@dreb/ai 2.19.3 → 2.21.0

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.
@@ -155,6 +155,23 @@ export const MODELS = {
155
155
  contextWindow: 1000000,
156
156
  maxTokens: 128000,
157
157
  },
158
+ "anthropic.claude-opus-4-8": {
159
+ id: "anthropic.claude-opus-4-8",
160
+ name: "Claude Opus 4.8",
161
+ api: "bedrock-converse-stream",
162
+ provider: "amazon-bedrock",
163
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
164
+ reasoning: true,
165
+ input: ["text", "image"],
166
+ cost: {
167
+ input: 5,
168
+ output: 25,
169
+ cacheRead: 0.5,
170
+ cacheWrite: 6.25,
171
+ },
172
+ contextWindow: 1000000,
173
+ maxTokens: 128000,
174
+ },
158
175
  "anthropic.claude-sonnet-4-5-20250929-v1:0": {
159
176
  id: "anthropic.claude-sonnet-4-5-20250929-v1:0",
160
177
  name: "Claude Sonnet 4.5",
@@ -1738,6 +1755,23 @@ export const MODELS = {
1738
1755
  contextWindow: 1000000,
1739
1756
  maxTokens: 128000,
1740
1757
  },
1758
+ "claude-opus-4-8": {
1759
+ id: "claude-opus-4-8",
1760
+ name: "Claude Opus 4.8",
1761
+ api: "anthropic-messages",
1762
+ provider: "anthropic",
1763
+ baseUrl: "https://api.anthropic.com",
1764
+ reasoning: true,
1765
+ input: ["text", "image"],
1766
+ cost: {
1767
+ input: 5,
1768
+ output: 25,
1769
+ cacheRead: 0.5,
1770
+ cacheWrite: 6.25,
1771
+ },
1772
+ contextWindow: 1000000,
1773
+ maxTokens: 128000,
1774
+ },
1741
1775
  "claude-sonnet-4-0": {
1742
1776
  id: "claude-sonnet-4-0",
1743
1777
  name: "Claude Sonnet 4 (latest)",
@@ -1904,7 +1938,7 @@ export const MODELS = {
1904
1938
  cost: {
1905
1939
  input: 0.1,
1906
1940
  output: 0.4,
1907
- cacheRead: 0.03,
1941
+ cacheRead: 0.025,
1908
1942
  cacheWrite: 0,
1909
1943
  },
1910
1944
  contextWindow: 1047576,
@@ -1989,7 +2023,7 @@ export const MODELS = {
1989
2023
  cost: {
1990
2024
  input: 0.15,
1991
2025
  output: 0.6,
1992
- cacheRead: 0.08,
2026
+ cacheRead: 0.075,
1993
2027
  cacheWrite: 0,
1994
2028
  },
1995
2029
  contextWindow: 128000,
@@ -2108,7 +2142,7 @@ export const MODELS = {
2108
2142
  cost: {
2109
2143
  input: 1.25,
2110
2144
  output: 10,
2111
- cacheRead: 0.13,
2145
+ cacheRead: 0.125,
2112
2146
  cacheWrite: 0,
2113
2147
  },
2114
2148
  contextWindow: 400000,
@@ -2516,7 +2550,7 @@ export const MODELS = {
2516
2550
  cost: {
2517
2551
  input: 1.1,
2518
2552
  output: 4.4,
2519
- cacheRead: 0.28,
2553
+ cacheRead: 0.275,
2520
2554
  cacheWrite: 0,
2521
2555
  },
2522
2556
  contextWindow: 200000,
@@ -2575,23 +2609,6 @@ export const MODELS = {
2575
2609
  contextWindow: 32000,
2576
2610
  maxTokens: 8000,
2577
2611
  },
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
2612
  },
2596
2613
  "github-copilot": {
2597
2614
  "claude-haiku-4.5": {
@@ -2759,6 +2776,25 @@ export const MODELS = {
2759
2776
  contextWindow: 128000,
2760
2777
  maxTokens: 64000,
2761
2778
  },
2779
+ "gemini-3.5-flash": {
2780
+ id: "gemini-3.5-flash",
2781
+ name: "Gemini 3.5 Flash",
2782
+ api: "openai-completions",
2783
+ provider: "github-copilot",
2784
+ baseUrl: "https://api.individual.githubcopilot.com",
2785
+ 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" },
2786
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
2787
+ reasoning: true,
2788
+ input: ["text", "image"],
2789
+ cost: {
2790
+ input: 0,
2791
+ output: 0,
2792
+ cacheRead: 0,
2793
+ cacheWrite: 0,
2794
+ },
2795
+ contextWindow: 128000,
2796
+ maxTokens: 64000,
2797
+ },
2762
2798
  "gpt-4.1": {
2763
2799
  id: "gpt-4.1",
2764
2800
  name: "GPT-4.1",
@@ -2944,57 +2980,6 @@ export const MODELS = {
2944
2980
  },
2945
2981
  },
2946
2982
  "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
2983
  "gemini-2.0-flash": {
2999
2984
  id: "gemini-2.0-flash",
3000
2985
  name: "Gemini 2.0 Flash",
@@ -3014,7 +2999,7 @@ export const MODELS = {
3014
2999
  },
3015
3000
  "gemini-2.0-flash-lite": {
3016
3001
  id: "gemini-2.0-flash-lite",
3017
- name: "Gemini 2.0 Flash Lite",
3002
+ name: "Gemini 2.0 Flash-Lite",
3018
3003
  api: "google-generative-ai",
3019
3004
  provider: "google",
3020
3005
  baseUrl: "https://generativelanguage.googleapis.com/v1beta",
@@ -3048,7 +3033,7 @@ export const MODELS = {
3048
3033
  },
3049
3034
  "gemini-2.5-flash-lite": {
3050
3035
  id: "gemini-2.5-flash-lite",
3051
- name: "Gemini 2.5 Flash Lite",
3036
+ name: "Gemini 2.5 Flash-Lite",
3052
3037
  api: "google-generative-ai",
3053
3038
  provider: "google",
3054
3039
  baseUrl: "https://generativelanguage.googleapis.com/v1beta",
@@ -3063,91 +3048,6 @@ export const MODELS = {
3063
3048
  contextWindow: 1048576,
3064
3049
  maxTokens: 65536,
3065
3050
  },
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
3051
  "gemini-2.5-pro": {
3152
3052
  id: "gemini-2.5-pro",
3153
3053
  name: "Gemini 2.5 Pro",
@@ -3165,40 +3065,6 @@ export const MODELS = {
3165
3065
  contextWindow: 1048576,
3166
3066
  maxTokens: 65536,
3167
3067
  },
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
3068
  "gemini-3-flash-preview": {
3203
3069
  id: "gemini-3-flash-preview",
3204
3070
  name: "Gemini 3 Flash Preview",
@@ -3230,8 +3096,8 @@ export const MODELS = {
3230
3096
  cacheRead: 0.2,
3231
3097
  cacheWrite: 0,
3232
3098
  },
3233
- contextWindow: 1000000,
3234
- maxTokens: 64000,
3099
+ contextWindow: 1048576,
3100
+ maxTokens: 65536,
3235
3101
  },
3236
3102
  "gemini-3.1-flash-lite": {
3237
3103
  id: "gemini-3.1-flash-lite",
@@ -3352,60 +3218,9 @@ export const MODELS = {
3352
3218
  contextWindow: 1048576,
3353
3219
  maxTokens: 65536,
3354
3220
  },
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
3221
  "gemma-4-26b-a4b-it": {
3407
3222
  id: "gemma-4-26b-a4b-it",
3408
- name: "Gemma 4 26B",
3223
+ name: "Gemma 4 26B A4B IT",
3409
3224
  api: "google-generative-ai",
3410
3225
  provider: "google",
3411
3226
  baseUrl: "https://generativelanguage.googleapis.com/v1beta",
@@ -3417,12 +3232,12 @@ export const MODELS = {
3417
3232
  cacheRead: 0,
3418
3233
  cacheWrite: 0,
3419
3234
  },
3420
- contextWindow: 256000,
3421
- maxTokens: 8192,
3235
+ contextWindow: 262144,
3236
+ maxTokens: 32768,
3422
3237
  },
3423
3238
  "gemma-4-31b-it": {
3424
3239
  id: "gemma-4-31b-it",
3425
- name: "Gemma 4 31B",
3240
+ name: "Gemma 4 31B IT",
3426
3241
  api: "google-generative-ai",
3427
3242
  provider: "google",
3428
3243
  baseUrl: "https://generativelanguage.googleapis.com/v1beta",
@@ -3434,8 +3249,8 @@ export const MODELS = {
3434
3249
  cacheRead: 0,
3435
3250
  cacheWrite: 0,
3436
3251
  },
3437
- contextWindow: 256000,
3438
- maxTokens: 8192,
3252
+ contextWindow: 262144,
3253
+ maxTokens: 32768,
3439
3254
  },
3440
3255
  },
3441
3256
  "google-antigravity": {
@@ -4119,7 +3934,7 @@ export const MODELS = {
4119
3934
  cost: {
4120
3935
  input: 1,
4121
3936
  output: 3,
4122
- cacheRead: 0,
3937
+ cacheRead: 0.5,
4123
3938
  cacheWrite: 0,
4124
3939
  },
4125
3940
  contextWindow: 262144,
@@ -4136,7 +3951,7 @@ export const MODELS = {
4136
3951
  cost: {
4137
3952
  input: 0.15,
4138
3953
  output: 0.6,
4139
- cacheRead: 0,
3954
+ cacheRead: 0.075,
4140
3955
  cacheWrite: 0,
4141
3956
  },
4142
3957
  contextWindow: 131072,
@@ -4153,7 +3968,7 @@ export const MODELS = {
4153
3968
  cost: {
4154
3969
  input: 0.075,
4155
3970
  output: 0.3,
4156
- cacheRead: 0,
3971
+ cacheRead: 0.0375,
4157
3972
  cacheWrite: 0,
4158
3973
  },
4159
3974
  contextWindow: 131072,
@@ -4438,9 +4253,9 @@ export const MODELS = {
4438
4253
  reasoning: true,
4439
4254
  input: ["text"],
4440
4255
  cost: {
4441
- input: 1.74,
4442
- output: 3.48,
4443
- cacheRead: 0.145,
4256
+ input: 0.435,
4257
+ output: 0.87,
4258
+ cacheRead: 0.003625,
4444
4259
  cacheWrite: 0,
4445
4260
  },
4446
4261
  contextWindow: 1048576,
@@ -5295,7 +5110,7 @@ export const MODELS = {
5295
5110
  cost: {
5296
5111
  input: 0.1,
5297
5112
  output: 0.4,
5298
- cacheRead: 0.03,
5113
+ cacheRead: 0.025,
5299
5114
  cacheWrite: 0,
5300
5115
  },
5301
5116
  contextWindow: 1047576,
@@ -5380,7 +5195,7 @@ export const MODELS = {
5380
5195
  cost: {
5381
5196
  input: 0.15,
5382
5197
  output: 0.6,
5383
- cacheRead: 0.08,
5198
+ cacheRead: 0.075,
5384
5199
  cacheWrite: 0,
5385
5200
  },
5386
5201
  contextWindow: 128000,
@@ -5499,7 +5314,7 @@ export const MODELS = {
5499
5314
  cost: {
5500
5315
  input: 1.25,
5501
5316
  output: 10,
5502
- cacheRead: 0.13,
5317
+ cacheRead: 0.125,
5503
5318
  cacheWrite: 0,
5504
5319
  },
5505
5320
  contextWindow: 400000,
@@ -5907,7 +5722,7 @@ export const MODELS = {
5907
5722
  cost: {
5908
5723
  input: 1.1,
5909
5724
  output: 4.4,
5910
- cacheRead: 0.28,
5725
+ cacheRead: 0.275,
5911
5726
  cacheWrite: 0,
5912
5727
  },
5913
5728
  contextWindow: 200000,
@@ -6085,7 +5900,7 @@ export const MODELS = {
6085
5900
  cacheWrite: 0,
6086
5901
  },
6087
5902
  contextWindow: 200000,
6088
- maxTokens: 128000,
5903
+ maxTokens: 32000,
6089
5904
  },
6090
5905
  "claude-haiku-4-5": {
6091
5906
  id: "claude-haiku-4-5",
@@ -6172,6 +5987,23 @@ export const MODELS = {
6172
5987
  contextWindow: 1000000,
6173
5988
  maxTokens: 128000,
6174
5989
  },
5990
+ "claude-opus-4-8": {
5991
+ id: "claude-opus-4-8",
5992
+ name: "Claude Opus 4.8",
5993
+ api: "anthropic-messages",
5994
+ provider: "opencode",
5995
+ baseUrl: "https://opencode.ai/zen",
5996
+ reasoning: true,
5997
+ input: ["text", "image"],
5998
+ cost: {
5999
+ input: 5,
6000
+ output: 25,
6001
+ cacheRead: 0.5,
6002
+ cacheWrite: 6.25,
6003
+ },
6004
+ contextWindow: 1000000,
6005
+ maxTokens: 128000,
6006
+ },
6175
6007
  "claude-sonnet-4": {
6176
6008
  id: "claude-sonnet-4",
6177
6009
  name: "Claude Sonnet 4",
@@ -6274,6 +6106,23 @@ export const MODELS = {
6274
6106
  contextWindow: 1048576,
6275
6107
  maxTokens: 65536,
6276
6108
  },
6109
+ "gemini-3.5-flash": {
6110
+ id: "gemini-3.5-flash",
6111
+ name: "Gemini 3.5 Flash",
6112
+ api: "google-generative-ai",
6113
+ provider: "opencode",
6114
+ baseUrl: "https://opencode.ai/zen/v1",
6115
+ reasoning: true,
6116
+ input: ["text", "image"],
6117
+ cost: {
6118
+ input: 1.5,
6119
+ output: 9,
6120
+ cacheRead: 0.15,
6121
+ cacheWrite: 0,
6122
+ },
6123
+ contextWindow: 1048576,
6124
+ maxTokens: 65536,
6125
+ },
6277
6126
  "glm-5": {
6278
6127
  id: "glm-5",
6279
6128
  name: "GLM-5",
@@ -6580,6 +6429,23 @@ export const MODELS = {
6580
6429
  contextWindow: 1050000,
6581
6430
  maxTokens: 128000,
6582
6431
  },
6432
+ "grok-build-0.1": {
6433
+ id: "grok-build-0.1",
6434
+ name: "Grok Build 0.1",
6435
+ api: "openai-completions",
6436
+ provider: "opencode",
6437
+ baseUrl: "https://opencode.ai/zen/v1",
6438
+ reasoning: true,
6439
+ input: ["text", "image"],
6440
+ cost: {
6441
+ input: 1,
6442
+ output: 2,
6443
+ cacheRead: 0.2,
6444
+ cacheWrite: 0,
6445
+ },
6446
+ contextWindow: 256000,
6447
+ maxTokens: 256000,
6448
+ },
6583
6449
  "kimi-k2.5": {
6584
6450
  id: "kimi-k2.5",
6585
6451
  name: "Kimi K2.5",
@@ -6614,35 +6480,35 @@ export const MODELS = {
6614
6480
  contextWindow: 262144,
6615
6481
  maxTokens: 65536,
6616
6482
  },
6617
- "minimax-m2.5": {
6618
- id: "minimax-m2.5",
6619
- name: "MiniMax M2.5",
6483
+ "mimo-v2.5-free": {
6484
+ id: "mimo-v2.5-free",
6485
+ name: "MiMo V2.5 Free",
6620
6486
  api: "openai-completions",
6621
6487
  provider: "opencode",
6622
6488
  baseUrl: "https://opencode.ai/zen/v1",
6623
6489
  reasoning: true,
6624
- input: ["text"],
6490
+ input: ["text", "image"],
6625
6491
  cost: {
6626
- input: 0.3,
6627
- output: 1.2,
6628
- cacheRead: 0.06,
6492
+ input: 0,
6493
+ output: 0,
6494
+ cacheRead: 0,
6629
6495
  cacheWrite: 0,
6630
6496
  },
6631
- contextWindow: 204800,
6632
- maxTokens: 131072,
6497
+ contextWindow: 1000000,
6498
+ maxTokens: 128000,
6633
6499
  },
6634
- "minimax-m2.5-free": {
6635
- id: "minimax-m2.5-free",
6636
- name: "MiniMax M2.5 Free",
6637
- api: "anthropic-messages",
6500
+ "minimax-m2.5": {
6501
+ id: "minimax-m2.5",
6502
+ name: "MiniMax M2.5",
6503
+ api: "openai-completions",
6638
6504
  provider: "opencode",
6639
- baseUrl: "https://opencode.ai/zen",
6505
+ baseUrl: "https://opencode.ai/zen/v1",
6640
6506
  reasoning: true,
6641
6507
  input: ["text"],
6642
6508
  cost: {
6643
- input: 0,
6644
- output: 0,
6645
- cacheRead: 0,
6509
+ input: 0.3,
6510
+ output: 1.2,
6511
+ cacheRead: 0.06,
6646
6512
  cacheWrite: 0,
6647
6513
  },
6648
6514
  contextWindow: 204800,
@@ -6716,23 +6582,6 @@ export const MODELS = {
6716
6582
  contextWindow: 262144,
6717
6583
  maxTokens: 65536,
6718
6584
  },
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
6585
  },
6737
6586
  "opencode-go": {
6738
6587
  "deepseek-v4-flash": {
@@ -6846,9 +6695,9 @@ export const MODELS = {
6846
6695
  reasoning: true,
6847
6696
  input: ["text", "image"],
6848
6697
  cost: {
6849
- input: 0.4,
6850
- output: 2,
6851
- cacheRead: 0.08,
6698
+ input: 0.14,
6699
+ output: 0.28,
6700
+ cacheRead: 0.0028,
6852
6701
  cacheWrite: 0,
6853
6702
  },
6854
6703
  contextWindow: 1000000,
@@ -6863,9 +6712,9 @@ export const MODELS = {
6863
6712
  reasoning: true,
6864
6713
  input: ["text"],
6865
6714
  cost: {
6866
- input: 1,
6867
- output: 3,
6868
- cacheRead: 0.2,
6715
+ input: 1.74,
6716
+ output: 3.48,
6717
+ cacheRead: 0.0145,
6869
6718
  cacheWrite: 0,
6870
6719
  },
6871
6720
  contextWindow: 1048576,
@@ -6939,6 +6788,23 @@ export const MODELS = {
6939
6788
  contextWindow: 262144,
6940
6789
  maxTokens: 65536,
6941
6790
  },
6791
+ "qwen3.7-max": {
6792
+ id: "qwen3.7-max",
6793
+ name: "Qwen3.7 Max",
6794
+ api: "anthropic-messages",
6795
+ provider: "opencode-go",
6796
+ baseUrl: "https://opencode.ai/zen/go",
6797
+ reasoning: true,
6798
+ input: ["text"],
6799
+ cost: {
6800
+ input: 2.5,
6801
+ output: 7.5,
6802
+ cacheRead: 0.5,
6803
+ cacheWrite: 3.125,
6804
+ },
6805
+ contextWindow: 1000000,
6806
+ maxTokens: 65536,
6807
+ },
6942
6808
  },
6943
6809
  "openrouter": {
6944
6810
  "ai21/jamba-large-1.7": {
@@ -6958,23 +6824,6 @@ export const MODELS = {
6958
6824
  contextWindow: 256000,
6959
6825
  maxTokens: 4096,
6960
6826
  },
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
6827
  "amazon/nova-2-lite-v1": {
6979
6828
  id: "amazon/nova-2-lite-v1",
6980
6829
  name: "Amazon: Nova 2 Lite",
@@ -7230,6 +7079,40 @@ export const MODELS = {
7230
7079
  contextWindow: 1000000,
7231
7080
  maxTokens: 128000,
7232
7081
  },
7082
+ "anthropic/claude-opus-4.8": {
7083
+ id: "anthropic/claude-opus-4.8",
7084
+ name: "Anthropic: Claude Opus 4.8",
7085
+ api: "openai-completions",
7086
+ provider: "openrouter",
7087
+ baseUrl: "https://openrouter.ai/api/v1",
7088
+ reasoning: true,
7089
+ input: ["text", "image"],
7090
+ cost: {
7091
+ input: 5,
7092
+ output: 25,
7093
+ cacheRead: 0.5,
7094
+ cacheWrite: 6.25,
7095
+ },
7096
+ contextWindow: 1000000,
7097
+ maxTokens: 128000,
7098
+ },
7099
+ "anthropic/claude-opus-4.8-fast": {
7100
+ id: "anthropic/claude-opus-4.8-fast",
7101
+ name: "Anthropic: Claude Opus 4.8 (Fast)",
7102
+ api: "openai-completions",
7103
+ provider: "openrouter",
7104
+ baseUrl: "https://openrouter.ai/api/v1",
7105
+ reasoning: true,
7106
+ input: ["text", "image"],
7107
+ cost: {
7108
+ input: 10,
7109
+ output: 50,
7110
+ cacheRead: 1,
7111
+ cacheWrite: 12.5,
7112
+ },
7113
+ contextWindow: 1000000,
7114
+ maxTokens: 128000,
7115
+ },
7233
7116
  "anthropic/claude-sonnet-4": {
7234
7117
  id: "anthropic/claude-sonnet-4",
7235
7118
  name: "Anthropic: Claude Sonnet 4",
@@ -7281,23 +7164,6 @@ export const MODELS = {
7281
7164
  contextWindow: 1000000,
7282
7165
  maxTokens: 128000,
7283
7166
  },
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
7167
  "arcee-ai/trinity-large-thinking": {
7302
7168
  id: "arcee-ai/trinity-large-thinking",
7303
7169
  name: "Arcee AI: Trinity Large Thinking",
@@ -7315,23 +7181,6 @@ export const MODELS = {
7315
7181
  contextWindow: 262144,
7316
7182
  maxTokens: 262144,
7317
7183
  },
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
7184
  "arcee-ai/trinity-mini": {
7336
7185
  id: "arcee-ai/trinity-mini",
7337
7186
  name: "Arcee AI: Trinity Mini",
@@ -7383,23 +7232,6 @@ export const MODELS = {
7383
7232
  contextWindow: 2000000,
7384
7233
  maxTokens: 30000,
7385
7234
  },
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
7235
  "baidu/ernie-4.5-21b-a3b": {
7404
7236
  id: "baidu/ernie-4.5-21b-a3b",
7405
7237
  name: "Baidu: ERNIE 4.5 21B A3B",
@@ -7545,13 +7377,13 @@ export const MODELS = {
7545
7377
  reasoning: false,
7546
7378
  input: ["text"],
7547
7379
  cost: {
7548
- input: 0.32,
7549
- output: 0.8899999999999999,
7380
+ input: 0.2288,
7381
+ output: 0.9144,
7550
7382
  cacheRead: 0,
7551
7383
  cacheWrite: 0,
7552
7384
  },
7553
- contextWindow: 163840,
7554
- maxTokens: 16384,
7385
+ contextWindow: 131072,
7386
+ maxTokens: 16000,
7555
7387
  },
7556
7388
  "deepseek/deepseek-chat-v3-0324": {
7557
7389
  id: "deepseek/deepseek-chat-v3-0324",
@@ -7681,13 +7513,13 @@ export const MODELS = {
7681
7513
  reasoning: true,
7682
7514
  input: ["text"],
7683
7515
  cost: {
7684
- input: 0.112,
7685
- output: 0.224,
7686
- cacheRead: 0.022,
7516
+ input: 0.09999999999999999,
7517
+ output: 0.19999999999999998,
7518
+ cacheRead: 0.02,
7687
7519
  cacheWrite: 0,
7688
7520
  },
7689
7521
  contextWindow: 1048576,
7690
- maxTokens: 4096,
7522
+ maxTokens: 16384,
7691
7523
  },
7692
7524
  "deepseek/deepseek-v4-flash:free": {
7693
7525
  id: "deepseek/deepseek-v4-flash:free",
@@ -7754,7 +7586,7 @@ export const MODELS = {
7754
7586
  cacheRead: 0.024999999999999998,
7755
7587
  cacheWrite: 0.08333333333333334,
7756
7588
  },
7757
- contextWindow: 1048576,
7589
+ contextWindow: 1000000,
7758
7590
  maxTokens: 8192,
7759
7591
  },
7760
7592
  "google/gemini-2.0-flash-lite-001": {
@@ -8123,9 +7955,9 @@ export const MODELS = {
8123
7955
  reasoning: false,
8124
7956
  input: ["text"],
8125
7957
  cost: {
8126
- input: 0.3,
8127
- output: 2.5,
8128
- cacheRead: 0.06,
7958
+ input: 0.075,
7959
+ output: 0.625,
7960
+ cacheRead: 0.015,
8129
7961
  cacheWrite: 0,
8130
7962
  },
8131
7963
  contextWindow: 262144,
@@ -8349,7 +8181,7 @@ export const MODELS = {
8349
8181
  cacheRead: 0,
8350
8182
  cacheWrite: 0,
8351
8183
  },
8352
- contextWindow: 204800,
8184
+ contextWindow: 262144,
8353
8185
  maxTokens: 8192,
8354
8186
  },
8355
8187
  "minimax/minimax-m2.7": {
@@ -8811,6 +8643,23 @@ export const MODELS = {
8811
8643
  contextWindow: 262144,
8812
8644
  maxTokens: 262142,
8813
8645
  },
8646
+ "moonshotai/kimi-k2.6:free": {
8647
+ id: "moonshotai/kimi-k2.6:free",
8648
+ name: "MoonshotAI: Kimi K2.6 (free)",
8649
+ api: "openai-completions",
8650
+ provider: "openrouter",
8651
+ baseUrl: "https://openrouter.ai/api/v1",
8652
+ reasoning: true,
8653
+ input: ["text", "image"],
8654
+ cost: {
8655
+ input: 0,
8656
+ output: 0,
8657
+ cacheRead: 0,
8658
+ cacheWrite: 0,
8659
+ },
8660
+ contextWindow: 262144,
8661
+ maxTokens: 4096,
8662
+ },
8814
8663
  "nex-agi/deepseek-v3.1-nex-n1": {
8815
8664
  id: "nex-agi/deepseek-v3.1-nex-n1",
8816
8665
  name: "Nex AGI: DeepSeek V3.1 Nex N1",
@@ -9400,11 +9249,11 @@ export const MODELS = {
9400
9249
  cost: {
9401
9250
  input: 1.25,
9402
9251
  output: 10,
9403
- cacheRead: 0.125,
9252
+ cacheRead: 0.13,
9404
9253
  cacheWrite: 0,
9405
9254
  },
9406
9255
  contextWindow: 128000,
9407
- maxTokens: 16384,
9256
+ maxTokens: 32000,
9408
9257
  },
9409
9258
  "openai/gpt-5.1-codex": {
9410
9259
  id: "openai/gpt-5.1-codex",
@@ -9417,7 +9266,7 @@ export const MODELS = {
9417
9266
  cost: {
9418
9267
  input: 1.25,
9419
9268
  output: 10,
9420
- cacheRead: 0.125,
9269
+ cacheRead: 0.13,
9421
9270
  cacheWrite: 0,
9422
9271
  },
9423
9272
  contextWindow: 400000,
@@ -9451,11 +9300,11 @@ export const MODELS = {
9451
9300
  cost: {
9452
9301
  input: 0.25,
9453
9302
  output: 2,
9454
- cacheRead: 0.03,
9303
+ cacheRead: 0.024999999999999998,
9455
9304
  cacheWrite: 0,
9456
9305
  },
9457
9306
  contextWindow: 400000,
9458
- maxTokens: 128000,
9307
+ maxTokens: 100000,
9459
9308
  },
9460
9309
  "openai/gpt-5.2": {
9461
9310
  id: "openai/gpt-5.2",
@@ -9489,7 +9338,7 @@ export const MODELS = {
9489
9338
  cacheWrite: 0,
9490
9339
  },
9491
9340
  contextWindow: 128000,
9492
- maxTokens: 32000,
9341
+ maxTokens: 16384,
9493
9342
  },
9494
9343
  "openai/gpt-5.2-codex": {
9495
9344
  id: "openai/gpt-5.2-codex",
@@ -10015,8 +9864,8 @@ export const MODELS = {
10015
9864
  cacheRead: 0,
10016
9865
  cacheWrite: 0,
10017
9866
  },
10018
- contextWindow: 131072,
10019
- maxTokens: 8192,
9867
+ contextWindow: 262144,
9868
+ maxTokens: 32768,
10020
9869
  },
10021
9870
  "poolside/laguna-xs.2:free": {
10022
9871
  id: "poolside/laguna-xs.2:free",
@@ -10032,8 +9881,8 @@ export const MODELS = {
10032
9881
  cacheRead: 0,
10033
9882
  cacheWrite: 0,
10034
9883
  },
10035
- contextWindow: 131072,
10036
- maxTokens: 8192,
9884
+ contextWindow: 262144,
9885
+ maxTokens: 32768,
10037
9886
  },
10038
9887
  "prime-intellect/intellect-3": {
10039
9888
  id: "prime-intellect/intellect-3",
@@ -10115,7 +9964,7 @@ export const MODELS = {
10115
9964
  input: 0.26,
10116
9965
  output: 0.78,
10117
9966
  cacheRead: 0,
10118
- cacheWrite: 0.325,
9967
+ cacheWrite: 0,
10119
9968
  },
10120
9969
  contextWindow: 1000000,
10121
9970
  maxTokens: 32768,
@@ -10611,7 +10460,7 @@ export const MODELS = {
10611
10460
  cacheWrite: 0,
10612
10461
  },
10613
10462
  contextWindow: 262144,
10614
- maxTokens: 65536,
10463
+ maxTokens: 262144,
10615
10464
  },
10616
10465
  "qwen/qwen3.5-27b": {
10617
10466
  id: "qwen/qwen3.5-27b",
@@ -10658,7 +10507,7 @@ export const MODELS = {
10658
10507
  cost: {
10659
10508
  input: 0.39,
10660
10509
  output: 2.34,
10661
- cacheRead: 0.195,
10510
+ cacheRead: 0,
10662
10511
  cacheWrite: 0,
10663
10512
  },
10664
10513
  contextWindow: 262144,
@@ -10693,7 +10542,7 @@ export const MODELS = {
10693
10542
  input: 0.065,
10694
10543
  output: 0.26,
10695
10544
  cacheRead: 0,
10696
- cacheWrite: 0.08125,
10545
+ cacheWrite: 0,
10697
10546
  },
10698
10547
  contextWindow: 1000000,
10699
10548
  maxTokens: 65536,
@@ -10710,7 +10559,7 @@ export const MODELS = {
10710
10559
  input: 0.26,
10711
10560
  output: 1.56,
10712
10561
  cacheRead: 0,
10713
- cacheWrite: 0.325,
10562
+ cacheWrite: 0,
10714
10563
  },
10715
10564
  contextWindow: 1000000,
10716
10565
  maxTokens: 65536,
@@ -10727,7 +10576,7 @@ export const MODELS = {
10727
10576
  input: 0.3,
10728
10577
  output: 1.7999999999999998,
10729
10578
  cacheRead: 0,
10730
- cacheWrite: 0,
10579
+ cacheWrite: 0.375,
10731
10580
  },
10732
10581
  contextWindow: 1000000,
10733
10582
  maxTokens: 65536,
@@ -10741,13 +10590,13 @@ export const MODELS = {
10741
10590
  reasoning: true,
10742
10591
  input: ["text", "image"],
10743
10592
  cost: {
10744
- input: 0.32,
10593
+ input: 0.29,
10745
10594
  output: 3.1999999999999997,
10746
10595
  cacheRead: 0,
10747
10596
  cacheWrite: 0,
10748
10597
  },
10749
10598
  contextWindow: 262144,
10750
- maxTokens: 81920,
10599
+ maxTokens: 262140,
10751
10600
  },
10752
10601
  "qwen/qwen3.6-35b-a3b": {
10753
10602
  id: "qwen/qwen3.6-35b-a3b",
@@ -10758,13 +10607,13 @@ export const MODELS = {
10758
10607
  reasoning: true,
10759
10608
  input: ["text", "image"],
10760
10609
  cost: {
10761
- input: 0.15,
10610
+ input: 0.14,
10762
10611
  output: 1,
10763
- cacheRead: 0.049999999999999996,
10612
+ cacheRead: 0,
10764
10613
  cacheWrite: 0,
10765
10614
  },
10766
10615
  contextWindow: 262144,
10767
- maxTokens: 262144,
10616
+ maxTokens: 262140,
10768
10617
  },
10769
10618
  "qwen/qwen3.6-flash": {
10770
10619
  id: "qwen/qwen3.6-flash",
@@ -10817,6 +10666,23 @@ export const MODELS = {
10817
10666
  contextWindow: 1000000,
10818
10667
  maxTokens: 65536,
10819
10668
  },
10669
+ "qwen/qwen3.7-max": {
10670
+ id: "qwen/qwen3.7-max",
10671
+ name: "Qwen: Qwen3.7 Max",
10672
+ api: "openai-completions",
10673
+ provider: "openrouter",
10674
+ baseUrl: "https://openrouter.ai/api/v1",
10675
+ reasoning: true,
10676
+ input: ["text"],
10677
+ cost: {
10678
+ input: 1.25,
10679
+ output: 3.75,
10680
+ cacheRead: 0.25,
10681
+ cacheWrite: 1.5625,
10682
+ },
10683
+ contextWindow: 1000000,
10684
+ maxTokens: 65536,
10685
+ },
10820
10686
  "rekaai/reka-edge": {
10821
10687
  id: "rekaai/reka-edge",
10822
10688
  name: "Reka Edge",
@@ -10894,13 +10760,13 @@ export const MODELS = {
10894
10760
  reasoning: true,
10895
10761
  input: ["text"],
10896
10762
  cost: {
10897
- input: 0.09999999999999999,
10763
+ input: 0.09,
10898
10764
  output: 0.3,
10899
- cacheRead: 0,
10765
+ cacheRead: 0.02,
10900
10766
  cacheWrite: 0,
10901
10767
  },
10902
10768
  contextWindow: 262144,
10903
- maxTokens: 65536,
10769
+ maxTokens: 16384,
10904
10770
  },
10905
10771
  "tencent/hy3-preview": {
10906
10772
  id: "tencent/hy3-preview",
@@ -10911,13 +10777,13 @@ export const MODELS = {
10911
10777
  reasoning: true,
10912
10778
  input: ["text"],
10913
10779
  cost: {
10914
- input: 0.06599999999999999,
10915
- output: 0.26,
10916
- cacheRead: 0.029,
10780
+ input: 0.063,
10781
+ output: 0.21,
10782
+ cacheRead: 0.020999999999999998,
10917
10783
  cacheWrite: 0,
10918
10784
  },
10919
10785
  contextWindow: 262144,
10920
- maxTokens: 262144,
10786
+ maxTokens: 4096,
10921
10787
  },
10922
10788
  "thedrummer/rocinante-12b": {
10923
10789
  id: "thedrummer/rocinante-12b",
@@ -11004,6 +10870,23 @@ export const MODELS = {
11004
10870
  contextWindow: 1000000,
11005
10871
  maxTokens: 4096,
11006
10872
  },
10873
+ "x-ai/grok-build-0.1": {
10874
+ id: "x-ai/grok-build-0.1",
10875
+ name: "xAI: Grok Build 0.1",
10876
+ api: "openai-completions",
10877
+ provider: "openrouter",
10878
+ baseUrl: "https://openrouter.ai/api/v1",
10879
+ reasoning: true,
10880
+ input: ["text", "image"],
10881
+ cost: {
10882
+ input: 1,
10883
+ output: 2,
10884
+ cacheRead: 0.19999999999999998,
10885
+ cacheWrite: 0,
10886
+ },
10887
+ contextWindow: 256000,
10888
+ maxTokens: 4096,
10889
+ },
11007
10890
  "xiaomi/mimo-v2-flash": {
11008
10891
  id: "xiaomi/mimo-v2-flash",
11009
10892
  name: "Xiaomi: MiMo-V2-Flash",
@@ -11064,9 +10947,9 @@ export const MODELS = {
11064
10947
  reasoning: true,
11065
10948
  input: ["text", "image"],
11066
10949
  cost: {
11067
- input: 0.39999999999999997,
11068
- output: 2,
11069
- cacheRead: 0.08,
10950
+ input: 0.14,
10951
+ output: 0.28,
10952
+ cacheRead: 0.0028,
11070
10953
  cacheWrite: 0,
11071
10954
  },
11072
10955
  contextWindow: 1048576,
@@ -11081,13 +10964,13 @@ export const MODELS = {
11081
10964
  reasoning: true,
11082
10965
  input: ["text"],
11083
10966
  cost: {
11084
- input: 1,
11085
- output: 3,
11086
- cacheRead: 0.19999999999999998,
10967
+ input: 0.435,
10968
+ output: 0.87,
10969
+ cacheRead: 0.0036,
11087
10970
  cacheWrite: 0,
11088
10971
  },
11089
10972
  contextWindow: 1048576,
11090
- maxTokens: 16384,
10973
+ maxTokens: 131072,
11091
10974
  },
11092
10975
  "z-ai/glm-4-32b": {
11093
10976
  id: "z-ai/glm-4-32b",
@@ -11132,13 +11015,13 @@ export const MODELS = {
11132
11015
  reasoning: true,
11133
11016
  input: ["text"],
11134
11017
  cost: {
11135
- input: 0.13,
11018
+ input: 0.125,
11136
11019
  output: 0.85,
11137
- cacheRead: 0.024999999999999998,
11020
+ cacheRead: 0.06,
11138
11021
  cacheWrite: 0,
11139
11022
  },
11140
11023
  contextWindow: 131072,
11141
- maxTokens: 98304,
11024
+ maxTokens: 131070,
11142
11025
  },
11143
11026
  "z-ai/glm-4.5-air:free": {
11144
11027
  id: "z-ai/glm-4.5-air:free",
@@ -11285,13 +11168,13 @@ export const MODELS = {
11285
11168
  reasoning: true,
11286
11169
  input: ["text"],
11287
11170
  cost: {
11288
- input: 0,
11289
- output: 0,
11290
- cacheRead: 0,
11171
+ input: 0.98,
11172
+ output: 3.08,
11173
+ cacheRead: 0.182,
11291
11174
  cacheWrite: 0,
11292
11175
  },
11293
- contextWindow: 202800,
11294
- maxTokens: 202800,
11176
+ contextWindow: 202752,
11177
+ maxTokens: 4096,
11295
11178
  },
11296
11179
  "z-ai/glm-5v-turbo": {
11297
11180
  id: "z-ai/glm-5v-turbo",
@@ -11754,6 +11637,23 @@ export const MODELS = {
11754
11637
  contextWindow: 1000000,
11755
11638
  maxTokens: 64000,
11756
11639
  },
11640
+ "alibaba/qwen3.7-max": {
11641
+ id: "alibaba/qwen3.7-max",
11642
+ name: "Qwen 3.7 Max",
11643
+ api: "anthropic-messages",
11644
+ provider: "vercel-ai-gateway",
11645
+ baseUrl: "https://ai-gateway.vercel.sh",
11646
+ reasoning: true,
11647
+ input: ["text", "image"],
11648
+ cost: {
11649
+ input: 1.25,
11650
+ output: 3.75,
11651
+ cacheRead: 0.25,
11652
+ cacheWrite: 1.5625,
11653
+ },
11654
+ contextWindow: 991000,
11655
+ maxTokens: 64000,
11656
+ },
11757
11657
  "anthropic/claude-3-haiku": {
11758
11658
  id: "anthropic/claude-3-haiku",
11759
11659
  name: "Claude 3 Haiku",
@@ -11890,6 +11790,23 @@ export const MODELS = {
11890
11790
  contextWindow: 1000000,
11891
11791
  maxTokens: 128000,
11892
11792
  },
11793
+ "anthropic/claude-opus-4.8": {
11794
+ id: "anthropic/claude-opus-4.8",
11795
+ name: "Claude Opus 4.8",
11796
+ api: "anthropic-messages",
11797
+ provider: "vercel-ai-gateway",
11798
+ baseUrl: "https://ai-gateway.vercel.sh",
11799
+ reasoning: true,
11800
+ input: ["text", "image"],
11801
+ cost: {
11802
+ input: 5,
11803
+ output: 25,
11804
+ cacheRead: 0.5,
11805
+ cacheWrite: 6.25,
11806
+ },
11807
+ contextWindow: 1000000,
11808
+ maxTokens: 128000,
11809
+ },
11893
11810
  "anthropic/claude-sonnet-4": {
11894
11811
  id: "anthropic/claude-sonnet-4",
11895
11812
  name: "Claude Sonnet 4",
@@ -12640,7 +12557,7 @@ export const MODELS = {
12640
12557
  },
12641
12558
  "minimax/minimax-m2.7": {
12642
12559
  id: "minimax/minimax-m2.7",
12643
- name: "Minimax M2.7",
12560
+ name: "MiniMax M2.7",
12644
12561
  api: "anthropic-messages",
12645
12562
  provider: "vercel-ai-gateway",
12646
12563
  baseUrl: "https://ai-gateway.vercel.sh",
@@ -12791,6 +12708,23 @@ export const MODELS = {
12791
12708
  contextWindow: 128000,
12792
12709
  maxTokens: 64000,
12793
12710
  },
12711
+ "mistral/mistral-medium-3.5": {
12712
+ id: "mistral/mistral-medium-3.5",
12713
+ name: "Mistral Medium Latest",
12714
+ api: "anthropic-messages",
12715
+ provider: "vercel-ai-gateway",
12716
+ baseUrl: "https://ai-gateway.vercel.sh",
12717
+ reasoning: true,
12718
+ input: ["text"],
12719
+ cost: {
12720
+ input: 1.5,
12721
+ output: 7.5,
12722
+ cacheRead: 0,
12723
+ cacheWrite: 0,
12724
+ },
12725
+ contextWindow: 256000,
12726
+ maxTokens: 256000,
12727
+ },
12794
12728
  "mistral/mistral-small": {
12795
12729
  id: "mistral/mistral-small",
12796
12730
  name: "Mistral Small",
@@ -13794,6 +13728,23 @@ export const MODELS = {
13794
13728
  contextWindow: 1000000,
13795
13729
  maxTokens: 1000000,
13796
13730
  },
13731
+ "xai/grok-build-0.1": {
13732
+ id: "xai/grok-build-0.1",
13733
+ name: "Grok Build 0.1",
13734
+ api: "anthropic-messages",
13735
+ provider: "vercel-ai-gateway",
13736
+ baseUrl: "https://ai-gateway.vercel.sh",
13737
+ reasoning: true,
13738
+ input: ["text", "image"],
13739
+ cost: {
13740
+ input: 1,
13741
+ output: 2,
13742
+ cacheRead: 0.19999999999999998,
13743
+ cacheWrite: 0,
13744
+ },
13745
+ contextWindow: 256000,
13746
+ maxTokens: 256000,
13747
+ },
13797
13748
  "xiaomi/mimo-v2-flash": {
13798
13749
  id: "xiaomi/mimo-v2-flash",
13799
13750
  name: "MiMo V2 Flash",
@@ -13837,9 +13788,9 @@ export const MODELS = {
13837
13788
  reasoning: true,
13838
13789
  input: ["text", "image"],
13839
13790
  cost: {
13840
- input: 0.39999999999999997,
13841
- output: 2,
13842
- cacheRead: 0.08,
13791
+ input: 0.14,
13792
+ output: 0.28,
13793
+ cacheRead: 0.0028,
13843
13794
  cacheWrite: 0,
13844
13795
  },
13845
13796
  contextWindow: 1050000,
@@ -13854,9 +13805,9 @@ export const MODELS = {
13854
13805
  reasoning: true,
13855
13806
  input: ["text", "image"],
13856
13807
  cost: {
13857
- input: 1,
13858
- output: 3,
13859
- cacheRead: 0.19999999999999998,
13808
+ input: 0.435,
13809
+ output: 0.87,
13810
+ cacheRead: 0.0036,
13860
13811
  cacheWrite: 0,
13861
13812
  },
13862
13813
  contextWindow: 1050000,
@@ -14085,108 +14036,6 @@ export const MODELS = {
14085
14036
  },
14086
14037
  },
14087
14038
  "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
14039
  "grok-4.20-0309-non-reasoning": {
14191
14040
  id: "grok-4.20-0309-non-reasoning",
14192
14041
  name: "Grok 4.20 (Non-Reasoning)",
@@ -14196,8 +14045,8 @@ export const MODELS = {
14196
14045
  reasoning: false,
14197
14046
  input: ["text", "image"],
14198
14047
  cost: {
14199
- input: 2,
14200
- output: 6,
14048
+ input: 1.25,
14049
+ output: 2.5,
14201
14050
  cacheRead: 0.2,
14202
14051
  cacheWrite: 0,
14203
14052
  },
@@ -14213,8 +14062,8 @@ export const MODELS = {
14213
14062
  reasoning: true,
14214
14063
  input: ["text", "image"],
14215
14064
  cost: {
14216
- input: 2,
14217
- output: 6,
14065
+ input: 1.25,
14066
+ output: 2.5,
14218
14067
  cacheRead: 0.2,
14219
14068
  cacheWrite: 0,
14220
14069
  },
@@ -14238,22 +14087,22 @@ export const MODELS = {
14238
14087
  contextWindow: 1000000,
14239
14088
  maxTokens: 30000,
14240
14089
  },
14241
- "grok-beta": {
14242
- id: "grok-beta",
14243
- name: "Grok Beta",
14090
+ "grok-build-0.1": {
14091
+ id: "grok-build-0.1",
14092
+ name: "Grok Build 0.1",
14244
14093
  api: "openai-completions",
14245
14094
  provider: "xai",
14246
14095
  baseUrl: "https://api.x.ai/v1",
14247
- reasoning: false,
14248
- input: ["text"],
14096
+ reasoning: true,
14097
+ input: ["text", "image"],
14249
14098
  cost: {
14250
- input: 5,
14251
- output: 15,
14252
- cacheRead: 5,
14099
+ input: 1,
14100
+ output: 2,
14101
+ cacheRead: 0.2,
14253
14102
  cacheWrite: 0,
14254
14103
  },
14255
- contextWindow: 131072,
14256
- maxTokens: 4096,
14104
+ contextWindow: 256000,
14105
+ maxTokens: 256000,
14257
14106
  },
14258
14107
  "grok-code-fast-1": {
14259
14108
  id: "grok-code-fast-1",
@@ -14272,23 +14121,6 @@ export const MODELS = {
14272
14121
  contextWindow: 32768,
14273
14122
  maxTokens: 8192,
14274
14123
  },
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
14124
  },
14293
14125
  };
14294
14126
  //# sourceMappingURL=models.generated.js.map