@dreb/ai 2.45.4 → 2.46.0

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.
@@ -5147,6 +5147,24 @@ export const MODELS = {
5147
5147
  contextWindow: 262144,
5148
5148
  maxTokens: 262144,
5149
5149
  },
5150
+ "moonshotai/Kimi-K3": {
5151
+ id: "moonshotai/Kimi-K3",
5152
+ name: "Kimi K3",
5153
+ api: "openai-completions",
5154
+ provider: "huggingface",
5155
+ baseUrl: "https://router.huggingface.co/v1",
5156
+ compat: { "supportsDeveloperRole": false },
5157
+ reasoning: true,
5158
+ input: ["text", "image"],
5159
+ cost: {
5160
+ input: 3,
5161
+ output: 15,
5162
+ cacheRead: 0,
5163
+ cacheWrite: 0,
5164
+ },
5165
+ contextWindow: 1000000,
5166
+ maxTokens: 131072,
5167
+ },
5150
5168
  "openai/gpt-oss-120b": {
5151
5169
  id: "openai/gpt-oss-120b",
5152
5170
  name: "GPT OSS 120B",
@@ -5219,6 +5237,42 @@ export const MODELS = {
5219
5237
  contextWindow: 262144,
5220
5238
  maxTokens: 256000,
5221
5239
  },
5240
+ "tencent/Hy3": {
5241
+ id: "tencent/Hy3",
5242
+ name: "Hy3",
5243
+ api: "openai-completions",
5244
+ provider: "huggingface",
5245
+ baseUrl: "https://router.huggingface.co/v1",
5246
+ compat: { "supportsDeveloperRole": false },
5247
+ reasoning: true,
5248
+ input: ["text"],
5249
+ cost: {
5250
+ input: 0.14,
5251
+ output: 0.58,
5252
+ cacheRead: 0,
5253
+ cacheWrite: 0,
5254
+ },
5255
+ contextWindow: 262144,
5256
+ maxTokens: 64000,
5257
+ },
5258
+ "thinkingmachines/Inkling": {
5259
+ id: "thinkingmachines/Inkling",
5260
+ name: "Inkling",
5261
+ api: "openai-completions",
5262
+ provider: "huggingface",
5263
+ baseUrl: "https://router.huggingface.co/v1",
5264
+ compat: { "supportsDeveloperRole": false },
5265
+ reasoning: true,
5266
+ input: ["text", "image"],
5267
+ cost: {
5268
+ input: 1,
5269
+ output: 4.05,
5270
+ cacheRead: 0,
5271
+ cacheWrite: 0,
5272
+ },
5273
+ contextWindow: 1048576,
5274
+ maxTokens: 1048576,
5275
+ },
5222
5276
  "zai-org/GLM-4.5": {
5223
5277
  id: "zai-org/GLM-4.5",
5224
5278
  name: "GLM-4.5",
@@ -8464,6 +8518,23 @@ export const MODELS = {
8464
8518
  contextWindow: 1000000,
8465
8519
  maxTokens: 128000,
8466
8520
  },
8521
+ "anthropic/claude-fable-5:batch": {
8522
+ id: "anthropic/claude-fable-5:batch",
8523
+ name: "Anthropic: Claude Fable 5 (batch)",
8524
+ api: "openai-completions",
8525
+ provider: "openrouter",
8526
+ baseUrl: "https://openrouter.ai/api/v1",
8527
+ reasoning: true,
8528
+ input: ["text", "image"],
8529
+ cost: {
8530
+ input: 5,
8531
+ output: 25,
8532
+ cacheRead: 0.5,
8533
+ cacheWrite: 6.25,
8534
+ },
8535
+ contextWindow: 1000000,
8536
+ maxTokens: 128000,
8537
+ },
8467
8538
  "anthropic/claude-haiku-4.5": {
8468
8539
  id: "anthropic/claude-haiku-4.5",
8469
8540
  name: "Anthropic: Claude Haiku 4.5",
@@ -8481,6 +8552,23 @@ export const MODELS = {
8481
8552
  contextWindow: 200000,
8482
8553
  maxTokens: 64000,
8483
8554
  },
8555
+ "anthropic/claude-haiku-4.5:batch": {
8556
+ id: "anthropic/claude-haiku-4.5:batch",
8557
+ name: "Anthropic: Claude Haiku 4.5 (batch)",
8558
+ api: "openai-completions",
8559
+ provider: "openrouter",
8560
+ baseUrl: "https://openrouter.ai/api/v1",
8561
+ reasoning: true,
8562
+ input: ["text", "image"],
8563
+ cost: {
8564
+ input: 0.5,
8565
+ output: 2.5,
8566
+ cacheRead: 0.049999999999999996,
8567
+ cacheWrite: 0.625,
8568
+ },
8569
+ contextWindow: 200000,
8570
+ maxTokens: 64000,
8571
+ },
8484
8572
  "anthropic/claude-opus-4": {
8485
8573
  id: "anthropic/claude-opus-4",
8486
8574
  name: "Anthropic: Claude Opus 4",
@@ -8515,6 +8603,23 @@ export const MODELS = {
8515
8603
  contextWindow: 200000,
8516
8604
  maxTokens: 32000,
8517
8605
  },
8606
+ "anthropic/claude-opus-4.1:batch": {
8607
+ id: "anthropic/claude-opus-4.1:batch",
8608
+ name: "Anthropic: Claude Opus 4.1 (batch)",
8609
+ api: "openai-completions",
8610
+ provider: "openrouter",
8611
+ baseUrl: "https://openrouter.ai/api/v1",
8612
+ reasoning: true,
8613
+ input: ["text", "image"],
8614
+ cost: {
8615
+ input: 7.5,
8616
+ output: 37.5,
8617
+ cacheRead: 0.75,
8618
+ cacheWrite: 9.375,
8619
+ },
8620
+ contextWindow: 200000,
8621
+ maxTokens: 32000,
8622
+ },
8518
8623
  "anthropic/claude-opus-4.5": {
8519
8624
  id: "anthropic/claude-opus-4.5",
8520
8625
  name: "Anthropic: Claude Opus 4.5",
@@ -8532,6 +8637,23 @@ export const MODELS = {
8532
8637
  contextWindow: 200000,
8533
8638
  maxTokens: 64000,
8534
8639
  },
8640
+ "anthropic/claude-opus-4.5:batch": {
8641
+ id: "anthropic/claude-opus-4.5:batch",
8642
+ name: "Anthropic: Claude Opus 4.5 (batch)",
8643
+ api: "openai-completions",
8644
+ provider: "openrouter",
8645
+ baseUrl: "https://openrouter.ai/api/v1",
8646
+ reasoning: true,
8647
+ input: ["text", "image"],
8648
+ cost: {
8649
+ input: 2.5,
8650
+ output: 12.5,
8651
+ cacheRead: 0.25,
8652
+ cacheWrite: 3.125,
8653
+ },
8654
+ contextWindow: 200000,
8655
+ maxTokens: 64000,
8656
+ },
8535
8657
  "anthropic/claude-opus-4.6": {
8536
8658
  id: "anthropic/claude-opus-4.6",
8537
8659
  name: "Anthropic: Claude Opus 4.6",
@@ -8549,6 +8671,23 @@ export const MODELS = {
8549
8671
  contextWindow: 1000000,
8550
8672
  maxTokens: 128000,
8551
8673
  },
8674
+ "anthropic/claude-opus-4.6:batch": {
8675
+ id: "anthropic/claude-opus-4.6:batch",
8676
+ name: "Anthropic: Claude Opus 4.6 (batch)",
8677
+ api: "openai-completions",
8678
+ provider: "openrouter",
8679
+ baseUrl: "https://openrouter.ai/api/v1",
8680
+ reasoning: true,
8681
+ input: ["text", "image"],
8682
+ cost: {
8683
+ input: 2.5,
8684
+ output: 12.5,
8685
+ cacheRead: 0.25,
8686
+ cacheWrite: 3.125,
8687
+ },
8688
+ contextWindow: 1000000,
8689
+ maxTokens: 128000,
8690
+ },
8552
8691
  "anthropic/claude-opus-4.7": {
8553
8692
  id: "anthropic/claude-opus-4.7",
8554
8693
  name: "Anthropic: Claude Opus 4.7",
@@ -8583,6 +8722,23 @@ export const MODELS = {
8583
8722
  contextWindow: 1000000,
8584
8723
  maxTokens: 128000,
8585
8724
  },
8725
+ "anthropic/claude-opus-4.7:batch": {
8726
+ id: "anthropic/claude-opus-4.7:batch",
8727
+ name: "Anthropic: Claude Opus 4.7 (batch)",
8728
+ api: "openai-completions",
8729
+ provider: "openrouter",
8730
+ baseUrl: "https://openrouter.ai/api/v1",
8731
+ reasoning: true,
8732
+ input: ["text", "image"],
8733
+ cost: {
8734
+ input: 2.5,
8735
+ output: 12.5,
8736
+ cacheRead: 0.25,
8737
+ cacheWrite: 3.125,
8738
+ },
8739
+ contextWindow: 1000000,
8740
+ maxTokens: 128000,
8741
+ },
8586
8742
  "anthropic/claude-opus-4.8": {
8587
8743
  id: "anthropic/claude-opus-4.8",
8588
8744
  name: "Anthropic: Claude Opus 4.8",
@@ -8617,6 +8773,23 @@ export const MODELS = {
8617
8773
  contextWindow: 1000000,
8618
8774
  maxTokens: 128000,
8619
8775
  },
8776
+ "anthropic/claude-opus-4.8:batch": {
8777
+ id: "anthropic/claude-opus-4.8:batch",
8778
+ name: "Anthropic: Claude Opus 4.8 (batch)",
8779
+ api: "openai-completions",
8780
+ provider: "openrouter",
8781
+ baseUrl: "https://openrouter.ai/api/v1",
8782
+ reasoning: true,
8783
+ input: ["text", "image"],
8784
+ cost: {
8785
+ input: 2.5,
8786
+ output: 12.5,
8787
+ cacheRead: 0.25,
8788
+ cacheWrite: 3.125,
8789
+ },
8790
+ contextWindow: 1000000,
8791
+ maxTokens: 128000,
8792
+ },
8620
8793
  "anthropic/claude-opus-5": {
8621
8794
  id: "anthropic/claude-opus-5",
8622
8795
  name: "Claude Opus 5",
@@ -8685,6 +8858,23 @@ export const MODELS = {
8685
8858
  contextWindow: 1000000,
8686
8859
  maxTokens: 64000,
8687
8860
  },
8861
+ "anthropic/claude-sonnet-4.5:batch": {
8862
+ id: "anthropic/claude-sonnet-4.5:batch",
8863
+ name: "Anthropic: Claude Sonnet 4.5 (batch)",
8864
+ api: "openai-completions",
8865
+ provider: "openrouter",
8866
+ baseUrl: "https://openrouter.ai/api/v1",
8867
+ reasoning: true,
8868
+ input: ["text", "image"],
8869
+ cost: {
8870
+ input: 1.5,
8871
+ output: 7.5,
8872
+ cacheRead: 0.15,
8873
+ cacheWrite: 1.875,
8874
+ },
8875
+ contextWindow: 1000000,
8876
+ maxTokens: 64000,
8877
+ },
8688
8878
  "anthropic/claude-sonnet-4.6": {
8689
8879
  id: "anthropic/claude-sonnet-4.6",
8690
8880
  name: "Anthropic: Claude Sonnet 4.6",
@@ -8719,6 +8909,23 @@ export const MODELS = {
8719
8909
  contextWindow: 1000000,
8720
8910
  maxTokens: 128000,
8721
8911
  },
8912
+ "anthropic/claude-sonnet-5:batch": {
8913
+ id: "anthropic/claude-sonnet-5:batch",
8914
+ name: "Anthropic: Claude Sonnet 5 (batch)",
8915
+ api: "openai-completions",
8916
+ provider: "openrouter",
8917
+ baseUrl: "https://openrouter.ai/api/v1",
8918
+ reasoning: true,
8919
+ input: ["text", "image"],
8920
+ cost: {
8921
+ input: 1,
8922
+ output: 5,
8923
+ cacheRead: 0.09999999999999999,
8924
+ cacheWrite: 1.25,
8925
+ },
8926
+ contextWindow: 1000000,
8927
+ maxTokens: 128000,
8928
+ },
8722
8929
  "arcee-ai/trinity-large-thinking": {
8723
8930
  id: "arcee-ai/trinity-large-thinking",
8724
8931
  name: "Arcee AI: Trinity Large Thinking",
@@ -8898,8 +9105,8 @@ export const MODELS = {
8898
9105
  reasoning: false,
8899
9106
  input: ["text"],
8900
9107
  cost: {
8901
- input: 0.20020000000000002,
8902
- output: 0.8000999999999999,
9108
+ input: 0.2574,
9109
+ output: 1.0287,
8903
9110
  cacheRead: 0,
8904
9111
  cacheWrite: 0,
8905
9112
  },
@@ -9093,6 +9300,40 @@ export const MODELS = {
9093
9300
  contextWindow: 1048576,
9094
9301
  maxTokens: 65535,
9095
9302
  },
9303
+ "google/gemini-2.5-flash-lite:batch": {
9304
+ id: "google/gemini-2.5-flash-lite:batch",
9305
+ name: "Google: Gemini 2.5 Flash Lite (batch)",
9306
+ api: "openai-completions",
9307
+ provider: "openrouter",
9308
+ baseUrl: "https://openrouter.ai/api/v1",
9309
+ reasoning: true,
9310
+ input: ["text", "image"],
9311
+ cost: {
9312
+ input: 0.049999999999999996,
9313
+ output: 0.19999999999999998,
9314
+ cacheRead: 0.01,
9315
+ cacheWrite: 0,
9316
+ },
9317
+ contextWindow: 1048576,
9318
+ maxTokens: 65535,
9319
+ },
9320
+ "google/gemini-2.5-flash:batch": {
9321
+ id: "google/gemini-2.5-flash:batch",
9322
+ name: "Google: Gemini 2.5 Flash (batch)",
9323
+ api: "openai-completions",
9324
+ provider: "openrouter",
9325
+ baseUrl: "https://openrouter.ai/api/v1",
9326
+ reasoning: true,
9327
+ input: ["text", "image"],
9328
+ cost: {
9329
+ input: 0.15,
9330
+ output: 1.25,
9331
+ cacheRead: 0.03,
9332
+ cacheWrite: 0,
9333
+ },
9334
+ contextWindow: 1048576,
9335
+ maxTokens: 65535,
9336
+ },
9096
9337
  "google/gemini-2.5-pro": {
9097
9338
  id: "google/gemini-2.5-pro",
9098
9339
  name: "Google: Gemini 2.5 Pro",
@@ -9144,6 +9385,23 @@ export const MODELS = {
9144
9385
  contextWindow: 1048576,
9145
9386
  maxTokens: 65535,
9146
9387
  },
9388
+ "google/gemini-2.5-pro:batch": {
9389
+ id: "google/gemini-2.5-pro:batch",
9390
+ name: "Google: Gemini 2.5 Pro (batch)",
9391
+ api: "openai-completions",
9392
+ provider: "openrouter",
9393
+ baseUrl: "https://openrouter.ai/api/v1",
9394
+ reasoning: true,
9395
+ input: ["text", "image"],
9396
+ cost: {
9397
+ input: 0.625,
9398
+ output: 5,
9399
+ cacheRead: 0.125,
9400
+ cacheWrite: 0,
9401
+ },
9402
+ contextWindow: 1048576,
9403
+ maxTokens: 65536,
9404
+ },
9147
9405
  "google/gemini-3-flash-preview": {
9148
9406
  id: "google/gemini-3-flash-preview",
9149
9407
  name: "Google: Gemini 3 Flash Preview",
@@ -9161,6 +9419,23 @@ export const MODELS = {
9161
9419
  contextWindow: 1048576,
9162
9420
  maxTokens: 65535,
9163
9421
  },
9422
+ "google/gemini-3-flash-preview:batch": {
9423
+ id: "google/gemini-3-flash-preview:batch",
9424
+ name: "Google: Gemini 3 Flash Preview (batch)",
9425
+ api: "openai-completions",
9426
+ provider: "openrouter",
9427
+ baseUrl: "https://openrouter.ai/api/v1",
9428
+ reasoning: true,
9429
+ input: ["text", "image"],
9430
+ cost: {
9431
+ input: 0.25,
9432
+ output: 1.5,
9433
+ cacheRead: 0,
9434
+ cacheWrite: 0,
9435
+ },
9436
+ contextWindow: 1048576,
9437
+ maxTokens: 65535,
9438
+ },
9164
9439
  "google/gemini-3-pro-image": {
9165
9440
  id: "google/gemini-3-pro-image",
9166
9441
  name: "Google: Nano Banana Pro (Gemini 3 Pro Image)",
@@ -9212,6 +9487,23 @@ export const MODELS = {
9212
9487
  contextWindow: 1048576,
9213
9488
  maxTokens: 65536,
9214
9489
  },
9490
+ "google/gemini-3.1-flash-lite:batch": {
9491
+ id: "google/gemini-3.1-flash-lite:batch",
9492
+ name: "Google: Gemini 3.1 Flash Lite (batch)",
9493
+ api: "openai-completions",
9494
+ provider: "openrouter",
9495
+ baseUrl: "https://openrouter.ai/api/v1",
9496
+ reasoning: true,
9497
+ input: ["text", "image"],
9498
+ cost: {
9499
+ input: 0.125,
9500
+ output: 0.75,
9501
+ cacheRead: 0.012499999999999999,
9502
+ cacheWrite: 0,
9503
+ },
9504
+ contextWindow: 1048576,
9505
+ maxTokens: 65536,
9506
+ },
9215
9507
  "google/gemini-3.1-pro-preview": {
9216
9508
  id: "google/gemini-3.1-pro-preview",
9217
9509
  name: "Google: Gemini 3.1 Pro Preview",
@@ -9246,6 +9538,23 @@ export const MODELS = {
9246
9538
  contextWindow: 1048576,
9247
9539
  maxTokens: 65536,
9248
9540
  },
9541
+ "google/gemini-3.1-pro-preview:batch": {
9542
+ id: "google/gemini-3.1-pro-preview:batch",
9543
+ name: "Google: Gemini 3.1 Pro Preview (batch)",
9544
+ api: "openai-completions",
9545
+ provider: "openrouter",
9546
+ baseUrl: "https://openrouter.ai/api/v1",
9547
+ reasoning: true,
9548
+ input: ["text", "image"],
9549
+ cost: {
9550
+ input: 1,
9551
+ output: 6,
9552
+ cacheRead: 0,
9553
+ cacheWrite: 0,
9554
+ },
9555
+ contextWindow: 1048576,
9556
+ maxTokens: 65536,
9557
+ },
9249
9558
  "google/gemini-3.5-flash": {
9250
9559
  id: "google/gemini-3.5-flash",
9251
9560
  name: "Google: Gemini 3.5 Flash",
@@ -9280,6 +9589,40 @@ export const MODELS = {
9280
9589
  contextWindow: 1048576,
9281
9590
  maxTokens: 65536,
9282
9591
  },
9592
+ "google/gemini-3.5-flash-lite:batch": {
9593
+ id: "google/gemini-3.5-flash-lite:batch",
9594
+ name: "Google: Gemini 3.5 Flash Lite (batch)",
9595
+ api: "openai-completions",
9596
+ provider: "openrouter",
9597
+ baseUrl: "https://openrouter.ai/api/v1",
9598
+ reasoning: true,
9599
+ input: ["text", "image"],
9600
+ cost: {
9601
+ input: 0.15,
9602
+ output: 1.25,
9603
+ cacheRead: 0.015,
9604
+ cacheWrite: 0,
9605
+ },
9606
+ contextWindow: 1048576,
9607
+ maxTokens: 65536,
9608
+ },
9609
+ "google/gemini-3.5-flash:batch": {
9610
+ id: "google/gemini-3.5-flash:batch",
9611
+ name: "Google: Gemini 3.5 Flash (batch)",
9612
+ api: "openai-completions",
9613
+ provider: "openrouter",
9614
+ baseUrl: "https://openrouter.ai/api/v1",
9615
+ reasoning: true,
9616
+ input: ["text", "image"],
9617
+ cost: {
9618
+ input: 0.75,
9619
+ output: 4.5,
9620
+ cacheRead: 0.075,
9621
+ cacheWrite: 0,
9622
+ },
9623
+ contextWindow: 1048576,
9624
+ maxTokens: 65536,
9625
+ },
9283
9626
  "google/gemini-3.6-flash": {
9284
9627
  id: "google/gemini-3.6-flash",
9285
9628
  name: "Google: Gemini 3.6 Flash",
@@ -9297,6 +9640,23 @@ export const MODELS = {
9297
9640
  contextWindow: 1048576,
9298
9641
  maxTokens: 65536,
9299
9642
  },
9643
+ "google/gemini-3.6-flash:batch": {
9644
+ id: "google/gemini-3.6-flash:batch",
9645
+ name: "Google: Gemini 3.6 Flash (batch)",
9646
+ api: "openai-completions",
9647
+ provider: "openrouter",
9648
+ baseUrl: "https://openrouter.ai/api/v1",
9649
+ reasoning: true,
9650
+ input: ["text", "image"],
9651
+ cost: {
9652
+ input: 0.75,
9653
+ output: 3.75,
9654
+ cacheRead: 0.075,
9655
+ cacheWrite: 0.08333333333333334,
9656
+ },
9657
+ contextWindow: 1048576,
9658
+ maxTokens: 65536,
9659
+ },
9300
9660
  "google/gemma-3-12b-it": {
9301
9661
  id: "google/gemma-3-12b-it",
9302
9662
  name: "Google: Gemma 3 12B",
@@ -9340,13 +9700,13 @@ export const MODELS = {
9340
9700
  reasoning: true,
9341
9701
  input: ["text", "image"],
9342
9702
  cost: {
9343
- input: 0.14,
9344
- output: 0.42,
9345
- cacheRead: 0.049999999999999996,
9703
+ input: 0.07,
9704
+ output: 0.33999999999999997,
9705
+ cacheRead: 0,
9346
9706
  cacheWrite: 0,
9347
9707
  },
9348
9708
  contextWindow: 262144,
9349
- maxTokens: 262144,
9709
+ maxTokens: 16384,
9350
9710
  },
9351
9711
  "google/gemma-4-26b-a4b-it:free": {
9352
9712
  id: "google/gemma-4-26b-a4b-it:free",
@@ -9374,9 +9734,9 @@ export const MODELS = {
9374
9734
  reasoning: true,
9375
9735
  input: ["text", "image"],
9376
9736
  cost: {
9377
- input: 0.14,
9378
- output: 0.39999999999999997,
9379
- cacheRead: 0,
9737
+ input: 0.09999999999999999,
9738
+ output: 0.33999999999999997,
9739
+ cacheRead: 0.09999999999999999,
9380
9740
  cacheWrite: 0,
9381
9741
  },
9382
9742
  contextWindow: 262144,
@@ -9773,6 +10133,23 @@ export const MODELS = {
9773
10133
  contextWindow: 1048576,
9774
10134
  maxTokens: 512000,
9775
10135
  },
10136
+ "minimax/minimax-m3:batch": {
10137
+ id: "minimax/minimax-m3:batch",
10138
+ name: "MiniMax: MiniMax M3 (batch)",
10139
+ api: "openai-completions",
10140
+ provider: "openrouter",
10141
+ baseUrl: "https://openrouter.ai/api/v1",
10142
+ reasoning: true,
10143
+ input: ["text", "image"],
10144
+ cost: {
10145
+ input: 0.15,
10146
+ output: 0.6,
10147
+ cacheRead: 0.03,
10148
+ cacheWrite: 0,
10149
+ },
10150
+ contextWindow: 524288,
10151
+ maxTokens: 4096,
10152
+ },
9776
10153
  "mistralai/codestral-2508": {
9777
10154
  id: "mistralai/codestral-2508",
9778
10155
  name: "Mistral: Codestral 2508",
@@ -10139,9 +10516,9 @@ export const MODELS = {
10139
10516
  reasoning: true,
10140
10517
  input: ["text", "image"],
10141
10518
  cost: {
10142
- input: 0.646,
10143
- output: 2.7199999999999998,
10144
- cacheRead: 0.1088,
10519
+ input: 0.95,
10520
+ output: 4,
10521
+ cacheRead: 0.16,
10145
10522
  cacheWrite: 0,
10146
10523
  },
10147
10524
  contextWindow: 262144,
@@ -10226,7 +10603,7 @@ export const MODELS = {
10226
10603
  cost: {
10227
10604
  input: 0.049999999999999996,
10228
10605
  output: 0.19999999999999998,
10229
- cacheRead: 0,
10606
+ cacheRead: 0.024999999999999998,
10230
10607
  cacheWrite: 0,
10231
10608
  },
10232
10609
  contextWindow: 262144,
@@ -10309,13 +10686,13 @@ export const MODELS = {
10309
10686
  reasoning: true,
10310
10687
  input: ["text"],
10311
10688
  cost: {
10312
- input: 0.5,
10313
- output: 2.2,
10314
- cacheRead: 0.09999999999999999,
10689
+ input: 0.6,
10690
+ output: 3.5999999999999996,
10691
+ cacheRead: 0.19999999999999998,
10315
10692
  cacheWrite: 0,
10316
10693
  },
10317
10694
  contextWindow: 512288,
10318
- maxTokens: 16384,
10695
+ maxTokens: 4096,
10319
10696
  },
10320
10697
  "nvidia/nemotron-3-ultra-550b-a55b:free": {
10321
10698
  id: "nvidia/nemotron-3-ultra-550b-a55b:free",
@@ -10640,35 +11017,35 @@ export const MODELS = {
10640
11017
  contextWindow: 400000,
10641
11018
  maxTokens: 128000,
10642
11019
  },
10643
- "openai/gpt-5-codex": {
10644
- id: "openai/gpt-5-codex",
10645
- name: "OpenAI: GPT-5 Codex",
11020
+ "openai/gpt-5-mini": {
11021
+ id: "openai/gpt-5-mini",
11022
+ name: "OpenAI: GPT-5 Mini",
10646
11023
  api: "openai-completions",
10647
11024
  provider: "openrouter",
10648
11025
  baseUrl: "https://openrouter.ai/api/v1",
10649
11026
  reasoning: true,
10650
11027
  input: ["text", "image"],
10651
11028
  cost: {
10652
- input: 1.25,
10653
- output: 10,
10654
- cacheRead: 0.125,
11029
+ input: 0.25,
11030
+ output: 2,
11031
+ cacheRead: 0.024999999999999998,
10655
11032
  cacheWrite: 0,
10656
11033
  },
10657
11034
  contextWindow: 400000,
10658
11035
  maxTokens: 128000,
10659
11036
  },
10660
- "openai/gpt-5-mini": {
10661
- id: "openai/gpt-5-mini",
10662
- name: "OpenAI: GPT-5 Mini",
11037
+ "openai/gpt-5-mini:batch": {
11038
+ id: "openai/gpt-5-mini:batch",
11039
+ name: "OpenAI: GPT-5 Mini (batch)",
10663
11040
  api: "openai-completions",
10664
11041
  provider: "openrouter",
10665
11042
  baseUrl: "https://openrouter.ai/api/v1",
10666
11043
  reasoning: true,
10667
11044
  input: ["text", "image"],
10668
11045
  cost: {
10669
- input: 0.25,
10670
- output: 2,
10671
- cacheRead: 0.024999999999999998,
11046
+ input: 0.125,
11047
+ output: 1,
11048
+ cacheRead: 0.012499999999999999,
10672
11049
  cacheWrite: 0,
10673
11050
  },
10674
11051
  contextWindow: 400000,
@@ -10691,6 +11068,23 @@ export const MODELS = {
10691
11068
  contextWindow: 400000,
10692
11069
  maxTokens: 128000,
10693
11070
  },
11071
+ "openai/gpt-5-nano:batch": {
11072
+ id: "openai/gpt-5-nano:batch",
11073
+ name: "OpenAI: GPT-5 Nano (batch)",
11074
+ api: "openai-completions",
11075
+ provider: "openrouter",
11076
+ baseUrl: "https://openrouter.ai/api/v1",
11077
+ reasoning: true,
11078
+ input: ["text", "image"],
11079
+ cost: {
11080
+ input: 0.024999999999999998,
11081
+ output: 0.19999999999999998,
11082
+ cacheRead: 0.0025,
11083
+ cacheWrite: 0,
11084
+ },
11085
+ contextWindow: 400000,
11086
+ maxTokens: 128000,
11087
+ },
10694
11088
  "openai/gpt-5-pro": {
10695
11089
  id: "openai/gpt-5-pro",
10696
11090
  name: "OpenAI: GPT-5 Pro",
@@ -10793,6 +11187,23 @@ export const MODELS = {
10793
11187
  contextWindow: 400000,
10794
11188
  maxTokens: 128000,
10795
11189
  },
11190
+ "openai/gpt-5.1:batch": {
11191
+ id: "openai/gpt-5.1:batch",
11192
+ name: "OpenAI: GPT-5.1 (batch)",
11193
+ api: "openai-completions",
11194
+ provider: "openrouter",
11195
+ baseUrl: "https://openrouter.ai/api/v1",
11196
+ reasoning: true,
11197
+ input: ["text", "image"],
11198
+ cost: {
11199
+ input: 0.625,
11200
+ output: 5,
11201
+ cacheRead: 0.0625,
11202
+ cacheWrite: 0,
11203
+ },
11204
+ contextWindow: 400000,
11205
+ maxTokens: 128000,
11206
+ },
10796
11207
  "openai/gpt-5.2": {
10797
11208
  id: "openai/gpt-5.2",
10798
11209
  name: "OpenAI: GPT-5.2",
@@ -10861,6 +11272,23 @@ export const MODELS = {
10861
11272
  contextWindow: 400000,
10862
11273
  maxTokens: 128000,
10863
11274
  },
11275
+ "openai/gpt-5.2:batch": {
11276
+ id: "openai/gpt-5.2:batch",
11277
+ name: "OpenAI: GPT-5.2 (batch)",
11278
+ api: "openai-completions",
11279
+ provider: "openrouter",
11280
+ baseUrl: "https://openrouter.ai/api/v1",
11281
+ reasoning: true,
11282
+ input: ["text", "image"],
11283
+ cost: {
11284
+ input: 0.875,
11285
+ output: 7,
11286
+ cacheRead: 0.0875,
11287
+ cacheWrite: 0,
11288
+ },
11289
+ contextWindow: 400000,
11290
+ maxTokens: 128000,
11291
+ },
10864
11292
  "openai/gpt-5.3-chat": {
10865
11293
  id: "openai/gpt-5.3-chat",
10866
11294
  name: "OpenAI: GPT-5.3 Chat",
@@ -10929,6 +11357,23 @@ export const MODELS = {
10929
11357
  contextWindow: 400000,
10930
11358
  maxTokens: 128000,
10931
11359
  },
11360
+ "openai/gpt-5.4-mini:batch": {
11361
+ id: "openai/gpt-5.4-mini:batch",
11362
+ name: "OpenAI: GPT-5.4 Mini (batch)",
11363
+ api: "openai-completions",
11364
+ provider: "openrouter",
11365
+ baseUrl: "https://openrouter.ai/api/v1",
11366
+ reasoning: true,
11367
+ input: ["text", "image"],
11368
+ cost: {
11369
+ input: 0.375,
11370
+ output: 2.25,
11371
+ cacheRead: 0.0375,
11372
+ cacheWrite: 0,
11373
+ },
11374
+ contextWindow: 400000,
11375
+ maxTokens: 128000,
11376
+ },
10932
11377
  "openai/gpt-5.4-nano": {
10933
11378
  id: "openai/gpt-5.4-nano",
10934
11379
  name: "OpenAI: GPT-5.4 Nano",
@@ -10946,18 +11391,52 @@ export const MODELS = {
10946
11391
  contextWindow: 400000,
10947
11392
  maxTokens: 128000,
10948
11393
  },
10949
- "openai/gpt-5.4-pro": {
10950
- id: "openai/gpt-5.4-pro",
10951
- name: "OpenAI: GPT-5.4 Pro",
11394
+ "openai/gpt-5.4-nano:batch": {
11395
+ id: "openai/gpt-5.4-nano:batch",
11396
+ name: "OpenAI: GPT-5.4 Nano (batch)",
11397
+ api: "openai-completions",
11398
+ provider: "openrouter",
11399
+ baseUrl: "https://openrouter.ai/api/v1",
11400
+ reasoning: true,
11401
+ input: ["text", "image"],
11402
+ cost: {
11403
+ input: 0.09999999999999999,
11404
+ output: 0.625,
11405
+ cacheRead: 0.01,
11406
+ cacheWrite: 0,
11407
+ },
11408
+ contextWindow: 400000,
11409
+ maxTokens: 128000,
11410
+ },
11411
+ "openai/gpt-5.4-pro": {
11412
+ id: "openai/gpt-5.4-pro",
11413
+ name: "OpenAI: GPT-5.4 Pro",
11414
+ api: "openai-completions",
11415
+ provider: "openrouter",
11416
+ baseUrl: "https://openrouter.ai/api/v1",
11417
+ reasoning: true,
11418
+ input: ["text", "image"],
11419
+ cost: {
11420
+ input: 30,
11421
+ output: 180,
11422
+ cacheRead: 0,
11423
+ cacheWrite: 0,
11424
+ },
11425
+ contextWindow: 1050000,
11426
+ maxTokens: 128000,
11427
+ },
11428
+ "openai/gpt-5.4:batch": {
11429
+ id: "openai/gpt-5.4:batch",
11430
+ name: "OpenAI: GPT-5.4 (batch)",
10952
11431
  api: "openai-completions",
10953
11432
  provider: "openrouter",
10954
11433
  baseUrl: "https://openrouter.ai/api/v1",
10955
11434
  reasoning: true,
10956
11435
  input: ["text", "image"],
10957
11436
  cost: {
10958
- input: 30,
10959
- output: 180,
10960
- cacheRead: 0,
11437
+ input: 1.25,
11438
+ output: 7.5,
11439
+ cacheRead: 0.125,
10961
11440
  cacheWrite: 0,
10962
11441
  },
10963
11442
  contextWindow: 1050000,
@@ -10997,6 +11476,23 @@ export const MODELS = {
10997
11476
  contextWindow: 1050000,
10998
11477
  maxTokens: 128000,
10999
11478
  },
11479
+ "openai/gpt-5.5:batch": {
11480
+ id: "openai/gpt-5.5:batch",
11481
+ name: "OpenAI: GPT-5.5 (batch)",
11482
+ api: "openai-completions",
11483
+ provider: "openrouter",
11484
+ baseUrl: "https://openrouter.ai/api/v1",
11485
+ reasoning: true,
11486
+ input: ["text", "image"],
11487
+ cost: {
11488
+ input: 2.5,
11489
+ output: 15,
11490
+ cacheRead: 0.25,
11491
+ cacheWrite: 0,
11492
+ },
11493
+ contextWindow: 1050000,
11494
+ maxTokens: 128000,
11495
+ },
11000
11496
  "openai/gpt-5.6-luna": {
11001
11497
  id: "openai/gpt-5.6-luna",
11002
11498
  name: "OpenAI: GPT-5.6 Luna",
@@ -11006,10 +11502,10 @@ export const MODELS = {
11006
11502
  reasoning: true,
11007
11503
  input: ["text", "image"],
11008
11504
  cost: {
11009
- input: 0.5,
11010
- output: 3,
11011
- cacheRead: 0.049999999999999996,
11012
- cacheWrite: 0.625,
11505
+ input: 0.09999999999999999,
11506
+ output: 0.6000000000000001,
11507
+ cacheRead: 0.01,
11508
+ cacheWrite: 0.12500000000000003,
11013
11509
  },
11014
11510
  contextWindow: 1050000,
11015
11511
  maxTokens: 128000,
@@ -11023,10 +11519,10 @@ export const MODELS = {
11023
11519
  reasoning: true,
11024
11520
  input: ["text", "image"],
11025
11521
  cost: {
11026
- input: 0.5,
11027
- output: 3,
11028
- cacheRead: 0.049999999999999996,
11029
- cacheWrite: 0.625,
11522
+ input: 0.09999999999999999,
11523
+ output: 0.6000000000000001,
11524
+ cacheRead: 0.01,
11525
+ cacheWrite: 0.12500000000000003,
11030
11526
  },
11031
11527
  contextWindow: 1050000,
11032
11528
  maxTokens: 128000,
@@ -11074,10 +11570,10 @@ export const MODELS = {
11074
11570
  reasoning: true,
11075
11571
  input: ["text", "image"],
11076
11572
  cost: {
11077
- input: 1.25,
11078
- output: 7.5,
11079
- cacheRead: 0.125,
11080
- cacheWrite: 1.5625,
11573
+ input: 1.0000000000000002,
11574
+ output: 6,
11575
+ cacheRead: 0.09999999999999999,
11576
+ cacheWrite: 1.25,
11081
11577
  },
11082
11578
  contextWindow: 1050000,
11083
11579
  maxTokens: 128000,
@@ -11091,14 +11587,31 @@ export const MODELS = {
11091
11587
  reasoning: true,
11092
11588
  input: ["text", "image"],
11093
11589
  cost: {
11094
- input: 1.25,
11095
- output: 7.5,
11096
- cacheRead: 0.125,
11097
- cacheWrite: 1.5625,
11590
+ input: 1.0000000000000002,
11591
+ output: 6,
11592
+ cacheRead: 0.09999999999999999,
11593
+ cacheWrite: 1.25,
11098
11594
  },
11099
11595
  contextWindow: 1050000,
11100
11596
  maxTokens: 128000,
11101
11597
  },
11598
+ "openai/gpt-5:batch": {
11599
+ id: "openai/gpt-5:batch",
11600
+ name: "OpenAI: GPT-5 (batch)",
11601
+ api: "openai-completions",
11602
+ provider: "openrouter",
11603
+ baseUrl: "https://openrouter.ai/api/v1",
11604
+ reasoning: true,
11605
+ input: ["text", "image"],
11606
+ cost: {
11607
+ input: 0.625,
11608
+ output: 5,
11609
+ cacheRead: 0.0625,
11610
+ cacheWrite: 0,
11611
+ },
11612
+ contextWindow: 400000,
11613
+ maxTokens: 128000,
11614
+ },
11102
11615
  "openai/gpt-audio": {
11103
11616
  id: "openai/gpt-audio",
11104
11617
  name: "OpenAI: GPT Audio",
@@ -11177,8 +11690,8 @@ export const MODELS = {
11177
11690
  input: ["text"],
11178
11691
  cost: {
11179
11692
  input: 0.03,
11180
- output: 0.14,
11181
- cacheRead: 0,
11693
+ output: 0.13,
11694
+ cacheRead: 0.03,
11182
11695
  cacheWrite: 0,
11183
11696
  },
11184
11697
  contextWindow: 131072,
@@ -11252,23 +11765,6 @@ export const MODELS = {
11252
11765
  contextWindow: 200000,
11253
11766
  maxTokens: 100000,
11254
11767
  },
11255
- "openai/o3-deep-research": {
11256
- id: "openai/o3-deep-research",
11257
- name: "OpenAI: o3 Deep Research",
11258
- api: "openai-completions",
11259
- provider: "openrouter",
11260
- baseUrl: "https://openrouter.ai/api/v1",
11261
- reasoning: true,
11262
- input: ["text", "image"],
11263
- cost: {
11264
- input: 10,
11265
- output: 40,
11266
- cacheRead: 2.5,
11267
- cacheWrite: 0,
11268
- },
11269
- contextWindow: 200000,
11270
- maxTokens: 100000,
11271
- },
11272
11768
  "openai/o3-mini": {
11273
11769
  id: "openai/o3-mini",
11274
11770
  name: "OpenAI: o3 Mini",
@@ -11337,23 +11833,6 @@ export const MODELS = {
11337
11833
  contextWindow: 200000,
11338
11834
  maxTokens: 100000,
11339
11835
  },
11340
- "openai/o4-mini-deep-research": {
11341
- id: "openai/o4-mini-deep-research",
11342
- name: "OpenAI: o4 Mini Deep Research",
11343
- api: "openai-completions",
11344
- provider: "openrouter",
11345
- baseUrl: "https://openrouter.ai/api/v1",
11346
- reasoning: true,
11347
- input: ["text", "image"],
11348
- cost: {
11349
- input: 2,
11350
- output: 8,
11351
- cacheRead: 0.5,
11352
- cacheWrite: 0,
11353
- },
11354
- contextWindow: 200000,
11355
- maxTokens: 100000,
11356
- },
11357
11836
  "openai/o4-mini-high": {
11358
11837
  id: "openai/o4-mini-high",
11359
11838
  name: "OpenAI: o4 Mini High",
@@ -11422,40 +11901,6 @@ export const MODELS = {
11422
11901
  contextWindow: 200000,
11423
11902
  maxTokens: 4096,
11424
11903
  },
11425
- "poolside/laguna-m.1": {
11426
- id: "poolside/laguna-m.1",
11427
- name: "Poolside: Laguna M.1",
11428
- api: "openai-completions",
11429
- provider: "openrouter",
11430
- baseUrl: "https://openrouter.ai/api/v1",
11431
- reasoning: true,
11432
- input: ["text"],
11433
- cost: {
11434
- input: 0.19999999999999998,
11435
- output: 0.39999999999999997,
11436
- cacheRead: 0.09999999999999999,
11437
- cacheWrite: 0,
11438
- },
11439
- contextWindow: 262144,
11440
- maxTokens: 32768,
11441
- },
11442
- "poolside/laguna-m.1:free": {
11443
- id: "poolside/laguna-m.1:free",
11444
- name: "Poolside: Laguna M.1 (free)",
11445
- api: "openai-completions",
11446
- provider: "openrouter",
11447
- baseUrl: "https://openrouter.ai/api/v1",
11448
- reasoning: true,
11449
- input: ["text"],
11450
- cost: {
11451
- input: 0,
11452
- output: 0,
11453
- cacheRead: 0,
11454
- cacheWrite: 0,
11455
- },
11456
- contextWindow: 262144,
11457
- maxTokens: 32768,
11458
- },
11459
11904
  "poolside/laguna-s-2.1": {
11460
11905
  id: "poolside/laguna-s-2.1",
11461
11906
  name: "Poolside: Laguna S 2.1",
@@ -11550,8 +11995,8 @@ export const MODELS = {
11550
11995
  reasoning: false,
11551
11996
  input: ["text"],
11552
11997
  cost: {
11553
- input: 0.04,
11554
- output: 0.09999999999999999,
11998
+ input: 0.09999999999999999,
11999
+ output: 0.19999999999999998,
11555
12000
  cacheRead: 0,
11556
12001
  cacheWrite: 0,
11557
12002
  },
@@ -11601,10 +12046,10 @@ export const MODELS = {
11601
12046
  reasoning: true,
11602
12047
  input: ["text"],
11603
12048
  cost: {
11604
- input: 0.26,
11605
- output: 0.78,
12049
+ input: 0.39999999999999997,
12050
+ output: 1.2,
11606
12051
  cacheRead: 0,
11607
- cacheWrite: 0.325,
12052
+ cacheWrite: 0.5,
11608
12053
  },
11609
12054
  contextWindow: 1000000,
11610
12055
  maxTokens: 32768,
@@ -11720,8 +12165,8 @@ export const MODELS = {
11720
12165
  reasoning: true,
11721
12166
  input: ["text"],
11722
12167
  cost: {
11723
- input: 0.13,
11724
- output: 1.56,
12168
+ input: 0.19999999999999998,
12169
+ output: 2.4,
11725
12170
  cacheRead: 0,
11726
12171
  cacheWrite: 0,
11727
12172
  },
@@ -11822,7 +12267,7 @@ export const MODELS = {
11822
12267
  reasoning: false,
11823
12268
  input: ["text"],
11824
12269
  cost: {
11825
- input: 0.11,
12270
+ input: 0.12,
11826
12271
  output: 0.7999999999999999,
11827
12272
  cacheRead: 0.07,
11828
12273
  cacheWrite: 0,
@@ -11862,7 +12307,7 @@ export const MODELS = {
11862
12307
  cacheWrite: 0.975,
11863
12308
  },
11864
12309
  contextWindow: 262144,
11865
- maxTokens: 32768,
12310
+ maxTokens: 65536,
11866
12311
  },
11867
12312
  "qwen/qwen3-max-thinking": {
11868
12313
  id: "qwen/qwen3-max-thinking",
@@ -11879,7 +12324,7 @@ export const MODELS = {
11879
12324
  cacheWrite: 0,
11880
12325
  },
11881
12326
  contextWindow: 262144,
11882
- maxTokens: 32768,
12327
+ maxTokens: 65536,
11883
12328
  },
11884
12329
  "qwen/qwen3-next-80b-a3b-instruct": {
11885
12330
  id: "qwen/qwen3-next-80b-a3b-instruct",
@@ -11907,8 +12352,8 @@ export const MODELS = {
11907
12352
  reasoning: true,
11908
12353
  input: ["text"],
11909
12354
  cost: {
11910
- input: 0.0975,
11911
- output: 0.78,
12355
+ input: 0.15,
12356
+ output: 1.2,
11912
12357
  cacheRead: 0,
11913
12358
  cacheWrite: 0,
11914
12359
  },
@@ -11941,8 +12386,8 @@ export const MODELS = {
11941
12386
  reasoning: true,
11942
12387
  input: ["text", "image"],
11943
12388
  cost: {
11944
- input: 0.26,
11945
- output: 2.6,
12389
+ input: 0.39999999999999997,
12390
+ output: 4,
11946
12391
  cacheRead: 0,
11947
12392
  cacheWrite: 0,
11948
12393
  },
@@ -11975,8 +12420,8 @@ export const MODELS = {
11975
12420
  reasoning: true,
11976
12421
  input: ["text", "image"],
11977
12422
  cost: {
11978
- input: 0.13,
11979
- output: 1.56,
12423
+ input: 0.19999999999999998,
12424
+ output: 2.4,
11980
12425
  cacheRead: 0,
11981
12426
  cacheWrite: 0,
11982
12427
  },
@@ -12026,8 +12471,8 @@ export const MODELS = {
12026
12471
  reasoning: true,
12027
12472
  input: ["text", "image"],
12028
12473
  cost: {
12029
- input: 0.117,
12030
- output: 1.365,
12474
+ input: 0.18,
12475
+ output: 2.0999999999999996,
12031
12476
  cacheRead: 0,
12032
12477
  cacheWrite: 0,
12033
12478
  },
@@ -12230,10 +12675,10 @@ export const MODELS = {
12230
12675
  reasoning: true,
12231
12676
  input: ["text"],
12232
12677
  cost: {
12233
- input: 1.04,
12234
- output: 6.24,
12678
+ input: 1.0270000000000001,
12679
+ output: 6.162,
12235
12680
  cacheRead: 0,
12236
- cacheWrite: 1.3,
12681
+ cacheWrite: 1.28375,
12237
12682
  },
12238
12683
  contextWindow: 262144,
12239
12684
  maxTokens: 65536,
@@ -12255,6 +12700,23 @@ export const MODELS = {
12255
12700
  contextWindow: 1000000,
12256
12701
  maxTokens: 65536,
12257
12702
  },
12703
+ "qwen/qwen3.7-flash": {
12704
+ id: "qwen/qwen3.7-flash",
12705
+ name: "Qwen: Qwen3.7 Flash",
12706
+ api: "openai-completions",
12707
+ provider: "openrouter",
12708
+ baseUrl: "https://openrouter.ai/api/v1",
12709
+ reasoning: true,
12710
+ input: ["text", "image"],
12711
+ cost: {
12712
+ input: 0.03,
12713
+ output: 0.13,
12714
+ cacheRead: 0.006,
12715
+ cacheWrite: 0.038000000000000006,
12716
+ },
12717
+ contextWindow: 1000000,
12718
+ maxTokens: 65536,
12719
+ },
12258
12720
  "qwen/qwen3.7-max": {
12259
12721
  id: "qwen/qwen3.7-max",
12260
12722
  name: "Qwen: Qwen3.7 Max",
@@ -12757,13 +13219,13 @@ export const MODELS = {
12757
13219
  reasoning: true,
12758
13220
  input: ["text"],
12759
13221
  cost: {
12760
- input: 0.7686000000000001,
12761
- output: 2.4156,
12762
- cacheRead: 0.14274,
13222
+ input: 0.966,
13223
+ output: 3.036,
13224
+ cacheRead: 0.1794,
12763
13225
  cacheWrite: 0,
12764
13226
  },
12765
13227
  contextWindow: 1048576,
12766
- maxTokens: 131072,
13228
+ maxTokens: 128000,
12767
13229
  },
12768
13230
  "z-ai/glm-5v-turbo": {
12769
13231
  id: "z-ai/glm-5v-turbo",
@@ -12893,13 +13355,13 @@ export const MODELS = {
12893
13355
  reasoning: true,
12894
13356
  input: ["text", "image"],
12895
13357
  cost: {
12896
- input: 2.7,
12897
- output: 13.5,
12898
- cacheRead: 0.27,
13358
+ input: 2.9000000000000004,
13359
+ output: 14,
13360
+ cacheRead: 0.29,
12899
13361
  cacheWrite: 0,
12900
13362
  },
12901
13363
  contextWindow: 1048576,
12902
- maxTokens: 16384,
13364
+ maxTokens: 1048576,
12903
13365
  },
12904
13366
  "~openai/gpt-latest": {
12905
13367
  id: "~openai/gpt-latest",
@@ -13328,6 +13790,23 @@ export const MODELS = {
13328
13790
  contextWindow: 1000000,
13329
13791
  maxTokens: 64000,
13330
13792
  },
13793
+ "alibaba/qwen3.7-flash": {
13794
+ id: "alibaba/qwen3.7-flash",
13795
+ name: "Qwen 3.7 Flash",
13796
+ api: "anthropic-messages",
13797
+ provider: "vercel-ai-gateway",
13798
+ baseUrl: "https://ai-gateway.vercel.sh",
13799
+ reasoning: true,
13800
+ input: ["text", "image"],
13801
+ cost: {
13802
+ input: 0.03,
13803
+ output: 0.13,
13804
+ cacheRead: 0.006,
13805
+ cacheWrite: 0.038000000000000006,
13806
+ },
13807
+ contextWindow: 991000,
13808
+ maxTokens: 64000,
13809
+ },
13331
13810
  "alibaba/qwen3.7-max": {
13332
13811
  id: "alibaba/qwen3.7-max",
13333
13812
  name: "Qwen 3.7 Max",
@@ -13878,7 +14357,7 @@ export const MODELS = {
13878
14357
  api: "anthropic-messages",
13879
14358
  provider: "vercel-ai-gateway",
13880
14359
  baseUrl: "https://ai-gateway.vercel.sh",
13881
- reasoning: true,
14360
+ reasoning: false,
13882
14361
  input: ["text"],
13883
14362
  cost: {
13884
14363
  input: 0.62,
@@ -13898,8 +14377,8 @@ export const MODELS = {
13898
14377
  reasoning: true,
13899
14378
  input: ["text"],
13900
14379
  cost: {
13901
- input: 0.14,
13902
- output: 0.28,
14380
+ input: 0.13799999999999998,
14381
+ output: 0.275,
13903
14382
  cacheRead: 0.028,
13904
14383
  cacheWrite: 0,
13905
14384
  },
@@ -13991,23 +14470,6 @@ export const MODELS = {
13991
14470
  contextWindow: 1000000,
13992
14471
  maxTokens: 65000,
13993
14472
  },
13994
- "google/gemini-3-pro-preview": {
13995
- id: "google/gemini-3-pro-preview",
13996
- name: "Gemini 3 Pro Preview",
13997
- api: "anthropic-messages",
13998
- provider: "vercel-ai-gateway",
13999
- baseUrl: "https://ai-gateway.vercel.sh",
14000
- reasoning: true,
14001
- input: ["text", "image"],
14002
- cost: {
14003
- input: 2,
14004
- output: 12,
14005
- cacheRead: 0.19999999999999998,
14006
- cacheWrite: 0,
14007
- },
14008
- contextWindow: 1000000,
14009
- maxTokens: 64000,
14010
- },
14011
14473
  "google/gemini-3.1-flash-lite": {
14012
14474
  id: "google/gemini-3.1-flash-lite",
14013
14475
  name: "Gemini 3.1 Flash Lite",
@@ -14452,7 +14914,7 @@ export const MODELS = {
14452
14914
  },
14453
14915
  "minimax/minimax-m2.7": {
14454
14916
  id: "minimax/minimax-m2.7",
14455
- name: "MiniMax M2.7",
14917
+ name: "Minimax M2.7",
14456
14918
  api: "anthropic-messages",
14457
14919
  provider: "vercel-ai-gateway",
14458
14920
  baseUrl: "https://ai-gateway.vercel.sh",
@@ -15107,7 +15569,7 @@ export const MODELS = {
15107
15569
  cost: {
15108
15570
  input: 1.25,
15109
15571
  output: 10,
15110
- cacheRead: 0.125,
15572
+ cacheRead: 0.13,
15111
15573
  cacheWrite: 0,
15112
15574
  },
15113
15575
  contextWindow: 400000,
@@ -15175,7 +15637,7 @@ export const MODELS = {
15175
15637
  cost: {
15176
15638
  input: 1.25,
15177
15639
  output: 10,
15178
- cacheRead: 0.125,
15640
+ cacheRead: 0.13,
15179
15641
  cacheWrite: 0,
15180
15642
  },
15181
15643
  contextWindow: 400000,
@@ -15209,7 +15671,7 @@ export const MODELS = {
15209
15671
  cost: {
15210
15672
  input: 0.25,
15211
15673
  output: 2,
15212
- cacheRead: 0.024999999999999998,
15674
+ cacheRead: 0.03,
15213
15675
  cacheWrite: 0,
15214
15676
  },
15215
15677
  contextWindow: 400000,
@@ -15226,7 +15688,7 @@ export const MODELS = {
15226
15688
  cost: {
15227
15689
  input: 1.25,
15228
15690
  output: 10,
15229
- cacheRead: 0.125,
15691
+ cacheRead: 0.13,
15230
15692
  cacheWrite: 0,
15231
15693
  },
15232
15694
  contextWindow: 128000,
@@ -15445,10 +15907,10 @@ export const MODELS = {
15445
15907
  reasoning: true,
15446
15908
  input: ["text", "image"],
15447
15909
  cost: {
15448
- input: 1,
15449
- output: 6,
15450
- cacheRead: 0.09999999999999999,
15451
- cacheWrite: 1.25,
15910
+ input: 0.19999999999999998,
15911
+ output: 1.2,
15912
+ cacheRead: 0.02,
15913
+ cacheWrite: 0.25,
15452
15914
  },
15453
15915
  contextWindow: 1050000,
15454
15916
  maxTokens: 128000,
@@ -15479,10 +15941,10 @@ export const MODELS = {
15479
15941
  reasoning: true,
15480
15942
  input: ["text", "image"],
15481
15943
  cost: {
15482
- input: 2.5,
15483
- output: 15,
15484
- cacheRead: 0.25,
15485
- cacheWrite: 3.125,
15944
+ input: 2,
15945
+ output: 12,
15946
+ cacheRead: 0.19999999999999998,
15947
+ cacheWrite: 2.5,
15486
15948
  },
15487
15949
  contextWindow: 1050000,
15488
15950
  maxTokens: 128000,
@@ -15759,6 +16221,23 @@ export const MODELS = {
15759
16221
  contextWindow: 256000,
15760
16222
  maxTokens: 256000,
15761
16223
  },
16224
+ "thinkingmachines/inkling-small": {
16225
+ id: "thinkingmachines/inkling-small",
16226
+ name: "Inkling Small",
16227
+ api: "anthropic-messages",
16228
+ provider: "vercel-ai-gateway",
16229
+ baseUrl: "https://ai-gateway.vercel.sh",
16230
+ reasoning: true,
16231
+ input: ["text", "image"],
16232
+ cost: {
16233
+ input: 0.5,
16234
+ output: 1.2,
16235
+ cacheRead: 0.09999999999999999,
16236
+ cacheWrite: 0,
16237
+ },
16238
+ contextWindow: 1000000,
16239
+ maxTokens: 1000000,
16240
+ },
15762
16241
  "xai/grok-4.1-fast-non-reasoning": {
15763
16242
  id: "xai/grok-4.1-fast-non-reasoning",
15764
16243
  name: "Grok 4.1 Fast Non-Reasoning",
@@ -16142,9 +16621,9 @@ export const MODELS = {
16142
16621
  reasoning: true,
16143
16622
  input: ["text"],
16144
16623
  cost: {
16145
- input: 0.95,
16146
- output: 3.15,
16147
- cacheRead: 0.19999999999999998,
16624
+ input: 1,
16625
+ output: 3.1999999999999997,
16626
+ cacheRead: 0,
16148
16627
  cacheWrite: 0,
16149
16628
  },
16150
16629
  contextWindow: 202800,
@@ -16176,8 +16655,8 @@ export const MODELS = {
16176
16655
  reasoning: true,
16177
16656
  input: ["text"],
16178
16657
  cost: {
16179
- input: 1.3,
16180
- output: 4.300000000000001,
16658
+ input: 1.4,
16659
+ output: 4.4,
16181
16660
  cacheRead: 0.26,
16182
16661
  cacheWrite: 0,
16183
16662
  },
@@ -16193,12 +16672,12 @@ export const MODELS = {
16193
16672
  reasoning: true,
16194
16673
  input: ["text"],
16195
16674
  cost: {
16196
- input: 1.4,
16197
- output: 4.4,
16198
- cacheRead: 0.26,
16675
+ input: 1.1,
16676
+ output: 3.851,
16677
+ cacheRead: 0.275,
16199
16678
  cacheWrite: 0,
16200
16679
  },
16201
- contextWindow: 1040000,
16680
+ contextWindow: 1000000,
16202
16681
  maxTokens: 128000,
16203
16682
  },
16204
16683
  "zai/glm-5.2-fast": {