@dreb/ai 2.19.2 → 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.
Files changed (5) hide show
  1. package/dist/models.generated.d.ts +224 -791
  2. package/dist/models.generated.d.ts.map +1 -1
  3. package/dist/models.generated.js +423 -999
  4. package/dist/models.generated.js.map +1 -1
  5. package/package.json +1 -1
package/dist/models.generated.js CHANGED
@@ -900,8 +900,8 @@ export const MODELS = {
900
900
  cacheRead: 0,
901
901
  cacheWrite: 0,
902
902
  },
903
- contextWindow: 256000,
904
- maxTokens: 256000,
903
+ contextWindow: 262143,
904
+ maxTokens: 16000,
905
905
  },
906
906
  "moonshotai.kimi-k2.5": {
907
907
  id: "moonshotai.kimi-k2.5",
@@ -917,8 +917,8 @@ export const MODELS = {
917
917
  cacheRead: 0,
918
918
  cacheWrite: 0,
919
919
  },
920
- contextWindow: 256000,
921
- maxTokens: 256000,
920
+ contextWindow: 262143,
921
+ maxTokens: 16000,
922
922
  },
923
923
  "nvidia.nemotron-nano-12b-v2": {
924
924
  id: "nvidia.nemotron-nano-12b-v2",
@@ -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",
@@ -3301,6 +3133,23 @@ export const MODELS = {
3301
3133
  contextWindow: 1048576,
3302
3134
  maxTokens: 65536,
3303
3135
  },
3136
+ "gemini-3.5-flash": {
3137
+ id: "gemini-3.5-flash",
3138
+ name: "Gemini 3.5 Flash",
3139
+ api: "google-generative-ai",
3140
+ provider: "google",
3141
+ baseUrl: "https://generativelanguage.googleapis.com/v1beta",
3142
+ reasoning: true,
3143
+ input: ["text", "image"],
3144
+ cost: {
3145
+ input: 1.5,
3146
+ output: 9,
3147
+ cacheRead: 0.15,
3148
+ cacheWrite: 0,
3149
+ },
3150
+ contextWindow: 1048576,
3151
+ maxTokens: 65536,
3152
+ },
3304
3153
  "gemini-flash-latest": {
3305
3154
  id: "gemini-flash-latest",
3306
3155
  name: "Gemini Flash Latest",
@@ -3335,47 +3184,30 @@ export const MODELS = {
3335
3184
  contextWindow: 1048576,
3336
3185
  maxTokens: 65536,
3337
3186
  },
3338
- "gemini-live-2.5-flash": {
3339
- id: "gemini-live-2.5-flash",
3340
- name: "Gemini Live 2.5 Flash",
3187
+ "gemma-4-26b-a4b-it": {
3188
+ id: "gemma-4-26b-a4b-it",
3189
+ name: "Gemma 4 26B A4B IT",
3341
3190
  api: "google-generative-ai",
3342
3191
  provider: "google",
3343
3192
  baseUrl: "https://generativelanguage.googleapis.com/v1beta",
3344
3193
  reasoning: true,
3345
3194
  input: ["text", "image"],
3346
3195
  cost: {
3347
- input: 0.5,
3348
- output: 2,
3196
+ input: 0,
3197
+ output: 0,
3349
3198
  cacheRead: 0,
3350
3199
  cacheWrite: 0,
3351
3200
  },
3352
- contextWindow: 128000,
3353
- maxTokens: 8000,
3201
+ contextWindow: 262144,
3202
+ maxTokens: 32768,
3354
3203
  },
3355
- "gemini-live-2.5-flash-preview-native-audio": {
3356
- id: "gemini-live-2.5-flash-preview-native-audio",
3357
- name: "Gemini Live 2.5 Flash Preview Native Audio",
3204
+ "gemma-4-31b-it": {
3205
+ id: "gemma-4-31b-it",
3206
+ name: "Gemma 4 31B IT",
3358
3207
  api: "google-generative-ai",
3359
3208
  provider: "google",
3360
3209
  baseUrl: "https://generativelanguage.googleapis.com/v1beta",
3361
3210
  reasoning: true,
3362
- input: ["text"],
3363
- cost: {
3364
- input: 0.5,
3365
- output: 2,
3366
- cacheRead: 0,
3367
- cacheWrite: 0,
3368
- },
3369
- contextWindow: 131072,
3370
- maxTokens: 65536,
3371
- },
3372
- "gemma-3-27b-it": {
3373
- id: "gemma-3-27b-it",
3374
- name: "Gemma 3 27B",
3375
- api: "google-generative-ai",
3376
- provider: "google",
3377
- baseUrl: "https://generativelanguage.googleapis.com/v1beta",
3378
- reasoning: false,
3379
3211
  input: ["text", "image"],
3380
3212
  cost: {
3381
3213
  input: 0,
@@ -3383,51 +3215,17 @@ export const MODELS = {
3383
3215
  cacheRead: 0,
3384
3216
  cacheWrite: 0,
3385
3217
  },
3386
- contextWindow: 131072,
3387
- maxTokens: 8192,
3218
+ contextWindow: 262144,
3219
+ maxTokens: 32768,
3388
3220
  },
3389
- "gemma-4-26b-a4b-it": {
3390
- id: "gemma-4-26b-a4b-it",
3391
- name: "Gemma 4 26B",
3392
- api: "google-generative-ai",
3393
- provider: "google",
3394
- baseUrl: "https://generativelanguage.googleapis.com/v1beta",
3395
- reasoning: true,
3396
- input: ["text", "image"],
3397
- cost: {
3398
- input: 0,
3399
- output: 0,
3400
- cacheRead: 0,
3401
- cacheWrite: 0,
3402
- },
3403
- contextWindow: 256000,
3404
- maxTokens: 8192,
3405
- },
3406
- "gemma-4-31b-it": {
3407
- id: "gemma-4-31b-it",
3408
- name: "Gemma 4 31B",
3409
- api: "google-generative-ai",
3410
- provider: "google",
3411
- baseUrl: "https://generativelanguage.googleapis.com/v1beta",
3412
- reasoning: true,
3413
- input: ["text", "image"],
3414
- cost: {
3415
- input: 0,
3416
- output: 0,
3417
- cacheRead: 0,
3418
- cacheWrite: 0,
3419
- },
3420
- contextWindow: 256000,
3421
- maxTokens: 8192,
3422
- },
3423
- },
3424
- "google-antigravity": {
3425
- "claude-opus-4-5-thinking": {
3426
- id: "claude-opus-4-5-thinking",
3427
- name: "Claude Opus 4.5 Thinking (Antigravity)",
3428
- api: "google-gemini-cli",
3429
- provider: "google-antigravity",
3430
- baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
3221
+ },
3222
+ "google-antigravity": {
3223
+ "claude-opus-4-5-thinking": {
3224
+ id: "claude-opus-4-5-thinking",
3225
+ name: "Claude Opus 4.5 Thinking (Antigravity)",
3226
+ api: "google-gemini-cli",
3227
+ provider: "google-antigravity",
3228
+ baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
3431
3229
  reasoning: true,
3432
3230
  input: ["text", "image"],
3433
3231
  cost: {
@@ -4102,7 +3900,7 @@ export const MODELS = {
4102
3900
  cost: {
4103
3901
  input: 1,
4104
3902
  output: 3,
4105
- cacheRead: 0,
3903
+ cacheRead: 0.5,
4106
3904
  cacheWrite: 0,
4107
3905
  },
4108
3906
  contextWindow: 262144,
@@ -4119,7 +3917,7 @@ export const MODELS = {
4119
3917
  cost: {
4120
3918
  input: 0.15,
4121
3919
  output: 0.6,
4122
- cacheRead: 0,
3920
+ cacheRead: 0.075,
4123
3921
  cacheWrite: 0,
4124
3922
  },
4125
3923
  contextWindow: 131072,
@@ -4136,7 +3934,7 @@ export const MODELS = {
4136
3934
  cost: {
4137
3935
  input: 0.075,
4138
3936
  output: 0.3,
4139
- cacheRead: 0,
3937
+ cacheRead: 0.0375,
4140
3938
  cacheWrite: 0,
4141
3939
  },
4142
3940
  contextWindow: 131072,
@@ -4421,9 +4219,9 @@ export const MODELS = {
4421
4219
  reasoning: true,
4422
4220
  input: ["text"],
4423
4221
  cost: {
4424
- input: 1.74,
4425
- output: 3.48,
4426
- cacheRead: 0.145,
4222
+ input: 0.435,
4223
+ output: 0.87,
4224
+ cacheRead: 0.003625,
4427
4225
  cacheWrite: 0,
4428
4226
  },
4429
4227
  contextWindow: 1048576,
@@ -5278,7 +5076,7 @@ export const MODELS = {
5278
5076
  cost: {
5279
5077
  input: 0.1,
5280
5078
  output: 0.4,
5281
- cacheRead: 0.03,
5079
+ cacheRead: 0.025,
5282
5080
  cacheWrite: 0,
5283
5081
  },
5284
5082
  contextWindow: 1047576,
@@ -5363,7 +5161,7 @@ export const MODELS = {
5363
5161
  cost: {
5364
5162
  input: 0.15,
5365
5163
  output: 0.6,
5366
- cacheRead: 0.08,
5164
+ cacheRead: 0.075,
5367
5165
  cacheWrite: 0,
5368
5166
  },
5369
5167
  contextWindow: 128000,
@@ -5482,7 +5280,7 @@ export const MODELS = {
5482
5280
  cost: {
5483
5281
  input: 1.25,
5484
5282
  output: 10,
5485
- cacheRead: 0.13,
5283
+ cacheRead: 0.125,
5486
5284
  cacheWrite: 0,
5487
5285
  },
5488
5286
  contextWindow: 400000,
@@ -5890,7 +5688,7 @@ export const MODELS = {
5890
5688
  cost: {
5891
5689
  input: 1.1,
5892
5690
  output: 4.4,
5893
- cacheRead: 0.28,
5691
+ cacheRead: 0.275,
5894
5692
  cacheWrite: 0,
5895
5693
  },
5896
5694
  contextWindow: 200000,
@@ -6068,7 +5866,7 @@ export const MODELS = {
6068
5866
  cacheWrite: 0,
6069
5867
  },
6070
5868
  contextWindow: 200000,
6071
- maxTokens: 128000,
5869
+ maxTokens: 32000,
6072
5870
  },
6073
5871
  "claude-haiku-4-5": {
6074
5872
  id: "claude-haiku-4-5",
@@ -6220,8 +6018,8 @@ export const MODELS = {
6220
6018
  cacheRead: 0,
6221
6019
  cacheWrite: 0,
6222
6020
  },
6223
- contextWindow: 1000000,
6224
- maxTokens: 384000,
6021
+ contextWindow: 200000,
6022
+ maxTokens: 128000,
6225
6023
  },
6226
6024
  "gemini-3-flash": {
6227
6025
  id: "gemini-3-flash",
@@ -6257,6 +6055,23 @@ export const MODELS = {
6257
6055
  contextWindow: 1048576,
6258
6056
  maxTokens: 65536,
6259
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
+ },
6260
6075
  "glm-5": {
6261
6076
  id: "glm-5",
6262
6077
  name: "GLM-5",
@@ -6563,6 +6378,23 @@ export const MODELS = {
6563
6378
  contextWindow: 1050000,
6564
6379
  maxTokens: 128000,
6565
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
+ },
6566
6398
  "kimi-k2.5": {
6567
6399
  id: "kimi-k2.5",
6568
6400
  name: "Kimi K2.5",
@@ -6597,35 +6429,35 @@ export const MODELS = {
6597
6429
  contextWindow: 262144,
6598
6430
  maxTokens: 65536,
6599
6431
  },
6600
- "minimax-m2.5": {
6601
- id: "minimax-m2.5",
6602
- name: "MiniMax M2.5",
6432
+ "mimo-v2.5-free": {
6433
+ id: "mimo-v2.5-free",
6434
+ name: "MiMo V2.5 Free",
6603
6435
  api: "openai-completions",
6604
6436
  provider: "opencode",
6605
6437
  baseUrl: "https://opencode.ai/zen/v1",
6606
6438
  reasoning: true,
6607
- input: ["text"],
6439
+ input: ["text", "image"],
6608
6440
  cost: {
6609
- input: 0.3,
6610
- output: 1.2,
6611
- cacheRead: 0.06,
6441
+ input: 0,
6442
+ output: 0,
6443
+ cacheRead: 0,
6612
6444
  cacheWrite: 0,
6613
6445
  },
6614
- contextWindow: 204800,
6615
- maxTokens: 131072,
6446
+ contextWindow: 1000000,
6447
+ maxTokens: 128000,
6616
6448
  },
6617
- "minimax-m2.5-free": {
6618
- id: "minimax-m2.5-free",
6619
- name: "MiniMax M2.5 Free",
6620
- api: "anthropic-messages",
6449
+ "minimax-m2.5": {
6450
+ id: "minimax-m2.5",
6451
+ name: "MiniMax M2.5",
6452
+ api: "openai-completions",
6621
6453
  provider: "opencode",
6622
- baseUrl: "https://opencode.ai/zen",
6454
+ baseUrl: "https://opencode.ai/zen/v1",
6623
6455
  reasoning: true,
6624
6456
  input: ["text"],
6625
6457
  cost: {
6626
- input: 0,
6627
- output: 0,
6628
- cacheRead: 0,
6458
+ input: 0.3,
6459
+ output: 1.2,
6460
+ cacheRead: 0.06,
6629
6461
  cacheWrite: 0,
6630
6462
  },
6631
6463
  contextWindow: 204800,
@@ -6699,23 +6531,6 @@ export const MODELS = {
6699
6531
  contextWindow: 262144,
6700
6532
  maxTokens: 65536,
6701
6533
  },
6702
- "qwen3.6-plus-free": {
6703
- id: "qwen3.6-plus-free",
6704
- name: "Qwen3.6 Plus Free",
6705
- api: "anthropic-messages",
6706
- provider: "opencode",
6707
- baseUrl: "https://opencode.ai/zen",
6708
- reasoning: true,
6709
- input: ["text", "image"],
6710
- cost: {
6711
- input: 0,
6712
- output: 0,
6713
- cacheRead: 0,
6714
- cacheWrite: 0,
6715
- },
6716
- contextWindow: 262144,
6717
- maxTokens: 65536,
6718
- },
6719
6534
  },
6720
6535
  "opencode-go": {
6721
6536
  "deepseek-v4-flash": {
@@ -6829,9 +6644,9 @@ export const MODELS = {
6829
6644
  reasoning: true,
6830
6645
  input: ["text", "image"],
6831
6646
  cost: {
6832
- input: 0.4,
6833
- output: 2,
6834
- cacheRead: 0.08,
6647
+ input: 0.14,
6648
+ output: 0.28,
6649
+ cacheRead: 0.0028,
6835
6650
  cacheWrite: 0,
6836
6651
  },
6837
6652
  contextWindow: 1000000,
@@ -6846,9 +6661,9 @@ export const MODELS = {
6846
6661
  reasoning: true,
6847
6662
  input: ["text"],
6848
6663
  cost: {
6849
- input: 1,
6850
- output: 3,
6851
- cacheRead: 0.2,
6664
+ input: 1.74,
6665
+ output: 3.48,
6666
+ cacheRead: 0.0145,
6852
6667
  cacheWrite: 0,
6853
6668
  },
6854
6669
  contextWindow: 1048576,
@@ -6922,6 +6737,23 @@ export const MODELS = {
6922
6737
  contextWindow: 262144,
6923
6738
  maxTokens: 65536,
6924
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
+ },
6925
6757
  },
6926
6758
  "openrouter": {
6927
6759
  "ai21/jamba-large-1.7": {
@@ -6941,23 +6773,6 @@ export const MODELS = {
6941
6773
  contextWindow: 256000,
6942
6774
  maxTokens: 4096,
6943
6775
  },
6944
- "alibaba/tongyi-deepresearch-30b-a3b": {
6945
- id: "alibaba/tongyi-deepresearch-30b-a3b",
6946
- name: "Tongyi DeepResearch 30B A3B",
6947
- api: "openai-completions",
6948
- provider: "openrouter",
6949
- baseUrl: "https://openrouter.ai/api/v1",
6950
- reasoning: true,
6951
- input: ["text"],
6952
- cost: {
6953
- input: 0.09,
6954
- output: 0.44999999999999996,
6955
- cacheRead: 0.09,
6956
- cacheWrite: 0,
6957
- },
6958
- contextWindow: 131072,
6959
- maxTokens: 131072,
6960
- },
6961
6776
  "amazon/nova-2-lite-v1": {
6962
6777
  id: "amazon/nova-2-lite-v1",
6963
6778
  name: "Amazon: Nova 2 Lite",
@@ -7264,23 +7079,6 @@ export const MODELS = {
7264
7079
  contextWindow: 1000000,
7265
7080
  maxTokens: 128000,
7266
7081
  },
7267
- "arcee-ai/trinity-large-preview": {
7268
- id: "arcee-ai/trinity-large-preview",
7269
- name: "Arcee AI: Trinity Large Preview",
7270
- api: "openai-completions",
7271
- provider: "openrouter",
7272
- baseUrl: "https://openrouter.ai/api/v1",
7273
- reasoning: false,
7274
- input: ["text"],
7275
- cost: {
7276
- input: 0.15,
7277
- output: 0.44999999999999996,
7278
- cacheRead: 0,
7279
- cacheWrite: 0,
7280
- },
7281
- contextWindow: 131000,
7282
- maxTokens: 4096,
7283
- },
7284
7082
  "arcee-ai/trinity-large-thinking": {
7285
7083
  id: "arcee-ai/trinity-large-thinking",
7286
7084
  name: "Arcee AI: Trinity Large Thinking",
@@ -7298,23 +7096,6 @@ export const MODELS = {
7298
7096
  contextWindow: 262144,
7299
7097
  maxTokens: 262144,
7300
7098
  },
7301
- "arcee-ai/trinity-large-thinking:free": {
7302
- id: "arcee-ai/trinity-large-thinking:free",
7303
- name: "Arcee AI: Trinity Large Thinking (free)",
7304
- api: "openai-completions",
7305
- provider: "openrouter",
7306
- baseUrl: "https://openrouter.ai/api/v1",
7307
- reasoning: true,
7308
- input: ["text"],
7309
- cost: {
7310
- input: 0,
7311
- output: 0,
7312
- cacheRead: 0,
7313
- cacheWrite: 0,
7314
- },
7315
- contextWindow: 262144,
7316
- maxTokens: 80000,
7317
- },
7318
7099
  "arcee-ai/trinity-mini": {
7319
7100
  id: "arcee-ai/trinity-mini",
7320
7101
  name: "Arcee AI: Trinity Mini",
@@ -7366,23 +7147,6 @@ export const MODELS = {
7366
7147
  contextWindow: 2000000,
7367
7148
  maxTokens: 30000,
7368
7149
  },
7369
- "baidu/cobuddy:free": {
7370
- id: "baidu/cobuddy:free",
7371
- name: "Baidu Qianfan: CoBuddy (free)",
7372
- api: "openai-completions",
7373
- provider: "openrouter",
7374
- baseUrl: "https://openrouter.ai/api/v1",
7375
- reasoning: true,
7376
- input: ["text"],
7377
- cost: {
7378
- input: 0,
7379
- output: 0,
7380
- cacheRead: 0,
7381
- cacheWrite: 0,
7382
- },
7383
- contextWindow: 131072,
7384
- maxTokens: 65536,
7385
- },
7386
7150
  "baidu/ernie-4.5-21b-a3b": {
7387
7151
  id: "baidu/ernie-4.5-21b-a3b",
7388
7152
  name: "Baidu: ERNIE 4.5 21B A3B",
@@ -7397,7 +7161,7 @@ export const MODELS = {
7397
7161
  cacheRead: 0,
7398
7162
  cacheWrite: 0,
7399
7163
  },
7400
- contextWindow: 120000,
7164
+ contextWindow: 131072,
7401
7165
  maxTokens: 8000,
7402
7166
  },
7403
7167
  "baidu/ernie-4.5-vl-28b-a3b": {
@@ -7414,7 +7178,7 @@ export const MODELS = {
7414
7178
  cacheRead: 0,
7415
7179
  cacheWrite: 0,
7416
7180
  },
7417
- contextWindow: 30000,
7181
+ contextWindow: 131072,
7418
7182
  maxTokens: 8000,
7419
7183
  },
7420
7184
  "bytedance-seed/seed-1.6": {
@@ -7528,13 +7292,13 @@ export const MODELS = {
7528
7292
  reasoning: false,
7529
7293
  input: ["text"],
7530
7294
  cost: {
7531
- input: 0.32,
7532
- output: 0.8899999999999999,
7295
+ input: 0.2288,
7296
+ output: 0.9144,
7533
7297
  cacheRead: 0,
7534
7298
  cacheWrite: 0,
7535
7299
  },
7536
- contextWindow: 163840,
7537
- maxTokens: 16384,
7300
+ contextWindow: 131072,
7301
+ maxTokens: 16000,
7538
7302
  },
7539
7303
  "deepseek/deepseek-chat-v3-0324": {
7540
7304
  id: "deepseek/deepseek-chat-v3-0324",
@@ -7584,7 +7348,7 @@ export const MODELS = {
7584
7348
  cacheRead: 0,
7585
7349
  cacheWrite: 0,
7586
7350
  },
7587
- contextWindow: 64000,
7351
+ contextWindow: 163840,
7588
7352
  maxTokens: 16000,
7589
7353
  },
7590
7354
  "deepseek/deepseek-r1-0528": {
@@ -7664,13 +7428,13 @@ export const MODELS = {
7664
7428
  reasoning: true,
7665
7429
  input: ["text"],
7666
7430
  cost: {
7667
- input: 0.112,
7668
- output: 0.224,
7669
- cacheRead: 0.022,
7431
+ input: 0.09999999999999999,
7432
+ output: 0.19999999999999998,
7433
+ cacheRead: 0.02,
7670
7434
  cacheWrite: 0,
7671
7435
  },
7672
- contextWindow: 1048575,
7673
- maxTokens: 4096,
7436
+ contextWindow: 1048576,
7437
+ maxTokens: 16384,
7674
7438
  },
7675
7439
  "deepseek/deepseek-v4-flash:free": {
7676
7440
  id: "deepseek/deepseek-v4-flash:free",
@@ -7737,7 +7501,7 @@ export const MODELS = {
7737
7501
  cacheRead: 0.024999999999999998,
7738
7502
  cacheWrite: 0.08333333333333334,
7739
7503
  },
7740
- contextWindow: 1048576,
7504
+ contextWindow: 1000000,
7741
7505
  maxTokens: 8192,
7742
7506
  },
7743
7507
  "google/gemini-2.0-flash-lite-001": {
@@ -7941,6 +7705,23 @@ export const MODELS = {
7941
7705
  cacheRead: 0.19999999999999998,
7942
7706
  cacheWrite: 0.375,
7943
7707
  },
7708
+ contextWindow: 1048756,
7709
+ maxTokens: 65536,
7710
+ },
7711
+ "google/gemini-3.5-flash": {
7712
+ id: "google/gemini-3.5-flash",
7713
+ name: "Google: Gemini 3.5 Flash",
7714
+ api: "openai-completions",
7715
+ provider: "openrouter",
7716
+ baseUrl: "https://openrouter.ai/api/v1",
7717
+ reasoning: true,
7718
+ input: ["text", "image"],
7719
+ cost: {
7720
+ input: 1.5,
7721
+ output: 9,
7722
+ cacheRead: 0.15,
7723
+ cacheWrite: 0.08333333333333334,
7724
+ },
7944
7725
  contextWindow: 1048576,
7945
7726
  maxTokens: 65536,
7946
7727
  },
@@ -8089,9 +7870,9 @@ export const MODELS = {
8089
7870
  reasoning: false,
8090
7871
  input: ["text"],
8091
7872
  cost: {
8092
- input: 0.3,
8093
- output: 2.5,
8094
- cacheRead: 0.06,
7873
+ input: 0.075,
7874
+ output: 0.625,
7875
+ cacheRead: 0.015,
8095
7876
  cacheWrite: 0,
8096
7877
  },
8097
7878
  contextWindow: 262144,
@@ -8179,7 +7960,7 @@ export const MODELS = {
8179
7960
  cacheRead: 0,
8180
7961
  cacheWrite: 0,
8181
7962
  },
8182
- contextWindow: 16384,
7963
+ contextWindow: 131072,
8183
7964
  maxTokens: 16384,
8184
7965
  },
8185
7966
  "meta-llama/llama-3.3-70b-instruct": {
@@ -8213,7 +7994,7 @@ export const MODELS = {
8213
7994
  cacheRead: 0,
8214
7995
  cacheWrite: 0,
8215
7996
  },
8216
- contextWindow: 65536,
7997
+ contextWindow: 131072,
8217
7998
  maxTokens: 4096,
8218
7999
  },
8219
8000
  "meta-llama/llama-4-scout": {
@@ -8230,7 +8011,7 @@ export const MODELS = {
8230
8011
  cacheRead: 0,
8231
8012
  cacheWrite: 0,
8232
8013
  },
8233
- contextWindow: 327680,
8014
+ contextWindow: 10000000,
8234
8015
  maxTokens: 16384,
8235
8016
  },
8236
8017
  "minimax/minimax-m1": {
@@ -8264,7 +8045,7 @@ export const MODELS = {
8264
8045
  cacheRead: 0.03,
8265
8046
  cacheWrite: 0,
8266
8047
  },
8267
- contextWindow: 196608,
8048
+ contextWindow: 204800,
8268
8049
  maxTokens: 196608,
8269
8050
  },
8270
8051
  "minimax/minimax-m2.1": {
@@ -8281,7 +8062,7 @@ export const MODELS = {
8281
8062
  cacheRead: 0.03,
8282
8063
  cacheWrite: 0,
8283
8064
  },
8284
- contextWindow: 196608,
8065
+ contextWindow: 204800,
8285
8066
  maxTokens: 196608,
8286
8067
  },
8287
8068
  "minimax/minimax-m2.5": {
@@ -8298,7 +8079,7 @@ export const MODELS = {
8298
8079
  cacheRead: 0,
8299
8080
  cacheWrite: 0,
8300
8081
  },
8301
- contextWindow: 196608,
8082
+ contextWindow: 204800,
8302
8083
  maxTokens: 196608,
8303
8084
  },
8304
8085
  "minimax/minimax-m2.5:free": {
@@ -8315,7 +8096,7 @@ export const MODELS = {
8315
8096
  cacheRead: 0,
8316
8097
  cacheWrite: 0,
8317
8098
  },
8318
- contextWindow: 196608,
8099
+ contextWindow: 262144,
8319
8100
  maxTokens: 8192,
8320
8101
  },
8321
8102
  "minimax/minimax-m2.7": {
@@ -8332,7 +8113,7 @@ export const MODELS = {
8332
8113
  cacheRead: 0,
8333
8114
  cacheWrite: 0,
8334
8115
  },
8335
- contextWindow: 196608,
8116
+ contextWindow: 204800,
8336
8117
  maxTokens: 131072,
8337
8118
  },
8338
8119
  "mistralai/codestral-2508": {
@@ -8774,9 +8555,26 @@ export const MODELS = {
8774
8555
  cacheRead: 0.25,
8775
8556
  cacheWrite: 0,
8776
8557
  },
8777
- contextWindow: 262142,
8558
+ contextWindow: 262144,
8778
8559
  maxTokens: 262142,
8779
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
+ },
8780
8578
  "nex-agi/deepseek-v3.1-nex-n1": {
8781
8579
  id: "nex-agi/deepseek-v3.1-nex-n1",
8782
8580
  name: "Nex AGI: DeepSeek V3.1 Nex N1",
@@ -8876,7 +8674,7 @@ export const MODELS = {
8876
8674
  cacheRead: 0,
8877
8675
  cacheWrite: 0,
8878
8676
  },
8879
- contextWindow: 262144,
8677
+ contextWindow: 1000000,
8880
8678
  maxTokens: 4096,
8881
8679
  },
8882
8680
  "nvidia/nemotron-3-super-120b-a12b:free": {
@@ -8893,7 +8691,7 @@ export const MODELS = {
8893
8691
  cacheRead: 0,
8894
8692
  cacheWrite: 0,
8895
8693
  },
8896
- contextWindow: 262144,
8694
+ contextWindow: 1000000,
8897
8695
  maxTokens: 262144,
8898
8696
  },
8899
8697
  "nvidia/nemotron-nano-12b-v2-vl:free": {
@@ -9366,11 +9164,11 @@ export const MODELS = {
9366
9164
  cost: {
9367
9165
  input: 1.25,
9368
9166
  output: 10,
9369
- cacheRead: 0.125,
9167
+ cacheRead: 0.13,
9370
9168
  cacheWrite: 0,
9371
9169
  },
9372
9170
  contextWindow: 128000,
9373
- maxTokens: 16384,
9171
+ maxTokens: 32000,
9374
9172
  },
9375
9173
  "openai/gpt-5.1-codex": {
9376
9174
  id: "openai/gpt-5.1-codex",
@@ -9383,7 +9181,7 @@ export const MODELS = {
9383
9181
  cost: {
9384
9182
  input: 1.25,
9385
9183
  output: 10,
9386
- cacheRead: 0.125,
9184
+ cacheRead: 0.13,
9387
9185
  cacheWrite: 0,
9388
9186
  },
9389
9187
  contextWindow: 400000,
@@ -9417,11 +9215,11 @@ export const MODELS = {
9417
9215
  cost: {
9418
9216
  input: 0.25,
9419
9217
  output: 2,
9420
- cacheRead: 0.03,
9218
+ cacheRead: 0.024999999999999998,
9421
9219
  cacheWrite: 0,
9422
9220
  },
9423
9221
  contextWindow: 400000,
9424
- maxTokens: 128000,
9222
+ maxTokens: 100000,
9425
9223
  },
9426
9224
  "openai/gpt-5.2": {
9427
9225
  id: "openai/gpt-5.2",
@@ -9455,7 +9253,7 @@ export const MODELS = {
9455
9253
  cacheWrite: 0,
9456
9254
  },
9457
9255
  contextWindow: 128000,
9458
- maxTokens: 32000,
9256
+ maxTokens: 16384,
9459
9257
  },
9460
9258
  "openai/gpt-5.2-codex": {
9461
9259
  id: "openai/gpt-5.2-codex",
@@ -9981,8 +9779,8 @@ export const MODELS = {
9981
9779
  cacheRead: 0,
9982
9780
  cacheWrite: 0,
9983
9781
  },
9984
- contextWindow: 131072,
9985
- maxTokens: 8192,
9782
+ contextWindow: 262144,
9783
+ maxTokens: 32768,
9986
9784
  },
9987
9785
  "poolside/laguna-xs.2:free": {
9988
9786
  id: "poolside/laguna-xs.2:free",
@@ -9998,8 +9796,8 @@ export const MODELS = {
9998
9796
  cacheRead: 0,
9999
9797
  cacheWrite: 0,
10000
9798
  },
10001
- contextWindow: 131072,
10002
- maxTokens: 8192,
9799
+ contextWindow: 262144,
9800
+ maxTokens: 32768,
10003
9801
  },
10004
9802
  "prime-intellect/intellect-3": {
10005
9803
  id: "prime-intellect/intellect-3",
@@ -10032,7 +9830,7 @@ export const MODELS = {
10032
9830
  cacheRead: 0,
10033
9831
  cacheWrite: 0,
10034
9832
  },
10035
- contextWindow: 32768,
9833
+ contextWindow: 131072,
10036
9834
  maxTokens: 16384,
10037
9835
  },
10038
9836
  "qwen/qwen-2.5-7b-instruct": {
@@ -10049,7 +9847,7 @@ export const MODELS = {
10049
9847
  cacheRead: 0,
10050
9848
  cacheWrite: 0,
10051
9849
  },
10052
- contextWindow: 32768,
9850
+ contextWindow: 131072,
10053
9851
  maxTokens: 32768,
10054
9852
  },
10055
9853
  "qwen/qwen-plus": {
@@ -10081,7 +9879,7 @@ export const MODELS = {
10081
9879
  input: 0.26,
10082
9880
  output: 0.78,
10083
9881
  cacheRead: 0,
10084
- cacheWrite: 0.325,
9882
+ cacheWrite: 0,
10085
9883
  },
10086
9884
  contextWindow: 1000000,
10087
9885
  maxTokens: 32768,
@@ -10117,7 +9915,7 @@ export const MODELS = {
10117
9915
  cacheRead: 0,
10118
9916
  cacheWrite: 0,
10119
9917
  },
10120
- contextWindow: 40960,
9918
+ contextWindow: 131702,
10121
9919
  maxTokens: 40960,
10122
9920
  },
10123
9921
  "qwen/qwen3-235b-a22b": {
@@ -10168,7 +9966,7 @@ export const MODELS = {
10168
9966
  cacheRead: 0,
10169
9967
  cacheWrite: 0,
10170
9968
  },
10171
- contextWindow: 131072,
9969
+ contextWindow: 262144,
10172
9970
  maxTokens: 4096,
10173
9971
  },
10174
9972
  "qwen/qwen3-30b-a3b": {
@@ -10185,7 +9983,7 @@ export const MODELS = {
10185
9983
  cacheRead: 0,
10186
9984
  cacheWrite: 0,
10187
9985
  },
10188
- contextWindow: 40960,
9986
+ contextWindow: 131072,
10189
9987
  maxTokens: 20000,
10190
9988
  },
10191
9989
  "qwen/qwen3-30b-a3b-instruct-2507": {
@@ -10236,7 +10034,7 @@ export const MODELS = {
10236
10034
  cacheRead: 0,
10237
10035
  cacheWrite: 0,
10238
10036
  },
10239
- contextWindow: 40960,
10037
+ contextWindow: 131072,
10240
10038
  maxTokens: 16384,
10241
10039
  },
10242
10040
  "qwen/qwen3-8b": {
@@ -10253,7 +10051,7 @@ export const MODELS = {
10253
10051
  cacheRead: 0.049999999999999996,
10254
10052
  cacheWrite: 0,
10255
10053
  },
10256
- contextWindow: 40960,
10054
+ contextWindow: 131072,
10257
10055
  maxTokens: 8192,
10258
10056
  },
10259
10057
  "qwen/qwen3-coder": {
@@ -10270,7 +10068,7 @@ export const MODELS = {
10270
10068
  cacheRead: 0,
10271
10069
  cacheWrite: 0,
10272
10070
  },
10273
- contextWindow: 262144,
10071
+ contextWindow: 1048576,
10274
10072
  maxTokens: 65536,
10275
10073
  },
10276
10074
  "qwen/qwen3-coder-30b-a3b-instruct": {
@@ -10355,7 +10153,7 @@ export const MODELS = {
10355
10153
  cacheRead: 0,
10356
10154
  cacheWrite: 0,
10357
10155
  },
10358
- contextWindow: 262000,
10156
+ contextWindow: 1048576,
10359
10157
  maxTokens: 262000,
10360
10158
  },
10361
10159
  "qwen/qwen3-max": {
@@ -10440,7 +10238,7 @@ export const MODELS = {
10440
10238
  cacheRead: 0,
10441
10239
  cacheWrite: 0,
10442
10240
  },
10443
- contextWindow: 131072,
10241
+ contextWindow: 262144,
10444
10242
  maxTokens: 32768,
10445
10243
  },
10446
10244
  "qwen/qwen3-vl-235b-a22b-instruct": {
@@ -10491,7 +10289,7 @@ export const MODELS = {
10491
10289
  cacheRead: 0,
10492
10290
  cacheWrite: 0,
10493
10291
  },
10494
- contextWindow: 131072,
10292
+ contextWindow: 262144,
10495
10293
  maxTokens: 32768,
10496
10294
  },
10497
10295
  "qwen/qwen3-vl-30b-a3b-thinking": {
@@ -10525,7 +10323,7 @@ export const MODELS = {
10525
10323
  cacheRead: 0,
10526
10324
  cacheWrite: 0,
10527
10325
  },
10528
- contextWindow: 131072,
10326
+ contextWindow: 262144,
10529
10327
  maxTokens: 32768,
10530
10328
  },
10531
10329
  "qwen/qwen3-vl-8b-instruct": {
@@ -10542,7 +10340,7 @@ export const MODELS = {
10542
10340
  cacheRead: 0,
10543
10341
  cacheWrite: 0,
10544
10342
  },
10545
- contextWindow: 131072,
10343
+ contextWindow: 256000,
10546
10344
  maxTokens: 32768,
10547
10345
  },
10548
10346
  "qwen/qwen3-vl-8b-thinking": {
@@ -10559,7 +10357,7 @@ export const MODELS = {
10559
10357
  cacheRead: 0,
10560
10358
  cacheWrite: 0,
10561
10359
  },
10562
- contextWindow: 131072,
10360
+ contextWindow: 256000,
10563
10361
  maxTokens: 32768,
10564
10362
  },
10565
10363
  "qwen/qwen3.5-122b-a10b": {
@@ -10577,7 +10375,7 @@ export const MODELS = {
10577
10375
  cacheWrite: 0,
10578
10376
  },
10579
10377
  contextWindow: 262144,
10580
- maxTokens: 65536,
10378
+ maxTokens: 262144,
10581
10379
  },
10582
10380
  "qwen/qwen3.5-27b": {
10583
10381
  id: "qwen/qwen3.5-27b",
@@ -10605,13 +10403,13 @@ export const MODELS = {
10605
10403
  reasoning: true,
10606
10404
  input: ["text", "image"],
10607
10405
  cost: {
10608
- input: 0.14,
10406
+ input: 0.13899999999999998,
10609
10407
  output: 1,
10610
- cacheRead: 0.049999999999999996,
10408
+ cacheRead: 0,
10611
10409
  cacheWrite: 0,
10612
10410
  },
10613
10411
  contextWindow: 262144,
10614
- maxTokens: 81920,
10412
+ maxTokens: 4096,
10615
10413
  },
10616
10414
  "qwen/qwen3.5-397b-a17b": {
10617
10415
  id: "qwen/qwen3.5-397b-a17b",
@@ -10624,7 +10422,7 @@ export const MODELS = {
10624
10422
  cost: {
10625
10423
  input: 0.39,
10626
10424
  output: 2.34,
10627
- cacheRead: 0.195,
10425
+ cacheRead: 0,
10628
10426
  cacheWrite: 0,
10629
10427
  },
10630
10428
  contextWindow: 262144,
@@ -10659,7 +10457,7 @@ export const MODELS = {
10659
10457
  input: 0.065,
10660
10458
  output: 0.26,
10661
10459
  cacheRead: 0,
10662
- cacheWrite: 0.08125,
10460
+ cacheWrite: 0,
10663
10461
  },
10664
10462
  contextWindow: 1000000,
10665
10463
  maxTokens: 65536,
@@ -10676,7 +10474,7 @@ export const MODELS = {
10676
10474
  input: 0.26,
10677
10475
  output: 1.56,
10678
10476
  cacheRead: 0,
10679
- cacheWrite: 0.325,
10477
+ cacheWrite: 0,
10680
10478
  },
10681
10479
  contextWindow: 1000000,
10682
10480
  maxTokens: 65536,
@@ -10693,7 +10491,7 @@ export const MODELS = {
10693
10491
  input: 0.3,
10694
10492
  output: 1.7999999999999998,
10695
10493
  cacheRead: 0,
10696
- cacheWrite: 0,
10494
+ cacheWrite: 0.375,
10697
10495
  },
10698
10496
  contextWindow: 1000000,
10699
10497
  maxTokens: 65536,
@@ -10707,13 +10505,13 @@ export const MODELS = {
10707
10505
  reasoning: true,
10708
10506
  input: ["text", "image"],
10709
10507
  cost: {
10710
- input: 0.32,
10508
+ input: 0.29,
10711
10509
  output: 3.1999999999999997,
10712
10510
  cacheRead: 0,
10713
10511
  cacheWrite: 0,
10714
10512
  },
10715
10513
  contextWindow: 262144,
10716
- maxTokens: 81920,
10514
+ maxTokens: 262140,
10717
10515
  },
10718
10516
  "qwen/qwen3.6-35b-a3b": {
10719
10517
  id: "qwen/qwen3.6-35b-a3b",
@@ -10724,13 +10522,13 @@ export const MODELS = {
10724
10522
  reasoning: true,
10725
10523
  input: ["text", "image"],
10726
10524
  cost: {
10727
- input: 0.15,
10525
+ input: 0.14,
10728
10526
  output: 1,
10729
- cacheRead: 0.049999999999999996,
10527
+ cacheRead: 0,
10730
10528
  cacheWrite: 0,
10731
10529
  },
10732
10530
  contextWindow: 262144,
10733
- maxTokens: 262144,
10531
+ maxTokens: 262140,
10734
10532
  },
10735
10533
  "qwen/qwen3.6-flash": {
10736
10534
  id: "qwen/qwen3.6-flash",
@@ -10783,6 +10581,23 @@ export const MODELS = {
10783
10581
  contextWindow: 1000000,
10784
10582
  maxTokens: 65536,
10785
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
+ },
10786
10601
  "rekaai/reka-edge": {
10787
10602
  id: "rekaai/reka-edge",
10788
10603
  name: "Reka Edge",
@@ -10860,13 +10675,13 @@ export const MODELS = {
10860
10675
  reasoning: true,
10861
10676
  input: ["text"],
10862
10677
  cost: {
10863
- input: 0.09999999999999999,
10678
+ input: 0.09,
10864
10679
  output: 0.3,
10865
- cacheRead: 0,
10680
+ cacheRead: 0.02,
10866
10681
  cacheWrite: 0,
10867
10682
  },
10868
10683
  contextWindow: 262144,
10869
- maxTokens: 65536,
10684
+ maxTokens: 16384,
10870
10685
  },
10871
10686
  "tencent/hy3-preview": {
10872
10687
  id: "tencent/hy3-preview",
@@ -10877,13 +10692,13 @@ export const MODELS = {
10877
10692
  reasoning: true,
10878
10693
  input: ["text"],
10879
10694
  cost: {
10880
- input: 0.06599999999999999,
10881
- output: 0.26,
10882
- cacheRead: 0.029,
10695
+ input: 0.063,
10696
+ output: 0.21,
10697
+ cacheRead: 0.020999999999999998,
10883
10698
  cacheWrite: 0,
10884
10699
  },
10885
10700
  contextWindow: 262144,
10886
- maxTokens: 262144,
10701
+ maxTokens: 4096,
10887
10702
  },
10888
10703
  "thedrummer/rocinante-12b": {
10889
10704
  id: "thedrummer/rocinante-12b",
@@ -10970,6 +10785,23 @@ export const MODELS = {
10970
10785
  contextWindow: 1000000,
10971
10786
  maxTokens: 4096,
10972
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
+ },
10973
10805
  "xiaomi/mimo-v2-flash": {
10974
10806
  id: "xiaomi/mimo-v2-flash",
10975
10807
  name: "Xiaomi: MiMo-V2-Flash",
@@ -11030,9 +10862,9 @@ export const MODELS = {
11030
10862
  reasoning: true,
11031
10863
  input: ["text", "image"],
11032
10864
  cost: {
11033
- input: 0.39999999999999997,
11034
- output: 2,
11035
- cacheRead: 0.08,
10865
+ input: 0.14,
10866
+ output: 0.28,
10867
+ cacheRead: 0.0028,
11036
10868
  cacheWrite: 0,
11037
10869
  },
11038
10870
  contextWindow: 1048576,
@@ -11047,13 +10879,13 @@ export const MODELS = {
11047
10879
  reasoning: true,
11048
10880
  input: ["text"],
11049
10881
  cost: {
11050
- input: 1,
11051
- output: 3,
11052
- cacheRead: 0.19999999999999998,
10882
+ input: 0.435,
10883
+ output: 0.87,
10884
+ cacheRead: 0.0036,
11053
10885
  cacheWrite: 0,
11054
10886
  },
11055
10887
  contextWindow: 1048576,
11056
- maxTokens: 16384,
10888
+ maxTokens: 131072,
11057
10889
  },
11058
10890
  "z-ai/glm-4-32b": {
11059
10891
  id: "z-ai/glm-4-32b",
@@ -11098,13 +10930,13 @@ export const MODELS = {
11098
10930
  reasoning: true,
11099
10931
  input: ["text"],
11100
10932
  cost: {
11101
- input: 0.13,
11102
- output: 0.85,
11103
- cacheRead: 0.024999999999999998,
10933
+ input: 0.125,
10934
+ output: 0.84,
10935
+ cacheRead: 0,
11104
10936
  cacheWrite: 0,
11105
10937
  },
11106
10938
  contextWindow: 131072,
11107
- maxTokens: 98304,
10939
+ maxTokens: 131070,
11108
10940
  },
11109
10941
  "z-ai/glm-4.5-air:free": {
11110
10942
  id: "z-ai/glm-4.5-air:free",
@@ -11336,9 +11168,9 @@ export const MODELS = {
11336
11168
  reasoning: true,
11337
11169
  input: ["text", "image"],
11338
11170
  cost: {
11339
- input: 0.5,
11340
- output: 3,
11341
- cacheRead: 0.049999999999999996,
11171
+ input: 1.5,
11172
+ output: 9,
11173
+ cacheRead: 0.15,
11342
11174
  cacheWrite: 0.08333333333333334,
11343
11175
  },
11344
11176
  contextWindow: 1048576,
@@ -11375,7 +11207,7 @@ export const MODELS = {
11375
11207
  cacheRead: 0.25,
11376
11208
  cacheWrite: 0,
11377
11209
  },
11378
- contextWindow: 262142,
11210
+ contextWindow: 262144,
11379
11211
  maxTokens: 262142,
11380
11212
  },
11381
11213
  "~openai/gpt-latest": {
@@ -11720,6 +11552,23 @@ export const MODELS = {
11720
11552
  contextWindow: 1000000,
11721
11553
  maxTokens: 64000,
11722
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
+ },
11723
11572
  "anthropic/claude-3-haiku": {
11724
11573
  id: "anthropic/claude-3-haiku",
11725
11574
  name: "Claude 3 Haiku",
@@ -12281,6 +12130,23 @@ export const MODELS = {
12281
12130
  contextWindow: 1000000,
12282
12131
  maxTokens: 64000,
12283
12132
  },
12133
+ "google/gemini-3.5-flash": {
12134
+ id: "google/gemini-3.5-flash",
12135
+ name: "Gemini 3.5 Flash",
12136
+ api: "anthropic-messages",
12137
+ provider: "vercel-ai-gateway",
12138
+ baseUrl: "https://ai-gateway.vercel.sh",
12139
+ reasoning: true,
12140
+ input: ["text", "image"],
12141
+ cost: {
12142
+ input: 1.5,
12143
+ output: 9,
12144
+ cacheRead: 0.15,
12145
+ cacheWrite: 0,
12146
+ },
12147
+ contextWindow: 1000000,
12148
+ maxTokens: 64000,
12149
+ },
12284
12150
  "google/gemma-4-26b-a4b-it": {
12285
12151
  id: "google/gemma-4-26b-a4b-it",
12286
12152
  name: "Gemma 4 26B A4B IT",
@@ -12589,7 +12455,7 @@ export const MODELS = {
12589
12455
  },
12590
12456
  "minimax/minimax-m2.7": {
12591
12457
  id: "minimax/minimax-m2.7",
12592
- name: "Minimax M2.7",
12458
+ name: "MiniMax M2.7",
12593
12459
  api: "anthropic-messages",
12594
12460
  provider: "vercel-ai-gateway",
12595
12461
  baseUrl: "https://ai-gateway.vercel.sh",
@@ -12740,6 +12606,23 @@ export const MODELS = {
12740
12606
  contextWindow: 128000,
12741
12607
  maxTokens: 64000,
12742
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
+ },
12743
12626
  "mistral/mistral-small": {
12744
12627
  id: "mistral/mistral-small",
12745
12628
  name: "Mistral Small",
@@ -13590,179 +13473,60 @@ export const MODELS = {
13590
13473
  contextWindow: 200000,
13591
13474
  maxTokens: 8000,
13592
13475
  },
13593
- "xai/grok-3": {
13594
- id: "xai/grok-3",
13595
- name: "Grok 3 Beta",
13596
- api: "anthropic-messages",
13597
- provider: "vercel-ai-gateway",
13598
- baseUrl: "https://ai-gateway.vercel.sh",
13599
- reasoning: false,
13600
- input: ["text"],
13601
- cost: {
13602
- input: 3,
13603
- output: 15,
13604
- cacheRead: 0.75,
13605
- cacheWrite: 0,
13606
- },
13607
- contextWindow: 131072,
13608
- maxTokens: 131072,
13609
- },
13610
- "xai/grok-3-fast": {
13611
- id: "xai/grok-3-fast",
13612
- name: "Grok 3 Fast Beta",
13476
+ "xai/grok-4.1-fast-non-reasoning": {
13477
+ id: "xai/grok-4.1-fast-non-reasoning",
13478
+ name: "Grok 4.1 Fast Non-Reasoning",
13613
13479
  api: "anthropic-messages",
13614
13480
  provider: "vercel-ai-gateway",
13615
13481
  baseUrl: "https://ai-gateway.vercel.sh",
13616
13482
  reasoning: false,
13617
- input: ["text"],
13483
+ input: ["text", "image"],
13618
13484
  cost: {
13619
- input: 5,
13620
- output: 25,
13621
- cacheRead: 1.25,
13485
+ input: 0.19999999999999998,
13486
+ output: 0.5,
13487
+ cacheRead: 0.049999999999999996,
13622
13488
  cacheWrite: 0,
13623
13489
  },
13624
- contextWindow: 131072,
13625
- maxTokens: 131072,
13490
+ contextWindow: 1000000,
13491
+ maxTokens: 1000000,
13626
13492
  },
13627
- "xai/grok-3-mini": {
13628
- id: "xai/grok-3-mini",
13629
- name: "Grok 3 Mini Beta",
13493
+ "xai/grok-4.1-fast-reasoning": {
13494
+ id: "xai/grok-4.1-fast-reasoning",
13495
+ name: "Grok 4.1 Fast Reasoning",
13630
13496
  api: "anthropic-messages",
13631
13497
  provider: "vercel-ai-gateway",
13632
13498
  baseUrl: "https://ai-gateway.vercel.sh",
13633
- reasoning: false,
13634
- input: ["text"],
13499
+ reasoning: true,
13500
+ input: ["text", "image"],
13635
13501
  cost: {
13636
- input: 0.3,
13502
+ input: 0.19999999999999998,
13637
13503
  output: 0.5,
13638
- cacheRead: 0.075,
13504
+ cacheRead: 0.049999999999999996,
13639
13505
  cacheWrite: 0,
13640
13506
  },
13641
- contextWindow: 131072,
13642
- maxTokens: 131072,
13507
+ contextWindow: 1000000,
13508
+ maxTokens: 1000000,
13643
13509
  },
13644
- "xai/grok-3-mini-fast": {
13645
- id: "xai/grok-3-mini-fast",
13646
- name: "Grok 3 Mini Fast Beta",
13510
+ "xai/grok-4.20-multi-agent": {
13511
+ id: "xai/grok-4.20-multi-agent",
13512
+ name: "Grok 4.20 Multi-Agent",
13647
13513
  api: "anthropic-messages",
13648
13514
  provider: "vercel-ai-gateway",
13649
13515
  baseUrl: "https://ai-gateway.vercel.sh",
13650
- reasoning: false,
13651
- input: ["text"],
13516
+ reasoning: true,
13517
+ input: ["text", "image"],
13652
13518
  cost: {
13653
- input: 0.6,
13654
- output: 4,
13655
- cacheRead: 0,
13519
+ input: 1.25,
13520
+ output: 2.5,
13521
+ cacheRead: 0.19999999999999998,
13656
13522
  cacheWrite: 0,
13657
13523
  },
13658
- contextWindow: 131072,
13659
- maxTokens: 131072,
13524
+ contextWindow: 2000000,
13525
+ maxTokens: 2000000,
13660
13526
  },
13661
- "xai/grok-4": {
13662
- id: "xai/grok-4",
13663
- name: "Grok 4",
13664
- api: "anthropic-messages",
13665
- provider: "vercel-ai-gateway",
13666
- baseUrl: "https://ai-gateway.vercel.sh",
13667
- reasoning: true,
13668
- input: ["text", "image"],
13669
- cost: {
13670
- input: 3,
13671
- output: 15,
13672
- cacheRead: 0.75,
13673
- cacheWrite: 0,
13674
- },
13675
- contextWindow: 256000,
13676
- maxTokens: 256000,
13677
- },
13678
- "xai/grok-4-fast-non-reasoning": {
13679
- id: "xai/grok-4-fast-non-reasoning",
13680
- name: "Grok 4 Fast Non-Reasoning",
13681
- api: "anthropic-messages",
13682
- provider: "vercel-ai-gateway",
13683
- baseUrl: "https://ai-gateway.vercel.sh",
13684
- reasoning: false,
13685
- input: ["text", "image"],
13686
- cost: {
13687
- input: 0.19999999999999998,
13688
- output: 0.5,
13689
- cacheRead: 0.049999999999999996,
13690
- cacheWrite: 0,
13691
- },
13692
- contextWindow: 2000000,
13693
- maxTokens: 256000,
13694
- },
13695
- "xai/grok-4-fast-reasoning": {
13696
- id: "xai/grok-4-fast-reasoning",
13697
- name: "Grok 4 Fast Reasoning",
13698
- api: "anthropic-messages",
13699
- provider: "vercel-ai-gateway",
13700
- baseUrl: "https://ai-gateway.vercel.sh",
13701
- reasoning: true,
13702
- input: ["text", "image"],
13703
- cost: {
13704
- input: 0.19999999999999998,
13705
- output: 0.5,
13706
- cacheRead: 0.049999999999999996,
13707
- cacheWrite: 0,
13708
- },
13709
- contextWindow: 2000000,
13710
- maxTokens: 256000,
13711
- },
13712
- "xai/grok-4.1-fast-non-reasoning": {
13713
- id: "xai/grok-4.1-fast-non-reasoning",
13714
- name: "Grok 4.1 Fast Non-Reasoning",
13715
- api: "anthropic-messages",
13716
- provider: "vercel-ai-gateway",
13717
- baseUrl: "https://ai-gateway.vercel.sh",
13718
- reasoning: false,
13719
- input: ["text", "image"],
13720
- cost: {
13721
- input: 0.19999999999999998,
13722
- output: 0.5,
13723
- cacheRead: 0.049999999999999996,
13724
- cacheWrite: 0,
13725
- },
13726
- contextWindow: 2000000,
13727
- maxTokens: 30000,
13728
- },
13729
- "xai/grok-4.1-fast-reasoning": {
13730
- id: "xai/grok-4.1-fast-reasoning",
13731
- name: "Grok 4.1 Fast Reasoning",
13732
- api: "anthropic-messages",
13733
- provider: "vercel-ai-gateway",
13734
- baseUrl: "https://ai-gateway.vercel.sh",
13735
- reasoning: true,
13736
- input: ["text", "image"],
13737
- cost: {
13738
- input: 0.19999999999999998,
13739
- output: 0.5,
13740
- cacheRead: 0.049999999999999996,
13741
- cacheWrite: 0,
13742
- },
13743
- contextWindow: 2000000,
13744
- maxTokens: 30000,
13745
- },
13746
- "xai/grok-4.20-multi-agent": {
13747
- id: "xai/grok-4.20-multi-agent",
13748
- name: "Grok 4.20 Multi-Agent",
13749
- api: "anthropic-messages",
13750
- provider: "vercel-ai-gateway",
13751
- baseUrl: "https://ai-gateway.vercel.sh",
13752
- reasoning: true,
13753
- input: ["text", "image"],
13754
- cost: {
13755
- input: 1.25,
13756
- output: 2.5,
13757
- cacheRead: 0.19999999999999998,
13758
- cacheWrite: 0,
13759
- },
13760
- contextWindow: 2000000,
13761
- maxTokens: 2000000,
13762
- },
13763
- "xai/grok-4.20-multi-agent-beta": {
13764
- id: "xai/grok-4.20-multi-agent-beta",
13765
- name: "Grok 4.20 Multi Agent Beta",
13527
+ "xai/grok-4.20-multi-agent-beta": {
13528
+ id: "xai/grok-4.20-multi-agent-beta",
13529
+ name: "Grok 4.20 Multi Agent Beta",
13766
13530
  api: "anthropic-messages",
13767
13531
  provider: "vercel-ai-gateway",
13768
13532
  baseUrl: "https://ai-gateway.vercel.sh",
@@ -13862,18 +13626,18 @@ export const MODELS = {
13862
13626
  contextWindow: 1000000,
13863
13627
  maxTokens: 1000000,
13864
13628
  },
13865
- "xai/grok-code-fast-1": {
13866
- id: "xai/grok-code-fast-1",
13867
- name: "Grok Code Fast 1",
13629
+ "xai/grok-build-0.1": {
13630
+ id: "xai/grok-build-0.1",
13631
+ name: "Grok Build 0.1",
13868
13632
  api: "anthropic-messages",
13869
13633
  provider: "vercel-ai-gateway",
13870
13634
  baseUrl: "https://ai-gateway.vercel.sh",
13871
13635
  reasoning: true,
13872
- input: ["text"],
13636
+ input: ["text", "image"],
13873
13637
  cost: {
13874
- input: 0.19999999999999998,
13875
- output: 1.5,
13876
- cacheRead: 0.02,
13638
+ input: 1,
13639
+ output: 2,
13640
+ cacheRead: 0.19999999999999998,
13877
13641
  cacheWrite: 0,
13878
13642
  },
13879
13643
  contextWindow: 256000,
@@ -13922,9 +13686,9 @@ export const MODELS = {
13922
13686
  reasoning: true,
13923
13687
  input: ["text", "image"],
13924
13688
  cost: {
13925
- input: 0.39999999999999997,
13926
- output: 2,
13927
- cacheRead: 0.08,
13689
+ input: 0.14,
13690
+ output: 0.28,
13691
+ cacheRead: 0.0028,
13928
13692
  cacheWrite: 0,
13929
13693
  },
13930
13694
  contextWindow: 1050000,
@@ -13939,9 +13703,9 @@ export const MODELS = {
13939
13703
  reasoning: true,
13940
13704
  input: ["text", "image"],
13941
13705
  cost: {
13942
- input: 1,
13943
- output: 3,
13944
- cacheRead: 0.19999999999999998,
13706
+ input: 0.435,
13707
+ output: 0.87,
13708
+ cacheRead: 0.0036,
13945
13709
  cacheWrite: 0,
13946
13710
  },
13947
13711
  contextWindow: 1050000,
@@ -14170,329 +13934,6 @@ export const MODELS = {
14170
13934
  },
14171
13935
  },
14172
13936
  "xai": {
14173
- "grok-2": {
14174
- id: "grok-2",
14175
- name: "Grok 2",
14176
- api: "openai-completions",
14177
- provider: "xai",
14178
- baseUrl: "https://api.x.ai/v1",
14179
- reasoning: false,
14180
- input: ["text"],
14181
- cost: {
14182
- input: 2,
14183
- output: 10,
14184
- cacheRead: 2,
14185
- cacheWrite: 0,
14186
- },
14187
- contextWindow: 131072,
14188
- maxTokens: 8192,
14189
- },
14190
- "grok-2-1212": {
14191
- id: "grok-2-1212",
14192
- name: "Grok 2 (1212)",
14193
- api: "openai-completions",
14194
- provider: "xai",
14195
- baseUrl: "https://api.x.ai/v1",
14196
- reasoning: false,
14197
- input: ["text"],
14198
- cost: {
14199
- input: 2,
14200
- output: 10,
14201
- cacheRead: 2,
14202
- cacheWrite: 0,
14203
- },
14204
- contextWindow: 131072,
14205
- maxTokens: 8192,
14206
- },
14207
- "grok-2-latest": {
14208
- id: "grok-2-latest",
14209
- name: "Grok 2 Latest",
14210
- api: "openai-completions",
14211
- provider: "xai",
14212
- baseUrl: "https://api.x.ai/v1",
14213
- reasoning: false,
14214
- input: ["text"],
14215
- cost: {
14216
- input: 2,
14217
- output: 10,
14218
- cacheRead: 2,
14219
- cacheWrite: 0,
14220
- },
14221
- contextWindow: 131072,
14222
- maxTokens: 8192,
14223
- },
14224
- "grok-2-vision": {
14225
- id: "grok-2-vision",
14226
- name: "Grok 2 Vision",
14227
- api: "openai-completions",
14228
- provider: "xai",
14229
- baseUrl: "https://api.x.ai/v1",
14230
- reasoning: false,
14231
- input: ["text", "image"],
14232
- cost: {
14233
- input: 2,
14234
- output: 10,
14235
- cacheRead: 2,
14236
- cacheWrite: 0,
14237
- },
14238
- contextWindow: 8192,
14239
- maxTokens: 4096,
14240
- },
14241
- "grok-2-vision-1212": {
14242
- id: "grok-2-vision-1212",
14243
- name: "Grok 2 Vision (1212)",
14244
- api: "openai-completions",
14245
- provider: "xai",
14246
- baseUrl: "https://api.x.ai/v1",
14247
- reasoning: false,
14248
- input: ["text", "image"],
14249
- cost: {
14250
- input: 2,
14251
- output: 10,
14252
- cacheRead: 2,
14253
- cacheWrite: 0,
14254
- },
14255
- contextWindow: 8192,
14256
- maxTokens: 4096,
14257
- },
14258
- "grok-2-vision-latest": {
14259
- id: "grok-2-vision-latest",
14260
- name: "Grok 2 Vision Latest",
14261
- api: "openai-completions",
14262
- provider: "xai",
14263
- baseUrl: "https://api.x.ai/v1",
14264
- reasoning: false,
14265
- input: ["text", "image"],
14266
- cost: {
14267
- input: 2,
14268
- output: 10,
14269
- cacheRead: 2,
14270
- cacheWrite: 0,
14271
- },
14272
- contextWindow: 8192,
14273
- maxTokens: 4096,
14274
- },
14275
- "grok-3": {
14276
- id: "grok-3",
14277
- name: "Grok 3",
14278
- api: "openai-completions",
14279
- provider: "xai",
14280
- baseUrl: "https://api.x.ai/v1",
14281
- reasoning: false,
14282
- input: ["text"],
14283
- cost: {
14284
- input: 3,
14285
- output: 15,
14286
- cacheRead: 0.75,
14287
- cacheWrite: 0,
14288
- },
14289
- contextWindow: 131072,
14290
- maxTokens: 8192,
14291
- },
14292
- "grok-3-fast": {
14293
- id: "grok-3-fast",
14294
- name: "Grok 3 Fast",
14295
- api: "openai-completions",
14296
- provider: "xai",
14297
- baseUrl: "https://api.x.ai/v1",
14298
- reasoning: false,
14299
- input: ["text"],
14300
- cost: {
14301
- input: 5,
14302
- output: 25,
14303
- cacheRead: 1.25,
14304
- cacheWrite: 0,
14305
- },
14306
- contextWindow: 131072,
14307
- maxTokens: 8192,
14308
- },
14309
- "grok-3-fast-latest": {
14310
- id: "grok-3-fast-latest",
14311
- name: "Grok 3 Fast Latest",
14312
- api: "openai-completions",
14313
- provider: "xai",
14314
- baseUrl: "https://api.x.ai/v1",
14315
- reasoning: false,
14316
- input: ["text"],
14317
- cost: {
14318
- input: 5,
14319
- output: 25,
14320
- cacheRead: 1.25,
14321
- cacheWrite: 0,
14322
- },
14323
- contextWindow: 131072,
14324
- maxTokens: 8192,
14325
- },
14326
- "grok-3-latest": {
14327
- id: "grok-3-latest",
14328
- name: "Grok 3 Latest",
14329
- api: "openai-completions",
14330
- provider: "xai",
14331
- baseUrl: "https://api.x.ai/v1",
14332
- reasoning: false,
14333
- input: ["text"],
14334
- cost: {
14335
- input: 3,
14336
- output: 15,
14337
- cacheRead: 0.75,
14338
- cacheWrite: 0,
14339
- },
14340
- contextWindow: 131072,
14341
- maxTokens: 8192,
14342
- },
14343
- "grok-3-mini": {
14344
- id: "grok-3-mini",
14345
- name: "Grok 3 Mini",
14346
- api: "openai-completions",
14347
- provider: "xai",
14348
- baseUrl: "https://api.x.ai/v1",
14349
- reasoning: true,
14350
- input: ["text"],
14351
- cost: {
14352
- input: 0.3,
14353
- output: 0.5,
14354
- cacheRead: 0.075,
14355
- cacheWrite: 0,
14356
- },
14357
- contextWindow: 131072,
14358
- maxTokens: 8192,
14359
- },
14360
- "grok-3-mini-fast": {
14361
- id: "grok-3-mini-fast",
14362
- name: "Grok 3 Mini Fast",
14363
- api: "openai-completions",
14364
- provider: "xai",
14365
- baseUrl: "https://api.x.ai/v1",
14366
- reasoning: true,
14367
- input: ["text"],
14368
- cost: {
14369
- input: 0.6,
14370
- output: 4,
14371
- cacheRead: 0.15,
14372
- cacheWrite: 0,
14373
- },
14374
- contextWindow: 131072,
14375
- maxTokens: 8192,
14376
- },
14377
- "grok-3-mini-fast-latest": {
14378
- id: "grok-3-mini-fast-latest",
14379
- name: "Grok 3 Mini Fast Latest",
14380
- api: "openai-completions",
14381
- provider: "xai",
14382
- baseUrl: "https://api.x.ai/v1",
14383
- reasoning: true,
14384
- input: ["text"],
14385
- cost: {
14386
- input: 0.6,
14387
- output: 4,
14388
- cacheRead: 0.15,
14389
- cacheWrite: 0,
14390
- },
14391
- contextWindow: 131072,
14392
- maxTokens: 8192,
14393
- },
14394
- "grok-3-mini-latest": {
14395
- id: "grok-3-mini-latest",
14396
- name: "Grok 3 Mini Latest",
14397
- api: "openai-completions",
14398
- provider: "xai",
14399
- baseUrl: "https://api.x.ai/v1",
14400
- reasoning: true,
14401
- input: ["text"],
14402
- cost: {
14403
- input: 0.3,
14404
- output: 0.5,
14405
- cacheRead: 0.075,
14406
- cacheWrite: 0,
14407
- },
14408
- contextWindow: 131072,
14409
- maxTokens: 8192,
14410
- },
14411
- "grok-4": {
14412
- id: "grok-4",
14413
- name: "Grok 4",
14414
- api: "openai-completions",
14415
- provider: "xai",
14416
- baseUrl: "https://api.x.ai/v1",
14417
- reasoning: true,
14418
- input: ["text"],
14419
- cost: {
14420
- input: 3,
14421
- output: 15,
14422
- cacheRead: 0.75,
14423
- cacheWrite: 0,
14424
- },
14425
- contextWindow: 256000,
14426
- maxTokens: 64000,
14427
- },
14428
- "grok-4-1-fast": {
14429
- id: "grok-4-1-fast",
14430
- name: "Grok 4.1 Fast",
14431
- api: "openai-completions",
14432
- provider: "xai",
14433
- baseUrl: "https://api.x.ai/v1",
14434
- reasoning: true,
14435
- input: ["text", "image"],
14436
- cost: {
14437
- input: 0.2,
14438
- output: 0.5,
14439
- cacheRead: 0.05,
14440
- cacheWrite: 0,
14441
- },
14442
- contextWindow: 2000000,
14443
- maxTokens: 30000,
14444
- },
14445
- "grok-4-1-fast-non-reasoning": {
14446
- id: "grok-4-1-fast-non-reasoning",
14447
- name: "Grok 4.1 Fast (Non-Reasoning)",
14448
- api: "openai-completions",
14449
- provider: "xai",
14450
- baseUrl: "https://api.x.ai/v1",
14451
- reasoning: false,
14452
- input: ["text", "image"],
14453
- cost: {
14454
- input: 0.2,
14455
- output: 0.5,
14456
- cacheRead: 0.05,
14457
- cacheWrite: 0,
14458
- },
14459
- contextWindow: 2000000,
14460
- maxTokens: 30000,
14461
- },
14462
- "grok-4-fast": {
14463
- id: "grok-4-fast",
14464
- name: "Grok 4 Fast",
14465
- api: "openai-completions",
14466
- provider: "xai",
14467
- baseUrl: "https://api.x.ai/v1",
14468
- reasoning: true,
14469
- input: ["text", "image"],
14470
- cost: {
14471
- input: 0.2,
14472
- output: 0.5,
14473
- cacheRead: 0.05,
14474
- cacheWrite: 0,
14475
- },
14476
- contextWindow: 2000000,
14477
- maxTokens: 30000,
14478
- },
14479
- "grok-4-fast-non-reasoning": {
14480
- id: "grok-4-fast-non-reasoning",
14481
- name: "Grok 4 Fast (Non-Reasoning)",
14482
- api: "openai-completions",
14483
- provider: "xai",
14484
- baseUrl: "https://api.x.ai/v1",
14485
- reasoning: false,
14486
- input: ["text", "image"],
14487
- cost: {
14488
- input: 0.2,
14489
- output: 0.5,
14490
- cacheRead: 0.05,
14491
- cacheWrite: 0,
14492
- },
14493
- contextWindow: 2000000,
14494
- maxTokens: 30000,
14495
- },
14496
13937
  "grok-4.20-0309-non-reasoning": {
14497
13938
  id: "grok-4.20-0309-non-reasoning",
14498
13939
  name: "Grok 4.20 (Non-Reasoning)",
@@ -14502,8 +13943,8 @@ export const MODELS = {
14502
13943
  reasoning: false,
14503
13944
  input: ["text", "image"],
14504
13945
  cost: {
14505
- input: 2,
14506
- output: 6,
13946
+ input: 1.25,
13947
+ output: 2.5,
14507
13948
  cacheRead: 0.2,
14508
13949
  cacheWrite: 0,
14509
13950
  },
@@ -14519,8 +13960,8 @@ export const MODELS = {
14519
13960
  reasoning: true,
14520
13961
  input: ["text", "image"],
14521
13962
  cost: {
14522
- input: 2,
14523
- output: 6,
13963
+ input: 1.25,
13964
+ output: 2.5,
14524
13965
  cacheRead: 0.2,
14525
13966
  cacheWrite: 0,
14526
13967
  },
@@ -14544,22 +13985,22 @@ export const MODELS = {
14544
13985
  contextWindow: 1000000,
14545
13986
  maxTokens: 30000,
14546
13987
  },
14547
- "grok-beta": {
14548
- id: "grok-beta",
14549
- name: "Grok Beta",
13988
+ "grok-build-0.1": {
13989
+ id: "grok-build-0.1",
13990
+ name: "Grok Build 0.1",
14550
13991
  api: "openai-completions",
14551
13992
  provider: "xai",
14552
13993
  baseUrl: "https://api.x.ai/v1",
14553
- reasoning: false,
14554
- input: ["text"],
13994
+ reasoning: true,
13995
+ input: ["text", "image"],
14555
13996
  cost: {
14556
- input: 5,
14557
- output: 15,
14558
- cacheRead: 5,
13997
+ input: 1,
13998
+ output: 2,
13999
+ cacheRead: 0.2,
14559
14000
  cacheWrite: 0,
14560
14001
  },
14561
- contextWindow: 131072,
14562
- maxTokens: 4096,
14002
+ contextWindow: 256000,
14003
+ maxTokens: 256000,
14563
14004
  },
14564
14005
  "grok-code-fast-1": {
14565
14006
  id: "grok-code-fast-1",
@@ -14567,7 +14008,7 @@ export const MODELS = {
14567
14008
  api: "openai-completions",
14568
14009
  provider: "xai",
14569
14010
  baseUrl: "https://api.x.ai/v1",
14570
- reasoning: true,
14011
+ reasoning: false,
14571
14012
  input: ["text"],
14572
14013
  cost: {
14573
14014
  input: 0.2,
@@ -14575,25 +14016,8 @@ export const MODELS = {
14575
14016
  cacheRead: 0.02,
14576
14017
  cacheWrite: 0,
14577
14018
  },
14578
- contextWindow: 256000,
14579
- maxTokens: 10000,
14580
- },
14581
- "grok-vision-beta": {
14582
- id: "grok-vision-beta",
14583
- name: "Grok Vision Beta",
14584
- api: "openai-completions",
14585
- provider: "xai",
14586
- baseUrl: "https://api.x.ai/v1",
14587
- reasoning: false,
14588
- input: ["text", "image"],
14589
- cost: {
14590
- input: 5,
14591
- output: 15,
14592
- cacheRead: 5,
14593
- cacheWrite: 0,
14594
- },
14595
- contextWindow: 8192,
14596
- maxTokens: 4096,
14019
+ contextWindow: 32768,
14020
+ maxTokens: 8192,
14597
14021
  },
14598
14022
  },
14599
14023
  };