@elyracode/ai 0.9.27 → 0.9.28

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.
@@ -1422,7 +1422,7 @@ export const MODELS = {
1422
1422
  cacheRead: 0.022,
1423
1423
  cacheWrite: 0.275,
1424
1424
  },
1425
- contextWindow: 272000,
1425
+ contextWindow: 1050000,
1426
1426
  maxTokens: 128000,
1427
1427
  },
1428
1428
  "openai.gpt-5.6-sol": {
@@ -1437,9 +1437,9 @@ export const MODELS = {
1437
1437
  input: 5.5,
1438
1438
  output: 33,
1439
1439
  cacheRead: 0.55,
1440
- cacheWrite: 6.88,
1440
+ cacheWrite: 6.875,
1441
1441
  },
1442
- contextWindow: 272000,
1442
+ contextWindow: 1050000,
1443
1443
  maxTokens: 128000,
1444
1444
  },
1445
1445
  "openai.gpt-5.6-terra": {
@@ -1456,7 +1456,7 @@ export const MODELS = {
1456
1456
  cacheRead: 0.22,
1457
1457
  cacheWrite: 2.75,
1458
1458
  },
1459
- contextWindow: 272000,
1459
+ contextWindow: 1050000,
1460
1460
  maxTokens: 128000,
1461
1461
  },
1462
1462
  "openai.gpt-oss-120b": {
@@ -3918,7 +3918,7 @@ export const MODELS = {
3918
3918
  cacheWrite: 0,
3919
3919
  },
3920
3920
  contextWindow: 262144,
3921
- maxTokens: 262144,
3921
+ maxTokens: 256000,
3922
3922
  },
3923
3923
  },
3924
3924
  "deepseek": {
@@ -4858,40 +4858,6 @@ export const MODELS = {
4858
4858
  contextWindow: 131072,
4859
4859
  maxTokens: 65536,
4860
4860
  },
4861
- "gemini-2.0-flash": {
4862
- id: "gemini-2.0-flash",
4863
- name: "Gemini 2.0 Flash",
4864
- api: "google-generative-ai",
4865
- provider: "google",
4866
- baseUrl: "https://generativelanguage.googleapis.com/v1beta",
4867
- reasoning: false,
4868
- input: ["text", "image"],
4869
- cost: {
4870
- input: 0.1,
4871
- output: 0.4,
4872
- cacheRead: 0.025,
4873
- cacheWrite: 0,
4874
- },
4875
- contextWindow: 1048576,
4876
- maxTokens: 8192,
4877
- },
4878
- "gemini-2.0-flash-lite": {
4879
- id: "gemini-2.0-flash-lite",
4880
- name: "Gemini 2.0 Flash-Lite",
4881
- api: "google-generative-ai",
4882
- provider: "google",
4883
- baseUrl: "https://generativelanguage.googleapis.com/v1beta",
4884
- reasoning: false,
4885
- input: ["text", "image"],
4886
- cost: {
4887
- input: 0.075,
4888
- output: 0.3,
4889
- cacheRead: 0,
4890
- cacheWrite: 0,
4891
- },
4892
- contextWindow: 1048576,
4893
- maxTokens: 8192,
4894
- },
4895
4861
  "gemini-2.5-computer-use-preview-10-2025": {
4896
4862
  id: "gemini-2.5-computer-use-preview-10-2025",
4897
4863
  name: "Gemini 2.5 Computer Use Preview 10-2025",
@@ -4978,24 +4944,6 @@ export const MODELS = {
4978
4944
  contextWindow: 1048576,
4979
4945
  maxTokens: 65536,
4980
4946
  },
4981
- "gemini-3-pro-preview": {
4982
- id: "gemini-3-pro-preview",
4983
- name: "Gemini 3 Pro Preview",
4984
- api: "google-generative-ai",
4985
- provider: "google",
4986
- baseUrl: "https://generativelanguage.googleapis.com/v1beta",
4987
- reasoning: true,
4988
- thinkingLevelMap: { "off": null, "minimal": null, "low": "LOW", "medium": null, "high": "HIGH" },
4989
- input: ["text", "image"],
4990
- cost: {
4991
- input: 2,
4992
- output: 12,
4993
- cacheRead: 0.2,
4994
- cacheWrite: 0,
4995
- },
4996
- contextWindow: 1048576,
4997
- maxTokens: 65536,
4998
- },
4999
4947
  "gemini-3.1-flash-lite": {
5000
4948
  id: "gemini-3.1-flash-lite",
5001
4949
  name: "Gemini 3.1 Flash Lite",
@@ -9296,6 +9244,23 @@ export const MODELS = {
9296
9244
  contextWindow: 256000,
9297
9245
  maxTokens: 256000,
9298
9246
  },
9247
+ "hy3-free": {
9248
+ id: "hy3-free",
9249
+ name: "Hy3 Free",
9250
+ api: "openai-completions",
9251
+ provider: "opencode",
9252
+ baseUrl: "https://opencode.ai/zen/v1",
9253
+ reasoning: true,
9254
+ input: ["text"],
9255
+ cost: {
9256
+ input: 0,
9257
+ output: 0,
9258
+ cacheRead: 0,
9259
+ cacheWrite: 0,
9260
+ },
9261
+ contextWindow: 190000,
9262
+ maxTokens: 64000,
9263
+ },
9299
9264
  "kimi-k2.5": {
9300
9265
  id: "kimi-k2.5",
9301
9266
  name: "Kimi K2.5",
@@ -9398,23 +9363,6 @@ export const MODELS = {
9398
9363
  contextWindow: 262144,
9399
9364
  maxTokens: 32768,
9400
9365
  },
9401
- "longcat-2.0-free": {
9402
- id: "longcat-2.0-free",
9403
- name: "LongCat-2.0 Free",
9404
- api: "openai-completions",
9405
- provider: "opencode",
9406
- baseUrl: "https://opencode.ai/zen/v1",
9407
- reasoning: true,
9408
- input: ["text"],
9409
- cost: {
9410
- input: 0,
9411
- output: 0,
9412
- cacheRead: 0,
9413
- cacheWrite: 0,
9414
- },
9415
- contextWindow: 1000000,
9416
- maxTokens: 131072,
9417
- },
9418
9366
  "mimo-v2.5-free": {
9419
9367
  id: "mimo-v2.5-free",
9420
9368
  name: "MiMo V2.5 Free",
@@ -9500,9 +9448,9 @@ export const MODELS = {
9500
9448
  contextWindow: 1000000,
9501
9449
  maxTokens: 128000,
9502
9450
  },
9503
- "north-mini-code-free": {
9504
- id: "north-mini-code-free",
9505
- name: "North Mini Code Free",
9451
+ "nemotron-3.5-lightning-free": {
9452
+ id: "nemotron-3.5-lightning-free",
9453
+ name: "Nemotron 3.5 Lightning Free",
9506
9454
  api: "openai-completions",
9507
9455
  provider: "opencode",
9508
9456
  baseUrl: "https://opencode.ai/zen/v1",
@@ -9514,8 +9462,8 @@ export const MODELS = {
9514
9462
  cacheRead: 0,
9515
9463
  cacheWrite: 0,
9516
9464
  },
9517
- contextWindow: 256000,
9518
- maxTokens: 64000,
9465
+ contextWindow: 262144,
9466
+ maxTokens: 262144,
9519
9467
  },
9520
9468
  "qwen3.5-plus": {
9521
9469
  id: "qwen3.5-plus",
@@ -10591,6 +10539,23 @@ export const MODELS = {
10591
10539
  contextWindow: 262144,
10592
10540
  maxTokens: 32768,
10593
10541
  },
10542
+ "bytedance-seed/seed-2.0-code": {
10543
+ id: "bytedance-seed/seed-2.0-code",
10544
+ name: "ByteDance Seed: Seed-2.0-Code",
10545
+ api: "openai-completions",
10546
+ provider: "openrouter",
10547
+ baseUrl: "https://openrouter.ai/api/v1",
10548
+ reasoning: true,
10549
+ input: ["text", "image"],
10550
+ cost: {
10551
+ input: 0.5,
10552
+ output: 3,
10553
+ cacheRead: 0,
10554
+ cacheWrite: 0,
10555
+ },
10556
+ contextWindow: 262144,
10557
+ maxTokens: 131072,
10558
+ },
10594
10559
  "bytedance-seed/seed-2.0-lite": {
10595
10560
  id: "bytedance-seed/seed-2.0-lite",
10596
10561
  name: "ByteDance Seed: Seed-2.0-Lite",
@@ -10771,8 +10736,8 @@ export const MODELS = {
10771
10736
  input: ["text"],
10772
10737
  cost: {
10773
10738
  input: 0.27,
10774
- output: 1,
10775
- cacheRead: 0.135,
10739
+ output: 0.95,
10740
+ cacheRead: 0.13,
10776
10741
  cacheWrite: 0,
10777
10742
  },
10778
10743
  contextWindow: 163840,
@@ -10787,13 +10752,13 @@ export const MODELS = {
10787
10752
  reasoning: true,
10788
10753
  input: ["text"],
10789
10754
  cost: {
10790
- input: 0.26,
10791
- output: 0.38,
10792
- cacheRead: 0.13,
10755
+ input: 0.26899999999999996,
10756
+ output: 0.39999999999999997,
10757
+ cacheRead: 0.13449999999999998,
10793
10758
  cacheWrite: 0,
10794
10759
  },
10795
10760
  contextWindow: 163840,
10796
- maxTokens: 163840,
10761
+ maxTokens: 65536,
10797
10762
  },
10798
10763
  "deepseek/deepseek-v3.2-exp": {
10799
10764
  id: "deepseek/deepseek-v3.2-exp",
@@ -10842,9 +10807,9 @@ export const MODELS = {
10842
10807
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
10843
10808
  input: ["text"],
10844
10809
  cost: {
10845
- input: 0.09,
10810
+ input: 0.08,
10846
10811
  output: 0.18,
10847
- cacheRead: 0.018,
10812
+ cacheRead: 0.016,
10848
10813
  cacheWrite: 0,
10849
10814
  },
10850
10815
  contextWindow: 1048576,
@@ -10861,13 +10826,13 @@ export const MODELS = {
10861
10826
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
10862
10827
  input: ["text"],
10863
10828
  cost: {
10864
- input: 0.435,
10865
- output: 0.87,
10866
- cacheRead: 0.003625,
10829
+ input: 1.1680000000000001,
10830
+ output: 2.3360000000000003,
10831
+ cacheRead: 0.09855000000000001,
10867
10832
  cacheWrite: 0,
10868
10833
  },
10869
10834
  contextWindow: 1048576,
10870
- maxTokens: 384000,
10835
+ maxTokens: 393216,
10871
10836
  },
10872
10837
  "google/gemini-2.5-flash": {
10873
10838
  id: "google/gemini-2.5-flash",
@@ -11303,13 +11268,13 @@ export const MODELS = {
11303
11268
  reasoning: true,
11304
11269
  input: ["text", "image"],
11305
11270
  cost: {
11306
- input: 0.07,
11307
- output: 0.33999999999999997,
11308
- cacheRead: 0,
11271
+ input: 0.12,
11272
+ output: 0.39999999999999997,
11273
+ cacheRead: 0.049999999999999996,
11309
11274
  cacheWrite: 0,
11310
11275
  },
11311
11276
  contextWindow: 262144,
11312
- maxTokens: 16384,
11277
+ maxTokens: 262144,
11313
11278
  },
11314
11279
  "google/gemma-4-26b-a4b-it:free": {
11315
11280
  id: "google/gemma-4-26b-a4b-it:free",
@@ -11532,6 +11497,23 @@ export const MODELS = {
11532
11497
  contextWindow: 256000,
11533
11498
  maxTokens: 80000,
11534
11499
  },
11500
+ "liquid/lfm-2.5-2.6b:free": {
11501
+ id: "liquid/lfm-2.5-2.6b:free",
11502
+ name: "LiquidAI: LFM2.5-2.6B (free)",
11503
+ api: "openai-completions",
11504
+ provider: "openrouter",
11505
+ baseUrl: "https://openrouter.ai/api/v1",
11506
+ reasoning: true,
11507
+ input: ["text"],
11508
+ cost: {
11509
+ input: 0,
11510
+ output: 0,
11511
+ cacheRead: 0,
11512
+ cacheWrite: 0,
11513
+ },
11514
+ contextWindow: 128000,
11515
+ maxTokens: 32768,
11516
+ },
11535
11517
  "meituan/longcat-2.0": {
11536
11518
  id: "meituan/longcat-2.0",
11537
11519
  name: "Meituan: LongCat 2.0",
@@ -11610,12 +11592,12 @@ export const MODELS = {
11610
11592
  input: ["text", "image"],
11611
11593
  cost: {
11612
11594
  input: 0.19999999999999998,
11613
- output: 0.7999999999999999,
11595
+ output: 0.696,
11614
11596
  cacheRead: 0,
11615
11597
  cacheWrite: 0,
11616
11598
  },
11617
11599
  contextWindow: 1048576,
11618
- maxTokens: 16384,
11600
+ maxTokens: 4096,
11619
11601
  },
11620
11602
  "meta-llama/llama-4-scout": {
11621
11603
  id: "meta-llama/llama-4-scout",
@@ -11634,6 +11616,23 @@ export const MODELS = {
11634
11616
  contextWindow: 1310720,
11635
11617
  maxTokens: 16384,
11636
11618
  },
11619
+ "meta/muse-glimmer-30b": {
11620
+ id: "meta/muse-glimmer-30b",
11621
+ name: "Meta: Muse Glimmer 30B",
11622
+ api: "openai-completions",
11623
+ provider: "openrouter",
11624
+ baseUrl: "https://openrouter.ai/api/v1",
11625
+ reasoning: true,
11626
+ input: ["text", "image"],
11627
+ cost: {
11628
+ input: 0.35,
11629
+ output: 1.5,
11630
+ cacheRead: 0.04,
11631
+ cacheWrite: 0,
11632
+ },
11633
+ contextWindow: 131072,
11634
+ maxTokens: 4096,
11635
+ },
11637
11636
  "meta/muse-spark-1.1": {
11638
11637
  id: "meta/muse-spark-1.1",
11639
11638
  name: "Meta: Muse Spark 1.1",
@@ -11745,9 +11744,9 @@ export const MODELS = {
11745
11744
  reasoning: true,
11746
11745
  input: ["text"],
11747
11746
  cost: {
11748
- input: 0.27,
11749
- output: 1.08,
11750
- cacheRead: 0.054,
11747
+ input: 0.3,
11748
+ output: 1.2,
11749
+ cacheRead: 0.06,
11751
11750
  cacheWrite: 0,
11752
11751
  },
11753
11752
  contextWindow: 204800,
@@ -12136,9 +12135,9 @@ export const MODELS = {
12136
12135
  reasoning: true,
12137
12136
  input: ["text", "image"],
12138
12137
  cost: {
12139
- input: 0.5795,
12140
- output: 2.44,
12141
- cacheRead: 0.0976,
12138
+ input: 0.95,
12139
+ output: 4,
12140
+ cacheRead: 0.16,
12142
12141
  cacheWrite: 0,
12143
12142
  },
12144
12143
  contextWindow: 262144,
@@ -12240,11 +12239,11 @@ export const MODELS = {
12240
12239
  cost: {
12241
12240
  input: 0.049999999999999996,
12242
12241
  output: 0.19999999999999998,
12243
- cacheRead: 0.03,
12242
+ cacheRead: 0.024999999999999998,
12244
12243
  cacheWrite: 0,
12245
12244
  },
12246
12245
  contextWindow: 262144,
12247
- maxTokens: 262144,
12246
+ maxTokens: 228000,
12248
12247
  },
12249
12248
  "nvidia/nemotron-3-nano-30b-a3b:free": {
12250
12249
  id: "nvidia/nemotron-3-nano-30b-a3b:free",
@@ -12365,6 +12364,23 @@ export const MODELS = {
12365
12364
  contextWindow: 1000000,
12366
12365
  maxTokens: 65536,
12367
12366
  },
12367
+ "nvidia/nemotron-3.5-lightning:free": {
12368
+ id: "nvidia/nemotron-3.5-lightning:free",
12369
+ name: "NVIDIA: Nemotron 3.5 Lightning (free)",
12370
+ api: "openai-completions",
12371
+ provider: "openrouter",
12372
+ baseUrl: "https://openrouter.ai/api/v1",
12373
+ reasoning: true,
12374
+ input: ["text"],
12375
+ cost: {
12376
+ input: 0,
12377
+ output: 0,
12378
+ cacheRead: 0,
12379
+ cacheWrite: 0,
12380
+ },
12381
+ contextWindow: 1000000,
12382
+ maxTokens: 65536,
12383
+ },
12368
12384
  "nvidia/nemotron-nano-12b-v2-vl:free": {
12369
12385
  id: "nvidia/nemotron-nano-12b-v2-vl:free",
12370
12386
  name: "NVIDIA: Nemotron Nano 12B 2 VL (free)",
@@ -12926,7 +12942,7 @@ export const MODELS = {
12926
12942
  cacheWrite: 0,
12927
12943
  },
12928
12944
  contextWindow: 128000,
12929
- maxTokens: 16384,
12945
+ maxTokens: 32000,
12930
12946
  },
12931
12947
  "openai/gpt-5.2-codex": {
12932
12948
  id: "openai/gpt-5.2-codex",
@@ -13000,24 +13016,6 @@ export const MODELS = {
13000
13016
  contextWindow: 400000,
13001
13017
  maxTokens: 128000,
13002
13018
  },
13003
- "openai/gpt-5.3-chat": {
13004
- id: "openai/gpt-5.3-chat",
13005
- name: "OpenAI: GPT-5.3 Chat",
13006
- api: "openai-completions",
13007
- provider: "openrouter",
13008
- baseUrl: "https://openrouter.ai/api/v1",
13009
- reasoning: false,
13010
- thinkingLevelMap: { "xhigh": "xhigh" },
13011
- input: ["text", "image"],
13012
- cost: {
13013
- input: 1.75,
13014
- output: 14,
13015
- cacheRead: 0.175,
13016
- cacheWrite: 0,
13017
- },
13018
- contextWindow: 128000,
13019
- maxTokens: 16384,
13020
- },
13021
13019
  "openai/gpt-5.3-codex": {
13022
13020
  id: "openai/gpt-5.3-codex",
13023
13021
  name: "OpenAI: GPT-5.3-Codex",
@@ -13533,9 +13531,9 @@ export const MODELS = {
13533
13531
  reasoning: true,
13534
13532
  input: ["text"],
13535
13533
  cost: {
13536
- input: 0.037,
13534
+ input: 0.03,
13537
13535
  output: 0.16999999999999998,
13538
- cacheRead: 0,
13536
+ cacheRead: 0.03,
13539
13537
  cacheWrite: 0,
13540
13538
  },
13541
13539
  contextWindow: 131072,
@@ -14043,13 +14041,13 @@ export const MODELS = {
14043
14041
  reasoning: true,
14044
14042
  input: ["text"],
14045
14043
  cost: {
14046
- input: 0.22749999999999998,
14047
- output: 0.9099999999999999,
14044
+ input: 0.12,
14045
+ output: 0.24,
14048
14046
  cacheRead: 0,
14049
14047
  cacheWrite: 0,
14050
14048
  },
14051
14049
  contextWindow: 131072,
14052
- maxTokens: 8192,
14050
+ maxTokens: 16384,
14053
14051
  },
14054
14052
  "qwen/qwen3-235b-a22b": {
14055
14053
  id: "qwen/qwen3-235b-a22b",
@@ -14214,12 +14212,12 @@ export const MODELS = {
14214
14212
  input: ["text"],
14215
14213
  cost: {
14216
14214
  input: 0.07,
14217
- output: 0.27,
14215
+ output: 0.28,
14218
14216
  cacheRead: 0,
14219
14217
  cacheWrite: 0,
14220
14218
  },
14221
14219
  contextWindow: 262144,
14222
- maxTokens: 32768,
14220
+ maxTokens: 262144,
14223
14221
  },
14224
14222
  "qwen/qwen3-coder-flash": {
14225
14223
  id: "qwen/qwen3-coder-flash",
@@ -14349,9 +14347,9 @@ export const MODELS = {
14349
14347
  reasoning: false,
14350
14348
  input: ["text", "image"],
14351
14349
  cost: {
14352
- input: 0.21,
14353
- output: 1.9,
14354
- cacheRead: 0.09999999999999999,
14350
+ input: 0.26,
14351
+ output: 1.04,
14352
+ cacheRead: 0,
14355
14353
  cacheWrite: 0,
14356
14354
  },
14357
14355
  contextWindow: 262144,
@@ -14519,13 +14517,13 @@ export const MODELS = {
14519
14517
  reasoning: true,
14520
14518
  input: ["text", "image"],
14521
14519
  cost: {
14522
- input: 0.39,
14523
- output: 2.34,
14524
- cacheRead: 0,
14520
+ input: 0.5,
14521
+ output: 3.5999999999999996,
14522
+ cacheRead: 0.3,
14525
14523
  cacheWrite: 0,
14526
14524
  },
14527
14525
  contextWindow: 262144,
14528
- maxTokens: 65536,
14526
+ maxTokens: 262144,
14529
14527
  },
14530
14528
  "qwen/qwen3.5-9b": {
14531
14529
  id: "qwen/qwen3.5-9b",
@@ -14621,7 +14619,7 @@ export const MODELS = {
14621
14619
  reasoning: true,
14622
14620
  input: ["text", "image"],
14623
14621
  cost: {
14624
- input: 0.14,
14622
+ input: 0.15,
14625
14623
  output: 1,
14626
14624
  cacheRead: 0.049999999999999996,
14627
14625
  cacheWrite: 0,
@@ -14799,6 +14797,23 @@ export const MODELS = {
14799
14797
  contextWindow: 1000000,
14800
14798
  maxTokens: 128000,
14801
14799
  },
14800
+ "sakana/sakana-namazu": {
14801
+ id: "sakana/sakana-namazu",
14802
+ name: "Sakana: Sakana Namazu",
14803
+ api: "openai-completions",
14804
+ provider: "openrouter",
14805
+ baseUrl: "https://openrouter.ai/api/v1",
14806
+ reasoning: true,
14807
+ input: ["text", "image"],
14808
+ cost: {
14809
+ input: 0.95,
14810
+ output: 4,
14811
+ cacheRead: 0.15,
14812
+ cacheWrite: 0,
14813
+ },
14814
+ contextWindow: 262144,
14815
+ maxTokens: 65536,
14816
+ },
14802
14817
  "sao10k/l3.1-euryale-70b": {
14803
14818
  id: "sao10k/l3.1-euryale-70b",
14804
14819
  name: "Sao10K: Llama 3.1 Euryale 70B v2.2",
@@ -14952,6 +14967,23 @@ export const MODELS = {
14952
14967
  contextWindow: 131072,
14953
14968
  maxTokens: 131072,
14954
14969
  },
14970
+ "upstage/solar-pro4": {
14971
+ id: "upstage/solar-pro4",
14972
+ name: "Upstage: Solar Pro 4",
14973
+ api: "openai-completions",
14974
+ provider: "openrouter",
14975
+ baseUrl: "https://openrouter.ai/api/v1",
14976
+ reasoning: true,
14977
+ input: ["text"],
14978
+ cost: {
14979
+ input: 0.03,
14980
+ output: 0.12,
14981
+ cacheRead: 0.006,
14982
+ cacheWrite: 0,
14983
+ },
14984
+ contextWindow: 524288,
14985
+ maxTokens: 131072,
14986
+ },
14955
14987
  "x-ai/grok-4.20": {
14956
14988
  id: "x-ai/grok-4.20",
14957
14989
  name: "SpaceXAI: Grok 4.20",
@@ -15114,9 +15146,9 @@ export const MODELS = {
15114
15146
  reasoning: true,
15115
15147
  input: ["text"],
15116
15148
  cost: {
15117
- input: 0.5,
15118
- output: 2,
15119
- cacheRead: 0.09999999999999999,
15149
+ input: 0.55,
15150
+ output: 2.2,
15151
+ cacheRead: 0.11,
15120
15152
  cacheWrite: 0,
15121
15153
  },
15122
15154
  contextWindow: 204800,
@@ -15216,9 +15248,9 @@ export const MODELS = {
15216
15248
  reasoning: true,
15217
15249
  input: ["text"],
15218
15250
  cost: {
15219
- input: 0.952,
15220
- output: 2.992,
15221
- cacheRead: 0.17679999999999998,
15251
+ input: 1.4,
15252
+ output: 4.4,
15253
+ cacheRead: 0.26,
15222
15254
  cacheWrite: 0,
15223
15255
  },
15224
15256
  contextWindow: 204800,
@@ -15233,13 +15265,13 @@ export const MODELS = {
15233
15265
  reasoning: true,
15234
15266
  input: ["text"],
15235
15267
  cost: {
15236
- input: 0.2772,
15237
- output: 0.8712,
15238
- cacheRead: 0.051480000000000005,
15268
+ input: 0.5,
15269
+ output: 3.15,
15270
+ cacheRead: 0.09999999999999999,
15239
15271
  cacheWrite: 0,
15240
15272
  },
15241
15273
  contextWindow: 1048576,
15242
- maxTokens: 128000,
15274
+ maxTokens: 131072,
15243
15275
  },
15244
15276
  "z-ai/glm-5.2:batch": {
15245
15277
  id: "z-ai/glm-5.2:batch",
@@ -15355,13 +15387,13 @@ export const MODELS = {
15355
15387
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
15356
15388
  input: ["text"],
15357
15389
  cost: {
15358
- input: 0.09,
15359
- output: 0.18,
15360
- cacheRead: 0.018,
15390
+ input: 0.079996,
15391
+ output: 0.252,
15392
+ cacheRead: 0.0252,
15361
15393
  cacheWrite: 0,
15362
15394
  },
15363
15395
  contextWindow: 1048576,
15364
- maxTokens: 384000,
15396
+ maxTokens: 4096,
15365
15397
  },
15366
15398
  "~google/gemini-flash-latest": {
15367
15399
  id: "~google/gemini-flash-latest",
@@ -15406,7 +15438,7 @@ export const MODELS = {
15406
15438
  reasoning: true,
15407
15439
  input: ["text", "image"],
15408
15440
  cost: {
15409
- input: 2.5,
15441
+ input: 2.8,
15410
15442
  output: 14,
15411
15443
  cacheRead: 0.29,
15412
15444
  cacheWrite: 0,
@@ -15803,7 +15835,7 @@ export const MODELS = {
15803
15835
  cacheRead: 0.26,
15804
15836
  cacheWrite: 0,
15805
15837
  },
15806
- contextWindow: 262144,
15838
+ contextWindow: 512000,
15807
15839
  maxTokens: 164000,
15808
15840
  },
15809
15841
  },
@@ -16493,6 +16525,23 @@ export const MODELS = {
16493
16525
  contextWindow: 1000000,
16494
16526
  maxTokens: 128000,
16495
16527
  },
16528
+ "anthropic/claude-opus-5-fast": {
16529
+ id: "anthropic/claude-opus-5-fast",
16530
+ name: "Claude Opus 5 (Fast)",
16531
+ api: "anthropic-messages",
16532
+ provider: "vercel-ai-gateway",
16533
+ baseUrl: "https://ai-gateway.vercel.sh",
16534
+ reasoning: true,
16535
+ input: ["text", "image"],
16536
+ cost: {
16537
+ input: 10,
16538
+ output: 50,
16539
+ cacheRead: 1,
16540
+ cacheWrite: 12.5,
16541
+ },
16542
+ contextWindow: 1000000,
16543
+ maxTokens: 128000,
16544
+ },
16496
16545
  "anthropic/claude-sonnet-4": {
16497
16546
  id: "anthropic/claude-sonnet-4",
16498
16547
  name: "Claude Sonnet 4",
@@ -16954,7 +17003,7 @@ export const MODELS = {
16954
17003
  },
16955
17004
  "google/gemma-4-26b-a4b-it": {
16956
17005
  id: "google/gemma-4-26b-a4b-it",
16957
- name: "Gemma 4 26B A4B IT",
17006
+ name: "Google Gemma 4 26B A4B",
16958
17007
  api: "anthropic-messages",
16959
17008
  provider: "vercel-ai-gateway",
16960
17009
  baseUrl: "https://ai-gateway.vercel.sh",
@@ -17224,6 +17273,23 @@ export const MODELS = {
17224
17273
  contextWindow: 128000,
17225
17274
  maxTokens: 8192,
17226
17275
  },
17276
+ "meta/muse-glimmer-30b": {
17277
+ id: "meta/muse-glimmer-30b",
17278
+ name: "Muse Glimmer 30B",
17279
+ api: "anthropic-messages",
17280
+ provider: "vercel-ai-gateway",
17281
+ baseUrl: "https://ai-gateway.vercel.sh",
17282
+ reasoning: true,
17283
+ input: ["text", "image"],
17284
+ cost: {
17285
+ input: 0.35,
17286
+ output: 1.5,
17287
+ cacheRead: 0.04,
17288
+ cacheWrite: 0,
17289
+ },
17290
+ contextWindow: 131072,
17291
+ maxTokens: 131072,
17292
+ },
17227
17293
  "meta/muse-spark-1.1": {
17228
17294
  id: "meta/muse-spark-1.1",
17229
17295
  name: "Muse Spark 1.1",
@@ -18108,23 +18174,6 @@ export const MODELS = {
18108
18174
  contextWindow: 400000,
18109
18175
  maxTokens: 128000,
18110
18176
  },
18111
- "openai/gpt-5.1-instant": {
18112
- id: "openai/gpt-5.1-instant",
18113
- name: "GPT-5.1 Instant",
18114
- api: "anthropic-messages",
18115
- provider: "vercel-ai-gateway",
18116
- baseUrl: "https://ai-gateway.vercel.sh",
18117
- reasoning: false,
18118
- input: ["text", "image"],
18119
- cost: {
18120
- input: 1.25,
18121
- output: 10,
18122
- cacheRead: 0.13,
18123
- cacheWrite: 0,
18124
- },
18125
- contextWindow: 128000,
18126
- maxTokens: 16384,
18127
- },
18128
18177
  "openai/gpt-5.1-thinking": {
18129
18178
  id: "openai/gpt-5.1-thinking",
18130
18179
  name: "GPT 5.1 Thinking",
@@ -18196,24 +18245,6 @@ export const MODELS = {
18196
18245
  contextWindow: 400000,
18197
18246
  maxTokens: 128000,
18198
18247
  },
18199
- "openai/gpt-5.3-chat": {
18200
- id: "openai/gpt-5.3-chat",
18201
- name: "GPT-5.3 Chat",
18202
- api: "anthropic-messages",
18203
- provider: "vercel-ai-gateway",
18204
- baseUrl: "https://ai-gateway.vercel.sh",
18205
- reasoning: false,
18206
- thinkingLevelMap: { "xhigh": "xhigh" },
18207
- input: ["text", "image"],
18208
- cost: {
18209
- input: 1.75,
18210
- output: 14,
18211
- cacheRead: 0.175,
18212
- cacheWrite: 0,
18213
- },
18214
- contextWindow: 128000,
18215
- maxTokens: 16384,
18216
- },
18217
18248
  "openai/gpt-5.3-codex": {
18218
18249
  id: "openai/gpt-5.3-codex",
18219
18250
  name: "GPT 5.3 Codex",
@@ -18595,6 +18626,23 @@ export const MODELS = {
18595
18626
  contextWindow: 1000000,
18596
18627
  maxTokens: 1000000,
18597
18628
  },
18629
+ "sakana/namazu": {
18630
+ id: "sakana/namazu",
18631
+ name: "Sakana Namazu",
18632
+ api: "anthropic-messages",
18633
+ provider: "vercel-ai-gateway",
18634
+ baseUrl: "https://ai-gateway.vercel.sh",
18635
+ reasoning: true,
18636
+ input: ["text", "image"],
18637
+ cost: {
18638
+ input: 0.95,
18639
+ output: 4,
18640
+ cacheRead: 0.15,
18641
+ cacheWrite: 0,
18642
+ },
18643
+ contextWindow: 256000,
18644
+ maxTokens: 256000,
18645
+ },
18598
18646
  "stepfun/step-3.5-flash": {
18599
18647
  id: "stepfun/step-3.5-flash",
18600
18648
  name: "StepFun 3.5 Flash",