@dreb/ai 2.64.0 → 2.64.2

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.
@@ -87,6 +87,23 @@ export const MODELS = {
87
87
  contextWindow: 1000000,
88
88
  maxTokens: 128000,
89
89
  },
90
+ "anthropic.claude-fable-5-1": {
91
+ id: "anthropic.claude-fable-5-1",
92
+ name: "Claude Fable 5.1",
93
+ api: "bedrock-converse-stream",
94
+ provider: "amazon-bedrock",
95
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
96
+ reasoning: true,
97
+ input: ["text", "image"],
98
+ cost: {
99
+ input: 10,
100
+ output: 50,
101
+ cacheRead: 0.25,
102
+ cacheWrite: 12.5,
103
+ },
104
+ contextWindow: 1000000,
105
+ maxTokens: 128000,
106
+ },
90
107
  "anthropic.claude-haiku-4-5-20251001-v1:0": {
91
108
  id: "anthropic.claude-haiku-4-5-20251001-v1:0",
92
109
  name: "Claude Haiku 4.5",
@@ -614,6 +631,23 @@ export const MODELS = {
614
631
  contextWindow: 1000000,
615
632
  maxTokens: 128000,
616
633
  },
634
+ "global.anthropic.claude-fable-5-1": {
635
+ id: "global.anthropic.claude-fable-5-1",
636
+ name: "Claude Fable 5.1 (Global)",
637
+ api: "bedrock-converse-stream",
638
+ provider: "amazon-bedrock",
639
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
640
+ reasoning: true,
641
+ input: ["text", "image"],
642
+ cost: {
643
+ input: 10,
644
+ output: 50,
645
+ cacheRead: 0.25,
646
+ cacheWrite: 12.5,
647
+ },
648
+ contextWindow: 1000000,
649
+ maxTokens: 128000,
650
+ },
617
651
  "global.anthropic.claude-haiku-4-5-20251001-v1:0": {
618
652
  id: "global.anthropic.claude-haiku-4-5-20251001-v1:0",
619
653
  name: "Claude Haiku 4.5 (Global)",
@@ -1685,6 +1719,23 @@ export const MODELS = {
1685
1719
  contextWindow: 1000000,
1686
1720
  maxTokens: 128000,
1687
1721
  },
1722
+ "us.anthropic.claude-fable-5-1": {
1723
+ id: "us.anthropic.claude-fable-5-1",
1724
+ name: "Claude Fable 5.1 (US)",
1725
+ api: "bedrock-converse-stream",
1726
+ provider: "amazon-bedrock",
1727
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1728
+ reasoning: true,
1729
+ input: ["text", "image"],
1730
+ cost: {
1731
+ input: 11,
1732
+ output: 55,
1733
+ cacheRead: 0.275,
1734
+ cacheWrite: 13.75,
1735
+ },
1736
+ contextWindow: 1000000,
1737
+ maxTokens: 128000,
1738
+ },
1688
1739
  "us.anthropic.claude-haiku-4-5-20251001-v1:0": {
1689
1740
  id: "us.anthropic.claude-haiku-4-5-20251001-v1:0",
1690
1741
  name: "Claude Haiku 4.5 (US)",
@@ -2044,6 +2095,23 @@ export const MODELS = {
2044
2095
  contextWindow: 1000000,
2045
2096
  maxTokens: 128000,
2046
2097
  },
2098
+ "claude-fable-5-1": {
2099
+ id: "claude-fable-5-1",
2100
+ name: "Claude Fable 5.1",
2101
+ api: "anthropic-messages",
2102
+ provider: "anthropic",
2103
+ baseUrl: "https://api.anthropic.com",
2104
+ reasoning: true,
2105
+ input: ["text", "image"],
2106
+ cost: {
2107
+ input: 10,
2108
+ output: 50,
2109
+ cacheRead: 0.25,
2110
+ cacheWrite: 12.5,
2111
+ },
2112
+ contextWindow: 1000000,
2113
+ maxTokens: 128000,
2114
+ },
2047
2115
  "claude-haiku-4-5": {
2048
2116
  id: "claude-haiku-4-5",
2049
2117
  name: "Claude Haiku 4.5 (latest)",
@@ -3004,27 +3072,28 @@ export const MODELS = {
3004
3072
  contextWindow: 1000000,
3005
3073
  maxTokens: 128000,
3006
3074
  },
3007
- "claude-haiku-4.5": {
3008
- id: "claude-haiku-4.5",
3009
- name: "Claude Haiku 4.5 (latest)",
3010
- api: "anthropic-messages",
3075
+ "claude-fable-5.1": {
3076
+ id: "claude-fable-5.1",
3077
+ name: "Claude Fable 5.1",
3078
+ api: "openai-completions",
3011
3079
  provider: "github-copilot",
3012
3080
  baseUrl: "https://api.individual.githubcopilot.com",
3013
3081
  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" },
3082
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
3014
3083
  reasoning: true,
3015
3084
  input: ["text", "image"],
3016
3085
  cost: {
3017
- input: 1,
3018
- output: 5,
3019
- cacheRead: 0.1,
3020
- cacheWrite: 1.25,
3086
+ input: 10,
3087
+ output: 50,
3088
+ cacheRead: 0.25,
3089
+ cacheWrite: 12.5,
3021
3090
  },
3022
- contextWindow: 200000,
3023
- maxTokens: 64000,
3091
+ contextWindow: 1000000,
3092
+ maxTokens: 128000,
3024
3093
  },
3025
- "claude-opus-4.5": {
3026
- id: "claude-opus-4.5",
3027
- name: "Claude Opus 4.5 (latest)",
3094
+ "claude-haiku-4.5": {
3095
+ id: "claude-haiku-4.5",
3096
+ name: "Claude Haiku 4.5 (latest)",
3028
3097
  api: "anthropic-messages",
3029
3098
  provider: "github-copilot",
3030
3099
  baseUrl: "https://api.individual.githubcopilot.com",
@@ -3032,31 +3101,13 @@ export const MODELS = {
3032
3101
  reasoning: true,
3033
3102
  input: ["text", "image"],
3034
3103
  cost: {
3035
- input: 5,
3036
- output: 25,
3037
- cacheRead: 0.5,
3038
- cacheWrite: 6.25,
3104
+ input: 1,
3105
+ output: 5,
3106
+ cacheRead: 0.1,
3107
+ cacheWrite: 1.25,
3039
3108
  },
3040
3109
  contextWindow: 200000,
3041
- maxTokens: 32000,
3042
- },
3043
- "claude-opus-4.6": {
3044
- id: "claude-opus-4.6",
3045
- name: "Claude Opus 4.6",
3046
- api: "anthropic-messages",
3047
- provider: "github-copilot",
3048
- baseUrl: "https://api.individual.githubcopilot.com",
3049
- 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" },
3050
- reasoning: true,
3051
- input: ["text", "image"],
3052
- cost: {
3053
- input: 5,
3054
- output: 25,
3055
- cacheRead: 0.5,
3056
- cacheWrite: 6.25,
3057
- },
3058
- contextWindow: 1000000,
3059
- maxTokens: 32000,
3110
+ maxTokens: 64000,
3060
3111
  },
3061
3112
  "claude-opus-4.7": {
3062
3113
  id: "claude-opus-4.7",
@@ -3113,42 +3164,6 @@ export const MODELS = {
3113
3164
  contextWindow: 1000000,
3114
3165
  maxTokens: 64000,
3115
3166
  },
3116
- "claude-sonnet-4": {
3117
- id: "claude-sonnet-4",
3118
- name: "Claude Sonnet 4 (latest)",
3119
- api: "anthropic-messages",
3120
- provider: "github-copilot",
3121
- baseUrl: "https://api.individual.githubcopilot.com",
3122
- 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" },
3123
- reasoning: true,
3124
- input: ["text", "image"],
3125
- cost: {
3126
- input: 3,
3127
- output: 15,
3128
- cacheRead: 0.3,
3129
- cacheWrite: 3.75,
3130
- },
3131
- contextWindow: 216000,
3132
- maxTokens: 16000,
3133
- },
3134
- "claude-sonnet-4.5": {
3135
- id: "claude-sonnet-4.5",
3136
- name: "Claude Sonnet 4.5 (latest)",
3137
- api: "anthropic-messages",
3138
- provider: "github-copilot",
3139
- baseUrl: "https://api.individual.githubcopilot.com",
3140
- 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" },
3141
- reasoning: true,
3142
- input: ["text", "image"],
3143
- cost: {
3144
- input: 3,
3145
- output: 15,
3146
- cacheRead: 0.3,
3147
- cacheWrite: 3.75,
3148
- },
3149
- contextWindow: 200000,
3150
- maxTokens: 32000,
3151
- },
3152
3167
  "claude-sonnet-4.6": {
3153
3168
  id: "claude-sonnet-4.6",
3154
3169
  name: "Claude Sonnet 4.6",
@@ -3186,25 +3201,6 @@ export const MODELS = {
3186
3201
  contextWindow: 1000000,
3187
3202
  maxTokens: 128000,
3188
3203
  },
3189
- "gemini-3.1-pro-preview": {
3190
- id: "gemini-3.1-pro-preview",
3191
- name: "Gemini 3.1 Pro Preview",
3192
- api: "openai-completions",
3193
- provider: "github-copilot",
3194
- baseUrl: "https://api.individual.githubcopilot.com",
3195
- 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" },
3196
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
3197
- reasoning: true,
3198
- input: ["text", "image"],
3199
- cost: {
3200
- input: 2,
3201
- output: 12,
3202
- cacheRead: 0.2,
3203
- cacheWrite: 0,
3204
- },
3205
- contextWindow: 1000000,
3206
- maxTokens: 64000,
3207
- },
3208
3204
  "gemini-3.5-flash": {
3209
3205
  id: "gemini-3.5-flash",
3210
3206
  name: "Gemini 3.5 Flash",
@@ -3262,24 +3258,24 @@ export const MODELS = {
3262
3258
  contextWindow: 1000000,
3263
3259
  maxTokens: 64000,
3264
3260
  },
3265
- "gpt-4.1": {
3266
- id: "gpt-4.1",
3267
- name: "GPT-4.1",
3261
+ "gemini-3.8-flash": {
3262
+ id: "gemini-3.8-flash",
3263
+ name: "Gemini 3.8 Flash",
3268
3264
  api: "openai-completions",
3269
3265
  provider: "github-copilot",
3270
3266
  baseUrl: "https://api.individual.githubcopilot.com",
3271
3267
  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" },
3272
3268
  compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
3273
- reasoning: false,
3269
+ reasoning: true,
3274
3270
  input: ["text", "image"],
3275
3271
  cost: {
3276
- input: 2,
3277
- output: 8,
3278
- cacheRead: 0.5,
3272
+ input: 0.75,
3273
+ output: 3.75,
3274
+ cacheRead: 0.075,
3279
3275
  cacheWrite: 0,
3280
3276
  },
3281
- contextWindow: 128000,
3282
- maxTokens: 16384,
3277
+ contextWindow: 1000000,
3278
+ maxTokens: 64000,
3283
3279
  },
3284
3280
  "gpt-5-mini": {
3285
3281
  id: "gpt-5-mini",
@@ -3299,42 +3295,6 @@ export const MODELS = {
3299
3295
  contextWindow: 264000,
3300
3296
  maxTokens: 64000,
3301
3297
  },
3302
- "gpt-5.2": {
3303
- id: "gpt-5.2",
3304
- name: "GPT-5.2",
3305
- api: "openai-responses",
3306
- provider: "github-copilot",
3307
- baseUrl: "https://api.individual.githubcopilot.com",
3308
- 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" },
3309
- reasoning: true,
3310
- input: ["text", "image"],
3311
- cost: {
3312
- input: 1.75,
3313
- output: 14,
3314
- cacheRead: 0.175,
3315
- cacheWrite: 0,
3316
- },
3317
- contextWindow: 400000,
3318
- maxTokens: 128000,
3319
- },
3320
- "gpt-5.2-codex": {
3321
- id: "gpt-5.2-codex",
3322
- name: "GPT-5.2 Codex",
3323
- api: "openai-responses",
3324
- provider: "github-copilot",
3325
- baseUrl: "https://api.individual.githubcopilot.com",
3326
- 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" },
3327
- reasoning: true,
3328
- input: ["text", "image"],
3329
- cost: {
3330
- input: 1.75,
3331
- output: 14,
3332
- cacheRead: 0.175,
3333
- cacheWrite: 0,
3334
- },
3335
- contextWindow: 400000,
3336
- maxTokens: 128000,
3337
- },
3338
3298
  "gpt-5.3-codex": {
3339
3299
  id: "gpt-5.3-codex",
3340
3300
  name: "GPT-5.3 Codex",
@@ -3884,9 +3844,9 @@ export const MODELS = {
3884
3844
  contextWindow: 1048576,
3885
3845
  maxTokens: 65536,
3886
3846
  },
3887
- "gemini-flash-latest": {
3888
- id: "gemini-flash-latest",
3889
- name: "Gemini Flash Latest",
3847
+ "gemini-3.8-flash": {
3848
+ id: "gemini-3.8-flash",
3849
+ name: "Gemini 3.8 Flash",
3890
3850
  api: "google-generative-ai",
3891
3851
  provider: "google",
3892
3852
  baseUrl: "https://generativelanguage.googleapis.com/v1beta",
@@ -3901,38 +3861,38 @@ export const MODELS = {
3901
3861
  contextWindow: 1048576,
3902
3862
  maxTokens: 65536,
3903
3863
  },
3904
- "gemini-flash-lite-latest": {
3905
- id: "gemini-flash-lite-latest",
3906
- name: "Gemini Flash-Lite Latest",
3864
+ "gemini-flash-latest": {
3865
+ id: "gemini-flash-latest",
3866
+ name: "Gemini Flash Latest",
3907
3867
  api: "google-generative-ai",
3908
3868
  provider: "google",
3909
3869
  baseUrl: "https://generativelanguage.googleapis.com/v1beta",
3910
3870
  reasoning: true,
3911
3871
  input: ["text", "image"],
3912
3872
  cost: {
3913
- input: 0.3,
3914
- output: 2.5,
3915
- cacheRead: 0.03,
3873
+ input: 0.75,
3874
+ output: 3.75,
3875
+ cacheRead: 0.075,
3916
3876
  cacheWrite: 0,
3917
3877
  },
3918
3878
  contextWindow: 1048576,
3919
3879
  maxTokens: 65536,
3920
3880
  },
3921
- "gemini-robotics-er-1.6-preview": {
3922
- id: "gemini-robotics-er-1.6-preview",
3923
- name: "Gemini Robotics-ER 1.6 Preview",
3881
+ "gemini-flash-lite-latest": {
3882
+ id: "gemini-flash-lite-latest",
3883
+ name: "Gemini Flash-Lite Latest",
3924
3884
  api: "google-generative-ai",
3925
3885
  provider: "google",
3926
3886
  baseUrl: "https://generativelanguage.googleapis.com/v1beta",
3927
3887
  reasoning: true,
3928
3888
  input: ["text", "image"],
3929
3889
  cost: {
3930
- input: 1,
3931
- output: 5,
3932
- cacheRead: 0,
3890
+ input: 0.3,
3891
+ output: 2.5,
3892
+ cacheRead: 0.03,
3933
3893
  cacheWrite: 0,
3934
3894
  },
3935
- contextWindow: 131072,
3895
+ contextWindow: 1048576,
3936
3896
  maxTokens: 65536,
3937
3897
  },
3938
3898
  "gemma-4-26b-a4b-it": {
@@ -4538,6 +4498,23 @@ export const MODELS = {
4538
4498
  contextWindow: 131072,
4539
4499
  maxTokens: 16384,
4540
4500
  },
4501
+ "qwen/qwen3.8-27b": {
4502
+ id: "qwen/qwen3.8-27b",
4503
+ name: "Qwen3.8 27B",
4504
+ api: "openai-completions",
4505
+ provider: "groq",
4506
+ baseUrl: "https://api.groq.com/openai/v1",
4507
+ reasoning: true,
4508
+ input: ["text", "image"],
4509
+ cost: {
4510
+ input: 0.8,
4511
+ output: 4,
4512
+ cacheRead: 0,
4513
+ cacheWrite: 0,
4514
+ },
4515
+ contextWindow: 131042,
4516
+ maxTokens: 16384,
4517
+ },
4541
4518
  },
4542
4519
  "huggingface": {
4543
4520
  "MiniMaxAI/MiniMax-M2": {
@@ -5224,18 +5201,36 @@ export const MODELS = {
5224
5201
  contextWindow: 1048576,
5225
5202
  maxTokens: 384000,
5226
5203
  },
5227
- "deepseek-ai/DeepSeek-V4-Pro": {
5228
- id: "deepseek-ai/DeepSeek-V4-Pro",
5229
- name: "DeepSeek V4 Pro",
5204
+ "deepseek-ai/DeepSeek-V4-Flash-Vision-Exp": {
5205
+ id: "deepseek-ai/DeepSeek-V4-Flash-Vision-Exp",
5206
+ name: "DeepSeek V4 Flash Vision Exp",
5230
5207
  api: "openai-completions",
5231
5208
  provider: "huggingface",
5232
5209
  baseUrl: "https://router.huggingface.co/v1",
5233
5210
  compat: { "supportsDeveloperRole": false },
5234
5211
  reasoning: true,
5235
- input: ["text"],
5212
+ input: ["text", "image"],
5236
5213
  cost: {
5237
- input: 0.435,
5238
- output: 0.87,
5214
+ input: 0.44,
5215
+ output: 1.32,
5216
+ cacheRead: 0,
5217
+ cacheWrite: 0,
5218
+ },
5219
+ contextWindow: 1048576,
5220
+ maxTokens: 384000,
5221
+ },
5222
+ "deepseek-ai/DeepSeek-V4-Pro": {
5223
+ id: "deepseek-ai/DeepSeek-V4-Pro",
5224
+ name: "DeepSeek V4 Pro",
5225
+ api: "openai-completions",
5226
+ provider: "huggingface",
5227
+ baseUrl: "https://router.huggingface.co/v1",
5228
+ compat: { "supportsDeveloperRole": false },
5229
+ reasoning: true,
5230
+ input: ["text"],
5231
+ cost: {
5232
+ input: 0.435,
5233
+ output: 0.87,
5239
5234
  cacheRead: 0.003625,
5240
5235
  cacheWrite: 0,
5241
5236
  },
@@ -5546,7 +5541,7 @@ export const MODELS = {
5546
5541
  cacheWrite: 0,
5547
5542
  },
5548
5543
  contextWindow: 262144,
5549
- maxTokens: 64000,
5544
+ maxTokens: 128000,
5550
5545
  },
5551
5546
  "thinkingmachines/Inkling": {
5552
5547
  id: "thinkingmachines/Inkling",
@@ -5764,6 +5759,24 @@ export const MODELS = {
5764
5759
  contextWindow: 262144,
5765
5760
  maxTokens: 131072,
5766
5761
  },
5762
+ "zai-org/GLM-5.3": {
5763
+ id: "zai-org/GLM-5.3",
5764
+ name: "GLM-5.3",
5765
+ api: "openai-completions",
5766
+ provider: "huggingface",
5767
+ baseUrl: "https://router.huggingface.co/v1",
5768
+ compat: { "supportsDeveloperRole": false },
5769
+ reasoning: true,
5770
+ input: ["text"],
5771
+ cost: {
5772
+ input: 1.4,
5773
+ output: 4.4,
5774
+ cacheRead: 0,
5775
+ cacheWrite: 0,
5776
+ },
5777
+ contextWindow: 1048576,
5778
+ maxTokens: 131072,
5779
+ },
5767
5780
  "zai-org/GLM-5.3-Flash": {
5768
5781
  id: "zai-org/GLM-5.3-Flash",
5769
5782
  name: "GLM-5.3-Flash",
@@ -7467,6 +7480,23 @@ export const MODELS = {
7467
7480
  contextWindow: 1000000,
7468
7481
  maxTokens: 128000,
7469
7482
  },
7483
+ "claude-fable-5-1": {
7484
+ id: "claude-fable-5-1",
7485
+ name: "Claude Fable 5.1",
7486
+ api: "anthropic-messages",
7487
+ provider: "opencode",
7488
+ baseUrl: "https://opencode.ai/zen",
7489
+ reasoning: true,
7490
+ input: ["text", "image"],
7491
+ cost: {
7492
+ input: 10,
7493
+ output: 50,
7494
+ cacheRead: 0.25,
7495
+ cacheWrite: 12.5,
7496
+ },
7497
+ contextWindow: 1000000,
7498
+ maxTokens: 128000,
7499
+ },
7470
7500
  "claude-haiku-4-5": {
7471
7501
  id: "claude-haiku-4-5",
7472
7502
  name: "Claude Haiku 4.5",
@@ -7773,6 +7803,23 @@ export const MODELS = {
7773
7803
  contextWindow: 1048576,
7774
7804
  maxTokens: 65536,
7775
7805
  },
7806
+ "gemini-3.8-flash": {
7807
+ id: "gemini-3.8-flash",
7808
+ name: "Gemini 3.8 Flash",
7809
+ api: "google-generative-ai",
7810
+ provider: "opencode",
7811
+ baseUrl: "https://opencode.ai/zen/v1",
7812
+ reasoning: true,
7813
+ input: ["text", "image"],
7814
+ cost: {
7815
+ input: 1.5,
7816
+ output: 7.5,
7817
+ cacheRead: 0.15,
7818
+ cacheWrite: 0,
7819
+ },
7820
+ contextWindow: 1048576,
7821
+ maxTokens: 65536,
7822
+ },
7776
7823
  "glm-5": {
7777
7824
  id: "glm-5",
7778
7825
  name: "GLM-5",
@@ -8198,23 +8245,6 @@ export const MODELS = {
8198
8245
  contextWindow: 256000,
8199
8246
  maxTokens: 256000,
8200
8247
  },
8201
- "hy3-free": {
8202
- id: "hy3-free",
8203
- name: "Hy3 Free",
8204
- api: "openai-completions",
8205
- provider: "opencode",
8206
- baseUrl: "https://opencode.ai/zen/v1",
8207
- reasoning: true,
8208
- input: ["text"],
8209
- cost: {
8210
- input: 0,
8211
- output: 0,
8212
- cacheRead: 0,
8213
- cacheWrite: 0,
8214
- },
8215
- contextWindow: 190000,
8216
- maxTokens: 64000,
8217
- },
8218
8248
  "kimi-k2.5": {
8219
8249
  id: "kimi-k2.5",
8220
8250
  name: "Kimi K2.5",
@@ -8402,6 +8432,23 @@ export const MODELS = {
8402
8432
  contextWindow: 1048576,
8403
8433
  maxTokens: 131072,
8404
8434
  },
8435
+ "muse-spark-1.3-contributor-free": {
8436
+ id: "muse-spark-1.3-contributor-free",
8437
+ name: "Muse Spark 1.3 Free",
8438
+ api: "openai-responses",
8439
+ provider: "opencode",
8440
+ baseUrl: "https://opencode.ai/zen/v1",
8441
+ reasoning: true,
8442
+ input: ["text", "image"],
8443
+ cost: {
8444
+ input: 0,
8445
+ output: 0,
8446
+ cacheRead: 0,
8447
+ cacheWrite: 0,
8448
+ },
8449
+ contextWindow: 1048576,
8450
+ maxTokens: 131072,
8451
+ },
8405
8452
  "nemotron-3-ultra-free": {
8406
8453
  id: "nemotron-3-ultra-free",
8407
8454
  name: "Nemotron 3 Ultra Free",
@@ -8627,20 +8674,20 @@ export const MODELS = {
8627
8674
  },
8628
8675
  "hy3": {
8629
8676
  id: "hy3",
8630
- name: "Hy3 (8x usage)",
8677
+ name: "Hy3",
8631
8678
  api: "openai-completions",
8632
8679
  provider: "opencode-go",
8633
8680
  baseUrl: "https://opencode.ai/zen/go/v1",
8634
8681
  reasoning: true,
8635
8682
  input: ["text"],
8636
8683
  cost: {
8637
- input: 0.0175,
8638
- output: 0.0725,
8639
- cacheRead: 0.004375,
8684
+ input: 0.14,
8685
+ output: 0.58,
8686
+ cacheRead: 0.035,
8640
8687
  cacheWrite: 0,
8641
8688
  },
8642
8689
  contextWindow: 256000,
8643
- maxTokens: 64000,
8690
+ maxTokens: 128000,
8644
8691
  },
8645
8692
  "hy4-preview": {
8646
8693
  id: "hy4-preview",
@@ -8812,6 +8859,40 @@ export const MODELS = {
8812
8859
  contextWindow: 1048576,
8813
8860
  maxTokens: 131072,
8814
8861
  },
8862
+ "muse-spark-1.3-contributor": {
8863
+ id: "muse-spark-1.3-contributor",
8864
+ name: "Muse Spark 1.3 Contributor",
8865
+ api: "openai-responses",
8866
+ provider: "opencode-go",
8867
+ baseUrl: "https://opencode.ai/zen/go/v1",
8868
+ reasoning: true,
8869
+ input: ["text", "image"],
8870
+ cost: {
8871
+ input: 0.1,
8872
+ output: 0.2,
8873
+ cacheRead: 0.002,
8874
+ cacheWrite: 0,
8875
+ },
8876
+ contextWindow: 1048576,
8877
+ maxTokens: 131072,
8878
+ },
8879
+ "omen-alpha": {
8880
+ id: "omen-alpha",
8881
+ name: "Omen Alpha",
8882
+ api: "openai-completions",
8883
+ provider: "opencode-go",
8884
+ baseUrl: "https://opencode.ai/zen/go/v1",
8885
+ reasoning: true,
8886
+ input: ["text", "image"],
8887
+ cost: {
8888
+ input: 0.2,
8889
+ output: 0.66,
8890
+ cacheRead: 0.04,
8891
+ cacheWrite: 0,
8892
+ },
8893
+ contextWindow: 500000,
8894
+ maxTokens: 128000,
8895
+ },
8815
8896
  "qwen3.6-plus": {
8816
8897
  id: "qwen3.6-plus",
8817
8898
  name: "Qwen3.6 Plus",
@@ -9069,6 +9150,40 @@ export const MODELS = {
9069
9150
  contextWindow: 1000000,
9070
9151
  maxTokens: 128000,
9071
9152
  },
9153
+ "anthropic/claude-fable-5.1": {
9154
+ id: "anthropic/claude-fable-5.1",
9155
+ name: "Anthropic: Claude Fable 5.1",
9156
+ api: "openai-completions",
9157
+ provider: "openrouter",
9158
+ baseUrl: "https://openrouter.ai/api/v1",
9159
+ reasoning: true,
9160
+ input: ["text", "image"],
9161
+ cost: {
9162
+ input: 10,
9163
+ output: 50,
9164
+ cacheRead: 0.25,
9165
+ cacheWrite: 12.5,
9166
+ },
9167
+ contextWindow: 1000000,
9168
+ maxTokens: 128000,
9169
+ },
9170
+ "anthropic/claude-fable-5.1:batch": {
9171
+ id: "anthropic/claude-fable-5.1:batch",
9172
+ name: "Anthropic: Claude Fable 5.1 (batch)",
9173
+ api: "openai-completions",
9174
+ provider: "openrouter",
9175
+ baseUrl: "https://openrouter.ai/api/v1",
9176
+ reasoning: true,
9177
+ input: ["text", "image"],
9178
+ cost: {
9179
+ input: 5,
9180
+ output: 25,
9181
+ cacheRead: 0.125,
9182
+ cacheWrite: 6.25,
9183
+ },
9184
+ contextWindow: 1000000,
9185
+ maxTokens: 128000,
9186
+ },
9072
9187
  "anthropic/claude-fable-5:batch": {
9073
9188
  id: "anthropic/claude-fable-5:batch",
9074
9189
  name: "Anthropic: Claude Fable 5 (batch)",
@@ -9256,23 +9371,6 @@ export const MODELS = {
9256
9371
  contextWindow: 1000000,
9257
9372
  maxTokens: 128000,
9258
9373
  },
9259
- "anthropic/claude-opus-4.7-fast": {
9260
- id: "anthropic/claude-opus-4.7-fast",
9261
- name: "Anthropic: Claude Opus 4.7 (Fast)",
9262
- api: "openai-completions",
9263
- provider: "openrouter",
9264
- baseUrl: "https://openrouter.ai/api/v1",
9265
- reasoning: true,
9266
- input: ["text", "image"],
9267
- cost: {
9268
- input: 30,
9269
- output: 150,
9270
- cacheRead: 3,
9271
- cacheWrite: 37.5,
9272
- },
9273
- contextWindow: 1000000,
9274
- maxTokens: 128000,
9275
- },
9276
9374
  "anthropic/claude-opus-4.7:batch": {
9277
9375
  id: "anthropic/claude-opus-4.7:batch",
9278
9376
  name: "Anthropic: Claude Opus 4.7 (batch)",
@@ -9307,23 +9405,6 @@ export const MODELS = {
9307
9405
  contextWindow: 1000000,
9308
9406
  maxTokens: 128000,
9309
9407
  },
9310
- "anthropic/claude-opus-4.8-fast": {
9311
- id: "anthropic/claude-opus-4.8-fast",
9312
- name: "Anthropic: Claude Opus 4.8 (Fast)",
9313
- api: "openai-completions",
9314
- provider: "openrouter",
9315
- baseUrl: "https://openrouter.ai/api/v1",
9316
- reasoning: true,
9317
- input: ["text", "image"],
9318
- cost: {
9319
- input: 10,
9320
- output: 50,
9321
- cacheRead: 1,
9322
- cacheWrite: 12.5,
9323
- },
9324
- contextWindow: 1000000,
9325
- maxTokens: 128000,
9326
- },
9327
9408
  "anthropic/claude-opus-4.8:batch": {
9328
9409
  id: "anthropic/claude-opus-4.8:batch",
9329
9410
  name: "Anthropic: Claude Opus 4.8 (batch)",
@@ -9358,23 +9439,6 @@ export const MODELS = {
9358
9439
  contextWindow: 1000000,
9359
9440
  maxTokens: 128000,
9360
9441
  },
9361
- "anthropic/claude-opus-5-fast": {
9362
- id: "anthropic/claude-opus-5-fast",
9363
- name: "Claude Opus 5 (Fast)",
9364
- api: "openai-completions",
9365
- provider: "openrouter",
9366
- baseUrl: "https://openrouter.ai/api/v1",
9367
- reasoning: true,
9368
- input: ["text", "image"],
9369
- cost: {
9370
- input: 10,
9371
- output: 50,
9372
- cacheRead: 1,
9373
- cacheWrite: 12.5,
9374
- },
9375
- contextWindow: 1000000,
9376
- maxTokens: 128000,
9377
- },
9378
9442
  "anthropic/claude-opus-5:batch": {
9379
9443
  id: "anthropic/claude-opus-5:batch",
9380
9444
  name: "Claude Opus 5 (batch)",
@@ -9520,30 +9584,13 @@ export const MODELS = {
9520
9584
  reasoning: true,
9521
9585
  input: ["text"],
9522
9586
  cost: {
9523
- input: 0.22,
9524
- output: 0.85,
9587
+ input: 0.25,
9588
+ output: 0.7999999999999999,
9525
9589
  cacheRead: 0.06,
9526
9590
  cacheWrite: 0,
9527
9591
  },
9528
9592
  contextWindow: 262144,
9529
- maxTokens: 235929,
9530
- },
9531
- "arcee-ai/virtuoso-large": {
9532
- id: "arcee-ai/virtuoso-large",
9533
- name: "Arcee AI: Virtuoso Large",
9534
- api: "openai-completions",
9535
- provider: "openrouter",
9536
- baseUrl: "https://openrouter.ai/api/v1",
9537
- reasoning: false,
9538
- input: ["text"],
9539
- cost: {
9540
- input: 0.75,
9541
- output: 1.2,
9542
- cacheRead: 0,
9543
- cacheWrite: 0,
9544
- },
9545
- contextWindow: 131072,
9546
- maxTokens: 64000,
9593
+ maxTokens: 80000,
9547
9594
  },
9548
9595
  "auto": {
9549
9596
  id: "auto",
@@ -9724,13 +9771,13 @@ export const MODELS = {
9724
9771
  reasoning: false,
9725
9772
  input: ["text"],
9726
9773
  cost: {
9727
- input: 0.2574,
9728
- output: 1.0287,
9774
+ input: 0.32,
9775
+ output: 0.8899999999999999,
9729
9776
  cacheRead: 0,
9730
9777
  cacheWrite: 0,
9731
9778
  },
9732
9779
  contextWindow: 163840,
9733
- maxTokens: 16000,
9780
+ maxTokens: 16384,
9734
9781
  },
9735
9782
  "deepseek/deepseek-chat-v3-0324": {
9736
9783
  id: "deepseek/deepseek-chat-v3-0324",
@@ -9860,9 +9907,9 @@ export const MODELS = {
9860
9907
  reasoning: true,
9861
9908
  input: ["text"],
9862
9909
  cost: {
9863
- input: 0.0868,
9864
- output: 0.1736,
9865
- cacheRead: 0.01736,
9910
+ input: 0.088606,
9911
+ output: 0.177212,
9912
+ cacheRead: 0.017721200000000003,
9866
9913
  cacheWrite: 0,
9867
9914
  },
9868
9915
  contextWindow: 1048576,
@@ -9877,9 +9924,9 @@ export const MODELS = {
9877
9924
  reasoning: true,
9878
9925
  input: ["text"],
9879
9926
  cost: {
9880
- input: 0.049999999999999996,
9881
- output: 0.09999999999999999,
9882
- cacheRead: 0.01,
9927
+ input: 0.065,
9928
+ output: 0.18,
9929
+ cacheRead: 0.016,
9883
9930
  cacheWrite: 0,
9884
9931
  },
9885
9932
  contextWindow: 1310720,
@@ -9928,9 +9975,9 @@ export const MODELS = {
9928
9975
  reasoning: true,
9929
9976
  input: ["text"],
9930
9977
  cost: {
9931
- input: 0.741588,
9932
- output: 1.483176,
9933
- cacheRead: 0.061799,
9978
+ input: 1.04226,
9979
+ output: 2.08452,
9980
+ cacheRead: 0.086855,
9934
9981
  cacheWrite: 0,
9935
9982
  },
9936
9983
  contextWindow: 1048576,
@@ -9945,9 +9992,9 @@ export const MODELS = {
9945
9992
  reasoning: true,
9946
9993
  input: ["text"],
9947
9994
  cost: {
9948
- input: 0.66,
9949
- output: 1.9800000000000002,
9950
- cacheRead: 0.022,
9995
+ input: 1.1154,
9996
+ output: 3.3461999999999996,
9997
+ cacheRead: 0.03718,
9951
9998
  cacheWrite: 0,
9952
9999
  },
9953
10000
  contextWindow: 1048576,
@@ -10404,33 +10451,67 @@ export const MODELS = {
10404
10451
  reasoning: true,
10405
10452
  input: ["text", "image"],
10406
10453
  cost: {
10407
- input: 0.1875,
10408
- output: 0.9375,
10409
- cacheRead: 0.01875,
10410
- cacheWrite: 0.0208333333333333,
10454
+ input: 0.375,
10455
+ output: 1.875,
10456
+ cacheRead: 0.0375,
10457
+ cacheWrite: 0.0416666666666667,
10411
10458
  },
10412
10459
  contextWindow: 1048576,
10413
10460
  maxTokens: 65536,
10414
10461
  },
10415
- "google/gemma-3-12b-it": {
10416
- id: "google/gemma-3-12b-it",
10417
- name: "Google: Gemma 3 12B",
10462
+ "google/gemini-3.8-flash": {
10463
+ id: "google/gemini-3.8-flash",
10464
+ name: "Google: Gemini 3.8 Flash",
10418
10465
  api: "openai-completions",
10419
10466
  provider: "openrouter",
10420
10467
  baseUrl: "https://openrouter.ai/api/v1",
10421
- reasoning: false,
10468
+ reasoning: true,
10422
10469
  input: ["text", "image"],
10423
10470
  cost: {
10424
- input: 0.049999999999999996,
10425
- output: 0.15,
10426
- cacheRead: 0,
10427
- cacheWrite: 0,
10471
+ input: 0.75,
10472
+ output: 3.75,
10473
+ cacheRead: 0.075,
10474
+ cacheWrite: 0.0416666666666667,
10428
10475
  },
10429
- contextWindow: 131072,
10430
- maxTokens: 16384,
10476
+ contextWindow: 1048576,
10477
+ maxTokens: 65536,
10431
10478
  },
10432
- "google/gemma-3-27b-it": {
10433
- id: "google/gemma-3-27b-it",
10479
+ "google/gemini-3.8-flash:batch": {
10480
+ id: "google/gemini-3.8-flash:batch",
10481
+ name: "Google: Gemini 3.8 Flash (batch)",
10482
+ api: "openai-completions",
10483
+ provider: "openrouter",
10484
+ baseUrl: "https://openrouter.ai/api/v1",
10485
+ reasoning: true,
10486
+ input: ["text", "image"],
10487
+ cost: {
10488
+ input: 0.375,
10489
+ output: 1.875,
10490
+ cacheRead: 0.0375,
10491
+ cacheWrite: 0.0416666666666667,
10492
+ },
10493
+ contextWindow: 1048576,
10494
+ maxTokens: 65536,
10495
+ },
10496
+ "google/gemma-3-12b-it": {
10497
+ id: "google/gemma-3-12b-it",
10498
+ name: "Google: Gemma 3 12B",
10499
+ api: "openai-completions",
10500
+ provider: "openrouter",
10501
+ baseUrl: "https://openrouter.ai/api/v1",
10502
+ reasoning: false,
10503
+ input: ["text", "image"],
10504
+ cost: {
10505
+ input: 0.049999999999999996,
10506
+ output: 0.15,
10507
+ cacheRead: 0,
10508
+ cacheWrite: 0,
10509
+ },
10510
+ contextWindow: 131072,
10511
+ maxTokens: 16384,
10512
+ },
10513
+ "google/gemma-3-27b-it": {
10514
+ id: "google/gemma-3-27b-it",
10434
10515
  name: "Google: Gemma 3 27B",
10435
10516
  api: "openai-completions",
10436
10517
  provider: "openrouter",
@@ -10548,6 +10629,23 @@ export const MODELS = {
10548
10629
  contextWindow: 131072,
10549
10630
  maxTokens: 117964,
10550
10631
  },
10632
+ "ibm-granite/granite-4.2-8b": {
10633
+ id: "ibm-granite/granite-4.2-8b",
10634
+ name: "IBM: Granite 4.2 8B",
10635
+ api: "openai-completions",
10636
+ provider: "openrouter",
10637
+ baseUrl: "https://openrouter.ai/api/v1",
10638
+ reasoning: true,
10639
+ input: ["text"],
10640
+ cost: {
10641
+ input: 0.09999999999999999,
10642
+ output: 0.15,
10643
+ cacheRead: 0.049999999999999996,
10644
+ cacheWrite: 0,
10645
+ },
10646
+ contextWindow: 131072,
10647
+ maxTokens: 117964,
10648
+ },
10551
10649
  "inception/mercury-2": {
10552
10650
  id: "inception/mercury-2",
10553
10651
  name: "Inception: Mercury 2",
@@ -10565,6 +10663,23 @@ export const MODELS = {
10565
10663
  contextWindow: 128000,
10566
10664
  maxTokens: 50000,
10567
10665
  },
10666
+ "inception/mercury-2.5-preview": {
10667
+ id: "inception/mercury-2.5-preview",
10668
+ name: "Inception: Mercury 2.5 Preview",
10669
+ api: "openai-completions",
10670
+ provider: "openrouter",
10671
+ baseUrl: "https://openrouter.ai/api/v1",
10672
+ reasoning: true,
10673
+ input: ["text"],
10674
+ cost: {
10675
+ input: 0.04,
10676
+ output: 0.15,
10677
+ cacheRead: 0.004,
10678
+ cacheWrite: 0,
10679
+ },
10680
+ contextWindow: 260000,
10681
+ maxTokens: 65536,
10682
+ },
10568
10683
  "inclusionai/ling-3.0-flash": {
10569
10684
  id: "inclusionai/ling-3.0-flash",
10570
10685
  name: "Ling-3.0-flash",
@@ -10582,39 +10697,39 @@ export const MODELS = {
10582
10697
  contextWindow: 262144,
10583
10698
  maxTokens: 32768,
10584
10699
  },
10585
- "inclusionai/ling-3.0-flash-fin:free": {
10586
- id: "inclusionai/ling-3.0-flash-fin:free",
10587
- name: "Ling 3.0 Flash Fin (free)",
10700
+ "inclusionai/ling-3.0-flash-fin": {
10701
+ id: "inclusionai/ling-3.0-flash-fin",
10702
+ name: "Ling 3.0 Flash Fin",
10588
10703
  api: "openai-completions",
10589
10704
  provider: "openrouter",
10590
10705
  baseUrl: "https://openrouter.ai/api/v1",
10591
10706
  reasoning: true,
10592
10707
  input: ["text"],
10593
10708
  cost: {
10594
- input: 0,
10595
- output: 0,
10596
- cacheRead: 0,
10709
+ input: 0.06,
10710
+ output: 0.18,
10711
+ cacheRead: 0.012,
10597
10712
  cacheWrite: 0,
10598
10713
  },
10599
10714
  contextWindow: 262144,
10600
- maxTokens: 32768,
10715
+ maxTokens: 235929,
10601
10716
  },
10602
- "kwaipilot/kat-coder-air-v2.5": {
10603
- id: "kwaipilot/kat-coder-air-v2.5",
10604
- name: "Kwaipilot: KAT-Coder-Air V2.5",
10717
+ "inclusionai/ling-3.0-flash-fin:free": {
10718
+ id: "inclusionai/ling-3.0-flash-fin:free",
10719
+ name: "Ling 3.0 Flash Fin (free)",
10605
10720
  api: "openai-completions",
10606
10721
  provider: "openrouter",
10607
10722
  baseUrl: "https://openrouter.ai/api/v1",
10608
- reasoning: false,
10723
+ reasoning: true,
10609
10724
  input: ["text"],
10610
10725
  cost: {
10611
- input: 0.15,
10612
- output: 0.6,
10613
- cacheRead: 0.03,
10726
+ input: 0,
10727
+ output: 0,
10728
+ cacheRead: 0,
10614
10729
  cacheWrite: 0,
10615
10730
  },
10616
- contextWindow: 256000,
10617
- maxTokens: 80000,
10731
+ contextWindow: 262144,
10732
+ maxTokens: 32768,
10618
10733
  },
10619
10734
  "kwaipilot/kat-coder-pro-v2": {
10620
10735
  id: "kwaipilot/kat-coder-pro-v2",
@@ -10631,7 +10746,7 @@ export const MODELS = {
10631
10746
  cacheWrite: 0,
10632
10747
  },
10633
10748
  contextWindow: 262144,
10634
- maxTokens: 80000,
10749
+ maxTokens: 144000,
10635
10750
  },
10636
10751
  "kwaipilot/kat-coder-pro-v2.5": {
10637
10752
  id: "kwaipilot/kat-coder-pro-v2.5",
@@ -10648,7 +10763,7 @@ export const MODELS = {
10648
10763
  cacheWrite: 0,
10649
10764
  },
10650
10765
  contextWindow: 262144,
10651
- maxTokens: 80000,
10766
+ maxTokens: 235929,
10652
10767
  },
10653
10768
  "liquid/lfm-2.5-2.6b:free": {
10654
10769
  id: "liquid/lfm-2.5-2.6b:free",
@@ -10727,13 +10842,13 @@ export const MODELS = {
10727
10842
  reasoning: false,
10728
10843
  input: ["text"],
10729
10844
  cost: {
10730
- input: 0.71,
10731
- output: 0.71,
10732
- cacheRead: 0.71,
10845
+ input: 0.09999999999999999,
10846
+ output: 0.32,
10847
+ cacheRead: 0,
10733
10848
  cacheWrite: 0,
10734
10849
  },
10735
10850
  contextWindow: 131072,
10736
- maxTokens: 115200,
10851
+ maxTokens: 16384,
10737
10852
  },
10738
10853
  "meta-llama/llama-4-maverick": {
10739
10854
  id: "meta-llama/llama-4-maverick",
@@ -10745,12 +10860,12 @@ export const MODELS = {
10745
10860
  input: ["text", "image"],
10746
10861
  cost: {
10747
10862
  input: 0.19999999999999998,
10748
- output: 0.7999999999999999,
10863
+ output: 0.696,
10749
10864
  cacheRead: 0,
10750
10865
  cacheWrite: 0,
10751
10866
  },
10752
10867
  contextWindow: 1048576,
10753
- maxTokens: 16384,
10868
+ maxTokens: 115200,
10754
10869
  },
10755
10870
  "meta-llama/llama-4-scout": {
10756
10871
  id: "meta-llama/llama-4-scout",
@@ -10761,13 +10876,13 @@ export const MODELS = {
10761
10876
  reasoning: false,
10762
10877
  input: ["text", "image"],
10763
10878
  cost: {
10764
- input: 0.11,
10765
- output: 0.33999999999999997,
10766
- cacheRead: 0.055,
10879
+ input: 0.09999999999999999,
10880
+ output: 0.3,
10881
+ cacheRead: 0,
10767
10882
  cacheWrite: 0,
10768
10883
  },
10769
10884
  contextWindow: 1310720,
10770
- maxTokens: 8192,
10885
+ maxTokens: 16384,
10771
10886
  },
10772
10887
  "meta/muse-glimmer-30b": {
10773
10888
  id: "meta/muse-glimmer-30b",
@@ -10779,12 +10894,12 @@ export const MODELS = {
10779
10894
  input: ["text", "image"],
10780
10895
  cost: {
10781
10896
  input: 0.3,
10782
- output: 1.2,
10897
+ output: 1.1,
10783
10898
  cacheRead: 0.04,
10784
10899
  cacheWrite: 0,
10785
10900
  },
10786
10901
  contextWindow: 131072,
10787
- maxTokens: 16384,
10902
+ maxTokens: 117964,
10788
10903
  },
10789
10904
  "meta/muse-glimmer-30b:batch": {
10790
10905
  id: "meta/muse-glimmer-30b:batch",
@@ -10854,6 +10969,40 @@ export const MODELS = {
10854
10969
  contextWindow: 1048576,
10855
10970
  maxTokens: 943718,
10856
10971
  },
10972
+ "meta/muse-spark-1.3": {
10973
+ id: "meta/muse-spark-1.3",
10974
+ name: "Meta: Muse Spark 1.3",
10975
+ api: "openai-completions",
10976
+ provider: "openrouter",
10977
+ baseUrl: "https://openrouter.ai/api/v1",
10978
+ reasoning: true,
10979
+ input: ["text", "image"],
10980
+ cost: {
10981
+ input: 1.25,
10982
+ output: 4.25,
10983
+ cacheRead: 0.15,
10984
+ cacheWrite: 0,
10985
+ },
10986
+ contextWindow: 1048576,
10987
+ maxTokens: 943718,
10988
+ },
10989
+ "meta/muse-spark-1.3-contributor": {
10990
+ id: "meta/muse-spark-1.3-contributor",
10991
+ name: "Meta: Muse Spark 1.3 Contributor",
10992
+ api: "openai-completions",
10993
+ provider: "openrouter",
10994
+ baseUrl: "https://openrouter.ai/api/v1",
10995
+ reasoning: true,
10996
+ input: ["text", "image"],
10997
+ cost: {
10998
+ input: 0.09999999999999999,
10999
+ output: 0.19999999999999998,
11000
+ cacheRead: 0.002,
11001
+ cacheWrite: 0,
11002
+ },
11003
+ contextWindow: 1048576,
11004
+ maxTokens: 943718,
11005
+ },
10857
11006
  "minimax/minimax-m1": {
10858
11007
  id: "minimax/minimax-m1",
10859
11008
  name: "MiniMax: MiniMax M1",
@@ -11024,23 +11173,6 @@ export const MODELS = {
11024
11173
  contextWindow: 256000,
11025
11174
  maxTokens: 204800,
11026
11175
  },
11027
- "mistralai/codestral-2508:batch": {
11028
- id: "mistralai/codestral-2508:batch",
11029
- name: "Mistral: Codestral 2508 (batch)",
11030
- api: "openai-completions",
11031
- provider: "openrouter",
11032
- baseUrl: "https://openrouter.ai/api/v1",
11033
- reasoning: false,
11034
- input: ["text"],
11035
- cost: {
11036
- input: 0.3,
11037
- output: 0.8999999999999999,
11038
- cacheRead: 0.03,
11039
- cacheWrite: 0,
11040
- },
11041
- contextWindow: 256000,
11042
- maxTokens: 204800,
11043
- },
11044
11176
  "mistralai/devstral-2512": {
11045
11177
  id: "mistralai/devstral-2512",
11046
11178
  name: "Mistral: Devstral 2 2512",
@@ -11050,9 +11182,9 @@ export const MODELS = {
11050
11182
  reasoning: false,
11051
11183
  input: ["text"],
11052
11184
  cost: {
11053
- input: 0.44,
11054
- output: 2.2,
11055
- cacheRead: 0.044,
11185
+ input: 0.39999999999999997,
11186
+ output: 2,
11187
+ cacheRead: 0.04,
11056
11188
  cacheWrite: 0,
11057
11189
  },
11058
11190
  contextWindow: 262144,
@@ -11109,23 +11241,6 @@ export const MODELS = {
11109
11241
  contextWindow: 262144,
11110
11242
  maxTokens: 209715,
11111
11243
  },
11112
- "mistralai/ministral-8b-2512:batch": {
11113
- id: "mistralai/ministral-8b-2512:batch",
11114
- name: "Mistral: Ministral 3 8B 2512 (batch)",
11115
- api: "openai-completions",
11116
- provider: "openrouter",
11117
- baseUrl: "https://openrouter.ai/api/v1",
11118
- reasoning: false,
11119
- input: ["text", "image"],
11120
- cost: {
11121
- input: 0.15,
11122
- output: 0.15,
11123
- cacheRead: 0.015,
11124
- cacheWrite: 0,
11125
- },
11126
- contextWindow: 262144,
11127
- maxTokens: 209715,
11128
- },
11129
11244
  "mistralai/mistral-large": {
11130
11245
  id: "mistralai/mistral-large",
11131
11246
  name: "Mistral Large",
@@ -11177,23 +11292,6 @@ export const MODELS = {
11177
11292
  contextWindow: 262144,
11178
11293
  maxTokens: 209715,
11179
11294
  },
11180
- "mistralai/mistral-large-2512:batch": {
11181
- id: "mistralai/mistral-large-2512:batch",
11182
- name: "Mistral: Mistral Large 3 2512 (batch)",
11183
- api: "openai-completions",
11184
- provider: "openrouter",
11185
- baseUrl: "https://openrouter.ai/api/v1",
11186
- reasoning: false,
11187
- input: ["text", "image"],
11188
- cost: {
11189
- input: 0.5,
11190
- output: 1.5,
11191
- cacheRead: 0.049999999999999996,
11192
- cacheWrite: 0,
11193
- },
11194
- contextWindow: 262144,
11195
- maxTokens: 209715,
11196
- },
11197
11295
  "mistralai/mistral-medium-3": {
11198
11296
  id: "mistralai/mistral-medium-3",
11199
11297
  name: "Mistral: Mistral Medium 3",
@@ -11242,8 +11340,8 @@ export const MODELS = {
11242
11340
  cacheRead: 0,
11243
11341
  cacheWrite: 0,
11244
11342
  },
11245
- contextWindow: 262144,
11246
- maxTokens: 209715,
11343
+ contextWindow: 32768,
11344
+ maxTokens: 26214,
11247
11345
  },
11248
11346
  "mistralai/mistral-medium-3.1": {
11249
11347
  id: "mistralai/mistral-medium-3.1",
@@ -11262,23 +11360,6 @@ export const MODELS = {
11262
11360
  contextWindow: 131072,
11263
11361
  maxTokens: 104857,
11264
11362
  },
11265
- "mistralai/mistral-medium-3.1:batch": {
11266
- id: "mistralai/mistral-medium-3.1:batch",
11267
- name: "Mistral: Mistral Medium 3.1 (batch)",
11268
- api: "openai-completions",
11269
- provider: "openrouter",
11270
- baseUrl: "https://openrouter.ai/api/v1",
11271
- reasoning: false,
11272
- input: ["text", "image"],
11273
- cost: {
11274
- input: 0.39999999999999997,
11275
- output: 2,
11276
- cacheRead: 0.04,
11277
- cacheWrite: 0,
11278
- },
11279
- contextWindow: 131072,
11280
- maxTokens: 104857,
11281
- },
11282
11363
  "mistralai/mistral-nemo": {
11283
11364
  id: "mistralai/mistral-nemo",
11284
11365
  name: "Mistral: Mistral Nemo",
@@ -11330,23 +11411,6 @@ export const MODELS = {
11330
11411
  contextWindow: 262144,
11331
11412
  maxTokens: 209715,
11332
11413
  },
11333
- "mistralai/mistral-small-2603:batch": {
11334
- id: "mistralai/mistral-small-2603:batch",
11335
- name: "Mistral: Mistral Small 4 (batch)",
11336
- api: "openai-completions",
11337
- provider: "openrouter",
11338
- baseUrl: "https://openrouter.ai/api/v1",
11339
- reasoning: true,
11340
- input: ["text", "image"],
11341
- cost: {
11342
- input: 0.15,
11343
- output: 0.6,
11344
- cacheRead: 0.015,
11345
- cacheWrite: 0,
11346
- },
11347
- contextWindow: 262144,
11348
- maxTokens: 209715,
11349
- },
11350
11414
  "mistralai/mistral-small-3.2-24b-instruct": {
11351
11415
  id: "mistralai/mistral-small-3.2-24b-instruct",
11352
11416
  name: "Mistral: Mistral Small 3.2 24B",
@@ -11509,9 +11573,9 @@ export const MODELS = {
11509
11573
  reasoning: true,
11510
11574
  input: ["text", "image"],
11511
11575
  cost: {
11512
- input: 2.5500000000000003,
11513
- output: 12.75,
11514
- cacheRead: 0.25599998999999996,
11576
+ input: 3,
11577
+ output: 15,
11578
+ cacheRead: 0.3,
11515
11579
  cacheWrite: 0,
11516
11580
  },
11517
11581
  contextWindow: 1048576,
@@ -11579,11 +11643,11 @@ export const MODELS = {
11579
11643
  cost: {
11580
11644
  input: 0.049999999999999996,
11581
11645
  output: 0.19999999999999998,
11582
- cacheRead: 0.024999999999999998,
11646
+ cacheRead: 0.03,
11583
11647
  cacheWrite: 0,
11584
11648
  },
11585
11649
  contextWindow: 262144,
11586
- maxTokens: 228000,
11650
+ maxTokens: 235929,
11587
11651
  },
11588
11652
  "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free": {
11589
11653
  id: "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
@@ -11645,30 +11709,13 @@ export const MODELS = {
11645
11709
  reasoning: true,
11646
11710
  input: ["text"],
11647
11711
  cost: {
11648
- input: 0.5,
11649
- output: 2.2,
11650
- cacheRead: 0.09999999999999999,
11712
+ input: 0.625,
11713
+ output: 3.125,
11714
+ cacheRead: 0.1875,
11651
11715
  cacheWrite: 0,
11652
11716
  },
11653
11717
  contextWindow: 262144,
11654
- maxTokens: 16384,
11655
- },
11656
- "nvidia/nemotron-3-ultra-550b-a55b:batch": {
11657
- id: "nvidia/nemotron-3-ultra-550b-a55b:batch",
11658
- name: "NVIDIA: Nemotron 3 Ultra (batch)",
11659
- api: "openai-completions",
11660
- provider: "openrouter",
11661
- baseUrl: "https://openrouter.ai/api/v1",
11662
- reasoning: true,
11663
- input: ["text"],
11664
- cost: {
11665
- input: 0.6,
11666
- output: 3.5999999999999996,
11667
- cacheRead: 0.19999999999999998,
11668
- cacheWrite: 0,
11669
- },
11670
- contextWindow: 512288,
11671
- maxTokens: 461059,
11718
+ maxTokens: 32768,
11672
11719
  },
11673
11720
  "nvidia/nemotron-3-ultra-550b-a55b:free": {
11674
11721
  id: "nvidia/nemotron-3-ultra-550b-a55b:free",
@@ -11772,6 +11819,23 @@ export const MODELS = {
11772
11819
  contextWindow: 16385,
11773
11820
  maxTokens: 4096,
11774
11821
  },
11822
+ "openai/gpt-3.5-turbo:batch": {
11823
+ id: "openai/gpt-3.5-turbo:batch",
11824
+ name: "OpenAI: GPT-3.5 Turbo (batch)",
11825
+ api: "openai-completions",
11826
+ provider: "openrouter",
11827
+ baseUrl: "https://openrouter.ai/api/v1",
11828
+ reasoning: false,
11829
+ input: ["text"],
11830
+ cost: {
11831
+ input: 0.25,
11832
+ output: 0.75,
11833
+ cacheRead: 0,
11834
+ cacheWrite: 0,
11835
+ },
11836
+ contextWindow: 16385,
11837
+ maxTokens: 4096,
11838
+ },
11775
11839
  "openai/gpt-4": {
11776
11840
  id: "openai/gpt-4",
11777
11841
  name: "OpenAI: GPT-4",
@@ -11823,6 +11887,23 @@ export const MODELS = {
11823
11887
  contextWindow: 128000,
11824
11888
  maxTokens: 4096,
11825
11889
  },
11890
+ "openai/gpt-4-turbo:batch": {
11891
+ id: "openai/gpt-4-turbo:batch",
11892
+ name: "OpenAI: GPT-4 Turbo (batch)",
11893
+ api: "openai-completions",
11894
+ provider: "openrouter",
11895
+ baseUrl: "https://openrouter.ai/api/v1",
11896
+ reasoning: false,
11897
+ input: ["text", "image"],
11898
+ cost: {
11899
+ input: 5,
11900
+ output: 15,
11901
+ cacheRead: 0,
11902
+ cacheWrite: 0,
11903
+ },
11904
+ contextWindow: 128000,
11905
+ maxTokens: 4096,
11906
+ },
11826
11907
  "openai/gpt-4.1": {
11827
11908
  id: "openai/gpt-4.1",
11828
11909
  name: "OpenAI: GPT-4.1",
@@ -11857,6 +11938,23 @@ export const MODELS = {
11857
11938
  contextWindow: 1047576,
11858
11939
  maxTokens: 32768,
11859
11940
  },
11941
+ "openai/gpt-4.1-mini:batch": {
11942
+ id: "openai/gpt-4.1-mini:batch",
11943
+ name: "OpenAI: GPT-4.1 Mini (batch)",
11944
+ api: "openai-completions",
11945
+ provider: "openrouter",
11946
+ baseUrl: "https://openrouter.ai/api/v1",
11947
+ reasoning: false,
11948
+ input: ["text", "image"],
11949
+ cost: {
11950
+ input: 0.19999999999999998,
11951
+ output: 0.7999999999999999,
11952
+ cacheRead: 0.049999999999999996,
11953
+ cacheWrite: 0,
11954
+ },
11955
+ contextWindow: 1047576,
11956
+ maxTokens: 32768,
11957
+ },
11860
11958
  "openai/gpt-4.1-nano": {
11861
11959
  id: "openai/gpt-4.1-nano",
11862
11960
  name: "OpenAI: GPT-4.1 Nano",
@@ -11868,11 +11966,45 @@ export const MODELS = {
11868
11966
  cost: {
11869
11967
  input: 0.09999999999999999,
11870
11968
  output: 0.39999999999999997,
11871
- cacheRead: 0.03,
11969
+ cacheRead: 0.024999999999999998,
11970
+ cacheWrite: 0,
11971
+ },
11972
+ contextWindow: 1047576,
11973
+ maxTokens: 32768,
11974
+ },
11975
+ "openai/gpt-4.1-nano:batch": {
11976
+ id: "openai/gpt-4.1-nano:batch",
11977
+ name: "OpenAI: GPT-4.1 Nano (batch)",
11978
+ api: "openai-completions",
11979
+ provider: "openrouter",
11980
+ baseUrl: "https://openrouter.ai/api/v1",
11981
+ reasoning: false,
11982
+ input: ["text", "image"],
11983
+ cost: {
11984
+ input: 0.049999999999999996,
11985
+ output: 0.19999999999999998,
11986
+ cacheRead: 0.012499999999999999,
11987
+ cacheWrite: 0,
11988
+ },
11989
+ contextWindow: 1047576,
11990
+ maxTokens: 32768,
11991
+ },
11992
+ "openai/gpt-4.1:batch": {
11993
+ id: "openai/gpt-4.1:batch",
11994
+ name: "OpenAI: GPT-4.1 (batch)",
11995
+ api: "openai-completions",
11996
+ provider: "openrouter",
11997
+ baseUrl: "https://openrouter.ai/api/v1",
11998
+ reasoning: false,
11999
+ input: ["text", "image"],
12000
+ cost: {
12001
+ input: 1,
12002
+ output: 4,
12003
+ cacheRead: 0.25,
11872
12004
  cacheWrite: 0,
11873
12005
  },
11874
12006
  contextWindow: 1047576,
11875
- maxTokens: 942818,
12007
+ maxTokens: 32768,
11876
12008
  },
11877
12009
  "openai/gpt-4o": {
11878
12010
  id: "openai/gpt-4o",
@@ -11976,6 +12108,40 @@ export const MODELS = {
11976
12108
  contextWindow: 128000,
11977
12109
  maxTokens: 16384,
11978
12110
  },
12111
+ "openai/gpt-4o-mini:batch": {
12112
+ id: "openai/gpt-4o-mini:batch",
12113
+ name: "OpenAI: GPT-4o-mini (batch)",
12114
+ api: "openai-completions",
12115
+ provider: "openrouter",
12116
+ baseUrl: "https://openrouter.ai/api/v1",
12117
+ reasoning: false,
12118
+ input: ["text", "image"],
12119
+ cost: {
12120
+ input: 0.075,
12121
+ output: 0.3,
12122
+ cacheRead: 0.0375,
12123
+ cacheWrite: 0,
12124
+ },
12125
+ contextWindow: 128000,
12126
+ maxTokens: 16384,
12127
+ },
12128
+ "openai/gpt-4o:batch": {
12129
+ id: "openai/gpt-4o:batch",
12130
+ name: "OpenAI: GPT-4o (batch)",
12131
+ api: "openai-completions",
12132
+ provider: "openrouter",
12133
+ baseUrl: "https://openrouter.ai/api/v1",
12134
+ reasoning: false,
12135
+ input: ["text", "image"],
12136
+ cost: {
12137
+ input: 1.25,
12138
+ output: 5,
12139
+ cacheRead: 0.625,
12140
+ cacheWrite: 0,
12141
+ },
12142
+ contextWindow: 128000,
12143
+ maxTokens: 16384,
12144
+ },
11979
12145
  "openai/gpt-5": {
11980
12146
  id: "openai/gpt-5",
11981
12147
  name: "OpenAI: GPT-5",
@@ -12010,6 +12176,23 @@ export const MODELS = {
12010
12176
  contextWindow: 400000,
12011
12177
  maxTokens: 128000,
12012
12178
  },
12179
+ "openai/gpt-5-mini:batch": {
12180
+ id: "openai/gpt-5-mini:batch",
12181
+ name: "OpenAI: GPT-5 Mini (batch)",
12182
+ api: "openai-completions",
12183
+ provider: "openrouter",
12184
+ baseUrl: "https://openrouter.ai/api/v1",
12185
+ reasoning: true,
12186
+ input: ["text", "image"],
12187
+ cost: {
12188
+ input: 0.125,
12189
+ output: 1,
12190
+ cacheRead: 0.012499999999999999,
12191
+ cacheWrite: 0,
12192
+ },
12193
+ contextWindow: 400000,
12194
+ maxTokens: 128000,
12195
+ },
12013
12196
  "openai/gpt-5-nano": {
12014
12197
  id: "openai/gpt-5-nano",
12015
12198
  name: "OpenAI: GPT-5 Nano",
@@ -12027,6 +12210,23 @@ export const MODELS = {
12027
12210
  contextWindow: 400000,
12028
12211
  maxTokens: 128000,
12029
12212
  },
12213
+ "openai/gpt-5-nano:batch": {
12214
+ id: "openai/gpt-5-nano:batch",
12215
+ name: "OpenAI: GPT-5 Nano (batch)",
12216
+ api: "openai-completions",
12217
+ provider: "openrouter",
12218
+ baseUrl: "https://openrouter.ai/api/v1",
12219
+ reasoning: true,
12220
+ input: ["text", "image"],
12221
+ cost: {
12222
+ input: 0.024999999999999998,
12223
+ output: 0.19999999999999998,
12224
+ cacheRead: 0.0025,
12225
+ cacheWrite: 0,
12226
+ },
12227
+ contextWindow: 400000,
12228
+ maxTokens: 128000,
12229
+ },
12030
12230
  "openai/gpt-5-pro": {
12031
12231
  id: "openai/gpt-5-pro",
12032
12232
  name: "OpenAI: GPT-5 Pro",
@@ -12044,6 +12244,23 @@ export const MODELS = {
12044
12244
  contextWindow: 400000,
12045
12245
  maxTokens: 128000,
12046
12246
  },
12247
+ "openai/gpt-5-pro:batch": {
12248
+ id: "openai/gpt-5-pro:batch",
12249
+ name: "OpenAI: GPT-5 Pro (batch)",
12250
+ api: "openai-completions",
12251
+ provider: "openrouter",
12252
+ baseUrl: "https://openrouter.ai/api/v1",
12253
+ reasoning: true,
12254
+ input: ["text", "image"],
12255
+ cost: {
12256
+ input: 7.5,
12257
+ output: 60,
12258
+ cacheRead: 0,
12259
+ cacheWrite: 0,
12260
+ },
12261
+ contextWindow: 400000,
12262
+ maxTokens: 128000,
12263
+ },
12047
12264
  "openai/gpt-5.1": {
12048
12265
  id: "openai/gpt-5.1",
12049
12266
  name: "OpenAI: GPT-5.1",
@@ -12112,6 +12329,23 @@ export const MODELS = {
12112
12329
  contextWindow: 400000,
12113
12330
  maxTokens: 128000,
12114
12331
  },
12332
+ "openai/gpt-5.1:batch": {
12333
+ id: "openai/gpt-5.1:batch",
12334
+ name: "OpenAI: GPT-5.1 (batch)",
12335
+ api: "openai-completions",
12336
+ provider: "openrouter",
12337
+ baseUrl: "https://openrouter.ai/api/v1",
12338
+ reasoning: true,
12339
+ input: ["text", "image"],
12340
+ cost: {
12341
+ input: 0.625,
12342
+ output: 5,
12343
+ cacheRead: 0.0625,
12344
+ cacheWrite: 0,
12345
+ },
12346
+ contextWindow: 400000,
12347
+ maxTokens: 128000,
12348
+ },
12115
12349
  "openai/gpt-5.2": {
12116
12350
  id: "openai/gpt-5.2",
12117
12351
  name: "OpenAI: GPT-5.2",
@@ -12180,6 +12414,40 @@ export const MODELS = {
12180
12414
  contextWindow: 400000,
12181
12415
  maxTokens: 128000,
12182
12416
  },
12417
+ "openai/gpt-5.2-pro:batch": {
12418
+ id: "openai/gpt-5.2-pro:batch",
12419
+ name: "OpenAI: GPT-5.2 Pro (batch)",
12420
+ api: "openai-completions",
12421
+ provider: "openrouter",
12422
+ baseUrl: "https://openrouter.ai/api/v1",
12423
+ reasoning: true,
12424
+ input: ["text", "image"],
12425
+ cost: {
12426
+ input: 10.5,
12427
+ output: 84,
12428
+ cacheRead: 0,
12429
+ cacheWrite: 0,
12430
+ },
12431
+ contextWindow: 400000,
12432
+ maxTokens: 128000,
12433
+ },
12434
+ "openai/gpt-5.2:batch": {
12435
+ id: "openai/gpt-5.2:batch",
12436
+ name: "OpenAI: GPT-5.2 (batch)",
12437
+ api: "openai-completions",
12438
+ provider: "openrouter",
12439
+ baseUrl: "https://openrouter.ai/api/v1",
12440
+ reasoning: true,
12441
+ input: ["text", "image"],
12442
+ cost: {
12443
+ input: 0.875,
12444
+ output: 7,
12445
+ cacheRead: 0.0875,
12446
+ cacheWrite: 0,
12447
+ },
12448
+ contextWindow: 400000,
12449
+ maxTokens: 128000,
12450
+ },
12183
12451
  "openai/gpt-5.3-codex": {
12184
12452
  id: "openai/gpt-5.3-codex",
12185
12453
  name: "OpenAI: GPT-5.3-Codex",
@@ -12231,6 +12499,23 @@ export const MODELS = {
12231
12499
  contextWindow: 400000,
12232
12500
  maxTokens: 128000,
12233
12501
  },
12502
+ "openai/gpt-5.4-mini:batch": {
12503
+ id: "openai/gpt-5.4-mini:batch",
12504
+ name: "OpenAI: GPT-5.4 Mini (batch)",
12505
+ api: "openai-completions",
12506
+ provider: "openrouter",
12507
+ baseUrl: "https://openrouter.ai/api/v1",
12508
+ reasoning: true,
12509
+ input: ["text", "image"],
12510
+ cost: {
12511
+ input: 0.375,
12512
+ output: 2.25,
12513
+ cacheRead: 0.0375,
12514
+ cacheWrite: 0,
12515
+ },
12516
+ contextWindow: 400000,
12517
+ maxTokens: 128000,
12518
+ },
12234
12519
  "openai/gpt-5.4-nano": {
12235
12520
  id: "openai/gpt-5.4-nano",
12236
12521
  name: "OpenAI: GPT-5.4 Nano",
@@ -12248,6 +12533,23 @@ export const MODELS = {
12248
12533
  contextWindow: 400000,
12249
12534
  maxTokens: 128000,
12250
12535
  },
12536
+ "openai/gpt-5.4-nano:batch": {
12537
+ id: "openai/gpt-5.4-nano:batch",
12538
+ name: "OpenAI: GPT-5.4 Nano (batch)",
12539
+ api: "openai-completions",
12540
+ provider: "openrouter",
12541
+ baseUrl: "https://openrouter.ai/api/v1",
12542
+ reasoning: true,
12543
+ input: ["text", "image"],
12544
+ cost: {
12545
+ input: 0.09999999999999999,
12546
+ output: 0.625,
12547
+ cacheRead: 0.01,
12548
+ cacheWrite: 0,
12549
+ },
12550
+ contextWindow: 400000,
12551
+ maxTokens: 128000,
12552
+ },
12251
12553
  "openai/gpt-5.4-pro": {
12252
12554
  id: "openai/gpt-5.4-pro",
12253
12555
  name: "OpenAI: GPT-5.4 Pro",
@@ -12265,6 +12567,40 @@ export const MODELS = {
12265
12567
  contextWindow: 1050000,
12266
12568
  maxTokens: 128000,
12267
12569
  },
12570
+ "openai/gpt-5.4-pro:batch": {
12571
+ id: "openai/gpt-5.4-pro:batch",
12572
+ name: "OpenAI: GPT-5.4 Pro (batch)",
12573
+ api: "openai-completions",
12574
+ provider: "openrouter",
12575
+ baseUrl: "https://openrouter.ai/api/v1",
12576
+ reasoning: true,
12577
+ input: ["text", "image"],
12578
+ cost: {
12579
+ input: 15,
12580
+ output: 90,
12581
+ cacheRead: 0,
12582
+ cacheWrite: 0,
12583
+ },
12584
+ contextWindow: 1050000,
12585
+ maxTokens: 128000,
12586
+ },
12587
+ "openai/gpt-5.4:batch": {
12588
+ id: "openai/gpt-5.4:batch",
12589
+ name: "OpenAI: GPT-5.4 (batch)",
12590
+ api: "openai-completions",
12591
+ provider: "openrouter",
12592
+ baseUrl: "https://openrouter.ai/api/v1",
12593
+ reasoning: true,
12594
+ input: ["text", "image"],
12595
+ cost: {
12596
+ input: 1.25,
12597
+ output: 7.5,
12598
+ cacheRead: 0.125,
12599
+ cacheWrite: 0,
12600
+ },
12601
+ contextWindow: 1050000,
12602
+ maxTokens: 128000,
12603
+ },
12268
12604
  "openai/gpt-5.5": {
12269
12605
  id: "openai/gpt-5.5",
12270
12606
  name: "OpenAI: GPT-5.5",
@@ -12299,6 +12635,40 @@ export const MODELS = {
12299
12635
  contextWindow: 1050000,
12300
12636
  maxTokens: 128000,
12301
12637
  },
12638
+ "openai/gpt-5.5-pro:batch": {
12639
+ id: "openai/gpt-5.5-pro:batch",
12640
+ name: "OpenAI: GPT-5.5 Pro (batch)",
12641
+ api: "openai-completions",
12642
+ provider: "openrouter",
12643
+ baseUrl: "https://openrouter.ai/api/v1",
12644
+ reasoning: true,
12645
+ input: ["text", "image"],
12646
+ cost: {
12647
+ input: 15,
12648
+ output: 90,
12649
+ cacheRead: 0,
12650
+ cacheWrite: 0,
12651
+ },
12652
+ contextWindow: 1050000,
12653
+ maxTokens: 128000,
12654
+ },
12655
+ "openai/gpt-5.5:batch": {
12656
+ id: "openai/gpt-5.5:batch",
12657
+ name: "OpenAI: GPT-5.5 (batch)",
12658
+ api: "openai-completions",
12659
+ provider: "openrouter",
12660
+ baseUrl: "https://openrouter.ai/api/v1",
12661
+ reasoning: true,
12662
+ input: ["text", "image"],
12663
+ cost: {
12664
+ input: 2.5,
12665
+ output: 15,
12666
+ cacheRead: 0.25,
12667
+ cacheWrite: 0,
12668
+ },
12669
+ contextWindow: 1050000,
12670
+ maxTokens: 128000,
12671
+ },
12302
12672
  "openai/gpt-5.6-luna": {
12303
12673
  id: "openai/gpt-5.6-luna",
12304
12674
  name: "OpenAI: GPT-5.6 Luna",
@@ -12333,6 +12703,40 @@ export const MODELS = {
12333
12703
  contextWindow: 1050000,
12334
12704
  maxTokens: 128000,
12335
12705
  },
12706
+ "openai/gpt-5.6-luna-pro:batch": {
12707
+ id: "openai/gpt-5.6-luna-pro:batch",
12708
+ name: "OpenAI: GPT-5.6 Luna Pro (batch)",
12709
+ api: "openai-completions",
12710
+ provider: "openrouter",
12711
+ baseUrl: "https://openrouter.ai/api/v1",
12712
+ reasoning: true,
12713
+ input: ["text", "image"],
12714
+ cost: {
12715
+ input: 0.09999999999999999,
12716
+ output: 0.6,
12717
+ cacheRead: 0.01,
12718
+ cacheWrite: 0,
12719
+ },
12720
+ contextWindow: 1050000,
12721
+ maxTokens: 128000,
12722
+ },
12723
+ "openai/gpt-5.6-luna:batch": {
12724
+ id: "openai/gpt-5.6-luna:batch",
12725
+ name: "OpenAI: GPT-5.6 Luna (batch)",
12726
+ api: "openai-completions",
12727
+ provider: "openrouter",
12728
+ baseUrl: "https://openrouter.ai/api/v1",
12729
+ reasoning: true,
12730
+ input: ["text", "image"],
12731
+ cost: {
12732
+ input: 0.09999999999999999,
12733
+ output: 0.6,
12734
+ cacheRead: 0.01,
12735
+ cacheWrite: 0,
12736
+ },
12737
+ contextWindow: 1050000,
12738
+ maxTokens: 128000,
12739
+ },
12336
12740
  "openai/gpt-5.6-sol": {
12337
12741
  id: "openai/gpt-5.6-sol",
12338
12742
  name: "OpenAI: GPT-5.6 Sol",
@@ -12367,6 +12771,40 @@ export const MODELS = {
12367
12771
  contextWindow: 1050000,
12368
12772
  maxTokens: 128000,
12369
12773
  },
12774
+ "openai/gpt-5.6-sol-pro:batch": {
12775
+ id: "openai/gpt-5.6-sol-pro:batch",
12776
+ name: "OpenAI: GPT-5.6 Sol Pro (batch)",
12777
+ api: "openai-completions",
12778
+ provider: "openrouter",
12779
+ baseUrl: "https://openrouter.ai/api/v1",
12780
+ reasoning: true,
12781
+ input: ["text", "image"],
12782
+ cost: {
12783
+ input: 1,
12784
+ output: 5,
12785
+ cacheRead: 0.09999999999999999,
12786
+ cacheWrite: 1.25,
12787
+ },
12788
+ contextWindow: 1050000,
12789
+ maxTokens: 128000,
12790
+ },
12791
+ "openai/gpt-5.6-sol:batch": {
12792
+ id: "openai/gpt-5.6-sol:batch",
12793
+ name: "OpenAI: GPT-5.6 Sol (batch)",
12794
+ api: "openai-completions",
12795
+ provider: "openrouter",
12796
+ baseUrl: "https://openrouter.ai/api/v1",
12797
+ reasoning: true,
12798
+ input: ["text", "image"],
12799
+ cost: {
12800
+ input: 1,
12801
+ output: 5,
12802
+ cacheRead: 0.09999999999999999,
12803
+ cacheWrite: 1.25,
12804
+ },
12805
+ contextWindow: 1050000,
12806
+ maxTokens: 128000,
12807
+ },
12370
12808
  "openai/gpt-5.6-terra": {
12371
12809
  id: "openai/gpt-5.6-terra",
12372
12810
  name: "OpenAI: GPT-5.6 Terra",
@@ -12401,6 +12839,57 @@ export const MODELS = {
12401
12839
  contextWindow: 1050000,
12402
12840
  maxTokens: 128000,
12403
12841
  },
12842
+ "openai/gpt-5.6-terra-pro:batch": {
12843
+ id: "openai/gpt-5.6-terra-pro:batch",
12844
+ name: "OpenAI: GPT-5.6 Terra Pro (batch)",
12845
+ api: "openai-completions",
12846
+ provider: "openrouter",
12847
+ baseUrl: "https://openrouter.ai/api/v1",
12848
+ reasoning: true,
12849
+ input: ["text", "image"],
12850
+ cost: {
12851
+ input: 1,
12852
+ output: 6,
12853
+ cacheRead: 0.09999999999999999,
12854
+ cacheWrite: 0,
12855
+ },
12856
+ contextWindow: 1050000,
12857
+ maxTokens: 128000,
12858
+ },
12859
+ "openai/gpt-5.6-terra:batch": {
12860
+ id: "openai/gpt-5.6-terra:batch",
12861
+ name: "OpenAI: GPT-5.6 Terra (batch)",
12862
+ api: "openai-completions",
12863
+ provider: "openrouter",
12864
+ baseUrl: "https://openrouter.ai/api/v1",
12865
+ reasoning: true,
12866
+ input: ["text", "image"],
12867
+ cost: {
12868
+ input: 1,
12869
+ output: 6,
12870
+ cacheRead: 0.09999999999999999,
12871
+ cacheWrite: 0,
12872
+ },
12873
+ contextWindow: 1050000,
12874
+ maxTokens: 128000,
12875
+ },
12876
+ "openai/gpt-5:batch": {
12877
+ id: "openai/gpt-5:batch",
12878
+ name: "OpenAI: GPT-5 (batch)",
12879
+ api: "openai-completions",
12880
+ provider: "openrouter",
12881
+ baseUrl: "https://openrouter.ai/api/v1",
12882
+ reasoning: true,
12883
+ input: ["text", "image"],
12884
+ cost: {
12885
+ input: 0.625,
12886
+ output: 5,
12887
+ cacheRead: 0.0625,
12888
+ cacheWrite: 0,
12889
+ },
12890
+ contextWindow: 400000,
12891
+ maxTokens: 128000,
12892
+ },
12404
12893
  "openai/gpt-audio": {
12405
12894
  id: "openai/gpt-audio",
12406
12895
  name: "OpenAI: GPT Audio",
@@ -12588,18 +13077,52 @@ export const MODELS = {
12588
13077
  contextWindow: 200000,
12589
13078
  maxTokens: 100000,
12590
13079
  },
12591
- "openai/o3-pro": {
12592
- id: "openai/o3-pro",
12593
- name: "OpenAI: o3 Pro",
13080
+ "openai/o3-mini:batch": {
13081
+ id: "openai/o3-mini:batch",
13082
+ name: "OpenAI: o3 Mini (batch)",
13083
+ api: "openai-completions",
13084
+ provider: "openrouter",
13085
+ baseUrl: "https://openrouter.ai/api/v1",
13086
+ reasoning: true,
13087
+ input: ["text"],
13088
+ cost: {
13089
+ input: 0.55,
13090
+ output: 2.2,
13091
+ cacheRead: 0.275,
13092
+ cacheWrite: 0,
13093
+ },
13094
+ contextWindow: 200000,
13095
+ maxTokens: 100000,
13096
+ },
13097
+ "openai/o3-pro": {
13098
+ id: "openai/o3-pro",
13099
+ name: "OpenAI: o3 Pro",
13100
+ api: "openai-completions",
13101
+ provider: "openrouter",
13102
+ baseUrl: "https://openrouter.ai/api/v1",
13103
+ reasoning: true,
13104
+ input: ["text", "image"],
13105
+ cost: {
13106
+ input: 20,
13107
+ output: 80,
13108
+ cacheRead: 0,
13109
+ cacheWrite: 0,
13110
+ },
13111
+ contextWindow: 200000,
13112
+ maxTokens: 100000,
13113
+ },
13114
+ "openai/o3:batch": {
13115
+ id: "openai/o3:batch",
13116
+ name: "OpenAI: o3 (batch)",
12594
13117
  api: "openai-completions",
12595
13118
  provider: "openrouter",
12596
13119
  baseUrl: "https://openrouter.ai/api/v1",
12597
13120
  reasoning: true,
12598
13121
  input: ["text", "image"],
12599
13122
  cost: {
12600
- input: 20,
12601
- output: 80,
12602
- cacheRead: 0,
13123
+ input: 1,
13124
+ output: 4,
13125
+ cacheRead: 0.25,
12603
13126
  cacheWrite: 0,
12604
13127
  },
12605
13128
  contextWindow: 200000,
@@ -12639,6 +13162,23 @@ export const MODELS = {
12639
13162
  contextWindow: 200000,
12640
13163
  maxTokens: 100000,
12641
13164
  },
13165
+ "openai/o4-mini:batch": {
13166
+ id: "openai/o4-mini:batch",
13167
+ name: "OpenAI: o4 Mini (batch)",
13168
+ api: "openai-completions",
13169
+ provider: "openrouter",
13170
+ baseUrl: "https://openrouter.ai/api/v1",
13171
+ reasoning: true,
13172
+ input: ["text", "image"],
13173
+ cost: {
13174
+ input: 0.55,
13175
+ output: 2.2,
13176
+ cacheRead: 0.1375,
13177
+ cacheWrite: 0,
13178
+ },
13179
+ contextWindow: 200000,
13180
+ maxTokens: 100000,
13181
+ },
12642
13182
  "openrouter/auto": {
12643
13183
  id: "openrouter/auto",
12644
13184
  name: "Auto Router",
@@ -13311,13 +13851,13 @@ export const MODELS = {
13311
13851
  reasoning: true,
13312
13852
  input: ["text", "image"],
13313
13853
  cost: {
13314
- input: 0.39,
13315
- output: 2.34,
13316
- cacheRead: 0,
13854
+ input: 0.55,
13855
+ output: 3.5,
13856
+ cacheRead: 0.22499999999999998,
13317
13857
  cacheWrite: 0,
13318
13858
  },
13319
13859
  contextWindow: 262144,
13320
- maxTokens: 65536,
13860
+ maxTokens: 235929,
13321
13861
  },
13322
13862
  "qwen/qwen3.5-9b": {
13323
13863
  id: "qwen/qwen3.5-9b",
@@ -13551,11 +14091,11 @@ export const MODELS = {
13551
14091
  cost: {
13552
14092
  input: 2,
13553
14093
  output: 6,
13554
- cacheRead: 0.19999999999999998,
14094
+ cacheRead: 0.25,
13555
14095
  cacheWrite: 0,
13556
14096
  },
13557
14097
  contextWindow: 1048576,
13558
- maxTokens: 131072,
14098
+ maxTokens: 262144,
13559
14099
  },
13560
14100
  "qwen/qwen3.8-2.4t-a95b:batch": {
13561
14101
  id: "qwen/qwen3.8-2.4t-a95b:batch",
@@ -13583,10 +14123,10 @@ export const MODELS = {
13583
14123
  reasoning: true,
13584
14124
  input: ["text", "image"],
13585
14125
  cost: {
13586
- input: 0.425,
13587
- output: 2.5500000000000003,
14126
+ input: 0.42,
14127
+ output: 3,
13588
14128
  cacheRead: 0.08499999999999999,
13589
- cacheWrite: 0.53125,
14129
+ cacheWrite: 0,
13590
14130
  },
13591
14131
  contextWindow: 1000000,
13592
14132
  maxTokens: 131072,
@@ -13753,9 +14293,9 @@ export const MODELS = {
13753
14293
  reasoning: true,
13754
14294
  input: ["text"],
13755
14295
  cost: {
13756
- input: 0.0825,
13757
- output: 0.33,
13758
- cacheRead: 0.020625,
14296
+ input: 0.13199999999999998,
14297
+ output: 0.5279999999999999,
14298
+ cacheRead: 0.032999999999999995,
13759
14299
  cacheWrite: 0,
13760
14300
  },
13761
14301
  contextWindow: 262144,
@@ -13821,13 +14361,13 @@ export const MODELS = {
13821
14361
  reasoning: true,
13822
14362
  input: ["text", "image"],
13823
14363
  cost: {
13824
- input: 0.95,
14364
+ input: 1,
13825
14365
  output: 4.05,
13826
- cacheRead: 0.16,
14366
+ cacheRead: 0.16999999999999998,
13827
14367
  cacheWrite: 0,
13828
14368
  },
13829
14369
  contextWindow: 1048576,
13830
- maxTokens: 262144,
14370
+ maxTokens: 471859,
13831
14371
  },
13832
14372
  "thinkingmachines/inkling-small": {
13833
14373
  id: "thinkingmachines/inkling-small",
@@ -13982,6 +14522,23 @@ export const MODELS = {
13982
14522
  contextWindow: 1000000,
13983
14523
  maxTokens: 900000,
13984
14524
  },
14525
+ "x-ai/grok-4.3:batch": {
14526
+ id: "x-ai/grok-4.3:batch",
14527
+ name: "SpaceXAI: Grok 4.3 (batch)",
14528
+ api: "openai-completions",
14529
+ provider: "openrouter",
14530
+ baseUrl: "https://openrouter.ai/api/v1",
14531
+ reasoning: true,
14532
+ input: ["text", "image"],
14533
+ cost: {
14534
+ input: 1,
14535
+ output: 2,
14536
+ cacheRead: 0.16,
14537
+ cacheWrite: 0,
14538
+ },
14539
+ contextWindow: 1000000,
14540
+ maxTokens: 900000,
14541
+ },
13985
14542
  "x-ai/grok-4.5": {
13986
14543
  id: "x-ai/grok-4.5",
13987
14544
  name: "SpaceXAI: Grok 4.5",
@@ -14127,13 +14684,13 @@ export const MODELS = {
14127
14684
  reasoning: true,
14128
14685
  input: ["text"],
14129
14686
  cost: {
14130
- input: 0.43,
14131
- output: 1.75,
14132
- cacheRead: 0.08,
14687
+ input: 0.55,
14688
+ output: 2.2,
14689
+ cacheRead: 0.11,
14133
14690
  cacheWrite: 0,
14134
14691
  },
14135
14692
  contextWindow: 204800,
14136
- maxTokens: 16384,
14693
+ maxTokens: 131072,
14137
14694
  },
14138
14695
  "z-ai/glm-4.6v": {
14139
14696
  id: "z-ai/glm-4.6v",
@@ -14229,13 +14786,13 @@ export const MODELS = {
14229
14786
  reasoning: true,
14230
14787
  input: ["text"],
14231
14788
  cost: {
14232
- input: 1.26,
14233
- output: 3.9600000000000004,
14234
- cacheRead: 0.234,
14789
+ input: 0.966,
14790
+ output: 3.036,
14791
+ cacheRead: 0.1794,
14235
14792
  cacheWrite: 0,
14236
14793
  },
14237
14794
  contextWindow: 204800,
14238
- maxTokens: 182476,
14795
+ maxTokens: 128000,
14239
14796
  },
14240
14797
  "z-ai/glm-5.2": {
14241
14798
  id: "z-ai/glm-5.2",
@@ -14246,13 +14803,13 @@ export const MODELS = {
14246
14803
  reasoning: true,
14247
14804
  input: ["text"],
14248
14805
  cost: {
14249
- input: 1.19,
14250
- output: 3.74,
14251
- cacheRead: 0.221,
14806
+ input: 0.966,
14807
+ output: 3.036,
14808
+ cacheRead: 0.1932,
14252
14809
  cacheWrite: 0,
14253
14810
  },
14254
14811
  contextWindow: 1048576,
14255
- maxTokens: 262144,
14812
+ maxTokens: 131072,
14256
14813
  },
14257
14814
  "z-ai/glm-5.2:free": {
14258
14815
  id: "z-ai/glm-5.2:free",
@@ -14282,11 +14839,11 @@ export const MODELS = {
14282
14839
  cost: {
14283
14840
  input: 1.4,
14284
14841
  output: 4.4,
14285
- cacheRead: 0.26,
14842
+ cacheRead: 0.14,
14286
14843
  cacheWrite: 0,
14287
14844
  },
14288
14845
  contextWindow: 1310720,
14289
- maxTokens: 131072,
14846
+ maxTokens: 262144,
14290
14847
  },
14291
14848
  "z-ai/glm-5.3-flash": {
14292
14849
  id: "z-ai/glm-5.3-flash",
@@ -14350,7 +14907,7 @@ export const MODELS = {
14350
14907
  cost: {
14351
14908
  input: 10,
14352
14909
  output: 50,
14353
- cacheRead: 1,
14910
+ cacheRead: 0.25,
14354
14911
  cacheWrite: 12.5,
14355
14912
  },
14356
14913
  contextWindow: 1000000,
@@ -14416,13 +14973,13 @@ export const MODELS = {
14416
14973
  reasoning: true,
14417
14974
  input: ["text"],
14418
14975
  cost: {
14419
- input: 0.03,
14420
- output: 0.09999999999999999,
14421
- cacheRead: 0.007,
14976
+ input: 0.049999999999999996,
14977
+ output: 0.16,
14978
+ cacheRead: 0.013000000000000001,
14422
14979
  cacheWrite: 0,
14423
14980
  },
14424
14981
  contextWindow: 1310720,
14425
- maxTokens: 131072,
14982
+ maxTokens: 393216,
14426
14983
  },
14427
14984
  "~google/gemini-flash-latest": {
14428
14985
  id: "~google/gemini-flash-latest",
@@ -14467,9 +15024,9 @@ export const MODELS = {
14467
15024
  reasoning: true,
14468
15025
  input: ["text", "image"],
14469
15026
  cost: {
14470
- input: 2.5500000000000003,
14471
- output: 12.75,
14472
- cacheRead: 0.25599998999999996,
15027
+ input: 2.5,
15028
+ output: 14,
15029
+ cacheRead: 0.29,
14473
15030
  cacheWrite: 0,
14474
15031
  },
14475
15032
  contextWindow: 1048576,
@@ -14526,6 +15083,23 @@ export const MODELS = {
14526
15083
  contextWindow: 500000,
14527
15084
  maxTokens: 450000,
14528
15085
  },
15086
+ "~z-ai/glm-flash-latest": {
15087
+ id: "~z-ai/glm-flash-latest",
15088
+ name: "Z.ai: GLM Flash Latest",
15089
+ api: "openai-completions",
15090
+ provider: "openrouter",
15091
+ baseUrl: "https://openrouter.ai/api/v1",
15092
+ reasoning: true,
15093
+ input: ["text", "image"],
15094
+ cost: {
15095
+ input: 0.075,
15096
+ output: 0.25,
15097
+ cacheRead: 0.015,
15098
+ cacheWrite: 0,
15099
+ },
15100
+ contextWindow: 1310720,
15101
+ maxTokens: 943718,
15102
+ },
14529
15103
  "~z-ai/glm-latest": {
14530
15104
  id: "~z-ai/glm-latest",
14531
15105
  name: "Z.ai: GLM Latest",
@@ -14535,13 +15109,13 @@ export const MODELS = {
14535
15109
  reasoning: true,
14536
15110
  input: ["text"],
14537
15111
  cost: {
14538
- input: 1.25,
14539
- output: 4.4,
14540
- cacheRead: 0.26,
15112
+ input: 1.15,
15113
+ output: 3.5,
15114
+ cacheRead: 0.09999999999999999,
14541
15115
  cacheWrite: 0,
14542
15116
  },
14543
15117
  contextWindow: 1310720,
14544
- maxTokens: 131072,
15118
+ maxTokens: 235929,
14545
15119
  },
14546
15120
  },
14547
15121
  "vercel-ai-gateway": {
@@ -14996,10 +15570,10 @@ export const MODELS = {
14996
15570
  reasoning: true,
14997
15571
  input: ["text", "image"],
14998
15572
  cost: {
14999
- input: 0.55,
15000
- output: 3.3000000000000003,
15001
- cacheRead: 0.11,
15002
- cacheWrite: 0,
15573
+ input: 0.5,
15574
+ output: 3,
15575
+ cacheRead: 0.09999999999999999,
15576
+ cacheWrite: 0.625,
15003
15577
  },
15004
15578
  contextWindow: 1000000,
15005
15579
  maxTokens: 131072,
@@ -15021,6 +15595,23 @@ export const MODELS = {
15021
15595
  contextWindow: 991000,
15022
15596
  maxTokens: 128000,
15023
15597
  },
15598
+ "alibaba/qwen3.8-flash-next": {
15599
+ id: "alibaba/qwen3.8-flash-next",
15600
+ name: "Qwen 3.8 Flash Next",
15601
+ api: "anthropic-messages",
15602
+ provider: "vercel-ai-gateway",
15603
+ baseUrl: "https://ai-gateway.vercel.sh",
15604
+ reasoning: true,
15605
+ input: ["text", "image"],
15606
+ cost: {
15607
+ input: 0.12,
15608
+ output: 0.39999999999999997,
15609
+ cacheRead: 0.01,
15610
+ cacheWrite: 0,
15611
+ },
15612
+ contextWindow: 1048576,
15613
+ maxTokens: 1048576,
15614
+ },
15024
15615
  "alibaba/qwen3.8-max": {
15025
15616
  id: "alibaba/qwen3.8-max",
15026
15617
  name: "Qwen 3.8 Max",
@@ -15038,6 +15629,23 @@ export const MODELS = {
15038
15629
  contextWindow: 1000000,
15039
15630
  maxTokens: 128000,
15040
15631
  },
15632
+ "alibaba/qwen3.8-max-0902": {
15633
+ id: "alibaba/qwen3.8-max-0902",
15634
+ name: "Qwen3.8 Max 0902",
15635
+ api: "anthropic-messages",
15636
+ provider: "vercel-ai-gateway",
15637
+ baseUrl: "https://ai-gateway.vercel.sh",
15638
+ reasoning: true,
15639
+ input: ["text", "image"],
15640
+ cost: {
15641
+ input: 2,
15642
+ output: 6,
15643
+ cacheRead: 0.25,
15644
+ cacheWrite: 2.5,
15645
+ },
15646
+ contextWindow: 991000,
15647
+ maxTokens: 128000,
15648
+ },
15041
15649
  "amazon/nova-2-lite": {
15042
15650
  id: "amazon/nova-2-lite",
15043
15651
  name: "Nova 2 Lite",
@@ -15140,6 +15748,23 @@ export const MODELS = {
15140
15748
  contextWindow: 1000000,
15141
15749
  maxTokens: 128000,
15142
15750
  },
15751
+ "anthropic/claude-fable-5.1": {
15752
+ id: "anthropic/claude-fable-5.1",
15753
+ name: "Claude Fable 5.1",
15754
+ api: "anthropic-messages",
15755
+ provider: "vercel-ai-gateway",
15756
+ baseUrl: "https://ai-gateway.vercel.sh",
15757
+ reasoning: true,
15758
+ input: ["text", "image"],
15759
+ cost: {
15760
+ input: 10,
15761
+ output: 50,
15762
+ cacheRead: 0.25,
15763
+ cacheWrite: 12.5,
15764
+ },
15765
+ contextWindow: 1000000,
15766
+ maxTokens: 128000,
15767
+ },
15143
15768
  "anthropic/claude-haiku-4.5": {
15144
15769
  id: "anthropic/claude-haiku-4.5",
15145
15770
  name: "Claude Haiku 4.5",
@@ -15446,23 +16071,6 @@ export const MODELS = {
15446
16071
  contextWindow: 128000,
15447
16072
  maxTokens: 8192,
15448
16073
  },
15449
- "deepseek/deepseek-v3": {
15450
- id: "deepseek/deepseek-v3",
15451
- name: "DeepSeek V3 0324",
15452
- api: "anthropic-messages",
15453
- provider: "vercel-ai-gateway",
15454
- baseUrl: "https://ai-gateway.vercel.sh",
15455
- reasoning: false,
15456
- input: ["text"],
15457
- cost: {
15458
- input: 0.27,
15459
- output: 1.12,
15460
- cacheRead: 0.135,
15461
- cacheWrite: 0,
15462
- },
15463
- contextWindow: 163840,
15464
- maxTokens: 163840,
15465
- },
15466
16074
  "deepseek/deepseek-v3.1": {
15467
16075
  id: "deepseek/deepseek-v3.1",
15468
16076
  name: "DeepSeek V3.1",
@@ -15579,8 +16187,8 @@ export const MODELS = {
15579
16187
  cacheRead: 0.007,
15580
16188
  cacheWrite: 0,
15581
16189
  },
15582
- contextWindow: 1000000,
15583
- maxTokens: 384000,
16190
+ contextWindow: 1048576,
16191
+ maxTokens: 1048576,
15584
16192
  },
15585
16193
  "deepseek/deepseek-v4-pro": {
15586
16194
  id: "deepseek/deepseek-v4-pro",
@@ -15786,6 +16394,23 @@ export const MODELS = {
15786
16394
  contextWindow: 1000000,
15787
16395
  maxTokens: 65536,
15788
16396
  },
16397
+ "google/gemini-3.8-flash": {
16398
+ id: "google/gemini-3.8-flash",
16399
+ name: "Gemini 3.8 Flash",
16400
+ api: "anthropic-messages",
16401
+ provider: "vercel-ai-gateway",
16402
+ baseUrl: "https://ai-gateway.vercel.sh",
16403
+ reasoning: true,
16404
+ input: ["text", "image"],
16405
+ cost: {
16406
+ input: 0.75,
16407
+ output: 3.75,
16408
+ cacheRead: 0.075,
16409
+ cacheWrite: 0,
16410
+ },
16411
+ contextWindow: 1000000,
16412
+ maxTokens: 65536,
16413
+ },
15789
16414
  "google/gemma-4-26b-a4b-it": {
15790
16415
  id: "google/gemma-4-26b-a4b-it",
15791
16416
  name: "Google Gemma 4 26B A4B",
@@ -16143,6 +16768,40 @@ export const MODELS = {
16143
16768
  contextWindow: 1048576,
16144
16769
  maxTokens: 1048576,
16145
16770
  },
16771
+ "meta/muse-spark-1.3": {
16772
+ id: "meta/muse-spark-1.3",
16773
+ name: "Muse Spark 1.3",
16774
+ api: "anthropic-messages",
16775
+ provider: "vercel-ai-gateway",
16776
+ baseUrl: "https://ai-gateway.vercel.sh",
16777
+ reasoning: true,
16778
+ input: ["text", "image"],
16779
+ cost: {
16780
+ input: 1.25,
16781
+ output: 4.25,
16782
+ cacheRead: 0.15,
16783
+ cacheWrite: 0,
16784
+ },
16785
+ contextWindow: 1048576,
16786
+ maxTokens: 1048576,
16787
+ },
16788
+ "meta/muse-spark-1.3-contributor": {
16789
+ id: "meta/muse-spark-1.3-contributor",
16790
+ name: "Muse Spark 1.3 Contributor",
16791
+ api: "anthropic-messages",
16792
+ provider: "vercel-ai-gateway",
16793
+ baseUrl: "https://ai-gateway.vercel.sh",
16794
+ reasoning: true,
16795
+ input: ["text", "image"],
16796
+ cost: {
16797
+ input: 0.09999999999999999,
16798
+ output: 0.19999999999999998,
16799
+ cacheRead: 0.002,
16800
+ cacheWrite: 0,
16801
+ },
16802
+ contextWindow: 1048576,
16803
+ maxTokens: 1048576,
16804
+ },
16146
16805
  "minimax/minimax-m2": {
16147
16806
  id: "minimax/minimax-m2",
16148
16807
  name: "MiniMax M2",
@@ -18115,6 +18774,23 @@ export const MODELS = {
18115
18774
  contextWindow: 1050000,
18116
18775
  maxTokens: 131000,
18117
18776
  },
18777
+ "xiaomi/mimo-v2.5-pro-ultraspeed": {
18778
+ id: "xiaomi/mimo-v2.5-pro-ultraspeed",
18779
+ name: "MiMo V2.5 Pro UltraSpeed",
18780
+ api: "anthropic-messages",
18781
+ provider: "vercel-ai-gateway",
18782
+ baseUrl: "https://ai-gateway.vercel.sh",
18783
+ reasoning: true,
18784
+ input: ["text"],
18785
+ cost: {
18786
+ input: 1.305,
18787
+ output: 2.61,
18788
+ cacheRead: 0.0108,
18789
+ cacheWrite: 0,
18790
+ },
18791
+ contextWindow: 1048576,
18792
+ maxTokens: 131072,
18793
+ },
18118
18794
  "zai/glm-4.5": {
18119
18795
  id: "zai/glm-4.5",
18120
18796
  name: "GLM 4.5",
@@ -18328,14 +19004,31 @@ export const MODELS = {
18328
19004
  reasoning: true,
18329
19005
  input: ["text"],
18330
19006
  cost: {
18331
- input: 1.4,
18332
- output: 4.4,
18333
- cacheRead: 0.14,
19007
+ input: 0.7,
19008
+ output: 2.2,
19009
+ cacheRead: 0.13,
18334
19010
  cacheWrite: 0,
18335
19011
  },
18336
19012
  contextWindow: 1000000,
18337
19013
  maxTokens: 1000000,
18338
19014
  },
19015
+ "zai/glm-5.3-fast": {
19016
+ id: "zai/glm-5.3-fast",
19017
+ name: "GLM 5.3 Fast",
19018
+ api: "anthropic-messages",
19019
+ provider: "vercel-ai-gateway",
19020
+ baseUrl: "https://ai-gateway.vercel.sh",
19021
+ reasoning: true,
19022
+ input: ["text"],
19023
+ cost: {
19024
+ input: 2.0999999999999996,
19025
+ output: 6.6000000000000005,
19026
+ cacheRead: 0.21,
19027
+ cacheWrite: 0,
19028
+ },
19029
+ contextWindow: 1048576,
19030
+ maxTokens: 262144,
19031
+ },
18339
19032
  "zai/glm-5.3-flash": {
18340
19033
  id: "zai/glm-5.3-flash",
18341
19034
  name: "GLM 5.3 Flash",
@@ -18353,6 +19046,23 @@ export const MODELS = {
18353
19046
  contextWindow: 1000000,
18354
19047
  maxTokens: 131000,
18355
19048
  },
19049
+ "zai/glm-5.3-promo-50": {
19050
+ id: "zai/glm-5.3-promo-50",
19051
+ name: "GLM 5.3 (50% off)",
19052
+ api: "anthropic-messages",
19053
+ provider: "vercel-ai-gateway",
19054
+ baseUrl: "https://ai-gateway.vercel.sh",
19055
+ reasoning: true,
19056
+ input: ["text"],
19057
+ cost: {
19058
+ input: 0.7,
19059
+ output: 2.2,
19060
+ cacheRead: 0.13,
19061
+ cacheWrite: 0,
19062
+ },
19063
+ contextWindow: 1048576,
19064
+ maxTokens: 1048576,
19065
+ },
18356
19066
  "zai/glm-5v-turbo": {
18357
19067
  id: "zai/glm-5v-turbo",
18358
19068
  name: "GLM 5V Turbo",