@dreb/ai 2.57.0 → 2.58.0

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.
@@ -767,6 +767,57 @@ export const MODELS = {
767
767
  contextWindow: 1000000,
768
768
  maxTokens: 128000,
769
769
  },
770
+ "global.openai.gpt-5.6-luna": {
771
+ id: "global.openai.gpt-5.6-luna",
772
+ name: "GPT-5.6 Luna (Global)",
773
+ api: "bedrock-converse-stream",
774
+ provider: "amazon-bedrock",
775
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
776
+ reasoning: true,
777
+ input: ["text", "image"],
778
+ cost: {
779
+ input: 0.22,
780
+ output: 1.32,
781
+ cacheRead: 0.022,
782
+ cacheWrite: 0.275,
783
+ },
784
+ contextWindow: 1050000,
785
+ maxTokens: 128000,
786
+ },
787
+ "global.openai.gpt-5.6-sol": {
788
+ id: "global.openai.gpt-5.6-sol",
789
+ name: "GPT-5.6 Sol (Global)",
790
+ api: "bedrock-converse-stream",
791
+ provider: "amazon-bedrock",
792
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
793
+ reasoning: true,
794
+ input: ["text", "image"],
795
+ cost: {
796
+ input: 5.5,
797
+ output: 33,
798
+ cacheRead: 0.55,
799
+ cacheWrite: 6.875,
800
+ },
801
+ contextWindow: 1050000,
802
+ maxTokens: 128000,
803
+ },
804
+ "global.openai.gpt-5.6-terra": {
805
+ id: "global.openai.gpt-5.6-terra",
806
+ name: "GPT-5.6 Terra (Global)",
807
+ api: "bedrock-converse-stream",
808
+ provider: "amazon-bedrock",
809
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
810
+ reasoning: true,
811
+ input: ["text", "image"],
812
+ cost: {
813
+ input: 2.2,
814
+ output: 13.2,
815
+ cacheRead: 0.22,
816
+ cacheWrite: 2.75,
817
+ },
818
+ contextWindow: 1050000,
819
+ maxTokens: 128000,
820
+ },
770
821
  "google.gemma-3-27b-it": {
771
822
  id: "google.gemma-3-27b-it",
772
823
  name: "Google Gemma 3 27B Instruct",
@@ -3175,6 +3226,25 @@ export const MODELS = {
3175
3226
  contextWindow: 1000000,
3176
3227
  maxTokens: 64000,
3177
3228
  },
3229
+ "gemini-3.7-flash": {
3230
+ id: "gemini-3.7-flash",
3231
+ name: "Gemini 3.7 Flash",
3232
+ api: "openai-completions",
3233
+ provider: "github-copilot",
3234
+ baseUrl: "https://api.individual.githubcopilot.com",
3235
+ 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" },
3236
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
3237
+ reasoning: true,
3238
+ input: ["text", "image"],
3239
+ cost: {
3240
+ input: 0.75,
3241
+ output: 3.75,
3242
+ cacheRead: 0.075,
3243
+ cacheWrite: 0,
3244
+ },
3245
+ contextWindow: 1000000,
3246
+ maxTokens: 64000,
3247
+ },
3178
3248
  "gpt-4.1": {
3179
3249
  id: "gpt-4.1",
3180
3250
  name: "GPT-4.1",
@@ -3411,6 +3481,25 @@ export const MODELS = {
3411
3481
  contextWindow: 500000,
3412
3482
  maxTokens: 128000,
3413
3483
  },
3484
+ "grok-4.6": {
3485
+ id: "grok-4.6",
3486
+ name: "Grok 4.6",
3487
+ api: "openai-completions",
3488
+ provider: "github-copilot",
3489
+ baseUrl: "https://api.individual.githubcopilot.com",
3490
+ 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" },
3491
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
3492
+ reasoning: true,
3493
+ input: ["text", "image"],
3494
+ cost: {
3495
+ input: 2,
3496
+ output: 6,
3497
+ cacheRead: 0.5,
3498
+ cacheWrite: 0,
3499
+ },
3500
+ contextWindow: 500000,
3501
+ maxTokens: 128000,
3502
+ },
3414
3503
  "kimi-k2.7-code": {
3415
3504
  id: "kimi-k2.7-code",
3416
3505
  name: "Kimi K2.7 Code",
@@ -4524,6 +4613,24 @@ export const MODELS = {
4524
4613
  contextWindow: 524288,
4525
4614
  maxTokens: 128000,
4526
4615
  },
4616
+ "Qwen/Qwen2.5-Coder-32B-Instruct": {
4617
+ id: "Qwen/Qwen2.5-Coder-32B-Instruct",
4618
+ name: "Qwen2.5-Coder-32B-Instruct",
4619
+ api: "openai-completions",
4620
+ provider: "huggingface",
4621
+ baseUrl: "https://router.huggingface.co/v1",
4622
+ compat: { "supportsDeveloperRole": false },
4623
+ reasoning: false,
4624
+ input: ["text"],
4625
+ cost: {
4626
+ input: 0.06,
4627
+ output: 0.2,
4628
+ cacheRead: 0,
4629
+ cacheWrite: 0,
4630
+ },
4631
+ contextWindow: 131072,
4632
+ maxTokens: 8192,
4633
+ },
4527
4634
  "Qwen/Qwen3-235B-A22B": {
4528
4635
  id: "Qwen/Qwen3-235B-A22B",
4529
4636
  name: "Qwen3 235B-A22B",
@@ -4578,6 +4685,24 @@ export const MODELS = {
4578
4685
  contextWindow: 262144,
4579
4686
  maxTokens: 131072,
4580
4687
  },
4688
+ "Qwen/Qwen3-30B-A3B": {
4689
+ id: "Qwen/Qwen3-30B-A3B",
4690
+ name: "Qwen3 30B A3B",
4691
+ api: "openai-completions",
4692
+ provider: "huggingface",
4693
+ baseUrl: "https://router.huggingface.co/v1",
4694
+ compat: { "supportsDeveloperRole": false },
4695
+ reasoning: true,
4696
+ input: ["text"],
4697
+ cost: {
4698
+ input: 0.12,
4699
+ output: 0.5,
4700
+ cacheRead: 0,
4701
+ cacheWrite: 0,
4702
+ },
4703
+ contextWindow: 40960,
4704
+ maxTokens: 16384,
4705
+ },
4581
4706
  "Qwen/Qwen3-32B": {
4582
4707
  id: "Qwen/Qwen3-32B",
4583
4708
  name: "Qwen3 32B",
@@ -4812,6 +4937,24 @@ export const MODELS = {
4812
4937
  contextWindow: 262144,
4813
4938
  maxTokens: 65536,
4814
4939
  },
4940
+ "Qwen/Qwen3.8-2.4T-A95B": {
4941
+ id: "Qwen/Qwen3.8-2.4T-A95B",
4942
+ name: "Qwen3.8 2.4T A95B",
4943
+ api: "openai-completions",
4944
+ provider: "huggingface",
4945
+ baseUrl: "https://router.huggingface.co/v1",
4946
+ compat: { "supportsDeveloperRole": false },
4947
+ reasoning: true,
4948
+ input: ["text"],
4949
+ cost: {
4950
+ input: 2.5,
4951
+ output: 6.25,
4952
+ cacheRead: 0,
4953
+ cacheWrite: 0,
4954
+ },
4955
+ contextWindow: 262144,
4956
+ maxTokens: 131072,
4957
+ },
4815
4958
  "XiaomiMiMo/MiMo-V2-Flash": {
4816
4959
  id: "XiaomiMiMo/MiMo-V2-Flash",
4817
4960
  name: "MiMo-V2-Flash",
@@ -4920,6 +5063,24 @@ export const MODELS = {
4920
5063
  contextWindow: 64000,
4921
5064
  maxTokens: 8192,
4922
5065
  },
5066
+ "deepseek-ai/DeepSeek-V3-0324": {
5067
+ id: "deepseek-ai/DeepSeek-V3-0324",
5068
+ name: "DeepSeek V3 0324",
5069
+ api: "openai-completions",
5070
+ provider: "huggingface",
5071
+ baseUrl: "https://router.huggingface.co/v1",
5072
+ compat: { "supportsDeveloperRole": false },
5073
+ reasoning: false,
5074
+ input: ["text"],
5075
+ cost: {
5076
+ input: 0.27,
5077
+ output: 1.12,
5078
+ cacheRead: 0,
5079
+ cacheWrite: 0,
5080
+ },
5081
+ contextWindow: 163840,
5082
+ maxTokens: 163840,
5083
+ },
4923
5084
  "deepseek-ai/DeepSeek-V3.1": {
4924
5085
  id: "deepseek-ai/DeepSeek-V3.1",
4925
5086
  name: "DeepSeek-V3.1",
@@ -5010,6 +5171,24 @@ export const MODELS = {
5010
5171
  contextWindow: 1048576,
5011
5172
  maxTokens: 393216,
5012
5173
  },
5174
+ "deepseek-ai/DeepSeek-V4-Pro-0813": {
5175
+ id: "deepseek-ai/DeepSeek-V4-Pro-0813",
5176
+ name: "DeepSeek V4 Pro 0813",
5177
+ api: "openai-completions",
5178
+ provider: "huggingface",
5179
+ baseUrl: "https://router.huggingface.co/v1",
5180
+ compat: { "supportsDeveloperRole": false },
5181
+ reasoning: true,
5182
+ input: ["text"],
5183
+ cost: {
5184
+ input: 1.32,
5185
+ output: 3.96,
5186
+ cacheRead: 0,
5187
+ cacheWrite: 0,
5188
+ },
5189
+ contextWindow: 1000000,
5190
+ maxTokens: 384000,
5191
+ },
5013
5192
  "google/gemma-4-26B-A4B-it": {
5014
5193
  id: "google/gemma-4-26B-A4B-it",
5015
5194
  name: "Gemma 4 26B A4B IT",
@@ -5046,6 +5225,24 @@ export const MODELS = {
5046
5225
  contextWindow: 262144,
5047
5226
  maxTokens: 32768,
5048
5227
  },
5228
+ "meta-llama/Llama-3.1-8B-Instruct": {
5229
+ id: "meta-llama/Llama-3.1-8B-Instruct",
5230
+ name: "Llama-3.1-8B-Instruct",
5231
+ api: "openai-completions",
5232
+ provider: "huggingface",
5233
+ baseUrl: "https://router.huggingface.co/v1",
5234
+ compat: { "supportsDeveloperRole": false },
5235
+ reasoning: false,
5236
+ input: ["text"],
5237
+ cost: {
5238
+ input: 0.06,
5239
+ output: 0.06,
5240
+ cacheRead: 0,
5241
+ cacheWrite: 0,
5242
+ },
5243
+ contextWindow: 131072,
5244
+ maxTokens: 4096,
5245
+ },
5049
5246
  "meta-llama/Llama-3.3-70B-Instruct": {
5050
5247
  id: "meta-llama/Llama-3.3-70B-Instruct",
5051
5248
  name: "Llama-3.3-70B-Instruct",
@@ -8064,6 +8261,23 @@ export const MODELS = {
8064
8261
  contextWindow: 512000,
8065
8262
  maxTokens: 128000,
8066
8263
  },
8264
+ "muse-spark-1.2": {
8265
+ id: "muse-spark-1.2",
8266
+ name: "Muse Spark 1.2",
8267
+ api: "openai-responses",
8268
+ provider: "opencode",
8269
+ baseUrl: "https://opencode.ai/zen/v1",
8270
+ reasoning: true,
8271
+ input: ["text", "image"],
8272
+ cost: {
8273
+ input: 1.25,
8274
+ output: 4.25,
8275
+ cacheRead: 0.15,
8276
+ cacheWrite: 0,
8277
+ },
8278
+ contextWindow: 1048576,
8279
+ maxTokens: 131072,
8280
+ },
8067
8281
  "nemotron-3-ultra-free": {
8068
8282
  id: "nemotron-3-ultra-free",
8069
8283
  name: "Nemotron 3 Ultra Free",
@@ -8136,16 +8350,16 @@ export const MODELS = {
8136
8350
  "opencode-go": {
8137
8351
  "deepseek-v4-flash": {
8138
8352
  id: "deepseek-v4-flash",
8139
- name: "DeepSeek V4 Flash (2x usage)",
8353
+ name: "DeepSeek V4 Flash",
8140
8354
  api: "openai-completions",
8141
8355
  provider: "opencode-go",
8142
8356
  baseUrl: "https://opencode.ai/zen/go/v1",
8143
8357
  reasoning: true,
8144
8358
  input: ["text"],
8145
8359
  cost: {
8146
- input: 0.07,
8147
- output: 0.14,
8148
- cacheRead: 0.0014,
8360
+ input: 0.22,
8361
+ output: 0.66,
8362
+ cacheRead: 0.007,
8149
8363
  cacheWrite: 0,
8150
8364
  },
8151
8365
  contextWindow: 1000000,
@@ -8160,9 +8374,9 @@ export const MODELS = {
8160
8374
  reasoning: true,
8161
8375
  input: ["text"],
8162
8376
  cost: {
8163
- input: 0.435,
8164
- output: 0.87,
8165
- cacheRead: 0.003625,
8377
+ input: 0.66,
8378
+ output: 1.98,
8379
+ cacheRead: 0.022,
8166
8380
  cacheWrite: 0,
8167
8381
  },
8168
8382
  contextWindow: 1000000,
@@ -8202,6 +8416,23 @@ export const MODELS = {
8202
8416
  contextWindow: 1000000,
8203
8417
  maxTokens: 131072,
8204
8418
  },
8419
+ "glm-5.3": {
8420
+ id: "glm-5.3",
8421
+ name: "GLM-5.3",
8422
+ api: "openai-completions",
8423
+ provider: "opencode-go",
8424
+ baseUrl: "https://opencode.ai/zen/go/v1",
8425
+ reasoning: true,
8426
+ input: ["text"],
8427
+ cost: {
8428
+ input: 1.4,
8429
+ output: 4.4,
8430
+ cacheRead: 0.26,
8431
+ cacheWrite: 0,
8432
+ },
8433
+ contextWindow: 1000000,
8434
+ maxTokens: 131072,
8435
+ },
8205
8436
  "gpt-5.6-luna": {
8206
8437
  id: "gpt-5.6-luna",
8207
8438
  name: "GPT-5.6 Luna (2x usage)",
@@ -8375,9 +8606,9 @@ export const MODELS = {
8375
8606
  "qwen3.6-plus": {
8376
8607
  id: "qwen3.6-plus",
8377
8608
  name: "Qwen3.6 Plus",
8378
- api: "anthropic-messages",
8609
+ api: "openai-completions",
8379
8610
  provider: "opencode-go",
8380
- baseUrl: "https://opencode.ai/zen/go",
8611
+ baseUrl: "https://opencode.ai/zen/go/v1",
8381
8612
  reasoning: true,
8382
8613
  input: ["text", "image"],
8383
8614
  cost: {
@@ -8392,9 +8623,9 @@ export const MODELS = {
8392
8623
  "qwen3.7-max": {
8393
8624
  id: "qwen3.7-max",
8394
8625
  name: "Qwen3.7 Max",
8395
- api: "anthropic-messages",
8626
+ api: "openai-completions",
8396
8627
  provider: "opencode-go",
8397
- baseUrl: "https://opencode.ai/zen/go",
8628
+ baseUrl: "https://opencode.ai/zen/go/v1",
8398
8629
  reasoning: true,
8399
8630
  input: ["text"],
8400
8631
  cost: {
@@ -8409,9 +8640,9 @@ export const MODELS = {
8409
8640
  "qwen3.7-plus": {
8410
8641
  id: "qwen3.7-plus",
8411
8642
  name: "Qwen3.7 Plus",
8412
- api: "anthropic-messages",
8643
+ api: "openai-completions",
8413
8644
  provider: "opencode-go",
8414
- baseUrl: "https://opencode.ai/zen/go",
8645
+ baseUrl: "https://opencode.ai/zen/go/v1",
8415
8646
  reasoning: true,
8416
8647
  input: ["text", "image"],
8417
8648
  cost: {
@@ -8426,9 +8657,9 @@ export const MODELS = {
8426
8657
  "qwen3.8-max": {
8427
8658
  id: "qwen3.8-max",
8428
8659
  name: "Qwen3.8 Max",
8429
- api: "anthropic-messages",
8660
+ api: "openai-completions",
8430
8661
  provider: "opencode-go",
8431
- baseUrl: "https://opencode.ai/zen/go",
8662
+ baseUrl: "https://opencode.ai/zen/go/v1",
8432
8663
  reasoning: true,
8433
8664
  input: ["text", "image"],
8434
8665
  cost: {
@@ -9370,12 +9601,12 @@ export const MODELS = {
9370
9601
  input: ["text"],
9371
9602
  cost: {
9372
9603
  input: 0.27,
9373
- output: 0.95,
9374
- cacheRead: 0.13,
9604
+ output: 1,
9605
+ cacheRead: 0,
9375
9606
  cacheWrite: 0,
9376
9607
  },
9377
9608
  contextWindow: 163840,
9378
- maxTokens: 32768,
9609
+ maxTokens: 163840,
9379
9610
  },
9380
9611
  "deepseek/deepseek-v3.2": {
9381
9612
  id: "deepseek/deepseek-v3.2",
@@ -9420,13 +9651,13 @@ export const MODELS = {
9420
9651
  reasoning: true,
9421
9652
  input: ["text"],
9422
9653
  cost: {
9423
- input: 0.14,
9424
- output: 0.28,
9425
- cacheRead: 0.028,
9654
+ input: 0.077,
9655
+ output: 0.154,
9656
+ cacheRead: 0.015399999999999999,
9426
9657
  cacheWrite: 0,
9427
9658
  },
9428
9659
  contextWindow: 1048576,
9429
- maxTokens: 393216,
9660
+ maxTokens: 384000,
9430
9661
  },
9431
9662
  "deepseek/deepseek-v4-flash-0731": {
9432
9663
  id: "deepseek/deepseek-v4-flash-0731",
@@ -9437,30 +9668,30 @@ export const MODELS = {
9437
9668
  reasoning: true,
9438
9669
  input: ["text"],
9439
9670
  cost: {
9440
- input: 0.08,
9441
- output: 0.18,
9442
- cacheRead: 0.016,
9671
+ input: 0.14,
9672
+ output: 0.28,
9673
+ cacheRead: 0.028,
9443
9674
  cacheWrite: 0,
9444
9675
  },
9445
- contextWindow: 1048576,
9446
- maxTokens: 384000,
9676
+ contextWindow: 1310720,
9677
+ maxTokens: 393216,
9447
9678
  },
9448
9679
  "deepseek/deepseek-v4-pro": {
9449
9680
  id: "deepseek/deepseek-v4-pro",
9450
- name: "DeepSeek: DeepSeek V4 Pro",
9681
+ name: "DeepSeek: DeepSeek V4 Pro 0423",
9451
9682
  api: "openai-completions",
9452
9683
  provider: "openrouter",
9453
9684
  baseUrl: "https://openrouter.ai/api/v1",
9454
9685
  reasoning: true,
9455
9686
  input: ["text"],
9456
9687
  cost: {
9457
- input: 1.1680000000000001,
9458
- output: 2.3360000000000003,
9459
- cacheRead: 0.09855000000000001,
9688
+ input: 0.66,
9689
+ output: 1.9800000000000002,
9690
+ cacheRead: 0.022,
9460
9691
  cacheWrite: 0,
9461
9692
  },
9462
9693
  contextWindow: 1048576,
9463
- maxTokens: 393216,
9694
+ maxTokens: 384000,
9464
9695
  },
9465
9696
  "deepseek/deepseek-v4-pro-0813": {
9466
9697
  id: "deepseek/deepseek-v4-pro-0813",
@@ -9471,14 +9702,31 @@ export const MODELS = {
9471
9702
  reasoning: true,
9472
9703
  input: ["text"],
9473
9704
  cost: {
9474
- input: 0.435,
9475
- output: 0.87,
9476
- cacheRead: 0.003625,
9705
+ input: 0.66,
9706
+ output: 1.9800000000000002,
9707
+ cacheRead: 0.022,
9477
9708
  cacheWrite: 0,
9478
9709
  },
9479
9710
  contextWindow: 1048576,
9480
9711
  maxTokens: 384000,
9481
9712
  },
9713
+ "dots-studio/dots-3-note-preview:free": {
9714
+ id: "dots-studio/dots-3-note-preview:free",
9715
+ name: "Dots Studio: Dots3-Note Preview (free)",
9716
+ api: "openai-completions",
9717
+ provider: "openrouter",
9718
+ baseUrl: "https://openrouter.ai/api/v1",
9719
+ reasoning: true,
9720
+ input: ["text", "image"],
9721
+ cost: {
9722
+ input: 0,
9723
+ output: 0,
9724
+ cacheRead: 0,
9725
+ cacheWrite: 0,
9726
+ },
9727
+ contextWindow: 512000,
9728
+ maxTokens: 512000,
9729
+ },
9482
9730
  "google/gemini-2.5-flash": {
9483
9731
  id: "google/gemini-2.5-flash",
9484
9732
  name: "Google: Gemini 2.5 Flash",
@@ -9947,13 +10195,13 @@ export const MODELS = {
9947
10195
  reasoning: true,
9948
10196
  input: ["text", "image"],
9949
10197
  cost: {
9950
- input: 0.12,
9951
- output: 0.39999999999999997,
9952
- cacheRead: 0.049999999999999996,
10198
+ input: 0.07,
10199
+ output: 0.33999999999999997,
10200
+ cacheRead: 0,
9953
10201
  cacheWrite: 0,
9954
10202
  },
9955
10203
  contextWindow: 262144,
9956
- maxTokens: 262144,
10204
+ maxTokens: 16384,
9957
10205
  },
9958
10206
  "google/gemma-4-26b-a4b-it:free": {
9959
10207
  id: "google/gemma-4-26b-a4b-it:free",
@@ -10174,7 +10422,7 @@ export const MODELS = {
10174
10422
  cacheWrite: 0,
10175
10423
  },
10176
10424
  contextWindow: 128000,
10177
- maxTokens: 32768,
10425
+ maxTokens: 8192,
10178
10426
  },
10179
10427
  "meituan/longcat-2.0": {
10180
10428
  id: "meituan/longcat-2.0",
@@ -10254,12 +10502,12 @@ export const MODELS = {
10254
10502
  input: ["text", "image"],
10255
10503
  cost: {
10256
10504
  input: 0.19999999999999998,
10257
- output: 0.696,
10505
+ output: 0.7999999999999999,
10258
10506
  cacheRead: 0,
10259
10507
  cacheWrite: 0,
10260
10508
  },
10261
10509
  contextWindow: 1048576,
10262
- maxTokens: 4096,
10510
+ maxTokens: 16384,
10263
10511
  },
10264
10512
  "meta-llama/llama-4-scout": {
10265
10513
  id: "meta-llama/llama-4-scout",
@@ -10814,8 +11062,8 @@ export const MODELS = {
10814
11062
  reasoning: true,
10815
11063
  input: ["text", "image"],
10816
11064
  cost: {
10817
- input: 0.67,
10818
- output: 3.4,
11065
+ input: 0.71,
11066
+ output: 3.5,
10819
11067
  cacheRead: 0.15,
10820
11068
  cacheWrite: 0,
10821
11069
  },
@@ -10901,11 +11149,11 @@ export const MODELS = {
10901
11149
  cost: {
10902
11150
  input: 0.049999999999999996,
10903
11151
  output: 0.19999999999999998,
10904
- cacheRead: 0.024999999999999998,
11152
+ cacheRead: 0.03,
10905
11153
  cacheWrite: 0,
10906
11154
  },
10907
11155
  contextWindow: 262144,
10908
- maxTokens: 228000,
11156
+ maxTokens: 262144,
10909
11157
  },
10910
11158
  "nvidia/nemotron-3-nano-30b-a3b:free": {
10911
11159
  id: "nvidia/nemotron-3-nano-30b-a3b:free",
@@ -11035,13 +11283,13 @@ export const MODELS = {
11035
11283
  reasoning: true,
11036
11284
  input: ["text"],
11037
11285
  cost: {
11038
- input: 0.09999999999999999,
11039
- output: 0.25,
11040
- cacheRead: 0.049999999999999996,
11286
+ input: 0.08,
11287
+ output: 0.19999999999999998,
11288
+ cacheRead: 0.04,
11041
11289
  cacheWrite: 0,
11042
11290
  },
11043
11291
  contextWindow: 1000000,
11044
- maxTokens: 262144,
11292
+ maxTokens: 131072,
11045
11293
  },
11046
11294
  "nvidia/nemotron-3.5-lightning:free": {
11047
11295
  id: "nvidia/nemotron-3.5-lightning:free",
@@ -12021,10 +12269,10 @@ export const MODELS = {
12021
12269
  reasoning: true,
12022
12270
  input: ["text", "image"],
12023
12271
  cost: {
12024
- input: 0.09999999999999999,
12025
- output: 0.6,
12026
- cacheRead: 0.01,
12027
- cacheWrite: 0.125,
12272
+ input: 0.19999999999999998,
12273
+ output: 1.2,
12274
+ cacheRead: 0.02,
12275
+ cacheWrite: 0.25,
12028
12276
  },
12029
12277
  contextWindow: 1050000,
12030
12278
  maxTokens: 128000,
@@ -12038,10 +12286,10 @@ export const MODELS = {
12038
12286
  reasoning: true,
12039
12287
  input: ["text", "image"],
12040
12288
  cost: {
12041
- input: 0.09999999999999999,
12042
- output: 0.6,
12043
- cacheRead: 0.01,
12044
- cacheWrite: 0.125,
12289
+ input: 0.19999999999999998,
12290
+ output: 1.2,
12291
+ cacheRead: 0.02,
12292
+ cacheWrite: 0.25,
12045
12293
  },
12046
12294
  contextWindow: 1050000,
12047
12295
  maxTokens: 128000,
@@ -12089,10 +12337,10 @@ export const MODELS = {
12089
12337
  reasoning: true,
12090
12338
  input: ["text", "image"],
12091
12339
  cost: {
12092
- input: 5,
12093
- output: 30,
12094
- cacheRead: 0.5,
12095
- cacheWrite: 6.25,
12340
+ input: 2.5,
12341
+ output: 15,
12342
+ cacheRead: 0.25,
12343
+ cacheWrite: 3.125,
12096
12344
  },
12097
12345
  contextWindow: 1050000,
12098
12346
  maxTokens: 128000,
@@ -12106,10 +12354,10 @@ export const MODELS = {
12106
12354
  reasoning: true,
12107
12355
  input: ["text", "image"],
12108
12356
  cost: {
12109
- input: 5,
12110
- output: 30,
12111
- cacheRead: 0.5,
12112
- cacheWrite: 6.25,
12357
+ input: 2.5,
12358
+ output: 15,
12359
+ cacheRead: 0.25,
12360
+ cacheWrite: 3.125,
12113
12361
  },
12114
12362
  contextWindow: 1050000,
12115
12363
  maxTokens: 128000,
@@ -12123,9 +12371,9 @@ export const MODELS = {
12123
12371
  reasoning: true,
12124
12372
  input: ["text", "image"],
12125
12373
  cost: {
12126
- input: 2.5,
12127
- output: 15,
12128
- cacheRead: 0.25,
12374
+ input: 1.25,
12375
+ output: 7.5,
12376
+ cacheRead: 0.125,
12129
12377
  cacheWrite: 0,
12130
12378
  },
12131
12379
  contextWindow: 1050000,
@@ -12140,9 +12388,9 @@ export const MODELS = {
12140
12388
  reasoning: true,
12141
12389
  input: ["text", "image"],
12142
12390
  cost: {
12143
- input: 2.5,
12144
- output: 15,
12145
- cacheRead: 0.25,
12391
+ input: 1.25,
12392
+ output: 7.5,
12393
+ cacheRead: 0.125,
12146
12394
  cacheWrite: 0,
12147
12395
  },
12148
12396
  contextWindow: 1050000,
@@ -12157,10 +12405,10 @@ export const MODELS = {
12157
12405
  reasoning: true,
12158
12406
  input: ["text", "image"],
12159
12407
  cost: {
12160
- input: 1,
12161
- output: 6,
12162
- cacheRead: 0.09999999999999999,
12163
- cacheWrite: 1.25,
12408
+ input: 2,
12409
+ output: 12,
12410
+ cacheRead: 0.19999999999999998,
12411
+ cacheWrite: 2.5,
12164
12412
  },
12165
12413
  contextWindow: 1050000,
12166
12414
  maxTokens: 128000,
@@ -12174,10 +12422,10 @@ export const MODELS = {
12174
12422
  reasoning: true,
12175
12423
  input: ["text", "image"],
12176
12424
  cost: {
12177
- input: 1,
12178
- output: 6,
12179
- cacheRead: 0.09999999999999999,
12180
- cacheWrite: 1.25,
12425
+ input: 2,
12426
+ output: 12,
12427
+ cacheRead: 0.19999999999999998,
12428
+ cacheWrite: 2.5,
12181
12429
  },
12182
12430
  contextWindow: 1050000,
12183
12431
  maxTokens: 128000,
@@ -12786,10 +13034,10 @@ export const MODELS = {
12786
13034
  reasoning: true,
12787
13035
  input: ["text"],
12788
13036
  cost: {
12789
- input: 0.39999999999999997,
12790
- output: 1.2,
13037
+ input: 0.26,
13038
+ output: 0.78,
12791
13039
  cacheRead: 0,
12792
- cacheWrite: 0.5,
13040
+ cacheWrite: 0,
12793
13041
  },
12794
13042
  contextWindow: 1000000,
12795
13043
  maxTokens: 32768,
@@ -12871,13 +13119,13 @@ export const MODELS = {
12871
13119
  reasoning: true,
12872
13120
  input: ["text"],
12873
13121
  cost: {
12874
- input: 0.12,
12875
- output: 0.5,
13122
+ input: 0.13,
13123
+ output: 0.52,
12876
13124
  cacheRead: 0,
12877
13125
  cacheWrite: 0,
12878
13126
  },
12879
13127
  contextWindow: 131072,
12880
- maxTokens: 16384,
13128
+ maxTokens: 8192,
12881
13129
  },
12882
13130
  "qwen/qwen3-30b-a3b-instruct-2507": {
12883
13131
  id: "qwen/qwen3-30b-a3b-instruct-2507",
@@ -13109,9 +13357,9 @@ export const MODELS = {
13109
13357
  reasoning: false,
13110
13358
  input: ["text", "image"],
13111
13359
  cost: {
13112
- input: 0.26,
13113
- output: 1.04,
13114
- cacheRead: 0,
13360
+ input: 0.21,
13361
+ output: 1.9,
13362
+ cacheRead: 0.09999999999999999,
13115
13363
  cacheWrite: 0,
13116
13364
  },
13117
13365
  contextWindow: 262144,
@@ -13143,13 +13391,13 @@ export const MODELS = {
13143
13391
  reasoning: false,
13144
13392
  input: ["text", "image"],
13145
13393
  cost: {
13146
- input: 0.15,
13147
- output: 0.6,
13394
+ input: 0.13,
13395
+ output: 0.52,
13148
13396
  cacheRead: 0,
13149
13397
  cacheWrite: 0,
13150
13398
  },
13151
13399
  contextWindow: 262144,
13152
- maxTokens: 16384,
13400
+ maxTokens: 32768,
13153
13401
  },
13154
13402
  "qwen/qwen3-vl-30b-a3b-thinking": {
13155
13403
  id: "qwen/qwen3-vl-30b-a3b-thinking",
@@ -13262,13 +13510,13 @@ export const MODELS = {
13262
13510
  reasoning: true,
13263
13511
  input: ["text", "image"],
13264
13512
  cost: {
13265
- input: 0.25,
13266
- output: 1.25,
13267
- cacheRead: 0.25,
13513
+ input: 0.22499999999999998,
13514
+ output: 1.7999999999999998,
13515
+ cacheRead: 0.22499999999999998,
13268
13516
  cacheWrite: 0,
13269
13517
  },
13270
13518
  contextWindow: 262144,
13271
- maxTokens: 262144,
13519
+ maxTokens: 65536,
13272
13520
  },
13273
13521
  "qwen/qwen3.5-397b-a17b": {
13274
13522
  id: "qwen/qwen3.5-397b-a17b",
@@ -13279,13 +13527,13 @@ export const MODELS = {
13279
13527
  reasoning: true,
13280
13528
  input: ["text", "image"],
13281
13529
  cost: {
13282
- input: 0.5,
13283
- output: 3.5999999999999996,
13284
- cacheRead: 0.3,
13530
+ input: 0.39,
13531
+ output: 2.34,
13532
+ cacheRead: 0,
13285
13533
  cacheWrite: 0,
13286
13534
  },
13287
13535
  contextWindow: 262144,
13288
- maxTokens: 262144,
13536
+ maxTokens: 65536,
13289
13537
  },
13290
13538
  "qwen/qwen3.5-9b": {
13291
13539
  id: "qwen/qwen3.5-9b",
@@ -13364,13 +13612,13 @@ export const MODELS = {
13364
13612
  reasoning: true,
13365
13613
  input: ["text", "image"],
13366
13614
  cost: {
13367
- input: 0.6,
13368
- output: 3.5999999999999996,
13369
- cacheRead: 0.12,
13615
+ input: 0.28900000000000003,
13616
+ output: 2.4,
13617
+ cacheRead: 0,
13370
13618
  cacheWrite: 0,
13371
13619
  },
13372
13620
  contextWindow: 262144,
13373
- maxTokens: 262144,
13621
+ maxTokens: 131072,
13374
13622
  },
13375
13623
  "qwen/qwen3.6-35b-a3b": {
13376
13624
  id: "qwen/qwen3.6-35b-a3b",
@@ -13381,7 +13629,7 @@ export const MODELS = {
13381
13629
  reasoning: true,
13382
13630
  input: ["text", "image"],
13383
13631
  cost: {
13384
- input: 0.15,
13632
+ input: 0.14,
13385
13633
  output: 1,
13386
13634
  cacheRead: 0.049999999999999996,
13387
13635
  cacheWrite: 0,
@@ -13505,9 +13753,26 @@ export const MODELS = {
13505
13753
  cacheRead: 0.25,
13506
13754
  cacheWrite: 0,
13507
13755
  },
13508
- contextWindow: 1000000,
13756
+ contextWindow: 1048576,
13509
13757
  maxTokens: 262144,
13510
13758
  },
13759
+ "qwen/qwen3.8-27b": {
13760
+ id: "qwen/qwen3.8-27b",
13761
+ name: "Qwen: Qwen3.8 27B",
13762
+ api: "openai-completions",
13763
+ provider: "openrouter",
13764
+ baseUrl: "https://openrouter.ai/api/v1",
13765
+ reasoning: true,
13766
+ input: ["text", "image"],
13767
+ cost: {
13768
+ input: 0.44999999999999996,
13769
+ output: 3.1999999999999997,
13770
+ cacheRead: 0.049999999999999996,
13771
+ cacheWrite: 0,
13772
+ },
13773
+ contextWindow: 262144,
13774
+ maxTokens: 131072,
13775
+ },
13511
13776
  "qwen/qwen3.8-max": {
13512
13777
  id: "qwen/qwen3.8-max",
13513
13778
  name: "Qwen: Qwen3.8 Max",
@@ -13670,9 +13935,9 @@ export const MODELS = {
13670
13935
  reasoning: true,
13671
13936
  input: ["text"],
13672
13937
  cost: {
13673
- input: 0.063,
13674
- output: 0.21,
13675
- cacheRead: 0.020999999999999998,
13938
+ input: 0.18,
13939
+ output: 0.6,
13940
+ cacheRead: 0.06,
13676
13941
  cacheWrite: 0,
13677
13942
  },
13678
13943
  contextWindow: 262144,
@@ -14027,13 +14292,13 @@ export const MODELS = {
14027
14292
  reasoning: true,
14028
14293
  input: ["text"],
14029
14294
  cost: {
14030
- input: 0.95,
14031
- output: 2.5500000000000003,
14032
- cacheRead: 0.19999999999999998,
14295
+ input: 0.6,
14296
+ output: 1.92,
14297
+ cacheRead: 0.12,
14033
14298
  cacheWrite: 0,
14034
14299
  },
14035
14300
  contextWindow: 204800,
14036
- maxTokens: 131072,
14301
+ maxTokens: 128000,
14037
14302
  },
14038
14303
  "z-ai/glm-5-turbo": {
14039
14304
  id: "z-ai/glm-5-turbo",
@@ -14061,13 +14326,13 @@ export const MODELS = {
14061
14326
  reasoning: true,
14062
14327
  input: ["text"],
14063
14328
  cost: {
14064
- input: 0.952,
14065
- output: 2.992,
14066
- cacheRead: 0.17679999999999998,
14329
+ input: 0.966,
14330
+ output: 3.036,
14331
+ cacheRead: 0.1794,
14067
14332
  cacheWrite: 0,
14068
14333
  },
14069
14334
  contextWindow: 204800,
14070
- maxTokens: 131072,
14335
+ maxTokens: 128000,
14071
14336
  },
14072
14337
  "z-ai/glm-5.2": {
14073
14338
  id: "z-ai/glm-5.2",
@@ -14078,9 +14343,9 @@ export const MODELS = {
14078
14343
  reasoning: true,
14079
14344
  input: ["text"],
14080
14345
  cost: {
14081
- input: 0.392,
14082
- output: 1.232,
14083
- cacheRead: 0.0728,
14346
+ input: 0.476,
14347
+ output: 1.496,
14348
+ cacheRead: 0.08839999999999999,
14084
14349
  cacheWrite: 0,
14085
14350
  },
14086
14351
  contextWindow: 1048576,
@@ -14197,13 +14462,13 @@ export const MODELS = {
14197
14462
  reasoning: true,
14198
14463
  input: ["text"],
14199
14464
  cost: {
14200
- input: 0.072,
14201
- output: 0.144,
14202
- cacheRead: 0.016,
14465
+ input: 0.0784,
14466
+ output: 0.1568,
14467
+ cacheRead: 0.01568,
14203
14468
  cacheWrite: 0,
14204
14469
  },
14205
- contextWindow: 1048576,
14206
- maxTokens: 262144,
14470
+ contextWindow: 1310720,
14471
+ maxTokens: 384000,
14207
14472
  },
14208
14473
  "~google/gemini-flash-latest": {
14209
14474
  id: "~google/gemini-flash-latest",
@@ -14248,9 +14513,9 @@ export const MODELS = {
14248
14513
  reasoning: true,
14249
14514
  input: ["text", "image"],
14250
14515
  cost: {
14251
- input: 2.4,
14252
- output: 12,
14253
- cacheRead: 0.24,
14516
+ input: 2.6,
14517
+ output: 13,
14518
+ cacheRead: 0.29,
14254
14519
  cacheWrite: 0,
14255
14520
  },
14256
14521
  contextWindow: 1048576,
@@ -14265,10 +14530,10 @@ export const MODELS = {
14265
14530
  reasoning: true,
14266
14531
  input: ["text", "image"],
14267
14532
  cost: {
14268
- input: 5,
14269
- output: 30,
14270
- cacheRead: 0.5,
14271
- cacheWrite: 6.25,
14533
+ input: 2.5,
14534
+ output: 15,
14535
+ cacheRead: 0.25,
14536
+ cacheWrite: 3.125,
14272
14537
  },
14273
14538
  contextWindow: 1050000,
14274
14539
  maxTokens: 128000,
@@ -14745,12 +15010,29 @@ export const MODELS = {
14745
15010
  cost: {
14746
15011
  input: 2,
14747
15012
  output: 6,
14748
- cacheRead: 0.25,
15013
+ cacheRead: 0.19999999999999998,
14749
15014
  cacheWrite: 0,
14750
15015
  },
14751
15016
  contextWindow: 262144,
14752
15017
  maxTokens: 131072,
14753
15018
  },
15019
+ "alibaba/qwen3.8-27b": {
15020
+ id: "alibaba/qwen3.8-27b",
15021
+ name: "Qwen3.8 27B",
15022
+ api: "anthropic-messages",
15023
+ provider: "vercel-ai-gateway",
15024
+ baseUrl: "https://ai-gateway.vercel.sh",
15025
+ reasoning: true,
15026
+ input: ["text", "image"],
15027
+ cost: {
15028
+ input: 0,
15029
+ output: 0,
15030
+ cacheRead: 0,
15031
+ cacheWrite: 0,
15032
+ },
15033
+ contextWindow: 262144,
15034
+ maxTokens: 262133,
15035
+ },
14754
15036
  "alibaba/qwen3.8-max": {
14755
15037
  id: "alibaba/qwen3.8-max",
14756
15038
  name: "Qwen 3.8 Max",
@@ -15287,9 +15569,9 @@ export const MODELS = {
15287
15569
  reasoning: true,
15288
15570
  input: ["text"],
15289
15571
  cost: {
15290
- input: 0.19999999999999998,
15291
- output: 0.39999999999999997,
15292
- cacheRead: 0.04,
15572
+ input: 0.13,
15573
+ output: 0.26,
15574
+ cacheRead: 0.028,
15293
15575
  cacheWrite: 0,
15294
15576
  },
15295
15577
  contextWindow: 1000000,
@@ -15304,9 +15586,9 @@ export const MODELS = {
15304
15586
  reasoning: true,
15305
15587
  input: ["text"],
15306
15588
  cost: {
15307
- input: 0.19999999999999998,
15308
- output: 0.39999999999999997,
15309
- cacheRead: 0.04,
15589
+ input: 0.13,
15590
+ output: 0.26,
15591
+ cacheRead: 0.028,
15310
15592
  cacheWrite: 0,
15311
15593
  },
15312
15594
  contextWindow: 1000000,
@@ -15338,9 +15620,9 @@ export const MODELS = {
15338
15620
  reasoning: true,
15339
15621
  input: ["text"],
15340
15622
  cost: {
15341
- input: 0.435,
15342
- output: 0.87,
15343
- cacheRead: 0.0036,
15623
+ input: 1.32,
15624
+ output: 3.9600000000000004,
15625
+ cacheRead: 0.13199999999999998,
15344
15626
  cacheWrite: 0,
15345
15627
  },
15346
15628
  contextWindow: 1000000,
@@ -15491,9 +15773,9 @@ export const MODELS = {
15491
15773
  reasoning: true,
15492
15774
  input: ["text", "image"],
15493
15775
  cost: {
15494
- input: 1.5,
15495
- output: 7.5,
15496
- cacheRead: 0.15,
15776
+ input: 0.75,
15777
+ output: 3.75,
15778
+ cacheRead: 0.075,
15497
15779
  cacheWrite: 0,
15498
15780
  },
15499
15781
  contextWindow: 1000000,
@@ -15601,23 +15883,6 @@ export const MODELS = {
15601
15883
  contextWindow: 256000,
15602
15884
  maxTokens: 32000,
15603
15885
  },
15604
- "inclusionai/ling-3.0-tiny-free": {
15605
- id: "inclusionai/ling-3.0-tiny-free",
15606
- name: "Ling 3.0 Tiny (Free)",
15607
- api: "anthropic-messages",
15608
- provider: "vercel-ai-gateway",
15609
- baseUrl: "https://ai-gateway.vercel.sh",
15610
- reasoning: true,
15611
- input: ["text"],
15612
- cost: {
15613
- input: 0,
15614
- output: 0,
15615
- cacheRead: 0,
15616
- cacheWrite: 0,
15617
- },
15618
- contextWindow: 256000,
15619
- maxTokens: 32000,
15620
- },
15621
15886
  "interfaze/interfaze-beta": {
15622
15887
  id: "interfaze/interfaze-beta",
15623
15888
  name: "Interfaze Beta",
@@ -16417,6 +16682,23 @@ export const MODELS = {
16417
16682
  contextWindow: 1000000,
16418
16683
  maxTokens: 65000,
16419
16684
  },
16685
+ "nvidia/nemotron-3.5-lightning": {
16686
+ id: "nvidia/nemotron-3.5-lightning",
16687
+ name: "Nemotron 3.5 Lightning 30B",
16688
+ api: "anthropic-messages",
16689
+ provider: "vercel-ai-gateway",
16690
+ baseUrl: "https://ai-gateway.vercel.sh",
16691
+ reasoning: true,
16692
+ input: ["text"],
16693
+ cost: {
16694
+ input: 0,
16695
+ output: 0,
16696
+ cacheRead: 0,
16697
+ cacheWrite: 0,
16698
+ },
16699
+ contextWindow: 262144,
16700
+ maxTokens: 131072,
16701
+ },
16420
16702
  "nvidia/nemotron-nano-12b-v2-vl": {
16421
16703
  id: "nvidia/nemotron-nano-12b-v2-vl",
16422
16704
  name: "Nvidia Nemotron Nano 12B V2 VL",
@@ -16919,10 +17201,10 @@ export const MODELS = {
16919
17201
  reasoning: true,
16920
17202
  input: ["text", "image"],
16921
17203
  cost: {
16922
- input: 5,
16923
- output: 30,
16924
- cacheRead: 0.5,
16925
- cacheWrite: 6.25,
17204
+ input: 2.5,
17205
+ output: 15,
17206
+ cacheRead: 0.25,
17207
+ cacheWrite: 3.125,
16926
17208
  },
16927
17209
  contextWindow: 1050000,
16928
17210
  maxTokens: 128000,
@@ -17427,7 +17709,7 @@ export const MODELS = {
17427
17709
  provider: "vercel-ai-gateway",
17428
17710
  baseUrl: "https://ai-gateway.vercel.sh",
17429
17711
  reasoning: true,
17430
- input: ["text"],
17712
+ input: ["text", "image"],
17431
17713
  cost: {
17432
17714
  input: 2,
17433
17715
  output: 6,