847
  cacheRead: 0,
18029
17848
  cacheWrite: 0,
18030
17849
  },
18031
17850
  contextWindow: 262144,
18032
- maxTokens: 32768,
17851
+ maxTokens: 235929,
18033
17852
  },
18034
17853
  "qwen/qwen3.5-flash-02-23": {
18035
17854
  id: "qwen/qwen3.5-flash-02-23",
@@ -18091,13 +17910,13 @@ export const MODELS = {
18091
17910
  reasoning: true,
18092
17911
  input: ["text", "image"],
18093
17912
  cost: {
18094
- input: 0.32,
18095
- output: 3.1999999999999997,
17913
+ input: 0.44999999999999996,
17914
+ output: 2.7,
18096
17915
  cacheRead: 0,
18097
17916
  cacheWrite: 0,
18098
17917
  },
18099
17918
  contextWindow: 262144,
18100
- maxTokens: 81920,
17919
+ maxTokens: 65536,
18101
17920
  },
18102
17921
  "qwen/qwen3.6-35b-a3b": {
18103
17922
  id: "qwen/qwen3.6-35b-a3b",
@@ -18109,12 +17928,12 @@ export const MODELS = {
18109
17928
  input: ["text", "image"],
18110
17929
  cost: {
18111
17930
  input: 0.09999999999999999,
18112
- output: 0.95,
18113
- cacheRead: 0.09999999999999999,
17931
+ output: 0.8999999999999999,
17932
+ cacheRead: 0.024999999999999998,
18114
17933
  cacheWrite: 0,
18115
17934
  },
18116
17935
  contextWindow: 262144,
18117
- maxTokens: 65536,
17936
+ maxTokens: 235929,
18118
17937
  },
18119
17938
  "qwen/qwen3.6-flash": {
18120
17939
  id: "qwen/qwen3.6-flash",
@@ -18201,6 +18020,23 @@ export const MODELS = {
18201
18020
  contextWindow: 1000000,
18202
18021
  maxTokens: 131072,
18203
18022
  },
18023
+ "qwen/qwen3.7-plus:batch": {
18024
+ id: "qwen/qwen3.7-plus:batch",
18025
+ name: "Qwen: Qwen3.7 Plus (batch)",
18026
+ api: "openai-completions",
18027
+ provider: "openrouter",
18028
+ baseUrl: "https://openrouter.ai/api/v1",
18029
+ reasoning: true,
18030
+ input: ["text", "image"],
18031
+ cost: {
18032
+ input: 0.22999999999999998,
18033
+ output: 0.9199999999999999,
18034
+ cacheRead: 0,
18035
+ cacheWrite: 0,
18036
+ },
18037
+ contextWindow: 262144,
18038
+ maxTokens: 131072,
18039
+ },
18204
18040
  "qwen/qwen3.8-2.4t-a95b": {
18205
18041
  id: "qwen/qwen3.8-2.4t-a95b",
18206
18042
  name: "Qwen: Qwen3.8 2.4T A95B",
@@ -18227,9 +18063,9 @@ export const MODELS = {
18227
18063
  reasoning: true,
18228
18064
  input: ["text", "image"],
18229
18065
  cost: {
18230
- input: 0.04,
18231
- output: 2.3,
18232
- cacheRead: 0.019799999999999998,
18066
+ input: 0.15,
18067
+ output: 1.875,
18068
+ cacheRead: 0.0375,
18233
18069
  cacheWrite: 0,
18234
18070
  },
18235
18071
  contextWindow: 1000000,
@@ -18303,6 +18139,40 @@ export const MODELS = {
18303
18139
  contextWindow: 1000000,
18304
18140
  maxTokens: 131072,
18305
18141
  },
18142
+ "recursive/flint-v1.0:free": {
18143
+ id: "recursive/flint-v1.0:free",
18144
+ name: "Recursive: Flint (free)",
18145
+ api: "openai-completions",
18146
+ provider: "openrouter",
18147
+ baseUrl: "https://openrouter.ai/api/v1",
18148
+ reasoning: true,
18149
+ input: ["text"],
18150
+ cost: {
18151
+ input: 0,
18152
+ output: 0,
18153
+ cacheRead: 0,
18154
+ cacheWrite: 0,
18155
+ },
18156
+ contextWindow: 262144,
18157
+ maxTokens: 235929,
18158
+ },
18159
+ "reflection/beam-1.0-501b-a23b": {
18160
+ id: "reflection/beam-1.0-501b-a23b",
18161
+ name: "Reflection: Beam 1.0 501B A23B",
18162
+ api: "openai-completions",
18163
+ provider: "openrouter",
18164
+ baseUrl: "https://openrouter.ai/api/v1",
18165
+ reasoning: true,
18166
+ input: ["text"],
18167
+ cost: {
18168
+ input: 0.25,
18169
+ output: 1,
18170
+ cacheRead: 0.049999999999999996,
18171
+ cacheWrite: 0,
18172
+ },
18173
+ contextWindow: 1048576,
18174
+ maxTokens: 131072,
18175
+ },
18306
18176
  "rekaai/reka-edge": {
18307
18177
  id: "rekaai/reka-edge",
18308
18178
  name: "Reka Edge",
@@ -18450,10 +18320,10 @@ export const MODELS = {
18450
18320
  cost: {
18451
18321
  input: 1,
18452
18322
  output: 2.7,
18453
- cacheRead: 0.049999999999999996,
18323
+ cacheRead: 0.09999999999999999,
18454
18324
  cacheWrite: 0,
18455
18325
  },
18456
- contextWindow: 1000000,
18326
+ contextWindow: 1048576,
18457
18327
  maxTokens: 64000,
18458
18328
  },
18459
18329
  "tencent/hy3": {
@@ -18465,9 +18335,9 @@ export const MODELS = {
18465
18335
  reasoning: true,
18466
18336
  input: ["text"],
18467
18337
  cost: {
18468
- input: 0.13199999999999998,
18469
- output: 0.5279999999999999,
18470
- cacheRead: 0.032999999999999995,
18338
+ input: 0.0825,
18339
+ output: 0.33,
18340
+ cacheRead: 0.020625,
18471
18341
  cacheWrite: 0,
18472
18342
  },
18473
18343
  contextWindow: 262144,
@@ -18482,9 +18352,9 @@ export const MODELS = {
18482
18352
  reasoning: true,
18483
18353
  input: ["text"],
18484
18354
  cost: {
18485
- input: 0.834,
18486
- output: 2.501,
18487
- cacheRead: 0.041999999999999996,
18355
+ input: 0.7505999999999999,
18356
+ output: 2.2509,
18357
+ cacheRead: 0.0378,
18488
18358
  cacheWrite: 0,
18489
18359
  },
18490
18360
  contextWindow: 1048576,
@@ -18573,11 +18443,11 @@ export const MODELS = {
18573
18443
  cacheWrite: 0,
18574
18444
  },
18575
18445
  contextWindow: 1000000,
18576
- maxTokens: 4096,
18446
+ maxTokens: 65536,
18577
18447
  },
18578
- "unbiased/pareto-26.10-preview": {
18579
- id: "unbiased/pareto-26.10-preview",
18580
- name: "Pareto 26.10 Preview",
18448
+ "unbiased/pareto-26.10": {
18449
+ id: "unbiased/pareto-26.10",
18450
+ name: "Pareto 26.10",
18581
18451
  api: "openai-completions",
18582
18452
  provider: "openrouter",
18583
18453
  baseUrl: "https://openrouter.ai/api/v1",
@@ -18626,23 +18496,6 @@ export const MODELS = {
18626
18496
  contextWindow: 524288,
18627
18497
  maxTokens: 131072,
18628
18498
  },
18629
- "upstage/solar-pro-3": {
18630
- id: "upstage/solar-pro-3",
18631
- name: "Upstage: Solar Pro 3",
18632
- api: "openai-completions",
18633
- provider: "openrouter",
18634
- baseUrl: "https://openrouter.ai/api/v1",
18635
- reasoning: true,
18636
- input: ["text"],
18637
- cost: {
18638
- input: 0.15,
18639
- output: 0.6,
18640
- cacheRead: 0.015,
18641
- cacheWrite: 0,
18642
- },
18643
- contextWindow: 131072,
18644
- maxTokens: 117964,
18645
- },
18646
18499
  "upstage/solar-pro4": {
18647
18500
  id: "upstage/solar-pro4",
18648
18501
  name: "Upstage: Solar Pro 4",
@@ -18652,9 +18505,9 @@ export const MODELS = {
18652
18505
  reasoning: true,
18653
18506
  input: ["text"],
18654
18507
  cost: {
18655
- input: 0.09,
18656
- output: 0.36,
18657
- cacheRead: 0.018,
18508
+ input: 0.15,
18509
+ output: 0.6,
18510
+ cacheRead: 0.03,
18658
18511
  cacheWrite: 0,
18659
18512
  },
18660
18513
  contextWindow: 524288,
@@ -18788,13 +18641,13 @@ export const MODELS = {
18788
18641
  reasoning: true,
18789
18642
  input: ["text", "image"],
18790
18643
  cost: {
18791
- input: 0.14,
18792
- output: 0.28,
18793
- cacheRead: 0.0028,
18644
+ input: 0.39999999999999997,
18645
+ output: 2,
18646
+ cacheRead: 0.08,
18794
18647
  cacheWrite: 0,
18795
18648
  },
18796
18649
  contextWindow: 1050000,
18797
- maxTokens: 131072,
18650
+ maxTokens: 65536,
18798
18651
  },
18799
18652
  "xiaomi/mimo-v2.5-pro": {
18800
18653
  id: "xiaomi/mimo-v2.5-pro",
@@ -18805,13 +18658,13 @@ export const MODELS = {
18805
18658
  reasoning: true,
18806
18659
  input: ["text"],
18807
18660
  cost: {
18808
- input: 0.435,
18809
- output: 0.87,
18810
- cacheRead: 0.0036,
18661
+ input: 0.48,
18662
+ output: 1.7999999999999998,
18663
+ cacheRead: 0.096,
18811
18664
  cacheWrite: 0,
18812
18665
  },
18813
18666
  contextWindow: 1050000,
18814
- maxTokens: 131072,
18667
+ maxTokens: 235929,
18815
18668
  },
18816
18669
  "xiaomi/mimo-v2.6-flash": {
18817
18670
  id: "xiaomi/mimo-v2.6-flash",
@@ -18864,6 +18717,23 @@ export const MODELS = {
18864
18717
  contextWindow: 1048576,
18865
18718
  maxTokens: 131072,
18866
18719
  },
18720
+ "xingchen-agi/xing4.0-29b-a4b:free": {
18721
+ id: "xingchen-agi/xing4.0-29b-a4b:free",
18722
+ name: "XingChen: Xing4.0 29B A4B (free)",
18723
+ api: "openai-completions",
18724
+ provider: "openrouter",
18725
+ baseUrl: "https://openrouter.ai/api/v1",
18726
+ reasoning: true,
18727
+ input: ["text"],
18728
+ cost: {
18729
+ input: 0,
18730
+ output: 0,
18731
+ cacheRead: 0,
18732
+ cacheWrite: 0,
18733
+ },
18734
+ contextWindow: 262144,
18735
+ maxTokens: 235929,
18736
+ },
18867
18737
  "z-ai/glm-4.5": {
18868
18738
  id: "z-ai/glm-4.5",
18869
18739
  name: "Z.ai: GLM 4.5",
@@ -18998,7 +18868,7 @@ export const MODELS = {
18998
18868
  cacheWrite: 0,
18999
18869
  },
19000
18870
  contextWindow: 204800,
19001
- maxTokens: 128000,
18871
+ maxTokens: 131072,
19002
18872
  },
19003
18873
  "z-ai/glm-5-turbo": {
19004
18874
  id: "z-ai/glm-5-turbo",
@@ -19026,9 +18896,9 @@ export const MODELS = {
19026
18896
  reasoning: true,
19027
18897
  input: ["text"],
19028
18898
  cost: {
19029
- input: 1.33,
19030
- output: 4.18,
19031
- cacheRead: 0.24699999999999997,
18899
+ input: 1.4,
18900
+ output: 4.4,
18901
+ cacheRead: 0.26,
19032
18902
  cacheWrite: 0,
19033
18903
  },
19034
18904
  contextWindow: 204800,
@@ -19043,9 +18913,9 @@ export const MODELS = {
19043
18913
  reasoning: true,
19044
18914
  input: ["text"],
19045
18915
  cost: {
19046
- input: 0.049999999999999996,
19047
- output: 7,
19048
- cacheRead: 0.049,
18916
+ input: 0.006,
18917
+ output: 6.8,
18918
+ cacheRead: 0.005,
19049
18919
  cacheWrite: 0,
19050
18920
  },
19051
18921
  contextWindow: 1048576,
@@ -19060,9 +18930,9 @@ export const MODELS = {
19060
18930
  reasoning: true,
19061
18931
  input: ["text"],
19062
18932
  cost: {
19063
- input: 0.079,
19064
- output: 4.8,
19065
- cacheRead: 0.059,
18933
+ input: 0.08,
18934
+ output: 3.5999999999999996,
18935
+ cacheRead: 0.07600000000000001,
19066
18936
  cacheWrite: 0,
19067
18937
  },
19068
18938
  contextWindow: 1048576,
@@ -19077,13 +18947,13 @@ export const MODELS = {
19077
18947
  reasoning: true,
19078
18948
  input: ["text", "image"],
19079
18949
  cost: {
19080
- input: 0.036,
19081
- output: 0.8999999999999999,
19082
- cacheRead: 0.0108,
18950
+ input: 0.0285,
18951
+ output: 0.0923,
18952
+ cacheRead: 0.0285,
19083
18953
  cacheWrite: 0,
19084
18954
  },
19085
18955
  contextWindow: 1048576,
19086
- maxTokens: 943718,
18956
+ maxTokens: 131072,
19087
18957
  },
19088
18958
  "z-ai/glm-5.3-flash:batch": {
19089
18959
  id: "z-ai/glm-5.3-flash:batch",
@@ -19094,9 +18964,9 @@ export const MODELS = {
19094
18964
  reasoning: true,
19095
18965
  input: ["text", "image"],
19096
18966
  cost: {
19097
- input: 0.06,
19098
- output: 0.19999999999999998,
19099
- cacheRead: 0.012,
18967
+ input: 0.049999999999999996,
18968
+ output: 0.18,
18969
+ cacheRead: 0.01,
19100
18970
  cacheWrite: 0,
19101
18971
  },
19102
18972
  contextWindow: 1048576,
@@ -19248,9 +19118,9 @@ export const MODELS = {
19248
19118
  reasoning: true,
19249
19119
  input: ["text", "image"],
19250
19120
  cost: {
19251
- input: 0.02016,
19252
- output: 0.891,
19253
- cacheRead: 0.0054,
19121
+ input: 0.035,
19122
+ output: 0.5,
19123
+ cacheRead: 0.005,
19254
19124
  cacheWrite: 0,
19255
19125
  },
19256
19126
  contextWindow: 1048576,
@@ -19265,9 +19135,9 @@ export const MODELS = {
19265
19135
  reasoning: true,
19266
19136
  input: ["text"],
19267
19137
  cost: {
19268
- input: 0.14609999999999998,
19138
+ input: 0.1035,
19269
19139
  output: 8,
19270
- cacheRead: 0.15,
19140
+ cacheRead: 0.09999999999999999,
19271
19141
  cacheWrite: 0,
19272
19142
  },
19273
19143
  contextWindow: 1048576,
@@ -19284,9 +19154,9 @@ export const MODELS = {
19284
19154
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
19285
19155
  input: ["text"],
19286
19156
  cost: {
19287
- input: 0.0144,
19288
- output: 0.576,
19289
- cacheRead: 0.0108,
19157
+ input: 0.059,
19158
+ output: 0.3,
19159
+ cacheRead: 0.035,
19290
19160
  cacheWrite: 0,
19291
19161
  },
19292
19162
  contextWindow: 1048576,
@@ -19319,12 +19189,12 @@ export const MODELS = {
19319
19189
  input: ["text", "image"],
19320
19190
  cost: {
19321
19191
  input: 2,
19322
- output: 12,
19323
- cacheRead: 0.19999999999999998,
19324
- cacheWrite: 0.375,
19192
+ output: 10,
19193
+ cacheRead: 0.09999999999999999,
19194
+ cacheWrite: 0.1875,
19325
19195
  },
19326
19196
  contextWindow: 1048576,
19327
- maxTokens: 65536,
19197
+ maxTokens: 943718,
19328
19198
  },
19329
19199
  "~moonshotai/kimi-latest": {
19330
19200
  id: "~moonshotai/kimi-latest",
@@ -19335,9 +19205,9 @@ export const MODELS = {
19335
19205
  reasoning: true,
19336
19206
  input: ["text", "image"],
19337
19207
  cost: {
19338
- input: 0.536,
19339
- output: 14,
19340
- cacheRead: 0.3,
19208
+ input: 0.14950000000000002,
19209
+ output: 7.15,
19210
+ cacheRead: 0.07475000000000001,
19341
19211
  cacheWrite: 0,
19342
19212
  },
19343
19213
  contextWindow: 1048576,
@@ -19420,10 +19290,10 @@ export const MODELS = {
19420
19290
  reasoning: true,
19421
19291
  input: ["text", "image"],
19422
19292
  cost: {
19423
- input: 2,
19424
- output: 12,
19425
- cacheRead: 0.19999999999999998,
19426
- cacheWrite: 2.5,
19293
+ input: 1,
19294
+ output: 5,
19295
+ cacheRead: 0.049999999999999996,
19296
+ cacheWrite: 1.25,
19427
19297
  },
19428
19298
  contextWindow: 1050000,
19429
19299
  maxTokens: 128000,
@@ -19437,12 +19307,12 @@ export const MODELS = {
19437
19307
  reasoning: false,
19438
19308
  input: ["text", "image"],
19439
19309
  cost: {
19440
- input: 2.5,
19441
- output: 7.5,
19442
- cacheRead: 0.25,
19310
+ input: 0.7999999999999999,
19311
+ output: 3.1999999999999997,
19312
+ cacheRead: 0.03,
19443
19313
  cacheWrite: 0,
19444
19314
  },
19445
- contextWindow: 262144,
19315
+ contextWindow: 1048576,
19446
19316
  maxTokens: 131072,
19447
19317
  },
19448
19318
  "~x-ai/grok-latest": {
@@ -19471,13 +19341,13 @@ export const MODELS = {
19471
19341
  reasoning: true,
19472
19342
  input: ["text", "image"],
19473
19343
  cost: {
19474
- input: 0.036,
19475
- output: 0.8999999999999999,
19476
- cacheRead: 0.0108,
19344
+ input: 0.0285,
19345
+ output: 0.0923,
19346
+ cacheRead: 0.0285,
19477
19347
  cacheWrite: 0,
19478
19348
  },
19479
19349
  contextWindow: 1048576,
19480
- maxTokens: 943718,
19350
+ maxTokens: 131072,
19481
19351
  },
19482
19352
  "~z-ai/glm-latest": {
19483
19353
  id: "~z-ai/glm-latest",
@@ -19488,35 +19358,16 @@ export const MODELS = {
19488
19358
  reasoning: true,
19489
19359
  input: ["text"],
19490
19360
  cost: {
19491
- input: 0.0576,
19492
- output: 4.4,
19493
- cacheRead: 0.053599999999999995,
19361
+ input: 0.0699,
19362
+ output: 1.4,
19363
+ cacheRead: 0.0689,
19494
19364
  cacheWrite: 0,
19495
19365
  },
19496
19366
  contextWindow: 1048576,
19497
- maxTokens: 131072,
19367
+ maxTokens: 943718,
19498
19368
  },
19499
19369
  },
19500
19370
  "together": {
19501
- "MiniMaxAI/MiniMax-M2.7": {
19502
- id: "MiniMaxAI/MiniMax-M2.7",
19503
- name: "MiniMax-M2.7",
19504
- api: "openai-completions",
19505
- provider: "together",
19506
- baseUrl: "https://api.together.ai/v1",
19507
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
19508
- reasoning: true,
19509
- thinkingLevelMap: { "off": null, "minimal": null, "low": null, "medium": null },
19510
- input: ["text"],
19511
- cost: {
19512
- input: 0.3,
19513
- output: 1.2,
19514
- cacheRead: 0.06,
19515
- cacheWrite: 0,
19516
- },
19517
- contextWindow: 196608,
19518
- maxTokens: 131072,
19519
- },
19520
19371
  "MiniMaxAI/MiniMax-M3": {
19521
19372
  id: "MiniMaxAI/MiniMax-M3",
19522
19373
  name: "MiniMax-M3",
@@ -19534,25 +19385,7 @@ export const MODELS = {
19534
19385
  cacheWrite: 0,
19535
19386
  },
19536
19387
  contextWindow: 524288,
19537
- maxTokens: 250000,
19538
- },
19539
- "Qwen/Qwen2.5-7B-Instruct-Turbo": {
19540
- id: "Qwen/Qwen2.5-7B-Instruct-Turbo",
19541
- name: "Qwen 2.5 7B Instruct Turbo",
19542
- api: "openai-completions",
19543
- provider: "together",
19544
- baseUrl: "https://api.together.ai/v1",
19545
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
19546
- reasoning: false,
19547
- input: ["text"],
19548
- cost: {
19549
- input: 0.3,
19550
- output: 0.3,
19551
- cacheRead: 0,
19552
- cacheWrite: 0,
19553
- },
19554
- contextWindow: 32768,
19555
- maxTokens: 32768,
19388
+ maxTokens: 524288,
19556
19389
  },
19557
19390
  "Qwen/Qwen3.5-9B": {
19558
19391
  id: "Qwen/Qwen3.5-9B",
@@ -19590,7 +19423,7 @@ export const MODELS = {
19590
19423
  cacheWrite: 0,
19591
19424
  },
19592
19425
  contextWindow: 1000000,
19593
- maxTokens: 500000,
19426
+ maxTokens: 65536,
19594
19427
  },
19595
19428
  "Qwen/Qwen3.7-Max": {
19596
19429
  id: "Qwen/Qwen3.7-Max",
@@ -19598,36 +19431,18 @@ export const MODELS = {
19598
19431
  api: "openai-completions",
19599
19432
  provider: "together",
19600
19433
  baseUrl: "https://api.together.ai/v1",
19601
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
19602
- reasoning: false,
19603
- input: ["text"],
19604
- cost: {
19605
- input: 1.25,
19606
- output: 3.75,
19607
- cacheRead: 0.125,
19608
- cacheWrite: 0,
19609
- },
19610
- contextWindow: 1000000,
19611
- maxTokens: 500000,
19612
- },
19613
- "deepseek-ai/DeepSeek-V4-Flash-0731": {
19614
- id: "deepseek-ai/DeepSeek-V4-Flash-0731",
19615
- name: "DeepSeek V4 Flash 0731",
19616
- api: "openai-completions",
19617
- provider: "together",
19618
- baseUrl: "https://api.together.ai/v1",
19619
19434
  compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
19620
19435
  reasoning: true,
19621
19436
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
19622
19437
  input: ["text"],
19623
19438
  cost: {
19624
- input: 0.14,
19625
- output: 0.28,
19626
- cacheRead: 0.03,
19439
+ input: 2.5,
19440
+ output: 7.5,
19441
+ cacheRead: 0.5,
19627
19442
  cacheWrite: 0,
19628
19443
  },
19629
- contextWindow: 1048576,
19630
- maxTokens: 384000,
19444
+ contextWindow: 1000000,
19445
+ maxTokens: 131072,
19631
19446
  },
19632
19447
  "deepseek-ai/DeepSeek-V4-Pro-0813": {
19633
19448
  id: "deepseek-ai/DeepSeek-V4-Pro-0813",
@@ -19667,22 +19482,23 @@ export const MODELS = {
19667
19482
  contextWindow: 1048576,
19668
19483
  maxTokens: 384000,
19669
19484
  },
19670
- "meta-llama/Llama-3.3-70B-Instruct-Turbo": {
19671
- id: "meta-llama/Llama-3.3-70B-Instruct-Turbo",
19672
- name: "Llama 3.3 70B",
19485
+ "meta-models/Muse-Spark-Open-816B-A42B": {
19486
+ id: "meta-models/Muse-Spark-Open-816B-A42B",
19487
+ name: "Muse Spark Open",
19673
19488
  api: "openai-completions",
19674
19489
  provider: "together",
19675
19490
  baseUrl: "https://api.together.ai/v1",
19676
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
19677
- reasoning: false,
19678
- input: ["text"],
19491
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
19492
+ reasoning: true,
19493
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
19494
+ input: ["text", "image"],
19679
19495
  cost: {
19680
- input: 1.04,
19681
- output: 1.04,
19682
- cacheRead: 0,
19496
+ input: 1.25,
19497
+ output: 4.25,
19498
+ cacheRead: 0.15,
19683
19499
  cacheWrite: 0,
19684
19500
  },
19685
- contextWindow: 131072,
19501
+ contextWindow: 1048576,
19686
19502
  maxTokens: 131072,
19687
19503
  },
19688
19504
  "moonshotai/Kimi-K3": {
@@ -19704,24 +19520,24 @@ export const MODELS = {
19704
19520
  contextWindow: 1048576,
19705
19521
  maxTokens: 131072,
19706
19522
  },
19707
- "nvidia/nemotron-3-ultra-550b-a55b": {
19708
- id: "nvidia/nemotron-3-ultra-550b-a55b",
19709
- name: "Nemotron 3 Ultra 550B A55B",
19523
+ "nvidia/NVIDIA-Nemotron-3.5-Super-VL": {
19524
+ id: "nvidia/NVIDIA-Nemotron-3.5-Super-VL",
19525
+ name: "Nemotron 3.5 Super VL 120B A12B",
19710
19526
  api: "openai-completions",
19711
19527
  provider: "together",
19712
19528
  baseUrl: "https://api.together.ai/v1",
19713
19529
  compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
19714
19530
  reasoning: true,
19715
19531
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
19716
- input: ["text"],
19532
+ input: ["text", "image"],
19717
19533
  cost: {
19718
- input: 0.6,
19719
- output: 3.6,
19720
- cacheRead: 0.2,
19534
+ input: 0.15,
19535
+ output: 0.5,
19536
+ cacheRead: 0.02,
19721
19537
  cacheWrite: 0,
19722
19538
  },
19723
- contextWindow: 512300,
19724
- maxTokens: 512300,
19539
+ contextWindow: 262144,
19540
+ maxTokens: 262144,
19725
19541
  },
19726
19542
  "openai/gpt-oss-120b": {
19727
19543
  id: "openai/gpt-oss-120b",
@@ -19742,6 +19558,25 @@ export const MODELS = {
19742
19558
  contextWindow: 131072,
19743
19559
  maxTokens: 131072,
19744
19560
  },
19561
+ "reflection/Beam-1.0-501B-A23B": {
19562
+ id: "reflection/Beam-1.0-501B-A23B",
19563
+ name: "Beam 1.0 501B A23B",
19564
+ api: "openai-completions",
19565
+ provider: "together",
19566
+ baseUrl: "https://api.together.ai/v1",
19567
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
19568
+ reasoning: true,
19569
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
19570
+ input: ["text"],
19571
+ cost: {
19572
+ input: 0.4,
19573
+ output: 1.2,
19574
+ cacheRead: 0.04,
19575
+ cacheWrite: 0,
19576
+ },
19577
+ contextWindow: 1048576,
19578
+ maxTokens: 131072,
19579
+ },
19745
19580
  "thinkingmachines/Inkling": {
19746
19581
  id: "thinkingmachines/Inkling",
19747
19582
  name: "Inkling",
@@ -19796,7 +19631,7 @@ export const MODELS = {
19796
19631
  cacheRead: 0.26,
19797
19632
  cacheWrite: 0,
19798
19633
  },
19799
- contextWindow: 1048576,
19634
+ contextWindow: 1048575,
19800
19635
  maxTokens: 262144,
19801
19636
  },
19802
19637
  "zai-org/GLM-5.3-Flash": {
@@ -20254,9 +20089,9 @@ export const MODELS = {
20254
20089
  reasoning: true,
20255
20090
  input: ["text", "image"],
20256
20091
  cost: {
20257
- input: 0.3,
20258
- output: 2.5,
20259
- cacheRead: 0.075,
20092
+ input: 0.33,
20093
+ output: 2.75,
20094
+ cacheRead: 0.0825,
20260
20095
  cacheWrite: 0,
20261
20096
  },
20262
20097
  contextWindow: 1000000,
@@ -20273,7 +20108,7 @@ export const MODELS = {
20273
20108
  cost: {
20274
20109
  input: 0.06,
20275
20110
  output: 0.24,
20276
- cacheRead: 0,
20111
+ cacheRead: 0.015,
20277
20112
  cacheWrite: 0,
20278
20113
  },
20279
20114
  contextWindow: 300000,
@@ -20290,7 +20125,7 @@ export const MODELS = {
20290
20125
  cost: {
20291
20126
  input: 0.035,
20292
20127
  output: 0.14,
20293
- cacheRead: 0,
20128
+ cacheRead: 0.0087,
20294
20129
  cacheWrite: 0,
20295
20130
  },
20296
20131
  contextWindow: 128000,
@@ -20307,7 +20142,7 @@ export const MODELS = {
20307
20142
  cost: {
20308
20143
  input: 0.7999999999999999,
20309
20144
  output: 3.1999999999999997,
20310
- cacheRead: 0,
20145
+ cacheRead: 0.19999999999999998,
20311
20146
  cacheWrite: 0,
20312
20147
  },
20313
20148
  contextWindow: 300000,
@@ -20715,23 +20550,6 @@ export const MODELS = {
20715
20550
  contextWindow: 1000000,
20716
20551
  maxTokens: 128000,
20717
20552
  },
20718
- "anthropic/claude-sonnet-4": {
20719
- id: "anthropic/claude-sonnet-4",
20720
- name: "Claude Sonnet 4",
20721
- api: "anthropic-messages",
20722
- provider: "vercel-ai-gateway",
20723
- baseUrl: "https://ai-gateway.vercel.sh",
20724
- reasoning: true,
20725
- input: ["text", "image"],
20726
- cost: {
20727
- input: 3,
20728
- output: 15,
20729
- cacheRead: 0.3,
20730
- cacheWrite: 3.75,
20731
- },
20732
- contextWindow: 1000000,
20733
- maxTokens: 64000,
20734
- },
20735
20553
  "anthropic/claude-sonnet-4.5": {
20736
20554
  id: "anthropic/claude-sonnet-4.5",
20737
20555
  name: "Claude Sonnet 4.5",
@@ -20868,23 +20686,6 @@ export const MODELS = {
20868
20686
  contextWindow: 1000000,
20869
20687
  maxTokens: 128000,
20870
20688
  },
20871
- "arcee-ai/trinity-large-thinking": {
20872
- id: "arcee-ai/trinity-large-thinking",
20873
- name: "Trinity Large Thinking",
20874
- api: "anthropic-messages",
20875
- provider: "vercel-ai-gateway",
20876
- baseUrl: "https://ai-gateway.vercel.sh",
20877
- reasoning: true,
20878
- input: ["text"],
20879
- cost: {
20880
- input: 0.25,
20881
- output: 0.7999999999999999,
20882
- cacheRead: 0,
20883
- cacheWrite: 0,
20884
- },
20885
- contextWindow: 262100,
20886
- maxTokens: 80000,
20887
- },
20888
20689
  "bytedance/seed-1.6": {
20889
20690
  id: "bytedance/seed-1.6",
20890
20691
  name: "Seed 1.6",
@@ -21140,6 +20941,40 @@ export const MODELS = {
21140
20941
  contextWindow: 1048576,
21141
20942
  maxTokens: 32768,
21142
20943
  },
20944
+ "deepseek/deepseek-v4.1-flash-1017": {
20945
+ id: "deepseek/deepseek-v4.1-flash-1017",
20946
+ name: "DeepSeek V4.1 Flash 1017",
20947
+ api: "anthropic-messages",
20948
+ provider: "vercel-ai-gateway",
20949
+ baseUrl: "https://ai-gateway.vercel.sh",
20950
+ reasoning: true,
20951
+ input: ["text", "image"],
20952
+ cost: {
20953
+ input: 0.3,
20954
+ output: 1.2,
20955
+ cacheRead: 0.007,
20956
+ cacheWrite: 0,
20957
+ },
20958
+ contextWindow: 1048576,
20959
+ maxTokens: 262144,
20960
+ },
20961
+ "deepseek/deepseek-v4.1-flash-1017-fast": {
20962
+ id: "deepseek/deepseek-v4.1-flash-1017-fast",
20963
+ name: "DeepSeek V4.1 Flash 1017 Fast",
20964
+ api: "anthropic-messages",
20965
+ provider: "vercel-ai-gateway",
20966
+ baseUrl: "https://ai-gateway.vercel.sh",
20967
+ reasoning: true,
20968
+ input: ["text", "image"],
20969
+ cost: {
20970
+ input: 0.6,
20971
+ output: 2.4,
20972
+ cacheRead: 0.014,
20973
+ cacheWrite: 0,
20974
+ },
20975
+ contextWindow: 1048576,
20976
+ maxTokens: 262144,
20977
+ },
21143
20978
  "deepseek/deepseek-v4.1-flash-fast": {
21144
20979
  id: "deepseek/deepseek-v4.1-flash-fast",
21145
20980
  name: "DeepSeek V4.1 Flash Fast",
@@ -21616,6 +21451,23 @@ export const MODELS = {
21616
21451
  contextWindow: 260000,
21617
21452
  maxTokens: 65536,
21618
21453
  },
21454
+ "inception/mercury-3": {
21455
+ id: "inception/mercury-3",
21456
+ name: "Mercury 3",
21457
+ api: "anthropic-messages",
21458
+ provider: "vercel-ai-gateway",
21459
+ baseUrl: "https://ai-gateway.vercel.sh",
21460
+ reasoning: true,
21461
+ input: ["text"],
21462
+ cost: {
21463
+ input: 0.09999999999999999,
21464
+ output: 0.35,
21465
+ cacheRead: 0.01,
21466
+ cacheWrite: 0,
21467
+ },
21468
+ contextWindow: 1000000,
21469
+ maxTokens: 131072,
21470
+ },
21619
21471
  "inception/mercury-coder-small": {
21620
21472
  id: "inception/mercury-coder-small",
21621
21473
  name: "Mercury Coder Small Beta",
@@ -21718,6 +21570,23 @@ export const MODELS = {
21718
21570
  contextWindow: 262144,
21719
21571
  maxTokens: 32768,
21720
21572
  },
21573
+ "inclusionai/ling-3.1-flash-1019": {
21574
+ id: "inclusionai/ling-3.1-flash-1019",
21575
+ name: "Ling 3.1 Flash 1019",
21576
+ api: "anthropic-messages",
21577
+ provider: "vercel-ai-gateway",
21578
+ baseUrl: "https://ai-gateway.vercel.sh",
21579
+ reasoning: true,
21580
+ input: ["text"],
21581
+ cost: {
21582
+ input: 0,
21583
+ output: 0,
21584
+ cacheRead: 0,
21585
+ cacheWrite: 0,
21586
+ },
21587
+ contextWindow: 1000000,
21588
+ maxTokens: 262144,
21589
+ },
21721
21590
  "interfaze/interfaze-beta": {
21722
21591
  id: "interfaze/interfaze-beta",
21723
21592
  name: "Interfaze Beta",
@@ -21939,18 +21808,35 @@ export const MODELS = {
21939
21808
  contextWindow: 1048576,
21940
21809
  maxTokens: 1048576,
21941
21810
  },
21942
- "meta/muse-spark-1.3-contributor": {
21943
- id: "meta/muse-spark-1.3-contributor",
21944
- name: "Muse Spark 1.3 Contributor",
21811
+ "meta/muse-spark-1.3-contributor": {
21812
+ id: "meta/muse-spark-1.3-contributor",
21813
+ name: "Muse Spark 1.3 Contributor",
21814
+ api: "anthropic-messages",
21815
+ provider: "vercel-ai-gateway",
21816
+ baseUrl: "https://ai-gateway.vercel.sh",
21817
+ reasoning: true,
21818
+ input: ["text", "image"],
21819
+ cost: {
21820
+ input: 0.09999999999999999,
21821
+ output: 0.19999999999999998,
21822
+ cacheRead: 0.002,
21823
+ cacheWrite: 0,
21824
+ },
21825
+ contextWindow: 1048576,
21826
+ maxTokens: 1048576,
21827
+ },
21828
+ "meta/muse-spark-open": {
21829
+ id: "meta/muse-spark-open",
21830
+ name: "Muse Spark Open",
21945
21831
  api: "anthropic-messages",
21946
21832
  provider: "vercel-ai-gateway",
21947
21833
  baseUrl: "https://ai-gateway.vercel.sh",
21948
21834
  reasoning: true,
21949
21835
  input: ["text", "image"],
21950
21836
  cost: {
21951
- input: 0.09999999999999999,
21952
- output: 0.19999999999999998,
21953
- cacheRead: 0.002,
21837
+ input: 1.25,
21838
+ output: 4.25,
21839
+ cacheRead: 0.15,
21954
21840
  cacheWrite: 0,
21955
21841
  },
21956
21842
  contextWindow: 1048576,
@@ -22109,6 +21995,23 @@ export const MODELS = {
22109
21995
  contextWindow: 512000,
22110
21996
  maxTokens: 512000,
22111
21997
  },
21998
+ "minimax/minimax-m3.1-flash": {
21999
+ id: "minimax/minimax-m3.1-flash",
22000
+ name: "MiniMax-M3.1-Flash",
22001
+ api: "anthropic-messages",
22002
+ provider: "vercel-ai-gateway",
22003
+ baseUrl: "https://ai-gateway.vercel.sh",
22004
+ reasoning: true,
22005
+ input: ["text", "image"],
22006
+ cost: {
22007
+ input: 0.15,
22008
+ output: 0.6,
22009
+ cacheRead: 0.015,
22010
+ cacheWrite: 0,
22011
+ },
22012
+ contextWindow: 1048576,
22013
+ maxTokens: 1048576,
22014
+ },
22112
22015
  "mistral/codestral": {
22113
22016
  id: "mistral/codestral",
22114
22017
  name: "Mistral Codestral",
@@ -22203,12 +22106,12 @@ export const MODELS = {
22203
22106
  reasoning: true,
22204
22107
  input: ["text", "image"],
22205
22108
  cost: {
22206
- input: 0.6799999999999999,
22207
- output: 2.09,
22109
+ input: 0.7,
22110
+ output: 2.0999999999999996,
22208
22111
  cacheRead: 0.07,
22209
22112
  cacheWrite: 0,
22210
22113
  },
22211
- contextWindow: 524288,
22114
+ contextWindow: 1048576,
22212
22115
  maxTokens: 262144,
22213
22116
  },
22214
22117
  "mistral/mistral-medium-3.5": {
@@ -22398,6 +22301,40 @@ export const MODELS = {
22398
22301
  contextWindow: 1000000,
22399
22302
  maxTokens: 131072,
22400
22303
  },
22304
+ "moonshotai/kimi-k3.1-pro": {
22305
+ id: "moonshotai/kimi-k3.1-pro",
22306
+ name: "Kimi K3.1 Pro",
22307
+ api: "anthropic-messages",
22308
+ provider: "vercel-ai-gateway",
22309
+ baseUrl: "https://ai-gateway.vercel.sh",
22310
+ reasoning: true,
22311
+ input: ["text", "image"],
22312
+ cost: {
22313
+ input: 2,
22314
+ output: 10,
22315
+ cacheRead: 0.19999999999999998,
22316
+ cacheWrite: 2,
22317
+ },
22318
+ contextWindow: 1048576,
22319
+ maxTokens: 1048576,
22320
+ },
22321
+ "moonshotai/kimi-k3.1-pro-highspeed": {
22322
+ id: "moonshotai/kimi-k3.1-pro-highspeed",
22323
+ name: "Kimi K3.1 Pro Highspeed",
22324
+ api: "anthropic-messages",
22325
+ provider: "vercel-ai-gateway",
22326
+ baseUrl: "https://ai-gateway.vercel.sh",
22327
+ reasoning: true,
22328
+ input: ["text", "image"],
22329
+ cost: {
22330
+ input: 4,
22331
+ output: 20,
22332
+ cacheRead: 0.19999999999999998,
22333
+ cacheWrite: 4,
22334
+ },
22335
+ contextWindow: 1048576,
22336
+ maxTokens: 1048576,
22337
+ },
22401
22338
  "nvidia/nemotron-3-nano-30b-a3b": {
22402
22339
  id: "nvidia/nemotron-3-nano-30b-a3b",
22403
22340
  name: "Nemotron 3 Nano 30B A3B",
@@ -22483,6 +22420,23 @@ export const MODELS = {
22483
22420
  contextWindow: 1000000,
22484
22421
  maxTokens: 65000,
22485
22422
  },
22423
+ "nvidia/nemotron-3.5-super-vl": {
22424
+ id: "nvidia/nemotron-3.5-super-vl",
22425
+ name: "NVIDIA Nemotron 3.5 Super VL",
22426
+ api: "anthropic-messages",
22427
+ provider: "vercel-ai-gateway",
22428
+ baseUrl: "https://ai-gateway.vercel.sh",
22429
+ reasoning: true,
22430
+ input: ["text", "image"],
22431
+ cost: {
22432
+ input: 0.19999999999999998,
22433
+ output: 0.5,
22434
+ cacheRead: 0.04,
22435
+ cacheWrite: 0,
22436
+ },
22437
+ contextWindow: 1048576,
22438
+ maxTokens: 1048576,
22439
+ },
22486
22440
  "nvidia/nemotron-nano-12b-v2-vl": {
22487
22441
  id: "nvidia/nemotron-nano-12b-v2-vl",
22488
22442
  name: "Nvidia Nemotron Nano 12B V2 VL",
@@ -22517,23 +22471,6 @@ export const MODELS = {
22517
22471
  contextWindow: 131072,
22518
22472
  maxTokens: 131072,
22519
22473
  },
22520
- "openai/gpt-3.5-turbo": {
22521
- id: "openai/gpt-3.5-turbo",
22522
- name: "GPT-3.5 Turbo",
22523
- api: "anthropic-messages",
22524
- provider: "vercel-ai-gateway",
22525
- baseUrl: "https://ai-gateway.vercel.sh",
22526
- reasoning: false,
22527
- input: ["text"],
22528
- cost: {
22529
- input: 0.5,
22530
- output: 1.5,
22531
- cacheRead: 0,
22532
- cacheWrite: 0,
22533
- },
22534
- contextWindow: 16385,
22535
- maxTokens: 4096,
22536
- },
22537
22474
  "openai/gpt-4.1": {
22538
22475
  id: "openai/gpt-4.1",
22539
22476
  name: "GPT-4.1",
@@ -22647,41 +22584,7 @@ export const MODELS = {
22647
22584
  cost: {
22648
22585
  input: 0.09999999999999999,
22649
22586
  output: 0.39999999999999997,
22650
- cacheRead: 0.024999999999999998,
22651
- cacheWrite: 0,
22652
- },
22653
- contextWindow: 1047576,
22654
- maxTokens: 32768,
22655
- },
22656
- "openai/gpt-4.1-nano-batch": {
22657
- id: "openai/gpt-4.1-nano-batch",
22658
- name: "GPT-4.1 nano (Batch)",
22659
- api: "anthropic-messages",
22660
- provider: "vercel-ai-gateway",
22661
- baseUrl: "https://ai-gateway.vercel.sh",
22662
- reasoning: false,
22663
- input: ["text", "image"],
22664
- cost: {
22665
- input: 0.049999999999999996,
22666
- output: 0.19999999999999998,
22667
- cacheRead: 0.012499999999999999,
22668
- cacheWrite: 0,
22669
- },
22670
- contextWindow: 1047576,
22671
- maxTokens: 32768,
22672
- },
22673
- "openai/gpt-4.1-nano-fast": {
22674
- id: "openai/gpt-4.1-nano-fast",
22675
- name: "GPT-4.1 nano (Fast)",
22676
- api: "anthropic-messages",
22677
- provider: "vercel-ai-gateway",
22678
- baseUrl: "https://ai-gateway.vercel.sh",
22679
- reasoning: false,
22680
- input: ["text", "image"],
22681
- cost: {
22682
- input: 0.19999999999999998,
22683
- output: 0.7999999999999999,
22684
- cacheRead: 0.049999999999999996,
22587
+ cacheRead: 0.03,
22685
22588
  cacheWrite: 0,
22686
22589
  },
22687
22590
  contextWindow: 1047576,
@@ -23796,6 +23699,40 @@ export const MODELS = {
23796
23699
  contextWindow: 1050000,
23797
23700
  maxTokens: 128000,
23798
23701
  },
23702
+ "openai/gpt-6.1-terra": {
23703
+ id: "openai/gpt-6.1-terra",
23704
+ name: "GPT-6.1 Terra",
23705
+ api: "anthropic-messages",
23706
+ provider: "vercel-ai-gateway",
23707
+ baseUrl: "https://ai-gateway.vercel.sh",
23708
+ reasoning: true,
23709
+ input: ["text", "image"],
23710
+ cost: {
23711
+ input: 1,
23712
+ output: 5,
23713
+ cacheRead: 0.049999999999999996,
23714
+ cacheWrite: 1.25,
23715
+ },
23716
+ contextWindow: 1050000,
23717
+ maxTokens: 128000,
23718
+ },
23719
+ "openai/gpt-6.1-terra-fast": {
23720
+ id: "openai/gpt-6.1-terra-fast",
23721
+ name: "GPT-6.1 Terra (Fast)",
23722
+ api: "anthropic-messages",
23723
+ provider: "vercel-ai-gateway",
23724
+ baseUrl: "https://ai-gateway.vercel.sh",
23725
+ reasoning: true,
23726
+ input: ["text", "image"],
23727
+ cost: {
23728
+ input: 2,
23729
+ output: 10,
23730
+ cacheRead: 0.09999999999999999,
23731
+ cacheWrite: 2.5,
23732
+ },
23733
+ contextWindow: 1050000,
23734
+ maxTokens: 128000,
23735
+ },
23799
23736
  "openai/gpt-oss-120b": {
23800
23737
  id: "openai/gpt-oss-120b",
23801
23738
  name: "GPT OSS 120B",
@@ -23966,22 +23903,22 @@ export const MODELS = {
23966
23903
  contextWindow: 200000,
23967
23904
  maxTokens: 100000,
23968
23905
  },
23969
- "openai/o4-mini-fast": {
23970
- id: "openai/o4-mini-fast",
23971
- name: "o4-mini (Fast)",
23906
+ "particle/particle-1": {
23907
+ id: "particle/particle-1",
23908
+ name: "Particle-1",
23972
23909
  api: "anthropic-messages",
23973
23910
  provider: "vercel-ai-gateway",
23974
23911
  baseUrl: "https://ai-gateway.vercel.sh",
23975
23912
  reasoning: true,
23976
23913
  input: ["text", "image"],
23977
23914
  cost: {
23978
- input: 2,
23979
- output: 8,
23980
- cacheRead: 0.5,
23915
+ input: 0.125,
23916
+ output: 0.5,
23917
+ cacheRead: 0.015,
23981
23918
  cacheWrite: 0,
23982
23919
  },
23983
- contextWindow: 200000,
23984
- maxTokens: 100000,
23920
+ contextWindow: 1048576,
23921
+ maxTokens: 131072,
23985
23922
  },
23986
23923
  "poolside/laguna-s-2.1": {
23987
23924
  id: "poolside/laguna-s-2.1",
@@ -24000,23 +23937,6 @@ export const MODELS = {
24000
23937
  contextWindow: 1000000,
24001
23938
  maxTokens: 131072,
24002
23939
  },
24003
- "poolside/laguna-s-2.1-free": {
24004
- id: "poolside/laguna-s-2.1-free",
24005
- name: "Laguna S 2.1 Free",
24006
- api: "anthropic-messages",
24007
- provider: "vercel-ai-gateway",
24008
- baseUrl: "https://ai-gateway.vercel.sh",
24009
- reasoning: true,
24010
- input: ["text"],
24011
- cost: {
24012
- input: 0,
24013
- output: 0,
24014
- cacheRead: 0,
24015
- cacheWrite: 0,
24016
- },
24017
- contextWindow: 256000,
24018
- maxTokens: 32768,
24019
- },
24020
23940
  "quiverai/arrow-2": {
24021
23941
  id: "quiverai/arrow-2",
24022
23942
  name: "Arrow 2",
@@ -24051,6 +23971,40 @@ export const MODELS = {
24051
23971
  contextWindow: 131072,
24052
23972
  maxTokens: 131072,
24053
23973
  },
23974
+ "reflection/beam": {
23975
+ id: "reflection/beam",
23976
+ name: "Beam 1.0",
23977
+ api: "anthropic-messages",
23978
+ provider: "vercel-ai-gateway",
23979
+ baseUrl: "https://ai-gateway.vercel.sh",
23980
+ reasoning: true,
23981
+ input: ["text"],
23982
+ cost: {
23983
+ input: 0,
23984
+ output: 0,
23985
+ cacheRead: 0,
23986
+ cacheWrite: 0,
23987
+ },
23988
+ contextWindow: 1048576,
23989
+ maxTokens: 131072,
23990
+ },
23991
+ "reflection/beam-free": {
23992
+ id: "reflection/beam-free",
23993
+ name: "Beam 1.0 (Free)",
23994
+ api: "anthropic-messages",
23995
+ provider: "vercel-ai-gateway",
23996
+ baseUrl: "https://ai-gateway.vercel.sh",
23997
+ reasoning: true,
23998
+ input: ["text"],
23999
+ cost: {
24000
+ input: 0,
24001
+ output: 0,
24002
+ cacheRead: 0,
24003
+ cacheWrite: 0,
24004
+ },
24005
+ contextWindow: 1048576,
24006
+ maxTokens: 131072,
24007
+ },
24054
24008
  "sakana/fugu-max": {
24055
24009
  id: "sakana/fugu-max",
24056
24010
  name: "Fugu Max",
@@ -24119,40 +24073,6 @@ export const MODELS = {
24119
24073
  contextWindow: 256000,
24120
24074
  maxTokens: 256000,
24121
24075
  },
24122
- "spacexai/grok-4.1-fast-non-reasoning": {
24123
- id: "spacexai/grok-4.1-fast-non-reasoning",
24124
- name: "Grok 4.1 Fast Non-Reasoning",
24125
- api: "anthropic-messages",
24126
- provider: "vercel-ai-gateway",
24127
- baseUrl: "https://ai-gateway.vercel.sh",
24128
- reasoning: false,
24129
- input: ["text", "image"],
24130
- cost: {
24131
- input: 0.19999999999999998,
24132
- output: 0.5,
24133
- cacheRead: 0.049999999999999996,
24134
- cacheWrite: 0,
24135
- },
24136
- contextWindow: 1000000,
24137
- maxTokens: 1000000,
24138
- },
24139
- "spacexai/grok-4.1-fast-reasoning": {
24140
- id: "spacexai/grok-4.1-fast-reasoning",
24141
- name: "Grok 4.1 Fast Reasoning",
24142
- api: "anthropic-messages",
24143
- provider: "vercel-ai-gateway",
24144
- baseUrl: "https://ai-gateway.vercel.sh",
24145
- reasoning: true,
24146
- input: ["text", "image"],
24147
- cost: {
24148
- input: 0.19999999999999998,
24149
- output: 0.5,
24150
- cacheRead: 0.049999999999999996,
24151
- cacheWrite: 0,
24152
- },
24153
- contextWindow: 1000000,
24154
- maxTokens: 1000000,
24155
- },
24156
24076
  "spacexai/grok-4.20-multi-agent": {
24157
24077
  id: "spacexai/grok-4.20-multi-agent",
24158
24078
  name: "Grok 4.20 Multi-Agent",
@@ -24408,6 +24328,23 @@ export const MODELS = {
24408
24328
  contextWindow: 256000,
24409
24329
  maxTokens: 256000,
24410
24330
  },
24331
+ "spacexai/grok-voice-3.0": {
24332
+ id: "spacexai/grok-voice-3.0",
24333
+ name: "Grok Voice 3.0",
24334
+ api: "anthropic-messages",
24335
+ provider: "vercel-ai-gateway",
24336
+ baseUrl: "https://ai-gateway.vercel.sh",
24337
+ reasoning: true,
24338
+ input: ["text"],
24339
+ cost: {
24340
+ input: 0,
24341
+ output: 0,
24342
+ cacheRead: 0,
24343
+ cacheWrite: 0,
24344
+ },
24345
+ contextWindow: 4096,
24346
+ maxTokens: 4096,
24347
+ },
24411
24348
  "stealth/glyph-cluster": {
24412
24349
  id: "stealth/glyph-cluster",
24413
24350
  name: "Glyph Cluster",
@@ -24442,6 +24379,23 @@ export const MODELS = {
24442
24379
  contextWindow: 256000,
24443
24380
  maxTokens: 256000,
24444
24381
  },
24382
+ "stepfun/step-5-preview": {
24383
+ id: "stepfun/step-5-preview",
24384
+ name: "Step 5 Preview",
24385
+ api: "anthropic-messages",
24386
+ provider: "vercel-ai-gateway",
24387
+ baseUrl: "https://ai-gateway.vercel.sh",
24388
+ reasoning: true,
24389
+ input: ["text", "image"],
24390
+ cost: {
24391
+ input: 1,
24392
+ output: 2.7,
24393
+ cacheRead: 0.09999999999999999,
24394
+ cacheWrite: 0,
24395
+ },
24396
+ contextWindow: 1048576,
24397
+ maxTokens: 1048576,
24398
+ },
24445
24399
  "tencent/hy3": {
24446
24400
  id: "tencent/hy3",
24447
24401
  name: "Hy3",
@@ -24519,9 +24473,9 @@ export const MODELS = {
24519
24473
  reasoning: true,
24520
24474
  input: ["text", "image"],
24521
24475
  cost: {
24522
- input: 0.14,
24523
- output: 0.28,
24524
- cacheRead: 0.0028,
24476
+ input: 0.119,
24477
+ output: 0.238,
24478
+ cacheRead: 0.0025,
24525
24479
  cacheWrite: 0,
24526
24480
  },
24527
24481
  contextWindow: 1050000,
@@ -24536,9 +24490,9 @@ export const MODELS = {
24536
24490
  reasoning: true,
24537
24491
  input: ["text"],
24538
24492
  cost: {
24539
- input: 0.435,
24540
- output: 0.87,
24541
- cacheRead: 0.0036,
24493
+ input: 0.3045,
24494
+ output: 0.609,
24495
+ cacheRead: 0.0028,
24542
24496
  cacheWrite: 0,
24543
24497
  },
24544
24498
  contextWindow: 1050000,