@dreb/ai 2.19.3 → 2.20.0

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.
@@ -1904,7 +1904,7 @@ export const MODELS = {
1904
1904
  cost: {
1905
1905
  input: 0.1,
1906
1906
  output: 0.4,
1907
- cacheRead: 0.03,
1907
+ cacheRead: 0.025,
1908
1908
  cacheWrite: 0,
1909
1909
  },
1910
1910
  contextWindow: 1047576,
@@ -1989,7 +1989,7 @@ export const MODELS = {
1989
1989
  cost: {
1990
1990
  input: 0.15,
1991
1991
  output: 0.6,
1992
- cacheRead: 0.08,
1992
+ cacheRead: 0.075,
1993
1993
  cacheWrite: 0,
1994
1994
  },
1995
1995
  contextWindow: 128000,
@@ -2108,7 +2108,7 @@ export const MODELS = {
2108
2108
  cost: {
2109
2109
  input: 1.25,
2110
2110
  output: 10,
2111
- cacheRead: 0.13,
2111
+ cacheRead: 0.125,
2112
2112
  cacheWrite: 0,
2113
2113
  },
2114
2114
  contextWindow: 400000,
@@ -2516,7 +2516,7 @@ export const MODELS = {
2516
2516
  cost: {
2517
2517
  input: 1.1,
2518
2518
  output: 4.4,
2519
- cacheRead: 0.28,
2519
+ cacheRead: 0.275,
2520
2520
  cacheWrite: 0,
2521
2521
  },
2522
2522
  contextWindow: 200000,
@@ -2575,23 +2575,6 @@ export const MODELS = {
2575
2575
  contextWindow: 32000,
2576
2576
  maxTokens: 8000,
2577
2577
  },
2578
- "qwen-3-235b-a22b-instruct-2507": {
2579
- id: "qwen-3-235b-a22b-instruct-2507",
2580
- name: "Qwen 3 235B Instruct",
2581
- api: "openai-completions",
2582
- provider: "cerebras",
2583
- baseUrl: "https://api.cerebras.ai/v1",
2584
- reasoning: false,
2585
- input: ["text"],
2586
- cost: {
2587
- input: 0.6,
2588
- output: 1.2,
2589
- cacheRead: 0,
2590
- cacheWrite: 0,
2591
- },
2592
- contextWindow: 131000,
2593
- maxTokens: 32000,
2594
- },
2595
2578
  },
2596
2579
  "github-copilot": {
2597
2580
  "claude-haiku-4.5": {
@@ -2759,6 +2742,25 @@ export const MODELS = {
2759
2742
  contextWindow: 128000,
2760
2743
  maxTokens: 64000,
2761
2744
  },
2745
+ "gemini-3.5-flash": {
2746
+ id: "gemini-3.5-flash",
2747
+ name: "Gemini 3.5 Flash",
2748
+ api: "openai-completions",
2749
+ provider: "github-copilot",
2750
+ baseUrl: "https://api.individual.githubcopilot.com",
2751
+ 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" },
2752
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
2753
+ reasoning: true,
2754
+ input: ["text", "image"],
2755
+ cost: {
2756
+ input: 0,
2757
+ output: 0,
2758
+ cacheRead: 0,
2759
+ cacheWrite: 0,
2760
+ },
2761
+ contextWindow: 128000,
2762
+ maxTokens: 64000,
2763
+ },
2762
2764
  "gpt-4.1": {
2763
2765
  id: "gpt-4.1",
2764
2766
  name: "GPT-4.1",
@@ -2944,57 +2946,6 @@ export const MODELS = {
2944
2946
  },
2945
2947
  },
2946
2948
  "google": {
2947
- "gemini-1.5-flash": {
2948
- id: "gemini-1.5-flash",
2949
- name: "Gemini 1.5 Flash",
2950
- api: "google-generative-ai",
2951
- provider: "google",
2952
- baseUrl: "https://generativelanguage.googleapis.com/v1beta",
2953
- reasoning: false,
2954
- input: ["text", "image"],
2955
- cost: {
2956
- input: 0.075,
2957
- output: 0.3,
2958
- cacheRead: 0.01875,
2959
- cacheWrite: 0,
2960
- },
2961
- contextWindow: 1000000,
2962
- maxTokens: 8192,
2963
- },
2964
- "gemini-1.5-flash-8b": {
2965
- id: "gemini-1.5-flash-8b",
2966
- name: "Gemini 1.5 Flash-8B",
2967
- api: "google-generative-ai",
2968
- provider: "google",
2969
- baseUrl: "https://generativelanguage.googleapis.com/v1beta",
2970
- reasoning: false,
2971
- input: ["text", "image"],
2972
- cost: {
2973
- input: 0.0375,
2974
- output: 0.15,
2975
- cacheRead: 0.01,
2976
- cacheWrite: 0,
2977
- },
2978
- contextWindow: 1000000,
2979
- maxTokens: 8192,
2980
- },
2981
- "gemini-1.5-pro": {
2982
- id: "gemini-1.5-pro",
2983
- name: "Gemini 1.5 Pro",
2984
- api: "google-generative-ai",
2985
- provider: "google",
2986
- baseUrl: "https://generativelanguage.googleapis.com/v1beta",
2987
- reasoning: false,
2988
- input: ["text", "image"],
2989
- cost: {
2990
- input: 1.25,
2991
- output: 5,
2992
- cacheRead: 0.3125,
2993
- cacheWrite: 0,
2994
- },
2995
- contextWindow: 1000000,
2996
- maxTokens: 8192,
2997
- },
2998
2949
  "gemini-2.0-flash": {
2999
2950
  id: "gemini-2.0-flash",
3000
2951
  name: "Gemini 2.0 Flash",
@@ -3014,7 +2965,7 @@ export const MODELS = {
3014
2965
  },
3015
2966
  "gemini-2.0-flash-lite": {
3016
2967
  id: "gemini-2.0-flash-lite",
3017
- name: "Gemini 2.0 Flash Lite",
2968
+ name: "Gemini 2.0 Flash-Lite",
3018
2969
  api: "google-generative-ai",
3019
2970
  provider: "google",
3020
2971
  baseUrl: "https://generativelanguage.googleapis.com/v1beta",
@@ -3048,7 +2999,7 @@ export const MODELS = {
3048
2999
  },
3049
3000
  "gemini-2.5-flash-lite": {
3050
3001
  id: "gemini-2.5-flash-lite",
3051
- name: "Gemini 2.5 Flash Lite",
3002
+ name: "Gemini 2.5 Flash-Lite",
3052
3003
  api: "google-generative-ai",
3053
3004
  provider: "google",
3054
3005
  baseUrl: "https://generativelanguage.googleapis.com/v1beta",
@@ -3063,91 +3014,6 @@ export const MODELS = {
3063
3014
  contextWindow: 1048576,
3064
3015
  maxTokens: 65536,
3065
3016
  },
3066
- "gemini-2.5-flash-lite-preview-06-17": {
3067
- id: "gemini-2.5-flash-lite-preview-06-17",
3068
- name: "Gemini 2.5 Flash Lite Preview 06-17",
3069
- api: "google-generative-ai",
3070
- provider: "google",
3071
- baseUrl: "https://generativelanguage.googleapis.com/v1beta",
3072
- reasoning: true,
3073
- input: ["text", "image"],
3074
- cost: {
3075
- input: 0.1,
3076
- output: 0.4,
3077
- cacheRead: 0.025,
3078
- cacheWrite: 0,
3079
- },
3080
- contextWindow: 1048576,
3081
- maxTokens: 65536,
3082
- },
3083
- "gemini-2.5-flash-lite-preview-09-2025": {
3084
- id: "gemini-2.5-flash-lite-preview-09-2025",
3085
- name: "Gemini 2.5 Flash Lite Preview 09-25",
3086
- api: "google-generative-ai",
3087
- provider: "google",
3088
- baseUrl: "https://generativelanguage.googleapis.com/v1beta",
3089
- reasoning: true,
3090
- input: ["text", "image"],
3091
- cost: {
3092
- input: 0.1,
3093
- output: 0.4,
3094
- cacheRead: 0.025,
3095
- cacheWrite: 0,
3096
- },
3097
- contextWindow: 1048576,
3098
- maxTokens: 65536,
3099
- },
3100
- "gemini-2.5-flash-preview-04-17": {
3101
- id: "gemini-2.5-flash-preview-04-17",
3102
- name: "Gemini 2.5 Flash Preview 04-17",
3103
- api: "google-generative-ai",
3104
- provider: "google",
3105
- baseUrl: "https://generativelanguage.googleapis.com/v1beta",
3106
- reasoning: true,
3107
- input: ["text", "image"],
3108
- cost: {
3109
- input: 0.15,
3110
- output: 0.6,
3111
- cacheRead: 0.0375,
3112
- cacheWrite: 0,
3113
- },
3114
- contextWindow: 1048576,
3115
- maxTokens: 65536,
3116
- },
3117
- "gemini-2.5-flash-preview-05-20": {
3118
- id: "gemini-2.5-flash-preview-05-20",
3119
- name: "Gemini 2.5 Flash Preview 05-20",
3120
- api: "google-generative-ai",
3121
- provider: "google",
3122
- baseUrl: "https://generativelanguage.googleapis.com/v1beta",
3123
- reasoning: true,
3124
- input: ["text", "image"],
3125
- cost: {
3126
- input: 0.15,
3127
- output: 0.6,
3128
- cacheRead: 0.0375,
3129
- cacheWrite: 0,
3130
- },
3131
- contextWindow: 1048576,
3132
- maxTokens: 65536,
3133
- },
3134
- "gemini-2.5-flash-preview-09-2025": {
3135
- id: "gemini-2.5-flash-preview-09-2025",
3136
- name: "Gemini 2.5 Flash Preview 09-25",
3137
- api: "google-generative-ai",
3138
- provider: "google",
3139
- baseUrl: "https://generativelanguage.googleapis.com/v1beta",
3140
- reasoning: true,
3141
- input: ["text", "image"],
3142
- cost: {
3143
- input: 0.3,
3144
- output: 2.5,
3145
- cacheRead: 0.075,
3146
- cacheWrite: 0,
3147
- },
3148
- contextWindow: 1048576,
3149
- maxTokens: 65536,
3150
- },
3151
3017
  "gemini-2.5-pro": {
3152
3018
  id: "gemini-2.5-pro",
3153
3019
  name: "Gemini 2.5 Pro",
@@ -3165,40 +3031,6 @@ export const MODELS = {
3165
3031
  contextWindow: 1048576,
3166
3032
  maxTokens: 65536,
3167
3033
  },
3168
- "gemini-2.5-pro-preview-05-06": {
3169
- id: "gemini-2.5-pro-preview-05-06",
3170
- name: "Gemini 2.5 Pro Preview 05-06",
3171
- api: "google-generative-ai",
3172
- provider: "google",
3173
- baseUrl: "https://generativelanguage.googleapis.com/v1beta",
3174
- reasoning: true,
3175
- input: ["text", "image"],
3176
- cost: {
3177
- input: 1.25,
3178
- output: 10,
3179
- cacheRead: 0.31,
3180
- cacheWrite: 0,
3181
- },
3182
- contextWindow: 1048576,
3183
- maxTokens: 65536,
3184
- },
3185
- "gemini-2.5-pro-preview-06-05": {
3186
- id: "gemini-2.5-pro-preview-06-05",
3187
- name: "Gemini 2.5 Pro Preview 06-05",
3188
- api: "google-generative-ai",
3189
- provider: "google",
3190
- baseUrl: "https://generativelanguage.googleapis.com/v1beta",
3191
- reasoning: true,
3192
- input: ["text", "image"],
3193
- cost: {
3194
- input: 1.25,
3195
- output: 10,
3196
- cacheRead: 0.31,
3197
- cacheWrite: 0,
3198
- },
3199
- contextWindow: 1048576,
3200
- maxTokens: 65536,
3201
- },
3202
3034
  "gemini-3-flash-preview": {
3203
3035
  id: "gemini-3-flash-preview",
3204
3036
  name: "Gemini 3 Flash Preview",
@@ -3230,8 +3062,8 @@ export const MODELS = {
3230
3062
  cacheRead: 0.2,
3231
3063
  cacheWrite: 0,
3232
3064
  },
3233
- contextWindow: 1000000,
3234
- maxTokens: 64000,
3065
+ contextWindow: 1048576,
3066
+ maxTokens: 65536,
3235
3067
  },
3236
3068
  "gemini-3.1-flash-lite": {
3237
3069
  id: "gemini-3.1-flash-lite",
@@ -3352,60 +3184,9 @@ export const MODELS = {
3352
3184
  contextWindow: 1048576,
3353
3185
  maxTokens: 65536,
3354
3186
  },
3355
- "gemini-live-2.5-flash": {
3356
- id: "gemini-live-2.5-flash",
3357
- name: "Gemini Live 2.5 Flash",
3358
- api: "google-generative-ai",
3359
- provider: "google",
3360
- baseUrl: "https://generativelanguage.googleapis.com/v1beta",
3361
- reasoning: true,
3362
- input: ["text", "image"],
3363
- cost: {
3364
- input: 0.5,
3365
- output: 2,
3366
- cacheRead: 0,
3367
- cacheWrite: 0,
3368
- },
3369
- contextWindow: 128000,
3370
- maxTokens: 8000,
3371
- },
3372
- "gemini-live-2.5-flash-preview-native-audio": {
3373
- id: "gemini-live-2.5-flash-preview-native-audio",
3374
- name: "Gemini Live 2.5 Flash Preview Native Audio",
3375
- api: "google-generative-ai",
3376
- provider: "google",
3377
- baseUrl: "https://generativelanguage.googleapis.com/v1beta",
3378
- reasoning: true,
3379
- input: ["text"],
3380
- cost: {
3381
- input: 0.5,
3382
- output: 2,
3383
- cacheRead: 0,
3384
- cacheWrite: 0,
3385
- },
3386
- contextWindow: 131072,
3387
- maxTokens: 65536,
3388
- },
3389
- "gemma-3-27b-it": {
3390
- id: "gemma-3-27b-it",
3391
- name: "Gemma 3 27B",
3392
- api: "google-generative-ai",
3393
- provider: "google",
3394
- baseUrl: "https://generativelanguage.googleapis.com/v1beta",
3395
- reasoning: false,
3396
- input: ["text", "image"],
3397
- cost: {
3398
- input: 0,
3399
- output: 0,
3400
- cacheRead: 0,
3401
- cacheWrite: 0,
3402
- },
3403
- contextWindow: 131072,
3404
- maxTokens: 8192,
3405
- },
3406
3187
  "gemma-4-26b-a4b-it": {
3407
3188
  id: "gemma-4-26b-a4b-it",
3408
- name: "Gemma 4 26B",
3189
+ name: "Gemma 4 26B A4B IT",
3409
3190
  api: "google-generative-ai",
3410
3191
  provider: "google",
3411
3192
  baseUrl: "https://generativelanguage.googleapis.com/v1beta",
@@ -3417,12 +3198,12 @@ export const MODELS = {
3417
3198
  cacheRead: 0,
3418
3199
  cacheWrite: 0,
3419
3200
  },
3420
- contextWindow: 256000,
3421
- maxTokens: 8192,
3201
+ contextWindow: 262144,
3202
+ maxTokens: 32768,
3422
3203
  },
3423
3204
  "gemma-4-31b-it": {
3424
3205
  id: "gemma-4-31b-it",
3425
- name: "Gemma 4 31B",
3206
+ name: "Gemma 4 31B IT",
3426
3207
  api: "google-generative-ai",
3427
3208
  provider: "google",
3428
3209
  baseUrl: "https://generativelanguage.googleapis.com/v1beta",
@@ -3434,8 +3215,8 @@ export const MODELS = {
3434
3215
  cacheRead: 0,
3435
3216
  cacheWrite: 0,
3436
3217
  },
3437
- contextWindow: 256000,
3438
- maxTokens: 8192,
3218
+ contextWindow: 262144,
3219
+ maxTokens: 32768,
3439
3220
  },
3440
3221
  },
3441
3222
  "google-antigravity": {
@@ -4119,7 +3900,7 @@ export const MODELS = {
4119
3900
  cost: {
4120
3901
  input: 1,
4121
3902
  output: 3,
4122
- cacheRead: 0,
3903
+ cacheRead: 0.5,
4123
3904
  cacheWrite: 0,
4124
3905
  },
4125
3906
  contextWindow: 262144,
@@ -4136,7 +3917,7 @@ export const MODELS = {
4136
3917
  cost: {
4137
3918
  input: 0.15,
4138
3919
  output: 0.6,
4139
- cacheRead: 0,
3920
+ cacheRead: 0.075,
4140
3921
  cacheWrite: 0,
4141
3922
  },
4142
3923
  contextWindow: 131072,
@@ -4153,7 +3934,7 @@ export const MODELS = {
4153
3934
  cost: {
4154
3935
  input: 0.075,
4155
3936
  output: 0.3,
4156
- cacheRead: 0,
3937
+ cacheRead: 0.0375,
4157
3938
  cacheWrite: 0,
4158
3939
  },
4159
3940
  contextWindow: 131072,
@@ -4438,9 +4219,9 @@ export const MODELS = {
4438
4219
  reasoning: true,
4439
4220
  input: ["text"],
4440
4221
  cost: {
4441
- input: 1.74,
4442
- output: 3.48,
4443
- cacheRead: 0.145,
4222
+ input: 0.435,
4223
+ output: 0.87,
4224
+ cacheRead: 0.003625,
4444
4225
  cacheWrite: 0,
4445
4226
  },
4446
4227
  contextWindow: 1048576,
@@ -5295,7 +5076,7 @@ export const MODELS = {
5295
5076
  cost: {
5296
5077
  input: 0.1,
5297
5078
  output: 0.4,
5298
- cacheRead: 0.03,
5079
+ cacheRead: 0.025,
5299
5080
  cacheWrite: 0,
5300
5081
  },
5301
5082
  contextWindow: 1047576,
@@ -5380,7 +5161,7 @@ export const MODELS = {
5380
5161
  cost: {
5381
5162
  input: 0.15,
5382
5163
  output: 0.6,
5383
- cacheRead: 0.08,
5164
+ cacheRead: 0.075,
5384
5165
  cacheWrite: 0,
5385
5166
  },
5386
5167
  contextWindow: 128000,
@@ -5499,7 +5280,7 @@ export const MODELS = {
5499
5280
  cost: {
5500
5281
  input: 1.25,
5501
5282
  output: 10,
5502
- cacheRead: 0.13,
5283
+ cacheRead: 0.125,
5503
5284
  cacheWrite: 0,
5504
5285
  },
5505
5286
  contextWindow: 400000,
@@ -5907,7 +5688,7 @@ export const MODELS = {
5907
5688
  cost: {
5908
5689
  input: 1.1,
5909
5690
  output: 4.4,
5910
- cacheRead: 0.28,
5691
+ cacheRead: 0.275,
5911
5692
  cacheWrite: 0,
5912
5693
  },
5913
5694
  contextWindow: 200000,
@@ -6085,7 +5866,7 @@ export const MODELS = {
6085
5866
  cacheWrite: 0,
6086
5867
  },
6087
5868
  contextWindow: 200000,
6088
- maxTokens: 128000,
5869
+ maxTokens: 32000,
6089
5870
  },
6090
5871
  "claude-haiku-4-5": {
6091
5872
  id: "claude-haiku-4-5",
@@ -6274,6 +6055,23 @@ export const MODELS = {
6274
6055
  contextWindow: 1048576,
6275
6056
  maxTokens: 65536,
6276
6057
  },
6058
+ "gemini-3.5-flash": {
6059
+ id: "gemini-3.5-flash",
6060
+ name: "Gemini 3.5 Flash",
6061
+ api: "google-generative-ai",
6062
+ provider: "opencode",
6063
+ baseUrl: "https://opencode.ai/zen/v1",
6064
+ reasoning: true,
6065
+ input: ["text", "image"],
6066
+ cost: {
6067
+ input: 1.5,
6068
+ output: 9,
6069
+ cacheRead: 0.15,
6070
+ cacheWrite: 0,
6071
+ },
6072
+ contextWindow: 1048576,
6073
+ maxTokens: 65536,
6074
+ },
6277
6075
  "glm-5": {
6278
6076
  id: "glm-5",
6279
6077
  name: "GLM-5",
@@ -6580,6 +6378,23 @@ export const MODELS = {
6580
6378
  contextWindow: 1050000,
6581
6379
  maxTokens: 128000,
6582
6380
  },
6381
+ "grok-build-0.1": {
6382
+ id: "grok-build-0.1",
6383
+ name: "Grok Build 0.1",
6384
+ api: "openai-completions",
6385
+ provider: "opencode",
6386
+ baseUrl: "https://opencode.ai/zen/v1",
6387
+ reasoning: true,
6388
+ input: ["text", "image"],
6389
+ cost: {
6390
+ input: 1,
6391
+ output: 2,
6392
+ cacheRead: 0.2,
6393
+ cacheWrite: 0,
6394
+ },
6395
+ contextWindow: 256000,
6396
+ maxTokens: 256000,
6397
+ },
6583
6398
  "kimi-k2.5": {
6584
6399
  id: "kimi-k2.5",
6585
6400
  name: "Kimi K2.5",
@@ -6614,35 +6429,35 @@ export const MODELS = {
6614
6429
  contextWindow: 262144,
6615
6430
  maxTokens: 65536,
6616
6431
  },
6617
- "minimax-m2.5": {
6618
- id: "minimax-m2.5",
6619
- name: "MiniMax M2.5",
6432
+ "mimo-v2.5-free": {
6433
+ id: "mimo-v2.5-free",
6434
+ name: "MiMo V2.5 Free",
6620
6435
  api: "openai-completions",
6621
6436
  provider: "opencode",
6622
6437
  baseUrl: "https://opencode.ai/zen/v1",
6623
6438
  reasoning: true,
6624
- input: ["text"],
6439
+ input: ["text", "image"],
6625
6440
  cost: {
6626
- input: 0.3,
6627
- output: 1.2,
6628
- cacheRead: 0.06,
6441
+ input: 0,
6442
+ output: 0,
6443
+ cacheRead: 0,
6629
6444
  cacheWrite: 0,
6630
6445
  },
6631
- contextWindow: 204800,
6632
- maxTokens: 131072,
6446
+ contextWindow: 1000000,
6447
+ maxTokens: 128000,
6633
6448
  },
6634
- "minimax-m2.5-free": {
6635
- id: "minimax-m2.5-free",
6636
- name: "MiniMax M2.5 Free",
6637
- api: "anthropic-messages",
6449
+ "minimax-m2.5": {
6450
+ id: "minimax-m2.5",
6451
+ name: "MiniMax M2.5",
6452
+ api: "openai-completions",
6638
6453
  provider: "opencode",
6639
- baseUrl: "https://opencode.ai/zen",
6454
+ baseUrl: "https://opencode.ai/zen/v1",
6640
6455
  reasoning: true,
6641
6456
  input: ["text"],
6642
6457
  cost: {
6643
- input: 0,
6644
- output: 0,
6645
- cacheRead: 0,
6458
+ input: 0.3,
6459
+ output: 1.2,
6460
+ cacheRead: 0.06,
6646
6461
  cacheWrite: 0,
6647
6462
  },
6648
6463
  contextWindow: 204800,
@@ -6716,23 +6531,6 @@ export const MODELS = {
6716
6531
  contextWindow: 262144,
6717
6532
  maxTokens: 65536,
6718
6533
  },
6719
- "qwen3.6-plus-free": {
6720
- id: "qwen3.6-plus-free",
6721
- name: "Qwen3.6 Plus Free",
6722
- api: "anthropic-messages",
6723
- provider: "opencode",
6724
- baseUrl: "https://opencode.ai/zen",
6725
- reasoning: true,
6726
- input: ["text", "image"],
6727
- cost: {
6728
- input: 0,
6729
- output: 0,
6730
- cacheRead: 0,
6731
- cacheWrite: 0,
6732
- },
6733
- contextWindow: 262144,
6734
- maxTokens: 65536,
6735
- },
6736
6534
  },
6737
6535
  "opencode-go": {
6738
6536
  "deepseek-v4-flash": {
@@ -6846,9 +6644,9 @@ export const MODELS = {
6846
6644
  reasoning: true,
6847
6645
  input: ["text", "image"],
6848
6646
  cost: {
6849
- input: 0.4,
6850
- output: 2,
6851
- cacheRead: 0.08,
6647
+ input: 0.14,
6648
+ output: 0.28,
6649
+ cacheRead: 0.0028,
6852
6650
  cacheWrite: 0,
6853
6651
  },
6854
6652
  contextWindow: 1000000,
@@ -6863,9 +6661,9 @@ export const MODELS = {
6863
6661
  reasoning: true,
6864
6662
  input: ["text"],
6865
6663
  cost: {
6866
- input: 1,
6867
- output: 3,
6868
- cacheRead: 0.2,
6664
+ input: 1.74,
6665
+ output: 3.48,
6666
+ cacheRead: 0.0145,
6869
6667
  cacheWrite: 0,
6870
6668
  },
6871
6669
  contextWindow: 1048576,
@@ -6939,6 +6737,23 @@ export const MODELS = {
6939
6737
  contextWindow: 262144,
6940
6738
  maxTokens: 65536,
6941
6739
  },
6740
+ "qwen3.7-max": {
6741
+ id: "qwen3.7-max",
6742
+ name: "Qwen3.7 Max",
6743
+ api: "anthropic-messages",
6744
+ provider: "opencode-go",
6745
+ baseUrl: "https://opencode.ai/zen/go",
6746
+ reasoning: true,
6747
+ input: ["text"],
6748
+ cost: {
6749
+ input: 2.5,
6750
+ output: 7.5,
6751
+ cacheRead: 0.5,
6752
+ cacheWrite: 3.125,
6753
+ },
6754
+ contextWindow: 1000000,
6755
+ maxTokens: 65536,
6756
+ },
6942
6757
  },
6943
6758
  "openrouter": {
6944
6759
  "ai21/jamba-large-1.7": {
@@ -6958,23 +6773,6 @@ export const MODELS = {
6958
6773
  contextWindow: 256000,
6959
6774
  maxTokens: 4096,
6960
6775
  },
6961
- "alibaba/tongyi-deepresearch-30b-a3b": {
6962
- id: "alibaba/tongyi-deepresearch-30b-a3b",
6963
- name: "Tongyi DeepResearch 30B A3B",
6964
- api: "openai-completions",
6965
- provider: "openrouter",
6966
- baseUrl: "https://openrouter.ai/api/v1",
6967
- reasoning: true,
6968
- input: ["text"],
6969
- cost: {
6970
- input: 0.09,
6971
- output: 0.44999999999999996,
6972
- cacheRead: 0.09,
6973
- cacheWrite: 0,
6974
- },
6975
- contextWindow: 131072,
6976
- maxTokens: 131072,
6977
- },
6978
6776
  "amazon/nova-2-lite-v1": {
6979
6777
  id: "amazon/nova-2-lite-v1",
6980
6778
  name: "Amazon: Nova 2 Lite",
@@ -7281,23 +7079,6 @@ export const MODELS = {
7281
7079
  contextWindow: 1000000,
7282
7080
  maxTokens: 128000,
7283
7081
  },
7284
- "arcee-ai/trinity-large-preview": {
7285
- id: "arcee-ai/trinity-large-preview",
7286
- name: "Arcee AI: Trinity Large Preview",
7287
- api: "openai-completions",
7288
- provider: "openrouter",
7289
- baseUrl: "https://openrouter.ai/api/v1",
7290
- reasoning: false,
7291
- input: ["text"],
7292
- cost: {
7293
- input: 0.15,
7294
- output: 0.44999999999999996,
7295
- cacheRead: 0,
7296
- cacheWrite: 0,
7297
- },
7298
- contextWindow: 131000,
7299
- maxTokens: 4096,
7300
- },
7301
7082
  "arcee-ai/trinity-large-thinking": {
7302
7083
  id: "arcee-ai/trinity-large-thinking",
7303
7084
  name: "Arcee AI: Trinity Large Thinking",
@@ -7315,23 +7096,6 @@ export const MODELS = {
7315
7096
  contextWindow: 262144,
7316
7097
  maxTokens: 262144,
7317
7098
  },
7318
- "arcee-ai/trinity-large-thinking:free": {
7319
- id: "arcee-ai/trinity-large-thinking:free",
7320
- name: "Arcee AI: Trinity Large Thinking (free)",
7321
- api: "openai-completions",
7322
- provider: "openrouter",
7323
- baseUrl: "https://openrouter.ai/api/v1",
7324
- reasoning: true,
7325
- input: ["text"],
7326
- cost: {
7327
- input: 0,
7328
- output: 0,
7329
- cacheRead: 0,
7330
- cacheWrite: 0,
7331
- },
7332
- contextWindow: 262144,
7333
- maxTokens: 80000,
7334
- },
7335
7099
  "arcee-ai/trinity-mini": {
7336
7100
  id: "arcee-ai/trinity-mini",
7337
7101
  name: "Arcee AI: Trinity Mini",
@@ -7383,23 +7147,6 @@ export const MODELS = {
7383
7147
  contextWindow: 2000000,
7384
7148
  maxTokens: 30000,
7385
7149
  },
7386
- "baidu/cobuddy:free": {
7387
- id: "baidu/cobuddy:free",
7388
- name: "Baidu Qianfan: CoBuddy (free)",
7389
- api: "openai-completions",
7390
- provider: "openrouter",
7391
- baseUrl: "https://openrouter.ai/api/v1",
7392
- reasoning: true,
7393
- input: ["text"],
7394
- cost: {
7395
- input: 0,
7396
- output: 0,
7397
- cacheRead: 0,
7398
- cacheWrite: 0,
7399
- },
7400
- contextWindow: 131072,
7401
- maxTokens: 65536,
7402
- },
7403
7150
  "baidu/ernie-4.5-21b-a3b": {
7404
7151
  id: "baidu/ernie-4.5-21b-a3b",
7405
7152
  name: "Baidu: ERNIE 4.5 21B A3B",
@@ -7545,13 +7292,13 @@ export const MODELS = {
7545
7292
  reasoning: false,
7546
7293
  input: ["text"],
7547
7294
  cost: {
7548
- input: 0.32,
7549
- output: 0.8899999999999999,
7295
+ input: 0.2288,
7296
+ output: 0.9144,
7550
7297
  cacheRead: 0,
7551
7298
  cacheWrite: 0,
7552
7299
  },
7553
- contextWindow: 163840,
7554
- maxTokens: 16384,
7300
+ contextWindow: 131072,
7301
+ maxTokens: 16000,
7555
7302
  },
7556
7303
  "deepseek/deepseek-chat-v3-0324": {
7557
7304
  id: "deepseek/deepseek-chat-v3-0324",
@@ -7681,13 +7428,13 @@ export const MODELS = {
7681
7428
  reasoning: true,
7682
7429
  input: ["text"],
7683
7430
  cost: {
7684
- input: 0.112,
7685
- output: 0.224,
7686
- cacheRead: 0.022,
7431
+ input: 0.09999999999999999,
7432
+ output: 0.19999999999999998,
7433
+ cacheRead: 0.02,
7687
7434
  cacheWrite: 0,
7688
7435
  },
7689
7436
  contextWindow: 1048576,
7690
- maxTokens: 4096,
7437
+ maxTokens: 16384,
7691
7438
  },
7692
7439
  "deepseek/deepseek-v4-flash:free": {
7693
7440
  id: "deepseek/deepseek-v4-flash:free",
@@ -7754,7 +7501,7 @@ export const MODELS = {
7754
7501
  cacheRead: 0.024999999999999998,
7755
7502
  cacheWrite: 0.08333333333333334,
7756
7503
  },
7757
- contextWindow: 1048576,
7504
+ contextWindow: 1000000,
7758
7505
  maxTokens: 8192,
7759
7506
  },
7760
7507
  "google/gemini-2.0-flash-lite-001": {
@@ -8123,9 +7870,9 @@ export const MODELS = {
8123
7870
  reasoning: false,
8124
7871
  input: ["text"],
8125
7872
  cost: {
8126
- input: 0.3,
8127
- output: 2.5,
8128
- cacheRead: 0.06,
7873
+ input: 0.075,
7874
+ output: 0.625,
7875
+ cacheRead: 0.015,
8129
7876
  cacheWrite: 0,
8130
7877
  },
8131
7878
  contextWindow: 262144,
@@ -8349,7 +8096,7 @@ export const MODELS = {
8349
8096
  cacheRead: 0,
8350
8097
  cacheWrite: 0,
8351
8098
  },
8352
- contextWindow: 204800,
8099
+ contextWindow: 262144,
8353
8100
  maxTokens: 8192,
8354
8101
  },
8355
8102
  "minimax/minimax-m2.7": {
@@ -8811,6 +8558,23 @@ export const MODELS = {
8811
8558
  contextWindow: 262144,
8812
8559
  maxTokens: 262142,
8813
8560
  },
8561
+ "moonshotai/kimi-k2.6:free": {
8562
+ id: "moonshotai/kimi-k2.6:free",
8563
+ name: "MoonshotAI: Kimi K2.6 (free)",
8564
+ api: "openai-completions",
8565
+ provider: "openrouter",
8566
+ baseUrl: "https://openrouter.ai/api/v1",
8567
+ reasoning: true,
8568
+ input: ["text", "image"],
8569
+ cost: {
8570
+ input: 0,
8571
+ output: 0,
8572
+ cacheRead: 0,
8573
+ cacheWrite: 0,
8574
+ },
8575
+ contextWindow: 262144,
8576
+ maxTokens: 4096,
8577
+ },
8814
8578
  "nex-agi/deepseek-v3.1-nex-n1": {
8815
8579
  id: "nex-agi/deepseek-v3.1-nex-n1",
8816
8580
  name: "Nex AGI: DeepSeek V3.1 Nex N1",
@@ -9400,11 +9164,11 @@ export const MODELS = {
9400
9164
  cost: {
9401
9165
  input: 1.25,
9402
9166
  output: 10,
9403
- cacheRead: 0.125,
9167
+ cacheRead: 0.13,
9404
9168
  cacheWrite: 0,
9405
9169
  },
9406
9170
  contextWindow: 128000,
9407
- maxTokens: 16384,
9171
+ maxTokens: 32000,
9408
9172
  },
9409
9173
  "openai/gpt-5.1-codex": {
9410
9174
  id: "openai/gpt-5.1-codex",
@@ -9417,7 +9181,7 @@ export const MODELS = {
9417
9181
  cost: {
9418
9182
  input: 1.25,
9419
9183
  output: 10,
9420
- cacheRead: 0.125,
9184
+ cacheRead: 0.13,
9421
9185
  cacheWrite: 0,
9422
9186
  },
9423
9187
  contextWindow: 400000,
@@ -9451,11 +9215,11 @@ export const MODELS = {
9451
9215
  cost: {
9452
9216
  input: 0.25,
9453
9217
  output: 2,
9454
- cacheRead: 0.03,
9218
+ cacheRead: 0.024999999999999998,
9455
9219
  cacheWrite: 0,
9456
9220
  },
9457
9221
  contextWindow: 400000,
9458
- maxTokens: 128000,
9222
+ maxTokens: 100000,
9459
9223
  },
9460
9224
  "openai/gpt-5.2": {
9461
9225
  id: "openai/gpt-5.2",
@@ -9489,7 +9253,7 @@ export const MODELS = {
9489
9253
  cacheWrite: 0,
9490
9254
  },
9491
9255
  contextWindow: 128000,
9492
- maxTokens: 32000,
9256
+ maxTokens: 16384,
9493
9257
  },
9494
9258
  "openai/gpt-5.2-codex": {
9495
9259
  id: "openai/gpt-5.2-codex",
@@ -10015,8 +9779,8 @@ export const MODELS = {
10015
9779
  cacheRead: 0,
10016
9780
  cacheWrite: 0,
10017
9781
  },
10018
- contextWindow: 131072,
10019
- maxTokens: 8192,
9782
+ contextWindow: 262144,
9783
+ maxTokens: 32768,
10020
9784
  },
10021
9785
  "poolside/laguna-xs.2:free": {
10022
9786
  id: "poolside/laguna-xs.2:free",
@@ -10032,8 +9796,8 @@ export const MODELS = {
10032
9796
  cacheRead: 0,
10033
9797
  cacheWrite: 0,
10034
9798
  },
10035
- contextWindow: 131072,
10036
- maxTokens: 8192,
9799
+ contextWindow: 262144,
9800
+ maxTokens: 32768,
10037
9801
  },
10038
9802
  "prime-intellect/intellect-3": {
10039
9803
  id: "prime-intellect/intellect-3",
@@ -10115,7 +9879,7 @@ export const MODELS = {
10115
9879
  input: 0.26,
10116
9880
  output: 0.78,
10117
9881
  cacheRead: 0,
10118
- cacheWrite: 0.325,
9882
+ cacheWrite: 0,
10119
9883
  },
10120
9884
  contextWindow: 1000000,
10121
9885
  maxTokens: 32768,
@@ -10611,7 +10375,7 @@ export const MODELS = {
10611
10375
  cacheWrite: 0,
10612
10376
  },
10613
10377
  contextWindow: 262144,
10614
- maxTokens: 65536,
10378
+ maxTokens: 262144,
10615
10379
  },
10616
10380
  "qwen/qwen3.5-27b": {
10617
10381
  id: "qwen/qwen3.5-27b",
@@ -10658,7 +10422,7 @@ export const MODELS = {
10658
10422
  cost: {
10659
10423
  input: 0.39,
10660
10424
  output: 2.34,
10661
- cacheRead: 0.195,
10425
+ cacheRead: 0,
10662
10426
  cacheWrite: 0,
10663
10427
  },
10664
10428
  contextWindow: 262144,
@@ -10693,7 +10457,7 @@ export const MODELS = {
10693
10457
  input: 0.065,
10694
10458
  output: 0.26,
10695
10459
  cacheRead: 0,
10696
- cacheWrite: 0.08125,
10460
+ cacheWrite: 0,
10697
10461
  },
10698
10462
  contextWindow: 1000000,
10699
10463
  maxTokens: 65536,
@@ -10710,7 +10474,7 @@ export const MODELS = {
10710
10474
  input: 0.26,
10711
10475
  output: 1.56,
10712
10476
  cacheRead: 0,
10713
- cacheWrite: 0.325,
10477
+ cacheWrite: 0,
10714
10478
  },
10715
10479
  contextWindow: 1000000,
10716
10480
  maxTokens: 65536,
@@ -10727,7 +10491,7 @@ export const MODELS = {
10727
10491
  input: 0.3,
10728
10492
  output: 1.7999999999999998,
10729
10493
  cacheRead: 0,
10730
- cacheWrite: 0,
10494
+ cacheWrite: 0.375,
10731
10495
  },
10732
10496
  contextWindow: 1000000,
10733
10497
  maxTokens: 65536,
@@ -10741,13 +10505,13 @@ export const MODELS = {
10741
10505
  reasoning: true,
10742
10506
  input: ["text", "image"],
10743
10507
  cost: {
10744
- input: 0.32,
10508
+ input: 0.29,
10745
10509
  output: 3.1999999999999997,
10746
10510
  cacheRead: 0,
10747
10511
  cacheWrite: 0,
10748
10512
  },
10749
10513
  contextWindow: 262144,
10750
- maxTokens: 81920,
10514
+ maxTokens: 262140,
10751
10515
  },
10752
10516
  "qwen/qwen3.6-35b-a3b": {
10753
10517
  id: "qwen/qwen3.6-35b-a3b",
@@ -10758,13 +10522,13 @@ export const MODELS = {
10758
10522
  reasoning: true,
10759
10523
  input: ["text", "image"],
10760
10524
  cost: {
10761
- input: 0.15,
10525
+ input: 0.14,
10762
10526
  output: 1,
10763
- cacheRead: 0.049999999999999996,
10527
+ cacheRead: 0,
10764
10528
  cacheWrite: 0,
10765
10529
  },
10766
10530
  contextWindow: 262144,
10767
- maxTokens: 262144,
10531
+ maxTokens: 262140,
10768
10532
  },
10769
10533
  "qwen/qwen3.6-flash": {
10770
10534
  id: "qwen/qwen3.6-flash",
@@ -10817,6 +10581,23 @@ export const MODELS = {
10817
10581
  contextWindow: 1000000,
10818
10582
  maxTokens: 65536,
10819
10583
  },
10584
+ "qwen/qwen3.7-max": {
10585
+ id: "qwen/qwen3.7-max",
10586
+ name: "Qwen: Qwen3.7 Max",
10587
+ api: "openai-completions",
10588
+ provider: "openrouter",
10589
+ baseUrl: "https://openrouter.ai/api/v1",
10590
+ reasoning: true,
10591
+ input: ["text"],
10592
+ cost: {
10593
+ input: 1.25,
10594
+ output: 3.75,
10595
+ cacheRead: 0.25,
10596
+ cacheWrite: 1.5625,
10597
+ },
10598
+ contextWindow: 1000000,
10599
+ maxTokens: 65536,
10600
+ },
10820
10601
  "rekaai/reka-edge": {
10821
10602
  id: "rekaai/reka-edge",
10822
10603
  name: "Reka Edge",
@@ -10894,13 +10675,13 @@ export const MODELS = {
10894
10675
  reasoning: true,
10895
10676
  input: ["text"],
10896
10677
  cost: {
10897
- input: 0.09999999999999999,
10678
+ input: 0.09,
10898
10679
  output: 0.3,
10899
- cacheRead: 0,
10680
+ cacheRead: 0.02,
10900
10681
  cacheWrite: 0,
10901
10682
  },
10902
10683
  contextWindow: 262144,
10903
- maxTokens: 65536,
10684
+ maxTokens: 16384,
10904
10685
  },
10905
10686
  "tencent/hy3-preview": {
10906
10687
  id: "tencent/hy3-preview",
@@ -10911,13 +10692,13 @@ export const MODELS = {
10911
10692
  reasoning: true,
10912
10693
  input: ["text"],
10913
10694
  cost: {
10914
- input: 0.06599999999999999,
10915
- output: 0.26,
10916
- cacheRead: 0.029,
10695
+ input: 0.063,
10696
+ output: 0.21,
10697
+ cacheRead: 0.020999999999999998,
10917
10698
  cacheWrite: 0,
10918
10699
  },
10919
10700
  contextWindow: 262144,
10920
- maxTokens: 262144,
10701
+ maxTokens: 4096,
10921
10702
  },
10922
10703
  "thedrummer/rocinante-12b": {
10923
10704
  id: "thedrummer/rocinante-12b",
@@ -11004,6 +10785,23 @@ export const MODELS = {
11004
10785
  contextWindow: 1000000,
11005
10786
  maxTokens: 4096,
11006
10787
  },
10788
+ "x-ai/grok-build-0.1": {
10789
+ id: "x-ai/grok-build-0.1",
10790
+ name: "xAI: Grok Build 0.1",
10791
+ api: "openai-completions",
10792
+ provider: "openrouter",
10793
+ baseUrl: "https://openrouter.ai/api/v1",
10794
+ reasoning: true,
10795
+ input: ["text", "image"],
10796
+ cost: {
10797
+ input: 1,
10798
+ output: 2,
10799
+ cacheRead: 0.19999999999999998,
10800
+ cacheWrite: 0,
10801
+ },
10802
+ contextWindow: 256000,
10803
+ maxTokens: 4096,
10804
+ },
11007
10805
  "xiaomi/mimo-v2-flash": {
11008
10806
  id: "xiaomi/mimo-v2-flash",
11009
10807
  name: "Xiaomi: MiMo-V2-Flash",
@@ -11064,9 +10862,9 @@ export const MODELS = {
11064
10862
  reasoning: true,
11065
10863
  input: ["text", "image"],
11066
10864
  cost: {
11067
- input: 0.39999999999999997,
11068
- output: 2,
11069
- cacheRead: 0.08,
10865
+ input: 0.14,
10866
+ output: 0.28,
10867
+ cacheRead: 0.0028,
11070
10868
  cacheWrite: 0,
11071
10869
  },
11072
10870
  contextWindow: 1048576,
@@ -11081,13 +10879,13 @@ export const MODELS = {
11081
10879
  reasoning: true,
11082
10880
  input: ["text"],
11083
10881
  cost: {
11084
- input: 1,
11085
- output: 3,
11086
- cacheRead: 0.19999999999999998,
10882
+ input: 0.435,
10883
+ output: 0.87,
10884
+ cacheRead: 0.0036,
11087
10885
  cacheWrite: 0,
11088
10886
  },
11089
10887
  contextWindow: 1048576,
11090
- maxTokens: 16384,
10888
+ maxTokens: 131072,
11091
10889
  },
11092
10890
  "z-ai/glm-4-32b": {
11093
10891
  id: "z-ai/glm-4-32b",
@@ -11132,13 +10930,13 @@ export const MODELS = {
11132
10930
  reasoning: true,
11133
10931
  input: ["text"],
11134
10932
  cost: {
11135
- input: 0.13,
11136
- output: 0.85,
11137
- cacheRead: 0.024999999999999998,
10933
+ input: 0.125,
10934
+ output: 0.84,
10935
+ cacheRead: 0,
11138
10936
  cacheWrite: 0,
11139
10937
  },
11140
10938
  contextWindow: 131072,
11141
- maxTokens: 98304,
10939
+ maxTokens: 131070,
11142
10940
  },
11143
10941
  "z-ai/glm-4.5-air:free": {
11144
10942
  id: "z-ai/glm-4.5-air:free",
@@ -11285,13 +11083,13 @@ export const MODELS = {
11285
11083
  reasoning: true,
11286
11084
  input: ["text"],
11287
11085
  cost: {
11288
- input: 0,
11289
- output: 0,
11290
- cacheRead: 0,
11086
+ input: 0.98,
11087
+ output: 3.08,
11088
+ cacheRead: 0.182,
11291
11089
  cacheWrite: 0,
11292
11090
  },
11293
- contextWindow: 202800,
11294
- maxTokens: 202800,
11091
+ contextWindow: 202752,
11092
+ maxTokens: 4096,
11295
11093
  },
11296
11094
  "z-ai/glm-5v-turbo": {
11297
11095
  id: "z-ai/glm-5v-turbo",
@@ -11754,6 +11552,23 @@ export const MODELS = {
11754
11552
  contextWindow: 1000000,
11755
11553
  maxTokens: 64000,
11756
11554
  },
11555
+ "alibaba/qwen3.7-max": {
11556
+ id: "alibaba/qwen3.7-max",
11557
+ name: "Qwen 3.7 Max",
11558
+ api: "anthropic-messages",
11559
+ provider: "vercel-ai-gateway",
11560
+ baseUrl: "https://ai-gateway.vercel.sh",
11561
+ reasoning: true,
11562
+ input: ["text", "image"],
11563
+ cost: {
11564
+ input: 1.25,
11565
+ output: 3.75,
11566
+ cacheRead: 0.25,
11567
+ cacheWrite: 1.5625,
11568
+ },
11569
+ contextWindow: 991000,
11570
+ maxTokens: 64000,
11571
+ },
11757
11572
  "anthropic/claude-3-haiku": {
11758
11573
  id: "anthropic/claude-3-haiku",
11759
11574
  name: "Claude 3 Haiku",
@@ -12640,7 +12455,7 @@ export const MODELS = {
12640
12455
  },
12641
12456
  "minimax/minimax-m2.7": {
12642
12457
  id: "minimax/minimax-m2.7",
12643
- name: "Minimax M2.7",
12458
+ name: "MiniMax M2.7",
12644
12459
  api: "anthropic-messages",
12645
12460
  provider: "vercel-ai-gateway",
12646
12461
  baseUrl: "https://ai-gateway.vercel.sh",
@@ -12791,6 +12606,23 @@ export const MODELS = {
12791
12606
  contextWindow: 128000,
12792
12607
  maxTokens: 64000,
12793
12608
  },
12609
+ "mistral/mistral-medium-3.5": {
12610
+ id: "mistral/mistral-medium-3.5",
12611
+ name: "Mistral Medium Latest",
12612
+ api: "anthropic-messages",
12613
+ provider: "vercel-ai-gateway",
12614
+ baseUrl: "https://ai-gateway.vercel.sh",
12615
+ reasoning: true,
12616
+ input: ["text"],
12617
+ cost: {
12618
+ input: 1.5,
12619
+ output: 7.5,
12620
+ cacheRead: 0,
12621
+ cacheWrite: 0,
12622
+ },
12623
+ contextWindow: 256000,
12624
+ maxTokens: 256000,
12625
+ },
12794
12626
  "mistral/mistral-small": {
12795
12627
  id: "mistral/mistral-small",
12796
12628
  name: "Mistral Small",
@@ -13794,6 +13626,23 @@ export const MODELS = {
13794
13626
  contextWindow: 1000000,
13795
13627
  maxTokens: 1000000,
13796
13628
  },
13629
+ "xai/grok-build-0.1": {
13630
+ id: "xai/grok-build-0.1",
13631
+ name: "Grok Build 0.1",
13632
+ api: "anthropic-messages",
13633
+ provider: "vercel-ai-gateway",
13634
+ baseUrl: "https://ai-gateway.vercel.sh",
13635
+ reasoning: true,
13636
+ input: ["text", "image"],
13637
+ cost: {
13638
+ input: 1,
13639
+ output: 2,
13640
+ cacheRead: 0.19999999999999998,
13641
+ cacheWrite: 0,
13642
+ },
13643
+ contextWindow: 256000,
13644
+ maxTokens: 256000,
13645
+ },
13797
13646
  "xiaomi/mimo-v2-flash": {
13798
13647
  id: "xiaomi/mimo-v2-flash",
13799
13648
  name: "MiMo V2 Flash",
@@ -13837,9 +13686,9 @@ export const MODELS = {
13837
13686
  reasoning: true,
13838
13687
  input: ["text", "image"],
13839
13688
  cost: {
13840
- input: 0.39999999999999997,
13841
- output: 2,
13842
- cacheRead: 0.08,
13689
+ input: 0.14,
13690
+ output: 0.28,
13691
+ cacheRead: 0.0028,
13843
13692
  cacheWrite: 0,
13844
13693
  },
13845
13694
  contextWindow: 1050000,
@@ -13854,9 +13703,9 @@ export const MODELS = {
13854
13703
  reasoning: true,
13855
13704
  input: ["text", "image"],
13856
13705
  cost: {
13857
- input: 1,
13858
- output: 3,
13859
- cacheRead: 0.19999999999999998,
13706
+ input: 0.435,
13707
+ output: 0.87,
13708
+ cacheRead: 0.0036,
13860
13709
  cacheWrite: 0,
13861
13710
  },
13862
13711
  contextWindow: 1050000,
@@ -14085,108 +13934,6 @@ export const MODELS = {
14085
13934
  },
14086
13935
  },
14087
13936
  "xai": {
14088
- "grok-2": {
14089
- id: "grok-2",
14090
- name: "Grok 2",
14091
- api: "openai-completions",
14092
- provider: "xai",
14093
- baseUrl: "https://api.x.ai/v1",
14094
- reasoning: false,
14095
- input: ["text"],
14096
- cost: {
14097
- input: 2,
14098
- output: 10,
14099
- cacheRead: 2,
14100
- cacheWrite: 0,
14101
- },
14102
- contextWindow: 131072,
14103
- maxTokens: 8192,
14104
- },
14105
- "grok-2-1212": {
14106
- id: "grok-2-1212",
14107
- name: "Grok 2 (1212)",
14108
- api: "openai-completions",
14109
- provider: "xai",
14110
- baseUrl: "https://api.x.ai/v1",
14111
- reasoning: false,
14112
- input: ["text"],
14113
- cost: {
14114
- input: 2,
14115
- output: 10,
14116
- cacheRead: 2,
14117
- cacheWrite: 0,
14118
- },
14119
- contextWindow: 131072,
14120
- maxTokens: 8192,
14121
- },
14122
- "grok-2-latest": {
14123
- id: "grok-2-latest",
14124
- name: "Grok 2 Latest",
14125
- api: "openai-completions",
14126
- provider: "xai",
14127
- baseUrl: "https://api.x.ai/v1",
14128
- reasoning: false,
14129
- input: ["text"],
14130
- cost: {
14131
- input: 2,
14132
- output: 10,
14133
- cacheRead: 2,
14134
- cacheWrite: 0,
14135
- },
14136
- contextWindow: 131072,
14137
- maxTokens: 8192,
14138
- },
14139
- "grok-2-vision": {
14140
- id: "grok-2-vision",
14141
- name: "Grok 2 Vision",
14142
- api: "openai-completions",
14143
- provider: "xai",
14144
- baseUrl: "https://api.x.ai/v1",
14145
- reasoning: false,
14146
- input: ["text", "image"],
14147
- cost: {
14148
- input: 2,
14149
- output: 10,
14150
- cacheRead: 2,
14151
- cacheWrite: 0,
14152
- },
14153
- contextWindow: 8192,
14154
- maxTokens: 4096,
14155
- },
14156
- "grok-2-vision-1212": {
14157
- id: "grok-2-vision-1212",
14158
- name: "Grok 2 Vision (1212)",
14159
- api: "openai-completions",
14160
- provider: "xai",
14161
- baseUrl: "https://api.x.ai/v1",
14162
- reasoning: false,
14163
- input: ["text", "image"],
14164
- cost: {
14165
- input: 2,
14166
- output: 10,
14167
- cacheRead: 2,
14168
- cacheWrite: 0,
14169
- },
14170
- contextWindow: 8192,
14171
- maxTokens: 4096,
14172
- },
14173
- "grok-2-vision-latest": {
14174
- id: "grok-2-vision-latest",
14175
- name: "Grok 2 Vision Latest",
14176
- api: "openai-completions",
14177
- provider: "xai",
14178
- baseUrl: "https://api.x.ai/v1",
14179
- reasoning: false,
14180
- input: ["text", "image"],
14181
- cost: {
14182
- input: 2,
14183
- output: 10,
14184
- cacheRead: 2,
14185
- cacheWrite: 0,
14186
- },
14187
- contextWindow: 8192,
14188
- maxTokens: 4096,
14189
- },
14190
13937
  "grok-4.20-0309-non-reasoning": {
14191
13938
  id: "grok-4.20-0309-non-reasoning",
14192
13939
  name: "Grok 4.20 (Non-Reasoning)",
@@ -14196,8 +13943,8 @@ export const MODELS = {
14196
13943
  reasoning: false,
14197
13944
  input: ["text", "image"],
14198
13945
  cost: {
14199
- input: 2,
14200
- output: 6,
13946
+ input: 1.25,
13947
+ output: 2.5,
14201
13948
  cacheRead: 0.2,
14202
13949
  cacheWrite: 0,
14203
13950
  },
@@ -14213,8 +13960,8 @@ export const MODELS = {
14213
13960
  reasoning: true,
14214
13961
  input: ["text", "image"],
14215
13962
  cost: {
14216
- input: 2,
14217
- output: 6,
13963
+ input: 1.25,
13964
+ output: 2.5,
14218
13965
  cacheRead: 0.2,
14219
13966
  cacheWrite: 0,
14220
13967
  },
@@ -14238,22 +13985,22 @@ export const MODELS = {
14238
13985
  contextWindow: 1000000,
14239
13986
  maxTokens: 30000,
14240
13987
  },
14241
- "grok-beta": {
14242
- id: "grok-beta",
14243
- name: "Grok Beta",
13988
+ "grok-build-0.1": {
13989
+ id: "grok-build-0.1",
13990
+ name: "Grok Build 0.1",
14244
13991
  api: "openai-completions",
14245
13992
  provider: "xai",
14246
13993
  baseUrl: "https://api.x.ai/v1",
14247
- reasoning: false,
14248
- input: ["text"],
13994
+ reasoning: true,
13995
+ input: ["text", "image"],
14249
13996
  cost: {
14250
- input: 5,
14251
- output: 15,
14252
- cacheRead: 5,
13997
+ input: 1,
13998
+ output: 2,
13999
+ cacheRead: 0.2,
14253
14000
  cacheWrite: 0,
14254
14001
  },
14255
- contextWindow: 131072,
14256
- maxTokens: 4096,
14002
+ contextWindow: 256000,
14003
+ maxTokens: 256000,
14257
14004
  },
14258
14005
  "grok-code-fast-1": {
14259
14006
  id: "grok-code-fast-1",
@@ -14272,23 +14019,6 @@ export const MODELS = {
14272
14019
  contextWindow: 32768,
14273
14020
  maxTokens: 8192,
14274
14021
  },
14275
- "grok-vision-beta": {
14276
- id: "grok-vision-beta",
14277
- name: "Grok Vision Beta",
14278
- api: "openai-completions",
14279
- provider: "xai",
14280
- baseUrl: "https://api.x.ai/v1",
14281
- reasoning: false,
14282
- input: ["text", "image"],
14283
- cost: {
14284
- input: 5,
14285
- output: 15,
14286
- cacheRead: 5,
14287
- cacheWrite: 0,
14288
- },
14289
- contextWindow: 8192,
14290
- maxTokens: 4096,
14291
- },
14292
14022
  },
14293
14023
  };
14294
14024
  //# sourceMappingURL=models.generated.js.map