@yeshwanthyk/ai 0.1.6 → 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 +582 -260
  2. package/dist/models.generated.d.ts.map +1 -1
  3. package/dist/models.generated.js +715 -420
  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",
@@ -87,6 +104,23 @@ export const MODELS = {
87
104
  contextWindow: 200000,
88
105
  maxTokens: 8192,
89
106
  },
107
+ "claude-opus-4-6": {
108
+ id: "claude-opus-4-6",
109
+ name: "Claude Opus 4.6",
110
+ api: "anthropic-messages",
111
+ provider: "anthropic",
112
+ baseUrl: "https://api.anthropic.com",
113
+ reasoning: true,
114
+ input: ["text", "image"],
115
+ cost: {
116
+ input: 5,
117
+ output: 25,
118
+ cacheRead: 0.5,
119
+ cacheWrite: 6.25,
120
+ },
121
+ contextWindow: 200000,
122
+ maxTokens: 128000,
123
+ },
90
124
  "claude-3-5-haiku-latest": {
91
125
  id: "claude-3-5-haiku-latest",
92
126
  name: "Claude Haiku 3.5 (latest)",
@@ -514,6 +548,23 @@ export const MODELS = {
514
548
  contextWindow: 131072,
515
549
  maxTokens: 65536,
516
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
+ },
517
568
  "gemini-2.0-flash": {
518
569
  id: "gemini-2.0-flash",
519
570
  name: "Gemini 2.0 Flash",
@@ -650,6 +701,23 @@ export const MODELS = {
650
701
  contextWindow: 1048576,
651
702
  maxTokens: 65536,
652
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
+ },
653
721
  "gemini-1.5-flash": {
654
722
  id: "gemini-1.5-flash",
655
723
  name: "Gemini 1.5 Flash",
@@ -737,6 +805,23 @@ export const MODELS = {
737
805
  contextWindow: 1047576,
738
806
  maxTokens: 32768,
739
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
+ },
740
825
  "gpt-4": {
741
826
  id: "gpt-4",
742
827
  name: "GPT-4",
@@ -1094,6 +1179,23 @@ export const MODELS = {
1094
1179
  contextWindow: 200000,
1095
1180
  maxTokens: 100000,
1096
1181
  },
1182
+ "gpt-5.3-codex": {
1183
+ id: "gpt-5.3-codex",
1184
+ name: "GPT-5.3 Codex",
1185
+ api: "openai-responses",
1186
+ provider: "openai",
1187
+ baseUrl: "https://api.openai.com/v1",
1188
+ reasoning: true,
1189
+ input: ["text", "image"],
1190
+ cost: {
1191
+ input: 1.75,
1192
+ output: 14,
1193
+ cacheRead: 0.175,
1194
+ cacheWrite: 0,
1195
+ },
1196
+ contextWindow: 400000,
1197
+ maxTokens: 128000,
1198
+ },
1097
1199
  "gpt-5-mini": {
1098
1200
  id: "gpt-5-mini",
1099
1201
  name: "GPT-5 Mini",
@@ -1566,8 +1668,8 @@ export const MODELS = {
1566
1668
  reasoning: false,
1567
1669
  input: ["text"],
1568
1670
  cost: {
1569
- input: 0,
1570
- output: 0,
1671
+ input: 2.25,
1672
+ output: 2.75,
1571
1673
  cacheRead: 0,
1572
1674
  cacheWrite: 0,
1573
1675
  },
@@ -1591,6 +1693,23 @@ export const MODELS = {
1591
1693
  contextWindow: 131000,
1592
1694
  maxTokens: 32000,
1593
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
+ },
1594
1713
  "gpt-oss-120b": {
1595
1714
  id: "gpt-oss-120b",
1596
1715
  name: "GPT OSS 120B",
@@ -2003,6 +2122,23 @@ export const MODELS = {
2003
2122
  contextWindow: 204800,
2004
2123
  maxTokens: 131072,
2005
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
+ },
2006
2142
  "glm-4.5-flash": {
2007
2143
  id: "glm-4.5-flash",
2008
2144
  name: "GLM-4.5-Flash",
@@ -2568,6 +2704,23 @@ export const MODELS = {
2568
2704
  contextWindow: 204800,
2569
2705
  maxTokens: 131072,
2570
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
+ },
2571
2724
  "qwen3-coder": {
2572
2725
  id: "qwen3-coder",
2573
2726
  name: "Qwen3 Coder",
@@ -2670,6 +2823,40 @@ export const MODELS = {
2670
2823
  contextWindow: 200000,
2671
2824
  maxTokens: 64000,
2672
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
+ },
2843
+ "claude-opus-4-6": {
2844
+ id: "claude-opus-4-6",
2845
+ name: "Claude Opus 4.6",
2846
+ api: "openai-completions",
2847
+ provider: "opencode",
2848
+ baseUrl: "https://opencode.ai/zen/v1",
2849
+ reasoning: true,
2850
+ input: ["text", "image"],
2851
+ cost: {
2852
+ input: 5,
2853
+ output: 25,
2854
+ cacheRead: 0.5,
2855
+ cacheWrite: 6.25,
2856
+ },
2857
+ contextWindow: 1000000,
2858
+ maxTokens: 128000,
2859
+ },
2673
2860
  "trinity-large-preview-free": {
2674
2861
  id: "trinity-large-preview-free",
2675
2862
  name: "Trinity Large Preview",
@@ -2719,7 +2906,7 @@ export const MODELS = {
2719
2906
  cacheWrite: 0,
2720
2907
  },
2721
2908
  contextWindow: 262144,
2722
- maxTokens: 262144,
2909
+ maxTokens: 65536,
2723
2910
  },
2724
2911
  "gemini-3-pro": {
2725
2912
  id: "gemini-3-pro",
@@ -2789,6 +2976,40 @@ export const MODELS = {
2789
2976
  contextWindow: 262144,
2790
2977
  maxTokens: 262144,
2791
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
+ },
2792
3013
  "gpt-5.1": {
2793
3014
  id: "gpt-5.1",
2794
3015
  name: "GPT-5.1",
@@ -3046,6 +3267,40 @@ export const MODELS = {
3046
3267
  contextWindow: 204800,
3047
3268
  maxTokens: 131072,
3048
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
+ },
3049
3304
  "gpt-5.2": {
3050
3305
  id: "gpt-5.2",
3051
3306
  name: "GPT-5.2",
@@ -3156,7 +3411,7 @@ export const MODELS = {
3156
3411
  cacheWrite: 0,
3157
3412
  },
3158
3413
  contextWindow: 128000,
3159
- maxTokens: 16000,
3414
+ maxTokens: 32000,
3160
3415
  },
3161
3416
  "gemini-3-pro-preview": {
3162
3417
  id: "gemini-3-pro-preview",
@@ -3193,7 +3448,7 @@ export const MODELS = {
3193
3448
  cacheWrite: 0,
3194
3449
  },
3195
3450
  contextWindow: 128000,
3196
- maxTokens: 100000,
3451
+ maxTokens: 128000,
3197
3452
  },
3198
3453
  "gpt-5.1": {
3199
3454
  id: "gpt-5.1",
@@ -3211,7 +3466,7 @@ export const MODELS = {
3211
3466
  cacheWrite: 0,
3212
3467
  },
3213
3468
  contextWindow: 128000,
3214
- maxTokens: 128000,
3469
+ maxTokens: 64000,
3215
3470
  },
3216
3471
  "gpt-4o": {
3217
3472
  id: "gpt-4o",
@@ -3269,6 +3524,25 @@ export const MODELS = {
3269
3524
  contextWindow: 128000,
3270
3525
  maxTokens: 64000,
3271
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
+ },
3272
3546
  "gemini-2.5-pro": {
3273
3547
  id: "gemini-2.5-pro",
3274
3548
  name: "Gemini 2.5 Pro",
@@ -3306,6 +3580,25 @@ export const MODELS = {
3306
3580
  contextWindow: 128000,
3307
3581
  maxTokens: 128000,
3308
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
+ },
3309
3602
  "claude-sonnet-4": {
3310
3603
  id: "claude-sonnet-4",
3311
3604
  name: "Claude Sonnet 4",
@@ -3360,7 +3653,7 @@ export const MODELS = {
3360
3653
  cacheWrite: 0,
3361
3654
  },
3362
3655
  contextWindow: 128000,
3363
- maxTokens: 16000,
3656
+ maxTokens: 32000,
3364
3657
  },
3365
3658
  "gpt-5.2": {
3366
3659
  id: "gpt-5.2",
@@ -3397,11 +3690,234 @@ export const MODELS = {
3397
3690
  cacheWrite: 0,
3398
3691
  },
3399
3692
  contextWindow: 128000,
3400
- maxTokens: 16000,
3693
+ maxTokens: 32000,
3401
3694
  },
3402
- },
3403
- "openrouter": {
3404
- "arcee-ai/trinity-large-preview:free": {
3695
+ "claude-opus-4.6": {
3696
+ id: "claude-opus-4.6",
3697
+ name: "Claude Opus 4.6",
3698
+ api: "openai-completions",
3699
+ provider: "github-copilot",
3700
+ baseUrl: "https://api.individual.githubcopilot.com",
3701
+ 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" },
3702
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
3703
+ reasoning: true,
3704
+ input: ["text", "image"],
3705
+ cost: {
3706
+ input: 0,
3707
+ output: 0,
3708
+ cacheRead: 0,
3709
+ cacheWrite: 0,
3710
+ },
3711
+ contextWindow: 128000,
3712
+ maxTokens: 64000,
3713
+ },
3714
+ },
3715
+ "openrouter": {
3716
+ "google/gemini-3.1-pro-preview": {
3717
+ id: "google/gemini-3.1-pro-preview",
3718
+ name: "Google: Gemini 3.1 Pro Preview",
3719
+ api: "openai-completions",
3720
+ provider: "openrouter",
3721
+ baseUrl: "https://openrouter.ai/api/v1",
3722
+ reasoning: true,
3723
+ input: ["text", "image"],
3724
+ cost: {
3725
+ input: 2,
3726
+ output: 12,
3727
+ cacheRead: 0.19999999999999998,
3728
+ cacheWrite: 0.375,
3729
+ },
3730
+ contextWindow: 1048576,
3731
+ maxTokens: 65536,
3732
+ },
3733
+ "anthropic/claude-sonnet-4.6": {
3734
+ id: "anthropic/claude-sonnet-4.6",
3735
+ name: "Anthropic: Claude Sonnet 4.6",
3736
+ api: "openai-completions",
3737
+ provider: "openrouter",
3738
+ baseUrl: "https://openrouter.ai/api/v1",
3739
+ reasoning: true,
3740
+ input: ["text", "image"],
3741
+ cost: {
3742
+ input: 3,
3743
+ output: 15,
3744
+ cacheRead: 0.3,
3745
+ cacheWrite: 3.75,
3746
+ },
3747
+ contextWindow: 1000000,
3748
+ maxTokens: 128000,
3749
+ },
3750
+ "qwen/qwen3.5-plus-02-15": {
3751
+ id: "qwen/qwen3.5-plus-02-15",
3752
+ name: "Qwen: Qwen3.5 Plus 2026-02-15",
3753
+ api: "openai-completions",
3754
+ provider: "openrouter",
3755
+ baseUrl: "https://openrouter.ai/api/v1",
3756
+ reasoning: true,
3757
+ input: ["text", "image"],
3758
+ cost: {
3759
+ input: 0.39999999999999997,
3760
+ output: 2.4,
3761
+ cacheRead: 0,
3762
+ cacheWrite: 0,
3763
+ },
3764
+ contextWindow: 1000000,
3765
+ maxTokens: 65536,
3766
+ },
3767
+ "qwen/qwen3.5-397b-a17b": {
3768
+ id: "qwen/qwen3.5-397b-a17b",
3769
+ name: "Qwen: Qwen3.5 397B A17B",
3770
+ api: "openai-completions",
3771
+ provider: "openrouter",
3772
+ baseUrl: "https://openrouter.ai/api/v1",
3773
+ reasoning: true,
3774
+ input: ["text", "image"],
3775
+ cost: {
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,
3880
+ cacheRead: 0,
3881
+ cacheWrite: 0,
3882
+ },
3883
+ contextWindow: 200000,
3884
+ maxTokens: 4096,
3885
+ },
3886
+ "stepfun/step-3.5-flash:free": {
3887
+ id: "stepfun/step-3.5-flash:free",
3888
+ name: "StepFun: Step 3.5 Flash (free)",
3889
+ api: "openai-completions",
3890
+ provider: "openrouter",
3891
+ baseUrl: "https://openrouter.ai/api/v1",
3892
+ reasoning: true,
3893
+ input: ["text"],
3894
+ cost: {
3895
+ input: 0,
3896
+ output: 0,
3897
+ cacheRead: 0,
3898
+ cacheWrite: 0,
3899
+ },
3900
+ contextWindow: 256000,
3901
+ maxTokens: 256000,
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
+ },
3920
+ "arcee-ai/trinity-large-preview:free": {
3405
3921
  id: "arcee-ai/trinity-large-preview:free",
3406
3922
  name: "Arcee AI: Trinity Large Preview (free)",
3407
3923
  api: "openai-completions",
@@ -3427,13 +3943,13 @@ export const MODELS = {
3427
3943
  reasoning: true,
3428
3944
  input: ["text", "image"],
3429
3945
  cost: {
3430
- input: 0.5,
3431
- output: 2.8,
3432
- cacheRead: 0,
3946
+ input: 0.44999999999999996,
3947
+ output: 2.2,
3948
+ cacheRead: 0.22499999999999998,
3433
3949
  cacheWrite: 0,
3434
3950
  },
3435
3951
  contextWindow: 262144,
3436
- maxTokens: 4096,
3952
+ maxTokens: 65535,
3437
3953
  },
3438
3954
  "upstage/solar-pro-3:free": {
3439
3955
  id: "upstage/solar-pro-3:free",
@@ -3454,20 +3970,20 @@ export const MODELS = {
3454
3970
  },
3455
3971
  "z-ai/glm-4.7-flash": {
3456
3972
  id: "z-ai/glm-4.7-flash",
3457
- name: "Z.AI: GLM 4.7 Flash",
3973
+ name: "Z.ai: GLM 4.7 Flash",
3458
3974
  api: "openai-completions",
3459
3975
  provider: "openrouter",
3460
3976
  baseUrl: "https://openrouter.ai/api/v1",
3461
3977
  reasoning: true,
3462
3978
  input: ["text"],
3463
3979
  cost: {
3464
- input: 0.07,
3980
+ input: 0.06,
3465
3981
  output: 0.39999999999999997,
3466
- cacheRead: 0.01,
3982
+ cacheRead: 0.0100000002,
3467
3983
  cacheWrite: 0,
3468
3984
  },
3469
- contextWindow: 200000,
3470
- maxTokens: 131072,
3985
+ contextWindow: 202752,
3986
+ maxTokens: 4096,
3471
3987
  },
3472
3988
  "openai/gpt-5.2-codex": {
3473
3989
  id: "openai/gpt-5.2-codex",
@@ -3547,25 +4063,25 @@ export const MODELS = {
3547
4063
  input: ["text"],
3548
4064
  cost: {
3549
4065
  input: 0.27,
3550
- output: 1.1,
3551
- cacheRead: 0,
4066
+ output: 0.95,
4067
+ cacheRead: 0.0299999997,
3552
4068
  cacheWrite: 0,
3553
4069
  },
3554
4070
  contextWindow: 196608,
3555
- maxTokens: 196608,
4071
+ maxTokens: 4096,
3556
4072
  },
3557
4073
  "z-ai/glm-4.7": {
3558
4074
  id: "z-ai/glm-4.7",
3559
- name: "Z.AI: GLM 4.7",
4075
+ name: "Z.ai: GLM 4.7",
3560
4076
  api: "openai-completions",
3561
4077
  provider: "openrouter",
3562
4078
  baseUrl: "https://openrouter.ai/api/v1",
3563
4079
  reasoning: true,
3564
4080
  input: ["text"],
3565
4081
  cost: {
3566
- input: 0.39999999999999997,
3567
- output: 1.5,
3568
- cacheRead: 0,
4082
+ input: 0.38,
4083
+ output: 1.7,
4084
+ cacheRead: 0.19,
3569
4085
  cacheWrite: 0,
3570
4086
  },
3571
4087
  contextWindow: 202752,
@@ -3616,11 +4132,11 @@ export const MODELS = {
3616
4132
  cost: {
3617
4133
  input: 0.09,
3618
4134
  output: 0.29,
3619
- cacheRead: 0,
4135
+ cacheRead: 0.045,
3620
4136
  cacheWrite: 0,
3621
4137
  },
3622
4138
  contextWindow: 262144,
3623
- maxTokens: 4096,
4139
+ maxTokens: 65536,
3624
4140
  },
3625
4141
  "nvidia/nemotron-3-nano-30b-a3b:free": {
3626
4142
  id: "nvidia/nemotron-3-nano-30b-a3b:free",
@@ -3716,13 +4232,13 @@ export const MODELS = {
3716
4232
  reasoning: false,
3717
4233
  input: ["text"],
3718
4234
  cost: {
3719
- input: 0.049999999999999996,
3720
- output: 0.22,
4235
+ input: 0.39999999999999997,
4236
+ output: 2,
3721
4237
  cacheRead: 0,
3722
4238
  cacheWrite: 0,
3723
4239
  },
3724
4240
  contextWindow: 262144,
3725
- maxTokens: 65536,
4241
+ maxTokens: 4096,
3726
4242
  },
3727
4243
  "relace/relace-search": {
3728
4244
  id: "relace/relace-search",
@@ -3743,7 +4259,7 @@ export const MODELS = {
3743
4259
  },
3744
4260
  "z-ai/glm-4.6v": {
3745
4261
  id: "z-ai/glm-4.6v",
3746
- name: "Z.AI: GLM 4.6V",
4262
+ name: "Z.ai: GLM 4.6V",
3747
4263
  api: "openai-completions",
3748
4264
  provider: "openrouter",
3749
4265
  baseUrl: "https://openrouter.ai/api/v1",
@@ -3920,13 +4436,13 @@ export const MODELS = {
3920
4436
  reasoning: true,
3921
4437
  input: ["text"],
3922
4438
  cost: {
3923
- input: 0.25,
4439
+ input: 0.26,
3924
4440
  output: 0.38,
3925
- cacheRead: 0,
4441
+ cacheRead: 0.13,
3926
4442
  cacheWrite: 0,
3927
4443
  },
3928
4444
  contextWindow: 163840,
3929
- maxTokens: 65536,
4445
+ maxTokens: 4096,
3930
4446
  },
3931
4447
  "prime-intellect/intellect-3": {
3932
4448
  id: "prime-intellect/intellect-3",
@@ -3945,40 +4461,6 @@ export const MODELS = {
3945
4461
  contextWindow: 131072,
3946
4462
  maxTokens: 131072,
3947
4463
  },
3948
- "tngtech/tng-r1t-chimera:free": {
3949
- id: "tngtech/tng-r1t-chimera:free",
3950
- name: "TNG: R1T Chimera (free)",
3951
- api: "openai-completions",
3952
- provider: "openrouter",
3953
- baseUrl: "https://openrouter.ai/api/v1",
3954
- reasoning: true,
3955
- input: ["text"],
3956
- cost: {
3957
- input: 0,
3958
- output: 0,
3959
- cacheRead: 0,
3960
- cacheWrite: 0,
3961
- },
3962
- contextWindow: 163840,
3963
- maxTokens: 65536,
3964
- },
3965
- "tngtech/tng-r1t-chimera": {
3966
- id: "tngtech/tng-r1t-chimera",
3967
- name: "TNG: R1T Chimera",
3968
- api: "openai-completions",
3969
- provider: "openrouter",
3970
- baseUrl: "https://openrouter.ai/api/v1",
3971
- reasoning: true,
3972
- input: ["text"],
3973
- cost: {
3974
- input: 0.25,
3975
- output: 0.85,
3976
- cacheRead: 0,
3977
- cacheWrite: 0,
3978
- },
3979
- contextWindow: 163840,
3980
- maxTokens: 65536,
3981
- },
3982
4464
  "anthropic/claude-opus-4.5": {
3983
4465
  id: "anthropic/claude-opus-4.5",
3984
4466
  name: "Anthropic: Claude Opus 4.5",
@@ -4124,13 +4606,13 @@ export const MODELS = {
4124
4606
  reasoning: true,
4125
4607
  input: ["text"],
4126
4608
  cost: {
4127
- input: 0.39999999999999997,
4128
- output: 1.75,
4129
- cacheRead: 0,
4609
+ input: 0.47,
4610
+ output: 2,
4611
+ cacheRead: 0.14100000000000001,
4130
4612
  cacheWrite: 0,
4131
4613
  },
4132
- contextWindow: 262144,
4133
- maxTokens: 65535,
4614
+ contextWindow: 131072,
4615
+ maxTokens: 4096,
4134
4616
  },
4135
4617
  "amazon/nova-premier-v1": {
4136
4618
  id: "amazon/nova-premier-v1",
@@ -4209,7 +4691,7 @@ export const MODELS = {
4209
4691
  reasoning: true,
4210
4692
  input: ["text"],
4211
4693
  cost: {
4212
- input: 0.19999999999999998,
4694
+ input: 0.255,
4213
4695
  output: 1,
4214
4696
  cacheRead: 0.03,
4215
4697
  cacheWrite: 0,
@@ -4217,22 +4699,22 @@ export const MODELS = {
4217
4699
  contextWindow: 196608,
4218
4700
  maxTokens: 65536,
4219
4701
  },
4220
- "deepcogito/cogito-v2-preview-llama-405b": {
4221
- id: "deepcogito/cogito-v2-preview-llama-405b",
4222
- name: "Deep Cogito: Cogito V2 Preview Llama 405B",
4702
+ "qwen/qwen3-vl-32b-instruct": {
4703
+ id: "qwen/qwen3-vl-32b-instruct",
4704
+ name: "Qwen: Qwen3 VL 32B Instruct",
4223
4705
  api: "openai-completions",
4224
4706
  provider: "openrouter",
4225
4707
  baseUrl: "https://openrouter.ai/api/v1",
4226
- reasoning: true,
4227
- input: ["text"],
4708
+ reasoning: false,
4709
+ input: ["text", "image"],
4228
4710
  cost: {
4229
- input: 3.5,
4230
- output: 3.5,
4711
+ input: 0.10400000000000001,
4712
+ output: 0.41600000000000004,
4231
4713
  cacheRead: 0,
4232
4714
  cacheWrite: 0,
4233
4715
  },
4234
- contextWindow: 32768,
4235
- maxTokens: 4096,
4716
+ contextWindow: 131072,
4717
+ maxTokens: 32768,
4236
4718
  },
4237
4719
  "openai/gpt-5-image-mini": {
4238
4720
  id: "openai/gpt-5-image-mini",
@@ -4277,12 +4759,12 @@ export const MODELS = {
4277
4759
  reasoning: true,
4278
4760
  input: ["text", "image"],
4279
4761
  cost: {
4280
- input: 0.18,
4281
- output: 2.0999999999999996,
4762
+ input: 0.117,
4763
+ output: 1.365,
4282
4764
  cacheRead: 0,
4283
4765
  cacheWrite: 0,
4284
4766
  },
4285
- contextWindow: 256000,
4767
+ contextWindow: 131072,
4286
4768
  maxTokens: 32768,
4287
4769
  },
4288
4770
  "qwen/qwen3-vl-8b-instruct": {
@@ -4379,8 +4861,8 @@ export const MODELS = {
4379
4861
  reasoning: true,
4380
4862
  input: ["text", "image"],
4381
4863
  cost: {
4382
- input: 0.19999999999999998,
4383
- output: 1,
4864
+ input: 0,
4865
+ output: 0,
4384
4866
  cacheRead: 0,
4385
4867
  cacheWrite: 0,
4386
4868
  },
@@ -4396,13 +4878,13 @@ export const MODELS = {
4396
4878
  reasoning: false,
4397
4879
  input: ["text", "image"],
4398
4880
  cost: {
4399
- input: 0.15,
4400
- output: 0.6,
4401
- cacheRead: 0.075,
4881
+ input: 0.13,
4882
+ output: 0.52,
4883
+ cacheRead: 0,
4402
4884
  cacheWrite: 0,
4403
4885
  },
4404
- contextWindow: 262144,
4405
- maxTokens: 4096,
4886
+ contextWindow: 131072,
4887
+ maxTokens: 32768,
4406
4888
  },
4407
4889
  "openai/gpt-5-pro": {
4408
4890
  id: "openai/gpt-5-pro",
@@ -4423,7 +4905,7 @@ export const MODELS = {
4423
4905
  },
4424
4906
  "z-ai/glm-4.6": {
4425
4907
  id: "z-ai/glm-4.6",
4426
- name: "Z.AI: GLM 4.6",
4908
+ name: "Z.ai: GLM 4.6",
4427
4909
  api: "openai-completions",
4428
4910
  provider: "openrouter",
4429
4911
  baseUrl: "https://openrouter.ai/api/v1",
@@ -4431,16 +4913,16 @@ export const MODELS = {
4431
4913
  input: ["text"],
4432
4914
  cost: {
4433
4915
  input: 0.35,
4434
- output: 1.5,
4916
+ output: 1.71,
4435
4917
  cacheRead: 0,
4436
4918
  cacheWrite: 0,
4437
4919
  },
4438
4920
  contextWindow: 202752,
4439
- maxTokens: 65536,
4921
+ maxTokens: 131072,
4440
4922
  },
4441
4923
  "z-ai/glm-4.6:exacto": {
4442
4924
  id: "z-ai/glm-4.6:exacto",
4443
- name: "Z.AI: GLM 4.6 (exacto)",
4925
+ name: "Z.ai: GLM 4.6 (exacto)",
4444
4926
  api: "openai-completions",
4445
4927
  provider: "openrouter",
4446
4928
  baseUrl: "https://openrouter.ai/api/v1",
@@ -4481,31 +4963,14 @@ export const MODELS = {
4481
4963
  reasoning: true,
4482
4964
  input: ["text"],
4483
4965
  cost: {
4484
- input: 0.21,
4485
- output: 0.32,
4486
- cacheRead: 0.21,
4966
+ input: 0.27,
4967
+ output: 0.41,
4968
+ cacheRead: 0,
4487
4969
  cacheWrite: 0,
4488
4970
  },
4489
4971
  contextWindow: 163840,
4490
4972
  maxTokens: 65536,
4491
4973
  },
4492
- "google/gemini-2.5-flash-preview-09-2025": {
4493
- id: "google/gemini-2.5-flash-preview-09-2025",
4494
- name: "Google: Gemini 2.5 Flash Preview 09-2025",
4495
- api: "openai-completions",
4496
- provider: "openrouter",
4497
- baseUrl: "https://openrouter.ai/api/v1",
4498
- reasoning: true,
4499
- input: ["text", "image"],
4500
- cost: {
4501
- input: 0.3,
4502
- output: 2.5,
4503
- cacheRead: 0.03,
4504
- cacheWrite: 0.08333333333333334,
4505
- },
4506
- contextWindow: 1048576,
4507
- maxTokens: 65536,
4508
- },
4509
4974
  "google/gemini-2.5-flash-lite-preview-09-2025": {
4510
4975
  id: "google/gemini-2.5-flash-lite-preview-09-2025",
4511
4976
  name: "Google: Gemini 2.5 Flash Lite Preview 09-2025",
@@ -4532,13 +4997,13 @@ export const MODELS = {
4532
4997
  reasoning: true,
4533
4998
  input: ["text", "image"],
4534
4999
  cost: {
4535
- input: 0.44999999999999996,
4536
- output: 3.5,
5000
+ input: 0,
5001
+ output: 0,
4537
5002
  cacheRead: 0,
4538
5003
  cacheWrite: 0,
4539
5004
  },
4540
- contextWindow: 262144,
4541
- maxTokens: 262144,
5005
+ contextWindow: 131072,
5006
+ maxTokens: 32768,
4542
5007
  },
4543
5008
  "qwen/qwen3-vl-235b-a22b-instruct": {
4544
5009
  id: "qwen/qwen3-vl-235b-a22b-instruct",
@@ -4550,8 +5015,8 @@ export const MODELS = {
4550
5015
  input: ["text", "image"],
4551
5016
  cost: {
4552
5017
  input: 0.19999999999999998,
4553
- output: 1.2,
4554
- cacheRead: 0,
5018
+ output: 0.88,
5019
+ cacheRead: 0.11,
4555
5020
  cacheWrite: 0,
4556
5021
  },
4557
5022
  contextWindow: 262144,
@@ -4571,7 +5036,7 @@ export const MODELS = {
4571
5036
  cacheRead: 0.24,
4572
5037
  cacheWrite: 0,
4573
5038
  },
4574
- contextWindow: 256000,
5039
+ contextWindow: 262144,
4575
5040
  maxTokens: 32768,
4576
5041
  },
4577
5042
  "qwen/qwen3-coder-plus": {
@@ -4585,10 +5050,10 @@ export const MODELS = {
4585
5050
  cost: {
4586
5051
  input: 1,
4587
5052
  output: 5,
4588
- cacheRead: 0.09999999999999999,
5053
+ cacheRead: 0.19999999999999998,
4589
5054
  cacheWrite: 0,
4590
5055
  },
4591
- contextWindow: 128000,
5056
+ contextWindow: 1000000,
4592
5057
  maxTokens: 65536,
4593
5058
  },
4594
5059
  "openai/gpt-5-codex": {
@@ -4636,7 +5101,7 @@ export const MODELS = {
4636
5101
  cost: {
4637
5102
  input: 0.21,
4638
5103
  output: 0.7899999999999999,
4639
- cacheRead: 0.16799999999999998,
5104
+ cacheRead: 0.1300000002,
4640
5105
  cacheWrite: 0,
4641
5106
  },
4642
5107
  contextWindow: 163840,
@@ -4669,8 +5134,8 @@ export const MODELS = {
4669
5134
  input: ["text"],
4670
5135
  cost: {
4671
5136
  input: 0.09,
4672
- output: 0.39999999999999997,
4673
- cacheRead: 0,
5137
+ output: 0.44999999999999996,
5138
+ cacheRead: 0.09,
4674
5139
  cacheWrite: 0,
4675
5140
  },
4676
5141
  contextWindow: 131072,
@@ -4687,10 +5152,10 @@ export const MODELS = {
4687
5152
  cost: {
4688
5153
  input: 0.3,
4689
5154
  output: 1.5,
4690
- cacheRead: 0.08,
5155
+ cacheRead: 0.06,
4691
5156
  cacheWrite: 0,
4692
5157
  },
4693
- contextWindow: 128000,
5158
+ contextWindow: 1000000,
4694
5159
  maxTokens: 65536,
4695
5160
  },
4696
5161
  "qwen/qwen3-next-80b-a3b-thinking": {
@@ -4771,7 +5236,7 @@ export const MODELS = {
4771
5236
  input: ["text"],
4772
5237
  cost: {
4773
5238
  input: 0.39999999999999997,
4774
- output: 4,
5239
+ output: 1.2,
4775
5240
  cacheRead: 0,
4776
5241
  cacheWrite: 0,
4777
5242
  },
@@ -4821,13 +5286,13 @@ export const MODELS = {
4821
5286
  reasoning: false,
4822
5287
  input: ["text"],
4823
5288
  cost: {
4824
- input: 0.39,
4825
- output: 1.9,
4826
- cacheRead: 0,
5289
+ input: 0.39999999999999997,
5290
+ output: 2,
5291
+ cacheRead: 0.15,
4827
5292
  cacheWrite: 0,
4828
5293
  },
4829
- contextWindow: 262144,
4830
- maxTokens: 262144,
5294
+ contextWindow: 131072,
5295
+ maxTokens: 4096,
4831
5296
  },
4832
5297
  "moonshotai/kimi-k2-0905:exacto": {
4833
5298
  id: "moonshotai/kimi-k2-0905:exacto",
@@ -4846,57 +5311,6 @@ export const MODELS = {
4846
5311
  contextWindow: 262144,
4847
5312
  maxTokens: 4096,
4848
5313
  },
4849
- "deepcogito/cogito-v2-preview-llama-70b": {
4850
- id: "deepcogito/cogito-v2-preview-llama-70b",
4851
- name: "Deep Cogito: Cogito V2 Preview Llama 70B",
4852
- api: "openai-completions",
4853
- provider: "openrouter",
4854
- baseUrl: "https://openrouter.ai/api/v1",
4855
- reasoning: true,
4856
- input: ["text"],
4857
- cost: {
4858
- input: 0.88,
4859
- output: 0.88,
4860
- cacheRead: 0,
4861
- cacheWrite: 0,
4862
- },
4863
- contextWindow: 32768,
4864
- maxTokens: 4096,
4865
- },
4866
- "deepcogito/cogito-v2-preview-llama-109b-moe": {
4867
- id: "deepcogito/cogito-v2-preview-llama-109b-moe",
4868
- name: "Cogito V2 Preview Llama 109B",
4869
- api: "openai-completions",
4870
- provider: "openrouter",
4871
- baseUrl: "https://openrouter.ai/api/v1",
4872
- reasoning: true,
4873
- input: ["text", "image"],
4874
- cost: {
4875
- input: 0.18,
4876
- output: 0.59,
4877
- cacheRead: 0,
4878
- cacheWrite: 0,
4879
- },
4880
- contextWindow: 32767,
4881
- maxTokens: 4096,
4882
- },
4883
- "stepfun-ai/step3": {
4884
- id: "stepfun-ai/step3",
4885
- name: "StepFun: Step3",
4886
- api: "openai-completions",
4887
- provider: "openrouter",
4888
- baseUrl: "https://openrouter.ai/api/v1",
4889
- reasoning: true,
4890
- input: ["text", "image"],
4891
- cost: {
4892
- input: 0.5700000000000001,
4893
- output: 1.42,
4894
- cacheRead: 0,
4895
- cacheWrite: 0,
4896
- },
4897
- contextWindow: 65536,
4898
- maxTokens: 65536,
4899
- },
4900
5314
  "qwen/qwen3-30b-a3b-thinking-2507": {
4901
5315
  id: "qwen/qwen3-30b-a3b-thinking-2507",
4902
5316
  name: "Qwen: Qwen3 30B A3B Thinking 2507",
@@ -4915,38 +5329,21 @@ export const MODELS = {
4915
5329
  maxTokens: 4096,
4916
5330
  },
4917
5331
  "x-ai/grok-code-fast-1": {
4918
- id: "x-ai/grok-code-fast-1",
4919
- name: "xAI: Grok Code Fast 1",
4920
- api: "openai-completions",
4921
- provider: "openrouter",
4922
- baseUrl: "https://openrouter.ai/api/v1",
4923
- reasoning: true,
4924
- input: ["text"],
4925
- cost: {
4926
- input: 0.19999999999999998,
4927
- output: 1.5,
4928
- cacheRead: 0.02,
4929
- cacheWrite: 0,
4930
- },
4931
- contextWindow: 256000,
4932
- maxTokens: 10000,
4933
- },
4934
- "nousresearch/hermes-4-70b": {
4935
- id: "nousresearch/hermes-4-70b",
4936
- name: "Nous: Hermes 4 70B",
5332
+ id: "x-ai/grok-code-fast-1",
5333
+ name: "xAI: Grok Code Fast 1",
4937
5334
  api: "openai-completions",
4938
5335
  provider: "openrouter",
4939
5336
  baseUrl: "https://openrouter.ai/api/v1",
4940
5337
  reasoning: true,
4941
5338
  input: ["text"],
4942
5339
  cost: {
4943
- input: 0.11,
4944
- output: 0.38,
4945
- cacheRead: 0,
5340
+ input: 0.19999999999999998,
5341
+ output: 1.5,
5342
+ cacheRead: 0.02,
4946
5343
  cacheWrite: 0,
4947
5344
  },
4948
- contextWindow: 131072,
4949
- maxTokens: 131072,
5345
+ contextWindow: 256000,
5346
+ maxTokens: 10000,
4950
5347
  },
4951
5348
  "deepseek/deepseek-chat-v3.1": {
4952
5349
  id: "deepseek/deepseek-chat-v3.1",
@@ -5035,7 +5432,7 @@ export const MODELS = {
5035
5432
  },
5036
5433
  "z-ai/glm-4.5v": {
5037
5434
  id: "z-ai/glm-4.5v",
5038
- name: "Z.AI: GLM 4.5V",
5435
+ name: "Z.ai: GLM 4.5V",
5039
5436
  api: "openai-completions",
5040
5437
  provider: "openrouter",
5041
5438
  baseUrl: "https://openrouter.ai/api/v1",
@@ -5050,23 +5447,6 @@ export const MODELS = {
5050
5447
  contextWindow: 65536,
5051
5448
  maxTokens: 16384,
5052
5449
  },
5053
- "ai21/jamba-mini-1.7": {
5054
- id: "ai21/jamba-mini-1.7",
5055
- name: "AI21: Jamba Mini 1.7",
5056
- api: "openai-completions",
5057
- provider: "openrouter",
5058
- baseUrl: "https://openrouter.ai/api/v1",
5059
- reasoning: false,
5060
- input: ["text"],
5061
- cost: {
5062
- input: 0.19999999999999998,
5063
- output: 0.39999999999999997,
5064
- cacheRead: 0,
5065
- cacheWrite: 0,
5066
- },
5067
- contextWindow: 256000,
5068
- maxTokens: 4096,
5069
- },
5070
5450
  "ai21/jamba-large-1.7": {
5071
5451
  id: "ai21/jamba-large-1.7",
5072
5452
  name: "AI21: Jamba Large 1.7",
@@ -5212,13 +5592,13 @@ export const MODELS = {
5212
5592
  reasoning: true,
5213
5593
  input: ["text"],
5214
5594
  cost: {
5215
- input: 0.02,
5216
- output: 0.09999999999999999,
5595
+ input: 0.03,
5596
+ output: 0.14,
5217
5597
  cacheRead: 0,
5218
5598
  cacheWrite: 0,
5219
5599
  },
5220
5600
  contextWindow: 131072,
5221
- maxTokens: 131072,
5601
+ maxTokens: 4096,
5222
5602
  },
5223
5603
  "anthropic/claude-opus-4.1": {
5224
5604
  id: "anthropic/claude-opus-4.1",
@@ -5280,8 +5660,8 @@ export const MODELS = {
5280
5660
  reasoning: false,
5281
5661
  input: ["text"],
5282
5662
  cost: {
5283
- input: 0.08,
5284
- output: 0.33,
5663
+ input: 0.09,
5664
+ output: 0.3,
5285
5665
  cacheRead: 0,
5286
5666
  cacheWrite: 0,
5287
5667
  },
@@ -5290,24 +5670,24 @@ export const MODELS = {
5290
5670
  },
5291
5671
  "z-ai/glm-4.5": {
5292
5672
  id: "z-ai/glm-4.5",
5293
- name: "Z.AI: GLM 4.5",
5673
+ name: "Z.ai: GLM 4.5",
5294
5674
  api: "openai-completions",
5295
5675
  provider: "openrouter",
5296
5676
  baseUrl: "https://openrouter.ai/api/v1",
5297
5677
  reasoning: true,
5298
5678
  input: ["text"],
5299
5679
  cost: {
5300
- input: 0.35,
5301
- output: 1.55,
5680
+ input: 0.55,
5681
+ output: 2,
5302
5682
  cacheRead: 0,
5303
5683
  cacheWrite: 0,
5304
5684
  },
5305
- contextWindow: 131072,
5306
- maxTokens: 65536,
5685
+ contextWindow: 131000,
5686
+ maxTokens: 131000,
5307
5687
  },
5308
5688
  "z-ai/glm-4.5-air:free": {
5309
5689
  id: "z-ai/glm-4.5-air:free",
5310
- name: "Z.AI: GLM 4.5 Air (free)",
5690
+ name: "Z.ai: GLM 4.5 Air (free)",
5311
5691
  api: "openai-completions",
5312
5692
  provider: "openrouter",
5313
5693
  baseUrl: "https://openrouter.ai/api/v1",
@@ -5324,20 +5704,20 @@ export const MODELS = {
5324
5704
  },
5325
5705
  "z-ai/glm-4.5-air": {
5326
5706
  id: "z-ai/glm-4.5-air",
5327
- name: "Z.AI: GLM 4.5 Air",
5707
+ name: "Z.ai: GLM 4.5 Air",
5328
5708
  api: "openai-completions",
5329
5709
  provider: "openrouter",
5330
5710
  baseUrl: "https://openrouter.ai/api/v1",
5331
5711
  reasoning: true,
5332
5712
  input: ["text"],
5333
5713
  cost: {
5334
- input: 0.049999999999999996,
5335
- output: 0.22,
5336
- cacheRead: 0,
5714
+ input: 0.13,
5715
+ output: 0.85,
5716
+ cacheRead: 0.024999999999999998,
5337
5717
  cacheWrite: 0,
5338
5718
  },
5339
5719
  contextWindow: 131072,
5340
- maxTokens: 131072,
5720
+ maxTokens: 98304,
5341
5721
  },
5342
5722
  "qwen/qwen3-235b-a22b-thinking-2507": {
5343
5723
  id: "qwen/qwen3-235b-a22b-thinking-2507",
@@ -5348,17 +5728,17 @@ export const MODELS = {
5348
5728
  reasoning: true,
5349
5729
  input: ["text"],
5350
5730
  cost: {
5351
- input: 0.11,
5352
- output: 0.6,
5731
+ input: 0,
5732
+ output: 0,
5353
5733
  cacheRead: 0,
5354
5734
  cacheWrite: 0,
5355
5735
  },
5356
- contextWindow: 262144,
5357
- maxTokens: 262144,
5736
+ contextWindow: 131072,
5737
+ maxTokens: 4096,
5358
5738
  },
5359
5739
  "z-ai/glm-4-32b": {
5360
5740
  id: "z-ai/glm-4-32b",
5361
- name: "Z.AI: GLM 4 32B ",
5741
+ name: "Z.ai: GLM 4 32B ",
5362
5742
  api: "openai-completions",
5363
5743
  provider: "openrouter",
5364
5744
  baseUrl: "https://openrouter.ai/api/v1",
@@ -5396,16 +5776,16 @@ export const MODELS = {
5396
5776
  api: "openai-completions",
5397
5777
  provider: "openrouter",
5398
5778
  baseUrl: "https://openrouter.ai/api/v1",
5399
- reasoning: true,
5779
+ reasoning: false,
5400
5780
  input: ["text"],
5401
5781
  cost: {
5402
5782
  input: 0.22,
5403
- output: 0.95,
5404
- cacheRead: 0,
5783
+ output: 1,
5784
+ cacheRead: 0.022,
5405
5785
  cacheWrite: 0,
5406
5786
  },
5407
5787
  contextWindow: 262144,
5408
- maxTokens: 262144,
5788
+ maxTokens: 4096,
5409
5789
  },
5410
5790
  "qwen/qwen3-coder:exacto": {
5411
5791
  id: "qwen/qwen3-coder:exacto",
@@ -5413,7 +5793,7 @@ export const MODELS = {
5413
5793
  api: "openai-completions",
5414
5794
  provider: "openrouter",
5415
5795
  baseUrl: "https://openrouter.ai/api/v1",
5416
- reasoning: true,
5796
+ reasoning: false,
5417
5797
  input: ["text"],
5418
5798
  cost: {
5419
5799
  input: 0.22,
@@ -5451,7 +5831,7 @@ export const MODELS = {
5451
5831
  input: ["text"],
5452
5832
  cost: {
5453
5833
  input: 0.071,
5454
- output: 0.463,
5834
+ output: 0.09999999999999999,
5455
5835
  cacheRead: 0,
5456
5836
  cacheWrite: 0,
5457
5837
  },
@@ -5537,7 +5917,7 @@ export const MODELS = {
5537
5917
  cost: {
5538
5918
  input: 0.25,
5539
5919
  output: 0.85,
5540
- cacheRead: 0,
5920
+ cacheRead: 0.125,
5541
5921
  cacheWrite: 0,
5542
5922
  },
5543
5923
  contextWindow: 163840,
@@ -5571,7 +5951,7 @@ export const MODELS = {
5571
5951
  cost: {
5572
5952
  input: 0.06,
5573
5953
  output: 0.18,
5574
- cacheRead: 0,
5954
+ cacheRead: 0.03,
5575
5955
  cacheWrite: 0,
5576
5956
  },
5577
5957
  contextWindow: 131072,
@@ -5707,7 +6087,7 @@ export const MODELS = {
5707
6087
  cost: {
5708
6088
  input: 0.39999999999999997,
5709
6089
  output: 1.75,
5710
- cacheRead: 0,
6090
+ cacheRead: 0.19999999999999998,
5711
6091
  cacheWrite: 0,
5712
6092
  },
5713
6093
  contextWindow: 163840,
@@ -5747,23 +6127,6 @@ export const MODELS = {
5747
6127
  contextWindow: 1000000,
5748
6128
  maxTokens: 64000,
5749
6129
  },
5750
- "nousresearch/deephermes-3-mistral-24b-preview": {
5751
- id: "nousresearch/deephermes-3-mistral-24b-preview",
5752
- name: "Nous: DeepHermes 3 Mistral 24B Preview",
5753
- api: "openai-completions",
5754
- provider: "openrouter",
5755
- baseUrl: "https://openrouter.ai/api/v1",
5756
- reasoning: true,
5757
- input: ["text"],
5758
- cost: {
5759
- input: 0.02,
5760
- output: 0.09999999999999999,
5761
- cacheRead: 0,
5762
- cacheWrite: 0,
5763
- },
5764
- contextWindow: 32768,
5765
- maxTokens: 32768,
5766
- },
5767
6130
  "mistralai/mistral-medium-3": {
5768
6131
  id: "mistralai/mistral-medium-3",
5769
6132
  name: "Mistral: Mistral Medium 3",
@@ -5858,8 +6221,8 @@ export const MODELS = {
5858
6221
  reasoning: true,
5859
6222
  input: ["text"],
5860
6223
  cost: {
5861
- input: 0.06,
5862
- output: 0.22,
6224
+ input: 0.08,
6225
+ output: 0.28,
5863
6226
  cacheRead: 0,
5864
6227
  cacheWrite: 0,
5865
6228
  },
@@ -5876,7 +6239,7 @@ export const MODELS = {
5876
6239
  input: ["text"],
5877
6240
  cost: {
5878
6241
  input: 0.049999999999999996,
5879
- output: 0.25,
6242
+ output: 0.39999999999999997,
5880
6243
  cacheRead: 0.049999999999999996,
5881
6244
  cacheWrite: 0,
5882
6245
  },
@@ -5892,8 +6255,8 @@ export const MODELS = {
5892
6255
  reasoning: true,
5893
6256
  input: ["text"],
5894
6257
  cost: {
5895
- input: 0.049999999999999996,
5896
- output: 0.22,
6258
+ input: 0.06,
6259
+ output: 0.24,
5897
6260
  cacheRead: 0,
5898
6261
  cacheWrite: 0,
5899
6262
  },
@@ -5911,7 +6274,7 @@ export const MODELS = {
5911
6274
  cost: {
5912
6275
  input: 0.08,
5913
6276
  output: 0.24,
5914
- cacheRead: 0,
6277
+ cacheRead: 0.04,
5915
6278
  cacheWrite: 0,
5916
6279
  },
5917
6280
  contextWindow: 40960,
@@ -5926,13 +6289,13 @@ export const MODELS = {
5926
6289
  reasoning: true,
5927
6290
  input: ["text"],
5928
6291
  cost: {
5929
- input: 0.19999999999999998,
5930
- output: 0.6,
6292
+ input: 0.45499999999999996,
6293
+ output: 1.8199999999999998,
5931
6294
  cacheRead: 0,
5932
6295
  cacheWrite: 0,
5933
6296
  },
5934
- contextWindow: 40960,
5935
- maxTokens: 4096,
6297
+ contextWindow: 131072,
6298
+ maxTokens: 8192,
5936
6299
  },
5937
6300
  "openai/o4-mini-high": {
5938
6301
  id: "openai/o4-mini-high",
@@ -6115,7 +6478,7 @@ export const MODELS = {
6115
6478
  cost: {
6116
6479
  input: 0.19,
6117
6480
  output: 0.87,
6118
- cacheRead: 0,
6481
+ cacheRead: 0.095,
6119
6482
  cacheWrite: 0,
6120
6483
  },
6121
6484
  contextWindow: 163840,
@@ -6138,23 +6501,6 @@ export const MODELS = {
6138
6501
  contextWindow: 128000,
6139
6502
  maxTokens: 4096,
6140
6503
  },
6141
- "mistralai/mistral-small-3.1-24b-instruct": {
6142
- id: "mistralai/mistral-small-3.1-24b-instruct",
6143
- name: "Mistral: Mistral Small 3.1 24B",
6144
- api: "openai-completions",
6145
- provider: "openrouter",
6146
- baseUrl: "https://openrouter.ai/api/v1",
6147
- reasoning: false,
6148
- input: ["text", "image"],
6149
- cost: {
6150
- input: 0.03,
6151
- output: 0.11,
6152
- cacheRead: 0,
6153
- cacheWrite: 0,
6154
- },
6155
- contextWindow: 131072,
6156
- maxTokens: 131072,
6157
- },
6158
6504
  "google/gemma-3-27b-it:free": {
6159
6505
  id: "google/gemma-3-27b-it:free",
6160
6506
  name: "Google: Gemma 3 27B (free)",
@@ -6170,7 +6516,7 @@ export const MODELS = {
6170
6516
  cacheWrite: 0,
6171
6517
  },
6172
6518
  contextWindow: 131072,
6173
- maxTokens: 4096,
6519
+ maxTokens: 8192,
6174
6520
  },
6175
6521
  "google/gemma-3-27b-it": {
6176
6522
  id: "google/gemma-3-27b-it",
@@ -6183,11 +6529,11 @@ export const MODELS = {
6183
6529
  cost: {
6184
6530
  input: 0.04,
6185
6531
  output: 0.15,
6186
- cacheRead: 0,
6532
+ cacheRead: 0.02,
6187
6533
  cacheWrite: 0,
6188
6534
  },
6189
- contextWindow: 96000,
6190
- maxTokens: 96000,
6535
+ contextWindow: 128000,
6536
+ maxTokens: 65536,
6191
6537
  },
6192
6538
  "qwen/qwq-32b": {
6193
6539
  id: "qwen/qwq-32b",
@@ -6223,9 +6569,9 @@ export const MODELS = {
6223
6569
  contextWindow: 1048576,
6224
6570
  maxTokens: 8192,
6225
6571
  },
6226
- "anthropic/claude-3.7-sonnet:thinking": {
6227
- id: "anthropic/claude-3.7-sonnet:thinking",
6228
- 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",
6229
6575
  api: "openai-completions",
6230
6576
  provider: "openrouter",
6231
6577
  baseUrl: "https://openrouter.ai/api/v1",
@@ -6240,9 +6586,9 @@ export const MODELS = {
6240
6586
  contextWindow: 200000,
6241
6587
  maxTokens: 64000,
6242
6588
  },
6243
- "anthropic/claude-3.7-sonnet": {
6244
- id: "anthropic/claude-3.7-sonnet",
6245
- 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)",
6246
6592
  api: "openai-completions",
6247
6593
  provider: "openrouter",
6248
6594
  baseUrl: "https://openrouter.ai/api/v1",
@@ -6323,7 +6669,7 @@ export const MODELS = {
6323
6669
  cacheWrite: 0,
6324
6670
  },
6325
6671
  contextWindow: 131072,
6326
- maxTokens: 8192,
6672
+ maxTokens: 32768,
6327
6673
  },
6328
6674
  "qwen/qwen-turbo": {
6329
6675
  id: "qwen/qwen-turbo",
@@ -6336,10 +6682,10 @@ export const MODELS = {
6336
6682
  cost: {
6337
6683
  input: 0.049999999999999996,
6338
6684
  output: 0.19999999999999998,
6339
- cacheRead: 0.02,
6685
+ cacheRead: 0.01,
6340
6686
  cacheWrite: 0,
6341
6687
  },
6342
- contextWindow: 1000000,
6688
+ contextWindow: 131072,
6343
6689
  maxTokens: 8192,
6344
6690
  },
6345
6691
  "qwen/qwen-plus": {
@@ -6353,11 +6699,11 @@ export const MODELS = {
6353
6699
  cost: {
6354
6700
  input: 0.39999999999999997,
6355
6701
  output: 1.2,
6356
- cacheRead: 0.16,
6702
+ cacheRead: 0.08,
6357
6703
  cacheWrite: 0,
6358
6704
  },
6359
- contextWindow: 131072,
6360
- maxTokens: 8192,
6705
+ contextWindow: 1000000,
6706
+ maxTokens: 32768,
6361
6707
  },
6362
6708
  "qwen/qwen-max": {
6363
6709
  id: "qwen/qwen-max",
@@ -6370,7 +6716,7 @@ export const MODELS = {
6370
6716
  cost: {
6371
6717
  input: 1.5999999999999999,
6372
6718
  output: 6.3999999999999995,
6373
- cacheRead: 0.64,
6719
+ cacheRead: 0.32,
6374
6720
  cacheWrite: 0,
6375
6721
  },
6376
6722
  contextWindow: 32768,
@@ -6402,13 +6748,13 @@ export const MODELS = {
6402
6748
  reasoning: false,
6403
6749
  input: ["text"],
6404
6750
  cost: {
6405
- input: 0.03,
6406
- output: 0.11,
6751
+ input: 0.049999999999999996,
6752
+ output: 0.08,
6407
6753
  cacheRead: 0,
6408
6754
  cacheWrite: 0,
6409
6755
  },
6410
6756
  contextWindow: 32768,
6411
- maxTokens: 32768,
6757
+ maxTokens: 16384,
6412
6758
  },
6413
6759
  "deepseek/deepseek-r1": {
6414
6760
  id: "deepseek/deepseek-r1",
@@ -6436,8 +6782,8 @@ export const MODELS = {
6436
6782
  reasoning: false,
6437
6783
  input: ["text"],
6438
6784
  cost: {
6439
- input: 0.3,
6440
- output: 1.2,
6785
+ input: 0.32,
6786
+ output: 0.8899999999999999,
6441
6787
  cacheRead: 0,
6442
6788
  cacheWrite: 0,
6443
6789
  },
@@ -6475,8 +6821,8 @@ export const MODELS = {
6475
6821
  cacheRead: 0,
6476
6822
  cacheWrite: 0,
6477
6823
  },
6478
- contextWindow: 131072,
6479
- maxTokens: 4096,
6824
+ contextWindow: 128000,
6825
+ maxTokens: 128000,
6480
6826
  },
6481
6827
  "meta-llama/llama-3.3-70b-instruct": {
6482
6828
  id: "meta-llama/llama-3.3-70b-instruct",
@@ -6659,46 +7005,12 @@ export const MODELS = {
6659
7005
  cost: {
6660
7006
  input: 6,
6661
7007
  output: 30,
6662
- cacheRead: 0,
6663
- cacheWrite: 0,
7008
+ cacheRead: 0.6,
7009
+ cacheWrite: 7.5,
6664
7010
  },
6665
7011
  contextWindow: 200000,
6666
7012
  maxTokens: 8192,
6667
7013
  },
6668
- "mistralai/ministral-8b": {
6669
- id: "mistralai/ministral-8b",
6670
- name: "Mistral: Ministral 8B",
6671
- api: "openai-completions",
6672
- provider: "openrouter",
6673
- baseUrl: "https://openrouter.ai/api/v1",
6674
- reasoning: false,
6675
- input: ["text"],
6676
- cost: {
6677
- input: 0.09999999999999999,
6678
- output: 0.09999999999999999,
6679
- cacheRead: 0,
6680
- cacheWrite: 0,
6681
- },
6682
- contextWindow: 131072,
6683
- maxTokens: 4096,
6684
- },
6685
- "mistralai/ministral-3b": {
6686
- id: "mistralai/ministral-3b",
6687
- name: "Mistral: Ministral 3B",
6688
- api: "openai-completions",
6689
- provider: "openrouter",
6690
- baseUrl: "https://openrouter.ai/api/v1",
6691
- reasoning: false,
6692
- input: ["text"],
6693
- cost: {
6694
- input: 0.04,
6695
- output: 0.04,
6696
- cacheRead: 0,
6697
- cacheWrite: 0,
6698
- },
6699
- contextWindow: 131072,
6700
- maxTokens: 4096,
6701
- },
6702
7014
  "qwen/qwen-2.5-7b-instruct": {
6703
7015
  id: "qwen/qwen-2.5-7b-instruct",
6704
7016
  name: "Qwen: Qwen2.5 7B Instruct",
@@ -6767,23 +7079,6 @@ export const MODELS = {
6767
7079
  contextWindow: 32768,
6768
7080
  maxTokens: 16384,
6769
7081
  },
6770
- "mistralai/pixtral-12b": {
6771
- id: "mistralai/pixtral-12b",
6772
- name: "Mistral: Pixtral 12B",
6773
- api: "openai-completions",
6774
- provider: "openrouter",
6775
- baseUrl: "https://openrouter.ai/api/v1",
6776
- reasoning: false,
6777
- input: ["text", "image"],
6778
- cost: {
6779
- input: 0.09999999999999999,
6780
- output: 0.09999999999999999,
6781
- cacheRead: 0,
6782
- cacheWrite: 0,
6783
- },
6784
- contextWindow: 32768,
6785
- maxTokens: 4096,
6786
- },
6787
7082
  "cohere/command-r-08-2024": {
6788
7083
  id: "cohere/command-r-08-2024",
6789
7084
  name: "Cohere: Command R (08-2024)",
@@ -6878,12 +7173,12 @@ export const MODELS = {
6878
7173
  reasoning: false,
6879
7174
  input: ["text"],
6880
7175
  cost: {
6881
- input: 3.5,
6882
- output: 3.5,
7176
+ input: 4,
7177
+ output: 4,
6883
7178
  cacheRead: 0,
6884
7179
  cacheWrite: 0,
6885
7180
  },
6886
- contextWindow: 10000,
7181
+ contextWindow: 131000,
6887
7182
  maxTokens: 4096,
6888
7183
  },
6889
7184
  "meta-llama/llama-3.1-70b-instruct": {
@@ -7032,7 +7327,7 @@ export const MODELS = {
7032
7327
  input: ["text"],
7033
7328
  cost: {
7034
7329
  input: 0.03,
7035
- output: 0.06,
7330
+ output: 0.04,
7036
7331
  cacheRead: 0,
7037
7332
  cacheWrite: 0,
7038
7333
  },
@@ -7141,39 +7436,39 @@ export const MODELS = {
7141
7436
  contextWindow: 128000,
7142
7437
  maxTokens: 4096,
7143
7438
  },
7144
- "mistralai/mistral-tiny": {
7145
- id: "mistralai/mistral-tiny",
7146
- name: "Mistral Tiny",
7439
+ "mistralai/mixtral-8x7b-instruct": {
7440
+ id: "mistralai/mixtral-8x7b-instruct",
7441
+ name: "Mistral: Mixtral 8x7B Instruct",
7147
7442
  api: "openai-completions",
7148
7443
  provider: "openrouter",
7149
7444
  baseUrl: "https://openrouter.ai/api/v1",
7150
7445
  reasoning: false,
7151
7446
  input: ["text"],
7152
7447
  cost: {
7153
- input: 0.25,
7154
- output: 0.25,
7448
+ input: 0.54,
7449
+ output: 0.54,
7155
7450
  cacheRead: 0,
7156
7451
  cacheWrite: 0,
7157
7452
  },
7158
7453
  contextWindow: 32768,
7159
- maxTokens: 4096,
7454
+ maxTokens: 16384,
7160
7455
  },
7161
- "mistralai/mixtral-8x7b-instruct": {
7162
- id: "mistralai/mixtral-8x7b-instruct",
7163
- name: "Mistral: Mixtral 8x7B Instruct",
7456
+ "openrouter/auto": {
7457
+ id: "openrouter/auto",
7458
+ name: "Auto Router",
7164
7459
  api: "openai-completions",
7165
7460
  provider: "openrouter",
7166
7461
  baseUrl: "https://openrouter.ai/api/v1",
7167
- reasoning: false,
7168
- input: ["text"],
7462
+ reasoning: true,
7463
+ input: ["text", "image"],
7169
7464
  cost: {
7170
- input: 0.54,
7171
- output: 0.54,
7465
+ input: -1000000,
7466
+ output: -1000000,
7172
7467
  cacheRead: 0,
7173
7468
  cacheWrite: 0,
7174
7469
  },
7175
- contextWindow: 32768,
7176
- maxTokens: 16384,
7470
+ contextWindow: 2000000,
7471
+ maxTokens: 4096,
7177
7472
  },
7178
7473
  "openai/gpt-4-1106-preview": {
7179
7474
  id: "openai/gpt-4-1106-preview",
@@ -7260,23 +7555,6 @@ export const MODELS = {
7260
7555
  contextWindow: 16385,
7261
7556
  maxTokens: 4096,
7262
7557
  },
7263
- "openrouter/auto": {
7264
- id: "openrouter/auto",
7265
- name: "OpenRouter: Auto Router",
7266
- api: "openai-completions",
7267
- provider: "openrouter",
7268
- baseUrl: "https://openrouter.ai/api/v1",
7269
- reasoning: true,
7270
- input: ["text", "image"],
7271
- cost: {
7272
- input: 0,
7273
- output: 0,
7274
- cacheRead: 0,
7275
- cacheWrite: 0,
7276
- },
7277
- contextWindow: 2000000,
7278
- maxTokens: 30000,
7279
- },
7280
7558
  },
7281
7559
  "codex": {
7282
7560
  "gpt-5.2": {
@@ -7330,6 +7608,23 @@ export const MODELS = {
7330
7608
  contextWindow: 400000,
7331
7609
  maxTokens: 32000,
7332
7610
  },
7611
+ "gpt-5.3-codex": {
7612
+ id: "gpt-5.3-codex",
7613
+ name: "GPT-5.3 Codex",
7614
+ api: "openai-responses",
7615
+ provider: "codex",
7616
+ baseUrl: "https://chatgpt.com/backend-api",
7617
+ reasoning: true,
7618
+ input: ["text", "image"],
7619
+ cost: {
7620
+ input: 0,
7621
+ output: 0,
7622
+ cacheRead: 0,
7623
+ cacheWrite: 0,
7624
+ },
7625
+ contextWindow: 400000,
7626
+ maxTokens: 128000,
7627
+ },
7333
7628
  },
7334
7629
  };
7335
7630
  //# sourceMappingURL=models.generated.js.map