@dreb/ai 2.49.0 → 2.50.0

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 +115 -503
  2. package/dist/models.generated.d.ts.map +1 -1
  3. package/dist/models.generated.js +112 -502
  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",
@@ -8535,23 +8570,6 @@ export const MODELS = {
8535
8570
  contextWindow: 1000000,
8536
8571
  maxTokens: 128000,
8537
8572
  },
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
8573
  "anthropic/claude-haiku-4.5": {
8556
8574
  id: "anthropic/claude-haiku-4.5",
8557
8575
  name: "Anthropic: Claude Haiku 4.5",
@@ -8569,23 +8587,6 @@ export const MODELS = {
8569
8587
  contextWindow: 200000,
8570
8588
  maxTokens: 64000,
8571
8589
  },
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
8590
  "anthropic/claude-opus-4": {
8590
8591
  id: "anthropic/claude-opus-4",
8591
8592
  name: "Anthropic: Claude Opus 4",
@@ -8620,23 +8621,6 @@ export const MODELS = {
8620
8621
  contextWindow: 200000,
8621
8622
  maxTokens: 32000,
8622
8623
  },
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
8624
  "anthropic/claude-opus-4.5": {
8641
8625
  id: "anthropic/claude-opus-4.5",
8642
8626
  name: "Anthropic: Claude Opus 4.5",
@@ -8654,23 +8638,6 @@ export const MODELS = {
8654
8638
  contextWindow: 200000,
8655
8639
  maxTokens: 64000,
8656
8640
  },
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
8641
  "anthropic/claude-opus-4.6": {
8675
8642
  id: "anthropic/claude-opus-4.6",
8676
8643
  name: "Anthropic: Claude Opus 4.6",
@@ -8688,23 +8655,6 @@ export const MODELS = {
8688
8655
  contextWindow: 1000000,
8689
8656
  maxTokens: 128000,
8690
8657
  },
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
8658
  "anthropic/claude-opus-4.7": {
8709
8659
  id: "anthropic/claude-opus-4.7",
8710
8660
  name: "Anthropic: Claude Opus 4.7",
@@ -8739,23 +8689,6 @@ export const MODELS = {
8739
8689
  contextWindow: 1000000,
8740
8690
  maxTokens: 128000,
8741
8691
  },
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
8692
  "anthropic/claude-opus-4.8": {
8760
8693
  id: "anthropic/claude-opus-4.8",
8761
8694
  name: "Anthropic: Claude Opus 4.8",
@@ -8790,23 +8723,6 @@ export const MODELS = {
8790
8723
  contextWindow: 1000000,
8791
8724
  maxTokens: 128000,
8792
8725
  },
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
8726
  "anthropic/claude-opus-5": {
8811
8727
  id: "anthropic/claude-opus-5",
8812
8728
  name: "Claude Opus 5",
@@ -8875,23 +8791,6 @@ export const MODELS = {
8875
8791
  contextWindow: 1000000,
8876
8792
  maxTokens: 64000,
8877
8793
  },
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
8794
  "anthropic/claude-sonnet-4.6": {
8896
8795
  id: "anthropic/claude-sonnet-4.6",
8897
8796
  name: "Anthropic: Claude Sonnet 4.6",
@@ -8926,23 +8825,6 @@ export const MODELS = {
8926
8825
  contextWindow: 1000000,
8927
8826
  maxTokens: 128000,
8928
8827
  },
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
8828
  "arcee-ai/trinity-large-thinking": {
8947
8829
  id: "arcee-ai/trinity-large-thinking",
8948
8830
  name: "Arcee AI: Trinity Large Thinking",
@@ -9275,13 +9157,13 @@ export const MODELS = {
9275
9157
  reasoning: true,
9276
9158
  input: ["text"],
9277
9159
  cost: {
9278
- input: 0.14,
9279
- output: 0.28,
9280
- cacheRead: 0.0028,
9160
+ input: 0.09,
9161
+ output: 0.18,
9162
+ cacheRead: 0.018,
9281
9163
  cacheWrite: 0,
9282
9164
  },
9283
9165
  contextWindow: 1048576,
9284
- maxTokens: 384000,
9166
+ maxTokens: 65536,
9285
9167
  },
9286
9168
  "deepseek/deepseek-v4-pro": {
9287
9169
  id: "deepseek/deepseek-v4-pro",
@@ -9334,40 +9216,6 @@ export const MODELS = {
9334
9216
  contextWindow: 1048576,
9335
9217
  maxTokens: 65535,
9336
9218
  },
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
9219
  "google/gemini-2.5-pro": {
9372
9220
  id: "google/gemini-2.5-pro",
9373
9221
  name: "Google: Gemini 2.5 Pro",
@@ -9419,23 +9267,6 @@ export const MODELS = {
9419
9267
  contextWindow: 1048576,
9420
9268
  maxTokens: 65535,
9421
9269
  },
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
9270
  "google/gemini-3-flash-preview": {
9440
9271
  id: "google/gemini-3-flash-preview",
9441
9272
  name: "Google: Gemini 3 Flash Preview",
@@ -9453,23 +9284,6 @@ export const MODELS = {
9453
9284
  contextWindow: 1048576,
9454
9285
  maxTokens: 65535,
9455
9286
  },
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
9287
  "google/gemini-3-pro-image": {
9474
9288
  id: "google/gemini-3-pro-image",
9475
9289
  name: "Google: Nano Banana Pro (Gemini 3 Pro Image)",
@@ -9521,23 +9335,6 @@ export const MODELS = {
9521
9335
  contextWindow: 1048576,
9522
9336
  maxTokens: 65536,
9523
9337
  },
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
9338
  "google/gemini-3.1-pro-preview": {
9542
9339
  id: "google/gemini-3.1-pro-preview",
9543
9340
  name: "Google: Gemini 3.1 Pro Preview",
@@ -9572,23 +9369,6 @@ export const MODELS = {
9572
9369
  contextWindow: 1048576,
9573
9370
  maxTokens: 65536,
9574
9371
  },
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
9372
  "google/gemini-3.5-flash": {
9593
9373
  id: "google/gemini-3.5-flash",
9594
9374
  name: "Google: Gemini 3.5 Flash",
@@ -9623,40 +9403,6 @@ export const MODELS = {
9623
9403
  contextWindow: 1048576,
9624
9404
  maxTokens: 65536,
9625
9405
  },
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,
9656
- },
9657
- contextWindow: 1048576,
9658
- maxTokens: 65536,
9659
- },
9660
9406
  "google/gemini-3.6-flash": {
9661
9407
  id: "google/gemini-3.6-flash",
9662
9408
  name: "Google: Gemini 3.6 Flash",
@@ -9674,23 +9420,6 @@ export const MODELS = {
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)",
9680
- api: "openai-completions",
9681
- provider: "openrouter",
9682
- baseUrl: "https://openrouter.ai/api/v1",
9683
- reasoning: true,
9684
- input: ["text", "image"],
9685
- cost: {
9686
- input: 0.75,
9687
- output: 3.75,
9688
- cacheRead: 0.075,
9689
- cacheWrite: 0.08333333333333334,
9690
- },
9691
- contextWindow: 1048576,
9692
- maxTokens: 65536,
9693
- },
9694
9423
  "google/gemma-3-12b-it": {
9695
9424
  id: "google/gemma-3-12b-it",
9696
9425
  name: "Google: Gemma 3 12B",
@@ -10167,23 +9896,6 @@ export const MODELS = {
10167
9896
  contextWindow: 1048576,
10168
9897
  maxTokens: 512000,
10169
9898
  },
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
9899
  "mistralai/codestral-2508": {
10188
9900
  id: "mistralai/codestral-2508",
10189
9901
  name: "Mistral: Codestral 2508",
@@ -10533,9 +10245,9 @@ export const MODELS = {
10533
10245
  reasoning: true,
10534
10246
  input: ["text", "image"],
10535
10247
  cost: {
10536
- input: 0.589,
10537
- output: 2.48,
10538
- cacheRead: 0.0992,
10248
+ input: 0.6,
10249
+ output: 3.41,
10250
+ cacheRead: 0.19999999999999998,
10539
10251
  cacheWrite: 0,
10540
10252
  },
10541
10253
  contextWindow: 262144,
@@ -11051,23 +10763,6 @@ export const MODELS = {
11051
10763
  contextWindow: 400000,
11052
10764
  maxTokens: 128000,
11053
10765
  },
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
10766
  "openai/gpt-5-nano": {
11072
10767
  id: "openai/gpt-5-nano",
11073
10768
  name: "OpenAI: GPT-5 Nano",
@@ -11085,23 +10780,6 @@ export const MODELS = {
11085
10780
  contextWindow: 400000,
11086
10781
  maxTokens: 128000,
11087
10782
  },
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
10783
  "openai/gpt-5-pro": {
11106
10784
  id: "openai/gpt-5-pro",
11107
10785
  name: "OpenAI: GPT-5 Pro",
@@ -11187,23 +10865,6 @@ export const MODELS = {
11187
10865
  contextWindow: 400000,
11188
10866
  maxTokens: 128000,
11189
10867
  },
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
10868
  "openai/gpt-5.2": {
11208
10869
  id: "openai/gpt-5.2",
11209
10870
  name: "OpenAI: GPT-5.2",
@@ -11272,23 +10933,6 @@ export const MODELS = {
11272
10933
  contextWindow: 400000,
11273
10934
  maxTokens: 128000,
11274
10935
  },
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
10936
  "openai/gpt-5.3-chat": {
11293
10937
  id: "openai/gpt-5.3-chat",
11294
10938
  name: "OpenAI: GPT-5.3 Chat",
@@ -11357,23 +11001,6 @@ export const MODELS = {
11357
11001
  contextWindow: 400000,
11358
11002
  maxTokens: 128000,
11359
11003
  },
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
11004
  "openai/gpt-5.4-nano": {
11378
11005
  id: "openai/gpt-5.4-nano",
11379
11006
  name: "OpenAI: GPT-5.4 Nano",
@@ -11391,23 +11018,6 @@ export const MODELS = {
11391
11018
  contextWindow: 400000,
11392
11019
  maxTokens: 128000,
11393
11020
  },
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
11021
  "openai/gpt-5.4-pro": {
11412
11022
  id: "openai/gpt-5.4-pro",
11413
11023
  name: "OpenAI: GPT-5.4 Pro",
@@ -11425,23 +11035,6 @@ export const MODELS = {
11425
11035
  contextWindow: 1050000,
11426
11036
  maxTokens: 128000,
11427
11037
  },
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
11038
  "openai/gpt-5.5": {
11446
11039
  id: "openai/gpt-5.5",
11447
11040
  name: "OpenAI: GPT-5.5",
@@ -11476,23 +11069,6 @@ export const MODELS = {
11476
11069
  contextWindow: 1050000,
11477
11070
  maxTokens: 128000,
11478
11071
  },
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
11072
  "openai/gpt-5.6-luna": {
11497
11073
  id: "openai/gpt-5.6-luna",
11498
11074
  name: "OpenAI: GPT-5.6 Luna",
@@ -11503,9 +11079,9 @@ export const MODELS = {
11503
11079
  input: ["text", "image"],
11504
11080
  cost: {
11505
11081
  input: 0.09999999999999999,
11506
- output: 0.6000000000000001,
11082
+ output: 0.6,
11507
11083
  cacheRead: 0.01,
11508
- cacheWrite: 0.12500000000000003,
11084
+ cacheWrite: 0.125,
11509
11085
  },
11510
11086
  contextWindow: 1050000,
11511
11087
  maxTokens: 128000,
@@ -11595,23 +11171,6 @@ export const MODELS = {
11595
11171
  contextWindow: 1050000,
11596
11172
  maxTokens: 128000,
11597
11173
  },
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
11174
  "openai/gpt-audio": {
11616
11175
  id: "openai/gpt-audio",
11617
11176
  name: "OpenAI: GPT Audio",
@@ -11690,8 +11249,8 @@ export const MODELS = {
11690
11249
  input: ["text"],
11691
11250
  cost: {
11692
11251
  input: 0.03,
11693
- output: 0.14,
11694
- cacheRead: 0,
11252
+ output: 0.13,
11253
+ cacheRead: 0.03,
11695
11254
  cacheWrite: 0,
11696
11255
  },
11697
11256
  contextWindow: 131072,
@@ -12234,12 +11793,12 @@ export const MODELS = {
12234
11793
  input: ["text"],
12235
11794
  cost: {
12236
11795
  input: 0.07,
12237
- output: 0.27,
11796
+ output: 0.28,
12238
11797
  cacheRead: 0,
12239
11798
  cacheWrite: 0,
12240
11799
  },
12241
11800
  contextWindow: 262144,
12242
- maxTokens: 32768,
11801
+ maxTokens: 262144,
12243
11802
  },
12244
11803
  "qwen/qwen3-coder-flash": {
12245
11804
  id: "qwen/qwen3-coder-flash",
@@ -12921,6 +12480,23 @@ export const MODELS = {
12921
12480
  contextWindow: 1048576,
12922
12481
  maxTokens: 4096,
12923
12482
  },
12483
+ "thinkingmachines/inkling-small": {
12484
+ id: "thinkingmachines/inkling-small",
12485
+ name: "Thinking Machines: Inkling Small",
12486
+ api: "openai-completions",
12487
+ provider: "openrouter",
12488
+ baseUrl: "https://openrouter.ai/api/v1",
12489
+ reasoning: true,
12490
+ input: ["text", "image"],
12491
+ cost: {
12492
+ input: 0.5,
12493
+ output: 1.2,
12494
+ cacheRead: 0.09999999999999999,
12495
+ cacheWrite: 0,
12496
+ },
12497
+ contextWindow: 524288,
12498
+ maxTokens: 4096,
12499
+ },
12924
12500
  "upstage/solar-pro-3": {
12925
12501
  id: "upstage/solar-pro-3",
12926
12502
  name: "Upstage: Solar Pro 3",
@@ -13219,13 +12795,13 @@ export const MODELS = {
13219
12795
  reasoning: true,
13220
12796
  input: ["text"],
13221
12797
  cost: {
13222
- input: 1.12,
13223
- output: 3.52,
13224
- cacheRead: 0.20800000000000002,
12798
+ input: 0.2842,
12799
+ output: 0.8932,
12800
+ cacheRead: 0.05278,
13225
12801
  cacheWrite: 0,
13226
12802
  },
13227
12803
  contextWindow: 1048576,
13228
- maxTokens: 128000,
12804
+ maxTokens: 131072,
13229
12805
  },
13230
12806
  "z-ai/glm-5v-turbo": {
13231
12807
  id: "z-ai/glm-5v-turbo",
@@ -13312,6 +12888,23 @@ export const MODELS = {
13312
12888
  contextWindow: 1000000,
13313
12889
  maxTokens: 128000,
13314
12890
  },
12891
+ "~deepseek/deepseek-v4-flash-latest": {
12892
+ id: "~deepseek/deepseek-v4-flash-latest",
12893
+ name: "DeepSeek V4 Flash Latest",
12894
+ api: "openai-completions",
12895
+ provider: "openrouter",
12896
+ baseUrl: "https://openrouter.ai/api/v1",
12897
+ reasoning: true,
12898
+ input: ["text"],
12899
+ cost: {
12900
+ input: 0.09,
12901
+ output: 0.18,
12902
+ cacheRead: 0.018,
12903
+ cacheWrite: 0,
12904
+ },
12905
+ contextWindow: 1048576,
12906
+ maxTokens: 65536,
12907
+ },
13315
12908
  "~google/gemini-flash-latest": {
13316
12909
  id: "~google/gemini-flash-latest",
13317
12910
  name: "Google Gemini Flash Latest",
@@ -14377,8 +13970,25 @@ export const MODELS = {
14377
13970
  reasoning: true,
14378
13971
  input: ["text"],
14379
13972
  cost: {
14380
- input: 0.13799999999999998,
14381
- output: 0.275,
13973
+ input: 0.14,
13974
+ output: 0.28,
13975
+ cacheRead: 0.0028,
13976
+ cacheWrite: 0,
13977
+ },
13978
+ contextWindow: 1000000,
13979
+ maxTokens: 384000,
13980
+ },
13981
+ "deepseek/deepseek-v4-flash-0731": {
13982
+ id: "deepseek/deepseek-v4-flash-0731",
13983
+ name: "DeepSeek V4 Flash 0731",
13984
+ api: "anthropic-messages",
13985
+ provider: "vercel-ai-gateway",
13986
+ baseUrl: "https://ai-gateway.vercel.sh",
13987
+ reasoning: true,
13988
+ input: ["text"],
13989
+ cost: {
13990
+ input: 0.13,
13991
+ output: 0.26,
14382
13992
  cacheRead: 0.028,
14383
13993
  cacheWrite: 0,
14384
13994
  },
@@ -14664,7 +14274,7 @@ export const MODELS = {
14664
14274
  provider: "vercel-ai-gateway",
14665
14275
  baseUrl: "https://ai-gateway.vercel.sh",
14666
14276
  reasoning: true,
14667
- input: ["text"],
14277
+ input: ["text", "image"],
14668
14278
  cost: {
14669
14279
  input: 0.15,
14670
14280
  output: 0.6,
@@ -14715,7 +14325,7 @@ export const MODELS = {
14715
14325
  provider: "vercel-ai-gateway",
14716
14326
  baseUrl: "https://ai-gateway.vercel.sh",
14717
14327
  reasoning: true,
14718
- input: ["text"],
14328
+ input: ["text", "image"],
14719
14329
  cost: {
14720
14330
  input: 0.74,
14721
14331
  output: 2.96,
@@ -15072,7 +14682,7 @@ export const MODELS = {
15072
14682
  provider: "vercel-ai-gateway",
15073
14683
  baseUrl: "https://ai-gateway.vercel.sh",
15074
14684
  reasoning: false,
15075
- input: ["text"],
14685
+ input: ["text", "image"],
15076
14686
  cost: {
15077
14687
  input: 0.09999999999999999,
15078
14688
  output: 0.09999999999999999,
@@ -15089,7 +14699,7 @@ export const MODELS = {
15089
14699
  provider: "vercel-ai-gateway",
15090
14700
  baseUrl: "https://ai-gateway.vercel.sh",
15091
14701
  reasoning: false,
15092
- input: ["text"],
14702
+ input: ["text", "image"],
15093
14703
  cost: {
15094
14704
  input: 0.15,
15095
14705
  output: 0.15,
@@ -15157,7 +14767,7 @@ export const MODELS = {
15157
14767
  provider: "vercel-ai-gateway",
15158
14768
  baseUrl: "https://ai-gateway.vercel.sh",
15159
14769
  reasoning: false,
15160
- input: ["text"],
14770
+ input: ["text", "image"],
15161
14771
  cost: {
15162
14772
  input: 0.15,
15163
14773
  output: 0.15,
@@ -16160,7 +15770,7 @@ export const MODELS = {
16160
15770
  provider: "vercel-ai-gateway",
16161
15771
  baseUrl: "https://ai-gateway.vercel.sh",
16162
15772
  reasoning: true,
16163
- input: ["text"],
15773
+ input: ["text", "image"],
16164
15774
  cost: {
16165
15775
  input: 0.09,
16166
15776
  output: 0.3,