@yeshwanthyk/ai 0.2.5 → 0.2.6

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (5) hide show
  1. package/dist/models.generated.d.ts +407 -215
  2. package/dist/models.generated.d.ts.map +1 -1
  3. package/dist/models.generated.js +528 -354
  4. package/dist/models.generated.js.map +1 -1
  5. package/package.json +1 -1
package/dist/models.generated.js CHANGED
@@ -70,6 +70,23 @@ export const MODELS = {
70
70
  contextWindow: 200000,
71
71
  maxTokens: 64000,
72
72
  },
73
+ "claude-sonnet-4-6": {
74
+ id: "claude-sonnet-4-6",
75
+ name: "Claude Sonnet 4.6",
76
+ api: "anthropic-messages",
77
+ provider: "anthropic",
78
+ baseUrl: "https://api.anthropic.com",
79
+ reasoning: true,
80
+ input: ["text", "image"],
81
+ cost: {
82
+ input: 3,
83
+ output: 15,
84
+ cacheRead: 0.3,
85
+ cacheWrite: 3.75,
86
+ },
87
+ contextWindow: 200000,
88
+ maxTokens: 64000,
89
+ },
73
90
  "claude-3-5-sonnet-20240620": {
74
91
  id: "claude-3-5-sonnet-20240620",
75
92
  name: "Claude Sonnet 3.5",
@@ -531,6 +548,23 @@ export const MODELS = {
531
548
  contextWindow: 131072,
532
549
  maxTokens: 65536,
533
550
  },
551
+ "gemini-3.1-pro-preview-customtools": {
552
+ id: "gemini-3.1-pro-preview-customtools",
553
+ name: "Gemini 3.1 Pro Preview Custom Tools",
554
+ api: "google-generative-ai",
555
+ provider: "google",
556
+ baseUrl: "https://generativelanguage.googleapis.com/v1beta",
557
+ reasoning: true,
558
+ input: ["text", "image"],
559
+ cost: {
560
+ input: 2,
561
+ output: 12,
562
+ cacheRead: 0.2,
563
+ cacheWrite: 0,
564
+ },
565
+ contextWindow: 1048576,
566
+ maxTokens: 65536,
567
+ },
534
568
  "gemini-2.0-flash": {
535
569
  id: "gemini-2.0-flash",
536
570
  name: "Gemini 2.0 Flash",
@@ -667,6 +701,23 @@ export const MODELS = {
667
701
  contextWindow: 1048576,
668
702
  maxTokens: 65536,
669
703
  },
704
+ "gemini-3.1-pro-preview": {
705
+ id: "gemini-3.1-pro-preview",
706
+ name: "Gemini 3.1 Pro Preview",
707
+ api: "google-generative-ai",
708
+ provider: "google",
709
+ baseUrl: "https://generativelanguage.googleapis.com/v1beta",
710
+ reasoning: true,
711
+ input: ["text", "image"],
712
+ cost: {
713
+ input: 2,
714
+ output: 12,
715
+ cacheRead: 0.2,
716
+ cacheWrite: 0,
717
+ },
718
+ contextWindow: 1048576,
719
+ maxTokens: 65536,
720
+ },
670
721
  "gemini-1.5-flash": {
671
722
  id: "gemini-1.5-flash",
672
723
  name: "Gemini 1.5 Flash",
@@ -754,6 +805,23 @@ export const MODELS = {
754
805
  contextWindow: 1047576,
755
806
  maxTokens: 32768,
756
807
  },
808
+ "gpt-5.3-codex-spark": {
809
+ id: "gpt-5.3-codex-spark",
810
+ name: "GPT-5.3 Codex Spark",
811
+ api: "openai-responses",
812
+ provider: "openai",
813
+ baseUrl: "https://api.openai.com/v1",
814
+ reasoning: true,
815
+ input: ["text", "image"],
816
+ cost: {
817
+ input: 1.75,
818
+ output: 14,
819
+ cacheRead: 0.175,
820
+ cacheWrite: 0,
821
+ },
822
+ contextWindow: 128000,
823
+ maxTokens: 32000,
824
+ },
757
825
  "gpt-4": {
758
826
  id: "gpt-4",
759
827
  name: "GPT-4",
@@ -1600,8 +1668,8 @@ export const MODELS = {
1600
1668
  reasoning: false,
1601
1669
  input: ["text"],
1602
1670
  cost: {
1603
- input: 0,
1604
- output: 0,
1671
+ input: 2.25,
1672
+ output: 2.75,
1605
1673
  cacheRead: 0,
1606
1674
  cacheWrite: 0,
1607
1675
  },
@@ -1625,6 +1693,23 @@ export const MODELS = {
1625
1693
  contextWindow: 131000,
1626
1694
  maxTokens: 32000,
1627
1695
  },
1696
+ "llama3.1-8b": {
1697
+ id: "llama3.1-8b",
1698
+ name: "Llama 3.1 8B",
1699
+ api: "openai-completions",
1700
+ provider: "cerebras",
1701
+ baseUrl: "https://api.cerebras.ai/v1",
1702
+ reasoning: false,
1703
+ input: ["text"],
1704
+ cost: {
1705
+ input: 0.1,
1706
+ output: 0.1,
1707
+ cacheRead: 0,
1708
+ cacheWrite: 0,
1709
+ },
1710
+ contextWindow: 32000,
1711
+ maxTokens: 8000,
1712
+ },
1628
1713
  "gpt-oss-120b": {
1629
1714
  id: "gpt-oss-120b",
1630
1715
  name: "GPT OSS 120B",
@@ -2037,6 +2122,23 @@ export const MODELS = {
2037
2122
  contextWindow: 204800,
2038
2123
  maxTokens: 131072,
2039
2124
  },
2125
+ "glm-5": {
2126
+ id: "glm-5",
2127
+ name: "GLM-5",
2128
+ api: "anthropic-messages",
2129
+ provider: "zai",
2130
+ baseUrl: "https://api.z.ai/api/anthropic",
2131
+ reasoning: true,
2132
+ input: ["text"],
2133
+ cost: {
2134
+ input: 1,
2135
+ output: 3.2,
2136
+ cacheRead: 0.2,
2137
+ cacheWrite: 0,
2138
+ },
2139
+ contextWindow: 204800,
2140
+ maxTokens: 131072,
2141
+ },
2040
2142
  "glm-4.5-flash": {
2041
2143
  id: "glm-4.5-flash",
2042
2144
  name: "GLM-4.5-Flash",
@@ -2602,6 +2704,23 @@ export const MODELS = {
2602
2704
  contextWindow: 204800,
2603
2705
  maxTokens: 131072,
2604
2706
  },
2707
+ "glm-5": {
2708
+ id: "glm-5",
2709
+ name: "GLM-5",
2710
+ api: "openai-completions",
2711
+ provider: "opencode",
2712
+ baseUrl: "https://opencode.ai/zen/v1",
2713
+ reasoning: true,
2714
+ input: ["text"],
2715
+ cost: {
2716
+ input: 1,
2717
+ output: 3.2,
2718
+ cacheRead: 0.2,
2719
+ cacheWrite: 0,
2720
+ },
2721
+ contextWindow: 204800,
2722
+ maxTokens: 131072,
2723
+ },
2605
2724
  "qwen3-coder": {
2606
2725
  id: "qwen3-coder",
2607
2726
  name: "Qwen3 Coder",
@@ -2704,6 +2823,23 @@ export const MODELS = {
2704
2823
  contextWindow: 200000,
2705
2824
  maxTokens: 64000,
2706
2825
  },
2826
+ "claude-sonnet-4-6": {
2827
+ id: "claude-sonnet-4-6",
2828
+ name: "Claude Sonnet 4.6",
2829
+ api: "openai-completions",
2830
+ provider: "opencode",
2831
+ baseUrl: "https://opencode.ai/zen/v1",
2832
+ reasoning: true,
2833
+ input: ["text", "image"],
2834
+ cost: {
2835
+ input: 3,
2836
+ output: 15,
2837
+ cacheRead: 0.3,
2838
+ cacheWrite: 3.75,
2839
+ },
2840
+ contextWindow: 1000000,
2841
+ maxTokens: 64000,
2842
+ },
2707
2843
  "claude-opus-4-6": {
2708
2844
  id: "claude-opus-4-6",
2709
2845
  name: "Claude Opus 4.6",
@@ -2770,7 +2906,7 @@ export const MODELS = {
2770
2906
  cacheWrite: 0,
2771
2907
  },
2772
2908
  contextWindow: 262144,
2773
- maxTokens: 262144,
2909
+ maxTokens: 65536,
2774
2910
  },
2775
2911
  "gemini-3-pro": {
2776
2912
  id: "gemini-3-pro",
@@ -2840,6 +2976,40 @@ export const MODELS = {
2840
2976
  contextWindow: 262144,
2841
2977
  maxTokens: 262144,
2842
2978
  },
2979
+ "glm-5-free": {
2980
+ id: "glm-5-free",
2981
+ name: "GLM-5 Free",
2982
+ api: "openai-completions",
2983
+ provider: "opencode",
2984
+ baseUrl: "https://opencode.ai/zen/v1",
2985
+ reasoning: true,
2986
+ input: ["text"],
2987
+ cost: {
2988
+ input: 0,
2989
+ output: 0,
2990
+ cacheRead: 0,
2991
+ cacheWrite: 0,
2992
+ },
2993
+ contextWindow: 204800,
2994
+ maxTokens: 131072,
2995
+ },
2996
+ "gemini-3.1-pro": {
2997
+ id: "gemini-3.1-pro",
2998
+ name: "Gemini 3.1 Pro Preview",
2999
+ api: "openai-completions",
3000
+ provider: "opencode",
3001
+ baseUrl: "https://opencode.ai/zen/v1",
3002
+ reasoning: true,
3003
+ input: ["text", "image"],
3004
+ cost: {
3005
+ input: 2,
3006
+ output: 12,
3007
+ cacheRead: 0.2,
3008
+ cacheWrite: 0,
3009
+ },
3010
+ contextWindow: 1048576,
3011
+ maxTokens: 65536,
3012
+ },
2843
3013
  "gpt-5.1": {
2844
3014
  id: "gpt-5.1",
2845
3015
  name: "GPT-5.1",
@@ -3097,6 +3267,40 @@ export const MODELS = {
3097
3267
  contextWindow: 204800,
3098
3268
  maxTokens: 131072,
3099
3269
  },
3270
+ "minimax-m2.5-free": {
3271
+ id: "minimax-m2.5-free",
3272
+ name: "MiniMax M2.5 Free",
3273
+ api: "openai-completions",
3274
+ provider: "opencode",
3275
+ baseUrl: "https://opencode.ai/zen/v1",
3276
+ reasoning: true,
3277
+ input: ["text"],
3278
+ cost: {
3279
+ input: 0,
3280
+ output: 0,
3281
+ cacheRead: 0,
3282
+ cacheWrite: 0,
3283
+ },
3284
+ contextWindow: 204800,
3285
+ maxTokens: 131072,
3286
+ },
3287
+ "minimax-m2.5": {
3288
+ id: "minimax-m2.5",
3289
+ name: "MiniMax M2.5",
3290
+ api: "openai-completions",
3291
+ provider: "opencode",
3292
+ baseUrl: "https://opencode.ai/zen/v1",
3293
+ reasoning: true,
3294
+ input: ["text"],
3295
+ cost: {
3296
+ input: 0.3,
3297
+ output: 1.2,
3298
+ cacheRead: 0.06,
3299
+ cacheWrite: 0,
3300
+ },
3301
+ contextWindow: 204800,
3302
+ maxTokens: 131072,
3303
+ },
3100
3304
  "gpt-5.2": {
3101
3305
  id: "gpt-5.2",
3102
3306
  name: "GPT-5.2",
@@ -3207,7 +3411,7 @@ export const MODELS = {
3207
3411
  cacheWrite: 0,
3208
3412
  },
3209
3413
  contextWindow: 128000,
3210
- maxTokens: 16000,
3414
+ maxTokens: 32000,
3211
3415
  },
3212
3416
  "gemini-3-pro-preview": {
3213
3417
  id: "gemini-3-pro-preview",
@@ -3244,7 +3448,7 @@ export const MODELS = {
3244
3448
  cacheWrite: 0,
3245
3449
  },
3246
3450
  contextWindow: 128000,
3247
- maxTokens: 100000,
3451
+ maxTokens: 128000,
3248
3452
  },
3249
3453
  "gpt-5.1": {
3250
3454
  id: "gpt-5.1",
@@ -3262,7 +3466,7 @@ export const MODELS = {
3262
3466
  cacheWrite: 0,
3263
3467
  },
3264
3468
  contextWindow: 128000,
3265
- maxTokens: 128000,
3469
+ maxTokens: 64000,
3266
3470
  },
3267
3471
  "gpt-4o": {
3268
3472
  id: "gpt-4o",
@@ -3299,7 +3503,7 @@ export const MODELS = {
3299
3503
  cacheRead: 0,
3300
3504
  cacheWrite: 0,
3301
3505
  },
3302
- contextWindow: 128000,
3506
+ contextWindow: 64000,
3303
3507
  maxTokens: 16384,
3304
3508
  },
3305
3509
  "gpt-5-mini": {
@@ -3320,6 +3524,25 @@ export const MODELS = {
3320
3524
  contextWindow: 128000,
3321
3525
  maxTokens: 64000,
3322
3526
  },
3527
+ "claude-sonnet-4.6": {
3528
+ id: "claude-sonnet-4.6",
3529
+ name: "Claude Sonnet 4.6",
3530
+ api: "openai-completions",
3531
+ provider: "github-copilot",
3532
+ baseUrl: "https://api.individual.githubcopilot.com",
3533
+ headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
3534
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
3535
+ reasoning: true,
3536
+ input: ["text", "image"],
3537
+ cost: {
3538
+ input: 0,
3539
+ output: 0,
3540
+ cacheRead: 0,
3541
+ cacheWrite: 0,
3542
+ },
3543
+ contextWindow: 128000,
3544
+ maxTokens: 32000,
3545
+ },
3323
3546
  "gemini-2.5-pro": {
3324
3547
  id: "gemini-2.5-pro",
3325
3548
  name: "Gemini 2.5 Pro",
@@ -3357,6 +3580,25 @@ export const MODELS = {
3357
3580
  contextWindow: 128000,
3358
3581
  maxTokens: 128000,
3359
3582
  },
3583
+ "gemini-3.1-pro-preview": {
3584
+ id: "gemini-3.1-pro-preview",
3585
+ name: "Gemini 3.1 Pro Preview",
3586
+ api: "openai-completions",
3587
+ provider: "github-copilot",
3588
+ baseUrl: "https://api.individual.githubcopilot.com",
3589
+ headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
3590
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
3591
+ reasoning: true,
3592
+ input: ["text", "image"],
3593
+ cost: {
3594
+ input: 0,
3595
+ output: 0,
3596
+ cacheRead: 0,
3597
+ cacheWrite: 0,
3598
+ },
3599
+ contextWindow: 128000,
3600
+ maxTokens: 64000,
3601
+ },
3360
3602
  "claude-sonnet-4": {
3361
3603
  id: "claude-sonnet-4",
3362
3604
  name: "Claude Sonnet 4",
@@ -3411,7 +3653,7 @@ export const MODELS = {
3411
3653
  cacheWrite: 0,
3412
3654
  },
3413
3655
  contextWindow: 128000,
3414
- maxTokens: 16000,
3656
+ maxTokens: 32000,
3415
3657
  },
3416
3658
  "gpt-5.2": {
3417
3659
  id: "gpt-5.2",
@@ -3448,7 +3690,7 @@ export const MODELS = {
3448
3690
  cacheWrite: 0,
3449
3691
  },
3450
3692
  contextWindow: 128000,
3451
- maxTokens: 16000,
3693
+ maxTokens: 32000,
3452
3694
  },
3453
3695
  "claude-opus-4.6": {
3454
3696
  id: "claude-opus-4.6",
@@ -3471,68 +3713,170 @@ export const MODELS = {
3471
3713
  },
3472
3714
  },
3473
3715
  "openrouter": {
3474
- "openrouter/pony-alpha": {
3475
- id: "openrouter/pony-alpha",
3476
- name: "Pony Alpha",
3716
+ "google/gemini-3.1-pro-preview": {
3717
+ id: "google/gemini-3.1-pro-preview",
3718
+ name: "Google: Gemini 3.1 Pro Preview",
3477
3719
  api: "openai-completions",
3478
3720
  provider: "openrouter",
3479
3721
  baseUrl: "https://openrouter.ai/api/v1",
3480
3722
  reasoning: true,
3481
- input: ["text"],
3723
+ input: ["text", "image"],
3482
3724
  cost: {
3483
- input: 0,
3484
- output: 0,
3485
- cacheRead: 0,
3486
- cacheWrite: 0,
3725
+ input: 2,
3726
+ output: 12,
3727
+ cacheRead: 0.19999999999999998,
3728
+ cacheWrite: 0.375,
3487
3729
  },
3488
- contextWindow: 200000,
3489
- maxTokens: 131000,
3730
+ contextWindow: 1048576,
3731
+ maxTokens: 65536,
3490
3732
  },
3491
- "anthropic/claude-opus-4.6": {
3492
- id: "anthropic/claude-opus-4.6",
3493
- name: "Anthropic: Claude Opus 4.6",
3733
+ "anthropic/claude-sonnet-4.6": {
3734
+ id: "anthropic/claude-sonnet-4.6",
3735
+ name: "Anthropic: Claude Sonnet 4.6",
3494
3736
  api: "openai-completions",
3495
3737
  provider: "openrouter",
3496
3738
  baseUrl: "https://openrouter.ai/api/v1",
3497
3739
  reasoning: true,
3498
3740
  input: ["text", "image"],
3499
3741
  cost: {
3500
- input: 5,
3501
- output: 25,
3502
- cacheRead: 0.5,
3503
- cacheWrite: 6.25,
3742
+ input: 3,
3743
+ output: 15,
3744
+ cacheRead: 0.3,
3745
+ cacheWrite: 3.75,
3504
3746
  },
3505
3747
  contextWindow: 1000000,
3506
3748
  maxTokens: 128000,
3507
3749
  },
3508
- "qwen/qwen3-coder-next": {
3509
- id: "qwen/qwen3-coder-next",
3510
- name: "Qwen: Qwen3 Coder Next",
3750
+ "qwen/qwen3.5-plus-02-15": {
3751
+ id: "qwen/qwen3.5-plus-02-15",
3752
+ name: "Qwen: Qwen3.5 Plus 2026-02-15",
3511
3753
  api: "openai-completions",
3512
3754
  provider: "openrouter",
3513
3755
  baseUrl: "https://openrouter.ai/api/v1",
3514
- reasoning: false,
3515
- input: ["text"],
3756
+ reasoning: true,
3757
+ input: ["text", "image"],
3516
3758
  cost: {
3517
- input: 0.07,
3518
- output: 0.3,
3759
+ input: 0.39999999999999997,
3760
+ output: 2.4,
3519
3761
  cacheRead: 0,
3520
3762
  cacheWrite: 0,
3521
3763
  },
3522
- contextWindow: 262144,
3764
+ contextWindow: 1000000,
3523
3765
  maxTokens: 65536,
3524
3766
  },
3525
- "openrouter/free": {
3526
- id: "openrouter/free",
3527
- name: "Free Models Router",
3767
+ "qwen/qwen3.5-397b-a17b": {
3768
+ id: "qwen/qwen3.5-397b-a17b",
3769
+ name: "Qwen: Qwen3.5 397B A17B",
3528
3770
  api: "openai-completions",
3529
3771
  provider: "openrouter",
3530
3772
  baseUrl: "https://openrouter.ai/api/v1",
3531
3773
  reasoning: true,
3532
3774
  input: ["text", "image"],
3533
3775
  cost: {
3534
- input: 0,
3535
- output: 0,
3776
+ input: 0.15,
3777
+ output: 1,
3778
+ cacheRead: 0.15,
3779
+ cacheWrite: 0,
3780
+ },
3781
+ contextWindow: 262144,
3782
+ maxTokens: 65536,
3783
+ },
3784
+ "minimax/minimax-m2.5": {
3785
+ id: "minimax/minimax-m2.5",
3786
+ name: "MiniMax: MiniMax M2.5",
3787
+ api: "openai-completions",
3788
+ provider: "openrouter",
3789
+ baseUrl: "https://openrouter.ai/api/v1",
3790
+ reasoning: true,
3791
+ input: ["text"],
3792
+ cost: {
3793
+ input: 0.3,
3794
+ output: 1.1,
3795
+ cacheRead: 0.15,
3796
+ cacheWrite: 0,
3797
+ },
3798
+ contextWindow: 196608,
3799
+ maxTokens: 65536,
3800
+ },
3801
+ "z-ai/glm-5": {
3802
+ id: "z-ai/glm-5",
3803
+ name: "Z.ai: GLM 5",
3804
+ api: "openai-completions",
3805
+ provider: "openrouter",
3806
+ baseUrl: "https://openrouter.ai/api/v1",
3807
+ reasoning: true,
3808
+ input: ["text"],
3809
+ cost: {
3810
+ input: 0.95,
3811
+ output: 2.5500000000000003,
3812
+ cacheRead: 0,
3813
+ cacheWrite: 0,
3814
+ },
3815
+ contextWindow: 204800,
3816
+ maxTokens: 131072,
3817
+ },
3818
+ "qwen/qwen3-max-thinking": {
3819
+ id: "qwen/qwen3-max-thinking",
3820
+ name: "Qwen: Qwen3 Max Thinking",
3821
+ api: "openai-completions",
3822
+ provider: "openrouter",
3823
+ baseUrl: "https://openrouter.ai/api/v1",
3824
+ reasoning: true,
3825
+ input: ["text"],
3826
+ cost: {
3827
+ input: 1.2,
3828
+ output: 6,
3829
+ cacheRead: 0,
3830
+ cacheWrite: 0,
3831
+ },
3832
+ contextWindow: 262144,
3833
+ maxTokens: 32768,
3834
+ },
3835
+ "anthropic/claude-opus-4.6": {
3836
+ id: "anthropic/claude-opus-4.6",
3837
+ name: "Anthropic: Claude Opus 4.6",
3838
+ api: "openai-completions",
3839
+ provider: "openrouter",
3840
+ baseUrl: "https://openrouter.ai/api/v1",
3841
+ reasoning: true,
3842
+ input: ["text", "image"],
3843
+ cost: {
3844
+ input: 5,
3845
+ output: 25,
3846
+ cacheRead: 0.5,
3847
+ cacheWrite: 6.25,
3848
+ },
3849
+ contextWindow: 1000000,
3850
+ maxTokens: 128000,
3851
+ },
3852
+ "qwen/qwen3-coder-next": {
3853
+ id: "qwen/qwen3-coder-next",
3854
+ name: "Qwen: Qwen3 Coder Next",
3855
+ api: "openai-completions",
3856
+ provider: "openrouter",
3857
+ baseUrl: "https://openrouter.ai/api/v1",
3858
+ reasoning: false,
3859
+ input: ["text"],
3860
+ cost: {
3861
+ input: 0.12,
3862
+ output: 0.75,
3863
+ cacheRead: 0.06,
3864
+ cacheWrite: 0,
3865
+ },
3866
+ contextWindow: 262144,
3867
+ maxTokens: 65536,
3868
+ },
3869
+ "openrouter/free": {
3870
+ id: "openrouter/free",
3871
+ name: "Free Models Router",
3872
+ api: "openai-completions",
3873
+ provider: "openrouter",
3874
+ baseUrl: "https://openrouter.ai/api/v1",
3875
+ reasoning: true,
3876
+ input: ["text", "image"],
3877
+ cost: {
3878
+ input: 0,
3879
+ output: 0,
3536
3880
  cacheRead: 0,
3537
3881
  cacheWrite: 0,
3538
3882
  },
@@ -3556,6 +3900,23 @@ export const MODELS = {
3556
3900
  contextWindow: 256000,
3557
3901
  maxTokens: 256000,
3558
3902
  },
3903
+ "stepfun/step-3.5-flash": {
3904
+ id: "stepfun/step-3.5-flash",
3905
+ name: "StepFun: Step 3.5 Flash",
3906
+ api: "openai-completions",
3907
+ provider: "openrouter",
3908
+ baseUrl: "https://openrouter.ai/api/v1",
3909
+ reasoning: true,
3910
+ input: ["text"],
3911
+ cost: {
3912
+ input: 0.09999999999999999,
3913
+ output: 0.3,
3914
+ cacheRead: 0.02,
3915
+ cacheWrite: 0,
3916
+ },
3917
+ contextWindow: 256000,
3918
+ maxTokens: 256000,
3919
+ },
3559
3920
  "arcee-ai/trinity-large-preview:free": {
3560
3921
  id: "arcee-ai/trinity-large-preview:free",
3561
3922
  name: "Arcee AI: Trinity Large Preview (free)",
@@ -3583,8 +3944,8 @@ export const MODELS = {
3583
3944
  input: ["text", "image"],
3584
3945
  cost: {
3585
3946
  input: 0.44999999999999996,
3586
- output: 2.5,
3587
- cacheRead: 0,
3947
+ output: 2.2,
3948
+ cacheRead: 0.22499999999999998,
3588
3949
  cacheWrite: 0,
3589
3950
  },
3590
3951
  contextWindow: 262144,
@@ -3609,7 +3970,7 @@ export const MODELS = {
3609
3970
  },
3610
3971
  "z-ai/glm-4.7-flash": {
3611
3972
  id: "z-ai/glm-4.7-flash",
3612
- name: "Z.AI: GLM 4.7 Flash",
3973
+ name: "Z.ai: GLM 4.7 Flash",
3613
3974
  api: "openai-completions",
3614
3975
  provider: "openrouter",
3615
3976
  baseUrl: "https://openrouter.ai/api/v1",
@@ -3711,16 +4072,16 @@ export const MODELS = {
3711
4072
  },
3712
4073
  "z-ai/glm-4.7": {
3713
4074
  id: "z-ai/glm-4.7",
3714
- name: "Z.AI: GLM 4.7",
4075
+ name: "Z.ai: GLM 4.7",
3715
4076
  api: "openai-completions",
3716
4077
  provider: "openrouter",
3717
4078
  baseUrl: "https://openrouter.ai/api/v1",
3718
4079
  reasoning: true,
3719
4080
  input: ["text"],
3720
4081
  cost: {
3721
- input: 0.39999999999999997,
3722
- output: 1.5,
3723
- cacheRead: 0,
4082
+ input: 0.38,
4083
+ output: 1.7,
4084
+ cacheRead: 0.19,
3724
4085
  cacheWrite: 0,
3725
4086
  },
3726
4087
  contextWindow: 202752,
@@ -3771,11 +4132,11 @@ export const MODELS = {
3771
4132
  cost: {
3772
4133
  input: 0.09,
3773
4134
  output: 0.29,
3774
- cacheRead: 0,
4135
+ cacheRead: 0.045,
3775
4136
  cacheWrite: 0,
3776
4137
  },
3777
4138
  contextWindow: 262144,
3778
- maxTokens: 4096,
4139
+ maxTokens: 65536,
3779
4140
  },
3780
4141
  "nvidia/nemotron-3-nano-30b-a3b:free": {
3781
4142
  id: "nvidia/nemotron-3-nano-30b-a3b:free",
@@ -3871,13 +4232,13 @@ export const MODELS = {
3871
4232
  reasoning: false,
3872
4233
  input: ["text"],
3873
4234
  cost: {
3874
- input: 0.049999999999999996,
3875
- output: 0.22,
4235
+ input: 0.39999999999999997,
4236
+ output: 2,
3876
4237
  cacheRead: 0,
3877
4238
  cacheWrite: 0,
3878
4239
  },
3879
4240
  contextWindow: 262144,
3880
- maxTokens: 65536,
4241
+ maxTokens: 4096,
3881
4242
  },
3882
4243
  "relace/relace-search": {
3883
4244
  id: "relace/relace-search",
@@ -3898,7 +4259,7 @@ export const MODELS = {
3898
4259
  },
3899
4260
  "z-ai/glm-4.6v": {
3900
4261
  id: "z-ai/glm-4.6v",
3901
- name: "Z.AI: GLM 4.6V",
4262
+ name: "Z.ai: GLM 4.6V",
3902
4263
  api: "openai-completions",
3903
4264
  provider: "openrouter",
3904
4265
  baseUrl: "https://openrouter.ai/api/v1",
@@ -4075,13 +4436,13 @@ export const MODELS = {
4075
4436
  reasoning: true,
4076
4437
  input: ["text"],
4077
4438
  cost: {
4078
- input: 0.25,
4439
+ input: 0.26,
4079
4440
  output: 0.38,
4080
- cacheRead: 0,
4441
+ cacheRead: 0.13,
4081
4442
  cacheWrite: 0,
4082
4443
  },
4083
4444
  contextWindow: 163840,
4084
- maxTokens: 65536,
4445
+ maxTokens: 4096,
4085
4446
  },
4086
4447
  "prime-intellect/intellect-3": {
4087
4448
  id: "prime-intellect/intellect-3",
@@ -4100,40 +4461,6 @@ export const MODELS = {
4100
4461
  contextWindow: 131072,
4101
4462
  maxTokens: 131072,
4102
4463
  },
4103
- "tngtech/tng-r1t-chimera:free": {
4104
- id: "tngtech/tng-r1t-chimera:free",
4105
- name: "TNG: R1T Chimera (free)",
4106
- api: "openai-completions",
4107
- provider: "openrouter",
4108
- baseUrl: "https://openrouter.ai/api/v1",
4109
- reasoning: true,
4110
- input: ["text"],
4111
- cost: {
4112
- input: 0,
4113
- output: 0,
4114
- cacheRead: 0,
4115
- cacheWrite: 0,
4116
- },
4117
- contextWindow: 163840,
4118
- maxTokens: 65536,
4119
- },
4120
- "tngtech/tng-r1t-chimera": {
4121
- id: "tngtech/tng-r1t-chimera",
4122
- name: "TNG: R1T Chimera",
4123
- api: "openai-completions",
4124
- provider: "openrouter",
4125
- baseUrl: "https://openrouter.ai/api/v1",
4126
- reasoning: true,
4127
- input: ["text"],
4128
- cost: {
4129
- input: 0.25,
4130
- output: 0.85,
4131
- cacheRead: 0,
4132
- cacheWrite: 0,
4133
- },
4134
- contextWindow: 163840,
4135
- maxTokens: 65536,
4136
- },
4137
4464
  "anthropic/claude-opus-4.5": {
4138
4465
  id: "anthropic/claude-opus-4.5",
4139
4466
  name: "Anthropic: Claude Opus 4.5",
@@ -4279,13 +4606,13 @@ export const MODELS = {
4279
4606
  reasoning: true,
4280
4607
  input: ["text"],
4281
4608
  cost: {
4282
- input: 0.39999999999999997,
4283
- output: 1.75,
4284
- cacheRead: 0,
4609
+ input: 0.47,
4610
+ output: 2,
4611
+ cacheRead: 0.14100000000000001,
4285
4612
  cacheWrite: 0,
4286
4613
  },
4287
- contextWindow: 262144,
4288
- maxTokens: 65535,
4614
+ contextWindow: 131072,
4615
+ maxTokens: 4096,
4289
4616
  },
4290
4617
  "amazon/nova-premier-v1": {
4291
4618
  id: "amazon/nova-premier-v1",
@@ -4372,6 +4699,23 @@ export const MODELS = {
4372
4699
  contextWindow: 196608,
4373
4700
  maxTokens: 65536,
4374
4701
  },
4702
+ "qwen/qwen3-vl-32b-instruct": {
4703
+ id: "qwen/qwen3-vl-32b-instruct",
4704
+ name: "Qwen: Qwen3 VL 32B Instruct",
4705
+ api: "openai-completions",
4706
+ provider: "openrouter",
4707
+ baseUrl: "https://openrouter.ai/api/v1",
4708
+ reasoning: false,
4709
+ input: ["text", "image"],
4710
+ cost: {
4711
+ input: 0.10400000000000001,
4712
+ output: 0.41600000000000004,
4713
+ cacheRead: 0,
4714
+ cacheWrite: 0,
4715
+ },
4716
+ contextWindow: 131072,
4717
+ maxTokens: 32768,
4718
+ },
4375
4719
  "openai/gpt-5-image-mini": {
4376
4720
  id: "openai/gpt-5-image-mini",
4377
4721
  name: "OpenAI: GPT-5 Image Mini",
@@ -4415,12 +4759,12 @@ export const MODELS = {
4415
4759
  reasoning: true,
4416
4760
  input: ["text", "image"],
4417
4761
  cost: {
4418
- input: 0.18,
4419
- output: 2.0999999999999996,
4762
+ input: 0.117,
4763
+ output: 1.365,
4420
4764
  cacheRead: 0,
4421
4765
  cacheWrite: 0,
4422
4766
  },
4423
- contextWindow: 256000,
4767
+ contextWindow: 131072,
4424
4768
  maxTokens: 32768,
4425
4769
  },
4426
4770
  "qwen/qwen3-vl-8b-instruct": {
@@ -4517,8 +4861,8 @@ export const MODELS = {
4517
4861
  reasoning: true,
4518
4862
  input: ["text", "image"],
4519
4863
  cost: {
4520
- input: 0.19999999999999998,
4521
- output: 1,
4864
+ input: 0,
4865
+ output: 0,
4522
4866
  cacheRead: 0,
4523
4867
  cacheWrite: 0,
4524
4868
  },
@@ -4534,13 +4878,13 @@ export const MODELS = {
4534
4878
  reasoning: false,
4535
4879
  input: ["text", "image"],
4536
4880
  cost: {
4537
- input: 0.15,
4538
- output: 0.6,
4539
- cacheRead: 0.075,
4881
+ input: 0.13,
4882
+ output: 0.52,
4883
+ cacheRead: 0,
4540
4884
  cacheWrite: 0,
4541
4885
  },
4542
- contextWindow: 262144,
4543
- maxTokens: 4096,
4886
+ contextWindow: 131072,
4887
+ maxTokens: 32768,
4544
4888
  },
4545
4889
  "openai/gpt-5-pro": {
4546
4890
  id: "openai/gpt-5-pro",
@@ -4561,7 +4905,7 @@ export const MODELS = {
4561
4905
  },
4562
4906
  "z-ai/glm-4.6": {
4563
4907
  id: "z-ai/glm-4.6",
4564
- name: "Z.AI: GLM 4.6",
4908
+ name: "Z.ai: GLM 4.6",
4565
4909
  api: "openai-completions",
4566
4910
  provider: "openrouter",
4567
4911
  baseUrl: "https://openrouter.ai/api/v1",
@@ -4569,16 +4913,16 @@ export const MODELS = {
4569
4913
  input: ["text"],
4570
4914
  cost: {
4571
4915
  input: 0.35,
4572
- output: 1.5,
4916
+ output: 1.71,
4573
4917
  cacheRead: 0,
4574
4918
  cacheWrite: 0,
4575
4919
  },
4576
4920
  contextWindow: 202752,
4577
- maxTokens: 65536,
4921
+ maxTokens: 131072,
4578
4922
  },
4579
4923
  "z-ai/glm-4.6:exacto": {
4580
4924
  id: "z-ai/glm-4.6:exacto",
4581
- name: "Z.AI: GLM 4.6 (exacto)",
4925
+ name: "Z.ai: GLM 4.6 (exacto)",
4582
4926
  api: "openai-completions",
4583
4927
  provider: "openrouter",
4584
4928
  baseUrl: "https://openrouter.ai/api/v1",
@@ -4627,23 +4971,6 @@ export const MODELS = {
4627
4971
  contextWindow: 163840,
4628
4972
  maxTokens: 65536,
4629
4973
  },
4630
- "google/gemini-2.5-flash-preview-09-2025": {
4631
- id: "google/gemini-2.5-flash-preview-09-2025",
4632
- name: "Google: Gemini 2.5 Flash Preview 09-2025",
4633
- api: "openai-completions",
4634
- provider: "openrouter",
4635
- baseUrl: "https://openrouter.ai/api/v1",
4636
- reasoning: true,
4637
- input: ["text", "image"],
4638
- cost: {
4639
- input: 0.3,
4640
- output: 2.5,
4641
- cacheRead: 0.03,
4642
- cacheWrite: 0.08333333333333334,
4643
- },
4644
- contextWindow: 1048576,
4645
- maxTokens: 65536,
4646
- },
4647
4974
  "google/gemini-2.5-flash-lite-preview-09-2025": {
4648
4975
  id: "google/gemini-2.5-flash-lite-preview-09-2025",
4649
4976
  name: "Google: Gemini 2.5 Flash Lite Preview 09-2025",
@@ -4670,13 +4997,13 @@ export const MODELS = {
4670
4997
  reasoning: true,
4671
4998
  input: ["text", "image"],
4672
4999
  cost: {
4673
- input: 0.44999999999999996,
4674
- output: 3.5,
5000
+ input: 0,
5001
+ output: 0,
4675
5002
  cacheRead: 0,
4676
5003
  cacheWrite: 0,
4677
5004
  },
4678
- contextWindow: 262144,
4679
- maxTokens: 262144,
5005
+ contextWindow: 131072,
5006
+ maxTokens: 32768,
4680
5007
  },
4681
5008
  "qwen/qwen3-vl-235b-a22b-instruct": {
4682
5009
  id: "qwen/qwen3-vl-235b-a22b-instruct",
@@ -4709,7 +5036,7 @@ export const MODELS = {
4709
5036
  cacheRead: 0.24,
4710
5037
  cacheWrite: 0,
4711
5038
  },
4712
- contextWindow: 256000,
5039
+ contextWindow: 262144,
4713
5040
  maxTokens: 32768,
4714
5041
  },
4715
5042
  "qwen/qwen3-coder-plus": {
@@ -4723,10 +5050,10 @@ export const MODELS = {
4723
5050
  cost: {
4724
5051
  input: 1,
4725
5052
  output: 5,
4726
- cacheRead: 0.09999999999999999,
5053
+ cacheRead: 0.19999999999999998,
4727
5054
  cacheWrite: 0,
4728
5055
  },
4729
- contextWindow: 128000,
5056
+ contextWindow: 1000000,
4730
5057
  maxTokens: 65536,
4731
5058
  },
4732
5059
  "openai/gpt-5-codex": {
@@ -4825,10 +5152,10 @@ export const MODELS = {
4825
5152
  cost: {
4826
5153
  input: 0.3,
4827
5154
  output: 1.5,
4828
- cacheRead: 0.08,
5155
+ cacheRead: 0.06,
4829
5156
  cacheWrite: 0,
4830
5157
  },
4831
- contextWindow: 128000,
5158
+ contextWindow: 1000000,
4832
5159
  maxTokens: 65536,
4833
5160
  },
4834
5161
  "qwen/qwen3-next-80b-a3b-thinking": {
@@ -4909,7 +5236,7 @@ export const MODELS = {
4909
5236
  input: ["text"],
4910
5237
  cost: {
4911
5238
  input: 0.39999999999999997,
4912
- output: 4,
5239
+ output: 1.2,
4913
5240
  cacheRead: 0,
4914
5241
  cacheWrite: 0,
4915
5242
  },
@@ -4959,13 +5286,13 @@ export const MODELS = {
4959
5286
  reasoning: false,
4960
5287
  input: ["text"],
4961
5288
  cost: {
4962
- input: 0.39,
4963
- output: 1.9,
4964
- cacheRead: 0,
5289
+ input: 0.39999999999999997,
5290
+ output: 2,
5291
+ cacheRead: 0.15,
4965
5292
  cacheWrite: 0,
4966
5293
  },
4967
- contextWindow: 262144,
4968
- maxTokens: 262144,
5294
+ contextWindow: 131072,
5295
+ maxTokens: 4096,
4969
5296
  },
4970
5297
  "moonshotai/kimi-k2-0905:exacto": {
4971
5298
  id: "moonshotai/kimi-k2-0905:exacto",
@@ -4984,23 +5311,6 @@ export const MODELS = {
4984
5311
  contextWindow: 262144,
4985
5312
  maxTokens: 4096,
4986
5313
  },
4987
- "stepfun-ai/step3": {
4988
- id: "stepfun-ai/step3",
4989
- name: "StepFun: Step3",
4990
- api: "openai-completions",
4991
- provider: "openrouter",
4992
- baseUrl: "https://openrouter.ai/api/v1",
4993
- reasoning: true,
4994
- input: ["text", "image"],
4995
- cost: {
4996
- input: 0.5700000000000001,
4997
- output: 1.42,
4998
- cacheRead: 0,
4999
- cacheWrite: 0,
5000
- },
5001
- contextWindow: 65536,
5002
- maxTokens: 65536,
5003
- },
5004
5314
  "qwen/qwen3-30b-a3b-thinking-2507": {
5005
5315
  id: "qwen/qwen3-30b-a3b-thinking-2507",
5006
5316
  name: "Qwen: Qwen3 30B A3B Thinking 2507",
@@ -5035,23 +5345,6 @@ export const MODELS = {
5035
5345
  contextWindow: 256000,
5036
5346
  maxTokens: 10000,
5037
5347
  },
5038
- "nousresearch/hermes-4-70b": {
5039
- id: "nousresearch/hermes-4-70b",
5040
- name: "Nous: Hermes 4 70B",
5041
- api: "openai-completions",
5042
- provider: "openrouter",
5043
- baseUrl: "https://openrouter.ai/api/v1",
5044
- reasoning: true,
5045
- input: ["text"],
5046
- cost: {
5047
- input: 0.11,
5048
- output: 0.38,
5049
- cacheRead: 0,
5050
- cacheWrite: 0,
5051
- },
5052
- contextWindow: 131072,
5053
- maxTokens: 131072,
5054
- },
5055
5348
  "deepseek/deepseek-chat-v3.1": {
5056
5349
  id: "deepseek/deepseek-chat-v3.1",
5057
5350
  name: "DeepSeek: DeepSeek V3.1",
@@ -5139,7 +5432,7 @@ export const MODELS = {
5139
5432
  },
5140
5433
  "z-ai/glm-4.5v": {
5141
5434
  id: "z-ai/glm-4.5v",
5142
- name: "Z.AI: GLM 4.5V",
5435
+ name: "Z.ai: GLM 4.5V",
5143
5436
  api: "openai-completions",
5144
5437
  provider: "openrouter",
5145
5438
  baseUrl: "https://openrouter.ai/api/v1",
@@ -5154,23 +5447,6 @@ export const MODELS = {
5154
5447
  contextWindow: 65536,
5155
5448
  maxTokens: 16384,
5156
5449
  },
5157
- "ai21/jamba-mini-1.7": {
5158
- id: "ai21/jamba-mini-1.7",
5159
- name: "AI21: Jamba Mini 1.7",
5160
- api: "openai-completions",
5161
- provider: "openrouter",
5162
- baseUrl: "https://openrouter.ai/api/v1",
5163
- reasoning: false,
5164
- input: ["text"],
5165
- cost: {
5166
- input: 0.19999999999999998,
5167
- output: 0.39999999999999997,
5168
- cacheRead: 0,
5169
- cacheWrite: 0,
5170
- },
5171
- contextWindow: 256000,
5172
- maxTokens: 4096,
5173
- },
5174
5450
  "ai21/jamba-large-1.7": {
5175
5451
  id: "ai21/jamba-large-1.7",
5176
5452
  name: "AI21: Jamba Large 1.7",
@@ -5316,13 +5592,13 @@ export const MODELS = {
5316
5592
  reasoning: true,
5317
5593
  input: ["text"],
5318
5594
  cost: {
5319
- input: 0.02,
5320
- output: 0.09999999999999999,
5595
+ input: 0.03,
5596
+ output: 0.14,
5321
5597
  cacheRead: 0,
5322
5598
  cacheWrite: 0,
5323
5599
  },
5324
5600
  contextWindow: 131072,
5325
- maxTokens: 131072,
5601
+ maxTokens: 4096,
5326
5602
  },
5327
5603
  "anthropic/claude-opus-4.1": {
5328
5604
  id: "anthropic/claude-opus-4.1",
@@ -5384,8 +5660,8 @@ export const MODELS = {
5384
5660
  reasoning: false,
5385
5661
  input: ["text"],
5386
5662
  cost: {
5387
- input: 0.08,
5388
- output: 0.33,
5663
+ input: 0.09,
5664
+ output: 0.3,
5389
5665
  cacheRead: 0,
5390
5666
  cacheWrite: 0,
5391
5667
  },
@@ -5394,24 +5670,24 @@ export const MODELS = {
5394
5670
  },
5395
5671
  "z-ai/glm-4.5": {
5396
5672
  id: "z-ai/glm-4.5",
5397
- name: "Z.AI: GLM 4.5",
5673
+ name: "Z.ai: GLM 4.5",
5398
5674
  api: "openai-completions",
5399
5675
  provider: "openrouter",
5400
5676
  baseUrl: "https://openrouter.ai/api/v1",
5401
5677
  reasoning: true,
5402
5678
  input: ["text"],
5403
5679
  cost: {
5404
- input: 0.35,
5405
- output: 1.55,
5680
+ input: 0.55,
5681
+ output: 2,
5406
5682
  cacheRead: 0,
5407
5683
  cacheWrite: 0,
5408
5684
  },
5409
- contextWindow: 131072,
5410
- maxTokens: 65536,
5685
+ contextWindow: 131000,
5686
+ maxTokens: 131000,
5411
5687
  },
5412
5688
  "z-ai/glm-4.5-air:free": {
5413
5689
  id: "z-ai/glm-4.5-air:free",
5414
- name: "Z.AI: GLM 4.5 Air (free)",
5690
+ name: "Z.ai: GLM 4.5 Air (free)",
5415
5691
  api: "openai-completions",
5416
5692
  provider: "openrouter",
5417
5693
  baseUrl: "https://openrouter.ai/api/v1",
@@ -5428,20 +5704,20 @@ export const MODELS = {
5428
5704
  },
5429
5705
  "z-ai/glm-4.5-air": {
5430
5706
  id: "z-ai/glm-4.5-air",
5431
- name: "Z.AI: GLM 4.5 Air",
5707
+ name: "Z.ai: GLM 4.5 Air",
5432
5708
  api: "openai-completions",
5433
5709
  provider: "openrouter",
5434
5710
  baseUrl: "https://openrouter.ai/api/v1",
5435
5711
  reasoning: true,
5436
5712
  input: ["text"],
5437
5713
  cost: {
5438
- input: 0.049999999999999996,
5439
- output: 0.22,
5440
- cacheRead: 0,
5714
+ input: 0.13,
5715
+ output: 0.85,
5716
+ cacheRead: 0.024999999999999998,
5441
5717
  cacheWrite: 0,
5442
5718
  },
5443
5719
  contextWindow: 131072,
5444
- maxTokens: 131072,
5720
+ maxTokens: 98304,
5445
5721
  },
5446
5722
  "qwen/qwen3-235b-a22b-thinking-2507": {
5447
5723
  id: "qwen/qwen3-235b-a22b-thinking-2507",
@@ -5452,17 +5728,17 @@ export const MODELS = {
5452
5728
  reasoning: true,
5453
5729
  input: ["text"],
5454
5730
  cost: {
5455
- input: 0.11,
5456
- output: 0.6,
5731
+ input: 0,
5732
+ output: 0,
5457
5733
  cacheRead: 0,
5458
5734
  cacheWrite: 0,
5459
5735
  },
5460
- contextWindow: 262144,
5461
- maxTokens: 262144,
5736
+ contextWindow: 131072,
5737
+ maxTokens: 4096,
5462
5738
  },
5463
5739
  "z-ai/glm-4-32b": {
5464
5740
  id: "z-ai/glm-4-32b",
5465
- name: "Z.AI: GLM 4 32B ",
5741
+ name: "Z.ai: GLM 4 32B ",
5466
5742
  api: "openai-completions",
5467
5743
  provider: "openrouter",
5468
5744
  baseUrl: "https://openrouter.ai/api/v1",
@@ -5500,16 +5776,16 @@ export const MODELS = {
5500
5776
  api: "openai-completions",
5501
5777
  provider: "openrouter",
5502
5778
  baseUrl: "https://openrouter.ai/api/v1",
5503
- reasoning: true,
5779
+ reasoning: false,
5504
5780
  input: ["text"],
5505
5781
  cost: {
5506
5782
  input: 0.22,
5507
- output: 0.95,
5508
- cacheRead: 0,
5783
+ output: 1,
5784
+ cacheRead: 0.022,
5509
5785
  cacheWrite: 0,
5510
5786
  },
5511
5787
  contextWindow: 262144,
5512
- maxTokens: 262144,
5788
+ maxTokens: 4096,
5513
5789
  },
5514
5790
  "qwen/qwen3-coder:exacto": {
5515
5791
  id: "qwen/qwen3-coder:exacto",
@@ -5641,7 +5917,7 @@ export const MODELS = {
5641
5917
  cost: {
5642
5918
  input: 0.25,
5643
5919
  output: 0.85,
5644
- cacheRead: 0,
5920
+ cacheRead: 0.125,
5645
5921
  cacheWrite: 0,
5646
5922
  },
5647
5923
  contextWindow: 163840,
@@ -5675,7 +5951,7 @@ export const MODELS = {
5675
5951
  cost: {
5676
5952
  input: 0.06,
5677
5953
  output: 0.18,
5678
- cacheRead: 0,
5954
+ cacheRead: 0.03,
5679
5955
  cacheWrite: 0,
5680
5956
  },
5681
5957
  contextWindow: 131072,
@@ -5811,7 +6087,7 @@ export const MODELS = {
5811
6087
  cost: {
5812
6088
  input: 0.39999999999999997,
5813
6089
  output: 1.75,
5814
- cacheRead: 0,
6090
+ cacheRead: 0.19999999999999998,
5815
6091
  cacheWrite: 0,
5816
6092
  },
5817
6093
  contextWindow: 163840,
@@ -5851,23 +6127,6 @@ export const MODELS = {
5851
6127
  contextWindow: 1000000,
5852
6128
  maxTokens: 64000,
5853
6129
  },
5854
- "nousresearch/deephermes-3-mistral-24b-preview": {
5855
- id: "nousresearch/deephermes-3-mistral-24b-preview",
5856
- name: "Nous: DeepHermes 3 Mistral 24B Preview",
5857
- api: "openai-completions",
5858
- provider: "openrouter",
5859
- baseUrl: "https://openrouter.ai/api/v1",
5860
- reasoning: true,
5861
- input: ["text"],
5862
- cost: {
5863
- input: 0.02,
5864
- output: 0.09999999999999999,
5865
- cacheRead: 0,
5866
- cacheWrite: 0,
5867
- },
5868
- contextWindow: 32768,
5869
- maxTokens: 32768,
5870
- },
5871
6130
  "mistralai/mistral-medium-3": {
5872
6131
  id: "mistralai/mistral-medium-3",
5873
6132
  name: "Mistral: Mistral Medium 3",
@@ -5962,8 +6221,8 @@ export const MODELS = {
5962
6221
  reasoning: true,
5963
6222
  input: ["text"],
5964
6223
  cost: {
5965
- input: 0.06,
5966
- output: 0.22,
6224
+ input: 0.08,
6225
+ output: 0.28,
5967
6226
  cacheRead: 0,
5968
6227
  cacheWrite: 0,
5969
6228
  },
@@ -5996,8 +6255,8 @@ export const MODELS = {
5996
6255
  reasoning: true,
5997
6256
  input: ["text"],
5998
6257
  cost: {
5999
- input: 0.049999999999999996,
6000
- output: 0.22,
6258
+ input: 0.06,
6259
+ output: 0.24,
6001
6260
  cacheRead: 0,
6002
6261
  cacheWrite: 0,
6003
6262
  },
@@ -6015,7 +6274,7 @@ export const MODELS = {
6015
6274
  cost: {
6016
6275
  input: 0.08,
6017
6276
  output: 0.24,
6018
- cacheRead: 0,
6277
+ cacheRead: 0.04,
6019
6278
  cacheWrite: 0,
6020
6279
  },
6021
6280
  contextWindow: 40960,
@@ -6030,13 +6289,13 @@ export const MODELS = {
6030
6289
  reasoning: true,
6031
6290
  input: ["text"],
6032
6291
  cost: {
6033
- input: 0.19999999999999998,
6034
- output: 0.6,
6292
+ input: 0.45499999999999996,
6293
+ output: 1.8199999999999998,
6035
6294
  cacheRead: 0,
6036
6295
  cacheWrite: 0,
6037
6296
  },
6038
- contextWindow: 40960,
6039
- maxTokens: 4096,
6297
+ contextWindow: 131072,
6298
+ maxTokens: 8192,
6040
6299
  },
6041
6300
  "openai/o4-mini-high": {
6042
6301
  id: "openai/o4-mini-high",
@@ -6219,7 +6478,7 @@ export const MODELS = {
6219
6478
  cost: {
6220
6479
  input: 0.19,
6221
6480
  output: 0.87,
6222
- cacheRead: 0,
6481
+ cacheRead: 0.095,
6223
6482
  cacheWrite: 0,
6224
6483
  },
6225
6484
  contextWindow: 163840,
@@ -6242,23 +6501,6 @@ export const MODELS = {
6242
6501
  contextWindow: 128000,
6243
6502
  maxTokens: 4096,
6244
6503
  },
6245
- "mistralai/mistral-small-3.1-24b-instruct": {
6246
- id: "mistralai/mistral-small-3.1-24b-instruct",
6247
- name: "Mistral: Mistral Small 3.1 24B",
6248
- api: "openai-completions",
6249
- provider: "openrouter",
6250
- baseUrl: "https://openrouter.ai/api/v1",
6251
- reasoning: false,
6252
- input: ["text", "image"],
6253
- cost: {
6254
- input: 0.03,
6255
- output: 0.11,
6256
- cacheRead: 0,
6257
- cacheWrite: 0,
6258
- },
6259
- contextWindow: 131072,
6260
- maxTokens: 131072,
6261
- },
6262
6504
  "google/gemma-3-27b-it:free": {
6263
6505
  id: "google/gemma-3-27b-it:free",
6264
6506
  name: "Google: Gemma 3 27B (free)",
@@ -6287,7 +6529,7 @@ export const MODELS = {
6287
6529
  cost: {
6288
6530
  input: 0.04,
6289
6531
  output: 0.15,
6290
- cacheRead: 0,
6532
+ cacheRead: 0.02,
6291
6533
  cacheWrite: 0,
6292
6534
  },
6293
6535
  contextWindow: 128000,
@@ -6327,9 +6569,9 @@ export const MODELS = {
6327
6569
  contextWindow: 1048576,
6328
6570
  maxTokens: 8192,
6329
6571
  },
6330
- "anthropic/claude-3.7-sonnet:thinking": {
6331
- id: "anthropic/claude-3.7-sonnet:thinking",
6332
- name: "Anthropic: Claude 3.7 Sonnet (thinking)",
6572
+ "anthropic/claude-3.7-sonnet": {
6573
+ id: "anthropic/claude-3.7-sonnet",
6574
+ name: "Anthropic: Claude 3.7 Sonnet",
6333
6575
  api: "openai-completions",
6334
6576
  provider: "openrouter",
6335
6577
  baseUrl: "https://openrouter.ai/api/v1",
@@ -6344,9 +6586,9 @@ export const MODELS = {
6344
6586
  contextWindow: 200000,
6345
6587
  maxTokens: 64000,
6346
6588
  },
6347
- "anthropic/claude-3.7-sonnet": {
6348
- id: "anthropic/claude-3.7-sonnet",
6349
- name: "Anthropic: Claude 3.7 Sonnet",
6589
+ "anthropic/claude-3.7-sonnet:thinking": {
6590
+ id: "anthropic/claude-3.7-sonnet:thinking",
6591
+ name: "Anthropic: Claude 3.7 Sonnet (thinking)",
6350
6592
  api: "openai-completions",
6351
6593
  provider: "openrouter",
6352
6594
  baseUrl: "https://openrouter.ai/api/v1",
@@ -6427,7 +6669,7 @@ export const MODELS = {
6427
6669
  cacheWrite: 0,
6428
6670
  },
6429
6671
  contextWindow: 131072,
6430
- maxTokens: 8192,
6672
+ maxTokens: 32768,
6431
6673
  },
6432
6674
  "qwen/qwen-turbo": {
6433
6675
  id: "qwen/qwen-turbo",
@@ -6440,10 +6682,10 @@ export const MODELS = {
6440
6682
  cost: {
6441
6683
  input: 0.049999999999999996,
6442
6684
  output: 0.19999999999999998,
6443
- cacheRead: 0.02,
6685
+ cacheRead: 0.01,
6444
6686
  cacheWrite: 0,
6445
6687
  },
6446
- contextWindow: 1000000,
6688
+ contextWindow: 131072,
6447
6689
  maxTokens: 8192,
6448
6690
  },
6449
6691
  "qwen/qwen-plus": {
@@ -6457,11 +6699,11 @@ export const MODELS = {
6457
6699
  cost: {
6458
6700
  input: 0.39999999999999997,
6459
6701
  output: 1.2,
6460
- cacheRead: 0.16,
6702
+ cacheRead: 0.08,
6461
6703
  cacheWrite: 0,
6462
6704
  },
6463
- contextWindow: 131072,
6464
- maxTokens: 8192,
6705
+ contextWindow: 1000000,
6706
+ maxTokens: 32768,
6465
6707
  },
6466
6708
  "qwen/qwen-max": {
6467
6709
  id: "qwen/qwen-max",
@@ -6474,7 +6716,7 @@ export const MODELS = {
6474
6716
  cost: {
6475
6717
  input: 1.5999999999999999,
6476
6718
  output: 6.3999999999999995,
6477
- cacheRead: 0.64,
6719
+ cacheRead: 0.32,
6478
6720
  cacheWrite: 0,
6479
6721
  },
6480
6722
  contextWindow: 32768,
@@ -6506,13 +6748,13 @@ export const MODELS = {
6506
6748
  reasoning: false,
6507
6749
  input: ["text"],
6508
6750
  cost: {
6509
- input: 0.03,
6510
- output: 0.11,
6751
+ input: 0.049999999999999996,
6752
+ output: 0.08,
6511
6753
  cacheRead: 0,
6512
6754
  cacheWrite: 0,
6513
6755
  },
6514
6756
  contextWindow: 32768,
6515
- maxTokens: 32768,
6757
+ maxTokens: 16384,
6516
6758
  },
6517
6759
  "deepseek/deepseek-r1": {
6518
6760
  id: "deepseek/deepseek-r1",
@@ -6540,8 +6782,8 @@ export const MODELS = {
6540
6782
  reasoning: false,
6541
6783
  input: ["text"],
6542
6784
  cost: {
6543
- input: 0.3,
6544
- output: 1.2,
6785
+ input: 0.32,
6786
+ output: 0.8899999999999999,
6545
6787
  cacheRead: 0,
6546
6788
  cacheWrite: 0,
6547
6789
  },
@@ -6763,46 +7005,12 @@ export const MODELS = {
6763
7005
  cost: {
6764
7006
  input: 6,
6765
7007
  output: 30,
6766
- cacheRead: 0,
6767
- cacheWrite: 0,
7008
+ cacheRead: 0.6,
7009
+ cacheWrite: 7.5,
6768
7010
  },
6769
7011
  contextWindow: 200000,
6770
7012
  maxTokens: 8192,
6771
7013
  },
6772
- "mistralai/ministral-8b": {
6773
- id: "mistralai/ministral-8b",
6774
- name: "Mistral: Ministral 8B",
6775
- api: "openai-completions",
6776
- provider: "openrouter",
6777
- baseUrl: "https://openrouter.ai/api/v1",
6778
- reasoning: false,
6779
- input: ["text"],
6780
- cost: {
6781
- input: 0.09999999999999999,
6782
- output: 0.09999999999999999,
6783
- cacheRead: 0,
6784
- cacheWrite: 0,
6785
- },
6786
- contextWindow: 131072,
6787
- maxTokens: 4096,
6788
- },
6789
- "mistralai/ministral-3b": {
6790
- id: "mistralai/ministral-3b",
6791
- name: "Mistral: Ministral 3B",
6792
- api: "openai-completions",
6793
- provider: "openrouter",
6794
- baseUrl: "https://openrouter.ai/api/v1",
6795
- reasoning: false,
6796
- input: ["text"],
6797
- cost: {
6798
- input: 0.04,
6799
- output: 0.04,
6800
- cacheRead: 0,
6801
- cacheWrite: 0,
6802
- },
6803
- contextWindow: 131072,
6804
- maxTokens: 4096,
6805
- },
6806
7014
  "qwen/qwen-2.5-7b-instruct": {
6807
7015
  id: "qwen/qwen-2.5-7b-instruct",
6808
7016
  name: "Qwen: Qwen2.5 7B Instruct",
@@ -6871,23 +7079,6 @@ export const MODELS = {
6871
7079
  contextWindow: 32768,
6872
7080
  maxTokens: 16384,
6873
7081
  },
6874
- "mistralai/pixtral-12b": {
6875
- id: "mistralai/pixtral-12b",
6876
- name: "Mistral: Pixtral 12B",
6877
- api: "openai-completions",
6878
- provider: "openrouter",
6879
- baseUrl: "https://openrouter.ai/api/v1",
6880
- reasoning: false,
6881
- input: ["text", "image"],
6882
- cost: {
6883
- input: 0.09999999999999999,
6884
- output: 0.09999999999999999,
6885
- cacheRead: 0,
6886
- cacheWrite: 0,
6887
- },
6888
- contextWindow: 32768,
6889
- maxTokens: 4096,
6890
- },
6891
7082
  "cohere/command-r-08-2024": {
6892
7083
  id: "cohere/command-r-08-2024",
6893
7084
  name: "Cohere: Command R (08-2024)",
@@ -7245,23 +7436,6 @@ export const MODELS = {
7245
7436
  contextWindow: 128000,
7246
7437
  maxTokens: 4096,
7247
7438
  },
7248
- "mistralai/mistral-tiny": {
7249
- id: "mistralai/mistral-tiny",
7250
- name: "Mistral Tiny",
7251
- api: "openai-completions",
7252
- provider: "openrouter",
7253
- baseUrl: "https://openrouter.ai/api/v1",
7254
- reasoning: false,
7255
- input: ["text"],
7256
- cost: {
7257
- input: 0.25,
7258
- output: 0.25,
7259
- cacheRead: 0,
7260
- cacheWrite: 0,
7261
- },
7262
- contextWindow: 32768,
7263
- maxTokens: 4096,
7264
- },
7265
7439
  "mistralai/mixtral-8x7b-instruct": {
7266
7440
  id: "mistralai/mixtral-8x7b-instruct",
7267
7441
  name: "Mistral: Mixtral 8x7B Instruct",
@@ -7449,7 +7623,7 @@ export const MODELS = {
7449
7623
  cacheWrite: 0,
7450
7624
  },
7451
7625
  contextWindow: 400000,
7452
- maxTokens: 32000,
7626
+ maxTokens: 128000,
7453
7627
  },
7454
7628
  },
7455
7629
  };