@dreb/ai 2.45.3 → 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",
@@ -7814,6 +7868,23 @@ export const MODELS = {
7814
7868
  contextWindow: 262144,
7815
7869
  maxTokens: 262144,
7816
7870
  },
7871
+ "kimi-k3": {
7872
+ id: "kimi-k3",
7873
+ name: "Kimi K3",
7874
+ api: "openai-completions",
7875
+ provider: "opencode",
7876
+ baseUrl: "https://opencode.ai/zen/v1",
7877
+ reasoning: true,
7878
+ input: ["text", "image"],
7879
+ cost: {
7880
+ input: 3,
7881
+ output: 15,
7882
+ cacheRead: 0.3,
7883
+ cacheWrite: 0,
7884
+ },
7885
+ contextWindow: 1048576,
7886
+ maxTokens: 131072,
7887
+ },
7817
7888
  "laguna-s-2.1-free": {
7818
7889
  id: "laguna-s-2.1-free",
7819
7890
  name: "Laguna S 2.1 Free",
@@ -8447,6 +8518,23 @@ export const MODELS = {
8447
8518
  contextWindow: 1000000,
8448
8519
  maxTokens: 128000,
8449
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
+ },
8450
8538
  "anthropic/claude-haiku-4.5": {
8451
8539
  id: "anthropic/claude-haiku-4.5",
8452
8540
  name: "Anthropic: Claude Haiku 4.5",
@@ -8464,6 +8552,23 @@ export const MODELS = {
8464
8552
  contextWindow: 200000,
8465
8553
  maxTokens: 64000,
8466
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
+ },
8467
8572
  "anthropic/claude-opus-4": {
8468
8573
  id: "anthropic/claude-opus-4",
8469
8574
  name: "Anthropic: Claude Opus 4",
@@ -8498,6 +8603,23 @@ export const MODELS = {
8498
8603
  contextWindow: 200000,
8499
8604
  maxTokens: 32000,
8500
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
+ },
8501
8623
  "anthropic/claude-opus-4.5": {
8502
8624
  id: "anthropic/claude-opus-4.5",
8503
8625
  name: "Anthropic: Claude Opus 4.5",
@@ -8515,6 +8637,23 @@ export const MODELS = {
8515
8637
  contextWindow: 200000,
8516
8638
  maxTokens: 64000,
8517
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
+ },
8518
8657
  "anthropic/claude-opus-4.6": {
8519
8658
  id: "anthropic/claude-opus-4.6",
8520
8659
  name: "Anthropic: Claude Opus 4.6",
@@ -8532,6 +8671,23 @@ export const MODELS = {
8532
8671
  contextWindow: 1000000,
8533
8672
  maxTokens: 128000,
8534
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
+ },
8535
8691
  "anthropic/claude-opus-4.7": {
8536
8692
  id: "anthropic/claude-opus-4.7",
8537
8693
  name: "Anthropic: Claude Opus 4.7",
@@ -8566,6 +8722,23 @@ export const MODELS = {
8566
8722
  contextWindow: 1000000,
8567
8723
  maxTokens: 128000,
8568
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
+ },
8569
8742
  "anthropic/claude-opus-4.8": {
8570
8743
  id: "anthropic/claude-opus-4.8",
8571
8744
  name: "Anthropic: Claude Opus 4.8",
@@ -8600,6 +8773,23 @@ export const MODELS = {
8600
8773
  contextWindow: 1000000,
8601
8774
  maxTokens: 128000,
8602
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
+ },
8603
8793
  "anthropic/claude-opus-5": {
8604
8794
  id: "anthropic/claude-opus-5",
8605
8795
  name: "Claude Opus 5",
@@ -8668,6 +8858,23 @@ export const MODELS = {
8668
8858
  contextWindow: 1000000,
8669
8859
  maxTokens: 64000,
8670
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
+ },
8671
8878
  "anthropic/claude-sonnet-4.6": {
8672
8879
  id: "anthropic/claude-sonnet-4.6",
8673
8880
  name: "Anthropic: Claude Sonnet 4.6",
@@ -8702,6 +8909,23 @@ export const MODELS = {
8702
8909
  contextWindow: 1000000,
8703
8910
  maxTokens: 128000,
8704
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
+ },
8705
8929
  "arcee-ai/trinity-large-thinking": {
8706
8930
  id: "arcee-ai/trinity-large-thinking",
8707
8931
  name: "Arcee AI: Trinity Large Thinking",
@@ -8881,8 +9105,8 @@ export const MODELS = {
8881
9105
  reasoning: false,
8882
9106
  input: ["text"],
8883
9107
  cost: {
8884
- input: 0.20020000000000002,
8885
- output: 0.8000999999999999,
9108
+ input: 0.2574,
9109
+ output: 1.0287,
8886
9110
  cacheRead: 0,
8887
9111
  cacheWrite: 0,
8888
9112
  },
@@ -9076,6 +9300,40 @@ export const MODELS = {
9076
9300
  contextWindow: 1048576,
9077
9301
  maxTokens: 65535,
9078
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
+ },
9079
9337
  "google/gemini-2.5-pro": {
9080
9338
  id: "google/gemini-2.5-pro",
9081
9339
  name: "Google: Gemini 2.5 Pro",
@@ -9127,6 +9385,23 @@ export const MODELS = {
9127
9385
  contextWindow: 1048576,
9128
9386
  maxTokens: 65535,
9129
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
+ },
9130
9405
  "google/gemini-3-flash-preview": {
9131
9406
  id: "google/gemini-3-flash-preview",
9132
9407
  name: "Google: Gemini 3 Flash Preview",
@@ -9144,6 +9419,23 @@ export const MODELS = {
9144
9419
  contextWindow: 1048576,
9145
9420
  maxTokens: 65535,
9146
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
+ },
9147
9439
  "google/gemini-3-pro-image": {
9148
9440
  id: "google/gemini-3-pro-image",
9149
9441
  name: "Google: Nano Banana Pro (Gemini 3 Pro Image)",
@@ -9195,6 +9487,23 @@ export const MODELS = {
9195
9487
  contextWindow: 1048576,
9196
9488
  maxTokens: 65536,
9197
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
+ },
9198
9507
  "google/gemini-3.1-pro-preview": {
9199
9508
  id: "google/gemini-3.1-pro-preview",
9200
9509
  name: "Google: Gemini 3.1 Pro Preview",
@@ -9229,6 +9538,23 @@ export const MODELS = {
9229
9538
  contextWindow: 1048576,
9230
9539
  maxTokens: 65536,
9231
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
+ },
9232
9558
  "google/gemini-3.5-flash": {
9233
9559
  id: "google/gemini-3.5-flash",
9234
9560
  name: "Google: Gemini 3.5 Flash",
@@ -9263,6 +9589,40 @@ export const MODELS = {
9263
9589
  contextWindow: 1048576,
9264
9590
  maxTokens: 65536,
9265
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
+ },
9266
9626
  "google/gemini-3.6-flash": {
9267
9627
  id: "google/gemini-3.6-flash",
9268
9628
  name: "Google: Gemini 3.6 Flash",
@@ -9280,6 +9640,23 @@ export const MODELS = {
9280
9640
  contextWindow: 1048576,
9281
9641
  maxTokens: 65536,
9282
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
+ },
9283
9660
  "google/gemma-3-12b-it": {
9284
9661
  id: "google/gemma-3-12b-it",
9285
9662
  name: "Google: Gemma 3 12B",
@@ -9323,13 +9700,13 @@ export const MODELS = {
9323
9700
  reasoning: true,
9324
9701
  input: ["text", "image"],
9325
9702
  cost: {
9326
- input: 0.13,
9327
- output: 0.39999999999999997,
9328
- cacheRead: 0.049999999999999996,
9703
+ input: 0.07,
9704
+ output: 0.33999999999999997,
9705
+ cacheRead: 0,
9329
9706
  cacheWrite: 0,
9330
9707
  },
9331
9708
  contextWindow: 262144,
9332
- maxTokens: 262144,
9709
+ maxTokens: 16384,
9333
9710
  },
9334
9711
  "google/gemma-4-26b-a4b-it:free": {
9335
9712
  id: "google/gemma-4-26b-a4b-it:free",
@@ -9357,9 +9734,9 @@ export const MODELS = {
9357
9734
  reasoning: true,
9358
9735
  input: ["text", "image"],
9359
9736
  cost: {
9360
- input: 0.14,
9361
- output: 0.39999999999999997,
9362
- cacheRead: 0,
9737
+ input: 0.09999999999999999,
9738
+ output: 0.33999999999999997,
9739
+ cacheRead: 0.09999999999999999,
9363
9740
  cacheWrite: 0,
9364
9741
  },
9365
9742
  contextWindow: 262144,
@@ -9756,6 +10133,23 @@ export const MODELS = {
9756
10133
  contextWindow: 1048576,
9757
10134
  maxTokens: 512000,
9758
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
+ },
9759
10153
  "mistralai/codestral-2508": {
9760
10154
  id: "mistralai/codestral-2508",
9761
10155
  name: "Mistral: Codestral 2508",
@@ -10122,9 +10516,9 @@ export const MODELS = {
10122
10516
  reasoning: true,
10123
10517
  input: ["text", "image"],
10124
10518
  cost: {
10125
- input: 0.646,
10126
- output: 2.7199999999999998,
10127
- cacheRead: 0.1088,
10519
+ input: 0.95,
10520
+ output: 4,
10521
+ cacheRead: 0.16,
10128
10522
  cacheWrite: 0,
10129
10523
  },
10130
10524
  contextWindow: 262144,
@@ -10209,7 +10603,7 @@ export const MODELS = {
10209
10603
  cost: {
10210
10604
  input: 0.049999999999999996,
10211
10605
  output: 0.19999999999999998,
10212
- cacheRead: 0,
10606
+ cacheRead: 0.024999999999999998,
10213
10607
  cacheWrite: 0,
10214
10608
  },
10215
10609
  contextWindow: 262144,
@@ -10292,13 +10686,13 @@ export const MODELS = {
10292
10686
  reasoning: true,
10293
10687
  input: ["text"],
10294
10688
  cost: {
10295
- input: 0.5,
10296
- output: 2.2,
10297
- cacheRead: 0.09999999999999999,
10689
+ input: 0.6,
10690
+ output: 3.5999999999999996,
10691
+ cacheRead: 0.19999999999999998,
10298
10692
  cacheWrite: 0,
10299
10693
  },
10300
10694
  contextWindow: 512288,
10301
- maxTokens: 16384,
10695
+ maxTokens: 4096,
10302
10696
  },
10303
10697
  "nvidia/nemotron-3-ultra-550b-a55b:free": {
10304
10698
  id: "nvidia/nemotron-3-ultra-550b-a55b:free",
@@ -10623,35 +11017,35 @@ export const MODELS = {
10623
11017
  contextWindow: 400000,
10624
11018
  maxTokens: 128000,
10625
11019
  },
10626
- "openai/gpt-5-codex": {
10627
- id: "openai/gpt-5-codex",
10628
- name: "OpenAI: GPT-5 Codex",
11020
+ "openai/gpt-5-mini": {
11021
+ id: "openai/gpt-5-mini",
11022
+ name: "OpenAI: GPT-5 Mini",
10629
11023
  api: "openai-completions",
10630
11024
  provider: "openrouter",
10631
11025
  baseUrl: "https://openrouter.ai/api/v1",
10632
11026
  reasoning: true,
10633
11027
  input: ["text", "image"],
10634
11028
  cost: {
10635
- input: 1.25,
10636
- output: 10,
10637
- cacheRead: 0.125,
11029
+ input: 0.25,
11030
+ output: 2,
11031
+ cacheRead: 0.024999999999999998,
10638
11032
  cacheWrite: 0,
10639
11033
  },
10640
11034
  contextWindow: 400000,
10641
11035
  maxTokens: 128000,
10642
11036
  },
10643
- "openai/gpt-5-mini": {
10644
- id: "openai/gpt-5-mini",
10645
- 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)",
10646
11040
  api: "openai-completions",
10647
11041
  provider: "openrouter",
10648
11042
  baseUrl: "https://openrouter.ai/api/v1",
10649
11043
  reasoning: true,
10650
11044
  input: ["text", "image"],
10651
11045
  cost: {
10652
- input: 0.25,
10653
- output: 2,
10654
- cacheRead: 0.024999999999999998,
11046
+ input: 0.125,
11047
+ output: 1,
11048
+ cacheRead: 0.012499999999999999,
10655
11049
  cacheWrite: 0,
10656
11050
  },
10657
11051
  contextWindow: 400000,
@@ -10674,6 +11068,23 @@ export const MODELS = {
10674
11068
  contextWindow: 400000,
10675
11069
  maxTokens: 128000,
10676
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
+ },
10677
11088
  "openai/gpt-5-pro": {
10678
11089
  id: "openai/gpt-5-pro",
10679
11090
  name: "OpenAI: GPT-5 Pro",
@@ -10719,11 +11130,11 @@ export const MODELS = {
10719
11130
  cost: {
10720
11131
  input: 1.25,
10721
11132
  output: 10,
10722
- cacheRead: 0.125,
11133
+ cacheRead: 0.13,
10723
11134
  cacheWrite: 0,
10724
11135
  },
10725
11136
  contextWindow: 128000,
10726
- maxTokens: 16384,
11137
+ maxTokens: 32000,
10727
11138
  },
10728
11139
  "openai/gpt-5.1-codex": {
10729
11140
  id: "openai/gpt-5.1-codex",
@@ -10776,6 +11187,23 @@ export const MODELS = {
10776
11187
  contextWindow: 400000,
10777
11188
  maxTokens: 128000,
10778
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
+ },
10779
11207
  "openai/gpt-5.2": {
10780
11208
  id: "openai/gpt-5.2",
10781
11209
  name: "OpenAI: GPT-5.2",
@@ -10844,6 +11272,23 @@ export const MODELS = {
10844
11272
  contextWindow: 400000,
10845
11273
  maxTokens: 128000,
10846
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
+ },
10847
11292
  "openai/gpt-5.3-chat": {
10848
11293
  id: "openai/gpt-5.3-chat",
10849
11294
  name: "OpenAI: GPT-5.3 Chat",
@@ -10912,6 +11357,23 @@ export const MODELS = {
10912
11357
  contextWindow: 400000,
10913
11358
  maxTokens: 128000,
10914
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
+ },
10915
11377
  "openai/gpt-5.4-nano": {
10916
11378
  id: "openai/gpt-5.4-nano",
10917
11379
  name: "OpenAI: GPT-5.4 Nano",
@@ -10929,6 +11391,23 @@ export const MODELS = {
10929
11391
  contextWindow: 400000,
10930
11392
  maxTokens: 128000,
10931
11393
  },
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
+ },
10932
11411
  "openai/gpt-5.4-pro": {
10933
11412
  id: "openai/gpt-5.4-pro",
10934
11413
  name: "OpenAI: GPT-5.4 Pro",
@@ -10946,6 +11425,23 @@ export const MODELS = {
10946
11425
  contextWindow: 1050000,
10947
11426
  maxTokens: 128000,
10948
11427
  },
11428
+ "openai/gpt-5.4:batch": {
11429
+ id: "openai/gpt-5.4:batch",
11430
+ name: "OpenAI: GPT-5.4 (batch)",
11431
+ api: "openai-completions",
11432
+ provider: "openrouter",
11433
+ baseUrl: "https://openrouter.ai/api/v1",
11434
+ reasoning: true,
11435
+ input: ["text", "image"],
11436
+ cost: {
11437
+ input: 1.25,
11438
+ output: 7.5,
11439
+ cacheRead: 0.125,
11440
+ cacheWrite: 0,
11441
+ },
11442
+ contextWindow: 1050000,
11443
+ maxTokens: 128000,
11444
+ },
10949
11445
  "openai/gpt-5.5": {
10950
11446
  id: "openai/gpt-5.5",
10951
11447
  name: "OpenAI: GPT-5.5",
@@ -10972,9 +11468,26 @@ export const MODELS = {
10972
11468
  reasoning: true,
10973
11469
  input: ["text", "image"],
10974
11470
  cost: {
10975
- input: 30,
10976
- output: 180,
10977
- cacheRead: 0,
11471
+ input: 30,
11472
+ output: 180,
11473
+ cacheRead: 0,
11474
+ cacheWrite: 0,
11475
+ },
11476
+ contextWindow: 1050000,
11477
+ maxTokens: 128000,
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,
10978
11491
  cacheWrite: 0,
10979
11492
  },
10980
11493
  contextWindow: 1050000,
@@ -10989,10 +11502,10 @@ export const MODELS = {
10989
11502
  reasoning: true,
10990
11503
  input: ["text", "image"],
10991
11504
  cost: {
10992
- input: 1,
10993
- output: 6,
10994
- cacheRead: 0.09999999999999999,
10995
- cacheWrite: 1.25,
11505
+ input: 0.09999999999999999,
11506
+ output: 0.6000000000000001,
11507
+ cacheRead: 0.01,
11508
+ cacheWrite: 0.12500000000000003,
10996
11509
  },
10997
11510
  contextWindow: 1050000,
10998
11511
  maxTokens: 128000,
@@ -11006,10 +11519,10 @@ export const MODELS = {
11006
11519
  reasoning: true,
11007
11520
  input: ["text", "image"],
11008
11521
  cost: {
11009
- input: 1,
11010
- output: 6,
11011
- cacheRead: 0.09999999999999999,
11012
- cacheWrite: 1.25,
11522
+ input: 0.09999999999999999,
11523
+ output: 0.6000000000000001,
11524
+ cacheRead: 0.01,
11525
+ cacheWrite: 0.12500000000000003,
11013
11526
  },
11014
11527
  contextWindow: 1050000,
11015
11528
  maxTokens: 128000,
@@ -11057,10 +11570,10 @@ export const MODELS = {
11057
11570
  reasoning: true,
11058
11571
  input: ["text", "image"],
11059
11572
  cost: {
11060
- input: 2.5,
11061
- output: 15,
11062
- cacheRead: 0.25,
11063
- cacheWrite: 3.125,
11573
+ input: 1.0000000000000002,
11574
+ output: 6,
11575
+ cacheRead: 0.09999999999999999,
11576
+ cacheWrite: 1.25,
11064
11577
  },
11065
11578
  contextWindow: 1050000,
11066
11579
  maxTokens: 128000,
@@ -11074,14 +11587,31 @@ export const MODELS = {
11074
11587
  reasoning: true,
11075
11588
  input: ["text", "image"],
11076
11589
  cost: {
11077
- input: 2.5,
11078
- output: 15,
11079
- cacheRead: 0.25,
11080
- cacheWrite: 3.125,
11590
+ input: 1.0000000000000002,
11591
+ output: 6,
11592
+ cacheRead: 0.09999999999999999,
11593
+ cacheWrite: 1.25,
11081
11594
  },
11082
11595
  contextWindow: 1050000,
11083
11596
  maxTokens: 128000,
11084
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
+ },
11085
11615
  "openai/gpt-audio": {
11086
11616
  id: "openai/gpt-audio",
11087
11617
  name: "OpenAI: GPT Audio",
@@ -11160,8 +11690,8 @@ export const MODELS = {
11160
11690
  input: ["text"],
11161
11691
  cost: {
11162
11692
  input: 0.03,
11163
- output: 0.14,
11164
- cacheRead: 0,
11693
+ output: 0.13,
11694
+ cacheRead: 0.03,
11165
11695
  cacheWrite: 0,
11166
11696
  },
11167
11697
  contextWindow: 131072,
@@ -11235,23 +11765,6 @@ export const MODELS = {
11235
11765
  contextWindow: 200000,
11236
11766
  maxTokens: 100000,
11237
11767
  },
11238
- "openai/o3-deep-research": {
11239
- id: "openai/o3-deep-research",
11240
- name: "OpenAI: o3 Deep Research",
11241
- api: "openai-completions",
11242
- provider: "openrouter",
11243
- baseUrl: "https://openrouter.ai/api/v1",
11244
- reasoning: true,
11245
- input: ["text", "image"],
11246
- cost: {
11247
- input: 10,
11248
- output: 40,
11249
- cacheRead: 2.5,
11250
- cacheWrite: 0,
11251
- },
11252
- contextWindow: 200000,
11253
- maxTokens: 100000,
11254
- },
11255
11768
  "openai/o3-mini": {
11256
11769
  id: "openai/o3-mini",
11257
11770
  name: "OpenAI: o3 Mini",
@@ -11320,23 +11833,6 @@ export const MODELS = {
11320
11833
  contextWindow: 200000,
11321
11834
  maxTokens: 100000,
11322
11835
  },
11323
- "openai/o4-mini-deep-research": {
11324
- id: "openai/o4-mini-deep-research",
11325
- name: "OpenAI: o4 Mini Deep Research",
11326
- api: "openai-completions",
11327
- provider: "openrouter",
11328
- baseUrl: "https://openrouter.ai/api/v1",
11329
- reasoning: true,
11330
- input: ["text", "image"],
11331
- cost: {
11332
- input: 2,
11333
- output: 8,
11334
- cacheRead: 0.5,
11335
- cacheWrite: 0,
11336
- },
11337
- contextWindow: 200000,
11338
- maxTokens: 100000,
11339
- },
11340
11836
  "openai/o4-mini-high": {
11341
11837
  id: "openai/o4-mini-high",
11342
11838
  name: "OpenAI: o4 Mini High",
@@ -11405,40 +11901,6 @@ export const MODELS = {
11405
11901
  contextWindow: 200000,
11406
11902
  maxTokens: 4096,
11407
11903
  },
11408
- "poolside/laguna-m.1": {
11409
- id: "poolside/laguna-m.1",
11410
- name: "Poolside: Laguna M.1",
11411
- api: "openai-completions",
11412
- provider: "openrouter",
11413
- baseUrl: "https://openrouter.ai/api/v1",
11414
- reasoning: true,
11415
- input: ["text"],
11416
- cost: {
11417
- input: 0.19999999999999998,
11418
- output: 0.39999999999999997,
11419
- cacheRead: 0.09999999999999999,
11420
- cacheWrite: 0,
11421
- },
11422
- contextWindow: 262144,
11423
- maxTokens: 32768,
11424
- },
11425
- "poolside/laguna-m.1:free": {
11426
- id: "poolside/laguna-m.1:free",
11427
- name: "Poolside: Laguna M.1 (free)",
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,
11435
- output: 0,
11436
- cacheRead: 0,
11437
- cacheWrite: 0,
11438
- },
11439
- contextWindow: 262144,
11440
- maxTokens: 32768,
11441
- },
11442
11904
  "poolside/laguna-s-2.1": {
11443
11905
  id: "poolside/laguna-s-2.1",
11444
11906
  name: "Poolside: Laguna S 2.1",
@@ -11533,8 +11995,8 @@ export const MODELS = {
11533
11995
  reasoning: false,
11534
11996
  input: ["text"],
11535
11997
  cost: {
11536
- input: 0.04,
11537
- output: 0.09999999999999999,
11998
+ input: 0.09999999999999999,
11999
+ output: 0.19999999999999998,
11538
12000
  cacheRead: 0,
11539
12001
  cacheWrite: 0,
11540
12002
  },
@@ -11584,10 +12046,10 @@ export const MODELS = {
11584
12046
  reasoning: true,
11585
12047
  input: ["text"],
11586
12048
  cost: {
11587
- input: 0.26,
11588
- output: 0.78,
12049
+ input: 0.39999999999999997,
12050
+ output: 1.2,
11589
12051
  cacheRead: 0,
11590
- cacheWrite: 0.325,
12052
+ cacheWrite: 0.5,
11591
12053
  },
11592
12054
  contextWindow: 1000000,
11593
12055
  maxTokens: 32768,
@@ -11703,8 +12165,8 @@ export const MODELS = {
11703
12165
  reasoning: true,
11704
12166
  input: ["text"],
11705
12167
  cost: {
11706
- input: 0.13,
11707
- output: 1.56,
12168
+ input: 0.19999999999999998,
12169
+ output: 2.4,
11708
12170
  cacheRead: 0,
11709
12171
  cacheWrite: 0,
11710
12172
  },
@@ -11805,7 +12267,7 @@ export const MODELS = {
11805
12267
  reasoning: false,
11806
12268
  input: ["text"],
11807
12269
  cost: {
11808
- input: 0.11,
12270
+ input: 0.12,
11809
12271
  output: 0.7999999999999999,
11810
12272
  cacheRead: 0.07,
11811
12273
  cacheWrite: 0,
@@ -11845,7 +12307,7 @@ export const MODELS = {
11845
12307
  cacheWrite: 0.975,
11846
12308
  },
11847
12309
  contextWindow: 262144,
11848
- maxTokens: 32768,
12310
+ maxTokens: 65536,
11849
12311
  },
11850
12312
  "qwen/qwen3-max-thinking": {
11851
12313
  id: "qwen/qwen3-max-thinking",
@@ -11862,7 +12324,7 @@ export const MODELS = {
11862
12324
  cacheWrite: 0,
11863
12325
  },
11864
12326
  contextWindow: 262144,
11865
- maxTokens: 32768,
12327
+ maxTokens: 65536,
11866
12328
  },
11867
12329
  "qwen/qwen3-next-80b-a3b-instruct": {
11868
12330
  id: "qwen/qwen3-next-80b-a3b-instruct",
@@ -11890,8 +12352,8 @@ export const MODELS = {
11890
12352
  reasoning: true,
11891
12353
  input: ["text"],
11892
12354
  cost: {
11893
- input: 0.0975,
11894
- output: 0.78,
12355
+ input: 0.15,
12356
+ output: 1.2,
11895
12357
  cacheRead: 0,
11896
12358
  cacheWrite: 0,
11897
12359
  },
@@ -11924,8 +12386,8 @@ export const MODELS = {
11924
12386
  reasoning: true,
11925
12387
  input: ["text", "image"],
11926
12388
  cost: {
11927
- input: 0.26,
11928
- output: 2.6,
12389
+ input: 0.39999999999999997,
12390
+ output: 4,
11929
12391
  cacheRead: 0,
11930
12392
  cacheWrite: 0,
11931
12393
  },
@@ -11958,8 +12420,8 @@ export const MODELS = {
11958
12420
  reasoning: true,
11959
12421
  input: ["text", "image"],
11960
12422
  cost: {
11961
- input: 0.13,
11962
- output: 1.56,
12423
+ input: 0.19999999999999998,
12424
+ output: 2.4,
11963
12425
  cacheRead: 0,
11964
12426
  cacheWrite: 0,
11965
12427
  },
@@ -12009,8 +12471,8 @@ export const MODELS = {
12009
12471
  reasoning: true,
12010
12472
  input: ["text", "image"],
12011
12473
  cost: {
12012
- input: 0.117,
12013
- output: 1.365,
12474
+ input: 0.18,
12475
+ output: 2.0999999999999996,
12014
12476
  cacheRead: 0,
12015
12477
  cacheWrite: 0,
12016
12478
  },
@@ -12213,10 +12675,10 @@ export const MODELS = {
12213
12675
  reasoning: true,
12214
12676
  input: ["text"],
12215
12677
  cost: {
12216
- input: 1.04,
12217
- output: 6.24,
12678
+ input: 1.0270000000000001,
12679
+ output: 6.162,
12218
12680
  cacheRead: 0,
12219
- cacheWrite: 1.3,
12681
+ cacheWrite: 1.28375,
12220
12682
  },
12221
12683
  contextWindow: 262144,
12222
12684
  maxTokens: 65536,
@@ -12238,6 +12700,23 @@ export const MODELS = {
12238
12700
  contextWindow: 1000000,
12239
12701
  maxTokens: 65536,
12240
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
+ },
12241
12720
  "qwen/qwen3.7-max": {
12242
12721
  id: "qwen/qwen3.7-max",
12243
12722
  name: "Qwen: Qwen3.7 Max",
@@ -12740,13 +13219,13 @@ export const MODELS = {
12740
13219
  reasoning: true,
12741
13220
  input: ["text"],
12742
13221
  cost: {
12743
- input: 0.784,
12744
- output: 2.464,
12745
- cacheRead: 0.1456,
13222
+ input: 0.966,
13223
+ output: 3.036,
13224
+ cacheRead: 0.1794,
12746
13225
  cacheWrite: 0,
12747
13226
  },
12748
13227
  contextWindow: 1048576,
12749
- maxTokens: 131072,
13228
+ maxTokens: 128000,
12750
13229
  },
12751
13230
  "z-ai/glm-5v-turbo": {
12752
13231
  id: "z-ai/glm-5v-turbo",
@@ -12876,13 +13355,13 @@ export const MODELS = {
12876
13355
  reasoning: true,
12877
13356
  input: ["text", "image"],
12878
13357
  cost: {
12879
- input: 3,
12880
- output: 15,
12881
- cacheRead: 0.3,
13358
+ input: 2.9000000000000004,
13359
+ output: 14,
13360
+ cacheRead: 0.29,
12882
13361
  cacheWrite: 0,
12883
13362
  },
12884
13363
  contextWindow: 1048576,
12885
- maxTokens: 4096,
13364
+ maxTokens: 1048576,
12886
13365
  },
12887
13366
  "~openai/gpt-latest": {
12888
13367
  id: "~openai/gpt-latest",
@@ -13311,6 +13790,23 @@ export const MODELS = {
13311
13790
  contextWindow: 1000000,
13312
13791
  maxTokens: 64000,
13313
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
+ },
13314
13810
  "alibaba/qwen3.7-max": {
13315
13811
  id: "alibaba/qwen3.7-max",
13316
13812
  name: "Qwen 3.7 Max",
@@ -13861,7 +14357,7 @@ export const MODELS = {
13861
14357
  api: "anthropic-messages",
13862
14358
  provider: "vercel-ai-gateway",
13863
14359
  baseUrl: "https://ai-gateway.vercel.sh",
13864
- reasoning: true,
14360
+ reasoning: false,
13865
14361
  input: ["text"],
13866
14362
  cost: {
13867
14363
  input: 0.62,
@@ -13881,8 +14377,8 @@ export const MODELS = {
13881
14377
  reasoning: true,
13882
14378
  input: ["text"],
13883
14379
  cost: {
13884
- input: 0.14,
13885
- output: 0.28,
14380
+ input: 0.13799999999999998,
14381
+ output: 0.275,
13886
14382
  cacheRead: 0.028,
13887
14383
  cacheWrite: 0,
13888
14384
  },
@@ -13974,23 +14470,6 @@ export const MODELS = {
13974
14470
  contextWindow: 1000000,
13975
14471
  maxTokens: 65000,
13976
14472
  },
13977
- "google/gemini-3-pro-preview": {
13978
- id: "google/gemini-3-pro-preview",
13979
- name: "Gemini 3 Pro Preview",
13980
- api: "anthropic-messages",
13981
- provider: "vercel-ai-gateway",
13982
- baseUrl: "https://ai-gateway.vercel.sh",
13983
- reasoning: true,
13984
- input: ["text", "image"],
13985
- cost: {
13986
- input: 2,
13987
- output: 12,
13988
- cacheRead: 0.19999999999999998,
13989
- cacheWrite: 0,
13990
- },
13991
- contextWindow: 1000000,
13992
- maxTokens: 64000,
13993
- },
13994
14473
  "google/gemini-3.1-flash-lite": {
13995
14474
  id: "google/gemini-3.1-flash-lite",
13996
14475
  name: "Gemini 3.1 Flash Lite",
@@ -14435,7 +14914,7 @@ export const MODELS = {
14435
14914
  },
14436
14915
  "minimax/minimax-m2.7": {
14437
14916
  id: "minimax/minimax-m2.7",
14438
- name: "MiniMax M2.7",
14917
+ name: "Minimax M2.7",
14439
14918
  api: "anthropic-messages",
14440
14919
  provider: "vercel-ai-gateway",
14441
14920
  baseUrl: "https://ai-gateway.vercel.sh",
@@ -14841,6 +15320,23 @@ export const MODELS = {
14841
15320
  contextWindow: 1000000,
14842
15321
  maxTokens: 131072,
14843
15322
  },
15323
+ "moonshotai/kimi-k3-fast": {
15324
+ id: "moonshotai/kimi-k3-fast",
15325
+ name: "Kimi K3 Fast",
15326
+ api: "anthropic-messages",
15327
+ provider: "vercel-ai-gateway",
15328
+ baseUrl: "https://ai-gateway.vercel.sh",
15329
+ reasoning: true,
15330
+ input: ["text", "image"],
15331
+ cost: {
15332
+ input: 4.5,
15333
+ output: 22.5,
15334
+ cacheRead: 0.44999999999999996,
15335
+ cacheWrite: 0,
15336
+ },
15337
+ contextWindow: 1000000,
15338
+ maxTokens: 131072,
15339
+ },
14844
15340
  "nvidia/nemotron-3-nano-30b-a3b": {
14845
15341
  id: "nvidia/nemotron-3-nano-30b-a3b",
14846
15342
  name: "Nemotron 3 Nano 30B A3B",
@@ -15073,7 +15569,7 @@ export const MODELS = {
15073
15569
  cost: {
15074
15570
  input: 1.25,
15075
15571
  output: 10,
15076
- cacheRead: 0.125,
15572
+ cacheRead: 0.13,
15077
15573
  cacheWrite: 0,
15078
15574
  },
15079
15575
  contextWindow: 400000,
@@ -15141,7 +15637,7 @@ export const MODELS = {
15141
15637
  cost: {
15142
15638
  input: 1.25,
15143
15639
  output: 10,
15144
- cacheRead: 0.125,
15640
+ cacheRead: 0.13,
15145
15641
  cacheWrite: 0,
15146
15642
  },
15147
15643
  contextWindow: 400000,
@@ -15175,7 +15671,7 @@ export const MODELS = {
15175
15671
  cost: {
15176
15672
  input: 0.25,
15177
15673
  output: 2,
15178
- cacheRead: 0.024999999999999998,
15674
+ cacheRead: 0.03,
15179
15675
  cacheWrite: 0,
15180
15676
  },
15181
15677
  contextWindow: 400000,
@@ -15192,7 +15688,7 @@ export const MODELS = {
15192
15688
  cost: {
15193
15689
  input: 1.25,
15194
15690
  output: 10,
15195
- cacheRead: 0.125,
15691
+ cacheRead: 0.13,
15196
15692
  cacheWrite: 0,
15197
15693
  },
15198
15694
  contextWindow: 128000,
@@ -15411,10 +15907,10 @@ export const MODELS = {
15411
15907
  reasoning: true,
15412
15908
  input: ["text", "image"],
15413
15909
  cost: {
15414
- input: 1,
15415
- output: 6,
15416
- cacheRead: 0.09999999999999999,
15417
- cacheWrite: 1.25,
15910
+ input: 0.19999999999999998,
15911
+ output: 1.2,
15912
+ cacheRead: 0.02,
15913
+ cacheWrite: 0.25,
15418
15914
  },
15419
15915
  contextWindow: 1050000,
15420
15916
  maxTokens: 128000,
@@ -15445,10 +15941,10 @@ export const MODELS = {
15445
15941
  reasoning: true,
15446
15942
  input: ["text", "image"],
15447
15943
  cost: {
15448
- input: 2.5,
15449
- output: 15,
15450
- cacheRead: 0.25,
15451
- cacheWrite: 3.125,
15944
+ input: 2,
15945
+ output: 12,
15946
+ cacheRead: 0.19999999999999998,
15947
+ cacheWrite: 2.5,
15452
15948
  },
15453
15949
  contextWindow: 1050000,
15454
15950
  maxTokens: 128000,
@@ -15725,6 +16221,23 @@ export const MODELS = {
15725
16221
  contextWindow: 256000,
15726
16222
  maxTokens: 256000,
15727
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
+ },
15728
16241
  "xai/grok-4.1-fast-non-reasoning": {
15729
16242
  id: "xai/grok-4.1-fast-non-reasoning",
15730
16243
  name: "Grok 4.1 Fast Non-Reasoning",
@@ -16108,9 +16621,9 @@ export const MODELS = {
16108
16621
  reasoning: true,
16109
16622
  input: ["text"],
16110
16623
  cost: {
16111
- input: 0.95,
16112
- output: 3.15,
16113
- cacheRead: 0.19999999999999998,
16624
+ input: 1,
16625
+ output: 3.1999999999999997,
16626
+ cacheRead: 0,
16114
16627
  cacheWrite: 0,
16115
16628
  },
16116
16629
  contextWindow: 202800,
@@ -16142,8 +16655,8 @@ export const MODELS = {
16142
16655
  reasoning: true,
16143
16656
  input: ["text"],
16144
16657
  cost: {
16145
- input: 1.3,
16146
- output: 4.300000000000001,
16658
+ input: 1.4,
16659
+ output: 4.4,
16147
16660
  cacheRead: 0.26,
16148
16661
  cacheWrite: 0,
16149
16662
  },
@@ -16159,12 +16672,12 @@ export const MODELS = {
16159
16672
  reasoning: true,
16160
16673
  input: ["text"],
16161
16674
  cost: {
16162
- input: 1.4,
16163
- output: 4.4,
16164
- cacheRead: 0.26,
16675
+ input: 1.1,
16676
+ output: 3.851,
16677
+ cacheRead: 0.275,
16165
16678
  cacheWrite: 0,
16166
16679
  },
16167
- contextWindow: 1040000,
16680
+ contextWindow: 1000000,
16168
16681
  maxTokens: 128000,
16169
16682
  },
16170
16683
  "zai/glm-5.2-fast": {