@dreb/ai 2.54.0 → 2.55.1

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.
@@ -3430,6 +3430,25 @@ export const MODELS = {
3430
3430
  contextWindow: 256000,
3431
3431
  maxTokens: 32000,
3432
3432
  },
3433
+ "kimi-k3": {
3434
+ id: "kimi-k3",
3435
+ name: "Kimi K3",
3436
+ api: "openai-completions",
3437
+ provider: "github-copilot",
3438
+ baseUrl: "https://api.individual.githubcopilot.com",
3439
+ 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" },
3440
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
3441
+ reasoning: true,
3442
+ input: ["text", "image"],
3443
+ cost: {
3444
+ input: 3,
3445
+ output: 15,
3446
+ cacheRead: 0.3,
3447
+ cacheWrite: 0,
3448
+ },
3449
+ contextWindow: 1048576,
3450
+ maxTokens: 131072,
3451
+ },
3433
3452
  "mai-code-1-flash-picker": {
3434
3453
  id: "mai-code-1-flash-picker",
3435
3454
  name: "MAI-Code-1-Flash",
@@ -3485,40 +3504,6 @@ export const MODELS = {
3485
3504
  contextWindow: 131072,
3486
3505
  maxTokens: 65536,
3487
3506
  },
3488
- "gemini-2.0-flash": {
3489
- id: "gemini-2.0-flash",
3490
- name: "Gemini 2.0 Flash",
3491
- api: "google-generative-ai",
3492
- provider: "google",
3493
- baseUrl: "https://generativelanguage.googleapis.com/v1beta",
3494
- reasoning: false,
3495
- input: ["text", "image"],
3496
- cost: {
3497
- input: 0.1,
3498
- output: 0.4,
3499
- cacheRead: 0.025,
3500
- cacheWrite: 0,
3501
- },
3502
- contextWindow: 1048576,
3503
- maxTokens: 8192,
3504
- },
3505
- "gemini-2.0-flash-lite": {
3506
- id: "gemini-2.0-flash-lite",
3507
- name: "Gemini 2.0 Flash-Lite",
3508
- api: "google-generative-ai",
3509
- provider: "google",
3510
- baseUrl: "https://generativelanguage.googleapis.com/v1beta",
3511
- reasoning: false,
3512
- input: ["text", "image"],
3513
- cost: {
3514
- input: 0.075,
3515
- output: 0.3,
3516
- cacheRead: 0,
3517
- cacheWrite: 0,
3518
- },
3519
- contextWindow: 1048576,
3520
- maxTokens: 8192,
3521
- },
3522
3507
  "gemini-2.5-computer-use-preview-10-2025": {
3523
3508
  id: "gemini-2.5-computer-use-preview-10-2025",
3524
3509
  name: "Gemini 2.5 Computer Use Preview 10-2025",
@@ -3604,23 +3589,6 @@ export const MODELS = {
3604
3589
  contextWindow: 1048576,
3605
3590
  maxTokens: 65536,
3606
3591
  },
3607
- "gemini-3-pro-preview": {
3608
- id: "gemini-3-pro-preview",
3609
- name: "Gemini 3 Pro Preview",
3610
- api: "google-generative-ai",
3611
- provider: "google",
3612
- baseUrl: "https://generativelanguage.googleapis.com/v1beta",
3613
- reasoning: true,
3614
- input: ["text", "image"],
3615
- cost: {
3616
- input: 2,
3617
- output: 12,
3618
- cacheRead: 0.2,
3619
- cacheWrite: 0,
3620
- },
3621
- contextWindow: 1048576,
3622
- maxTokens: 65536,
3623
- },
3624
3592
  "gemini-3.1-flash-lite": {
3625
3593
  id: "gemini-3.1-flash-lite",
3626
3594
  name: "Gemini 3.1 Flash Lite",
@@ -7159,23 +7127,6 @@ export const MODELS = {
7159
7127
  contextWindow: 200000,
7160
7128
  maxTokens: 64000,
7161
7129
  },
7162
- "claude-opus-4-1": {
7163
- id: "claude-opus-4-1",
7164
- name: "Claude Opus 4.1",
7165
- api: "anthropic-messages",
7166
- provider: "opencode",
7167
- baseUrl: "https://opencode.ai/zen",
7168
- reasoning: true,
7169
- input: ["text", "image"],
7170
- cost: {
7171
- input: 15,
7172
- output: 75,
7173
- cacheRead: 1.5,
7174
- cacheWrite: 18.75,
7175
- },
7176
- contextWindow: 200000,
7177
- maxTokens: 32000,
7178
- },
7179
7130
  "claude-opus-4-5": {
7180
7131
  id: "claude-opus-4-5",
7181
7132
  name: "Claude Opus 4.5",
@@ -7331,7 +7282,7 @@ export const MODELS = {
7331
7282
  },
7332
7283
  "deepseek-v4-flash": {
7333
7284
  id: "deepseek-v4-flash",
7334
- name: "DeepSeek V4 Flash (New)",
7285
+ name: "DeepSeek V4 Flash",
7335
7286
  api: "openai-completions",
7336
7287
  provider: "opencode",
7337
7288
  baseUrl: "https://opencode.ai/zen/v1",
@@ -7348,7 +7299,7 @@ export const MODELS = {
7348
7299
  },
7349
7300
  "deepseek-v4-flash-free": {
7350
7301
  id: "deepseek-v4-flash-free",
7351
- name: "DeepSeek V4 Flash Free (New)",
7302
+ name: "DeepSeek V4 Flash Free",
7352
7303
  api: "openai-completions",
7353
7304
  provider: "opencode",
7354
7305
  baseUrl: "https://opencode.ai/zen/v1",
@@ -7859,7 +7810,7 @@ export const MODELS = {
7859
7810
  "grok-build-0.1": {
7860
7811
  id: "grok-build-0.1",
7861
7812
  name: "Grok Build 0.1",
7862
- api: "openai-completions",
7813
+ api: "openai-responses",
7863
7814
  provider: "opencode",
7864
7815
  baseUrl: "https://opencode.ai/zen/v1",
7865
7816
  reasoning: true,
@@ -7958,9 +7909,9 @@ export const MODELS = {
7958
7909
  contextWindow: 256000,
7959
7910
  maxTokens: 32000,
7960
7911
  },
7961
- "ling-3.0-flash-free": {
7962
- id: "ling-3.0-flash-free",
7963
- name: "Ling-3.0-flash Free",
7912
+ "ling-3.0-tiny-free": {
7913
+ id: "ling-3.0-tiny-free",
7914
+ name: "Ling-3.0-tiny Free",
7964
7915
  api: "openai-completions",
7965
7916
  provider: "opencode",
7966
7917
  baseUrl: "https://opencode.ai/zen/v1",
@@ -8132,16 +8083,16 @@ export const MODELS = {
8132
8083
  "opencode-go": {
8133
8084
  "deepseek-v4-flash": {
8134
8085
  id: "deepseek-v4-flash",
8135
- name: "DeepSeek V4 Flash (New)",
8086
+ name: "DeepSeek V4 Flash (2x usage)",
8136
8087
  api: "openai-completions",
8137
8088
  provider: "opencode-go",
8138
8089
  baseUrl: "https://opencode.ai/zen/go/v1",
8139
8090
  reasoning: true,
8140
8091
  input: ["text"],
8141
8092
  cost: {
8142
- input: 0.14,
8143
- output: 0.28,
8144
- cacheRead: 0.0028,
8093
+ input: 0.07,
8094
+ output: 0.14,
8095
+ cacheRead: 0.0014,
8145
8096
  cacheWrite: 0,
8146
8097
  },
8147
8098
  contextWindow: 1000000,
@@ -9382,13 +9333,13 @@ export const MODELS = {
9382
9333
  reasoning: true,
9383
9334
  input: ["text"],
9384
9335
  cost: {
9385
- input: 0.0882,
9386
- output: 0.1764,
9387
- cacheRead: 0.01764,
9336
+ input: 0.14,
9337
+ output: 0.28,
9338
+ cacheRead: 0.028,
9388
9339
  cacheWrite: 0,
9389
9340
  },
9390
9341
  contextWindow: 1048576,
9391
- maxTokens: 131072,
9342
+ maxTokens: 393216,
9392
9343
  },
9393
9344
  "deepseek/deepseek-v4-flash-0731": {
9394
9345
  id: "deepseek/deepseek-v4-flash-0731",
@@ -9399,13 +9350,13 @@ export const MODELS = {
9399
9350
  reasoning: true,
9400
9351
  input: ["text"],
9401
9352
  cost: {
9402
- input: 0.09,
9353
+ input: 0.08,
9403
9354
  output: 0.18,
9404
- cacheRead: 0.018,
9355
+ cacheRead: 0.016,
9405
9356
  cacheWrite: 0,
9406
9357
  },
9407
9358
  contextWindow: 1048576,
9408
- maxTokens: 65536,
9359
+ maxTokens: 384000,
9409
9360
  },
9410
9361
  "deepseek/deepseek-v4-pro": {
9411
9362
  id: "deepseek/deepseek-v4-pro",
@@ -9575,7 +9526,7 @@ export const MODELS = {
9575
9526
  cacheWrite: 0.0833333333333333,
9576
9527
  },
9577
9528
  contextWindow: 1048576,
9578
- maxTokens: 65535,
9529
+ maxTokens: 65536,
9579
9530
  },
9580
9531
  "google/gemini-3-flash-preview:batch": {
9581
9532
  id: "google/gemini-3-flash-preview:batch",
@@ -9592,7 +9543,7 @@ export const MODELS = {
9592
9543
  cacheWrite: 0,
9593
9544
  },
9594
9545
  contextWindow: 1048576,
9595
- maxTokens: 65535,
9546
+ maxTokens: 65536,
9596
9547
  },
9597
9548
  "google/gemini-3-pro-image": {
9598
9549
  id: "google/gemini-3-pro-image",
@@ -9858,13 +9809,13 @@ export const MODELS = {
9858
9809
  reasoning: true,
9859
9810
  input: ["text", "image"],
9860
9811
  cost: {
9861
- input: 0.07,
9862
- output: 0.33999999999999997,
9863
- cacheRead: 0,
9812
+ input: 0.12,
9813
+ output: 0.39999999999999997,
9814
+ cacheRead: 0.049999999999999996,
9864
9815
  cacheWrite: 0,
9865
9816
  },
9866
9817
  contextWindow: 262144,
9867
- maxTokens: 16384,
9818
+ maxTokens: 262144,
9868
9819
  },
9869
9820
  "google/gemma-4-26b-a4b-it:free": {
9870
9821
  id: "google/gemma-4-26b-a4b-it:free",
@@ -9994,17 +9945,17 @@ export const MODELS = {
9994
9945
  reasoning: true,
9995
9946
  input: ["text"],
9996
9947
  cost: {
9997
- input: 0.075,
9998
- output: 0.22,
9999
- cacheRead: 0.015,
9948
+ input: 0.020999999999999998,
9949
+ output: 0.063,
9950
+ cacheRead: 0.004200000000000001,
10000
9951
  cacheWrite: 0,
10001
9952
  },
10002
- contextWindow: 131072,
9953
+ contextWindow: 262144,
10003
9954
  maxTokens: 32768,
10004
9955
  },
10005
- "inclusionai/ling-3.0-flash:free": {
10006
- id: "inclusionai/ling-3.0-flash:free",
10007
- name: "Ling-3.0-flash (free)",
9956
+ "inclusionai/ling-3.0-tiny:free": {
9957
+ id: "inclusionai/ling-3.0-tiny:free",
9958
+ name: "inclusionAI: Ling 3.0 Tiny (free)",
10008
9959
  api: "openai-completions",
10009
9960
  provider: "openrouter",
10010
9961
  baseUrl: "https://openrouter.ai/api/v1",
@@ -10165,12 +10116,12 @@ export const MODELS = {
10165
10116
  input: ["text", "image"],
10166
10117
  cost: {
10167
10118
  input: 0.19999999999999998,
10168
- output: 0.7999999999999999,
10119
+ output: 0.696,
10169
10120
  cacheRead: 0,
10170
10121
  cacheWrite: 0,
10171
10122
  },
10172
10123
  contextWindow: 1048576,
10173
- maxTokens: 16384,
10124
+ maxTokens: 4096,
10174
10125
  },
10175
10126
  "meta-llama/llama-4-scout": {
10176
10127
  id: "meta-llama/llama-4-scout",
@@ -10300,9 +10251,9 @@ export const MODELS = {
10300
10251
  reasoning: true,
10301
10252
  input: ["text"],
10302
10253
  cost: {
10303
- input: 0.27,
10304
- output: 1.08,
10305
- cacheRead: 0.054,
10254
+ input: 0.3,
10255
+ output: 1.2,
10256
+ cacheRead: 0.06,
10306
10257
  cacheWrite: 0,
10307
10258
  },
10308
10259
  contextWindow: 204800,
@@ -10691,9 +10642,9 @@ export const MODELS = {
10691
10642
  reasoning: true,
10692
10643
  input: ["text", "image"],
10693
10644
  cost: {
10694
- input: 0.5700000000000001,
10695
- output: 2.4,
10696
- cacheRead: 0.096,
10645
+ input: 0.5795,
10646
+ output: 2.44,
10647
+ cacheRead: 0.0976,
10697
10648
  cacheWrite: 0,
10698
10649
  },
10699
10650
  contextWindow: 262144,
@@ -10795,11 +10746,11 @@ export const MODELS = {
10795
10746
  cost: {
10796
10747
  input: 0.049999999999999996,
10797
10748
  output: 0.19999999999999998,
10798
- cacheRead: 0.03,
10749
+ cacheRead: 0.024999999999999998,
10799
10750
  cacheWrite: 0,
10800
10751
  },
10801
10752
  contextWindow: 262144,
10802
- maxTokens: 262144,
10753
+ maxTokens: 228000,
10803
10754
  },
10804
10755
  "nvidia/nemotron-3-nano-30b-a3b:free": {
10805
10756
  id: "nvidia/nemotron-3-nano-30b-a3b:free",
@@ -11581,7 +11532,7 @@ export const MODELS = {
11581
11532
  cacheWrite: 0,
11582
11533
  },
11583
11534
  contextWindow: 128000,
11584
- maxTokens: 16384,
11535
+ maxTokens: 32000,
11585
11536
  },
11586
11537
  "openai/gpt-5.2-codex": {
11587
11538
  id: "openai/gpt-5.2-codex",
@@ -11651,23 +11602,6 @@ export const MODELS = {
11651
11602
  contextWindow: 400000,
11652
11603
  maxTokens: 128000,
11653
11604
  },
11654
- "openai/gpt-5.3-chat": {
11655
- id: "openai/gpt-5.3-chat",
11656
- name: "OpenAI: GPT-5.3 Chat",
11657
- api: "openai-completions",
11658
- provider: "openrouter",
11659
- baseUrl: "https://openrouter.ai/api/v1",
11660
- reasoning: false,
11661
- input: ["text", "image"],
11662
- cost: {
11663
- input: 1.75,
11664
- output: 14,
11665
- cacheRead: 0.175,
11666
- cacheWrite: 0,
11667
- },
11668
- contextWindow: 128000,
11669
- maxTokens: 16384,
11670
- },
11671
11605
  "openai/gpt-5.3-codex": {
11672
11606
  id: "openai/gpt-5.3-codex",
11673
11607
  name: "OpenAI: GPT-5.3-Codex",
@@ -12680,13 +12614,13 @@ export const MODELS = {
12680
12614
  reasoning: true,
12681
12615
  input: ["text"],
12682
12616
  cost: {
12683
- input: 0.22749999999999998,
12684
- output: 0.9099999999999999,
12617
+ input: 0.12,
12618
+ output: 0.24,
12685
12619
  cacheRead: 0,
12686
12620
  cacheWrite: 0,
12687
12621
  },
12688
12622
  contextWindow: 131072,
12689
- maxTokens: 8192,
12623
+ maxTokens: 16384,
12690
12624
  },
12691
12625
  "qwen/qwen3-235b-a22b": {
12692
12626
  id: "qwen/qwen3-235b-a22b",
@@ -12975,7 +12909,7 @@ export const MODELS = {
12975
12909
  cacheWrite: 0,
12976
12910
  },
12977
12911
  contextWindow: 262144,
12978
- maxTokens: 4096,
12912
+ maxTokens: 32768,
12979
12913
  },
12980
12914
  "qwen/qwen3-vl-235b-a22b-instruct": {
12981
12915
  id: "qwen/qwen3-vl-235b-a22b-instruct",
@@ -13003,8 +12937,8 @@ export const MODELS = {
13003
12937
  reasoning: true,
13004
12938
  input: ["text", "image"],
13005
12939
  cost: {
13006
- input: 0.98,
13007
- output: 3.95,
12940
+ input: 0.39999999999999997,
12941
+ output: 4,
13008
12942
  cacheRead: 0,
13009
12943
  cacheWrite: 0,
13010
12944
  },
@@ -13105,13 +13039,13 @@ export const MODELS = {
13105
13039
  reasoning: true,
13106
13040
  input: ["text", "image"],
13107
13041
  cost: {
13108
- input: 0.26,
13109
- output: 2.08,
13042
+ input: 0.29,
13043
+ output: 2.4,
13110
13044
  cacheRead: 0,
13111
13045
  cacheWrite: 0,
13112
13046
  },
13113
13047
  contextWindow: 262144,
13114
- maxTokens: 65536,
13048
+ maxTokens: 81920,
13115
13049
  },
13116
13050
  "qwen/qwen3.5-27b": {
13117
13051
  id: "qwen/qwen3.5-27b",
@@ -13258,9 +13192,9 @@ export const MODELS = {
13258
13192
  reasoning: true,
13259
13193
  input: ["text", "image"],
13260
13194
  cost: {
13261
- input: 0.14,
13195
+ input: 0.15,
13262
13196
  output: 1,
13263
- cacheRead: 0,
13197
+ cacheRead: 0.049999999999999996,
13264
13198
  cacheWrite: 0,
13265
13199
  },
13266
13200
  contextWindow: 262144,
@@ -13547,13 +13481,13 @@ export const MODELS = {
13547
13481
  reasoning: true,
13548
13482
  input: ["text", "image"],
13549
13483
  cost: {
13550
- input: 1,
13484
+ input: 0.95,
13551
13485
  output: 4.05,
13552
- cacheRead: 0.16999999999999998,
13486
+ cacheRead: 0.16,
13553
13487
  cacheWrite: 0,
13554
13488
  },
13555
13489
  contextWindow: 1048576,
13556
- maxTokens: 4096,
13490
+ maxTokens: 262144,
13557
13491
  },
13558
13492
  "thinkingmachines/inkling-small": {
13559
13493
  id: "thinkingmachines/inkling-small",
@@ -13564,13 +13498,13 @@ export const MODELS = {
13564
13498
  reasoning: true,
13565
13499
  input: ["text", "image"],
13566
13500
  cost: {
13567
- input: 0.5,
13501
+ input: 0.44999999999999996,
13568
13502
  output: 1.2,
13569
13503
  cacheRead: 0.09999999999999999,
13570
13504
  cacheWrite: 0,
13571
13505
  },
13572
13506
  contextWindow: 524288,
13573
- maxTokens: 4096,
13507
+ maxTokens: 262144,
13574
13508
  },
13575
13509
  "thinkingmachines/inkling:batch": {
13576
13510
  id: "thinkingmachines/inkling:batch",
@@ -13887,13 +13821,13 @@ export const MODELS = {
13887
13821
  reasoning: true,
13888
13822
  input: ["text"],
13889
13823
  cost: {
13890
- input: 0.56,
13891
- output: 1.76,
13892
- cacheRead: 0.10400000000000001,
13824
+ input: 0.76,
13825
+ output: 2.42,
13826
+ cacheRead: 0.14,
13893
13827
  cacheWrite: 0,
13894
13828
  },
13895
13829
  contextWindow: 1048576,
13896
- maxTokens: 128000,
13830
+ maxTokens: 262144,
13897
13831
  },
13898
13832
  "z-ai/glm-5.2:batch": {
13899
13833
  id: "z-ai/glm-5.2:batch",
@@ -14006,13 +13940,13 @@ export const MODELS = {
14006
13940
  reasoning: true,
14007
13941
  input: ["text"],
14008
13942
  cost: {
14009
- input: 0.09,
14010
- output: 0.18,
14011
- cacheRead: 0.018,
13943
+ input: 0.0798,
13944
+ output: 0.1596,
13945
+ cacheRead: 0.01596,
14012
13946
  cacheWrite: 0,
14013
13947
  },
14014
13948
  contextWindow: 1048576,
14015
- maxTokens: 65536,
13949
+ maxTokens: 131072,
14016
13950
  },
14017
13951
  "~google/gemini-flash-latest": {
14018
13952
  id: "~google/gemini-flash-latest",
@@ -14057,7 +13991,7 @@ export const MODELS = {
14057
13991
  reasoning: true,
14058
13992
  input: ["text", "image"],
14059
13993
  cost: {
14060
- input: 2.9000000000000004,
13994
+ input: 2.8,
14061
13995
  output: 14,
14062
13996
  cacheRead: 0.29,
14063
13997
  cacheWrite: 0,
@@ -14798,6 +14732,23 @@ export const MODELS = {
14798
14732
  contextWindow: 1000000,
14799
14733
  maxTokens: 128000,
14800
14734
  },
14735
+ "anthropic/claude-opus-5-fast": {
14736
+ id: "anthropic/claude-opus-5-fast",
14737
+ name: "Claude Opus 5 (Fast)",
14738
+ api: "anthropic-messages",
14739
+ provider: "vercel-ai-gateway",
14740
+ baseUrl: "https://ai-gateway.vercel.sh",
14741
+ reasoning: true,
14742
+ input: ["text", "image"],
14743
+ cost: {
14744
+ input: 10,
14745
+ output: 50,
14746
+ cacheRead: 1,
14747
+ cacheWrite: 12.5,
14748
+ },
14749
+ contextWindow: 1000000,
14750
+ maxTokens: 128000,
14751
+ },
14801
14752
  "anthropic/claude-sonnet-4": {
14802
14753
  id: "anthropic/claude-sonnet-4",
14803
14754
  name: "Claude Sonnet 4",
@@ -15079,9 +15030,9 @@ export const MODELS = {
15079
15030
  reasoning: true,
15080
15031
  input: ["text"],
15081
15032
  cost: {
15082
- input: 0.13,
15083
- output: 0.26,
15084
- cacheRead: 0.028,
15033
+ input: 0.19999999999999998,
15034
+ output: 0.39999999999999997,
15035
+ cacheRead: 0.04,
15085
15036
  cacheWrite: 0,
15086
15037
  },
15087
15038
  contextWindow: 1000000,
@@ -15259,7 +15210,7 @@ export const MODELS = {
15259
15210
  },
15260
15211
  "google/gemma-4-26b-a4b-it": {
15261
15212
  id: "google/gemma-4-26b-a4b-it",
15262
- name: "Gemma 4 26B A4B IT",
15213
+ name: "Google Gemma 4 26B A4B",
15263
15214
  api: "anthropic-messages",
15264
15215
  provider: "vercel-ai-gateway",
15265
15216
  baseUrl: "https://ai-gateway.vercel.sh",
@@ -15325,14 +15276,31 @@ export const MODELS = {
15325
15276
  contextWindow: 32000,
15326
15277
  maxTokens: 16384,
15327
15278
  },
15328
- "inclusionai/ling-3.0-flash-free": {
15329
- id: "inclusionai/ling-3.0-flash-free",
15279
+ "inclusionai/ling-3.0-flash": {
15280
+ id: "inclusionai/ling-3.0-flash",
15330
15281
  name: "Ling 3.0 Flash",
15331
15282
  api: "anthropic-messages",
15332
15283
  provider: "vercel-ai-gateway",
15333
15284
  baseUrl: "https://ai-gateway.vercel.sh",
15334
15285
  reasoning: true,
15335
15286
  input: ["text"],
15287
+ cost: {
15288
+ input: 0.06,
15289
+ output: 0.18,
15290
+ cacheRead: 0.012,
15291
+ cacheWrite: 0,
15292
+ },
15293
+ contextWindow: 256000,
15294
+ maxTokens: 32000,
15295
+ },
15296
+ "inclusionai/ling-3.0-tiny-free": {
15297
+ id: "inclusionai/ling-3.0-tiny-free",
15298
+ name: "Ling 3.0 Tiny (Free)",
15299
+ api: "anthropic-messages",
15300
+ provider: "vercel-ai-gateway",
15301
+ baseUrl: "https://ai-gateway.vercel.sh",
15302
+ reasoning: true,
15303
+ input: ["text"],
15336
15304
  cost: {
15337
15305
  input: 0,
15338
15306
  output: 0,
@@ -15340,7 +15308,7 @@ export const MODELS = {
15340
15308
  cacheWrite: 0,
15341
15309
  },
15342
15310
  contextWindow: 256000,
15343
- maxTokens: 256000,
15311
+ maxTokens: 32000,
15344
15312
  },
15345
15313
  "interfaze/interfaze-beta": {
15346
15314
  id: "interfaze/interfaze-beta",
@@ -16413,23 +16381,6 @@ export const MODELS = {
16413
16381
  contextWindow: 400000,
16414
16382
  maxTokens: 128000,
16415
16383
  },
16416
- "openai/gpt-5.1-instant": {
16417
- id: "openai/gpt-5.1-instant",
16418
- name: "GPT-5.1 Instant",
16419
- api: "anthropic-messages",
16420
- provider: "vercel-ai-gateway",
16421
- baseUrl: "https://ai-gateway.vercel.sh",
16422
- reasoning: false,
16423
- input: ["text", "image"],
16424
- cost: {
16425
- input: 1.25,
16426
- output: 10,
16427
- cacheRead: 0.13,
16428
- cacheWrite: 0,
16429
- },
16430
- contextWindow: 128000,
16431
- maxTokens: 16384,
16432
- },
16433
16384
  "openai/gpt-5.1-thinking": {
16434
16385
  id: "openai/gpt-5.1-thinking",
16435
16386
  name: "GPT 5.1 Thinking",
@@ -16498,23 +16449,6 @@ export const MODELS = {
16498
16449
  contextWindow: 400000,
16499
16450
  maxTokens: 128000,
16500
16451
  },
16501
- "openai/gpt-5.3-chat": {
16502
- id: "openai/gpt-5.3-chat",
16503
- name: "GPT-5.3 Chat",
16504
- api: "anthropic-messages",
16505
- provider: "vercel-ai-gateway",
16506
- baseUrl: "https://ai-gateway.vercel.sh",
16507
- reasoning: false,
16508
- input: ["text", "image"],
16509
- cost: {
16510
- input: 1.75,
16511
- output: 14,
16512
- cacheRead: 0.175,
16513
- cacheWrite: 0,
16514
- },
16515
- contextWindow: 128000,
16516
- maxTokens: 16384,
16517
- },
16518
16452
  "openai/gpt-5.3-codex": {
16519
16453
  id: "openai/gpt-5.3-codex",
16520
16454
  name: "GPT 5.3 Codex",
@@ -17396,8 +17330,8 @@ export const MODELS = {
17396
17330
  cacheRead: 0.26,
17397
17331
  cacheWrite: 0,
17398
17332
  },
17399
- contextWindow: 202000,
17400
- maxTokens: 202000,
17333
+ contextWindow: 202800,
17334
+ maxTokens: 64000,
17401
17335
  },
17402
17336
  "zai/glm-5.2": {
17403
17337
  id: "zai/glm-5.2",