@dreb/ai 2.49.0 → 2.51.0

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.
Files changed (5) hide show
  1. package/dist/models.generated.d.ts +140 -494
  2. package/dist/models.generated.d.ts.map +1 -1
  3. package/dist/models.generated.js +174 -530
  4. package/dist/models.generated.js.map +1 -1
  5. package/package.json +1 -1
package/dist/models.generated.js CHANGED
@@ -5273,6 +5273,24 @@ export const MODELS = {
5273
5273
  contextWindow: 1048576,
5274
5274
  maxTokens: 1048576,
5275
5275
  },
5276
+ "thinkingmachines/Inkling-Small": {
5277
+ id: "thinkingmachines/Inkling-Small",
5278
+ name: "Inkling Small",
5279
+ api: "openai-completions",
5280
+ provider: "huggingface",
5281
+ baseUrl: "https://router.huggingface.co/v1",
5282
+ compat: { "supportsDeveloperRole": false },
5283
+ reasoning: true,
5284
+ input: ["text", "image"],
5285
+ cost: {
5286
+ input: 0.5,
5287
+ output: 1.2,
5288
+ cacheRead: 0,
5289
+ cacheWrite: 0,
5290
+ },
5291
+ contextWindow: 524288,
5292
+ maxTokens: 1048576,
5293
+ },
5276
5294
  "zai-org/GLM-4.5": {
5277
5295
  id: "zai-org/GLM-4.5",
5278
5296
  name: "GLM-4.5",
@@ -6162,6 +6180,23 @@ export const MODELS = {
6162
6180
  contextWindow: 128000,
6163
6181
  maxTokens: 128000,
6164
6182
  },
6183
+ "voxtral-small-latest": {
6184
+ id: "voxtral-small-latest",
6185
+ name: "Voxtral Small (latest)",
6186
+ api: "mistral-conversations",
6187
+ provider: "mistral",
6188
+ baseUrl: "https://api.mistral.ai",
6189
+ reasoning: false,
6190
+ input: ["text"],
6191
+ cost: {
6192
+ input: 0.1,
6193
+ output: 0.3,
6194
+ cacheRead: 0,
6195
+ cacheWrite: 0,
6196
+ },
6197
+ contextWindow: 32000,
6198
+ maxTokens: 32000,
6199
+ },
6165
6200
  },
6166
6201
  "openai": {
6167
6202
  "gpt-4": {
@@ -7275,7 +7310,7 @@ export const MODELS = {
7275
7310
  },
7276
7311
  "deepseek-v4-flash": {
7277
7312
  id: "deepseek-v4-flash",
7278
- name: "DeepSeek V4 Flash",
7313
+ name: "DeepSeek V4 Flash 0731",
7279
7314
  api: "openai-completions",
7280
7315
  provider: "opencode",
7281
7316
  baseUrl: "https://opencode.ai/zen/v1",
@@ -8346,6 +8381,23 @@ export const MODELS = {
8346
8381
  contextWindow: 1000000,
8347
8382
  maxTokens: 65536,
8348
8383
  },
8384
+ "qwen3.8-max": {
8385
+ id: "qwen3.8-max",
8386
+ name: "Qwen3.8 Max",
8387
+ api: "anthropic-messages",
8388
+ provider: "opencode-go",
8389
+ baseUrl: "https://opencode.ai/zen/go",
8390
+ reasoning: true,
8391
+ input: ["text", "image"],
8392
+ cost: {
8393
+ input: 2,
8394
+ output: 6,
8395
+ cacheRead: 0.25,
8396
+ cacheWrite: 2.5,
8397
+ },
8398
+ contextWindow: 1000000,
8399
+ maxTokens: 131072,
8400
+ },
8349
8401
  },
8350
8402
  "openrouter": {
8351
8403
  "ai21/jamba-large-1.7": {
@@ -8535,23 +8587,6 @@ export const MODELS = {
8535
8587
  contextWindow: 1000000,
8536
8588
  maxTokens: 128000,
8537
8589
  },
8538
- "anthropic/claude-fable-5:batch": {
8539
- id: "anthropic/claude-fable-5:batch",
8540
- name: "Anthropic: Claude Fable 5 (batch)",
8541
- api: "openai-completions",
8542
- provider: "openrouter",
8543
- baseUrl: "https://openrouter.ai/api/v1",
8544
- reasoning: true,
8545
- input: ["text", "image"],
8546
- cost: {
8547
- input: 5,
8548
- output: 25,
8549
- cacheRead: 0.5,
8550
- cacheWrite: 6.25,
8551
- },
8552
- contextWindow: 1000000,
8553
- maxTokens: 128000,
8554
- },
8555
8590
  "anthropic/claude-haiku-4.5": {
8556
8591
  id: "anthropic/claude-haiku-4.5",
8557
8592
  name: "Anthropic: Claude Haiku 4.5",
@@ -8569,23 +8604,6 @@ export const MODELS = {
8569
8604
  contextWindow: 200000,
8570
8605
  maxTokens: 64000,
8571
8606
  },
8572
- "anthropic/claude-haiku-4.5:batch": {
8573
- id: "anthropic/claude-haiku-4.5:batch",
8574
- name: "Anthropic: Claude Haiku 4.5 (batch)",
8575
- api: "openai-completions",
8576
- provider: "openrouter",
8577
- baseUrl: "https://openrouter.ai/api/v1",
8578
- reasoning: true,
8579
- input: ["text", "image"],
8580
- cost: {
8581
- input: 0.5,
8582
- output: 2.5,
8583
- cacheRead: 0.049999999999999996,
8584
- cacheWrite: 0.625,
8585
- },
8586
- contextWindow: 200000,
8587
- maxTokens: 64000,
8588
- },
8589
8607
  "anthropic/claude-opus-4": {
8590
8608
  id: "anthropic/claude-opus-4",
8591
8609
  name: "Anthropic: Claude Opus 4",
@@ -8620,23 +8638,6 @@ export const MODELS = {
8620
8638
  contextWindow: 200000,
8621
8639
  maxTokens: 32000,
8622
8640
  },
8623
- "anthropic/claude-opus-4.1:batch": {
8624
- id: "anthropic/claude-opus-4.1:batch",
8625
- name: "Anthropic: Claude Opus 4.1 (batch)",
8626
- api: "openai-completions",
8627
- provider: "openrouter",
8628
- baseUrl: "https://openrouter.ai/api/v1",
8629
- reasoning: true,
8630
- input: ["text", "image"],
8631
- cost: {
8632
- input: 7.5,
8633
- output: 37.5,
8634
- cacheRead: 0.75,
8635
- cacheWrite: 9.375,
8636
- },
8637
- contextWindow: 200000,
8638
- maxTokens: 32000,
8639
- },
8640
8641
  "anthropic/claude-opus-4.5": {
8641
8642
  id: "anthropic/claude-opus-4.5",
8642
8643
  name: "Anthropic: Claude Opus 4.5",
@@ -8654,23 +8655,6 @@ export const MODELS = {
8654
8655
  contextWindow: 200000,
8655
8656
  maxTokens: 64000,
8656
8657
  },
8657
- "anthropic/claude-opus-4.5:batch": {
8658
- id: "anthropic/claude-opus-4.5:batch",
8659
- name: "Anthropic: Claude Opus 4.5 (batch)",
8660
- api: "openai-completions",
8661
- provider: "openrouter",
8662
- baseUrl: "https://openrouter.ai/api/v1",
8663
- reasoning: true,
8664
- input: ["text", "image"],
8665
- cost: {
8666
- input: 2.5,
8667
- output: 12.5,
8668
- cacheRead: 0.25,
8669
- cacheWrite: 3.125,
8670
- },
8671
- contextWindow: 200000,
8672
- maxTokens: 64000,
8673
- },
8674
8658
  "anthropic/claude-opus-4.6": {
8675
8659
  id: "anthropic/claude-opus-4.6",
8676
8660
  name: "Anthropic: Claude Opus 4.6",
@@ -8688,23 +8672,6 @@ export const MODELS = {
8688
8672
  contextWindow: 1000000,
8689
8673
  maxTokens: 128000,
8690
8674
  },
8691
- "anthropic/claude-opus-4.6:batch": {
8692
- id: "anthropic/claude-opus-4.6:batch",
8693
- name: "Anthropic: Claude Opus 4.6 (batch)",
8694
- api: "openai-completions",
8695
- provider: "openrouter",
8696
- baseUrl: "https://openrouter.ai/api/v1",
8697
- reasoning: true,
8698
- input: ["text", "image"],
8699
- cost: {
8700
- input: 2.5,
8701
- output: 12.5,
8702
- cacheRead: 0.25,
8703
- cacheWrite: 3.125,
8704
- },
8705
- contextWindow: 1000000,
8706
- maxTokens: 128000,
8707
- },
8708
8675
  "anthropic/claude-opus-4.7": {
8709
8676
  id: "anthropic/claude-opus-4.7",
8710
8677
  name: "Anthropic: Claude Opus 4.7",
@@ -8739,23 +8706,6 @@ export const MODELS = {
8739
8706
  contextWindow: 1000000,
8740
8707
  maxTokens: 128000,
8741
8708
  },
8742
- "anthropic/claude-opus-4.7:batch": {
8743
- id: "anthropic/claude-opus-4.7:batch",
8744
- name: "Anthropic: Claude Opus 4.7 (batch)",
8745
- api: "openai-completions",
8746
- provider: "openrouter",
8747
- baseUrl: "https://openrouter.ai/api/v1",
8748
- reasoning: true,
8749
- input: ["text", "image"],
8750
- cost: {
8751
- input: 2.5,
8752
- output: 12.5,
8753
- cacheRead: 0.25,
8754
- cacheWrite: 3.125,
8755
- },
8756
- contextWindow: 1000000,
8757
- maxTokens: 128000,
8758
- },
8759
8709
  "anthropic/claude-opus-4.8": {
8760
8710
  id: "anthropic/claude-opus-4.8",
8761
8711
  name: "Anthropic: Claude Opus 4.8",
@@ -8790,23 +8740,6 @@ export const MODELS = {
8790
8740
  contextWindow: 1000000,
8791
8741
  maxTokens: 128000,
8792
8742
  },
8793
- "anthropic/claude-opus-4.8:batch": {
8794
- id: "anthropic/claude-opus-4.8:batch",
8795
- name: "Anthropic: Claude Opus 4.8 (batch)",
8796
- api: "openai-completions",
8797
- provider: "openrouter",
8798
- baseUrl: "https://openrouter.ai/api/v1",
8799
- reasoning: true,
8800
- input: ["text", "image"],
8801
- cost: {
8802
- input: 2.5,
8803
- output: 12.5,
8804
- cacheRead: 0.25,
8805
- cacheWrite: 3.125,
8806
- },
8807
- contextWindow: 1000000,
8808
- maxTokens: 128000,
8809
- },
8810
8743
  "anthropic/claude-opus-5": {
8811
8744
  id: "anthropic/claude-opus-5",
8812
8745
  name: "Claude Opus 5",
@@ -8875,23 +8808,6 @@ export const MODELS = {
8875
8808
  contextWindow: 1000000,
8876
8809
  maxTokens: 64000,
8877
8810
  },
8878
- "anthropic/claude-sonnet-4.5:batch": {
8879
- id: "anthropic/claude-sonnet-4.5:batch",
8880
- name: "Anthropic: Claude Sonnet 4.5 (batch)",
8881
- api: "openai-completions",
8882
- provider: "openrouter",
8883
- baseUrl: "https://openrouter.ai/api/v1",
8884
- reasoning: true,
8885
- input: ["text", "image"],
8886
- cost: {
8887
- input: 1.5,
8888
- output: 7.5,
8889
- cacheRead: 0.15,
8890
- cacheWrite: 1.875,
8891
- },
8892
- contextWindow: 1000000,
8893
- maxTokens: 64000,
8894
- },
8895
8811
  "anthropic/claude-sonnet-4.6": {
8896
8812
  id: "anthropic/claude-sonnet-4.6",
8897
8813
  name: "Anthropic: Claude Sonnet 4.6",
@@ -8926,23 +8842,6 @@ export const MODELS = {
8926
8842
  contextWindow: 1000000,
8927
8843
  maxTokens: 128000,
8928
8844
  },
8929
- "anthropic/claude-sonnet-5:batch": {
8930
- id: "anthropic/claude-sonnet-5:batch",
8931
- name: "Anthropic: Claude Sonnet 5 (batch)",
8932
- api: "openai-completions",
8933
- provider: "openrouter",
8934
- baseUrl: "https://openrouter.ai/api/v1",
8935
- reasoning: true,
8936
- input: ["text", "image"],
8937
- cost: {
8938
- input: 1,
8939
- output: 5,
8940
- cacheRead: 0.09999999999999999,
8941
- cacheWrite: 1.25,
8942
- },
8943
- contextWindow: 1000000,
8944
- maxTokens: 128000,
8945
- },
8946
8845
  "arcee-ai/trinity-large-thinking": {
8947
8846
  id: "arcee-ai/trinity-large-thinking",
8948
8847
  name: "Arcee AI: Trinity Large Thinking",
@@ -9275,13 +9174,13 @@ export const MODELS = {
9275
9174
  reasoning: true,
9276
9175
  input: ["text"],
9277
9176
  cost: {
9278
- input: 0.14,
9279
- output: 0.28,
9280
- cacheRead: 0.0028,
9177
+ input: 0.09,
9178
+ output: 0.18,
9179
+ cacheRead: 0.018,
9281
9180
  cacheWrite: 0,
9282
9181
  },
9283
9182
  contextWindow: 1048576,
9284
- maxTokens: 384000,
9183
+ maxTokens: 65536,
9285
9184
  },
9286
9185
  "deepseek/deepseek-v4-pro": {
9287
9186
  id: "deepseek/deepseek-v4-pro",
@@ -9334,40 +9233,6 @@ export const MODELS = {
9334
9233
  contextWindow: 1048576,
9335
9234
  maxTokens: 65535,
9336
9235
  },
9337
- "google/gemini-2.5-flash-lite:batch": {
9338
- id: "google/gemini-2.5-flash-lite:batch",
9339
- name: "Google: Gemini 2.5 Flash Lite (batch)",
9340
- api: "openai-completions",
9341
- provider: "openrouter",
9342
- baseUrl: "https://openrouter.ai/api/v1",
9343
- reasoning: true,
9344
- input: ["text", "image"],
9345
- cost: {
9346
- input: 0.049999999999999996,
9347
- output: 0.19999999999999998,
9348
- cacheRead: 0.01,
9349
- cacheWrite: 0,
9350
- },
9351
- contextWindow: 1048576,
9352
- maxTokens: 65535,
9353
- },
9354
- "google/gemini-2.5-flash:batch": {
9355
- id: "google/gemini-2.5-flash:batch",
9356
- name: "Google: Gemini 2.5 Flash (batch)",
9357
- api: "openai-completions",
9358
- provider: "openrouter",
9359
- baseUrl: "https://openrouter.ai/api/v1",
9360
- reasoning: true,
9361
- input: ["text", "image"],
9362
- cost: {
9363
- input: 0.15,
9364
- output: 1.25,
9365
- cacheRead: 0.03,
9366
- cacheWrite: 0,
9367
- },
9368
- contextWindow: 1048576,
9369
- maxTokens: 65535,
9370
- },
9371
9236
  "google/gemini-2.5-pro": {
9372
9237
  id: "google/gemini-2.5-pro",
9373
9238
  name: "Google: Gemini 2.5 Pro",
@@ -9419,23 +9284,6 @@ export const MODELS = {
9419
9284
  contextWindow: 1048576,
9420
9285
  maxTokens: 65535,
9421
9286
  },
9422
- "google/gemini-2.5-pro:batch": {
9423
- id: "google/gemini-2.5-pro:batch",
9424
- name: "Google: Gemini 2.5 Pro (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: 0.625,
9432
- output: 5,
9433
- cacheRead: 0.125,
9434
- cacheWrite: 0,
9435
- },
9436
- contextWindow: 1048576,
9437
- maxTokens: 65536,
9438
- },
9439
9287
  "google/gemini-3-flash-preview": {
9440
9288
  id: "google/gemini-3-flash-preview",
9441
9289
  name: "Google: Gemini 3 Flash Preview",
@@ -9453,23 +9301,6 @@ export const MODELS = {
9453
9301
  contextWindow: 1048576,
9454
9302
  maxTokens: 65535,
9455
9303
  },
9456
- "google/gemini-3-flash-preview:batch": {
9457
- id: "google/gemini-3-flash-preview:batch",
9458
- name: "Google: Gemini 3 Flash Preview (batch)",
9459
- api: "openai-completions",
9460
- provider: "openrouter",
9461
- baseUrl: "https://openrouter.ai/api/v1",
9462
- reasoning: true,
9463
- input: ["text", "image"],
9464
- cost: {
9465
- input: 0.25,
9466
- output: 1.5,
9467
- cacheRead: 0,
9468
- cacheWrite: 0,
9469
- },
9470
- contextWindow: 1048576,
9471
- maxTokens: 65535,
9472
- },
9473
9304
  "google/gemini-3-pro-image": {
9474
9305
  id: "google/gemini-3-pro-image",
9475
9306
  name: "Google: Nano Banana Pro (Gemini 3 Pro Image)",
@@ -9521,23 +9352,6 @@ export const MODELS = {
9521
9352
  contextWindow: 1048576,
9522
9353
  maxTokens: 65536,
9523
9354
  },
9524
- "google/gemini-3.1-flash-lite:batch": {
9525
- id: "google/gemini-3.1-flash-lite:batch",
9526
- name: "Google: Gemini 3.1 Flash Lite (batch)",
9527
- api: "openai-completions",
9528
- provider: "openrouter",
9529
- baseUrl: "https://openrouter.ai/api/v1",
9530
- reasoning: true,
9531
- input: ["text", "image"],
9532
- cost: {
9533
- input: 0.125,
9534
- output: 0.75,
9535
- cacheRead: 0.012499999999999999,
9536
- cacheWrite: 0,
9537
- },
9538
- contextWindow: 1048576,
9539
- maxTokens: 65536,
9540
- },
9541
9355
  "google/gemini-3.1-pro-preview": {
9542
9356
  id: "google/gemini-3.1-pro-preview",
9543
9357
  name: "Google: Gemini 3.1 Pro Preview",
@@ -9572,23 +9386,6 @@ export const MODELS = {
9572
9386
  contextWindow: 1048576,
9573
9387
  maxTokens: 65536,
9574
9388
  },
9575
- "google/gemini-3.1-pro-preview:batch": {
9576
- id: "google/gemini-3.1-pro-preview:batch",
9577
- name: "Google: Gemini 3.1 Pro Preview (batch)",
9578
- api: "openai-completions",
9579
- provider: "openrouter",
9580
- baseUrl: "https://openrouter.ai/api/v1",
9581
- reasoning: true,
9582
- input: ["text", "image"],
9583
- cost: {
9584
- input: 1,
9585
- output: 6,
9586
- cacheRead: 0,
9587
- cacheWrite: 0,
9588
- },
9589
- contextWindow: 1048576,
9590
- maxTokens: 65536,
9591
- },
9592
9389
  "google/gemini-3.5-flash": {
9593
9390
  id: "google/gemini-3.5-flash",
9594
9391
  name: "Google: Gemini 3.5 Flash",
@@ -9598,94 +9395,43 @@ export const MODELS = {
9598
9395
  reasoning: true,
9599
9396
  input: ["text", "image"],
9600
9397
  cost: {
9601
- input: 1.5,
9602
- output: 9,
9603
- cacheRead: 0.15,
9604
- cacheWrite: 0.08333333333333334,
9605
- },
9606
- contextWindow: 1048576,
9607
- maxTokens: 65536,
9608
- },
9609
- "google/gemini-3.5-flash-lite": {
9610
- id: "google/gemini-3.5-flash-lite",
9611
- name: "Google: Gemini 3.5 Flash Lite",
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: 0.3,
9619
- output: 2.5,
9620
- cacheRead: 0.03,
9621
- cacheWrite: 0.08333333333333334,
9622
- },
9623
- contextWindow: 1048576,
9624
- maxTokens: 65536,
9625
- },
9626
- "google/gemini-3.5-flash-lite:batch": {
9627
- id: "google/gemini-3.5-flash-lite:batch",
9628
- name: "Google: Gemini 3.5 Flash Lite (batch)",
9629
- api: "openai-completions",
9630
- provider: "openrouter",
9631
- baseUrl: "https://openrouter.ai/api/v1",
9632
- reasoning: true,
9633
- input: ["text", "image"],
9634
- cost: {
9635
- input: 0.15,
9636
- output: 1.25,
9637
- cacheRead: 0.015,
9638
- cacheWrite: 0,
9639
- },
9640
- contextWindow: 1048576,
9641
- maxTokens: 65536,
9642
- },
9643
- "google/gemini-3.5-flash:batch": {
9644
- id: "google/gemini-3.5-flash:batch",
9645
- name: "Google: Gemini 3.5 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: 4.5,
9654
- cacheRead: 0.075,
9655
- cacheWrite: 0,
9398
+ input: 1.5,
9399
+ output: 9,
9400
+ cacheRead: 0.15,
9401
+ cacheWrite: 0.08333333333333334,
9656
9402
  },
9657
9403
  contextWindow: 1048576,
9658
9404
  maxTokens: 65536,
9659
9405
  },
9660
- "google/gemini-3.6-flash": {
9661
- id: "google/gemini-3.6-flash",
9662
- name: "Google: Gemini 3.6 Flash",
9406
+ "google/gemini-3.5-flash-lite": {
9407
+ id: "google/gemini-3.5-flash-lite",
9408
+ name: "Google: Gemini 3.5 Flash Lite",
9663
9409
  api: "openai-completions",
9664
9410
  provider: "openrouter",
9665
9411
  baseUrl: "https://openrouter.ai/api/v1",
9666
9412
  reasoning: true,
9667
9413
  input: ["text", "image"],
9668
9414
  cost: {
9669
- input: 1.5,
9670
- output: 7.5,
9671
- cacheRead: 0.15,
9415
+ input: 0.3,
9416
+ output: 2.5,
9417
+ cacheRead: 0.03,
9672
9418
  cacheWrite: 0.08333333333333334,
9673
9419
  },
9674
9420
  contextWindow: 1048576,
9675
9421
  maxTokens: 65536,
9676
9422
  },
9677
- "google/gemini-3.6-flash:batch": {
9678
- id: "google/gemini-3.6-flash:batch",
9679
- name: "Google: Gemini 3.6 Flash (batch)",
9423
+ "google/gemini-3.6-flash": {
9424
+ id: "google/gemini-3.6-flash",
9425
+ name: "Google: Gemini 3.6 Flash",
9680
9426
  api: "openai-completions",
9681
9427
  provider: "openrouter",
9682
9428
  baseUrl: "https://openrouter.ai/api/v1",
9683
9429
  reasoning: true,
9684
9430
  input: ["text", "image"],
9685
9431
  cost: {
9686
- input: 0.75,
9687
- output: 3.75,
9688
- cacheRead: 0.075,
9432
+ input: 1.5,
9433
+ output: 7.5,
9434
+ cacheRead: 0.15,
9689
9435
  cacheWrite: 0.08333333333333334,
9690
9436
  },
9691
9437
  contextWindow: 1048576,
@@ -10167,23 +9913,6 @@ export const MODELS = {
10167
9913
  contextWindow: 1048576,
10168
9914
  maxTokens: 512000,
10169
9915
  },
10170
- "minimax/minimax-m3:batch": {
10171
- id: "minimax/minimax-m3:batch",
10172
- name: "MiniMax: MiniMax M3 (batch)",
10173
- api: "openai-completions",
10174
- provider: "openrouter",
10175
- baseUrl: "https://openrouter.ai/api/v1",
10176
- reasoning: true,
10177
- input: ["text", "image"],
10178
- cost: {
10179
- input: 0.15,
10180
- output: 0.6,
10181
- cacheRead: 0.03,
10182
- cacheWrite: 0,
10183
- },
10184
- contextWindow: 524288,
10185
- maxTokens: 4096,
10186
- },
10187
9916
  "mistralai/codestral-2508": {
10188
9917
  id: "mistralai/codestral-2508",
10189
9918
  name: "Mistral: Codestral 2508",
@@ -10533,9 +10262,9 @@ export const MODELS = {
10533
10262
  reasoning: true,
10534
10263
  input: ["text", "image"],
10535
10264
  cost: {
10536
- input: 0.589,
10537
- output: 2.48,
10538
- cacheRead: 0.0992,
10265
+ input: 0.6,
10266
+ output: 3.41,
10267
+ cacheRead: 0.19999999999999998,
10539
10268
  cacheWrite: 0,
10540
10269
  },
10541
10270
  contextWindow: 262144,
@@ -11051,23 +10780,6 @@ export const MODELS = {
11051
10780
  contextWindow: 400000,
11052
10781
  maxTokens: 128000,
11053
10782
  },
11054
- "openai/gpt-5-mini:batch": {
11055
- id: "openai/gpt-5-mini:batch",
11056
- name: "OpenAI: GPT-5 Mini (batch)",
11057
- api: "openai-completions",
11058
- provider: "openrouter",
11059
- baseUrl: "https://openrouter.ai/api/v1",
11060
- reasoning: true,
11061
- input: ["text", "image"],
11062
- cost: {
11063
- input: 0.125,
11064
- output: 1,
11065
- cacheRead: 0.012499999999999999,
11066
- cacheWrite: 0,
11067
- },
11068
- contextWindow: 400000,
11069
- maxTokens: 128000,
11070
- },
11071
10783
  "openai/gpt-5-nano": {
11072
10784
  id: "openai/gpt-5-nano",
11073
10785
  name: "OpenAI: GPT-5 Nano",
@@ -11085,23 +10797,6 @@ export const MODELS = {
11085
10797
  contextWindow: 400000,
11086
10798
  maxTokens: 128000,
11087
10799
  },
11088
- "openai/gpt-5-nano:batch": {
11089
- id: "openai/gpt-5-nano:batch",
11090
- name: "OpenAI: GPT-5 Nano (batch)",
11091
- api: "openai-completions",
11092
- provider: "openrouter",
11093
- baseUrl: "https://openrouter.ai/api/v1",
11094
- reasoning: true,
11095
- input: ["text", "image"],
11096
- cost: {
11097
- input: 0.024999999999999998,
11098
- output: 0.19999999999999998,
11099
- cacheRead: 0.0025,
11100
- cacheWrite: 0,
11101
- },
11102
- contextWindow: 400000,
11103
- maxTokens: 128000,
11104
- },
11105
10800
  "openai/gpt-5-pro": {
11106
10801
  id: "openai/gpt-5-pro",
11107
10802
  name: "OpenAI: GPT-5 Pro",
@@ -11187,23 +10882,6 @@ export const MODELS = {
11187
10882
  contextWindow: 400000,
11188
10883
  maxTokens: 128000,
11189
10884
  },
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
- },
11207
10885
  "openai/gpt-5.2": {
11208
10886
  id: "openai/gpt-5.2",
11209
10887
  name: "OpenAI: GPT-5.2",
@@ -11272,23 +10950,6 @@ export const MODELS = {
11272
10950
  contextWindow: 400000,
11273
10951
  maxTokens: 128000,
11274
10952
  },
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
- },
11292
10953
  "openai/gpt-5.3-chat": {
11293
10954
  id: "openai/gpt-5.3-chat",
11294
10955
  name: "OpenAI: GPT-5.3 Chat",
@@ -11357,23 +11018,6 @@ export const MODELS = {
11357
11018
  contextWindow: 400000,
11358
11019
  maxTokens: 128000,
11359
11020
  },
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
- },
11377
11021
  "openai/gpt-5.4-nano": {
11378
11022
  id: "openai/gpt-5.4-nano",
11379
11023
  name: "OpenAI: GPT-5.4 Nano",
@@ -11391,23 +11035,6 @@ export const MODELS = {
11391
11035
  contextWindow: 400000,
11392
11036
  maxTokens: 128000,
11393
11037
  },
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
11038
  "openai/gpt-5.4-pro": {
11412
11039
  id: "openai/gpt-5.4-pro",
11413
11040
  name: "OpenAI: GPT-5.4 Pro",
@@ -11425,23 +11052,6 @@ export const MODELS = {
11425
11052
  contextWindow: 1050000,
11426
11053
  maxTokens: 128000,
11427
11054
  },
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
- },
11445
11055
  "openai/gpt-5.5": {
11446
11056
  id: "openai/gpt-5.5",
11447
11057
  name: "OpenAI: GPT-5.5",
@@ -11476,23 +11086,6 @@ export const MODELS = {
11476
11086
  contextWindow: 1050000,
11477
11087
  maxTokens: 128000,
11478
11088
  },
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
- },
11496
11089
  "openai/gpt-5.6-luna": {
11497
11090
  id: "openai/gpt-5.6-luna",
11498
11091
  name: "OpenAI: GPT-5.6 Luna",
@@ -11503,9 +11096,9 @@ export const MODELS = {
11503
11096
  input: ["text", "image"],
11504
11097
  cost: {
11505
11098
  input: 0.09999999999999999,
11506
- output: 0.6000000000000001,
11099
+ output: 0.6,
11507
11100
  cacheRead: 0.01,
11508
- cacheWrite: 0.12500000000000003,
11101
+ cacheWrite: 0.125,
11509
11102
  },
11510
11103
  contextWindow: 1050000,
11511
11104
  maxTokens: 128000,
@@ -11520,9 +11113,9 @@ export const MODELS = {
11520
11113
  input: ["text", "image"],
11521
11114
  cost: {
11522
11115
  input: 0.09999999999999999,
11523
- output: 0.6000000000000001,
11116
+ output: 0.6,
11524
11117
  cacheRead: 0.01,
11525
- cacheWrite: 0.12500000000000003,
11118
+ cacheWrite: 0.125,
11526
11119
  },
11527
11120
  contextWindow: 1050000,
11528
11121
  maxTokens: 128000,
@@ -11570,7 +11163,7 @@ export const MODELS = {
11570
11163
  reasoning: true,
11571
11164
  input: ["text", "image"],
11572
11165
  cost: {
11573
- input: 1.0000000000000002,
11166
+ input: 1,
11574
11167
  output: 6,
11575
11168
  cacheRead: 0.09999999999999999,
11576
11169
  cacheWrite: 1.25,
@@ -11587,7 +11180,7 @@ export const MODELS = {
11587
11180
  reasoning: true,
11588
11181
  input: ["text", "image"],
11589
11182
  cost: {
11590
- input: 1.0000000000000002,
11183
+ input: 1,
11591
11184
  output: 6,
11592
11185
  cacheRead: 0.09999999999999999,
11593
11186
  cacheWrite: 1.25,
@@ -11595,23 +11188,6 @@ export const MODELS = {
11595
11188
  contextWindow: 1050000,
11596
11189
  maxTokens: 128000,
11597
11190
  },
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
- },
11615
11191
  "openai/gpt-audio": {
11616
11192
  id: "openai/gpt-audio",
11617
11193
  name: "OpenAI: GPT Audio",
@@ -11690,8 +11266,8 @@ export const MODELS = {
11690
11266
  input: ["text"],
11691
11267
  cost: {
11692
11268
  input: 0.03,
11693
- output: 0.14,
11694
- cacheRead: 0,
11269
+ output: 0.13,
11270
+ cacheRead: 0.03,
11695
11271
  cacheWrite: 0,
11696
11272
  },
11697
11273
  contextWindow: 131072,
@@ -12097,13 +11673,13 @@ export const MODELS = {
12097
11673
  reasoning: false,
12098
11674
  input: ["text"],
12099
11675
  cost: {
12100
- input: 0.09,
12101
- output: 0.55,
11676
+ input: 0.14950000000000002,
11677
+ output: 0.5980000000000001,
12102
11678
  cacheRead: 0,
12103
11679
  cacheWrite: 0,
12104
11680
  },
12105
11681
  contextWindow: 262144,
12106
- maxTokens: 16384,
11682
+ maxTokens: 32768,
12107
11683
  },
12108
11684
  "qwen/qwen3-235b-a22b-thinking-2507": {
12109
11685
  id: "qwen/qwen3-235b-a22b-thinking-2507",
@@ -12234,12 +11810,12 @@ export const MODELS = {
12234
11810
  input: ["text"],
12235
11811
  cost: {
12236
11812
  input: 0.07,
12237
- output: 0.27,
11813
+ output: 0.28,
12238
11814
  cacheRead: 0,
12239
11815
  cacheWrite: 0,
12240
11816
  },
12241
11817
  contextWindow: 262144,
12242
- maxTokens: 32768,
11818
+ maxTokens: 262144,
12243
11819
  },
12244
11820
  "qwen/qwen3-coder-flash": {
12245
11821
  id: "qwen/qwen3-coder-flash",
@@ -12386,8 +11962,8 @@ export const MODELS = {
12386
11962
  reasoning: true,
12387
11963
  input: ["text", "image"],
12388
11964
  cost: {
12389
- input: 0.39999999999999997,
12390
- output: 4,
11965
+ input: 0.98,
11966
+ output: 3.95,
12391
11967
  cacheRead: 0,
12392
11968
  cacheWrite: 0,
12393
11969
  },
@@ -12488,8 +12064,8 @@ export const MODELS = {
12488
12064
  reasoning: true,
12489
12065
  input: ["text", "image"],
12490
12066
  cost: {
12491
- input: 0.26,
12492
- output: 2.08,
12067
+ input: 0.39999999999999997,
12068
+ output: 3.1999999999999997,
12493
12069
  cacheRead: 0,
12494
12070
  cacheWrite: 0,
12495
12071
  },
@@ -12902,7 +12478,7 @@ export const MODELS = {
12902
12478
  cacheWrite: 0,
12903
12479
  },
12904
12480
  contextWindow: 1024000,
12905
- maxTokens: 32768,
12481
+ maxTokens: 1024000,
12906
12482
  },
12907
12483
  "thinkingmachines/inkling": {
12908
12484
  id: "thinkingmachines/inkling",
@@ -12921,6 +12497,23 @@ export const MODELS = {
12921
12497
  contextWindow: 1048576,
12922
12498
  maxTokens: 4096,
12923
12499
  },
12500
+ "thinkingmachines/inkling-small": {
12501
+ id: "thinkingmachines/inkling-small",
12502
+ name: "Thinking Machines: Inkling Small",
12503
+ api: "openai-completions",
12504
+ provider: "openrouter",
12505
+ baseUrl: "https://openrouter.ai/api/v1",
12506
+ reasoning: true,
12507
+ input: ["text", "image"],
12508
+ cost: {
12509
+ input: 0.5,
12510
+ output: 1.2,
12511
+ cacheRead: 0.09999999999999999,
12512
+ cacheWrite: 0,
12513
+ },
12514
+ contextWindow: 524288,
12515
+ maxTokens: 4096,
12516
+ },
12924
12517
  "upstage/solar-pro-3": {
12925
12518
  id: "upstage/solar-pro-3",
12926
12519
  name: "Upstage: Solar Pro 3",
@@ -13219,13 +12812,13 @@ export const MODELS = {
13219
12812
  reasoning: true,
13220
12813
  input: ["text"],
13221
12814
  cost: {
13222
- input: 1.12,
13223
- output: 3.52,
13224
- cacheRead: 0.20800000000000002,
12815
+ input: 0.7153999999999999,
12816
+ output: 2.2483999999999997,
12817
+ cacheRead: 0.13286,
13225
12818
  cacheWrite: 0,
13226
12819
  },
13227
12820
  contextWindow: 1048576,
13228
- maxTokens: 128000,
12821
+ maxTokens: 131072,
13229
12822
  },
13230
12823
  "z-ai/glm-5v-turbo": {
13231
12824
  id: "z-ai/glm-5v-turbo",
@@ -13312,6 +12905,23 @@ export const MODELS = {
13312
12905
  contextWindow: 1000000,
13313
12906
  maxTokens: 128000,
13314
12907
  },
12908
+ "~deepseek/deepseek-v4-flash-latest": {
12909
+ id: "~deepseek/deepseek-v4-flash-latest",
12910
+ name: "DeepSeek V4 Flash Latest",
12911
+ api: "openai-completions",
12912
+ provider: "openrouter",
12913
+ baseUrl: "https://openrouter.ai/api/v1",
12914
+ reasoning: true,
12915
+ input: ["text"],
12916
+ cost: {
12917
+ input: 0.09,
12918
+ output: 0.18,
12919
+ cacheRead: 0.018,
12920
+ cacheWrite: 0,
12921
+ },
12922
+ contextWindow: 1048576,
12923
+ maxTokens: 65536,
12924
+ },
13315
12925
  "~google/gemini-flash-latest": {
13316
12926
  id: "~google/gemini-flash-latest",
13317
12927
  name: "Google Gemini Flash Latest",
@@ -13841,6 +13451,23 @@ export const MODELS = {
13841
13451
  contextWindow: 1000000,
13842
13452
  maxTokens: 64000,
13843
13453
  },
13454
+ "alibaba/qwen3.8-max": {
13455
+ id: "alibaba/qwen3.8-max",
13456
+ name: "Qwen 3.8 Max",
13457
+ api: "anthropic-messages",
13458
+ provider: "vercel-ai-gateway",
13459
+ baseUrl: "https://ai-gateway.vercel.sh",
13460
+ reasoning: true,
13461
+ input: ["text", "image"],
13462
+ cost: {
13463
+ input: 2,
13464
+ output: 6,
13465
+ cacheRead: 0.25,
13466
+ cacheWrite: 2.5,
13467
+ },
13468
+ contextWindow: 1000000,
13469
+ maxTokens: 128000,
13470
+ },
13844
13471
  "amazon/nova-2-lite": {
13845
13472
  id: "amazon/nova-2-lite",
13846
13473
  name: "Nova 2 Lite",
@@ -14377,8 +14004,25 @@ export const MODELS = {
14377
14004
  reasoning: true,
14378
14005
  input: ["text"],
14379
14006
  cost: {
14380
- input: 0.13799999999999998,
14381
- output: 0.275,
14007
+ input: 0.19999999999999998,
14008
+ output: 0.39999999999999997,
14009
+ cacheRead: 0.04,
14010
+ cacheWrite: 0,
14011
+ },
14012
+ contextWindow: 1000000,
14013
+ maxTokens: 384000,
14014
+ },
14015
+ "deepseek/deepseek-v4-flash-0731": {
14016
+ id: "deepseek/deepseek-v4-flash-0731",
14017
+ name: "DeepSeek V4 Flash 0731",
14018
+ api: "anthropic-messages",
14019
+ provider: "vercel-ai-gateway",
14020
+ baseUrl: "https://ai-gateway.vercel.sh",
14021
+ reasoning: true,
14022
+ input: ["text"],
14023
+ cost: {
14024
+ input: 0.13,
14025
+ output: 0.26,
14382
14026
  cacheRead: 0.028,
14383
14027
  cacheWrite: 0,
14384
14028
  },
@@ -14664,7 +14308,7 @@ export const MODELS = {
14664
14308
  provider: "vercel-ai-gateway",
14665
14309
  baseUrl: "https://ai-gateway.vercel.sh",
14666
14310
  reasoning: true,
14667
- input: ["text"],
14311
+ input: ["text", "image"],
14668
14312
  cost: {
14669
14313
  input: 0.15,
14670
14314
  output: 0.6,
@@ -14715,7 +14359,7 @@ export const MODELS = {
14715
14359
  provider: "vercel-ai-gateway",
14716
14360
  baseUrl: "https://ai-gateway.vercel.sh",
14717
14361
  reasoning: true,
14718
- input: ["text"],
14362
+ input: ["text", "image"],
14719
14363
  cost: {
14720
14364
  input: 0.74,
14721
14365
  output: 2.96,
@@ -15072,7 +14716,7 @@ export const MODELS = {
15072
14716
  provider: "vercel-ai-gateway",
15073
14717
  baseUrl: "https://ai-gateway.vercel.sh",
15074
14718
  reasoning: false,
15075
- input: ["text"],
14719
+ input: ["text", "image"],
15076
14720
  cost: {
15077
14721
  input: 0.09999999999999999,
15078
14722
  output: 0.09999999999999999,
@@ -15089,7 +14733,7 @@ export const MODELS = {
15089
14733
  provider: "vercel-ai-gateway",
15090
14734
  baseUrl: "https://ai-gateway.vercel.sh",
15091
14735
  reasoning: false,
15092
- input: ["text"],
14736
+ input: ["text", "image"],
15093
14737
  cost: {
15094
14738
  input: 0.15,
15095
14739
  output: 0.15,
@@ -15157,7 +14801,7 @@ export const MODELS = {
15157
14801
  provider: "vercel-ai-gateway",
15158
14802
  baseUrl: "https://ai-gateway.vercel.sh",
15159
14803
  reasoning: false,
15160
- input: ["text"],
14804
+ input: ["text", "image"],
15161
14805
  cost: {
15162
14806
  input: 0.15,
15163
14807
  output: 0.15,
@@ -16160,7 +15804,7 @@ export const MODELS = {
16160
15804
  provider: "vercel-ai-gateway",
16161
15805
  baseUrl: "https://ai-gateway.vercel.sh",
16162
15806
  reasoning: true,
16163
- input: ["text"],
15807
+ input: ["text", "image"],
16164
15808
  cost: {
16165
15809
  input: 0.09,
16166
15810
  output: 0.3,