@dreb/ai 2.63.0 → 2.64.1

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.
@@ -87,6 +87,23 @@ export const MODELS = {
87
87
  contextWindow: 1000000,
88
88
  maxTokens: 128000,
89
89
  },
90
+ "anthropic.claude-fable-5-1": {
91
+ id: "anthropic.claude-fable-5-1",
92
+ name: "Claude Fable 5.1",
93
+ api: "bedrock-converse-stream",
94
+ provider: "amazon-bedrock",
95
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
96
+ reasoning: true,
97
+ input: ["text", "image"],
98
+ cost: {
99
+ input: 10,
100
+ output: 50,
101
+ cacheRead: 0.25,
102
+ cacheWrite: 12.5,
103
+ },
104
+ contextWindow: 1000000,
105
+ maxTokens: 128000,
106
+ },
90
107
  "anthropic.claude-haiku-4-5-20251001-v1:0": {
91
108
  id: "anthropic.claude-haiku-4-5-20251001-v1:0",
92
109
  name: "Claude Haiku 4.5",
@@ -614,6 +631,23 @@ export const MODELS = {
614
631
  contextWindow: 1000000,
615
632
  maxTokens: 128000,
616
633
  },
634
+ "global.anthropic.claude-fable-5-1": {
635
+ id: "global.anthropic.claude-fable-5-1",
636
+ name: "Claude Fable 5.1 (Global)",
637
+ api: "bedrock-converse-stream",
638
+ provider: "amazon-bedrock",
639
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
640
+ reasoning: true,
641
+ input: ["text", "image"],
642
+ cost: {
643
+ input: 10,
644
+ output: 50,
645
+ cacheRead: 0.25,
646
+ cacheWrite: 12.5,
647
+ },
648
+ contextWindow: 1000000,
649
+ maxTokens: 128000,
650
+ },
617
651
  "global.anthropic.claude-haiku-4-5-20251001-v1:0": {
618
652
  id: "global.anthropic.claude-haiku-4-5-20251001-v1:0",
619
653
  name: "Claude Haiku 4.5 (Global)",
@@ -1685,6 +1719,23 @@ export const MODELS = {
1685
1719
  contextWindow: 1000000,
1686
1720
  maxTokens: 128000,
1687
1721
  },
1722
+ "us.anthropic.claude-fable-5-1": {
1723
+ id: "us.anthropic.claude-fable-5-1",
1724
+ name: "Claude Fable 5.1 (US)",
1725
+ api: "bedrock-converse-stream",
1726
+ provider: "amazon-bedrock",
1727
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1728
+ reasoning: true,
1729
+ input: ["text", "image"],
1730
+ cost: {
1731
+ input: 11,
1732
+ output: 55,
1733
+ cacheRead: 0.275,
1734
+ cacheWrite: 13.75,
1735
+ },
1736
+ contextWindow: 1000000,
1737
+ maxTokens: 128000,
1738
+ },
1688
1739
  "us.anthropic.claude-haiku-4-5-20251001-v1:0": {
1689
1740
  id: "us.anthropic.claude-haiku-4-5-20251001-v1:0",
1690
1741
  name: "Claude Haiku 4.5 (US)",
@@ -2044,6 +2095,23 @@ export const MODELS = {
2044
2095
  contextWindow: 1000000,
2045
2096
  maxTokens: 128000,
2046
2097
  },
2098
+ "claude-fable-5-1": {
2099
+ id: "claude-fable-5-1",
2100
+ name: "Claude Fable 5.1",
2101
+ api: "anthropic-messages",
2102
+ provider: "anthropic",
2103
+ baseUrl: "https://api.anthropic.com",
2104
+ reasoning: true,
2105
+ input: ["text", "image"],
2106
+ cost: {
2107
+ input: 10,
2108
+ output: 50,
2109
+ cacheRead: 0.25,
2110
+ cacheWrite: 12.5,
2111
+ },
2112
+ contextWindow: 1000000,
2113
+ maxTokens: 128000,
2114
+ },
2047
2115
  "claude-haiku-4-5": {
2048
2116
  id: "claude-haiku-4-5",
2049
2117
  name: "Claude Haiku 4.5 (latest)",
@@ -3918,23 +3986,6 @@ export const MODELS = {
3918
3986
  contextWindow: 1048576,
3919
3987
  maxTokens: 65536,
3920
3988
  },
3921
- "gemini-robotics-er-1.6-preview": {
3922
- id: "gemini-robotics-er-1.6-preview",
3923
- name: "Gemini Robotics-ER 1.6 Preview",
3924
- api: "google-generative-ai",
3925
- provider: "google",
3926
- baseUrl: "https://generativelanguage.googleapis.com/v1beta",
3927
- reasoning: true,
3928
- input: ["text", "image"],
3929
- cost: {
3930
- input: 1,
3931
- output: 5,
3932
- cacheRead: 0,
3933
- cacheWrite: 0,
3934
- },
3935
- contextWindow: 131072,
3936
- maxTokens: 65536,
3937
- },
3938
3989
  "gemma-4-26b-a4b-it": {
3939
3990
  id: "gemma-4-26b-a4b-it",
3940
3991
  name: "Gemma 4 26B A4B IT",
@@ -4538,6 +4589,23 @@ export const MODELS = {
4538
4589
  contextWindow: 131072,
4539
4590
  maxTokens: 16384,
4540
4591
  },
4592
+ "qwen/qwen3.8-27b": {
4593
+ id: "qwen/qwen3.8-27b",
4594
+ name: "Qwen3.8 27B",
4595
+ api: "openai-completions",
4596
+ provider: "groq",
4597
+ baseUrl: "https://api.groq.com/openai/v1",
4598
+ reasoning: true,
4599
+ input: ["text", "image"],
4600
+ cost: {
4601
+ input: 0.8,
4602
+ output: 4,
4603
+ cacheRead: 0,
4604
+ cacheWrite: 0,
4605
+ },
4606
+ contextWindow: 131042,
4607
+ maxTokens: 16384,
4608
+ },
4541
4609
  },
4542
4610
  "huggingface": {
4543
4611
  "MiniMaxAI/MiniMax-M2": {
@@ -5764,6 +5832,24 @@ export const MODELS = {
5764
5832
  contextWindow: 262144,
5765
5833
  maxTokens: 131072,
5766
5834
  },
5835
+ "zai-org/GLM-5.3": {
5836
+ id: "zai-org/GLM-5.3",
5837
+ name: "GLM-5.3",
5838
+ api: "openai-completions",
5839
+ provider: "huggingface",
5840
+ baseUrl: "https://router.huggingface.co/v1",
5841
+ compat: { "supportsDeveloperRole": false },
5842
+ reasoning: true,
5843
+ input: ["text"],
5844
+ cost: {
5845
+ input: 1.4,
5846
+ output: 4.4,
5847
+ cacheRead: 0,
5848
+ cacheWrite: 0,
5849
+ },
5850
+ contextWindow: 1048576,
5851
+ maxTokens: 131072,
5852
+ },
5767
5853
  "zai-org/GLM-5.3-Flash": {
5768
5854
  id: "zai-org/GLM-5.3-Flash",
5769
5855
  name: "GLM-5.3-Flash",
@@ -7467,6 +7553,23 @@ export const MODELS = {
7467
7553
  contextWindow: 1000000,
7468
7554
  maxTokens: 128000,
7469
7555
  },
7556
+ "claude-fable-5-1": {
7557
+ id: "claude-fable-5-1",
7558
+ name: "Claude Fable 5.1",
7559
+ api: "anthropic-messages",
7560
+ provider: "opencode",
7561
+ baseUrl: "https://opencode.ai/zen",
7562
+ reasoning: true,
7563
+ input: ["text", "image"],
7564
+ cost: {
7565
+ input: 10,
7566
+ output: 50,
7567
+ cacheRead: 0.25,
7568
+ cacheWrite: 12.5,
7569
+ },
7570
+ contextWindow: 1000000,
7571
+ maxTokens: 128000,
7572
+ },
7470
7573
  "claude-haiku-4-5": {
7471
7574
  id: "claude-haiku-4-5",
7472
7575
  name: "Claude Haiku 4.5",
@@ -8198,23 +8301,6 @@ export const MODELS = {
8198
8301
  contextWindow: 256000,
8199
8302
  maxTokens: 256000,
8200
8303
  },
8201
- "hy3-free": {
8202
- id: "hy3-free",
8203
- name: "Hy3 Free",
8204
- api: "openai-completions",
8205
- provider: "opencode",
8206
- baseUrl: "https://opencode.ai/zen/v1",
8207
- reasoning: true,
8208
- input: ["text"],
8209
- cost: {
8210
- input: 0,
8211
- output: 0,
8212
- cacheRead: 0,
8213
- cacheWrite: 0,
8214
- },
8215
- contextWindow: 190000,
8216
- maxTokens: 64000,
8217
- },
8218
8304
  "kimi-k2.5": {
8219
8305
  id: "kimi-k2.5",
8220
8306
  name: "Kimi K2.5",
@@ -8627,16 +8713,16 @@ export const MODELS = {
8627
8713
  },
8628
8714
  "hy3": {
8629
8715
  id: "hy3",
8630
- name: "Hy3 (8x usage)",
8716
+ name: "Hy3",
8631
8717
  api: "openai-completions",
8632
8718
  provider: "opencode-go",
8633
8719
  baseUrl: "https://opencode.ai/zen/go/v1",
8634
8720
  reasoning: true,
8635
8721
  input: ["text"],
8636
8722
  cost: {
8637
- input: 0.0175,
8638
- output: 0.0725,
8639
- cacheRead: 0.004375,
8723
+ input: 0.14,
8724
+ output: 0.58,
8725
+ cacheRead: 0.035,
8640
8726
  cacheWrite: 0,
8641
8727
  },
8642
8728
  contextWindow: 256000,
@@ -9069,6 +9155,23 @@ export const MODELS = {
9069
9155
  contextWindow: 1000000,
9070
9156
  maxTokens: 128000,
9071
9157
  },
9158
+ "anthropic/claude-fable-5.1": {
9159
+ id: "anthropic/claude-fable-5.1",
9160
+ name: "Anthropic: Claude Fable 5.1",
9161
+ api: "openai-completions",
9162
+ provider: "openrouter",
9163
+ baseUrl: "https://openrouter.ai/api/v1",
9164
+ reasoning: true,
9165
+ input: ["text", "image"],
9166
+ cost: {
9167
+ input: 10,
9168
+ output: 50,
9169
+ cacheRead: 0.25,
9170
+ cacheWrite: 12.5,
9171
+ },
9172
+ contextWindow: 1000000,
9173
+ maxTokens: 128000,
9174
+ },
9072
9175
  "anthropic/claude-fable-5:batch": {
9073
9176
  id: "anthropic/claude-fable-5:batch",
9074
9177
  name: "Anthropic: Claude Fable 5 (batch)",
@@ -9256,23 +9359,6 @@ export const MODELS = {
9256
9359
  contextWindow: 1000000,
9257
9360
  maxTokens: 128000,
9258
9361
  },
9259
- "anthropic/claude-opus-4.7-fast": {
9260
- id: "anthropic/claude-opus-4.7-fast",
9261
- name: "Anthropic: Claude Opus 4.7 (Fast)",
9262
- api: "openai-completions",
9263
- provider: "openrouter",
9264
- baseUrl: "https://openrouter.ai/api/v1",
9265
- reasoning: true,
9266
- input: ["text", "image"],
9267
- cost: {
9268
- input: 30,
9269
- output: 150,
9270
- cacheRead: 3,
9271
- cacheWrite: 37.5,
9272
- },
9273
- contextWindow: 1000000,
9274
- maxTokens: 128000,
9275
- },
9276
9362
  "anthropic/claude-opus-4.7:batch": {
9277
9363
  id: "anthropic/claude-opus-4.7:batch",
9278
9364
  name: "Anthropic: Claude Opus 4.7 (batch)",
@@ -9307,23 +9393,6 @@ export const MODELS = {
9307
9393
  contextWindow: 1000000,
9308
9394
  maxTokens: 128000,
9309
9395
  },
9310
- "anthropic/claude-opus-4.8-fast": {
9311
- id: "anthropic/claude-opus-4.8-fast",
9312
- name: "Anthropic: Claude Opus 4.8 (Fast)",
9313
- api: "openai-completions",
9314
- provider: "openrouter",
9315
- baseUrl: "https://openrouter.ai/api/v1",
9316
- reasoning: true,
9317
- input: ["text", "image"],
9318
- cost: {
9319
- input: 10,
9320
- output: 50,
9321
- cacheRead: 1,
9322
- cacheWrite: 12.5,
9323
- },
9324
- contextWindow: 1000000,
9325
- maxTokens: 128000,
9326
- },
9327
9396
  "anthropic/claude-opus-4.8:batch": {
9328
9397
  id: "anthropic/claude-opus-4.8:batch",
9329
9398
  name: "Anthropic: Claude Opus 4.8 (batch)",
@@ -9358,23 +9427,6 @@ export const MODELS = {
9358
9427
  contextWindow: 1000000,
9359
9428
  maxTokens: 128000,
9360
9429
  },
9361
- "anthropic/claude-opus-5-fast": {
9362
- id: "anthropic/claude-opus-5-fast",
9363
- name: "Claude Opus 5 (Fast)",
9364
- api: "openai-completions",
9365
- provider: "openrouter",
9366
- baseUrl: "https://openrouter.ai/api/v1",
9367
- reasoning: true,
9368
- input: ["text", "image"],
9369
- cost: {
9370
- input: 10,
9371
- output: 50,
9372
- cacheRead: 1,
9373
- cacheWrite: 12.5,
9374
- },
9375
- contextWindow: 1000000,
9376
- maxTokens: 128000,
9377
- },
9378
9430
  "anthropic/claude-opus-5:batch": {
9379
9431
  id: "anthropic/claude-opus-5:batch",
9380
9432
  name: "Claude Opus 5 (batch)",
@@ -9520,30 +9572,13 @@ export const MODELS = {
9520
9572
  reasoning: true,
9521
9573
  input: ["text"],
9522
9574
  cost: {
9523
- input: 0.22,
9524
- output: 0.85,
9575
+ input: 0.25,
9576
+ output: 0.7999999999999999,
9525
9577
  cacheRead: 0.06,
9526
9578
  cacheWrite: 0,
9527
9579
  },
9528
9580
  contextWindow: 262144,
9529
- maxTokens: 235929,
9530
- },
9531
- "arcee-ai/virtuoso-large": {
9532
- id: "arcee-ai/virtuoso-large",
9533
- name: "Arcee AI: Virtuoso Large",
9534
- api: "openai-completions",
9535
- provider: "openrouter",
9536
- baseUrl: "https://openrouter.ai/api/v1",
9537
- reasoning: false,
9538
- input: ["text"],
9539
- cost: {
9540
- input: 0.75,
9541
- output: 1.2,
9542
- cacheRead: 0,
9543
- cacheWrite: 0,
9544
- },
9545
- contextWindow: 131072,
9546
- maxTokens: 64000,
9581
+ maxTokens: 80000,
9547
9582
  },
9548
9583
  "auto": {
9549
9584
  id: "auto",
@@ -9860,9 +9895,9 @@ export const MODELS = {
9860
9895
  reasoning: true,
9861
9896
  input: ["text"],
9862
9897
  cost: {
9863
- input: 0.0868,
9864
- output: 0.1736,
9865
- cacheRead: 0.01736,
9898
+ input: 0.07168000000000001,
9899
+ output: 0.14336000000000002,
9900
+ cacheRead: 0.014336,
9866
9901
  cacheWrite: 0,
9867
9902
  },
9868
9903
  contextWindow: 1048576,
@@ -9877,14 +9912,31 @@ export const MODELS = {
9877
9912
  reasoning: true,
9878
9913
  input: ["text"],
9879
9914
  cost: {
9880
- input: 0.06,
9881
- output: 0.12,
9882
- cacheRead: 0.012,
9915
+ input: 0.065,
9916
+ output: 0.18,
9917
+ cacheRead: 0.016,
9883
9918
  cacheWrite: 0,
9884
9919
  },
9885
9920
  contextWindow: 1310720,
9886
9921
  maxTokens: 943718,
9887
9922
  },
9923
+ "deepseek/deepseek-v4-flash-0731:batch": {
9924
+ id: "deepseek/deepseek-v4-flash-0731:batch",
9925
+ name: "DeepSeek: DeepSeek V4 Flash 0731 (batch)",
9926
+ api: "openai-completions",
9927
+ provider: "openrouter",
9928
+ baseUrl: "https://openrouter.ai/api/v1",
9929
+ reasoning: true,
9930
+ input: ["text"],
9931
+ cost: {
9932
+ input: 0.14,
9933
+ output: 0.28,
9934
+ cacheRead: 0.03,
9935
+ cacheWrite: 0,
9936
+ },
9937
+ contextWindow: 1048576,
9938
+ maxTokens: 943718,
9939
+ },
9888
9940
  "deepseek/deepseek-v4-flash-vision-exp": {
9889
9941
  id: "deepseek/deepseek-v4-flash-vision-exp",
9890
9942
  name: "DeepSeek: DeepSeek V4 Flash Vision Exp",
@@ -9911,9 +9963,9 @@ export const MODELS = {
9911
9963
  reasoning: true,
9912
9964
  input: ["text"],
9913
9965
  cost: {
9914
- input: 0.7518539999999999,
9915
- output: 1.5037079999999998,
9916
- cacheRead: 0.0626545,
9966
+ input: 1.0274699999999999,
9967
+ output: 2.0549399999999998,
9968
+ cacheRead: 0.0856225,
9917
9969
  cacheWrite: 0,
9918
9970
  },
9919
9971
  contextWindow: 1048576,
@@ -9936,6 +9988,23 @@ export const MODELS = {
9936
9988
  contextWindow: 1048576,
9937
9989
  maxTokens: 384000,
9938
9990
  },
9991
+ "deepseek/deepseek-v4-pro-0813:batch": {
9992
+ id: "deepseek/deepseek-v4-pro-0813:batch",
9993
+ name: "DeepSeek: DeepSeek V4 Pro 0813 (batch)",
9994
+ api: "openai-completions",
9995
+ provider: "openrouter",
9996
+ baseUrl: "https://openrouter.ai/api/v1",
9997
+ reasoning: true,
9998
+ input: ["text"],
9999
+ cost: {
10000
+ input: 1.32,
10001
+ output: 3.9600000000000004,
10002
+ cacheRead: 0.13,
10003
+ cacheWrite: 0,
10004
+ },
10005
+ contextWindow: 1048576,
10006
+ maxTokens: 943718,
10007
+ },
9939
10008
  "dots-studio/dots-3-note-preview:free": {
9940
10009
  id: "dots-studio/dots-3-note-preview:free",
9941
10010
  name: "Dots Studio: Dots3-Note Preview (free)",
@@ -10463,25 +10532,42 @@ export const MODELS = {
10463
10532
  contextWindow: 262144,
10464
10533
  maxTokens: 16384,
10465
10534
  },
10466
- "google/gemma-4-31b-it:free": {
10467
- id: "google/gemma-4-31b-it:free",
10468
- name: "Google: Gemma 4 31B (free)",
10535
+ "google/gemma-4-31b-it:batch": {
10536
+ id: "google/gemma-4-31b-it:batch",
10537
+ name: "Google: Gemma 4 31B (batch)",
10469
10538
  api: "openai-completions",
10470
10539
  provider: "openrouter",
10471
10540
  baseUrl: "https://openrouter.ai/api/v1",
10472
10541
  reasoning: true,
10473
10542
  input: ["text", "image"],
10474
10543
  cost: {
10475
- input: 0,
10476
- output: 0,
10544
+ input: 0.39,
10545
+ output: 0.9700000000000001,
10477
10546
  cacheRead: 0,
10478
10547
  cacheWrite: 0,
10479
10548
  },
10480
10549
  contextWindow: 262144,
10481
- maxTokens: 32768,
10550
+ maxTokens: 235929,
10482
10551
  },
10483
- "ibm-granite/granite-4.1-8b": {
10484
- id: "ibm-granite/granite-4.1-8b",
10552
+ "google/gemma-4-31b-it:free": {
10553
+ id: "google/gemma-4-31b-it:free",
10554
+ name: "Google: Gemma 4 31B (free)",
10555
+ api: "openai-completions",
10556
+ provider: "openrouter",
10557
+ baseUrl: "https://openrouter.ai/api/v1",
10558
+ reasoning: true,
10559
+ input: ["text", "image"],
10560
+ cost: {
10561
+ input: 0,
10562
+ output: 0,
10563
+ cacheRead: 0,
10564
+ cacheWrite: 0,
10565
+ },
10566
+ contextWindow: 262144,
10567
+ maxTokens: 32768,
10568
+ },
10569
+ "ibm-granite/granite-4.1-8b": {
10570
+ id: "ibm-granite/granite-4.1-8b",
10485
10571
  name: "IBM: Granite 4.1 8B",
10486
10572
  api: "openai-completions",
10487
10573
  provider: "openrouter",
@@ -10497,6 +10583,23 @@ export const MODELS = {
10497
10583
  contextWindow: 131072,
10498
10584
  maxTokens: 117964,
10499
10585
  },
10586
+ "ibm-granite/granite-4.2-8b": {
10587
+ id: "ibm-granite/granite-4.2-8b",
10588
+ name: "IBM: Granite 4.2 8B",
10589
+ api: "openai-completions",
10590
+ provider: "openrouter",
10591
+ baseUrl: "https://openrouter.ai/api/v1",
10592
+ reasoning: true,
10593
+ input: ["text"],
10594
+ cost: {
10595
+ input: 0.09999999999999999,
10596
+ output: 0.15,
10597
+ cacheRead: 0.049999999999999996,
10598
+ cacheWrite: 0,
10599
+ },
10600
+ contextWindow: 131072,
10601
+ maxTokens: 117964,
10602
+ },
10500
10603
  "inception/mercury-2": {
10501
10604
  id: "inception/mercury-2",
10502
10605
  name: "Inception: Mercury 2",
@@ -10514,6 +10617,23 @@ export const MODELS = {
10514
10617
  contextWindow: 128000,
10515
10618
  maxTokens: 50000,
10516
10619
  },
10620
+ "inception/mercury-2.5-preview": {
10621
+ id: "inception/mercury-2.5-preview",
10622
+ name: "Inception: Mercury 2.5 Preview",
10623
+ api: "openai-completions",
10624
+ provider: "openrouter",
10625
+ baseUrl: "https://openrouter.ai/api/v1",
10626
+ reasoning: true,
10627
+ input: ["text"],
10628
+ cost: {
10629
+ input: 0.04,
10630
+ output: 0.15,
10631
+ cacheRead: 0.004,
10632
+ cacheWrite: 0,
10633
+ },
10634
+ contextWindow: 260000,
10635
+ maxTokens: 65536,
10636
+ },
10517
10637
  "inclusionai/ling-3.0-flash": {
10518
10638
  id: "inclusionai/ling-3.0-flash",
10519
10639
  name: "Ling-3.0-flash",
@@ -10548,23 +10668,6 @@ export const MODELS = {
10548
10668
  contextWindow: 262144,
10549
10669
  maxTokens: 32768,
10550
10670
  },
10551
- "kwaipilot/kat-coder-air-v2.5": {
10552
- id: "kwaipilot/kat-coder-air-v2.5",
10553
- name: "Kwaipilot: KAT-Coder-Air V2.5",
10554
- api: "openai-completions",
10555
- provider: "openrouter",
10556
- baseUrl: "https://openrouter.ai/api/v1",
10557
- reasoning: false,
10558
- input: ["text"],
10559
- cost: {
10560
- input: 0.15,
10561
- output: 0.6,
10562
- cacheRead: 0.03,
10563
- cacheWrite: 0,
10564
- },
10565
- contextWindow: 256000,
10566
- maxTokens: 80000,
10567
- },
10568
10671
  "kwaipilot/kat-coder-pro-v2": {
10569
10672
  id: "kwaipilot/kat-coder-pro-v2",
10570
10673
  name: "Kwaipilot: KAT-Coder-Pro V2",
@@ -10580,7 +10683,7 @@ export const MODELS = {
10580
10683
  cacheWrite: 0,
10581
10684
  },
10582
10685
  contextWindow: 262144,
10583
- maxTokens: 80000,
10686
+ maxTokens: 144000,
10584
10687
  },
10585
10688
  "kwaipilot/kat-coder-pro-v2.5": {
10586
10689
  id: "kwaipilot/kat-coder-pro-v2.5",
@@ -10597,7 +10700,7 @@ export const MODELS = {
10597
10700
  cacheWrite: 0,
10598
10701
  },
10599
10702
  contextWindow: 262144,
10600
- maxTokens: 80000,
10703
+ maxTokens: 235929,
10601
10704
  },
10602
10705
  "liquid/lfm-2.5-2.6b:free": {
10603
10706
  id: "liquid/lfm-2.5-2.6b:free",
@@ -10694,12 +10797,12 @@ export const MODELS = {
10694
10797
  input: ["text", "image"],
10695
10798
  cost: {
10696
10799
  input: 0.19999999999999998,
10697
- output: 0.7999999999999999,
10800
+ output: 0.696,
10698
10801
  cacheRead: 0,
10699
10802
  cacheWrite: 0,
10700
10803
  },
10701
10804
  contextWindow: 1048576,
10702
- maxTokens: 16384,
10805
+ maxTokens: 115200,
10703
10806
  },
10704
10807
  "meta-llama/llama-4-scout": {
10705
10808
  id: "meta-llama/llama-4-scout",
@@ -10710,13 +10813,13 @@ export const MODELS = {
10710
10813
  reasoning: false,
10711
10814
  input: ["text", "image"],
10712
10815
  cost: {
10713
- input: 0.11,
10714
- output: 0.33999999999999997,
10715
- cacheRead: 0.055,
10816
+ input: 0.09999999999999999,
10817
+ output: 0.3,
10818
+ cacheRead: 0,
10716
10819
  cacheWrite: 0,
10717
10820
  },
10718
10821
  contextWindow: 1310720,
10719
- maxTokens: 8192,
10822
+ maxTokens: 16384,
10720
10823
  },
10721
10824
  "meta/muse-glimmer-30b": {
10722
10825
  id: "meta/muse-glimmer-30b",
@@ -10726,6 +10829,23 @@ export const MODELS = {
10726
10829
  baseUrl: "https://openrouter.ai/api/v1",
10727
10830
  reasoning: true,
10728
10831
  input: ["text", "image"],
10832
+ cost: {
10833
+ input: 0.3,
10834
+ output: 1.2,
10835
+ cacheRead: 0.04,
10836
+ cacheWrite: 0,
10837
+ },
10838
+ contextWindow: 131072,
10839
+ maxTokens: 16384,
10840
+ },
10841
+ "meta/muse-glimmer-30b:batch": {
10842
+ id: "meta/muse-glimmer-30b:batch",
10843
+ name: "Meta: Muse Glimmer 30B (batch)",
10844
+ api: "openai-completions",
10845
+ provider: "openrouter",
10846
+ baseUrl: "https://openrouter.ai/api/v1",
10847
+ reasoning: true,
10848
+ input: ["text", "image"],
10729
10849
  cost: {
10730
10850
  input: 0.35,
10731
10851
  output: 1.5,
@@ -10956,23 +11076,6 @@ export const MODELS = {
10956
11076
  contextWindow: 256000,
10957
11077
  maxTokens: 204800,
10958
11078
  },
10959
- "mistralai/codestral-2508:batch": {
10960
- id: "mistralai/codestral-2508:batch",
10961
- name: "Mistral: Codestral 2508 (batch)",
10962
- api: "openai-completions",
10963
- provider: "openrouter",
10964
- baseUrl: "https://openrouter.ai/api/v1",
10965
- reasoning: false,
10966
- input: ["text"],
10967
- cost: {
10968
- input: 0.3,
10969
- output: 0.8999999999999999,
10970
- cacheRead: 0.03,
10971
- cacheWrite: 0,
10972
- },
10973
- contextWindow: 256000,
10974
- maxTokens: 204800,
10975
- },
10976
11079
  "mistralai/devstral-2512": {
10977
11080
  id: "mistralai/devstral-2512",
10978
11081
  name: "Mistral: Devstral 2 2512",
@@ -10982,9 +11085,9 @@ export const MODELS = {
10982
11085
  reasoning: false,
10983
11086
  input: ["text"],
10984
11087
  cost: {
10985
- input: 0.44,
10986
- output: 2.2,
10987
- cacheRead: 0.044,
11088
+ input: 0.39999999999999997,
11089
+ output: 2,
11090
+ cacheRead: 0.04,
10988
11091
  cacheWrite: 0,
10989
11092
  },
10990
11093
  contextWindow: 262144,
@@ -11041,23 +11144,6 @@ export const MODELS = {
11041
11144
  contextWindow: 262144,
11042
11145
  maxTokens: 209715,
11043
11146
  },
11044
- "mistralai/ministral-8b-2512:batch": {
11045
- id: "mistralai/ministral-8b-2512:batch",
11046
- name: "Mistral: Ministral 3 8B 2512 (batch)",
11047
- api: "openai-completions",
11048
- provider: "openrouter",
11049
- baseUrl: "https://openrouter.ai/api/v1",
11050
- reasoning: false,
11051
- input: ["text", "image"],
11052
- cost: {
11053
- input: 0.15,
11054
- output: 0.15,
11055
- cacheRead: 0.015,
11056
- cacheWrite: 0,
11057
- },
11058
- contextWindow: 262144,
11059
- maxTokens: 209715,
11060
- },
11061
11147
  "mistralai/mistral-large": {
11062
11148
  id: "mistralai/mistral-large",
11063
11149
  name: "Mistral Large",
@@ -11109,23 +11195,6 @@ export const MODELS = {
11109
11195
  contextWindow: 262144,
11110
11196
  maxTokens: 209715,
11111
11197
  },
11112
- "mistralai/mistral-large-2512:batch": {
11113
- id: "mistralai/mistral-large-2512:batch",
11114
- name: "Mistral: Mistral Large 3 2512 (batch)",
11115
- api: "openai-completions",
11116
- provider: "openrouter",
11117
- baseUrl: "https://openrouter.ai/api/v1",
11118
- reasoning: false,
11119
- input: ["text", "image"],
11120
- cost: {
11121
- input: 0.5,
11122
- output: 1.5,
11123
- cacheRead: 0.049999999999999996,
11124
- cacheWrite: 0,
11125
- },
11126
- contextWindow: 262144,
11127
- maxTokens: 209715,
11128
- },
11129
11198
  "mistralai/mistral-medium-3": {
11130
11199
  id: "mistralai/mistral-medium-3",
11131
11200
  name: "Mistral: Mistral Medium 3",
@@ -11194,23 +11263,6 @@ export const MODELS = {
11194
11263
  contextWindow: 131072,
11195
11264
  maxTokens: 104857,
11196
11265
  },
11197
- "mistralai/mistral-medium-3.1:batch": {
11198
- id: "mistralai/mistral-medium-3.1:batch",
11199
- name: "Mistral: Mistral Medium 3.1 (batch)",
11200
- api: "openai-completions",
11201
- provider: "openrouter",
11202
- baseUrl: "https://openrouter.ai/api/v1",
11203
- reasoning: false,
11204
- input: ["text", "image"],
11205
- cost: {
11206
- input: 0.39999999999999997,
11207
- output: 2,
11208
- cacheRead: 0.04,
11209
- cacheWrite: 0,
11210
- },
11211
- contextWindow: 131072,
11212
- maxTokens: 104857,
11213
- },
11214
11266
  "mistralai/mistral-nemo": {
11215
11267
  id: "mistralai/mistral-nemo",
11216
11268
  name: "Mistral: Mistral Nemo",
@@ -11262,23 +11314,6 @@ export const MODELS = {
11262
11314
  contextWindow: 262144,
11263
11315
  maxTokens: 209715,
11264
11316
  },
11265
- "mistralai/mistral-small-2603:batch": {
11266
- id: "mistralai/mistral-small-2603:batch",
11267
- name: "Mistral: Mistral Small 4 (batch)",
11268
- api: "openai-completions",
11269
- provider: "openrouter",
11270
- baseUrl: "https://openrouter.ai/api/v1",
11271
- reasoning: true,
11272
- input: ["text", "image"],
11273
- cost: {
11274
- input: 0.15,
11275
- output: 0.6,
11276
- cacheRead: 0.015,
11277
- cacheWrite: 0,
11278
- },
11279
- contextWindow: 262144,
11280
- maxTokens: 209715,
11281
- },
11282
11317
  "mistralai/mistral-small-3.2-24b-instruct": {
11283
11318
  id: "mistralai/mistral-small-3.2-24b-instruct",
11284
11319
  name: "Mistral: Mistral Small 3.2 24B",
@@ -11449,6 +11484,23 @@ export const MODELS = {
11449
11484
  contextWindow: 1048576,
11450
11485
  maxTokens: 943718,
11451
11486
  },
11487
+ "moonshotai/kimi-k3:batch": {
11488
+ id: "moonshotai/kimi-k3:batch",
11489
+ name: "MoonshotAI: Kimi K3 (batch)",
11490
+ api: "openai-completions",
11491
+ provider: "openrouter",
11492
+ baseUrl: "https://openrouter.ai/api/v1",
11493
+ reasoning: true,
11494
+ input: ["text", "image"],
11495
+ cost: {
11496
+ input: 3,
11497
+ output: 15,
11498
+ cacheRead: 0.3,
11499
+ cacheWrite: 0,
11500
+ },
11501
+ contextWindow: 1048576,
11502
+ maxTokens: 943718,
11503
+ },
11452
11504
  "nex-agi/nex-n2-mini": {
11453
11505
  id: "nex-agi/nex-n2-mini",
11454
11506
  name: "Nex AGI: Nex-N2-Mini",
@@ -11687,6 +11739,23 @@ export const MODELS = {
11687
11739
  contextWindow: 16385,
11688
11740
  maxTokens: 4096,
11689
11741
  },
11742
+ "openai/gpt-3.5-turbo:batch": {
11743
+ id: "openai/gpt-3.5-turbo:batch",
11744
+ name: "OpenAI: GPT-3.5 Turbo (batch)",
11745
+ api: "openai-completions",
11746
+ provider: "openrouter",
11747
+ baseUrl: "https://openrouter.ai/api/v1",
11748
+ reasoning: false,
11749
+ input: ["text"],
11750
+ cost: {
11751
+ input: 0.25,
11752
+ output: 0.75,
11753
+ cacheRead: 0,
11754
+ cacheWrite: 0,
11755
+ },
11756
+ contextWindow: 16385,
11757
+ maxTokens: 4096,
11758
+ },
11690
11759
  "openai/gpt-4": {
11691
11760
  id: "openai/gpt-4",
11692
11761
  name: "OpenAI: GPT-4",
@@ -11738,6 +11807,23 @@ export const MODELS = {
11738
11807
  contextWindow: 128000,
11739
11808
  maxTokens: 4096,
11740
11809
  },
11810
+ "openai/gpt-4-turbo:batch": {
11811
+ id: "openai/gpt-4-turbo:batch",
11812
+ name: "OpenAI: GPT-4 Turbo (batch)",
11813
+ api: "openai-completions",
11814
+ provider: "openrouter",
11815
+ baseUrl: "https://openrouter.ai/api/v1",
11816
+ reasoning: false,
11817
+ input: ["text", "image"],
11818
+ cost: {
11819
+ input: 5,
11820
+ output: 15,
11821
+ cacheRead: 0,
11822
+ cacheWrite: 0,
11823
+ },
11824
+ contextWindow: 128000,
11825
+ maxTokens: 4096,
11826
+ },
11741
11827
  "openai/gpt-4.1": {
11742
11828
  id: "openai/gpt-4.1",
11743
11829
  name: "OpenAI: GPT-4.1",
@@ -11772,6 +11858,23 @@ export const MODELS = {
11772
11858
  contextWindow: 1047576,
11773
11859
  maxTokens: 32768,
11774
11860
  },
11861
+ "openai/gpt-4.1-mini:batch": {
11862
+ id: "openai/gpt-4.1-mini:batch",
11863
+ name: "OpenAI: GPT-4.1 Mini (batch)",
11864
+ api: "openai-completions",
11865
+ provider: "openrouter",
11866
+ baseUrl: "https://openrouter.ai/api/v1",
11867
+ reasoning: false,
11868
+ input: ["text", "image"],
11869
+ cost: {
11870
+ input: 0.19999999999999998,
11871
+ output: 0.7999999999999999,
11872
+ cacheRead: 0.049999999999999996,
11873
+ cacheWrite: 0,
11874
+ },
11875
+ contextWindow: 1047576,
11876
+ maxTokens: 32768,
11877
+ },
11775
11878
  "openai/gpt-4.1-nano": {
11776
11879
  id: "openai/gpt-4.1-nano",
11777
11880
  name: "OpenAI: GPT-4.1 Nano",
@@ -11783,11 +11886,45 @@ export const MODELS = {
11783
11886
  cost: {
11784
11887
  input: 0.09999999999999999,
11785
11888
  output: 0.39999999999999997,
11786
- cacheRead: 0.03,
11889
+ cacheRead: 0.024999999999999998,
11890
+ cacheWrite: 0,
11891
+ },
11892
+ contextWindow: 1047576,
11893
+ maxTokens: 32768,
11894
+ },
11895
+ "openai/gpt-4.1-nano:batch": {
11896
+ id: "openai/gpt-4.1-nano:batch",
11897
+ name: "OpenAI: GPT-4.1 Nano (batch)",
11898
+ api: "openai-completions",
11899
+ provider: "openrouter",
11900
+ baseUrl: "https://openrouter.ai/api/v1",
11901
+ reasoning: false,
11902
+ input: ["text", "image"],
11903
+ cost: {
11904
+ input: 0.049999999999999996,
11905
+ output: 0.19999999999999998,
11906
+ cacheRead: 0.012499999999999999,
11907
+ cacheWrite: 0,
11908
+ },
11909
+ contextWindow: 1047576,
11910
+ maxTokens: 32768,
11911
+ },
11912
+ "openai/gpt-4.1:batch": {
11913
+ id: "openai/gpt-4.1:batch",
11914
+ name: "OpenAI: GPT-4.1 (batch)",
11915
+ api: "openai-completions",
11916
+ provider: "openrouter",
11917
+ baseUrl: "https://openrouter.ai/api/v1",
11918
+ reasoning: false,
11919
+ input: ["text", "image"],
11920
+ cost: {
11921
+ input: 1,
11922
+ output: 4,
11923
+ cacheRead: 0.25,
11787
11924
  cacheWrite: 0,
11788
11925
  },
11789
11926
  contextWindow: 1047576,
11790
- maxTokens: 942818,
11927
+ maxTokens: 32768,
11791
11928
  },
11792
11929
  "openai/gpt-4o": {
11793
11930
  id: "openai/gpt-4o",
@@ -11891,17 +12028,51 @@ export const MODELS = {
11891
12028
  contextWindow: 128000,
11892
12029
  maxTokens: 16384,
11893
12030
  },
11894
- "openai/gpt-5": {
11895
- id: "openai/gpt-5",
11896
- name: "OpenAI: GPT-5",
12031
+ "openai/gpt-4o-mini:batch": {
12032
+ id: "openai/gpt-4o-mini:batch",
12033
+ name: "OpenAI: GPT-4o-mini (batch)",
11897
12034
  api: "openai-completions",
11898
12035
  provider: "openrouter",
11899
12036
  baseUrl: "https://openrouter.ai/api/v1",
11900
- reasoning: true,
12037
+ reasoning: false,
11901
12038
  input: ["text", "image"],
11902
12039
  cost: {
11903
- input: 1.25,
11904
- output: 10,
12040
+ input: 0.075,
12041
+ output: 0.3,
12042
+ cacheRead: 0.0375,
12043
+ cacheWrite: 0,
12044
+ },
12045
+ contextWindow: 128000,
12046
+ maxTokens: 16384,
12047
+ },
12048
+ "openai/gpt-4o:batch": {
12049
+ id: "openai/gpt-4o:batch",
12050
+ name: "OpenAI: GPT-4o (batch)",
12051
+ api: "openai-completions",
12052
+ provider: "openrouter",
12053
+ baseUrl: "https://openrouter.ai/api/v1",
12054
+ reasoning: false,
12055
+ input: ["text", "image"],
12056
+ cost: {
12057
+ input: 1.25,
12058
+ output: 5,
12059
+ cacheRead: 0.625,
12060
+ cacheWrite: 0,
12061
+ },
12062
+ contextWindow: 128000,
12063
+ maxTokens: 16384,
12064
+ },
12065
+ "openai/gpt-5": {
12066
+ id: "openai/gpt-5",
12067
+ name: "OpenAI: GPT-5",
12068
+ api: "openai-completions",
12069
+ provider: "openrouter",
12070
+ baseUrl: "https://openrouter.ai/api/v1",
12071
+ reasoning: true,
12072
+ input: ["text", "image"],
12073
+ cost: {
12074
+ input: 1.25,
12075
+ output: 10,
11905
12076
  cacheRead: 0.125,
11906
12077
  cacheWrite: 0,
11907
12078
  },
@@ -11925,6 +12096,23 @@ export const MODELS = {
11925
12096
  contextWindow: 400000,
11926
12097
  maxTokens: 128000,
11927
12098
  },
12099
+ "openai/gpt-5-mini:batch": {
12100
+ id: "openai/gpt-5-mini:batch",
12101
+ name: "OpenAI: GPT-5 Mini (batch)",
12102
+ api: "openai-completions",
12103
+ provider: "openrouter",
12104
+ baseUrl: "https://openrouter.ai/api/v1",
12105
+ reasoning: true,
12106
+ input: ["text", "image"],
12107
+ cost: {
12108
+ input: 0.125,
12109
+ output: 1,
12110
+ cacheRead: 0.012499999999999999,
12111
+ cacheWrite: 0,
12112
+ },
12113
+ contextWindow: 400000,
12114
+ maxTokens: 128000,
12115
+ },
11928
12116
  "openai/gpt-5-nano": {
11929
12117
  id: "openai/gpt-5-nano",
11930
12118
  name: "OpenAI: GPT-5 Nano",
@@ -11942,6 +12130,23 @@ export const MODELS = {
11942
12130
  contextWindow: 400000,
11943
12131
  maxTokens: 128000,
11944
12132
  },
12133
+ "openai/gpt-5-nano:batch": {
12134
+ id: "openai/gpt-5-nano:batch",
12135
+ name: "OpenAI: GPT-5 Nano (batch)",
12136
+ api: "openai-completions",
12137
+ provider: "openrouter",
12138
+ baseUrl: "https://openrouter.ai/api/v1",
12139
+ reasoning: true,
12140
+ input: ["text", "image"],
12141
+ cost: {
12142
+ input: 0.024999999999999998,
12143
+ output: 0.19999999999999998,
12144
+ cacheRead: 0.0025,
12145
+ cacheWrite: 0,
12146
+ },
12147
+ contextWindow: 400000,
12148
+ maxTokens: 128000,
12149
+ },
11945
12150
  "openai/gpt-5-pro": {
11946
12151
  id: "openai/gpt-5-pro",
11947
12152
  name: "OpenAI: GPT-5 Pro",
@@ -11959,6 +12164,23 @@ export const MODELS = {
11959
12164
  contextWindow: 400000,
11960
12165
  maxTokens: 128000,
11961
12166
  },
12167
+ "openai/gpt-5-pro:batch": {
12168
+ id: "openai/gpt-5-pro:batch",
12169
+ name: "OpenAI: GPT-5 Pro (batch)",
12170
+ api: "openai-completions",
12171
+ provider: "openrouter",
12172
+ baseUrl: "https://openrouter.ai/api/v1",
12173
+ reasoning: true,
12174
+ input: ["text", "image"],
12175
+ cost: {
12176
+ input: 7.5,
12177
+ output: 60,
12178
+ cacheRead: 0,
12179
+ cacheWrite: 0,
12180
+ },
12181
+ contextWindow: 400000,
12182
+ maxTokens: 128000,
12183
+ },
11962
12184
  "openai/gpt-5.1": {
11963
12185
  id: "openai/gpt-5.1",
11964
12186
  name: "OpenAI: GPT-5.1",
@@ -12027,6 +12249,23 @@ export const MODELS = {
12027
12249
  contextWindow: 400000,
12028
12250
  maxTokens: 128000,
12029
12251
  },
12252
+ "openai/gpt-5.1:batch": {
12253
+ id: "openai/gpt-5.1:batch",
12254
+ name: "OpenAI: GPT-5.1 (batch)",
12255
+ api: "openai-completions",
12256
+ provider: "openrouter",
12257
+ baseUrl: "https://openrouter.ai/api/v1",
12258
+ reasoning: true,
12259
+ input: ["text", "image"],
12260
+ cost: {
12261
+ input: 0.625,
12262
+ output: 5,
12263
+ cacheRead: 0.0625,
12264
+ cacheWrite: 0,
12265
+ },
12266
+ contextWindow: 400000,
12267
+ maxTokens: 128000,
12268
+ },
12030
12269
  "openai/gpt-5.2": {
12031
12270
  id: "openai/gpt-5.2",
12032
12271
  name: "OpenAI: GPT-5.2",
@@ -12095,6 +12334,40 @@ export const MODELS = {
12095
12334
  contextWindow: 400000,
12096
12335
  maxTokens: 128000,
12097
12336
  },
12337
+ "openai/gpt-5.2-pro:batch": {
12338
+ id: "openai/gpt-5.2-pro:batch",
12339
+ name: "OpenAI: GPT-5.2 Pro (batch)",
12340
+ api: "openai-completions",
12341
+ provider: "openrouter",
12342
+ baseUrl: "https://openrouter.ai/api/v1",
12343
+ reasoning: true,
12344
+ input: ["text", "image"],
12345
+ cost: {
12346
+ input: 10.5,
12347
+ output: 84,
12348
+ cacheRead: 0,
12349
+ cacheWrite: 0,
12350
+ },
12351
+ contextWindow: 400000,
12352
+ maxTokens: 128000,
12353
+ },
12354
+ "openai/gpt-5.2:batch": {
12355
+ id: "openai/gpt-5.2:batch",
12356
+ name: "OpenAI: GPT-5.2 (batch)",
12357
+ api: "openai-completions",
12358
+ provider: "openrouter",
12359
+ baseUrl: "https://openrouter.ai/api/v1",
12360
+ reasoning: true,
12361
+ input: ["text", "image"],
12362
+ cost: {
12363
+ input: 0.875,
12364
+ output: 7,
12365
+ cacheRead: 0.0875,
12366
+ cacheWrite: 0,
12367
+ },
12368
+ contextWindow: 400000,
12369
+ maxTokens: 128000,
12370
+ },
12098
12371
  "openai/gpt-5.3-codex": {
12099
12372
  id: "openai/gpt-5.3-codex",
12100
12373
  name: "OpenAI: GPT-5.3-Codex",
@@ -12146,6 +12419,23 @@ export const MODELS = {
12146
12419
  contextWindow: 400000,
12147
12420
  maxTokens: 128000,
12148
12421
  },
12422
+ "openai/gpt-5.4-mini:batch": {
12423
+ id: "openai/gpt-5.4-mini:batch",
12424
+ name: "OpenAI: GPT-5.4 Mini (batch)",
12425
+ api: "openai-completions",
12426
+ provider: "openrouter",
12427
+ baseUrl: "https://openrouter.ai/api/v1",
12428
+ reasoning: true,
12429
+ input: ["text", "image"],
12430
+ cost: {
12431
+ input: 0.375,
12432
+ output: 2.25,
12433
+ cacheRead: 0.0375,
12434
+ cacheWrite: 0,
12435
+ },
12436
+ contextWindow: 400000,
12437
+ maxTokens: 128000,
12438
+ },
12149
12439
  "openai/gpt-5.4-nano": {
12150
12440
  id: "openai/gpt-5.4-nano",
12151
12441
  name: "OpenAI: GPT-5.4 Nano",
@@ -12163,6 +12453,23 @@ export const MODELS = {
12163
12453
  contextWindow: 400000,
12164
12454
  maxTokens: 128000,
12165
12455
  },
12456
+ "openai/gpt-5.4-nano:batch": {
12457
+ id: "openai/gpt-5.4-nano:batch",
12458
+ name: "OpenAI: GPT-5.4 Nano (batch)",
12459
+ api: "openai-completions",
12460
+ provider: "openrouter",
12461
+ baseUrl: "https://openrouter.ai/api/v1",
12462
+ reasoning: true,
12463
+ input: ["text", "image"],
12464
+ cost: {
12465
+ input: 0.09999999999999999,
12466
+ output: 0.625,
12467
+ cacheRead: 0.01,
12468
+ cacheWrite: 0,
12469
+ },
12470
+ contextWindow: 400000,
12471
+ maxTokens: 128000,
12472
+ },
12166
12473
  "openai/gpt-5.4-pro": {
12167
12474
  id: "openai/gpt-5.4-pro",
12168
12475
  name: "OpenAI: GPT-5.4 Pro",
@@ -12180,6 +12487,40 @@ export const MODELS = {
12180
12487
  contextWindow: 1050000,
12181
12488
  maxTokens: 128000,
12182
12489
  },
12490
+ "openai/gpt-5.4-pro:batch": {
12491
+ id: "openai/gpt-5.4-pro:batch",
12492
+ name: "OpenAI: GPT-5.4 Pro (batch)",
12493
+ api: "openai-completions",
12494
+ provider: "openrouter",
12495
+ baseUrl: "https://openrouter.ai/api/v1",
12496
+ reasoning: true,
12497
+ input: ["text", "image"],
12498
+ cost: {
12499
+ input: 15,
12500
+ output: 90,
12501
+ cacheRead: 0,
12502
+ cacheWrite: 0,
12503
+ },
12504
+ contextWindow: 1050000,
12505
+ maxTokens: 128000,
12506
+ },
12507
+ "openai/gpt-5.4:batch": {
12508
+ id: "openai/gpt-5.4:batch",
12509
+ name: "OpenAI: GPT-5.4 (batch)",
12510
+ api: "openai-completions",
12511
+ provider: "openrouter",
12512
+ baseUrl: "https://openrouter.ai/api/v1",
12513
+ reasoning: true,
12514
+ input: ["text", "image"],
12515
+ cost: {
12516
+ input: 1.25,
12517
+ output: 7.5,
12518
+ cacheRead: 0.125,
12519
+ cacheWrite: 0,
12520
+ },
12521
+ contextWindow: 1050000,
12522
+ maxTokens: 128000,
12523
+ },
12183
12524
  "openai/gpt-5.5": {
12184
12525
  id: "openai/gpt-5.5",
12185
12526
  name: "OpenAI: GPT-5.5",
@@ -12214,6 +12555,40 @@ export const MODELS = {
12214
12555
  contextWindow: 1050000,
12215
12556
  maxTokens: 128000,
12216
12557
  },
12558
+ "openai/gpt-5.5-pro:batch": {
12559
+ id: "openai/gpt-5.5-pro:batch",
12560
+ name: "OpenAI: GPT-5.5 Pro (batch)",
12561
+ api: "openai-completions",
12562
+ provider: "openrouter",
12563
+ baseUrl: "https://openrouter.ai/api/v1",
12564
+ reasoning: true,
12565
+ input: ["text", "image"],
12566
+ cost: {
12567
+ input: 15,
12568
+ output: 90,
12569
+ cacheRead: 0,
12570
+ cacheWrite: 0,
12571
+ },
12572
+ contextWindow: 1050000,
12573
+ maxTokens: 128000,
12574
+ },
12575
+ "openai/gpt-5.5:batch": {
12576
+ id: "openai/gpt-5.5:batch",
12577
+ name: "OpenAI: GPT-5.5 (batch)",
12578
+ api: "openai-completions",
12579
+ provider: "openrouter",
12580
+ baseUrl: "https://openrouter.ai/api/v1",
12581
+ reasoning: true,
12582
+ input: ["text", "image"],
12583
+ cost: {
12584
+ input: 2.5,
12585
+ output: 15,
12586
+ cacheRead: 0.25,
12587
+ cacheWrite: 0,
12588
+ },
12589
+ contextWindow: 1050000,
12590
+ maxTokens: 128000,
12591
+ },
12217
12592
  "openai/gpt-5.6-luna": {
12218
12593
  id: "openai/gpt-5.6-luna",
12219
12594
  name: "OpenAI: GPT-5.6 Luna",
@@ -12240,17 +12615,119 @@ export const MODELS = {
12240
12615
  reasoning: true,
12241
12616
  input: ["text", "image"],
12242
12617
  cost: {
12243
- input: 0.19999999999999998,
12244
- output: 1.2,
12245
- cacheRead: 0.02,
12246
- cacheWrite: 0.25,
12618
+ input: 0.19999999999999998,
12619
+ output: 1.2,
12620
+ cacheRead: 0.02,
12621
+ cacheWrite: 0.25,
12622
+ },
12623
+ contextWindow: 1050000,
12624
+ maxTokens: 128000,
12625
+ },
12626
+ "openai/gpt-5.6-luna-pro:batch": {
12627
+ id: "openai/gpt-5.6-luna-pro:batch",
12628
+ name: "OpenAI: GPT-5.6 Luna Pro (batch)",
12629
+ api: "openai-completions",
12630
+ provider: "openrouter",
12631
+ baseUrl: "https://openrouter.ai/api/v1",
12632
+ reasoning: true,
12633
+ input: ["text", "image"],
12634
+ cost: {
12635
+ input: 0.09999999999999999,
12636
+ output: 0.6,
12637
+ cacheRead: 0.01,
12638
+ cacheWrite: 0,
12639
+ },
12640
+ contextWindow: 1050000,
12641
+ maxTokens: 128000,
12642
+ },
12643
+ "openai/gpt-5.6-luna:batch": {
12644
+ id: "openai/gpt-5.6-luna:batch",
12645
+ name: "OpenAI: GPT-5.6 Luna (batch)",
12646
+ api: "openai-completions",
12647
+ provider: "openrouter",
12648
+ baseUrl: "https://openrouter.ai/api/v1",
12649
+ reasoning: true,
12650
+ input: ["text", "image"],
12651
+ cost: {
12652
+ input: 0.09999999999999999,
12653
+ output: 0.6,
12654
+ cacheRead: 0.01,
12655
+ cacheWrite: 0,
12656
+ },
12657
+ contextWindow: 1050000,
12658
+ maxTokens: 128000,
12659
+ },
12660
+ "openai/gpt-5.6-sol": {
12661
+ id: "openai/gpt-5.6-sol",
12662
+ name: "OpenAI: GPT-5.6 Sol",
12663
+ api: "openai-completions",
12664
+ provider: "openrouter",
12665
+ baseUrl: "https://openrouter.ai/api/v1",
12666
+ reasoning: true,
12667
+ input: ["text", "image"],
12668
+ cost: {
12669
+ input: 2,
12670
+ output: 10,
12671
+ cacheRead: 0.19999999999999998,
12672
+ cacheWrite: 2.5,
12673
+ },
12674
+ contextWindow: 1050000,
12675
+ maxTokens: 128000,
12676
+ },
12677
+ "openai/gpt-5.6-sol-pro": {
12678
+ id: "openai/gpt-5.6-sol-pro",
12679
+ name: "OpenAI: GPT-5.6 Sol Pro",
12680
+ api: "openai-completions",
12681
+ provider: "openrouter",
12682
+ baseUrl: "https://openrouter.ai/api/v1",
12683
+ reasoning: true,
12684
+ input: ["text", "image"],
12685
+ cost: {
12686
+ input: 2,
12687
+ output: 10,
12688
+ cacheRead: 0.19999999999999998,
12689
+ cacheWrite: 2.5,
12690
+ },
12691
+ contextWindow: 1050000,
12692
+ maxTokens: 128000,
12693
+ },
12694
+ "openai/gpt-5.6-sol-pro:batch": {
12695
+ id: "openai/gpt-5.6-sol-pro:batch",
12696
+ name: "OpenAI: GPT-5.6 Sol Pro (batch)",
12697
+ api: "openai-completions",
12698
+ provider: "openrouter",
12699
+ baseUrl: "https://openrouter.ai/api/v1",
12700
+ reasoning: true,
12701
+ input: ["text", "image"],
12702
+ cost: {
12703
+ input: 1,
12704
+ output: 5,
12705
+ cacheRead: 0.09999999999999999,
12706
+ cacheWrite: 1.25,
12707
+ },
12708
+ contextWindow: 1050000,
12709
+ maxTokens: 128000,
12710
+ },
12711
+ "openai/gpt-5.6-sol:batch": {
12712
+ id: "openai/gpt-5.6-sol:batch",
12713
+ name: "OpenAI: GPT-5.6 Sol (batch)",
12714
+ api: "openai-completions",
12715
+ provider: "openrouter",
12716
+ baseUrl: "https://openrouter.ai/api/v1",
12717
+ reasoning: true,
12718
+ input: ["text", "image"],
12719
+ cost: {
12720
+ input: 1,
12721
+ output: 5,
12722
+ cacheRead: 0.09999999999999999,
12723
+ cacheWrite: 1.25,
12247
12724
  },
12248
12725
  contextWindow: 1050000,
12249
12726
  maxTokens: 128000,
12250
12727
  },
12251
- "openai/gpt-5.6-sol": {
12252
- id: "openai/gpt-5.6-sol",
12253
- name: "OpenAI: GPT-5.6 Sol",
12728
+ "openai/gpt-5.6-terra": {
12729
+ id: "openai/gpt-5.6-terra",
12730
+ name: "OpenAI: GPT-5.6 Terra",
12254
12731
  api: "openai-completions",
12255
12732
  provider: "openrouter",
12256
12733
  baseUrl: "https://openrouter.ai/api/v1",
@@ -12258,16 +12735,16 @@ export const MODELS = {
12258
12735
  input: ["text", "image"],
12259
12736
  cost: {
12260
12737
  input: 2,
12261
- output: 10,
12738
+ output: 12,
12262
12739
  cacheRead: 0.19999999999999998,
12263
12740
  cacheWrite: 2.5,
12264
12741
  },
12265
12742
  contextWindow: 1050000,
12266
12743
  maxTokens: 128000,
12267
12744
  },
12268
- "openai/gpt-5.6-sol-pro": {
12269
- id: "openai/gpt-5.6-sol-pro",
12270
- name: "OpenAI: GPT-5.6 Sol Pro",
12745
+ "openai/gpt-5.6-terra-pro": {
12746
+ id: "openai/gpt-5.6-terra-pro",
12747
+ name: "OpenAI: GPT-5.6 Terra Pro",
12271
12748
  api: "openai-completions",
12272
12749
  provider: "openrouter",
12273
12750
  baseUrl: "https://openrouter.ai/api/v1",
@@ -12275,47 +12752,64 @@ export const MODELS = {
12275
12752
  input: ["text", "image"],
12276
12753
  cost: {
12277
12754
  input: 2,
12278
- output: 10,
12755
+ output: 12,
12279
12756
  cacheRead: 0.19999999999999998,
12280
12757
  cacheWrite: 2.5,
12281
12758
  },
12282
12759
  contextWindow: 1050000,
12283
12760
  maxTokens: 128000,
12284
12761
  },
12285
- "openai/gpt-5.6-terra": {
12286
- id: "openai/gpt-5.6-terra",
12287
- name: "OpenAI: GPT-5.6 Terra",
12762
+ "openai/gpt-5.6-terra-pro:batch": {
12763
+ id: "openai/gpt-5.6-terra-pro:batch",
12764
+ name: "OpenAI: GPT-5.6 Terra Pro (batch)",
12288
12765
  api: "openai-completions",
12289
12766
  provider: "openrouter",
12290
12767
  baseUrl: "https://openrouter.ai/api/v1",
12291
12768
  reasoning: true,
12292
12769
  input: ["text", "image"],
12293
12770
  cost: {
12294
- input: 2,
12295
- output: 12,
12296
- cacheRead: 0.19999999999999998,
12297
- cacheWrite: 2.5,
12771
+ input: 1,
12772
+ output: 6,
12773
+ cacheRead: 0.09999999999999999,
12774
+ cacheWrite: 0,
12298
12775
  },
12299
12776
  contextWindow: 1050000,
12300
12777
  maxTokens: 128000,
12301
12778
  },
12302
- "openai/gpt-5.6-terra-pro": {
12303
- id: "openai/gpt-5.6-terra-pro",
12304
- name: "OpenAI: GPT-5.6 Terra Pro",
12779
+ "openai/gpt-5.6-terra:batch": {
12780
+ id: "openai/gpt-5.6-terra:batch",
12781
+ name: "OpenAI: GPT-5.6 Terra (batch)",
12305
12782
  api: "openai-completions",
12306
12783
  provider: "openrouter",
12307
12784
  baseUrl: "https://openrouter.ai/api/v1",
12308
12785
  reasoning: true,
12309
12786
  input: ["text", "image"],
12310
12787
  cost: {
12311
- input: 2,
12312
- output: 12,
12313
- cacheRead: 0.19999999999999998,
12314
- cacheWrite: 2.5,
12788
+ input: 1,
12789
+ output: 6,
12790
+ cacheRead: 0.09999999999999999,
12791
+ cacheWrite: 0,
12315
12792
  },
12316
12793
  contextWindow: 1050000,
12317
12794
  maxTokens: 128000,
12318
12795
  },
12796
+ "openai/gpt-5:batch": {
12797
+ id: "openai/gpt-5:batch",
12798
+ name: "OpenAI: GPT-5 (batch)",
12799
+ api: "openai-completions",
12800
+ provider: "openrouter",
12801
+ baseUrl: "https://openrouter.ai/api/v1",
12802
+ reasoning: true,
12803
+ input: ["text", "image"],
12804
+ cost: {
12805
+ input: 0.625,
12806
+ output: 5,
12807
+ cacheRead: 0.0625,
12808
+ cacheWrite: 0,
12809
+ },
12810
+ contextWindow: 400000,
12811
+ maxTokens: 128000,
12812
+ },
12319
12813
  "openai/gpt-audio": {
12320
12814
  id: "openai/gpt-audio",
12321
12815
  name: "OpenAI: GPT Audio",
@@ -12384,6 +12878,23 @@ export const MODELS = {
12384
12878
  contextWindow: 131072,
12385
12879
  maxTokens: 117964,
12386
12880
  },
12881
+ "openai/gpt-oss-120b:batch": {
12882
+ id: "openai/gpt-oss-120b:batch",
12883
+ name: "OpenAI: gpt-oss-120b (batch)",
12884
+ api: "openai-completions",
12885
+ provider: "openrouter",
12886
+ baseUrl: "https://openrouter.ai/api/v1",
12887
+ reasoning: true,
12888
+ input: ["text"],
12889
+ cost: {
12890
+ input: 0.15,
12891
+ output: 0.6,
12892
+ cacheRead: 0,
12893
+ cacheWrite: 0,
12894
+ },
12895
+ contextWindow: 131072,
12896
+ maxTokens: 117964,
12897
+ },
12387
12898
  "openai/gpt-oss-20b": {
12388
12899
  id: "openai/gpt-oss-20b",
12389
12900
  name: "OpenAI: gpt-oss-20b",
@@ -12486,6 +12997,23 @@ export const MODELS = {
12486
12997
  contextWindow: 200000,
12487
12998
  maxTokens: 100000,
12488
12999
  },
13000
+ "openai/o3-mini:batch": {
13001
+ id: "openai/o3-mini:batch",
13002
+ name: "OpenAI: o3 Mini (batch)",
13003
+ api: "openai-completions",
13004
+ provider: "openrouter",
13005
+ baseUrl: "https://openrouter.ai/api/v1",
13006
+ reasoning: true,
13007
+ input: ["text"],
13008
+ cost: {
13009
+ input: 0.55,
13010
+ output: 2.2,
13011
+ cacheRead: 0.275,
13012
+ cacheWrite: 0,
13013
+ },
13014
+ contextWindow: 200000,
13015
+ maxTokens: 100000,
13016
+ },
12489
13017
  "openai/o3-pro": {
12490
13018
  id: "openai/o3-pro",
12491
13019
  name: "OpenAI: o3 Pro",
@@ -12503,6 +13031,23 @@ export const MODELS = {
12503
13031
  contextWindow: 200000,
12504
13032
  maxTokens: 100000,
12505
13033
  },
13034
+ "openai/o3:batch": {
13035
+ id: "openai/o3:batch",
13036
+ name: "OpenAI: o3 (batch)",
13037
+ api: "openai-completions",
13038
+ provider: "openrouter",
13039
+ baseUrl: "https://openrouter.ai/api/v1",
13040
+ reasoning: true,
13041
+ input: ["text", "image"],
13042
+ cost: {
13043
+ input: 1,
13044
+ output: 4,
13045
+ cacheRead: 0.25,
13046
+ cacheWrite: 0,
13047
+ },
13048
+ contextWindow: 200000,
13049
+ maxTokens: 100000,
13050
+ },
12506
13051
  "openai/o4-mini": {
12507
13052
  id: "openai/o4-mini",
12508
13053
  name: "OpenAI: o4 Mini",
@@ -12537,6 +13082,23 @@ export const MODELS = {
12537
13082
  contextWindow: 200000,
12538
13083
  maxTokens: 100000,
12539
13084
  },
13085
+ "openai/o4-mini:batch": {
13086
+ id: "openai/o4-mini:batch",
13087
+ name: "OpenAI: o4 Mini (batch)",
13088
+ api: "openai-completions",
13089
+ provider: "openrouter",
13090
+ baseUrl: "https://openrouter.ai/api/v1",
13091
+ reasoning: true,
13092
+ input: ["text", "image"],
13093
+ cost: {
13094
+ input: 0.55,
13095
+ output: 2.2,
13096
+ cacheRead: 0.1375,
13097
+ cacheWrite: 0,
13098
+ },
13099
+ contextWindow: 200000,
13100
+ maxTokens: 100000,
13101
+ },
12540
13102
  "openrouter/auto": {
12541
13103
  id: "openrouter/auto",
12542
13104
  name: "Auto Router",
@@ -13073,13 +13635,13 @@ export const MODELS = {
13073
13635
  reasoning: false,
13074
13636
  input: ["text", "image"],
13075
13637
  cost: {
13076
- input: 0.13,
13077
- output: 0.52,
13638
+ input: 0.15,
13639
+ output: 0.6,
13078
13640
  cacheRead: 0,
13079
13641
  cacheWrite: 0,
13080
13642
  },
13081
13643
  contextWindow: 262144,
13082
- maxTokens: 32768,
13644
+ maxTokens: 16384,
13083
13645
  },
13084
13646
  "qwen/qwen3-vl-30b-a3b-thinking": {
13085
13647
  id: "qwen/qwen3-vl-30b-a3b-thinking",
@@ -13234,6 +13796,23 @@ export const MODELS = {
13234
13796
  contextWindow: 262144,
13235
13797
  maxTokens: 235929,
13236
13798
  },
13799
+ "qwen/qwen3.5-9b:batch": {
13800
+ id: "qwen/qwen3.5-9b:batch",
13801
+ name: "Qwen: Qwen3.5-9B (batch)",
13802
+ api: "openai-completions",
13803
+ provider: "openrouter",
13804
+ baseUrl: "https://openrouter.ai/api/v1",
13805
+ reasoning: true,
13806
+ input: ["text", "image"],
13807
+ cost: {
13808
+ input: 0.16999999999999998,
13809
+ output: 0.25,
13810
+ cacheRead: 0,
13811
+ cacheWrite: 0,
13812
+ },
13813
+ contextWindow: 262144,
13814
+ maxTokens: 235929,
13815
+ },
13237
13816
  "qwen/qwen3.5-flash-02-23": {
13238
13817
  id: "qwen/qwen3.5-flash-02-23",
13239
13818
  name: "Qwen: Qwen3.5-Flash",
@@ -13432,11 +14011,11 @@ export const MODELS = {
13432
14011
  cost: {
13433
14012
  input: 2,
13434
14013
  output: 6,
13435
- cacheRead: 0.19999999999999998,
14014
+ cacheRead: 0.25,
13436
14015
  cacheWrite: 0,
13437
14016
  },
13438
14017
  contextWindow: 1048576,
13439
- maxTokens: 131072,
14018
+ maxTokens: 262144,
13440
14019
  },
13441
14020
  "qwen/qwen3.8-2.4t-a95b:batch": {
13442
14021
  id: "qwen/qwen3.8-2.4t-a95b:batch",
@@ -13447,9 +14026,9 @@ export const MODELS = {
13447
14026
  reasoning: true,
13448
14027
  input: ["text"],
13449
14028
  cost: {
13450
- input: 2,
13451
- output: 6,
13452
- cacheRead: 0.25,
14029
+ input: 2.5,
14030
+ output: 6.25,
14031
+ cacheRead: 0.5,
13453
14032
  cacheWrite: 0,
13454
14033
  },
13455
14034
  contextWindow: 1010000,
@@ -13702,13 +14281,13 @@ export const MODELS = {
13702
14281
  reasoning: true,
13703
14282
  input: ["text", "image"],
13704
14283
  cost: {
13705
- input: 0.95,
14284
+ input: 1,
13706
14285
  output: 4.05,
13707
- cacheRead: 0.16,
14286
+ cacheRead: 0.16999999999999998,
13708
14287
  cacheWrite: 0,
13709
14288
  },
13710
14289
  contextWindow: 1048576,
13711
- maxTokens: 262144,
14290
+ maxTokens: 471859,
13712
14291
  },
13713
14292
  "thinkingmachines/inkling-small": {
13714
14293
  id: "thinkingmachines/inkling-small",
@@ -13727,6 +14306,23 @@ export const MODELS = {
13727
14306
  contextWindow: 1048576,
13728
14307
  maxTokens: 262144,
13729
14308
  },
14309
+ "thinkingmachines/inkling-small:batch": {
14310
+ id: "thinkingmachines/inkling-small:batch",
14311
+ name: "Thinking Machines: Inkling Small (batch)",
14312
+ api: "openai-completions",
14313
+ provider: "openrouter",
14314
+ baseUrl: "https://openrouter.ai/api/v1",
14315
+ reasoning: true,
14316
+ input: ["text", "image"],
14317
+ cost: {
14318
+ input: 0.5,
14319
+ output: 1.2,
14320
+ cacheRead: 0.09999999999999999,
14321
+ cacheWrite: 0,
14322
+ },
14323
+ contextWindow: 524288,
14324
+ maxTokens: 471859,
14325
+ },
13730
14326
  "thinkingmachines/inkling-small:free": {
13731
14327
  id: "thinkingmachines/inkling-small:free",
13732
14328
  name: "Thinking Machines: Inkling Small (free)",
@@ -14093,13 +14689,13 @@ export const MODELS = {
14093
14689
  reasoning: true,
14094
14690
  input: ["text"],
14095
14691
  cost: {
14096
- input: 1.26,
14097
- output: 3.9600000000000004,
14098
- cacheRead: 0.234,
14692
+ input: 0.966,
14693
+ output: 3.036,
14694
+ cacheRead: 0.1794,
14099
14695
  cacheWrite: 0,
14100
14696
  },
14101
14697
  contextWindow: 204800,
14102
- maxTokens: 182476,
14698
+ maxTokens: 128000,
14103
14699
  },
14104
14700
  "z-ai/glm-5.2": {
14105
14701
  id: "z-ai/glm-5.2",
@@ -14169,6 +14765,23 @@ export const MODELS = {
14169
14765
  contextWindow: 1310720,
14170
14766
  maxTokens: 131072,
14171
14767
  },
14768
+ "z-ai/glm-5.3-flash:batch": {
14769
+ id: "z-ai/glm-5.3-flash:batch",
14770
+ name: "Z.ai: GLM 5.3 Flash (batch)",
14771
+ api: "openai-completions",
14772
+ provider: "openrouter",
14773
+ baseUrl: "https://openrouter.ai/api/v1",
14774
+ reasoning: true,
14775
+ input: ["text", "image"],
14776
+ cost: {
14777
+ input: 0.15,
14778
+ output: 0.5,
14779
+ cacheRead: 0.03,
14780
+ cacheWrite: 0,
14781
+ },
14782
+ contextWindow: 1048575,
14783
+ maxTokens: 943717,
14784
+ },
14172
14785
  "z-ai/glm-5v-turbo": {
14173
14786
  id: "z-ai/glm-5v-turbo",
14174
14787
  name: "Z.ai: GLM 5V Turbo",
@@ -14197,7 +14810,7 @@ export const MODELS = {
14197
14810
  cost: {
14198
14811
  input: 10,
14199
14812
  output: 50,
14200
- cacheRead: 1,
14813
+ cacheRead: 0.25,
14201
14814
  cacheWrite: 12.5,
14202
14815
  },
14203
14816
  contextWindow: 1000000,
@@ -14263,9 +14876,9 @@ export const MODELS = {
14263
14876
  reasoning: true,
14264
14877
  input: ["text"],
14265
14878
  cost: {
14266
- input: 0.03,
14267
- output: 0.09999999999999999,
14268
- cacheRead: 0.007,
14879
+ input: 0.049980000000000004,
14880
+ output: 0.09996000000000001,
14881
+ cacheRead: 0.009996000000000001,
14269
14882
  cacheWrite: 0,
14270
14883
  },
14271
14884
  contextWindow: 1310720,
@@ -14382,13 +14995,13 @@ export const MODELS = {
14382
14995
  reasoning: true,
14383
14996
  input: ["text"],
14384
14997
  cost: {
14385
- input: 1.25,
14386
- output: 4.4,
14387
- cacheRead: 0.26,
14998
+ input: 1.17,
14999
+ output: 3.9600000000000004,
15000
+ cacheRead: 0.234,
14388
15001
  cacheWrite: 0,
14389
15002
  },
14390
15003
  contextWindow: 1310720,
14391
- maxTokens: 131072,
15004
+ maxTokens: 943718,
14392
15005
  },
14393
15006
  },
14394
15007
  "vercel-ai-gateway": {
@@ -14843,10 +15456,10 @@ export const MODELS = {
14843
15456
  reasoning: true,
14844
15457
  input: ["text", "image"],
14845
15458
  cost: {
14846
- input: 0.55,
14847
- output: 3.3000000000000003,
14848
- cacheRead: 0.11,
14849
- cacheWrite: 0,
15459
+ input: 0.5,
15460
+ output: 3,
15461
+ cacheRead: 0.09999999999999999,
15462
+ cacheWrite: 0.625,
14850
15463
  },
14851
15464
  contextWindow: 1000000,
14852
15465
  maxTokens: 131072,
@@ -14868,6 +15481,23 @@ export const MODELS = {
14868
15481
  contextWindow: 991000,
14869
15482
  maxTokens: 128000,
14870
15483
  },
15484
+ "alibaba/qwen3.8-flash-next": {
15485
+ id: "alibaba/qwen3.8-flash-next",
15486
+ name: "Qwen 3.8 Flash Next",
15487
+ api: "anthropic-messages",
15488
+ provider: "vercel-ai-gateway",
15489
+ baseUrl: "https://ai-gateway.vercel.sh",
15490
+ reasoning: true,
15491
+ input: ["text", "image"],
15492
+ cost: {
15493
+ input: 0.12,
15494
+ output: 0.39999999999999997,
15495
+ cacheRead: 0.01,
15496
+ cacheWrite: 0,
15497
+ },
15498
+ contextWindow: 1048576,
15499
+ maxTokens: 1048576,
15500
+ },
14871
15501
  "alibaba/qwen3.8-max": {
14872
15502
  id: "alibaba/qwen3.8-max",
14873
15503
  name: "Qwen 3.8 Max",
@@ -14987,6 +15617,23 @@ export const MODELS = {
14987
15617
  contextWindow: 1000000,
14988
15618
  maxTokens: 128000,
14989
15619
  },
15620
+ "anthropic/claude-fable-5.1": {
15621
+ id: "anthropic/claude-fable-5.1",
15622
+ name: "Claude Fable 5.1",
15623
+ api: "anthropic-messages",
15624
+ provider: "vercel-ai-gateway",
15625
+ baseUrl: "https://ai-gateway.vercel.sh",
15626
+ reasoning: true,
15627
+ input: ["text", "image"],
15628
+ cost: {
15629
+ input: 10,
15630
+ output: 50,
15631
+ cacheRead: 0.25,
15632
+ cacheWrite: 12.5,
15633
+ },
15634
+ contextWindow: 1000000,
15635
+ maxTokens: 128000,
15636
+ },
14990
15637
  "anthropic/claude-haiku-4.5": {
14991
15638
  id: "anthropic/claude-haiku-4.5",
14992
15639
  name: "Claude Haiku 4.5",
@@ -15293,23 +15940,6 @@ export const MODELS = {
15293
15940
  contextWindow: 128000,
15294
15941
  maxTokens: 8192,
15295
15942
  },
15296
- "deepseek/deepseek-v3": {
15297
- id: "deepseek/deepseek-v3",
15298
- name: "DeepSeek V3 0324",
15299
- api: "anthropic-messages",
15300
- provider: "vercel-ai-gateway",
15301
- baseUrl: "https://ai-gateway.vercel.sh",
15302
- reasoning: false,
15303
- input: ["text"],
15304
- cost: {
15305
- input: 0.27,
15306
- output: 1.12,
15307
- cacheRead: 0.135,
15308
- cacheWrite: 0,
15309
- },
15310
- contextWindow: 163840,
15311
- maxTokens: 163840,
15312
- },
15313
15943
  "deepseek/deepseek-v3.1": {
15314
15944
  id: "deepseek/deepseek-v3.1",
15315
15945
  name: "DeepSeek V3.1",
@@ -15426,8 +16056,8 @@ export const MODELS = {
15426
16056
  cacheRead: 0.007,
15427
16057
  cacheWrite: 0,
15428
16058
  },
15429
- contextWindow: 1000000,
15430
- maxTokens: 384000,
16059
+ contextWindow: 1048576,
16060
+ maxTokens: 1048576,
15431
16061
  },
15432
16062
  "deepseek/deepseek-v4-pro": {
15433
16063
  id: "deepseek/deepseek-v4-pro",
@@ -17962,6 +18592,23 @@ export const MODELS = {
17962
18592
  contextWindow: 1050000,
17963
18593
  maxTokens: 131000,
17964
18594
  },
18595
+ "xiaomi/mimo-v2.5-pro-ultraspeed": {
18596
+ id: "xiaomi/mimo-v2.5-pro-ultraspeed",
18597
+ name: "MiMo V2.5 Pro UltraSpeed",
18598
+ api: "anthropic-messages",
18599
+ provider: "vercel-ai-gateway",
18600
+ baseUrl: "https://ai-gateway.vercel.sh",
18601
+ reasoning: true,
18602
+ input: ["text"],
18603
+ cost: {
18604
+ input: 1.305,
18605
+ output: 2.61,
18606
+ cacheRead: 0.0108,
18607
+ cacheWrite: 0,
18608
+ },
18609
+ contextWindow: 1048576,
18610
+ maxTokens: 131072,
18611
+ },
17965
18612
  "zai/glm-4.5": {
17966
18613
  id: "zai/glm-4.5",
17967
18614
  name: "GLM 4.5",