@elyracode/ai 0.9.29 → 0.9.31

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.
@@ -2985,74 +2985,6 @@ export const MODELS = {
2985
2985
  },
2986
2986
  },
2987
2987
  "cloudflare-ai-gateway": {
2988
- "claude-3-haiku": {
2989
- id: "claude-3-haiku",
2990
- name: "Claude Haiku 3",
2991
- api: "anthropic-messages",
2992
- provider: "cloudflare-ai-gateway",
2993
- baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
2994
- reasoning: false,
2995
- input: ["text", "image"],
2996
- cost: {
2997
- input: 0.25,
2998
- output: 1.25,
2999
- cacheRead: 0.03,
3000
- cacheWrite: 0.3,
3001
- },
3002
- contextWindow: 200000,
3003
- maxTokens: 4096,
3004
- },
3005
- "claude-3-opus": {
3006
- id: "claude-3-opus",
3007
- name: "Claude Opus 3",
3008
- api: "anthropic-messages",
3009
- provider: "cloudflare-ai-gateway",
3010
- baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
3011
- reasoning: false,
3012
- input: ["text", "image"],
3013
- cost: {
3014
- input: 15,
3015
- output: 75,
3016
- cacheRead: 1.5,
3017
- cacheWrite: 18.75,
3018
- },
3019
- contextWindow: 200000,
3020
- maxTokens: 4096,
3021
- },
3022
- "claude-3-sonnet": {
3023
- id: "claude-3-sonnet",
3024
- name: "Claude Sonnet 3",
3025
- api: "anthropic-messages",
3026
- provider: "cloudflare-ai-gateway",
3027
- baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
3028
- reasoning: false,
3029
- input: ["text", "image"],
3030
- cost: {
3031
- input: 3,
3032
- output: 15,
3033
- cacheRead: 0.3,
3034
- cacheWrite: 0.3,
3035
- },
3036
- contextWindow: 200000,
3037
- maxTokens: 4096,
3038
- },
3039
- "claude-3.5-sonnet": {
3040
- id: "claude-3.5-sonnet",
3041
- name: "Claude Sonnet 3.5 v2",
3042
- api: "anthropic-messages",
3043
- provider: "cloudflare-ai-gateway",
3044
- baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
3045
- reasoning: false,
3046
- input: ["text", "image"],
3047
- cost: {
3048
- input: 3,
3049
- output: 15,
3050
- cacheRead: 0.3,
3051
- cacheWrite: 3.75,
3052
- },
3053
- contextWindow: 200000,
3054
- maxTokens: 8192,
3055
- },
3056
2988
  "claude-fable-5": {
3057
2989
  id: "claude-fable-5",
3058
2990
  name: "Claude Fable 5",
@@ -3088,40 +3020,6 @@ export const MODELS = {
3088
3020
  contextWindow: 200000,
3089
3021
  maxTokens: 64000,
3090
3022
  },
3091
- "claude-opus-4": {
3092
- id: "claude-opus-4",
3093
- name: "Claude Opus 4 (latest)",
3094
- api: "anthropic-messages",
3095
- provider: "cloudflare-ai-gateway",
3096
- baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
3097
- reasoning: true,
3098
- input: ["text", "image"],
3099
- cost: {
3100
- input: 15,
3101
- output: 75,
3102
- cacheRead: 1.5,
3103
- cacheWrite: 18.75,
3104
- },
3105
- contextWindow: 200000,
3106
- maxTokens: 32000,
3107
- },
3108
- "claude-opus-4-1": {
3109
- id: "claude-opus-4-1",
3110
- name: "Claude Opus 4.1 (latest)",
3111
- api: "anthropic-messages",
3112
- provider: "cloudflare-ai-gateway",
3113
- baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
3114
- reasoning: true,
3115
- input: ["text", "image"],
3116
- cost: {
3117
- input: 15,
3118
- output: 75,
3119
- cacheRead: 1.5,
3120
- cacheWrite: 18.75,
3121
- },
3122
- contextWindow: 200000,
3123
- maxTokens: 32000,
3124
- },
3125
3023
  "claude-opus-4-5": {
3126
3024
  id: "claude-opus-4-5",
3127
3025
  name: "Claude Opus 4.5 (latest)",
@@ -3141,7 +3039,7 @@ export const MODELS = {
3141
3039
  },
3142
3040
  "claude-opus-4-6": {
3143
3041
  id: "claude-opus-4-6",
3144
- name: "Claude Opus 4.6 (latest)",
3042
+ name: "Claude Opus 4.6",
3145
3043
  api: "anthropic-messages",
3146
3044
  provider: "cloudflare-ai-gateway",
3147
3045
  baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
@@ -3210,23 +3108,6 @@ export const MODELS = {
3210
3108
  contextWindow: 1000000,
3211
3109
  maxTokens: 128000,
3212
3110
  },
3213
- "claude-sonnet-4": {
3214
- id: "claude-sonnet-4",
3215
- name: "Claude Sonnet 4 (latest)",
3216
- api: "anthropic-messages",
3217
- provider: "cloudflare-ai-gateway",
3218
- baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
3219
- reasoning: true,
3220
- input: ["text", "image"],
3221
- cost: {
3222
- input: 3,
3223
- output: 15,
3224
- cacheRead: 0.3,
3225
- cacheWrite: 3.75,
3226
- },
3227
- contextWindow: 200000,
3228
- maxTokens: 64000,
3229
- },
3230
3111
  "claude-sonnet-4-5": {
3231
3112
  id: "claude-sonnet-4-5",
3232
3113
  name: "Claude Sonnet 4.5 (latest)",
@@ -3241,7 +3122,7 @@ export const MODELS = {
3241
3122
  cacheRead: 0.3,
3242
3123
  cacheWrite: 3.75,
3243
3124
  },
3244
- contextWindow: 200000,
3125
+ contextWindow: 1000000,
3245
3126
  maxTokens: 64000,
3246
3127
  },
3247
3128
  "claude-sonnet-4-6": {
@@ -3259,7 +3140,7 @@ export const MODELS = {
3259
3140
  cacheWrite: 3.75,
3260
3141
  },
3261
3142
  contextWindow: 1000000,
3262
- maxTokens: 64000,
3143
+ maxTokens: 128000,
3263
3144
  },
3264
3145
  "claude-sonnet-5": {
3265
3146
  id: "claude-sonnet-5",
@@ -3295,6 +3176,57 @@ export const MODELS = {
3295
3176
  contextWindow: 8192,
3296
3177
  maxTokens: 8192,
3297
3178
  },
3179
+ "gpt-4.1": {
3180
+ id: "gpt-4.1",
3181
+ name: "GPT-4.1",
3182
+ api: "openai-responses",
3183
+ provider: "cloudflare-ai-gateway",
3184
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
3185
+ reasoning: false,
3186
+ input: ["text", "image"],
3187
+ cost: {
3188
+ input: 2,
3189
+ output: 8,
3190
+ cacheRead: 0.5,
3191
+ cacheWrite: 0,
3192
+ },
3193
+ contextWindow: 1047576,
3194
+ maxTokens: 32768,
3195
+ },
3196
+ "gpt-4.1-mini": {
3197
+ id: "gpt-4.1-mini",
3198
+ name: "GPT-4.1 mini",
3199
+ api: "openai-responses",
3200
+ provider: "cloudflare-ai-gateway",
3201
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
3202
+ reasoning: false,
3203
+ input: ["text", "image"],
3204
+ cost: {
3205
+ input: 0.4,
3206
+ output: 1.6,
3207
+ cacheRead: 0.1,
3208
+ cacheWrite: 0,
3209
+ },
3210
+ contextWindow: 1047576,
3211
+ maxTokens: 32768,
3212
+ },
3213
+ "gpt-4.1-nano": {
3214
+ id: "gpt-4.1-nano",
3215
+ name: "GPT-4.1 nano",
3216
+ api: "openai-responses",
3217
+ provider: "cloudflare-ai-gateway",
3218
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
3219
+ reasoning: false,
3220
+ input: ["text", "image"],
3221
+ cost: {
3222
+ input: 0.1,
3223
+ output: 0.4,
3224
+ cacheRead: 0.025,
3225
+ cacheWrite: 0,
3226
+ },
3227
+ contextWindow: 1047576,
3228
+ maxTokens: 32768,
3229
+ },
3298
3230
  "gpt-4o": {
3299
3231
  id: "gpt-4o",
3300
3232
  name: "GPT-4o",
@@ -3323,15 +3255,15 @@ export const MODELS = {
3323
3255
  cost: {
3324
3256
  input: 0.15,
3325
3257
  output: 0.6,
3326
- cacheRead: 0.08,
3258
+ cacheRead: 0.075,
3327
3259
  cacheWrite: 0,
3328
3260
  },
3329
3261
  contextWindow: 128000,
3330
3262
  maxTokens: 16384,
3331
3263
  },
3332
- "gpt-5.1": {
3333
- id: "gpt-5.1",
3334
- name: "GPT-5.1",
3264
+ "gpt-5": {
3265
+ id: "gpt-5",
3266
+ name: "GPT-5",
3335
3267
  api: "openai-responses",
3336
3268
  provider: "cloudflare-ai-gateway",
3337
3269
  baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
@@ -3341,15 +3273,69 @@ export const MODELS = {
3341
3273
  cost: {
3342
3274
  input: 1.25,
3343
3275
  output: 10,
3344
- cacheRead: 0.13,
3276
+ cacheRead: 0.125,
3345
3277
  cacheWrite: 0,
3346
3278
  },
3347
3279
  contextWindow: 400000,
3348
3280
  maxTokens: 128000,
3349
3281
  },
3350
- "gpt-5.1-codex": {
3351
- id: "gpt-5.1-codex",
3352
- name: "GPT-5.1 Codex",
3282
+ "gpt-5-mini": {
3283
+ id: "gpt-5-mini",
3284
+ name: "GPT-5 Mini",
3285
+ api: "openai-responses",
3286
+ provider: "cloudflare-ai-gateway",
3287
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
3288
+ reasoning: true,
3289
+ thinkingLevelMap: { "off": null },
3290
+ input: ["text", "image"],
3291
+ cost: {
3292
+ input: 0.25,
3293
+ output: 2,
3294
+ cacheRead: 0.025,
3295
+ cacheWrite: 0,
3296
+ },
3297
+ contextWindow: 400000,
3298
+ maxTokens: 128000,
3299
+ },
3300
+ "gpt-5-nano": {
3301
+ id: "gpt-5-nano",
3302
+ name: "GPT-5 Nano",
3303
+ api: "openai-responses",
3304
+ provider: "cloudflare-ai-gateway",
3305
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
3306
+ reasoning: true,
3307
+ thinkingLevelMap: { "off": null },
3308
+ input: ["text", "image"],
3309
+ cost: {
3310
+ input: 0.05,
3311
+ output: 0.4,
3312
+ cacheRead: 0.005,
3313
+ cacheWrite: 0,
3314
+ },
3315
+ contextWindow: 400000,
3316
+ maxTokens: 128000,
3317
+ },
3318
+ "gpt-5-pro": {
3319
+ id: "gpt-5-pro",
3320
+ name: "GPT-5 Pro",
3321
+ api: "openai-responses",
3322
+ provider: "cloudflare-ai-gateway",
3323
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
3324
+ reasoning: true,
3325
+ thinkingLevelMap: { "off": null },
3326
+ input: ["text", "image"],
3327
+ cost: {
3328
+ input: 15,
3329
+ output: 120,
3330
+ cacheRead: 0,
3331
+ cacheWrite: 0,
3332
+ },
3333
+ contextWindow: 400000,
3334
+ maxTokens: 272000,
3335
+ },
3336
+ "gpt-5.1": {
3337
+ id: "gpt-5.1",
3338
+ name: "GPT-5.1",
3353
3339
  api: "openai-responses",
3354
3340
  provider: "cloudflare-ai-gateway",
3355
3341
  baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
@@ -3383,9 +3369,9 @@ export const MODELS = {
3383
3369
  contextWindow: 400000,
3384
3370
  maxTokens: 128000,
3385
3371
  },
3386
- "gpt-5.2-codex": {
3387
- id: "gpt-5.2-codex",
3388
- name: "GPT-5.2 Codex",
3372
+ "gpt-5.2-chat-latest": {
3373
+ id: "gpt-5.2-chat-latest",
3374
+ name: "GPT-5.2 Chat",
3389
3375
  api: "openai-responses",
3390
3376
  provider: "cloudflare-ai-gateway",
3391
3377
  baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
@@ -3398,9 +3384,45 @@ export const MODELS = {
3398
3384
  cacheRead: 0.175,
3399
3385
  cacheWrite: 0,
3400
3386
  },
3387
+ contextWindow: 128000,
3388
+ maxTokens: 16384,
3389
+ },
3390
+ "gpt-5.2-pro": {
3391
+ id: "gpt-5.2-pro",
3392
+ name: "GPT-5.2 Pro",
3393
+ api: "openai-responses",
3394
+ provider: "cloudflare-ai-gateway",
3395
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
3396
+ reasoning: true,
3397
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
3398
+ input: ["text", "image"],
3399
+ cost: {
3400
+ input: 21,
3401
+ output: 168,
3402
+ cacheRead: 0,
3403
+ cacheWrite: 0,
3404
+ },
3401
3405
  contextWindow: 400000,
3402
3406
  maxTokens: 128000,
3403
3407
  },
3408
+ "gpt-5.3-chat-latest": {
3409
+ id: "gpt-5.3-chat-latest",
3410
+ name: "GPT-5.3 Chat (latest)",
3411
+ api: "openai-responses",
3412
+ provider: "cloudflare-ai-gateway",
3413
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
3414
+ reasoning: false,
3415
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
3416
+ input: ["text", "image"],
3417
+ cost: {
3418
+ input: 1.75,
3419
+ output: 14,
3420
+ cacheRead: 0.175,
3421
+ cacheWrite: 0,
3422
+ },
3423
+ contextWindow: 128000,
3424
+ maxTokens: 16384,
3425
+ },
3404
3426
  "gpt-5.3-codex": {
3405
3427
  id: "gpt-5.3-codex",
3406
3428
  name: "GPT-5.3 Codex",
@@ -3419,6 +3441,24 @@ export const MODELS = {
3419
3441
  contextWindow: 400000,
3420
3442
  maxTokens: 128000,
3421
3443
  },
3444
+ "gpt-5.3-codex-spark": {
3445
+ id: "gpt-5.3-codex-spark",
3446
+ name: "GPT-5.3 Codex Spark",
3447
+ api: "openai-responses",
3448
+ provider: "cloudflare-ai-gateway",
3449
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
3450
+ reasoning: true,
3451
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
3452
+ input: ["text", "image"],
3453
+ cost: {
3454
+ input: 1.75,
3455
+ output: 14,
3456
+ cacheRead: 0.175,
3457
+ cacheWrite: 0,
3458
+ },
3459
+ contextWindow: 128000,
3460
+ maxTokens: 32000,
3461
+ },
3422
3462
  "gpt-5.4": {
3423
3463
  id: "gpt-5.4",
3424
3464
  name: "GPT-5.4",
@@ -3437,6 +3477,60 @@ export const MODELS = {
3437
3477
  contextWindow: 1050000,
3438
3478
  maxTokens: 128000,
3439
3479
  },
3480
+ "gpt-5.4-mini": {
3481
+ id: "gpt-5.4-mini",
3482
+ name: "GPT-5.4 mini",
3483
+ api: "openai-responses",
3484
+ provider: "cloudflare-ai-gateway",
3485
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
3486
+ reasoning: true,
3487
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
3488
+ input: ["text", "image"],
3489
+ cost: {
3490
+ input: 0.75,
3491
+ output: 4.5,
3492
+ cacheRead: 0.075,
3493
+ cacheWrite: 0,
3494
+ },
3495
+ contextWindow: 400000,
3496
+ maxTokens: 128000,
3497
+ },
3498
+ "gpt-5.4-nano": {
3499
+ id: "gpt-5.4-nano",
3500
+ name: "GPT-5.4 nano",
3501
+ api: "openai-responses",
3502
+ provider: "cloudflare-ai-gateway",
3503
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
3504
+ reasoning: true,
3505
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
3506
+ input: ["text", "image"],
3507
+ cost: {
3508
+ input: 0.2,
3509
+ output: 1.25,
3510
+ cacheRead: 0.02,
3511
+ cacheWrite: 0,
3512
+ },
3513
+ contextWindow: 400000,
3514
+ maxTokens: 128000,
3515
+ },
3516
+ "gpt-5.4-pro": {
3517
+ id: "gpt-5.4-pro",
3518
+ name: "GPT-5.4 Pro",
3519
+ api: "openai-responses",
3520
+ provider: "cloudflare-ai-gateway",
3521
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
3522
+ reasoning: true,
3523
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
3524
+ input: ["text", "image"],
3525
+ cost: {
3526
+ input: 30,
3527
+ output: 180,
3528
+ cacheRead: 0,
3529
+ cacheWrite: 0,
3530
+ },
3531
+ contextWindow: 1050000,
3532
+ maxTokens: 128000,
3533
+ },
3440
3534
  "gpt-5.5": {
3441
3535
  id: "gpt-5.5",
3442
3536
  name: "GPT-5.5",
@@ -3455,6 +3549,42 @@ export const MODELS = {
3455
3549
  contextWindow: 1050000,
3456
3550
  maxTokens: 128000,
3457
3551
  },
3552
+ "gpt-5.5-pro": {
3553
+ id: "gpt-5.5-pro",
3554
+ name: "GPT-5.5 Pro",
3555
+ api: "openai-responses",
3556
+ provider: "cloudflare-ai-gateway",
3557
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
3558
+ reasoning: true,
3559
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
3560
+ input: ["text", "image"],
3561
+ cost: {
3562
+ input: 30,
3563
+ output: 180,
3564
+ cacheRead: 0,
3565
+ cacheWrite: 0,
3566
+ },
3567
+ contextWindow: 1050000,
3568
+ maxTokens: 128000,
3569
+ },
3570
+ "gpt-5.6": {
3571
+ id: "gpt-5.6",
3572
+ name: "GPT-5.6",
3573
+ api: "openai-responses",
3574
+ provider: "cloudflare-ai-gateway",
3575
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
3576
+ reasoning: true,
3577
+ thinkingLevelMap: { "off": null },
3578
+ input: ["text", "image"],
3579
+ cost: {
3580
+ input: 5,
3581
+ output: 30,
3582
+ cacheRead: 0.5,
3583
+ cacheWrite: 6.25,
3584
+ },
3585
+ contextWindow: 1050000,
3586
+ maxTokens: 128000,
3587
+ },
3458
3588
  "gpt-5.6-luna": {
3459
3589
  id: "gpt-5.6-luna",
3460
3590
  name: "GPT-5.6 Luna",
@@ -3465,10 +3595,10 @@ export const MODELS = {
3465
3595
  thinkingLevelMap: { "off": null },
3466
3596
  input: ["text", "image"],
3467
3597
  cost: {
3468
- input: 1,
3469
- output: 6,
3470
- cacheRead: 0.1,
3471
- cacheWrite: 0,
3598
+ input: 0.2,
3599
+ output: 1.2,
3600
+ cacheRead: 0.02,
3601
+ cacheWrite: 0.25,
3472
3602
  },
3473
3603
  contextWindow: 1050000,
3474
3604
  maxTokens: 128000,
@@ -3486,7 +3616,7 @@ export const MODELS = {
3486
3616
  input: 5,
3487
3617
  output: 30,
3488
3618
  cacheRead: 0.5,
3489
- cacheWrite: 0,
3619
+ cacheWrite: 6.25,
3490
3620
  },
3491
3621
  contextWindow: 1050000,
3492
3622
  maxTokens: 128000,
@@ -3501,10 +3631,10 @@ export const MODELS = {
3501
3631
  thinkingLevelMap: { "off": null },
3502
3632
  input: ["text", "image"],
3503
3633
  cost: {
3504
- input: 2.5,
3505
- output: 15,
3506
- cacheRead: 0.25,
3507
- cacheWrite: 0,
3634
+ input: 2,
3635
+ output: 12,
3636
+ cacheRead: 0.2,
3637
+ cacheWrite: 2.5,
3508
3638
  },
3509
3639
  contextWindow: 1050000,
3510
3640
  maxTokens: 128000,
@@ -3526,6 +3656,23 @@ export const MODELS = {
3526
3656
  contextWindow: 200000,
3527
3657
  maxTokens: 100000,
3528
3658
  },
3659
+ "o1-pro": {
3660
+ id: "o1-pro",
3661
+ name: "o1-pro",
3662
+ api: "openai-responses",
3663
+ provider: "cloudflare-ai-gateway",
3664
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
3665
+ reasoning: true,
3666
+ input: ["text", "image"],
3667
+ cost: {
3668
+ input: 150,
3669
+ output: 600,
3670
+ cacheRead: 0,
3671
+ cacheWrite: 0,
3672
+ },
3673
+ contextWindow: 200000,
3674
+ maxTokens: 100000,
3675
+ },
3529
3676
  "o3": {
3530
3677
  id: "o3",
3531
3678
  name: "o3",
@@ -3574,29 +3721,119 @@ export const MODELS = {
3574
3721
  cacheRead: 0,
3575
3722
  cacheWrite: 0,
3576
3723
  },
3577
- contextWindow: 200000,
3578
- maxTokens: 100000,
3724
+ contextWindow: 200000,
3725
+ maxTokens: 100000,
3726
+ },
3727
+ "o4-mini": {
3728
+ id: "o4-mini",
3729
+ name: "o4-mini",
3730
+ api: "openai-responses",
3731
+ provider: "cloudflare-ai-gateway",
3732
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
3733
+ reasoning: true,
3734
+ input: ["text", "image"],
3735
+ cost: {
3736
+ input: 1.1,
3737
+ output: 4.4,
3738
+ cacheRead: 0.275,
3739
+ cacheWrite: 0,
3740
+ },
3741
+ contextWindow: 200000,
3742
+ maxTokens: 100000,
3743
+ },
3744
+ "workers-ai/@cf/google/gemma-4-26b-a4b-it": {
3745
+ id: "workers-ai/@cf/google/gemma-4-26b-a4b-it",
3746
+ name: "Gemma 4 26B A4B IT",
3747
+ api: "openai-completions",
3748
+ provider: "cloudflare-ai-gateway",
3749
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
3750
+ compat: { "sendSessionAffinityHeaders": true },
3751
+ reasoning: true,
3752
+ input: ["text", "image"],
3753
+ cost: {
3754
+ input: 0.1,
3755
+ output: 0.3,
3756
+ cacheRead: 0,
3757
+ cacheWrite: 0,
3758
+ },
3759
+ contextWindow: 256000,
3760
+ maxTokens: 16384,
3761
+ },
3762
+ "workers-ai/@cf/ibm-granite/granite-4.0-h-micro": {
3763
+ id: "workers-ai/@cf/ibm-granite/granite-4.0-h-micro",
3764
+ name: "Granite 4.0 H Micro",
3765
+ api: "openai-completions",
3766
+ provider: "cloudflare-ai-gateway",
3767
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
3768
+ compat: { "sendSessionAffinityHeaders": true },
3769
+ reasoning: false,
3770
+ input: ["text"],
3771
+ cost: {
3772
+ input: 0.017,
3773
+ output: 0.112,
3774
+ cacheRead: 0,
3775
+ cacheWrite: 0,
3776
+ },
3777
+ contextWindow: 131000,
3778
+ maxTokens: 131000,
3779
+ },
3780
+ "workers-ai/@cf/meta/llama-3.3-70b-instruct-fp8-fast": {
3781
+ id: "workers-ai/@cf/meta/llama-3.3-70b-instruct-fp8-fast",
3782
+ name: "Llama 3.3 70B Instruct fp8 Fast",
3783
+ api: "openai-completions",
3784
+ provider: "cloudflare-ai-gateway",
3785
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
3786
+ compat: { "sendSessionAffinityHeaders": true },
3787
+ reasoning: false,
3788
+ input: ["text"],
3789
+ cost: {
3790
+ input: 0.293,
3791
+ output: 2.253,
3792
+ cacheRead: 0,
3793
+ cacheWrite: 0,
3794
+ },
3795
+ contextWindow: 24000,
3796
+ maxTokens: 24000,
3797
+ },
3798
+ "workers-ai/@cf/meta/llama-4-scout-17b-16e-instruct": {
3799
+ id: "workers-ai/@cf/meta/llama-4-scout-17b-16e-instruct",
3800
+ name: "Llama 4 Scout 17B 16E Instruct",
3801
+ api: "openai-completions",
3802
+ provider: "cloudflare-ai-gateway",
3803
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
3804
+ compat: { "sendSessionAffinityHeaders": true },
3805
+ reasoning: false,
3806
+ input: ["text", "image"],
3807
+ cost: {
3808
+ input: 0.27,
3809
+ output: 0.85,
3810
+ cacheRead: 0,
3811
+ cacheWrite: 0,
3812
+ },
3813
+ contextWindow: 131000,
3814
+ maxTokens: 16384,
3579
3815
  },
3580
- "o4-mini": {
3581
- id: "o4-mini",
3582
- name: "o4-mini",
3583
- api: "openai-responses",
3816
+ "workers-ai/@cf/mistralai/mistral-small-3.1-24b-instruct": {
3817
+ id: "workers-ai/@cf/mistralai/mistral-small-3.1-24b-instruct",
3818
+ name: "Mistral Small 3.1 24B Instruct",
3819
+ api: "openai-completions",
3584
3820
  provider: "cloudflare-ai-gateway",
3585
- baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
3586
- reasoning: true,
3587
- input: ["text", "image"],
3821
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
3822
+ compat: { "sendSessionAffinityHeaders": true },
3823
+ reasoning: false,
3824
+ input: ["text"],
3588
3825
  cost: {
3589
- input: 1.1,
3590
- output: 4.4,
3591
- cacheRead: 0.28,
3826
+ input: 0.351,
3827
+ output: 0.555,
3828
+ cacheRead: 0,
3592
3829
  cacheWrite: 0,
3593
3830
  },
3594
- contextWindow: 200000,
3595
- maxTokens: 100000,
3831
+ contextWindow: 128000,
3832
+ maxTokens: 128000,
3596
3833
  },
3597
- "workers-ai/@cf/moonshotai/kimi-k2.5": {
3598
- id: "workers-ai/@cf/moonshotai/kimi-k2.5",
3599
- name: "Kimi K2.5",
3834
+ "workers-ai/@cf/moonshotai/kimi-k2.6": {
3835
+ id: "workers-ai/@cf/moonshotai/kimi-k2.6",
3836
+ name: "Kimi K2.6",
3600
3837
  api: "openai-completions",
3601
3838
  provider: "cloudflare-ai-gateway",
3602
3839
  baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
@@ -3604,17 +3841,17 @@ export const MODELS = {
3604
3841
  reasoning: true,
3605
3842
  input: ["text", "image"],
3606
3843
  cost: {
3607
- input: 0.6,
3608
- output: 3,
3609
- cacheRead: 0.1,
3844
+ input: 0.95,
3845
+ output: 4,
3846
+ cacheRead: 0.16,
3610
3847
  cacheWrite: 0,
3611
3848
  },
3612
- contextWindow: 256000,
3849
+ contextWindow: 262144,
3613
3850
  maxTokens: 256000,
3614
3851
  },
3615
- "workers-ai/@cf/moonshotai/kimi-k2.6": {
3616
- id: "workers-ai/@cf/moonshotai/kimi-k2.6",
3617
- name: "Kimi K2.6",
3852
+ "workers-ai/@cf/moonshotai/kimi-k2.7-code": {
3853
+ id: "workers-ai/@cf/moonshotai/kimi-k2.7-code",
3854
+ name: "Kimi K2.7 Code",
3618
3855
  api: "openai-completions",
3619
3856
  provider: "cloudflare-ai-gateway",
3620
3857
  baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
@@ -3624,11 +3861,11 @@ export const MODELS = {
3624
3861
  cost: {
3625
3862
  input: 0.95,
3626
3863
  output: 4,
3627
- cacheRead: 0.16,
3864
+ cacheRead: 0.19,
3628
3865
  cacheWrite: 0,
3629
3866
  },
3630
- contextWindow: 256000,
3631
- maxTokens: 256000,
3867
+ contextWindow: 262144,
3868
+ maxTokens: 262144,
3632
3869
  },
3633
3870
  "workers-ai/@cf/nvidia/nemotron-3-120b-a12b": {
3634
3871
  id: "workers-ai/@cf/nvidia/nemotron-3-120b-a12b",
@@ -3648,6 +3885,60 @@ export const MODELS = {
3648
3885
  contextWindow: 256000,
3649
3886
  maxTokens: 256000,
3650
3887
  },
3888
+ "workers-ai/@cf/openai/gpt-oss-120b": {
3889
+ id: "workers-ai/@cf/openai/gpt-oss-120b",
3890
+ name: "GPT OSS 120B",
3891
+ api: "openai-completions",
3892
+ provider: "cloudflare-ai-gateway",
3893
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
3894
+ compat: { "sendSessionAffinityHeaders": true },
3895
+ reasoning: true,
3896
+ input: ["text"],
3897
+ cost: {
3898
+ input: 0.35,
3899
+ output: 0.75,
3900
+ cacheRead: 0,
3901
+ cacheWrite: 0,
3902
+ },
3903
+ contextWindow: 128000,
3904
+ maxTokens: 16384,
3905
+ },
3906
+ "workers-ai/@cf/openai/gpt-oss-20b": {
3907
+ id: "workers-ai/@cf/openai/gpt-oss-20b",
3908
+ name: "GPT OSS 20B",
3909
+ api: "openai-completions",
3910
+ provider: "cloudflare-ai-gateway",
3911
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
3912
+ compat: { "sendSessionAffinityHeaders": true },
3913
+ reasoning: true,
3914
+ input: ["text"],
3915
+ cost: {
3916
+ input: 0.2,
3917
+ output: 0.3,
3918
+ cacheRead: 0,
3919
+ cacheWrite: 0,
3920
+ },
3921
+ contextWindow: 128000,
3922
+ maxTokens: 16384,
3923
+ },
3924
+ "workers-ai/@cf/qwen/qwen3-30b-a3b-fp8": {
3925
+ id: "workers-ai/@cf/qwen/qwen3-30b-a3b-fp8",
3926
+ name: "Qwen3 30B A3b fp8",
3927
+ api: "openai-completions",
3928
+ provider: "cloudflare-ai-gateway",
3929
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
3930
+ compat: { "sendSessionAffinityHeaders": true },
3931
+ reasoning: true,
3932
+ input: ["text"],
3933
+ cost: {
3934
+ input: 0.0509,
3935
+ output: 0.335,
3936
+ cacheRead: 0,
3937
+ cacheWrite: 0,
3938
+ },
3939
+ contextWindow: 32768,
3940
+ maxTokens: 32768,
3941
+ },
3651
3942
  "workers-ai/@cf/zai-org/glm-4.7-flash": {
3652
3943
  id: "workers-ai/@cf/zai-org/glm-4.7-flash",
3653
3944
  name: "GLM-4.7-Flash",
@@ -3658,7 +3949,7 @@ export const MODELS = {
3658
3949
  reasoning: true,
3659
3950
  input: ["text"],
3660
3951
  cost: {
3661
- input: 0.06,
3952
+ input: 0.0605,
3662
3953
  output: 0.4,
3663
3954
  cacheRead: 0,
3664
3955
  cacheWrite: 0,
@@ -3682,10 +3973,48 @@ export const MODELS = {
3682
3973
  cacheWrite: 0,
3683
3974
  },
3684
3975
  contextWindow: 262144,
3685
- maxTokens: 262144,
3976
+ maxTokens: 256000,
3686
3977
  },
3687
3978
  },
3688
3979
  "cloudflare-workers-ai": {
3980
+ "@cf/deepseek-ai/deepseek-v4-flash-0731": {
3981
+ id: "@cf/deepseek-ai/deepseek-v4-flash-0731",
3982
+ name: "DeepSeek V4 Flash 0731",
3983
+ api: "openai-completions",
3984
+ provider: "cloudflare-workers-ai",
3985
+ baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
3986
+ compat: { "sendSessionAffinityHeaders": true, "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
3987
+ reasoning: true,
3988
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
3989
+ input: ["text"],
3990
+ cost: {
3991
+ input: 0.44,
3992
+ output: 1.32,
3993
+ cacheRead: 0.014,
3994
+ cacheWrite: 0,
3995
+ },
3996
+ contextWindow: 1048576,
3997
+ maxTokens: 1048576,
3998
+ },
3999
+ "@cf/deepseek-ai/deepseek-v4-pro-0813": {
4000
+ id: "@cf/deepseek-ai/deepseek-v4-pro-0813",
4001
+ name: "DeepSeek V4 Pro 0813",
4002
+ api: "openai-completions",
4003
+ provider: "cloudflare-workers-ai",
4004
+ baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
4005
+ compat: { "sendSessionAffinityHeaders": true, "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
4006
+ reasoning: true,
4007
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
4008
+ input: ["text"],
4009
+ cost: {
4010
+ input: 1.32,
4011
+ output: 3.96,
4012
+ cacheRead: 0.044,
4013
+ cacheWrite: 0,
4014
+ },
4015
+ contextWindow: 1048576,
4016
+ maxTokens: 1048576,
4017
+ },
3689
4018
  "@cf/google/gemma-4-26b-a4b-it": {
3690
4019
  id: "@cf/google/gemma-4-26b-a4b-it",
3691
4020
  name: "Gemma 4 26B A4B IT",
@@ -4013,6 +4342,23 @@ export const MODELS = {
4013
4342
  contextWindow: 1000000,
4014
4343
  maxTokens: 384000,
4015
4344
  },
4345
+ "accounts/fireworks/models/deepseek-v4-pro-0813": {
4346
+ id: "accounts/fireworks/models/deepseek-v4-pro-0813",
4347
+ name: "DeepSeek V4 Pro 0813",
4348
+ api: "anthropic-messages",
4349
+ provider: "fireworks",
4350
+ baseUrl: "https://api.fireworks.ai/inference",
4351
+ reasoning: true,
4352
+ input: ["text"],
4353
+ cost: {
4354
+ input: 1.32,
4355
+ output: 3.96,
4356
+ cacheRead: 0.044,
4357
+ cacheWrite: 0,
4358
+ },
4359
+ contextWindow: 1000000,
4360
+ maxTokens: 384000,
4361
+ },
4016
4362
  "accounts/fireworks/models/glm-5p2": {
4017
4363
  id: "accounts/fireworks/models/glm-5p2",
4018
4364
  name: "GLM 5.2",
@@ -4064,6 +4410,23 @@ export const MODELS = {
4064
4410
  contextWindow: 131072,
4065
4411
  maxTokens: 32768,
4066
4412
  },
4413
+ "accounts/fireworks/models/inkling": {
4414
+ id: "accounts/fireworks/models/inkling",
4415
+ name: "Inkling",
4416
+ api: "anthropic-messages",
4417
+ provider: "fireworks",
4418
+ baseUrl: "https://api.fireworks.ai/inference",
4419
+ reasoning: true,
4420
+ input: ["text", "image"],
4421
+ cost: {
4422
+ input: 1,
4423
+ output: 4.05,
4424
+ cacheRead: 0.17,
4425
+ cacheWrite: 0,
4426
+ },
4427
+ contextWindow: 1048576,
4428
+ maxTokens: 1048576,
4429
+ },
4067
4430
  "accounts/fireworks/models/kimi-k2p6": {
4068
4431
  id: "accounts/fireworks/models/kimi-k2p6",
4069
4432
  name: "Kimi K2.6",
@@ -4149,6 +4512,57 @@ export const MODELS = {
4149
4512
  contextWindow: 512000,
4150
4513
  maxTokens: 512000,
4151
4514
  },
4515
+ "accounts/fireworks/models/muse-glimmer-30b": {
4516
+ id: "accounts/fireworks/models/muse-glimmer-30b",
4517
+ name: "Muse Glimmer 30B",
4518
+ api: "anthropic-messages",
4519
+ provider: "fireworks",
4520
+ baseUrl: "https://api.fireworks.ai/inference",
4521
+ reasoning: true,
4522
+ input: ["text", "image"],
4523
+ cost: {
4524
+ input: 0.35,
4525
+ output: 1.5,
4526
+ cacheRead: 0.04,
4527
+ cacheWrite: 0,
4528
+ },
4529
+ contextWindow: 131072,
4530
+ maxTokens: 131072,
4531
+ },
4532
+ "accounts/fireworks/models/nemotron-3-ultra-nvfp4": {
4533
+ id: "accounts/fireworks/models/nemotron-3-ultra-nvfp4",
4534
+ name: "Nemotron 3 Ultra 550B A55B",
4535
+ api: "anthropic-messages",
4536
+ provider: "fireworks",
4537
+ baseUrl: "https://api.fireworks.ai/inference",
4538
+ reasoning: true,
4539
+ input: ["text"],
4540
+ cost: {
4541
+ input: 0.6,
4542
+ output: 2.4,
4543
+ cacheRead: 0.119,
4544
+ cacheWrite: 0,
4545
+ },
4546
+ contextWindow: 262144,
4547
+ maxTokens: 128000,
4548
+ },
4549
+ "accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b": {
4550
+ id: "accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b",
4551
+ name: "Nemotron 3.5 Lightning 30B A3B",
4552
+ api: "anthropic-messages",
4553
+ provider: "fireworks",
4554
+ baseUrl: "https://api.fireworks.ai/inference",
4555
+ reasoning: true,
4556
+ input: ["text"],
4557
+ cost: {
4558
+ input: 0.05,
4559
+ output: 0.2,
4560
+ cacheRead: 0.01,
4561
+ cacheWrite: 0,
4562
+ },
4563
+ contextWindow: 262144,
4564
+ maxTokens: 262144,
4565
+ },
4152
4566
  "accounts/fireworks/models/qwen3p7-plus": {
4153
4567
  id: "accounts/fireworks/models/qwen3p7-plus",
4154
4568
  name: "Qwen 3.7 Plus",
@@ -4166,6 +4580,23 @@ export const MODELS = {
4166
4580
  contextWindow: 262144,
4167
4581
  maxTokens: 65536,
4168
4582
  },
4583
+ "accounts/fireworks/models/qwen3p8-max": {
4584
+ id: "accounts/fireworks/models/qwen3p8-max",
4585
+ name: "Qwen3.8 Max",
4586
+ api: "anthropic-messages",
4587
+ provider: "fireworks",
4588
+ baseUrl: "https://api.fireworks.ai/inference",
4589
+ reasoning: true,
4590
+ input: ["text"],
4591
+ cost: {
4592
+ input: 2,
4593
+ output: 6,
4594
+ cacheRead: 0.25,
4595
+ cacheWrite: 0,
4596
+ },
4597
+ contextWindow: 262144,
4598
+ maxTokens: 131072,
4599
+ },
4169
4600
  "accounts/fireworks/routers/glm-5p2-fast": {
4170
4601
  id: "accounts/fireworks/routers/glm-5p2-fast",
4171
4602
  name: "GLM 5.2 Fast",
@@ -4518,6 +4949,25 @@ export const MODELS = {
4518
4949
  contextWindow: 1000000,
4519
4950
  maxTokens: 64000,
4520
4951
  },
4952
+ "gemini-3.7-flash": {
4953
+ id: "gemini-3.7-flash",
4954
+ name: "Gemini 3.7 Flash",
4955
+ api: "openai-completions",
4956
+ provider: "github-copilot",
4957
+ baseUrl: "https://api.individual.githubcopilot.com",
4958
+ 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" },
4959
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
4960
+ reasoning: true,
4961
+ input: ["text", "image"],
4962
+ cost: {
4963
+ input: 0.75,
4964
+ output: 3.75,
4965
+ cacheRead: 0.075,
4966
+ cacheWrite: 0,
4967
+ },
4968
+ contextWindow: 1000000,
4969
+ maxTokens: 64000,
4970
+ },
4521
4971
  "gpt-4.1": {
4522
4972
  id: "gpt-4.1",
4523
4973
  name: "GPT-4.1",
@@ -4765,6 +5215,25 @@ export const MODELS = {
4765
5215
  contextWindow: 500000,
4766
5216
  maxTokens: 128000,
4767
5217
  },
5218
+ "grok-4.6": {
5219
+ id: "grok-4.6",
5220
+ name: "Grok 4.6",
5221
+ api: "openai-completions",
5222
+ provider: "github-copilot",
5223
+ baseUrl: "https://api.individual.githubcopilot.com",
5224
+ 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" },
5225
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
5226
+ reasoning: true,
5227
+ input: ["text", "image"],
5228
+ cost: {
5229
+ input: 2,
5230
+ output: 6,
5231
+ cacheRead: 0.5,
5232
+ cacheWrite: 0,
5233
+ },
5234
+ contextWindow: 500000,
5235
+ maxTokens: 128000,
5236
+ },
4768
5237
  "kimi-k2.7-code": {
4769
5238
  id: "kimi-k2.7-code",
4770
5239
  name: "Kimi K2.7 Code",
@@ -4822,6 +5291,25 @@ export const MODELS = {
4822
5291
  contextWindow: 256000,
4823
5292
  maxTokens: 128000,
4824
5293
  },
5294
+ "mai-code-1.1-flash": {
5295
+ id: "mai-code-1.1-flash",
5296
+ name: "MAI-Code-1.1-Flash",
5297
+ api: "openai-completions",
5298
+ provider: "github-copilot",
5299
+ baseUrl: "https://api.individual.githubcopilot.com",
5300
+ 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" },
5301
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
5302
+ reasoning: true,
5303
+ input: ["text", "image"],
5304
+ cost: {
5305
+ input: 0.2,
5306
+ output: 1.2,
5307
+ cacheRead: 0.02,
5308
+ cacheWrite: 0,
5309
+ },
5310
+ contextWindow: 256000,
5311
+ maxTokens: 128000,
5312
+ },
4825
5313
  },
4826
5314
  "google": {
4827
5315
  "deep-research-max-preview-04-2026": {
@@ -5106,6 +5594,24 @@ export const MODELS = {
5106
5594
  contextWindow: 1048576,
5107
5595
  maxTokens: 65536,
5108
5596
  },
5597
+ "gemini-3.7-flash": {
5598
+ id: "gemini-3.7-flash",
5599
+ name: "Gemini 3.7 Flash",
5600
+ api: "google-generative-ai",
5601
+ provider: "google",
5602
+ baseUrl: "https://generativelanguage.googleapis.com/v1beta",
5603
+ reasoning: true,
5604
+ thinkingLevelMap: { "off": null },
5605
+ input: ["text", "image"],
5606
+ cost: {
5607
+ input: 0.75,
5608
+ output: 3.75,
5609
+ cacheRead: 0.075,
5610
+ cacheWrite: 0,
5611
+ },
5612
+ contextWindow: 1048576,
5613
+ maxTokens: 65536,
5614
+ },
5109
5615
  "gemini-flash-latest": {
5110
5616
  id: "gemini-flash-latest",
5111
5617
  name: "Gemini Flash Latest",
@@ -5616,6 +6122,24 @@ export const MODELS = {
5616
6122
  contextWindow: 524288,
5617
6123
  maxTokens: 128000,
5618
6124
  },
6125
+ "Qwen/Qwen2.5-Coder-32B-Instruct": {
6126
+ id: "Qwen/Qwen2.5-Coder-32B-Instruct",
6127
+ name: "Qwen2.5-Coder-32B-Instruct",
6128
+ api: "openai-completions",
6129
+ provider: "huggingface",
6130
+ baseUrl: "https://router.huggingface.co/v1",
6131
+ compat: { "supportsDeveloperRole": false },
6132
+ reasoning: false,
6133
+ input: ["text"],
6134
+ cost: {
6135
+ input: 0.06,
6136
+ output: 0.2,
6137
+ cacheRead: 0,
6138
+ cacheWrite: 0,
6139
+ },
6140
+ contextWindow: 131072,
6141
+ maxTokens: 8192,
6142
+ },
5619
6143
  "Qwen/Qwen3-235B-A22B": {
5620
6144
  id: "Qwen/Qwen3-235B-A22B",
5621
6145
  name: "Qwen3 235B-A22B",
@@ -5670,6 +6194,24 @@ export const MODELS = {
5670
6194
  contextWindow: 262144,
5671
6195
  maxTokens: 131072,
5672
6196
  },
6197
+ "Qwen/Qwen3-30B-A3B": {
6198
+ id: "Qwen/Qwen3-30B-A3B",
6199
+ name: "Qwen3 30B A3B",
6200
+ api: "openai-completions",
6201
+ provider: "huggingface",
6202
+ baseUrl: "https://router.huggingface.co/v1",
6203
+ compat: { "supportsDeveloperRole": false },
6204
+ reasoning: true,
6205
+ input: ["text"],
6206
+ cost: {
6207
+ input: 0.12,
6208
+ output: 0.5,
6209
+ cacheRead: 0,
6210
+ cacheWrite: 0,
6211
+ },
6212
+ contextWindow: 40960,
6213
+ maxTokens: 16384,
6214
+ },
5673
6215
  "Qwen/Qwen3-32B": {
5674
6216
  id: "Qwen/Qwen3-32B",
5675
6217
  name: "Qwen3 32B",
@@ -5994,6 +6536,24 @@ export const MODELS = {
5994
6536
  contextWindow: 64000,
5995
6537
  maxTokens: 8192,
5996
6538
  },
6539
+ "deepseek-ai/DeepSeek-V3-0324": {
6540
+ id: "deepseek-ai/DeepSeek-V3-0324",
6541
+ name: "DeepSeek V3 0324",
6542
+ api: "openai-completions",
6543
+ provider: "huggingface",
6544
+ baseUrl: "https://router.huggingface.co/v1",
6545
+ compat: { "supportsDeveloperRole": false },
6546
+ reasoning: false,
6547
+ input: ["text"],
6548
+ cost: {
6549
+ input: 0.27,
6550
+ output: 1.12,
6551
+ cacheRead: 0,
6552
+ cacheWrite: 0,
6553
+ },
6554
+ contextWindow: 163840,
6555
+ maxTokens: 163840,
6556
+ },
5997
6557
  "deepseek-ai/DeepSeek-V3.1": {
5998
6558
  id: "deepseek-ai/DeepSeek-V3.1",
5999
6559
  name: "DeepSeek-V3.1",
@@ -6084,6 +6644,24 @@ export const MODELS = {
6084
6644
  contextWindow: 1048576,
6085
6645
  maxTokens: 393216,
6086
6646
  },
6647
+ "deepseek-ai/DeepSeek-V4-Pro-0813": {
6648
+ id: "deepseek-ai/DeepSeek-V4-Pro-0813",
6649
+ name: "DeepSeek V4 Pro 0813",
6650
+ api: "openai-completions",
6651
+ provider: "huggingface",
6652
+ baseUrl: "https://router.huggingface.co/v1",
6653
+ compat: { "supportsDeveloperRole": false },
6654
+ reasoning: true,
6655
+ input: ["text"],
6656
+ cost: {
6657
+ input: 1.32,
6658
+ output: 3.96,
6659
+ cacheRead: 0,
6660
+ cacheWrite: 0,
6661
+ },
6662
+ contextWindow: 1000000,
6663
+ maxTokens: 384000,
6664
+ },
6087
6665
  "google/gemma-4-26B-A4B-it": {
6088
6666
  id: "google/gemma-4-26B-A4B-it",
6089
6667
  name: "Gemma 4 26B A4B IT",
@@ -6120,6 +6698,24 @@ export const MODELS = {
6120
6698
  contextWindow: 262144,
6121
6699
  maxTokens: 32768,
6122
6700
  },
6701
+ "meta-llama/Llama-3.1-8B-Instruct": {
6702
+ id: "meta-llama/Llama-3.1-8B-Instruct",
6703
+ name: "Llama-3.1-8B-Instruct",
6704
+ api: "openai-completions",
6705
+ provider: "huggingface",
6706
+ baseUrl: "https://router.huggingface.co/v1",
6707
+ compat: { "supportsDeveloperRole": false },
6708
+ reasoning: false,
6709
+ input: ["text"],
6710
+ cost: {
6711
+ input: 0.06,
6712
+ output: 0.06,
6713
+ cacheRead: 0,
6714
+ cacheWrite: 0,
6715
+ },
6716
+ contextWindow: 131072,
6717
+ maxTokens: 4096,
6718
+ },
6123
6719
  "meta-llama/Llama-3.3-70B-Instruct": {
6124
6720
  id: "meta-llama/Llama-3.3-70B-Instruct",
6125
6721
  name: "Llama-3.3-70B-Instruct",
@@ -8817,6 +9413,24 @@ export const MODELS = {
8817
9413
  contextWindow: 1048576,
8818
9414
  maxTokens: 65536,
8819
9415
  },
9416
+ "gemini-3.7-flash": {
9417
+ id: "gemini-3.7-flash",
9418
+ name: "Gemini 3.7 Flash",
9419
+ api: "google-generative-ai",
9420
+ provider: "opencode",
9421
+ baseUrl: "https://opencode.ai/zen/v1",
9422
+ reasoning: true,
9423
+ thinkingLevelMap: { "off": null },
9424
+ input: ["text", "image"],
9425
+ cost: {
9426
+ input: 1.5,
9427
+ output: 7.5,
9428
+ cacheRead: 0.15,
9429
+ cacheWrite: 0,
9430
+ },
9431
+ contextWindow: 1048576,
9432
+ maxTokens: 65536,
9433
+ },
8820
9434
  "glm-5": {
8821
9435
  id: "glm-5",
8822
9436
  name: "GLM-5",
@@ -9227,6 +9841,23 @@ export const MODELS = {
9227
9841
  contextWindow: 500000,
9228
9842
  maxTokens: 500000,
9229
9843
  },
9844
+ "grok-4.6": {
9845
+ id: "grok-4.6",
9846
+ name: "Grok 4.6",
9847
+ api: "openai-responses",
9848
+ provider: "opencode",
9849
+ baseUrl: "https://opencode.ai/zen/v1",
9850
+ reasoning: true,
9851
+ input: ["text", "image"],
9852
+ cost: {
9853
+ input: 2,
9854
+ output: 6,
9855
+ cacheRead: 0.5,
9856
+ cacheWrite: 0,
9857
+ },
9858
+ contextWindow: 500000,
9859
+ maxTokens: 500000,
9860
+ },
9230
9861
  "grok-build-0.1": {
9231
9862
  id: "grok-build-0.1",
9232
9863
  name: "Grok Build 0.1",
@@ -9346,23 +9977,6 @@ export const MODELS = {
9346
9977
  contextWindow: 256000,
9347
9978
  maxTokens: 32000,
9348
9979
  },
9349
- "ling-3.0-tiny-free": {
9350
- id: "ling-3.0-tiny-free",
9351
- name: "Ling-3.0-tiny Free",
9352
- api: "openai-completions",
9353
- provider: "opencode",
9354
- baseUrl: "https://opencode.ai/zen/v1",
9355
- reasoning: true,
9356
- input: ["text"],
9357
- cost: {
9358
- input: 0,
9359
- output: 0,
9360
- cacheRead: 0,
9361
- cacheWrite: 0,
9362
- },
9363
- contextWindow: 262144,
9364
- maxTokens: 32768,
9365
- },
9366
9980
  "mimo-v2.5-free": {
9367
9981
  id: "mimo-v2.5-free",
9368
9982
  name: "MiMo V2.5 Free",
@@ -9431,6 +10045,23 @@ export const MODELS = {
9431
10045
  contextWindow: 512000,
9432
10046
  maxTokens: 128000,
9433
10047
  },
10048
+ "muse-spark-1.2": {
10049
+ id: "muse-spark-1.2",
10050
+ name: "Muse Spark 1.2",
10051
+ api: "openai-responses",
10052
+ provider: "opencode",
10053
+ baseUrl: "https://opencode.ai/zen/v1",
10054
+ reasoning: true,
10055
+ input: ["text", "image"],
10056
+ cost: {
10057
+ input: 1.25,
10058
+ output: 4.25,
10059
+ cacheRead: 0.15,
10060
+ cacheWrite: 0,
10061
+ },
10062
+ contextWindow: 1048576,
10063
+ maxTokens: 131072,
10064
+ },
9434
10065
  "nemotron-3-ultra-free": {
9435
10066
  id: "nemotron-3-ultra-free",
9436
10067
  name: "Nemotron 3 Ultra Free",
@@ -9522,7 +10153,7 @@ export const MODELS = {
9522
10153
  },
9523
10154
  "deepseek-v4-pro": {
9524
10155
  id: "deepseek-v4-pro",
9525
- name: "DeepSeek V4 Pro",
10156
+ name: "DeepSeek V4 Pro (New)",
9526
10157
  api: "openai-completions",
9527
10158
  provider: "opencode-go",
9528
10159
  baseUrl: "https://opencode.ai/zen/go/v1",
@@ -9573,6 +10204,23 @@ export const MODELS = {
9573
10204
  contextWindow: 1000000,
9574
10205
  maxTokens: 131072,
9575
10206
  },
10207
+ "glm-5.3": {
10208
+ id: "glm-5.3",
10209
+ name: "GLM-5.3",
10210
+ api: "openai-completions",
10211
+ provider: "opencode-go",
10212
+ baseUrl: "https://opencode.ai/zen/go/v1",
10213
+ reasoning: true,
10214
+ input: ["text"],
10215
+ cost: {
10216
+ input: 1.4,
10217
+ output: 4.4,
10218
+ cacheRead: 0.26,
10219
+ cacheWrite: 0,
10220
+ },
10221
+ contextWindow: 1000000,
10222
+ maxTokens: 131072,
10223
+ },
9576
10224
  "gpt-5.6-luna": {
9577
10225
  id: "gpt-5.6-luna",
9578
10226
  name: "GPT-5.6 Luna (2x usage)",
@@ -10539,6 +11187,23 @@ export const MODELS = {
10539
11187
  contextWindow: 262144,
10540
11188
  maxTokens: 32768,
10541
11189
  },
11190
+ "bytedance-seed/seed-2-1-turbo": {
11191
+ id: "bytedance-seed/seed-2-1-turbo",
11192
+ name: "ByteDance Seed: Seed 2.1 Turbo",
11193
+ api: "openai-completions",
11194
+ provider: "openrouter",
11195
+ baseUrl: "https://openrouter.ai/api/v1",
11196
+ reasoning: true,
11197
+ input: ["text", "image"],
11198
+ cost: {
11199
+ input: 0.5,
11200
+ output: 2.5,
11201
+ cacheRead: 0,
11202
+ cacheWrite: 0,
11203
+ },
11204
+ contextWindow: 262144,
11205
+ maxTokens: 262144,
11206
+ },
10542
11207
  "bytedance-seed/seed-2.0-code": {
10543
11208
  id: "bytedance-seed/seed-2.0-code",
10544
11209
  name: "ByteDance Seed: Seed-2.0-Code",
@@ -10706,7 +11371,7 @@ export const MODELS = {
10706
11371
  cacheRead: 0,
10707
11372
  cacheWrite: 0,
10708
11373
  },
10709
- contextWindow: 163840,
11374
+ contextWindow: 64000,
10710
11375
  maxTokens: 16000,
10711
11376
  },
10712
11377
  "deepseek/deepseek-r1-0528": {
@@ -10788,13 +11453,13 @@ export const MODELS = {
10788
11453
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
10789
11454
  input: ["text"],
10790
11455
  cost: {
10791
- input: 0.14,
10792
- output: 0.28,
10793
- cacheRead: 0.028,
11456
+ input: 0.06286,
11457
+ output: 0.12572,
11458
+ cacheRead: 0.012572,
10794
11459
  cacheWrite: 0,
10795
11460
  },
10796
11461
  contextWindow: 1048576,
10797
- maxTokens: 393216,
11462
+ maxTokens: 384000,
10798
11463
  },
10799
11464
  "deepseek/deepseek-v4-flash-0731": {
10800
11465
  id: "deepseek/deepseek-v4-flash-0731",
@@ -10807,13 +11472,13 @@ export const MODELS = {
10807
11472
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
10808
11473
  input: ["text"],
10809
11474
  cost: {
10810
- input: 0.08,
10811
- output: 0.18,
10812
- cacheRead: 0.016,
11475
+ input: 0.14,
11476
+ output: 0.28,
11477
+ cacheRead: 0.028,
10813
11478
  cacheWrite: 0,
10814
11479
  },
10815
11480
  contextWindow: 1048576,
10816
- maxTokens: 384000,
11481
+ maxTokens: 393216,
10817
11482
  },
10818
11483
  "deepseek/deepseek-v4-pro": {
10819
11484
  id: "deepseek/deepseek-v4-pro",
@@ -10834,6 +11499,42 @@ export const MODELS = {
10834
11499
  contextWindow: 1048576,
10835
11500
  maxTokens: 393216,
10836
11501
  },
11502
+ "deepseek/deepseek-v4-pro-0813": {
11503
+ id: "deepseek/deepseek-v4-pro-0813",
11504
+ name: "DeepSeek: DeepSeek V4 Pro 0813",
11505
+ api: "openai-completions",
11506
+ provider: "openrouter",
11507
+ baseUrl: "https://openrouter.ai/api/v1",
11508
+ compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
11509
+ reasoning: true,
11510
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
11511
+ input: ["text"],
11512
+ cost: {
11513
+ input: 0.435,
11514
+ output: 0.87,
11515
+ cacheRead: 0.003625,
11516
+ cacheWrite: 0,
11517
+ },
11518
+ contextWindow: 1048576,
11519
+ maxTokens: 384000,
11520
+ },
11521
+ "dots-studio/dots-3-note-preview:free": {
11522
+ id: "dots-studio/dots-3-note-preview:free",
11523
+ name: "Dots Studio: Dots3-Note Preview (free)",
11524
+ api: "openai-completions",
11525
+ provider: "openrouter",
11526
+ baseUrl: "https://openrouter.ai/api/v1",
11527
+ reasoning: true,
11528
+ input: ["text", "image"],
11529
+ cost: {
11530
+ input: 0,
11531
+ output: 0,
11532
+ cacheRead: 0,
11533
+ cacheWrite: 0,
11534
+ },
11535
+ contextWindow: 512000,
11536
+ maxTokens: 512000,
11537
+ },
10837
11538
  "google/gemini-2.5-flash": {
10838
11539
  id: "google/gemini-2.5-flash",
10839
11540
  name: "Google: Gemini 2.5 Flash",
@@ -11200,27 +11901,61 @@ export const MODELS = {
11200
11901
  reasoning: true,
11201
11902
  input: ["text", "image"],
11202
11903
  cost: {
11203
- input: 1.5,
11204
- output: 7.5,
11205
- cacheRead: 0.15,
11206
- cacheWrite: 0.0833333333333333,
11904
+ input: 0.75,
11905
+ output: 3.75,
11906
+ cacheRead: 0.075,
11907
+ cacheWrite: 0.0416666666666667,
11908
+ },
11909
+ contextWindow: 1048576,
11910
+ maxTokens: 65536,
11911
+ },
11912
+ "google/gemini-3.6-flash:batch": {
11913
+ id: "google/gemini-3.6-flash:batch",
11914
+ name: "Google: Gemini 3.6 Flash (batch)",
11915
+ api: "openai-completions",
11916
+ provider: "openrouter",
11917
+ baseUrl: "https://openrouter.ai/api/v1",
11918
+ reasoning: true,
11919
+ input: ["text", "image"],
11920
+ cost: {
11921
+ input: 0.375,
11922
+ output: 1.875,
11923
+ cacheRead: 0.0375,
11924
+ cacheWrite: 0.0416666666666667,
11925
+ },
11926
+ contextWindow: 1048576,
11927
+ maxTokens: 65536,
11928
+ },
11929
+ "google/gemini-3.7-flash": {
11930
+ id: "google/gemini-3.7-flash",
11931
+ name: "Google: Gemini 3.7 Flash",
11932
+ api: "openai-completions",
11933
+ provider: "openrouter",
11934
+ baseUrl: "https://openrouter.ai/api/v1",
11935
+ reasoning: true,
11936
+ input: ["text", "image"],
11937
+ cost: {
11938
+ input: 0.375,
11939
+ output: 1.875,
11940
+ cacheRead: 0.0375,
11941
+ cacheWrite: 0.0208333333333333,
11207
11942
  },
11208
11943
  contextWindow: 1048576,
11209
11944
  maxTokens: 65536,
11210
11945
  },
11211
- "google/gemini-3.6-flash:batch": {
11212
- id: "google/gemini-3.6-flash:batch",
11213
- name: "Google: Gemini 3.6 Flash (batch)",
11946
+ "google/gemini-3.7-flash:batch": {
11947
+ id: "google/gemini-3.7-flash:batch",
11948
+ name: "Google: Gemini 3.7 Flash (batch)",
11214
11949
  api: "openai-completions",
11215
11950
  provider: "openrouter",
11216
11951
  baseUrl: "https://openrouter.ai/api/v1",
11217
11952
  reasoning: true,
11218
11953
  input: ["text", "image"],
11219
11954
  cost: {
11220
- input: 0.75,
11221
- output: 3.75,
11222
- cacheRead: 0.075,
11223
- cacheWrite: 0.0833333333333333,
11955
+ input: 0.1875,
11956
+ output: 0.9375,
11957
+ cacheRead: 0.01875,
11958
+ cacheWrite: 0.0208333333333333,
11224
11959
  },
11225
11960
  contextWindow: 1048576,
11226
11961
  maxTokens: 65536,
@@ -11412,23 +12147,6 @@ export const MODELS = {
11412
12147
  contextWindow: 262144,
11413
12148
  maxTokens: 32768,
11414
12149
  },
11415
- "inclusionai/ling-3.0-tiny:free": {
11416
- id: "inclusionai/ling-3.0-tiny:free",
11417
- name: "inclusionAI: Ling 3.0 Tiny (free)",
11418
- api: "openai-completions",
11419
- provider: "openrouter",
11420
- baseUrl: "https://openrouter.ai/api/v1",
11421
- reasoning: true,
11422
- input: ["text"],
11423
- cost: {
11424
- input: 0,
11425
- output: 0,
11426
- cacheRead: 0,
11427
- cacheWrite: 0,
11428
- },
11429
- contextWindow: 262144,
11430
- maxTokens: 32768,
11431
- },
11432
12150
  "inclusionai/ring-2.6-1t": {
11433
12151
  id: "inclusionai/ring-2.6-1t",
11434
12152
  name: "inclusionAI: Ring-2.6-1T",
@@ -11512,7 +12230,7 @@ export const MODELS = {
11512
12230
  cacheWrite: 0,
11513
12231
  },
11514
12232
  contextWindow: 128000,
11515
- maxTokens: 32768,
12233
+ maxTokens: 8192,
11516
12234
  },
11517
12235
  "meituan/longcat-2.0": {
11518
12236
  id: "meituan/longcat-2.0",
@@ -11592,12 +12310,12 @@ export const MODELS = {
11592
12310
  input: ["text", "image"],
11593
12311
  cost: {
11594
12312
  input: 0.19999999999999998,
11595
- output: 0.696,
12313
+ output: 0.7999999999999999,
11596
12314
  cacheRead: 0,
11597
12315
  cacheWrite: 0,
11598
12316
  },
11599
12317
  contextWindow: 1048576,
11600
- maxTokens: 4096,
12318
+ maxTokens: 16384,
11601
12319
  },
11602
12320
  "meta-llama/llama-4-scout": {
11603
12321
  id: "meta-llama/llama-4-scout",
@@ -11676,7 +12394,7 @@ export const MODELS = {
11676
12394
  reasoning: true,
11677
12395
  input: ["text"],
11678
12396
  cost: {
11679
- input: 0.55,
12397
+ input: 0.39999999999999997,
11680
12398
  output: 2.2,
11681
12399
  cacheRead: 0,
11682
12400
  cacheWrite: 0,
@@ -12135,9 +12853,9 @@ export const MODELS = {
12135
12853
  reasoning: true,
12136
12854
  input: ["text", "image"],
12137
12855
  cost: {
12138
- input: 0.95,
12139
- output: 4,
12140
- cacheRead: 0.16,
12856
+ input: 0.65,
12857
+ output: 3.41,
12858
+ cacheRead: 0.15,
12141
12859
  cacheWrite: 0,
12142
12860
  },
12143
12861
  contextWindow: 262144,
@@ -12152,7 +12870,7 @@ export const MODELS = {
12152
12870
  reasoning: true,
12153
12871
  input: ["text", "image"],
12154
12872
  cost: {
12155
- input: 0.7,
12873
+ input: 0.71,
12156
12874
  output: 3.5,
12157
12875
  cacheRead: 0.15,
12158
12876
  cacheWrite: 0,
@@ -12364,6 +13082,23 @@ export const MODELS = {
12364
13082
  contextWindow: 1000000,
12365
13083
  maxTokens: 65536,
12366
13084
  },
13085
+ "nvidia/nemotron-3.5-lightning": {
13086
+ id: "nvidia/nemotron-3.5-lightning",
13087
+ name: "NVIDIA: Nemotron 3.5 Lightning",
13088
+ api: "openai-completions",
13089
+ provider: "openrouter",
13090
+ baseUrl: "https://openrouter.ai/api/v1",
13091
+ reasoning: true,
13092
+ input: ["text"],
13093
+ cost: {
13094
+ input: 0.09999999999999999,
13095
+ output: 0.25,
13096
+ cacheRead: 0.049999999999999996,
13097
+ cacheWrite: 0,
13098
+ },
13099
+ contextWindow: 1000000,
13100
+ maxTokens: 262144,
13101
+ },
12367
13102
  "nvidia/nemotron-3.5-lightning:free": {
12368
13103
  id: "nvidia/nemotron-3.5-lightning:free",
12369
13104
  name: "NVIDIA: Nemotron 3.5 Lightning (free)",
@@ -14024,10 +14759,10 @@ export const MODELS = {
14024
14759
  reasoning: true,
14025
14760
  input: ["text"],
14026
14761
  cost: {
14027
- input: 0.39999999999999997,
14028
- output: 1.2,
14762
+ input: 0.26,
14763
+ output: 0.78,
14029
14764
  cacheRead: 0,
14030
- cacheWrite: 0.5,
14765
+ cacheWrite: 0,
14031
14766
  },
14032
14767
  contextWindow: 1000000,
14033
14768
  maxTokens: 32768,
@@ -14109,13 +14844,13 @@ export const MODELS = {
14109
14844
  reasoning: true,
14110
14845
  input: ["text"],
14111
14846
  cost: {
14112
- input: 0.12,
14113
- output: 0.5,
14847
+ input: 0.13,
14848
+ output: 0.52,
14114
14849
  cacheRead: 0,
14115
14850
  cacheWrite: 0,
14116
14851
  },
14117
14852
  contextWindow: 131072,
14118
- maxTokens: 16384,
14853
+ maxTokens: 8192,
14119
14854
  },
14120
14855
  "qwen/qwen3-30b-a3b-instruct-2507": {
14121
14856
  id: "qwen/qwen3-30b-a3b-instruct-2507",
@@ -14313,13 +15048,13 @@ export const MODELS = {
14313
15048
  reasoning: false,
14314
15049
  input: ["text"],
14315
15050
  cost: {
14316
- input: 0.09,
15051
+ input: 0.09999999999999999,
14317
15052
  output: 1.1,
14318
- cacheRead: 0,
15053
+ cacheRead: 0.07,
14319
15054
  cacheWrite: 0,
14320
15055
  },
14321
15056
  contextWindow: 262144,
14322
- maxTokens: 16384,
15057
+ maxTokens: 262144,
14323
15058
  },
14324
15059
  "qwen/qwen3-next-80b-a3b-thinking": {
14325
15060
  id: "qwen/qwen3-next-80b-a3b-thinking",
@@ -14336,7 +15071,7 @@ export const MODELS = {
14336
15071
  cacheWrite: 0,
14337
15072
  },
14338
15073
  contextWindow: 262144,
14339
- maxTokens: 262144,
15074
+ maxTokens: 32768,
14340
15075
  },
14341
15076
  "qwen/qwen3-vl-235b-a22b-instruct": {
14342
15077
  id: "qwen/qwen3-vl-235b-a22b-instruct",
@@ -14381,13 +15116,13 @@ export const MODELS = {
14381
15116
  reasoning: false,
14382
15117
  input: ["text", "image"],
14383
15118
  cost: {
14384
- input: 0.15,
14385
- output: 0.6,
15119
+ input: 0.13,
15120
+ output: 0.52,
14386
15121
  cacheRead: 0,
14387
15122
  cacheWrite: 0,
14388
15123
  },
14389
15124
  contextWindow: 262144,
14390
- maxTokens: 16384,
15125
+ maxTokens: 32768,
14391
15126
  },
14392
15127
  "qwen/qwen3-vl-30b-a3b-thinking": {
14393
15128
  id: "qwen/qwen3-vl-30b-a3b-thinking",
@@ -14500,13 +15235,13 @@ export const MODELS = {
14500
15235
  reasoning: true,
14501
15236
  input: ["text", "image"],
14502
15237
  cost: {
14503
- input: 0.14,
14504
- output: 1,
14505
- cacheRead: 0,
15238
+ input: 0.22499999999999998,
15239
+ output: 1.7999999999999998,
15240
+ cacheRead: 0.22499999999999998,
14506
15241
  cacheWrite: 0,
14507
15242
  },
14508
15243
  contextWindow: 262144,
14509
- maxTokens: 262144,
15244
+ maxTokens: 65536,
14510
15245
  },
14511
15246
  "qwen/qwen3.5-397b-a17b": {
14512
15247
  id: "qwen/qwen3.5-397b-a17b",
@@ -14517,13 +15252,13 @@ export const MODELS = {
14517
15252
  reasoning: true,
14518
15253
  input: ["text", "image"],
14519
15254
  cost: {
14520
- input: 0.5,
14521
- output: 3.5999999999999996,
14522
- cacheRead: 0.3,
15255
+ input: 0.39,
15256
+ output: 2.34,
15257
+ cacheRead: 0,
14523
15258
  cacheWrite: 0,
14524
15259
  },
14525
15260
  contextWindow: 262144,
14526
- maxTokens: 262144,
15261
+ maxTokens: 65536,
14527
15262
  },
14528
15263
  "qwen/qwen3.5-9b": {
14529
15264
  id: "qwen/qwen3.5-9b",
@@ -14602,13 +15337,13 @@ export const MODELS = {
14602
15337
  reasoning: true,
14603
15338
  input: ["text", "image"],
14604
15339
  cost: {
14605
- input: 0.6,
14606
- output: 3.5999999999999996,
14607
- cacheRead: 0.12,
15340
+ input: 0.3,
15341
+ output: 2,
15342
+ cacheRead: 0.03,
14608
15343
  cacheWrite: 0,
14609
15344
  },
14610
15345
  contextWindow: 262144,
14611
- maxTokens: 262144,
15346
+ maxTokens: 65536,
14612
15347
  },
14613
15348
  "qwen/qwen3.6-35b-a3b": {
14614
15349
  id: "qwen/qwen3.6-35b-a3b",
@@ -14729,6 +15464,40 @@ export const MODELS = {
14729
15464
  contextWindow: 1000000,
14730
15465
  maxTokens: 131072,
14731
15466
  },
15467
+ "qwen/qwen3.8-2.4t-a95b": {
15468
+ id: "qwen/qwen3.8-2.4t-a95b",
15469
+ name: "Qwen: Qwen3.8 2.4T A95B",
15470
+ api: "openai-completions",
15471
+ provider: "openrouter",
15472
+ baseUrl: "https://openrouter.ai/api/v1",
15473
+ reasoning: true,
15474
+ input: ["text"],
15475
+ cost: {
15476
+ input: 2,
15477
+ output: 6,
15478
+ cacheRead: 0.25,
15479
+ cacheWrite: 0,
15480
+ },
15481
+ contextWindow: 1048576,
15482
+ maxTokens: 262144,
15483
+ },
15484
+ "qwen/qwen3.8-27b": {
15485
+ id: "qwen/qwen3.8-27b",
15486
+ name: "Qwen: Qwen3.8 27B",
15487
+ api: "openai-completions",
15488
+ provider: "openrouter",
15489
+ baseUrl: "https://openrouter.ai/api/v1",
15490
+ reasoning: true,
15491
+ input: ["text", "image"],
15492
+ cost: {
15493
+ input: 0.44999999999999996,
15494
+ output: 3.1999999999999997,
15495
+ cacheRead: 0,
15496
+ cacheWrite: 0,
15497
+ },
15498
+ contextWindow: 262144,
15499
+ maxTokens: 131072,
15500
+ },
14732
15501
  "qwen/qwen3.8-max": {
14733
15502
  id: "qwen/qwen3.8-max",
14734
15503
  name: "Qwen: Qwen3.8 Max",
@@ -15035,6 +15804,23 @@ export const MODELS = {
15035
15804
  contextWindow: 500000,
15036
15805
  maxTokens: 4096,
15037
15806
  },
15807
+ "x-ai/grok-4.6": {
15808
+ id: "x-ai/grok-4.6",
15809
+ name: "SpaceXAI: Grok 4.6",
15810
+ api: "openai-completions",
15811
+ provider: "openrouter",
15812
+ baseUrl: "https://openrouter.ai/api/v1",
15813
+ reasoning: true,
15814
+ input: ["text", "image"],
15815
+ cost: {
15816
+ input: 2,
15817
+ output: 6,
15818
+ cacheRead: 0.5,
15819
+ cacheWrite: 0,
15820
+ },
15821
+ contextWindow: 500000,
15822
+ maxTokens: 4096,
15823
+ },
15038
15824
  "x-ai/grok-build-0.1": {
15039
15825
  id: "x-ai/grok-build-0.1",
15040
15826
  name: "SpaceXAI: Grok Build 0.1",
@@ -15220,7 +16006,7 @@ export const MODELS = {
15220
16006
  cacheWrite: 0,
15221
16007
  },
15222
16008
  contextWindow: 204800,
15223
- maxTokens: 131072,
16009
+ maxTokens: 128000,
15224
16010
  },
15225
16011
  "z-ai/glm-5-turbo": {
15226
16012
  id: "z-ai/glm-5-turbo",
@@ -15248,13 +16034,13 @@ export const MODELS = {
15248
16034
  reasoning: true,
15249
16035
  input: ["text"],
15250
16036
  cost: {
15251
- input: 1.4,
15252
- output: 4.4,
15253
- cacheRead: 0.26,
16037
+ input: 0.966,
16038
+ output: 3.036,
16039
+ cacheRead: 0.1794,
15254
16040
  cacheWrite: 0,
15255
16041
  },
15256
16042
  contextWindow: 204800,
15257
- maxTokens: 131072,
16043
+ maxTokens: 128000,
15258
16044
  },
15259
16045
  "z-ai/glm-5.2": {
15260
16046
  id: "z-ai/glm-5.2",
@@ -15265,13 +16051,13 @@ export const MODELS = {
15265
16051
  reasoning: true,
15266
16052
  input: ["text"],
15267
16053
  cost: {
15268
- input: 0.5,
15269
- output: 3.15,
15270
- cacheRead: 0.09999999999999999,
16054
+ input: 0.308,
16055
+ output: 0.9680000000000001,
16056
+ cacheRead: 0.0572,
15271
16057
  cacheWrite: 0,
15272
16058
  },
15273
16059
  contextWindow: 1048576,
15274
- maxTokens: 131072,
16060
+ maxTokens: 128000,
15275
16061
  },
15276
16062
  "z-ai/glm-5.2:batch": {
15277
16063
  id: "z-ai/glm-5.2:batch",
@@ -15387,13 +16173,13 @@ export const MODELS = {
15387
16173
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
15388
16174
  input: ["text"],
15389
16175
  cost: {
15390
- input: 0.079996,
15391
- output: 0.252,
15392
- cacheRead: 0.0252,
16176
+ input: 0.06706000000000001,
16177
+ output: 0.13412000000000002,
16178
+ cacheRead: 0.013412,
15393
16179
  cacheWrite: 0,
15394
16180
  },
15395
16181
  contextWindow: 1048576,
15396
- maxTokens: 4096,
16182
+ maxTokens: 384000,
15397
16183
  },
15398
16184
  "~google/gemini-flash-latest": {
15399
16185
  id: "~google/gemini-flash-latest",
@@ -15404,10 +16190,10 @@ export const MODELS = {
15404
16190
  reasoning: true,
15405
16191
  input: ["text", "image"],
15406
16192
  cost: {
15407
- input: 1.5,
15408
- output: 7.5,
15409
- cacheRead: 0.15,
15410
- cacheWrite: 0.0833333333333333,
16193
+ input: 0.375,
16194
+ output: 1.875,
16195
+ cacheRead: 0.0375,
16196
+ cacheWrite: 0.0208333333333333,
15411
16197
  },
15412
16198
  contextWindow: 1048576,
15413
16199
  maxTokens: 65536,
@@ -15491,7 +16277,7 @@ export const MODELS = {
15491
16277
  cost: {
15492
16278
  input: 2,
15493
16279
  output: 6,
15494
- cacheRead: 0.3,
16280
+ cacheRead: 0.5,
15495
16281
  cacheWrite: 0,
15496
16282
  },
15497
16283
  contextWindow: 500000,
@@ -16265,6 +17051,23 @@ export const MODELS = {
16265
17051
  contextWindow: 1000000,
16266
17052
  maxTokens: 64000,
16267
17053
  },
17054
+ "alibaba/qwen3.8-2.4t-a95b": {
17055
+ id: "alibaba/qwen3.8-2.4t-a95b",
17056
+ name: "Qwen3.8 2.4T A95B",
17057
+ api: "anthropic-messages",
17058
+ provider: "vercel-ai-gateway",
17059
+ baseUrl: "https://ai-gateway.vercel.sh",
17060
+ reasoning: true,
17061
+ input: ["text"],
17062
+ cost: {
17063
+ input: 2,
17064
+ output: 6,
17065
+ cacheRead: 0.25,
17066
+ cacheWrite: 0,
17067
+ },
17068
+ contextWindow: 262144,
17069
+ maxTokens: 131072,
17070
+ },
16268
17071
  "alibaba/qwen3.8-max": {
16269
17072
  id: "alibaba/qwen3.8-max",
16270
17073
  name: "Qwen 3.8 Max",
@@ -16848,6 +17651,23 @@ export const MODELS = {
16848
17651
  contextWindow: 1048600,
16849
17652
  maxTokens: 1048600,
16850
17653
  },
17654
+ "deepseek/deepseek-v4-pro-0813": {
17655
+ id: "deepseek/deepseek-v4-pro-0813",
17656
+ name: "DeepSeek V4 Pro 0813",
17657
+ api: "anthropic-messages",
17658
+ provider: "vercel-ai-gateway",
17659
+ baseUrl: "https://ai-gateway.vercel.sh",
17660
+ reasoning: true,
17661
+ input: ["text"],
17662
+ cost: {
17663
+ input: 1.32,
17664
+ output: 3.9600000000000004,
17665
+ cacheRead: 0.13199999999999998,
17666
+ cacheWrite: 0,
17667
+ },
17668
+ contextWindow: 1000000,
17669
+ maxTokens: 384000,
17670
+ },
16851
17671
  "google/gemini-2.5-flash": {
16852
17672
  id: "google/gemini-2.5-flash",
16853
17673
  name: "Gemini 2.5 Flash",
@@ -17001,6 +17821,23 @@ export const MODELS = {
17001
17821
  contextWindow: 1000000,
17002
17822
  maxTokens: 64000,
17003
17823
  },
17824
+ "google/gemini-3.7-flash": {
17825
+ id: "google/gemini-3.7-flash",
17826
+ name: "Gemini 3.7 Flash",
17827
+ api: "anthropic-messages",
17828
+ provider: "vercel-ai-gateway",
17829
+ baseUrl: "https://ai-gateway.vercel.sh",
17830
+ reasoning: true,
17831
+ input: ["text", "image"],
17832
+ cost: {
17833
+ input: 0.75,
17834
+ output: 3.75,
17835
+ cacheRead: 0.075,
17836
+ cacheWrite: 0,
17837
+ },
17838
+ contextWindow: 1000000,
17839
+ maxTokens: 65536,
17840
+ },
17004
17841
  "google/gemma-4-26b-a4b-it": {
17005
17842
  id: "google/gemma-4-26b-a4b-it",
17006
17843
  name: "Google Gemma 4 26B A4B",
@@ -17032,7 +17869,7 @@ export const MODELS = {
17032
17869
  cacheRead: 0,
17033
17870
  cacheWrite: 0,
17034
17871
  },
17035
- contextWindow: 256000,
17872
+ contextWindow: 262144,
17036
17873
  maxTokens: 131072,
17037
17874
  },
17038
17875
  "inception/mercury-2": {
@@ -17086,23 +17923,6 @@ export const MODELS = {
17086
17923
  contextWindow: 256000,
17087
17924
  maxTokens: 32000,
17088
17925
  },
17089
- "inclusionai/ling-3.0-tiny-free": {
17090
- id: "inclusionai/ling-3.0-tiny-free",
17091
- name: "Ling 3.0 Tiny (Free)",
17092
- api: "anthropic-messages",
17093
- provider: "vercel-ai-gateway",
17094
- baseUrl: "https://ai-gateway.vercel.sh",
17095
- reasoning: true,
17096
- input: ["text"],
17097
- cost: {
17098
- input: 0,
17099
- output: 0,
17100
- cacheRead: 0,
17101
- cacheWrite: 0,
17102
- },
17103
- contextWindow: 256000,
17104
- maxTokens: 32000,
17105
- },
17106
17926
  "interfaze/interfaze-beta": {
17107
17927
  id: "interfaze/interfaze-beta",
17108
17928
  name: "Interfaze Beta",
@@ -18898,6 +19718,23 @@ export const MODELS = {
18898
19718
  contextWindow: 500000,
18899
19719
  maxTokens: 500000,
18900
19720
  },
19721
+ "xai/grok-4.6": {
19722
+ id: "xai/grok-4.6",
19723
+ name: "Grok 4.6",
19724
+ api: "anthropic-messages",
19725
+ provider: "vercel-ai-gateway",
19726
+ baseUrl: "https://ai-gateway.vercel.sh",
19727
+ reasoning: true,
19728
+ input: ["text", "image"],
19729
+ cost: {
19730
+ input: 2,
19731
+ output: 6,
19732
+ cacheRead: 0.5,
19733
+ cacheWrite: 0,
19734
+ },
19735
+ contextWindow: 500000,
19736
+ maxTokens: 500000,
19737
+ },
18901
19738
  "xai/grok-build-0.1": {
18902
19739
  id: "xai/grok-build-0.1",
18903
19740
  name: "Grok Build 0.1",
@@ -19274,6 +20111,23 @@ export const MODELS = {
19274
20111
  contextWindow: 500000,
19275
20112
  maxTokens: 500000,
19276
20113
  },
20114
+ "grok-4.6": {
20115
+ id: "grok-4.6",
20116
+ name: "Grok 4.6",
20117
+ api: "openai-completions",
20118
+ provider: "xai",
20119
+ baseUrl: "https://api.x.ai/v1",
20120
+ reasoning: true,
20121
+ input: ["text", "image"],
20122
+ cost: {
20123
+ input: 2,
20124
+ output: 6,
20125
+ cacheRead: 0.5,
20126
+ cacheWrite: 0,
20127
+ },
20128
+ contextWindow: 500000,
20129
+ maxTokens: 500000,
20130
+ },
19277
20131
  "grok-build-0.1": {
19278
20132
  id: "grok-build-0.1",
19279
20133
  name: "Grok Build 0.1",
@@ -19594,6 +20448,24 @@ export const MODELS = {
19594
20448
  contextWindow: 1000000,
19595
20449
  maxTokens: 131072,
19596
20450
  },
20451
+ "glm-5.3": {
20452
+ id: "glm-5.3",
20453
+ name: "GLM-5.3",
20454
+ api: "openai-completions",
20455
+ provider: "zai",
20456
+ baseUrl: "https://api.z.ai/api/coding/paas/v4",
20457
+ compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
20458
+ reasoning: true,
20459
+ input: ["text"],
20460
+ cost: {
20461
+ input: 0,
20462
+ output: 0,
20463
+ cacheRead: 0,
20464
+ cacheWrite: 0,
20465
+ },
20466
+ contextWindow: 1000000,
20467
+ maxTokens: 131072,
20468
+ },
19597
20469
  },
19598
20470
  };
19599
20471
  //# sourceMappingURL=models.generated.js.map