@dreb/ai 2.64.0 → 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,
@@ -9877,9 +9912,9 @@ export const MODELS = {
9877
9912
  reasoning: true,
9878
9913
  input: ["text"],
9879
9914
  cost: {
9880
- input: 0.049999999999999996,
9881
- output: 0.09999999999999999,
9882
- cacheRead: 0.01,
9915
+ input: 0.065,
9916
+ output: 0.18,
9917
+ cacheRead: 0.016,
9883
9918
  cacheWrite: 0,
9884
9919
  },
9885
9920
  contextWindow: 1310720,
@@ -9928,9 +9963,9 @@ export const MODELS = {
9928
9963
  reasoning: true,
9929
9964
  input: ["text"],
9930
9965
  cost: {
9931
- input: 0.741588,
9932
- output: 1.483176,
9933
- cacheRead: 0.061799,
9966
+ input: 1.0274699999999999,
9967
+ output: 2.0549399999999998,
9968
+ cacheRead: 0.0856225,
9934
9969
  cacheWrite: 0,
9935
9970
  },
9936
9971
  contextWindow: 1048576,
@@ -10548,6 +10583,23 @@ export const MODELS = {
10548
10583
  contextWindow: 131072,
10549
10584
  maxTokens: 117964,
10550
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
+ },
10551
10603
  "inception/mercury-2": {
10552
10604
  id: "inception/mercury-2",
10553
10605
  name: "Inception: Mercury 2",
@@ -10565,6 +10617,23 @@ export const MODELS = {
10565
10617
  contextWindow: 128000,
10566
10618
  maxTokens: 50000,
10567
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
+ },
10568
10637
  "inclusionai/ling-3.0-flash": {
10569
10638
  id: "inclusionai/ling-3.0-flash",
10570
10639
  name: "Ling-3.0-flash",
@@ -10599,39 +10668,22 @@ export const MODELS = {
10599
10668
  contextWindow: 262144,
10600
10669
  maxTokens: 32768,
10601
10670
  },
10602
- "kwaipilot/kat-coder-air-v2.5": {
10603
- id: "kwaipilot/kat-coder-air-v2.5",
10604
- name: "Kwaipilot: KAT-Coder-Air V2.5",
10671
+ "kwaipilot/kat-coder-pro-v2": {
10672
+ id: "kwaipilot/kat-coder-pro-v2",
10673
+ name: "Kwaipilot: KAT-Coder-Pro V2",
10605
10674
  api: "openai-completions",
10606
10675
  provider: "openrouter",
10607
10676
  baseUrl: "https://openrouter.ai/api/v1",
10608
10677
  reasoning: false,
10609
10678
  input: ["text"],
10610
10679
  cost: {
10611
- input: 0.15,
10612
- output: 0.6,
10613
- cacheRead: 0.03,
10614
- cacheWrite: 0,
10615
- },
10616
- contextWindow: 256000,
10617
- maxTokens: 80000,
10618
- },
10619
- "kwaipilot/kat-coder-pro-v2": {
10620
- id: "kwaipilot/kat-coder-pro-v2",
10621
- name: "Kwaipilot: KAT-Coder-Pro V2",
10622
- api: "openai-completions",
10623
- provider: "openrouter",
10624
- baseUrl: "https://openrouter.ai/api/v1",
10625
- reasoning: false,
10626
- input: ["text"],
10627
- cost: {
10628
- input: 0.3,
10629
- output: 1.2,
10630
- cacheRead: 0.06,
10680
+ input: 0.3,
10681
+ output: 1.2,
10682
+ cacheRead: 0.06,
10631
10683
  cacheWrite: 0,
10632
10684
  },
10633
10685
  contextWindow: 262144,
10634
- maxTokens: 80000,
10686
+ maxTokens: 144000,
10635
10687
  },
10636
10688
  "kwaipilot/kat-coder-pro-v2.5": {
10637
10689
  id: "kwaipilot/kat-coder-pro-v2.5",
@@ -10648,7 +10700,7 @@ export const MODELS = {
10648
10700
  cacheWrite: 0,
10649
10701
  },
10650
10702
  contextWindow: 262144,
10651
- maxTokens: 80000,
10703
+ maxTokens: 235929,
10652
10704
  },
10653
10705
  "liquid/lfm-2.5-2.6b:free": {
10654
10706
  id: "liquid/lfm-2.5-2.6b:free",
@@ -10745,12 +10797,12 @@ export const MODELS = {
10745
10797
  input: ["text", "image"],
10746
10798
  cost: {
10747
10799
  input: 0.19999999999999998,
10748
- output: 0.7999999999999999,
10800
+ output: 0.696,
10749
10801
  cacheRead: 0,
10750
10802
  cacheWrite: 0,
10751
10803
  },
10752
10804
  contextWindow: 1048576,
10753
- maxTokens: 16384,
10805
+ maxTokens: 115200,
10754
10806
  },
10755
10807
  "meta-llama/llama-4-scout": {
10756
10808
  id: "meta-llama/llama-4-scout",
@@ -10761,13 +10813,13 @@ export const MODELS = {
10761
10813
  reasoning: false,
10762
10814
  input: ["text", "image"],
10763
10815
  cost: {
10764
- input: 0.11,
10765
- output: 0.33999999999999997,
10766
- cacheRead: 0.055,
10816
+ input: 0.09999999999999999,
10817
+ output: 0.3,
10818
+ cacheRead: 0,
10767
10819
  cacheWrite: 0,
10768
10820
  },
10769
10821
  contextWindow: 1310720,
10770
- maxTokens: 8192,
10822
+ maxTokens: 16384,
10771
10823
  },
10772
10824
  "meta/muse-glimmer-30b": {
10773
10825
  id: "meta/muse-glimmer-30b",
@@ -11024,23 +11076,6 @@ export const MODELS = {
11024
11076
  contextWindow: 256000,
11025
11077
  maxTokens: 204800,
11026
11078
  },
11027
- "mistralai/codestral-2508:batch": {
11028
- id: "mistralai/codestral-2508:batch",
11029
- name: "Mistral: Codestral 2508 (batch)",
11030
- api: "openai-completions",
11031
- provider: "openrouter",
11032
- baseUrl: "https://openrouter.ai/api/v1",
11033
- reasoning: false,
11034
- input: ["text"],
11035
- cost: {
11036
- input: 0.3,
11037
- output: 0.8999999999999999,
11038
- cacheRead: 0.03,
11039
- cacheWrite: 0,
11040
- },
11041
- contextWindow: 256000,
11042
- maxTokens: 204800,
11043
- },
11044
11079
  "mistralai/devstral-2512": {
11045
11080
  id: "mistralai/devstral-2512",
11046
11081
  name: "Mistral: Devstral 2 2512",
@@ -11050,9 +11085,9 @@ export const MODELS = {
11050
11085
  reasoning: false,
11051
11086
  input: ["text"],
11052
11087
  cost: {
11053
- input: 0.44,
11054
- output: 2.2,
11055
- cacheRead: 0.044,
11088
+ input: 0.39999999999999997,
11089
+ output: 2,
11090
+ cacheRead: 0.04,
11056
11091
  cacheWrite: 0,
11057
11092
  },
11058
11093
  contextWindow: 262144,
@@ -11109,23 +11144,6 @@ export const MODELS = {
11109
11144
  contextWindow: 262144,
11110
11145
  maxTokens: 209715,
11111
11146
  },
11112
- "mistralai/ministral-8b-2512:batch": {
11113
- id: "mistralai/ministral-8b-2512:batch",
11114
- name: "Mistral: Ministral 3 8B 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: 0.15,
11122
- output: 0.15,
11123
- cacheRead: 0.015,
11124
- cacheWrite: 0,
11125
- },
11126
- contextWindow: 262144,
11127
- maxTokens: 209715,
11128
- },
11129
11147
  "mistralai/mistral-large": {
11130
11148
  id: "mistralai/mistral-large",
11131
11149
  name: "Mistral Large",
@@ -11177,23 +11195,6 @@ export const MODELS = {
11177
11195
  contextWindow: 262144,
11178
11196
  maxTokens: 209715,
11179
11197
  },
11180
- "mistralai/mistral-large-2512:batch": {
11181
- id: "mistralai/mistral-large-2512:batch",
11182
- name: "Mistral: Mistral Large 3 2512 (batch)",
11183
- api: "openai-completions",
11184
- provider: "openrouter",
11185
- baseUrl: "https://openrouter.ai/api/v1",
11186
- reasoning: false,
11187
- input: ["text", "image"],
11188
- cost: {
11189
- input: 0.5,
11190
- output: 1.5,
11191
- cacheRead: 0.049999999999999996,
11192
- cacheWrite: 0,
11193
- },
11194
- contextWindow: 262144,
11195
- maxTokens: 209715,
11196
- },
11197
11198
  "mistralai/mistral-medium-3": {
11198
11199
  id: "mistralai/mistral-medium-3",
11199
11200
  name: "Mistral: Mistral Medium 3",
@@ -11262,23 +11263,6 @@ export const MODELS = {
11262
11263
  contextWindow: 131072,
11263
11264
  maxTokens: 104857,
11264
11265
  },
11265
- "mistralai/mistral-medium-3.1:batch": {
11266
- id: "mistralai/mistral-medium-3.1:batch",
11267
- name: "Mistral: Mistral Medium 3.1 (batch)",
11268
- api: "openai-completions",
11269
- provider: "openrouter",
11270
- baseUrl: "https://openrouter.ai/api/v1",
11271
- reasoning: false,
11272
- input: ["text", "image"],
11273
- cost: {
11274
- input: 0.39999999999999997,
11275
- output: 2,
11276
- cacheRead: 0.04,
11277
- cacheWrite: 0,
11278
- },
11279
- contextWindow: 131072,
11280
- maxTokens: 104857,
11281
- },
11282
11266
  "mistralai/mistral-nemo": {
11283
11267
  id: "mistralai/mistral-nemo",
11284
11268
  name: "Mistral: Mistral Nemo",
@@ -11330,23 +11314,6 @@ export const MODELS = {
11330
11314
  contextWindow: 262144,
11331
11315
  maxTokens: 209715,
11332
11316
  },
11333
- "mistralai/mistral-small-2603:batch": {
11334
- id: "mistralai/mistral-small-2603:batch",
11335
- name: "Mistral: Mistral Small 4 (batch)",
11336
- api: "openai-completions",
11337
- provider: "openrouter",
11338
- baseUrl: "https://openrouter.ai/api/v1",
11339
- reasoning: true,
11340
- input: ["text", "image"],
11341
- cost: {
11342
- input: 0.15,
11343
- output: 0.6,
11344
- cacheRead: 0.015,
11345
- cacheWrite: 0,
11346
- },
11347
- contextWindow: 262144,
11348
- maxTokens: 209715,
11349
- },
11350
11317
  "mistralai/mistral-small-3.2-24b-instruct": {
11351
11318
  id: "mistralai/mistral-small-3.2-24b-instruct",
11352
11319
  name: "Mistral: Mistral Small 3.2 24B",
@@ -11509,9 +11476,9 @@ export const MODELS = {
11509
11476
  reasoning: true,
11510
11477
  input: ["text", "image"],
11511
11478
  cost: {
11512
- input: 2.5500000000000003,
11513
- output: 12.75,
11514
- cacheRead: 0.25599998999999996,
11479
+ input: 3,
11480
+ output: 15,
11481
+ cacheRead: 0.3,
11515
11482
  cacheWrite: 0,
11516
11483
  },
11517
11484
  contextWindow: 1048576,
@@ -11772,6 +11739,23 @@ export const MODELS = {
11772
11739
  contextWindow: 16385,
11773
11740
  maxTokens: 4096,
11774
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
+ },
11775
11759
  "openai/gpt-4": {
11776
11760
  id: "openai/gpt-4",
11777
11761
  name: "OpenAI: GPT-4",
@@ -11823,6 +11807,23 @@ export const MODELS = {
11823
11807
  contextWindow: 128000,
11824
11808
  maxTokens: 4096,
11825
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
+ },
11826
11827
  "openai/gpt-4.1": {
11827
11828
  id: "openai/gpt-4.1",
11828
11829
  name: "OpenAI: GPT-4.1",
@@ -11857,6 +11858,23 @@ export const MODELS = {
11857
11858
  contextWindow: 1047576,
11858
11859
  maxTokens: 32768,
11859
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
+ },
11860
11878
  "openai/gpt-4.1-nano": {
11861
11879
  id: "openai/gpt-4.1-nano",
11862
11880
  name: "OpenAI: GPT-4.1 Nano",
@@ -11868,11 +11886,45 @@ export const MODELS = {
11868
11886
  cost: {
11869
11887
  input: 0.09999999999999999,
11870
11888
  output: 0.39999999999999997,
11871
- 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,
11872
11907
  cacheWrite: 0,
11873
11908
  },
11874
11909
  contextWindow: 1047576,
11875
- maxTokens: 942818,
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,
11924
+ cacheWrite: 0,
11925
+ },
11926
+ contextWindow: 1047576,
11927
+ maxTokens: 32768,
11876
11928
  },
11877
11929
  "openai/gpt-4o": {
11878
11930
  id: "openai/gpt-4o",
@@ -11976,6 +12028,40 @@ export const MODELS = {
11976
12028
  contextWindow: 128000,
11977
12029
  maxTokens: 16384,
11978
12030
  },
12031
+ "openai/gpt-4o-mini:batch": {
12032
+ id: "openai/gpt-4o-mini:batch",
12033
+ name: "OpenAI: GPT-4o-mini (batch)",
12034
+ api: "openai-completions",
12035
+ provider: "openrouter",
12036
+ baseUrl: "https://openrouter.ai/api/v1",
12037
+ reasoning: false,
12038
+ input: ["text", "image"],
12039
+ cost: {
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
+ },
11979
12065
  "openai/gpt-5": {
11980
12066
  id: "openai/gpt-5",
11981
12067
  name: "OpenAI: GPT-5",
@@ -12010,6 +12096,23 @@ export const MODELS = {
12010
12096
  contextWindow: 400000,
12011
12097
  maxTokens: 128000,
12012
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
+ },
12013
12116
  "openai/gpt-5-nano": {
12014
12117
  id: "openai/gpt-5-nano",
12015
12118
  name: "OpenAI: GPT-5 Nano",
@@ -12027,6 +12130,23 @@ export const MODELS = {
12027
12130
  contextWindow: 400000,
12028
12131
  maxTokens: 128000,
12029
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
+ },
12030
12150
  "openai/gpt-5-pro": {
12031
12151
  id: "openai/gpt-5-pro",
12032
12152
  name: "OpenAI: GPT-5 Pro",
@@ -12044,6 +12164,23 @@ export const MODELS = {
12044
12164
  contextWindow: 400000,
12045
12165
  maxTokens: 128000,
12046
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
+ },
12047
12184
  "openai/gpt-5.1": {
12048
12185
  id: "openai/gpt-5.1",
12049
12186
  name: "OpenAI: GPT-5.1",
@@ -12112,6 +12249,23 @@ export const MODELS = {
12112
12249
  contextWindow: 400000,
12113
12250
  maxTokens: 128000,
12114
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
+ },
12115
12269
  "openai/gpt-5.2": {
12116
12270
  id: "openai/gpt-5.2",
12117
12271
  name: "OpenAI: GPT-5.2",
@@ -12180,6 +12334,40 @@ export const MODELS = {
12180
12334
  contextWindow: 400000,
12181
12335
  maxTokens: 128000,
12182
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
+ },
12183
12371
  "openai/gpt-5.3-codex": {
12184
12372
  id: "openai/gpt-5.3-codex",
12185
12373
  name: "OpenAI: GPT-5.3-Codex",
@@ -12231,6 +12419,23 @@ export const MODELS = {
12231
12419
  contextWindow: 400000,
12232
12420
  maxTokens: 128000,
12233
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
+ },
12234
12439
  "openai/gpt-5.4-nano": {
12235
12440
  id: "openai/gpt-5.4-nano",
12236
12441
  name: "OpenAI: GPT-5.4 Nano",
@@ -12248,6 +12453,23 @@ export const MODELS = {
12248
12453
  contextWindow: 400000,
12249
12454
  maxTokens: 128000,
12250
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
+ },
12251
12473
  "openai/gpt-5.4-pro": {
12252
12474
  id: "openai/gpt-5.4-pro",
12253
12475
  name: "OpenAI: GPT-5.4 Pro",
@@ -12265,35 +12487,103 @@ export const MODELS = {
12265
12487
  contextWindow: 1050000,
12266
12488
  maxTokens: 128000,
12267
12489
  },
12268
- "openai/gpt-5.5": {
12269
- id: "openai/gpt-5.5",
12270
- name: "OpenAI: GPT-5.5",
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
+ },
12524
+ "openai/gpt-5.5": {
12525
+ id: "openai/gpt-5.5",
12526
+ name: "OpenAI: GPT-5.5",
12527
+ api: "openai-completions",
12528
+ provider: "openrouter",
12529
+ baseUrl: "https://openrouter.ai/api/v1",
12530
+ reasoning: true,
12531
+ input: ["text", "image"],
12532
+ cost: {
12533
+ input: 5,
12534
+ output: 30,
12535
+ cacheRead: 0.5,
12536
+ cacheWrite: 0,
12537
+ },
12538
+ contextWindow: 1050000,
12539
+ maxTokens: 128000,
12540
+ },
12541
+ "openai/gpt-5.5-pro": {
12542
+ id: "openai/gpt-5.5-pro",
12543
+ name: "OpenAI: GPT-5.5 Pro",
12544
+ api: "openai-completions",
12545
+ provider: "openrouter",
12546
+ baseUrl: "https://openrouter.ai/api/v1",
12547
+ reasoning: true,
12548
+ input: ["text", "image"],
12549
+ cost: {
12550
+ input: 30,
12551
+ output: 180,
12552
+ cacheRead: 0,
12553
+ cacheWrite: 0,
12554
+ },
12555
+ contextWindow: 1050000,
12556
+ maxTokens: 128000,
12557
+ },
12558
+ "openai/gpt-5.5-pro:batch": {
12559
+ id: "openai/gpt-5.5-pro:batch",
12560
+ name: "OpenAI: GPT-5.5 Pro (batch)",
12271
12561
  api: "openai-completions",
12272
12562
  provider: "openrouter",
12273
12563
  baseUrl: "https://openrouter.ai/api/v1",
12274
12564
  reasoning: true,
12275
12565
  input: ["text", "image"],
12276
12566
  cost: {
12277
- input: 5,
12278
- output: 30,
12279
- cacheRead: 0.5,
12567
+ input: 15,
12568
+ output: 90,
12569
+ cacheRead: 0,
12280
12570
  cacheWrite: 0,
12281
12571
  },
12282
12572
  contextWindow: 1050000,
12283
12573
  maxTokens: 128000,
12284
12574
  },
12285
- "openai/gpt-5.5-pro": {
12286
- id: "openai/gpt-5.5-pro",
12287
- name: "OpenAI: GPT-5.5 Pro",
12575
+ "openai/gpt-5.5:batch": {
12576
+ id: "openai/gpt-5.5:batch",
12577
+ name: "OpenAI: GPT-5.5 (batch)",
12288
12578
  api: "openai-completions",
12289
12579
  provider: "openrouter",
12290
12580
  baseUrl: "https://openrouter.ai/api/v1",
12291
12581
  reasoning: true,
12292
12582
  input: ["text", "image"],
12293
12583
  cost: {
12294
- input: 30,
12295
- output: 180,
12296
- cacheRead: 0,
12584
+ input: 2.5,
12585
+ output: 15,
12586
+ cacheRead: 0.25,
12297
12587
  cacheWrite: 0,
12298
12588
  },
12299
12589
  contextWindow: 1050000,
@@ -12333,6 +12623,40 @@ export const MODELS = {
12333
12623
  contextWindow: 1050000,
12334
12624
  maxTokens: 128000,
12335
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
+ },
12336
12660
  "openai/gpt-5.6-sol": {
12337
12661
  id: "openai/gpt-5.6-sol",
12338
12662
  name: "OpenAI: GPT-5.6 Sol",
@@ -12367,6 +12691,40 @@ export const MODELS = {
12367
12691
  contextWindow: 1050000,
12368
12692
  maxTokens: 128000,
12369
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,
12724
+ },
12725
+ contextWindow: 1050000,
12726
+ maxTokens: 128000,
12727
+ },
12370
12728
  "openai/gpt-5.6-terra": {
12371
12729
  id: "openai/gpt-5.6-terra",
12372
12730
  name: "OpenAI: GPT-5.6 Terra",
@@ -12401,6 +12759,57 @@ export const MODELS = {
12401
12759
  contextWindow: 1050000,
12402
12760
  maxTokens: 128000,
12403
12761
  },
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)",
12765
+ api: "openai-completions",
12766
+ provider: "openrouter",
12767
+ baseUrl: "https://openrouter.ai/api/v1",
12768
+ reasoning: true,
12769
+ input: ["text", "image"],
12770
+ cost: {
12771
+ input: 1,
12772
+ output: 6,
12773
+ cacheRead: 0.09999999999999999,
12774
+ cacheWrite: 0,
12775
+ },
12776
+ contextWindow: 1050000,
12777
+ maxTokens: 128000,
12778
+ },
12779
+ "openai/gpt-5.6-terra:batch": {
12780
+ id: "openai/gpt-5.6-terra:batch",
12781
+ name: "OpenAI: GPT-5.6 Terra (batch)",
12782
+ api: "openai-completions",
12783
+ provider: "openrouter",
12784
+ baseUrl: "https://openrouter.ai/api/v1",
12785
+ reasoning: true,
12786
+ input: ["text", "image"],
12787
+ cost: {
12788
+ input: 1,
12789
+ output: 6,
12790
+ cacheRead: 0.09999999999999999,
12791
+ cacheWrite: 0,
12792
+ },
12793
+ contextWindow: 1050000,
12794
+ maxTokens: 128000,
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
+ },
12404
12813
  "openai/gpt-audio": {
12405
12814
  id: "openai/gpt-audio",
12406
12815
  name: "OpenAI: GPT Audio",
@@ -12588,6 +12997,23 @@ export const MODELS = {
12588
12997
  contextWindow: 200000,
12589
12998
  maxTokens: 100000,
12590
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
+ },
12591
13017
  "openai/o3-pro": {
12592
13018
  id: "openai/o3-pro",
12593
13019
  name: "OpenAI: o3 Pro",
@@ -12605,6 +13031,23 @@ export const MODELS = {
12605
13031
  contextWindow: 200000,
12606
13032
  maxTokens: 100000,
12607
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
+ },
12608
13051
  "openai/o4-mini": {
12609
13052
  id: "openai/o4-mini",
12610
13053
  name: "OpenAI: o4 Mini",
@@ -12639,6 +13082,23 @@ export const MODELS = {
12639
13082
  contextWindow: 200000,
12640
13083
  maxTokens: 100000,
12641
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
+ },
12642
13102
  "openrouter/auto": {
12643
13103
  id: "openrouter/auto",
12644
13104
  name: "Auto Router",
@@ -13551,11 +14011,11 @@ export const MODELS = {
13551
14011
  cost: {
13552
14012
  input: 2,
13553
14013
  output: 6,
13554
- cacheRead: 0.19999999999999998,
14014
+ cacheRead: 0.25,
13555
14015
  cacheWrite: 0,
13556
14016
  },
13557
14017
  contextWindow: 1048576,
13558
- maxTokens: 131072,
14018
+ maxTokens: 262144,
13559
14019
  },
13560
14020
  "qwen/qwen3.8-2.4t-a95b:batch": {
13561
14021
  id: "qwen/qwen3.8-2.4t-a95b:batch",
@@ -13566,9 +14026,9 @@ export const MODELS = {
13566
14026
  reasoning: true,
13567
14027
  input: ["text"],
13568
14028
  cost: {
13569
- input: 2,
13570
- output: 6,
13571
- cacheRead: 0.25,
14029
+ input: 2.5,
14030
+ output: 6.25,
14031
+ cacheRead: 0.5,
13572
14032
  cacheWrite: 0,
13573
14033
  },
13574
14034
  contextWindow: 1010000,
@@ -13821,13 +14281,13 @@ export const MODELS = {
13821
14281
  reasoning: true,
13822
14282
  input: ["text", "image"],
13823
14283
  cost: {
13824
- input: 0.95,
14284
+ input: 1,
13825
14285
  output: 4.05,
13826
- cacheRead: 0.16,
14286
+ cacheRead: 0.16999999999999998,
13827
14287
  cacheWrite: 0,
13828
14288
  },
13829
14289
  contextWindow: 1048576,
13830
- maxTokens: 262144,
14290
+ maxTokens: 471859,
13831
14291
  },
13832
14292
  "thinkingmachines/inkling-small": {
13833
14293
  id: "thinkingmachines/inkling-small",
@@ -14229,13 +14689,13 @@ export const MODELS = {
14229
14689
  reasoning: true,
14230
14690
  input: ["text"],
14231
14691
  cost: {
14232
- input: 1.26,
14233
- output: 3.9600000000000004,
14234
- cacheRead: 0.234,
14692
+ input: 0.966,
14693
+ output: 3.036,
14694
+ cacheRead: 0.1794,
14235
14695
  cacheWrite: 0,
14236
14696
  },
14237
14697
  contextWindow: 204800,
14238
- maxTokens: 182476,
14698
+ maxTokens: 128000,
14239
14699
  },
14240
14700
  "z-ai/glm-5.2": {
14241
14701
  id: "z-ai/glm-5.2",
@@ -14350,7 +14810,7 @@ export const MODELS = {
14350
14810
  cost: {
14351
14811
  input: 10,
14352
14812
  output: 50,
14353
- cacheRead: 1,
14813
+ cacheRead: 0.25,
14354
14814
  cacheWrite: 12.5,
14355
14815
  },
14356
14816
  contextWindow: 1000000,
@@ -14416,9 +14876,9 @@ export const MODELS = {
14416
14876
  reasoning: true,
14417
14877
  input: ["text"],
14418
14878
  cost: {
14419
- input: 0.03,
14420
- output: 0.09999999999999999,
14421
- cacheRead: 0.007,
14879
+ input: 0.049980000000000004,
14880
+ output: 0.09996000000000001,
14881
+ cacheRead: 0.009996000000000001,
14422
14882
  cacheWrite: 0,
14423
14883
  },
14424
14884
  contextWindow: 1310720,
@@ -14535,13 +14995,13 @@ export const MODELS = {
14535
14995
  reasoning: true,
14536
14996
  input: ["text"],
14537
14997
  cost: {
14538
- input: 1.25,
14539
- output: 4.4,
14540
- cacheRead: 0.26,
14998
+ input: 1.17,
14999
+ output: 3.9600000000000004,
15000
+ cacheRead: 0.234,
14541
15001
  cacheWrite: 0,
14542
15002
  },
14543
15003
  contextWindow: 1310720,
14544
- maxTokens: 131072,
15004
+ maxTokens: 943718,
14545
15005
  },
14546
15006
  },
14547
15007
  "vercel-ai-gateway": {
@@ -14996,10 +15456,10 @@ export const MODELS = {
14996
15456
  reasoning: true,
14997
15457
  input: ["text", "image"],
14998
15458
  cost: {
14999
- input: 0.55,
15000
- output: 3.3000000000000003,
15001
- cacheRead: 0.11,
15002
- cacheWrite: 0,
15459
+ input: 0.5,
15460
+ output: 3,
15461
+ cacheRead: 0.09999999999999999,
15462
+ cacheWrite: 0.625,
15003
15463
  },
15004
15464
  contextWindow: 1000000,
15005
15465
  maxTokens: 131072,
@@ -15021,6 +15481,23 @@ export const MODELS = {
15021
15481
  contextWindow: 991000,
15022
15482
  maxTokens: 128000,
15023
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
+ },
15024
15501
  "alibaba/qwen3.8-max": {
15025
15502
  id: "alibaba/qwen3.8-max",
15026
15503
  name: "Qwen 3.8 Max",
@@ -15140,6 +15617,23 @@ export const MODELS = {
15140
15617
  contextWindow: 1000000,
15141
15618
  maxTokens: 128000,
15142
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
+ },
15143
15637
  "anthropic/claude-haiku-4.5": {
15144
15638
  id: "anthropic/claude-haiku-4.5",
15145
15639
  name: "Claude Haiku 4.5",
@@ -15446,23 +15940,6 @@ export const MODELS = {
15446
15940
  contextWindow: 128000,
15447
15941
  maxTokens: 8192,
15448
15942
  },
15449
- "deepseek/deepseek-v3": {
15450
- id: "deepseek/deepseek-v3",
15451
- name: "DeepSeek V3 0324",
15452
- api: "anthropic-messages",
15453
- provider: "vercel-ai-gateway",
15454
- baseUrl: "https://ai-gateway.vercel.sh",
15455
- reasoning: false,
15456
- input: ["text"],
15457
- cost: {
15458
- input: 0.27,
15459
- output: 1.12,
15460
- cacheRead: 0.135,
15461
- cacheWrite: 0,
15462
- },
15463
- contextWindow: 163840,
15464
- maxTokens: 163840,
15465
- },
15466
15943
  "deepseek/deepseek-v3.1": {
15467
15944
  id: "deepseek/deepseek-v3.1",
15468
15945
  name: "DeepSeek V3.1",
@@ -15579,8 +16056,8 @@ export const MODELS = {
15579
16056
  cacheRead: 0.007,
15580
16057
  cacheWrite: 0,
15581
16058
  },
15582
- contextWindow: 1000000,
15583
- maxTokens: 384000,
16059
+ contextWindow: 1048576,
16060
+ maxTokens: 1048576,
15584
16061
  },
15585
16062
  "deepseek/deepseek-v4-pro": {
15586
16063
  id: "deepseek/deepseek-v4-pro",
@@ -18115,6 +18592,23 @@ export const MODELS = {
18115
18592
  contextWindow: 1050000,
18116
18593
  maxTokens: 131000,
18117
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
+ },
18118
18612
  "zai/glm-4.5": {
18119
18613
  id: "zai/glm-4.5",
18120
18614
  name: "GLM 4.5",