@elyracode/ai 0.9.48 → 0.9.49

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.
@@ -5301,7 +5301,7 @@ export const MODELS = {
5301
5301
  baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
5302
5302
  compat: { "sendSessionAffinityHeaders": true },
5303
5303
  reasoning: false,
5304
- input: ["text"],
5304
+ input: ["text", "image"],
5305
5305
  cost: {
5306
5306
  input: 0.351,
5307
5307
  output: 0.555,
@@ -7333,6 +7333,24 @@ export const MODELS = {
7333
7333
  },
7334
7334
  },
7335
7335
  "huggingface": {
7336
+ "MiniMaxAI/MiniMax-M1-80k": {
7337
+ id: "MiniMaxAI/MiniMax-M1-80k",
7338
+ name: "MiniMax M1 80K",
7339
+ api: "openai-completions",
7340
+ provider: "huggingface",
7341
+ baseUrl: "https://router.huggingface.co/v1",
7342
+ compat: { "supportsDeveloperRole": false },
7343
+ reasoning: true,
7344
+ input: ["text"],
7345
+ cost: {
7346
+ input: 0.55,
7347
+ output: 2.2,
7348
+ cacheRead: 0,
7349
+ cacheWrite: 0,
7350
+ },
7351
+ contextWindow: 1000000,
7352
+ maxTokens: 80000,
7353
+ },
7336
7354
  "MiniMaxAI/MiniMax-M2": {
7337
7355
  id: "MiniMaxAI/MiniMax-M2",
7338
7356
  name: "MiniMax-M2",
@@ -7657,6 +7675,24 @@ export const MODELS = {
7657
7675
  contextWindow: 131072,
7658
7676
  maxTokens: 32768,
7659
7677
  },
7678
+ "Qwen/Qwen3-VL-30B-A3B-Instruct": {
7679
+ id: "Qwen/Qwen3-VL-30B-A3B-Instruct",
7680
+ name: "Qwen3 VL 30B A3B Instruct",
7681
+ api: "openai-completions",
7682
+ provider: "huggingface",
7683
+ baseUrl: "https://router.huggingface.co/v1",
7684
+ compat: { "supportsDeveloperRole": false },
7685
+ reasoning: false,
7686
+ input: ["text", "image"],
7687
+ cost: {
7688
+ input: 0.2,
7689
+ output: 0.7,
7690
+ cacheRead: 0,
7691
+ cacheWrite: 0,
7692
+ },
7693
+ contextWindow: 131072,
7694
+ maxTokens: 32768,
7695
+ },
7660
7696
  "Qwen/Qwen3.5-122B-A10B": {
7661
7697
  id: "Qwen/Qwen3.5-122B-A10B",
7662
7698
  name: "Qwen3.5 122B-A10B",
@@ -9202,7 +9238,7 @@ export const MODELS = {
9202
9238
  cacheRead: 0.07,
9203
9239
  cacheWrite: 0,
9204
9240
  },
9205
- contextWindow: 524288,
9241
+ contextWindow: 1048576,
9206
9242
  maxTokens: 262144,
9207
9243
  },
9208
9244
  "mistral-large-latest": {
@@ -11002,23 +11038,6 @@ export const MODELS = {
11002
11038
  contextWindow: 1048576,
11003
11039
  maxTokens: 131072,
11004
11040
  },
11005
- "fledge-alpha-free": {
11006
- id: "fledge-alpha-free",
11007
- name: "Fledge Alpha Free",
11008
- api: "openai-completions",
11009
- provider: "opencode",
11010
- baseUrl: "https://opencode.ai/zen/v1",
11011
- reasoning: true,
11012
- input: ["text", "image"],
11013
- cost: {
11014
- input: 0,
11015
- output: 0,
11016
- cacheRead: 0,
11017
- cacheWrite: 0,
11018
- },
11019
- contextWindow: 1048576,
11020
- maxTokens: 131072,
11021
- },
11022
11041
  "gemini-3-flash": {
11023
11042
  id: "gemini-3-flash",
11024
11043
  name: "Gemini 3 Flash",
@@ -12082,6 +12101,23 @@ export const MODELS = {
12082
12101
  contextWindow: 1048576,
12083
12102
  maxTokens: 524288,
12084
12103
  },
12104
+ "step-5-preview-free": {
12105
+ id: "step-5-preview-free",
12106
+ name: "Step 5 Preview Free",
12107
+ api: "openai-completions",
12108
+ provider: "opencode",
12109
+ baseUrl: "https://opencode.ai/zen/v1",
12110
+ reasoning: true,
12111
+ input: ["text", "image"],
12112
+ cost: {
12113
+ input: 0,
12114
+ output: 0,
12115
+ cacheRead: 0,
12116
+ cacheWrite: 0,
12117
+ },
12118
+ contextWindow: 1000000,
12119
+ maxTokens: 65536,
12120
+ },
12085
12121
  },
12086
12122
  "opencode-go": {
12087
12123
  "claude-haiku-5-5": {
@@ -12603,6 +12639,23 @@ export const MODELS = {
12603
12639
  contextWindow: 1048576,
12604
12640
  maxTokens: 524288,
12605
12641
  },
12642
+ "step-5-preview-free": {
12643
+ id: "step-5-preview-free",
12644
+ name: "Step 5 Preview Free",
12645
+ api: "openai-completions",
12646
+ provider: "opencode-go",
12647
+ baseUrl: "https://opencode.ai/zen/go/v1",
12648
+ reasoning: true,
12649
+ input: ["text", "image"],
12650
+ cost: {
12651
+ input: 0,
12652
+ output: 0,
12653
+ cacheRead: 0,
12654
+ cacheWrite: 0,
12655
+ },
12656
+ contextWindow: 1000000,
12657
+ maxTokens: 65536,
12658
+ },
12606
12659
  },
12607
12660
  "openrouter": {
12608
12661
  "aion-labs/aion-2.0": {
@@ -13542,13 +13595,13 @@ export const MODELS = {
13542
13595
  reasoning: false,
13543
13596
  input: ["text"],
13544
13597
  cost: {
13545
- input: 0.2574,
13546
- output: 1.0287,
13598
+ input: 0.32,
13599
+ output: 0.8899999999999999,
13547
13600
  cacheRead: 0,
13548
13601
  cacheWrite: 0,
13549
13602
  },
13550
13603
  contextWindow: 163840,
13551
- maxTokens: 16000,
13604
+ maxTokens: 16384,
13552
13605
  },
13553
13606
  "deepseek/deepseek-chat-v3-0324": {
13554
13607
  id: "deepseek/deepseek-chat-v3-0324",
@@ -13645,8 +13698,8 @@ export const MODELS = {
13645
13698
  input: ["text"],
13646
13699
  cost: {
13647
13700
  input: 0.25899999999999995,
13648
- output: 0.42,
13649
- cacheRead: 0.135,
13701
+ output: 0.7999999999999999,
13702
+ cacheRead: 0.14,
13650
13703
  cacheWrite: 0,
13651
13704
  },
13652
13705
  contextWindow: 163840,
@@ -13680,9 +13733,9 @@ export const MODELS = {
13680
13733
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13681
13734
  input: ["text"],
13682
13735
  cost: {
13683
- input: 0.009699999999999999,
13736
+ input: 0.012100000000000001,
13684
13737
  output: 1.28,
13685
- cacheRead: 0.009699999999999999,
13738
+ cacheRead: 0.012100000000000001,
13686
13739
  cacheWrite: 0,
13687
13740
  },
13688
13741
  contextWindow: 1048576,
@@ -13699,9 +13752,9 @@ export const MODELS = {
13699
13752
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13700
13753
  input: ["text"],
13701
13754
  cost: {
13702
- input: 0.010400000000000001,
13755
+ input: 0.0068,
13703
13756
  output: 1.28,
13704
- cacheRead: 0.010400000000000001,
13757
+ cacheRead: 0.0068,
13705
13758
  cacheWrite: 0,
13706
13759
  },
13707
13760
  contextWindow: 1048576,
@@ -13737,9 +13790,9 @@ export const MODELS = {
13737
13790
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13738
13791
  input: ["text"],
13739
13792
  cost: {
13740
- input: 0.9552599999999999,
13741
- output: 1.9105199999999998,
13742
- cacheRead: 0.07960500000000001,
13793
+ input: 0.9483,
13794
+ output: 1.8966,
13795
+ cacheRead: 0.079025,
13743
13796
  cacheWrite: 0,
13744
13797
  },
13745
13798
  contextWindow: 1048576,
@@ -13756,9 +13809,9 @@ export const MODELS = {
13756
13809
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13757
13810
  input: ["text"],
13758
13811
  cost: {
13759
- input: 1.32,
13760
- output: 3.9600000000000004,
13761
- cacheRead: 0.044,
13812
+ input: 0.66,
13813
+ output: 1.9800000000000002,
13814
+ cacheRead: 0.022,
13762
13815
  cacheWrite: 0,
13763
13816
  },
13764
13817
  contextWindow: 1048576,
@@ -14338,9 +14391,9 @@ export const MODELS = {
14338
14391
  reasoning: true,
14339
14392
  input: ["text", "image"],
14340
14393
  cost: {
14341
- input: 0.09,
14342
- output: 0.3,
14343
- cacheRead: 0.049999999999999996,
14394
+ input: 0.0675,
14395
+ output: 0.22499999999999998,
14396
+ cacheRead: 0.0375,
14344
14397
  cacheWrite: 0,
14345
14398
  },
14346
14399
  contextWindow: 262144,
@@ -14482,18 +14535,18 @@ export const MODELS = {
14482
14535
  contextWindow: 262144,
14483
14536
  maxTokens: 32768,
14484
14537
  },
14485
- "inclusionai/ling-3.0-flash-sante:free": {
14486
- id: "inclusionai/ling-3.0-flash-sante:free",
14487
- name: "inclusionAI: Ling 3.0 Flash Sante (free)",
14538
+ "inclusionai/ling-3.0-flash-sante": {
14539
+ id: "inclusionai/ling-3.0-flash-sante",
14540
+ name: "inclusionAI: Ling 3.0 Flash Sante",
14488
14541
  api: "openai-completions",
14489
14542
  provider: "openrouter",
14490
14543
  baseUrl: "https://openrouter.ai/api/v1",
14491
14544
  reasoning: true,
14492
14545
  input: ["text"],
14493
14546
  cost: {
14494
- input: 0,
14495
- output: 0,
14496
- cacheRead: 0,
14547
+ input: 0.041999999999999996,
14548
+ output: 0.12319999999999999,
14549
+ cacheRead: 0.008400000000000001,
14497
14550
  cacheWrite: 0,
14498
14551
  },
14499
14552
  contextWindow: 262144,
@@ -14610,9 +14663,9 @@ export const MODELS = {
14610
14663
  reasoning: false,
14611
14664
  input: ["text"],
14612
14665
  cost: {
14613
- input: 0.09999999999999999,
14614
- output: 0.32,
14615
- cacheRead: 0,
14666
+ input: 0.22,
14667
+ output: 0.5,
14668
+ cacheRead: 0.11,
14616
14669
  cacheWrite: 0,
14617
14670
  },
14618
14671
  contextWindow: 131072,
@@ -15057,7 +15110,7 @@ export const MODELS = {
15057
15110
  cacheRead: 0.07,
15058
15111
  cacheWrite: 0,
15059
15112
  },
15060
- contextWindow: 524288,
15113
+ contextWindow: 1048576,
15061
15114
  maxTokens: 262144,
15062
15115
  },
15063
15116
  "mistralai/mistral-medium-3": {
@@ -15154,7 +15207,7 @@ export const MODELS = {
15154
15207
  reasoning: false,
15155
15208
  input: ["text"],
15156
15209
  cost: {
15157
- input: 0.019000000000000003,
15210
+ input: 0.029,
15158
15211
  output: 0.03,
15159
15212
  cacheRead: 0,
15160
15213
  cacheWrite: 0,
@@ -15326,11 +15379,11 @@ export const MODELS = {
15326
15379
  cost: {
15327
15380
  input: 0.6,
15328
15381
  output: 2.5,
15329
- cacheRead: 0,
15382
+ cacheRead: 0.15,
15330
15383
  cacheWrite: 0,
15331
15384
  },
15332
15385
  contextWindow: 262144,
15333
- maxTokens: 235929,
15386
+ maxTokens: 98304,
15334
15387
  },
15335
15388
  "moonshotai/kimi-k2.5": {
15336
15389
  id: "moonshotai/kimi-k2.5",
@@ -15360,7 +15413,7 @@ export const MODELS = {
15360
15413
  cost: {
15361
15414
  input: 0.46499999999999997,
15362
15415
  output: 2.4499999999999997,
15363
- cacheRead: 0.0975,
15416
+ cacheRead: 0.0875,
15364
15417
  cacheWrite: 0,
15365
15418
  },
15366
15419
  contextWindow: 262144,
@@ -15392,9 +15445,9 @@ export const MODELS = {
15392
15445
  reasoning: true,
15393
15446
  input: ["text", "image"],
15394
15447
  cost: {
15395
- input: 0.58,
15396
- output: 12.3,
15397
- cacheRead: 0.39999999999999997,
15448
+ input: 0.64,
15449
+ output: 13.5,
15450
+ cacheRead: 0.28,
15398
15451
  cacheWrite: 0,
15399
15452
  },
15400
15453
  contextWindow: 1048576,
@@ -15477,13 +15530,13 @@ export const MODELS = {
15477
15530
  reasoning: true,
15478
15531
  input: ["text"],
15479
15532
  cost: {
15480
- input: 0.08499999999999999,
15481
- output: 0.39999999999999997,
15533
+ input: 0.08,
15534
+ output: 0.44999999999999996,
15482
15535
  cacheRead: 0,
15483
15536
  cacheWrite: 0,
15484
15537
  },
15485
15538
  contextWindow: 262144,
15486
- maxTokens: 16384,
15539
+ maxTokens: 235929,
15487
15540
  },
15488
15541
  "nvidia/nemotron-3-super-120b-a12b:free": {
15489
15542
  id: "nvidia/nemotron-3-super-120b-a12b:free",
@@ -15545,13 +15598,13 @@ export const MODELS = {
15545
15598
  reasoning: true,
15546
15599
  input: ["text"],
15547
15600
  cost: {
15548
- input: 0.049,
15549
- output: 0.14,
15550
- cacheRead: 0.0245,
15601
+ input: 0.07,
15602
+ output: 0.19999999999999998,
15603
+ cacheRead: 0.04,
15551
15604
  cacheWrite: 0,
15552
15605
  },
15553
15606
  contextWindow: 262144,
15554
- maxTokens: 131072,
15607
+ maxTokens: 235929,
15555
15608
  },
15556
15609
  "nvidia/nemotron-3.5-lightning:free": {
15557
15610
  id: "nvidia/nemotron-3.5-lightning:free",
@@ -16847,6 +16900,40 @@ export const MODELS = {
16847
16900
  contextWindow: 1050000,
16848
16901
  maxTokens: 128000,
16849
16902
  },
16903
+ "openai/gpt-6.1-sol-pro:batch": {
16904
+ id: "openai/gpt-6.1-sol-pro:batch",
16905
+ name: "OpenAI: GPT-6.1 Sol Pro (batch)",
16906
+ api: "openai-completions",
16907
+ provider: "openrouter",
16908
+ baseUrl: "https://openrouter.ai/api/v1",
16909
+ reasoning: true,
16910
+ input: ["text", "image"],
16911
+ cost: {
16912
+ input: 1,
16913
+ output: 5,
16914
+ cacheRead: 0.049999999999999996,
16915
+ cacheWrite: 1.25,
16916
+ },
16917
+ contextWindow: 1050000,
16918
+ maxTokens: 128000,
16919
+ },
16920
+ "openai/gpt-6.1-sol:batch": {
16921
+ id: "openai/gpt-6.1-sol:batch",
16922
+ name: "OpenAI: GPT-6.1 Sol (batch)",
16923
+ api: "openai-completions",
16924
+ provider: "openrouter",
16925
+ baseUrl: "https://openrouter.ai/api/v1",
16926
+ reasoning: true,
16927
+ input: ["text", "image"],
16928
+ cost: {
16929
+ input: 1,
16930
+ output: 5,
16931
+ cacheRead: 0.049999999999999996,
16932
+ cacheWrite: 1.25,
16933
+ },
16934
+ contextWindow: 1050000,
16935
+ maxTokens: 128000,
16936
+ },
16850
16937
  "openai/gpt-audio": {
16851
16938
  id: "openai/gpt-audio",
16852
16939
  name: "OpenAI: GPT Audio",
@@ -17357,23 +17444,6 @@ export const MODELS = {
17357
17444
  contextWindow: 1000000,
17358
17445
  maxTokens: 32768,
17359
17446
  },
17360
- "qwen/qwen-plus-2025-07-28": {
17361
- id: "qwen/qwen-plus-2025-07-28",
17362
- name: "Qwen: Qwen Plus 0728",
17363
- api: "openai-completions",
17364
- provider: "openrouter",
17365
- baseUrl: "https://openrouter.ai/api/v1",
17366
- reasoning: false,
17367
- input: ["text"],
17368
- cost: {
17369
- input: 0.26,
17370
- output: 0.78,
17371
- cacheRead: 0,
17372
- cacheWrite: 0,
17373
- },
17374
- contextWindow: 1000000,
17375
- maxTokens: 32768,
17376
- },
17377
17447
  "qwen/qwen3-14b": {
17378
17448
  id: "qwen/qwen3-14b",
17379
17449
  name: "Qwen: Qwen3 14B",
@@ -17383,30 +17453,13 @@ export const MODELS = {
17383
17453
  reasoning: true,
17384
17454
  input: ["text"],
17385
17455
  cost: {
17386
- input: 0.12,
17387
- output: 0.24,
17388
- cacheRead: 0,
17389
- cacheWrite: 0,
17390
- },
17391
- contextWindow: 131072,
17392
- maxTokens: 16384,
17393
- },
17394
- "qwen/qwen3-235b-a22b": {
17395
- id: "qwen/qwen3-235b-a22b",
17396
- name: "Qwen: Qwen3 235B A22B",
17397
- api: "openai-completions",
17398
- provider: "openrouter",
17399
- baseUrl: "https://openrouter.ai/api/v1",
17400
- reasoning: true,
17401
- input: ["text"],
17402
- cost: {
17403
- input: 0.45499999999999996,
17404
- output: 1.8199999999999998,
17456
+ input: 0.09999999999999999,
17457
+ output: 0.22,
17405
17458
  cacheRead: 0,
17406
17459
  cacheWrite: 0,
17407
17460
  },
17408
- contextWindow: 131072,
17409
- maxTokens: 8192,
17461
+ contextWindow: 40960,
17462
+ maxTokens: 36864,
17410
17463
  },
17411
17464
  "qwen/qwen3-235b-a22b-2507": {
17412
17465
  id: "qwen/qwen3-235b-a22b-2507",
@@ -17434,13 +17487,13 @@ export const MODELS = {
17434
17487
  reasoning: true,
17435
17488
  input: ["text"],
17436
17489
  cost: {
17437
- input: 0.22999999999999998,
17438
- output: 2.3,
17490
+ input: 0.44999999999999996,
17491
+ output: 3.5,
17439
17492
  cacheRead: 0,
17440
17493
  cacheWrite: 0,
17441
17494
  },
17442
- contextWindow: 131072,
17443
- maxTokens: 117964,
17495
+ contextWindow: 128000,
17496
+ maxTokens: 16384,
17444
17497
  },
17445
17498
  "qwen/qwen3-30b-a3b": {
17446
17499
  id: "qwen/qwen3-30b-a3b",
@@ -17456,7 +17509,7 @@ export const MODELS = {
17456
17509
  cacheRead: 0,
17457
17510
  cacheWrite: 0,
17458
17511
  },
17459
- contextWindow: 131072,
17512
+ contextWindow: 40960,
17460
17513
  maxTokens: 16384,
17461
17514
  },
17462
17515
  "qwen/qwen3-30b-a3b-instruct-2507": {
@@ -17468,30 +17521,13 @@ export const MODELS = {
17468
17521
  reasoning: false,
17469
17522
  input: ["text"],
17470
17523
  cost: {
17471
- input: 0.04815,
17472
- output: 0.19305,
17524
+ input: 0.09999999999999999,
17525
+ output: 0.3,
17473
17526
  cacheRead: 0,
17474
17527
  cacheWrite: 0,
17475
17528
  },
17476
17529
  contextWindow: 262144,
17477
- maxTokens: 32000,
17478
- },
17479
- "qwen/qwen3-30b-a3b-thinking-2507": {
17480
- id: "qwen/qwen3-30b-a3b-thinking-2507",
17481
- name: "Qwen: Qwen3 30B A3B Thinking 2507",
17482
- api: "openai-completions",
17483
- provider: "openrouter",
17484
- baseUrl: "https://openrouter.ai/api/v1",
17485
- reasoning: true,
17486
- input: ["text"],
17487
- cost: {
17488
- input: 0.19999999999999998,
17489
- output: 2.4,
17490
- cacheRead: 0,
17491
- cacheWrite: 0,
17492
- },
17493
- contextWindow: 81920,
17494
- maxTokens: 32768,
17530
+ maxTokens: 235929,
17495
17531
  },
17496
17532
  "qwen/qwen3-32b": {
17497
17533
  id: "qwen/qwen3-32b",
@@ -17510,23 +17546,6 @@ export const MODELS = {
17510
17546
  contextWindow: 131072,
17511
17547
  maxTokens: 16384,
17512
17548
  },
17513
- "qwen/qwen3-8b": {
17514
- id: "qwen/qwen3-8b",
17515
- name: "Qwen: Qwen3 8B",
17516
- api: "openai-completions",
17517
- provider: "openrouter",
17518
- baseUrl: "https://openrouter.ai/api/v1",
17519
- reasoning: true,
17520
- input: ["text"],
17521
- cost: {
17522
- input: 0.117,
17523
- output: 0.45499999999999996,
17524
- cacheRead: 0,
17525
- cacheWrite: 0,
17526
- },
17527
- contextWindow: 131072,
17528
- maxTokens: 8192,
17529
- },
17530
17549
  "qwen/qwen3-coder": {
17531
17550
  id: "qwen/qwen3-coder",
17532
17551
  name: "Qwen: Qwen3 Coder 480B A35B",
@@ -17595,57 +17614,6 @@ export const MODELS = {
17595
17614
  contextWindow: 262144,
17596
17615
  maxTokens: 235929,
17597
17616
  },
17598
- "qwen/qwen3-coder-plus": {
17599
- id: "qwen/qwen3-coder-plus",
17600
- name: "Qwen: Qwen3 Coder Plus",
17601
- api: "openai-completions",
17602
- provider: "openrouter",
17603
- baseUrl: "https://openrouter.ai/api/v1",
17604
- reasoning: false,
17605
- input: ["text"],
17606
- cost: {
17607
- input: 0.65,
17608
- output: 3.25,
17609
- cacheRead: 0.13,
17610
- cacheWrite: 0.8125,
17611
- },
17612
- contextWindow: 1000000,
17613
- maxTokens: 65536,
17614
- },
17615
- "qwen/qwen3-max": {
17616
- id: "qwen/qwen3-max",
17617
- name: "Qwen: Qwen3 Max",
17618
- api: "openai-completions",
17619
- provider: "openrouter",
17620
- baseUrl: "https://openrouter.ai/api/v1",
17621
- reasoning: false,
17622
- input: ["text"],
17623
- cost: {
17624
- input: 0.78,
17625
- output: 3.9,
17626
- cacheRead: 0.156,
17627
- cacheWrite: 0.975,
17628
- },
17629
- contextWindow: 262144,
17630
- maxTokens: 65536,
17631
- },
17632
- "qwen/qwen3-max-thinking": {
17633
- id: "qwen/qwen3-max-thinking",
17634
- name: "Qwen: Qwen3 Max Thinking",
17635
- api: "openai-completions",
17636
- provider: "openrouter",
17637
- baseUrl: "https://openrouter.ai/api/v1",
17638
- reasoning: true,
17639
- input: ["text"],
17640
- cost: {
17641
- input: 0.78,
17642
- output: 3.9,
17643
- cacheRead: 0,
17644
- cacheWrite: 0,
17645
- },
17646
- contextWindow: 262144,
17647
- maxTokens: 65536,
17648
- },
17649
17617
  "qwen/qwen3-next-80b-a3b-instruct": {
17650
17618
  id: "qwen/qwen3-next-80b-a3b-instruct",
17651
17619
  name: "Qwen: Qwen3 Next 80B A3B Instruct",
@@ -17655,13 +17623,13 @@ export const MODELS = {
17655
17623
  reasoning: false,
17656
17624
  input: ["text"],
17657
17625
  cost: {
17658
- input: 0.15,
17659
- output: 1.5,
17660
- cacheRead: 0,
17626
+ input: 0.09999999999999999,
17627
+ output: 1.1,
17628
+ cacheRead: 0.07,
17661
17629
  cacheWrite: 0,
17662
17630
  },
17663
17631
  contextWindow: 262144,
17664
- maxTokens: 32768,
17632
+ maxTokens: 235929,
17665
17633
  },
17666
17634
  "qwen/qwen3-next-80b-a3b-thinking": {
17667
17635
  id: "qwen/qwen3-next-80b-a3b-thinking",
@@ -17678,7 +17646,7 @@ export const MODELS = {
17678
17646
  cacheWrite: 0,
17679
17647
  },
17680
17648
  contextWindow: 262144,
17681
- maxTokens: 32768,
17649
+ maxTokens: 235929,
17682
17650
  },
17683
17651
  "qwen/qwen3-vl-235b-a22b-instruct": {
17684
17652
  id: "qwen/qwen3-vl-235b-a22b-instruct",
@@ -17697,23 +17665,6 @@ export const MODELS = {
17697
17665
  contextWindow: 262144,
17698
17666
  maxTokens: 32768,
17699
17667
  },
17700
- "qwen/qwen3-vl-235b-a22b-thinking": {
17701
- id: "qwen/qwen3-vl-235b-a22b-thinking",
17702
- name: "Qwen: Qwen3 VL 235B A22B Thinking",
17703
- api: "openai-completions",
17704
- provider: "openrouter",
17705
- baseUrl: "https://openrouter.ai/api/v1",
17706
- reasoning: true,
17707
- input: ["text", "image"],
17708
- cost: {
17709
- input: 0.39999999999999997,
17710
- output: 4,
17711
- cacheRead: 0,
17712
- cacheWrite: 0,
17713
- },
17714
- contextWindow: 131072,
17715
- maxTokens: 32768,
17716
- },
17717
17668
  "qwen/qwen3-vl-30b-a3b-instruct": {
17718
17669
  id: "qwen/qwen3-vl-30b-a3b-instruct",
17719
17670
  name: "Qwen: Qwen3 VL 30B A3B Instruct",
@@ -17740,30 +17691,13 @@ export const MODELS = {
17740
17691
  reasoning: true,
17741
17692
  input: ["text", "image"],
17742
17693
  cost: {
17743
- input: 0.19999999999999998,
17744
- output: 2.4,
17694
+ input: 0.29,
17695
+ output: 1,
17745
17696
  cacheRead: 0,
17746
17697
  cacheWrite: 0,
17747
17698
  },
17748
17699
  contextWindow: 262144,
17749
- maxTokens: 32768,
17750
- },
17751
- "qwen/qwen3-vl-32b-instruct": {
17752
- id: "qwen/qwen3-vl-32b-instruct",
17753
- name: "Qwen: Qwen3 VL 32B Instruct",
17754
- api: "openai-completions",
17755
- provider: "openrouter",
17756
- baseUrl: "https://openrouter.ai/api/v1",
17757
- reasoning: false,
17758
- input: ["text", "image"],
17759
- cost: {
17760
- input: 0.10400000000000001,
17761
- output: 0.41600000000000004,
17762
- cacheRead: 0,
17763
- cacheWrite: 0,
17764
- },
17765
- contextWindow: 131072,
17766
- maxTokens: 32768,
17700
+ maxTokens: 235929,
17767
17701
  },
17768
17702
  "qwen/qwen3-vl-8b-instruct": {
17769
17703
  id: "qwen/qwen3-vl-8b-instruct",
@@ -17774,30 +17708,13 @@ export const MODELS = {
17774
17708
  reasoning: false,
17775
17709
  input: ["text", "image"],
17776
17710
  cost: {
17777
- input: 0.117,
17778
- output: 0.45499999999999996,
17779
- cacheRead: 0,
17711
+ input: 0.25,
17712
+ output: 0.75,
17713
+ cacheRead: 0.12,
17780
17714
  cacheWrite: 0,
17781
17715
  },
17782
17716
  contextWindow: 262144,
17783
- maxTokens: 32768,
17784
- },
17785
- "qwen/qwen3-vl-8b-thinking": {
17786
- id: "qwen/qwen3-vl-8b-thinking",
17787
- name: "Qwen: Qwen3 VL 8B Thinking",
17788
- api: "openai-completions",
17789
- provider: "openrouter",
17790
- baseUrl: "https://openrouter.ai/api/v1",
17791
- reasoning: true,
17792
- input: ["text", "image"],
17793
- cost: {
17794
- input: 0.18,
17795
- output: 2.0999999999999996,
17796
- cacheRead: 0,
17797
- cacheWrite: 0,
17798
- },
17799
- contextWindow: 131072,
17800
- maxTokens: 32768,
17717
+ maxTokens: 235929,
17801
17718
  },
17802
17719
  "qwen/qwen3.5-122b-a10b": {
17803
17720
  id: "qwen/qwen3.5-122b-a10b",
@@ -17842,13 +17759,13 @@ export const MODELS = {
17842
17759
  reasoning: true,
17843
17760
  input: ["text", "image"],
17844
17761
  cost: {
17845
- input: 0.15,
17846
- output: 1,
17847
- cacheRead: 0.049999999999999996,
17762
+ input: 0.08,
17763
+ output: 0.75,
17764
+ cacheRead: 0.04,
17848
17765
  cacheWrite: 0,
17849
17766
  },
17850
17767
  contextWindow: 262144,
17851
- maxTokens: 235929,
17768
+ maxTokens: 32768,
17852
17769
  },
17853
17770
  "qwen/qwen3.5-397b-a17b": {
17854
17771
  id: "qwen/qwen3.5-397b-a17b",
@@ -17859,13 +17776,13 @@ export const MODELS = {
17859
17776
  reasoning: true,
17860
17777
  input: ["text", "image"],
17861
17778
  cost: {
17862
- input: 0.44999999999999996,
17863
- output: 3,
17864
- cacheRead: 0.22,
17779
+ input: 0.55,
17780
+ output: 3.5,
17781
+ cacheRead: 0.22499999999999998,
17865
17782
  cacheWrite: 0,
17866
17783
  },
17867
17784
  contextWindow: 262144,
17868
- maxTokens: 81920,
17785
+ maxTokens: 235929,
17869
17786
  },
17870
17787
  "qwen/qwen3.5-9b": {
17871
17788
  id: "qwen/qwen3.5-9b",
@@ -17944,13 +17861,13 @@ export const MODELS = {
17944
17861
  reasoning: true,
17945
17862
  input: ["text", "image"],
17946
17863
  cost: {
17947
- input: 0.3,
17948
- output: 2,
17949
- cacheRead: 0.03,
17864
+ input: 0.32,
17865
+ output: 3.1999999999999997,
17866
+ cacheRead: 0,
17950
17867
  cacheWrite: 0,
17951
17868
  },
17952
17869
  contextWindow: 262144,
17953
- maxTokens: 65536,
17870
+ maxTokens: 81920,
17954
17871
  },
17955
17872
  "qwen/qwen3.6-35b-a3b": {
17956
17873
  id: "qwen/qwen3.6-35b-a3b",
@@ -17986,23 +17903,6 @@ export const MODELS = {
17986
17903
  contextWindow: 1000000,
17987
17904
  maxTokens: 65536,
17988
17905
  },
17989
- "qwen/qwen3.6-max-preview": {
17990
- id: "qwen/qwen3.6-max-preview",
17991
- name: "Qwen: Qwen3.6 Max Preview",
17992
- api: "openai-completions",
17993
- provider: "openrouter",
17994
- baseUrl: "https://openrouter.ai/api/v1",
17995
- reasoning: true,
17996
- input: ["text"],
17997
- cost: {
17998
- input: 1.0270000000000001,
17999
- output: 6.162,
18000
- cacheRead: 0,
18001
- cacheWrite: 1.28375,
18002
- },
18003
- contextWindow: 262144,
18004
- maxTokens: 65536,
18005
- },
18006
17906
  "qwen/qwen3.6-plus": {
18007
17907
  id: "qwen/qwen3.6-plus",
18008
17908
  name: "Qwen: Qwen3.6 Plus",
@@ -18117,7 +18017,7 @@ export const MODELS = {
18117
18017
  input: 0.15,
18118
18018
  output: 0.47,
18119
18019
  cacheRead: 0.016,
18120
- cacheWrite: 0.19999999999999998,
18020
+ cacheWrite: 0,
18121
18021
  },
18122
18022
  contextWindow: 1000000,
18123
18023
  maxTokens: 131072,
@@ -18134,7 +18034,7 @@ export const MODELS = {
18134
18034
  input: 2,
18135
18035
  output: 6,
18136
18036
  cacheRead: 0.25,
18137
- cacheWrite: 2.5,
18037
+ cacheWrite: 0,
18138
18038
  },
18139
18039
  contextWindow: 1000000,
18140
18040
  maxTokens: 131072,
@@ -18275,23 +18175,6 @@ export const MODELS = {
18275
18175
  contextWindow: 262144,
18276
18176
  maxTokens: 65536,
18277
18177
  },
18278
- "sao10k/l3.1-euryale-70b": {
18279
- id: "sao10k/l3.1-euryale-70b",
18280
- name: "Sao10K: Llama 3.1 Euryale 70B v2.2",
18281
- api: "openai-completions",
18282
- provider: "openrouter",
18283
- baseUrl: "https://openrouter.ai/api/v1",
18284
- reasoning: false,
18285
- input: ["text"],
18286
- cost: {
18287
- input: 0.85,
18288
- output: 0.85,
18289
- cacheRead: 0,
18290
- cacheWrite: 0,
18291
- },
18292
- contextWindow: 131072,
18293
- maxTokens: 16384,
18294
- },
18295
18178
  "stepfun/step-3.5-flash": {
18296
18179
  id: "stepfun/step-3.5-flash",
18297
18180
  name: "StepFun: Step 3.5 Flash",
@@ -18326,6 +18209,23 @@ export const MODELS = {
18326
18209
  contextWindow: 262144,
18327
18210
  maxTokens: 230400,
18328
18211
  },
18212
+ "stepfun/step-5-preview": {
18213
+ id: "stepfun/step-5-preview",
18214
+ name: "StepFun: Step 5 Preview",
18215
+ api: "openai-completions",
18216
+ provider: "openrouter",
18217
+ baseUrl: "https://openrouter.ai/api/v1",
18218
+ reasoning: true,
18219
+ input: ["text", "image"],
18220
+ cost: {
18221
+ input: 1,
18222
+ output: 2.7,
18223
+ cacheRead: 0.049999999999999996,
18224
+ cacheWrite: 0,
18225
+ },
18226
+ contextWindow: 1000000,
18227
+ maxTokens: 64000,
18228
+ },
18329
18229
  "tencent/hy3": {
18330
18230
  id: "tencent/hy3",
18331
18231
  name: "Tencent: Hy3",
@@ -18794,13 +18694,13 @@ export const MODELS = {
18794
18694
  reasoning: true,
18795
18695
  input: ["text"],
18796
18696
  cost: {
18797
- input: 0.43,
18798
- output: 1.75,
18799
- cacheRead: 0.08,
18697
+ input: 0.5,
18698
+ output: 2,
18699
+ cacheRead: 0.09999999999999999,
18800
18700
  cacheWrite: 0,
18801
18701
  },
18802
18702
  contextWindow: 204800,
18803
- maxTokens: 16384,
18703
+ maxTokens: 131072,
18804
18704
  },
18805
18705
  "z-ai/glm-4.6v": {
18806
18706
  id: "z-ai/glm-4.6v",
@@ -18913,13 +18813,13 @@ export const MODELS = {
18913
18813
  reasoning: true,
18914
18814
  input: ["text"],
18915
18815
  cost: {
18916
- input: 0.03,
18917
- output: 10,
18918
- cacheRead: 0.03,
18816
+ input: 0.06,
18817
+ output: 7,
18818
+ cacheRead: 0.059,
18919
18819
  cacheWrite: 0,
18920
18820
  },
18921
18821
  contextWindow: 1048576,
18922
- maxTokens: 131072,
18822
+ maxTokens: 943718,
18923
18823
  },
18924
18824
  "z-ai/glm-5.3": {
18925
18825
  id: "z-ai/glm-5.3",
@@ -18930,9 +18830,9 @@ export const MODELS = {
18930
18830
  reasoning: true,
18931
18831
  input: ["text"],
18932
18832
  cost: {
18933
- input: 0.049,
18934
- output: 3.39,
18935
- cacheRead: 0.048,
18833
+ input: 0.039,
18834
+ output: 4.8,
18835
+ cacheRead: 0.038000000000000006,
18936
18836
  cacheWrite: 0,
18937
18837
  },
18938
18838
  contextWindow: 1048576,
@@ -19118,9 +19018,9 @@ export const MODELS = {
19118
19018
  reasoning: true,
19119
19019
  input: ["text", "image"],
19120
19020
  cost: {
19121
- input: 0.003,
19122
- output: 2.4,
19123
- cacheRead: 0.003,
19021
+ input: 0.0015,
19022
+ output: 0.6,
19023
+ cacheRead: 0.005,
19124
19024
  cacheWrite: 0,
19125
19025
  },
19126
19026
  contextWindow: 1048576,
@@ -19135,13 +19035,13 @@ export const MODELS = {
19135
19035
  reasoning: true,
19136
19036
  input: ["text"],
19137
19037
  cost: {
19138
- input: 0.135,
19139
- output: 8,
19140
- cacheRead: 0.09999999999999999,
19038
+ input: 0.3,
19039
+ output: 5,
19040
+ cacheRead: 0.219,
19141
19041
  cacheWrite: 0,
19142
19042
  },
19143
19043
  contextWindow: 1048576,
19144
- maxTokens: 393216,
19044
+ maxTokens: 943718,
19145
19045
  },
19146
19046
  "~deepseek/deepseek-v4-flash-latest": {
19147
19047
  id: "~deepseek/deepseek-v4-flash-latest",
@@ -19154,9 +19054,9 @@ export const MODELS = {
19154
19054
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
19155
19055
  input: ["text"],
19156
19056
  cost: {
19157
- input: 0.010400000000000001,
19057
+ input: 0.0068,
19158
19058
  output: 1.28,
19159
- cacheRead: 0.010400000000000001,
19059
+ cacheRead: 0.0068,
19160
19060
  cacheWrite: 0,
19161
19061
  },
19162
19062
  contextWindow: 1048576,
@@ -19205,9 +19105,9 @@ export const MODELS = {
19205
19105
  reasoning: true,
19206
19106
  input: ["text", "image"],
19207
19107
  cost: {
19208
- input: 0.56,
19209
- output: 13,
19210
- cacheRead: 0.44999999999999996,
19108
+ input: 0.39999999999999997,
19109
+ output: 15,
19110
+ cacheRead: 0.3,
19211
19111
  cacheWrite: 0,
19212
19112
  },
19213
19113
  contextWindow: 1048576,
@@ -19324,13 +19224,13 @@ export const MODELS = {
19324
19224
  reasoning: true,
19325
19225
  input: ["text", "image"],
19326
19226
  cost: {
19327
- input: 0.032,
19328
- output: 1.414768,
19329
- cacheRead: 0.02,
19227
+ input: 0.04,
19228
+ output: 0.5,
19229
+ cacheRead: 0.012499999999999999,
19330
19230
  cacheWrite: 0,
19331
19231
  },
19332
19232
  contextWindow: 1048576,
19333
- maxTokens: 943718,
19233
+ maxTokens: 131072,
19334
19234
  },
19335
19235
  "~z-ai/glm-latest": {
19336
19236
  id: "~z-ai/glm-latest",
@@ -19341,13 +19241,13 @@ export const MODELS = {
19341
19241
  reasoning: true,
19342
19242
  input: ["text"],
19343
19243
  cost: {
19344
- input: 0.036,
19345
- output: 12,
19346
- cacheRead: 0.0335,
19244
+ input: 0.039,
19245
+ output: 4.8,
19246
+ cacheRead: 0.038000000000000006,
19347
19247
  cacheWrite: 0,
19348
19248
  },
19349
19249
  contextWindow: 1048576,
19350
- maxTokens: 131072,
19250
+ maxTokens: 943718,
19351
19251
  },
19352
19252
  },
19353
19253
  "together": {
@@ -19696,7 +19596,7 @@ export const MODELS = {
19696
19596
  api: "anthropic-messages",
19697
19597
  provider: "vercel-ai-gateway",
19698
19598
  baseUrl: "https://ai-gateway.vercel.sh",
19699
- reasoning: true,
19599
+ reasoning: false,
19700
19600
  input: ["text"],
19701
19601
  cost: {
19702
19602
  input: 0.22,
@@ -20699,6 +20599,23 @@ export const MODELS = {
20699
20599
  contextWindow: 262144,
20700
20600
  maxTokens: 262144,
20701
20601
  },
20602
+ "callstack/apex": {
20603
+ id: "callstack/apex",
20604
+ name: "Apex",
20605
+ api: "anthropic-messages",
20606
+ provider: "vercel-ai-gateway",
20607
+ baseUrl: "https://ai-gateway.vercel.sh",
20608
+ reasoning: true,
20609
+ input: ["text", "image"],
20610
+ cost: {
20611
+ input: 0.5,
20612
+ output: 3,
20613
+ cacheRead: 0.19999999999999998,
20614
+ cacheWrite: 0,
20615
+ },
20616
+ contextWindow: 262144,
20617
+ maxTokens: 131072,
20618
+ },
20702
20619
  "cohere/command-a": {
20703
20620
  id: "cohere/command-a",
20704
20621
  name: "Command A",
@@ -21762,13 +21679,13 @@ export const MODELS = {
21762
21679
  reasoning: false,
21763
21680
  input: ["text"],
21764
21681
  cost: {
21765
- input: 0.04,
21766
- output: 0.16999999999999998,
21682
+ input: 0.029,
21683
+ output: 0.03,
21767
21684
  cacheRead: 0,
21768
21685
  cacheWrite: 0,
21769
21686
  },
21770
- contextWindow: 60288,
21771
- maxTokens: 16000,
21687
+ contextWindow: 131072,
21688
+ maxTokens: 131072,
21772
21689
  },
21773
21690
  "mistral/mistral-small": {
21774
21691
  id: "mistral/mistral-small",
@@ -23613,9 +23530,9 @@ export const MODELS = {
23613
23530
  reasoning: true,
23614
23531
  input: ["text", "image"],
23615
23532
  cost: {
23616
- input: 0.04,
23617
- output: 1.28,
23618
- cacheRead: 0.04,
23533
+ input: 0.14,
23534
+ output: 0.28,
23535
+ cacheRead: 0.0028,
23619
23536
  cacheWrite: 0,
23620
23537
  },
23621
23538
  contextWindow: 1048576,