@dreb/ai 2.55.0 → 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.
@@ -3504,40 +3504,6 @@ export const MODELS = {
3504
3504
  contextWindow: 131072,
3505
3505
  maxTokens: 65536,
3506
3506
  },
3507
- "gemini-2.0-flash": {
3508
- id: "gemini-2.0-flash",
3509
- name: "Gemini 2.0 Flash",
3510
- api: "google-generative-ai",
3511
- provider: "google",
3512
- baseUrl: "https://generativelanguage.googleapis.com/v1beta",
3513
- reasoning: false,
3514
- input: ["text", "image"],
3515
- cost: {
3516
- input: 0.1,
3517
- output: 0.4,
3518
- cacheRead: 0.025,
3519
- cacheWrite: 0,
3520
- },
3521
- contextWindow: 1048576,
3522
- maxTokens: 8192,
3523
- },
3524
- "gemini-2.0-flash-lite": {
3525
- id: "gemini-2.0-flash-lite",
3526
- name: "Gemini 2.0 Flash-Lite",
3527
- api: "google-generative-ai",
3528
- provider: "google",
3529
- baseUrl: "https://generativelanguage.googleapis.com/v1beta",
3530
- reasoning: false,
3531
- input: ["text", "image"],
3532
- cost: {
3533
- input: 0.075,
3534
- output: 0.3,
3535
- cacheRead: 0,
3536
- cacheWrite: 0,
3537
- },
3538
- contextWindow: 1048576,
3539
- maxTokens: 8192,
3540
- },
3541
3507
  "gemini-2.5-computer-use-preview-10-2025": {
3542
3508
  id: "gemini-2.5-computer-use-preview-10-2025",
3543
3509
  name: "Gemini 2.5 Computer Use Preview 10-2025",
@@ -3623,23 +3589,6 @@ export const MODELS = {
3623
3589
  contextWindow: 1048576,
3624
3590
  maxTokens: 65536,
3625
3591
  },
3626
- "gemini-3-pro-preview": {
3627
- id: "gemini-3-pro-preview",
3628
- name: "Gemini 3 Pro Preview",
3629
- api: "google-generative-ai",
3630
- provider: "google",
3631
- baseUrl: "https://generativelanguage.googleapis.com/v1beta",
3632
- reasoning: true,
3633
- input: ["text", "image"],
3634
- cost: {
3635
- input: 2,
3636
- output: 12,
3637
- cacheRead: 0.2,
3638
- cacheWrite: 0,
3639
- },
3640
- contextWindow: 1048576,
3641
- maxTokens: 65536,
3642
- },
3643
3592
  "gemini-3.1-flash-lite": {
3644
3593
  id: "gemini-3.1-flash-lite",
3645
3594
  name: "Gemini 3.1 Flash Lite",
@@ -9401,13 +9350,13 @@ export const MODELS = {
9401
9350
  reasoning: true,
9402
9351
  input: ["text"],
9403
9352
  cost: {
9404
- input: 0.09,
9353
+ input: 0.08,
9405
9354
  output: 0.18,
9406
- cacheRead: 0.018,
9355
+ cacheRead: 0.016,
9407
9356
  cacheWrite: 0,
9408
9357
  },
9409
9358
  contextWindow: 1048576,
9410
- maxTokens: 65536,
9359
+ maxTokens: 384000,
9411
9360
  },
9412
9361
  "deepseek/deepseek-v4-pro": {
9413
9362
  id: "deepseek/deepseek-v4-pro",
@@ -9860,13 +9809,13 @@ export const MODELS = {
9860
9809
  reasoning: true,
9861
9810
  input: ["text", "image"],
9862
9811
  cost: {
9863
- input: 0.07,
9864
- output: 0.33999999999999997,
9865
- cacheRead: 0,
9812
+ input: 0.12,
9813
+ output: 0.39999999999999997,
9814
+ cacheRead: 0.049999999999999996,
9866
9815
  cacheWrite: 0,
9867
9816
  },
9868
9817
  contextWindow: 262144,
9869
- maxTokens: 16384,
9818
+ maxTokens: 262144,
9870
9819
  },
9871
9820
  "google/gemma-4-26b-a4b-it:free": {
9872
9821
  id: "google/gemma-4-26b-a4b-it:free",
@@ -10167,12 +10116,12 @@ export const MODELS = {
10167
10116
  input: ["text", "image"],
10168
10117
  cost: {
10169
10118
  input: 0.19999999999999998,
10170
- output: 0.7999999999999999,
10119
+ output: 0.696,
10171
10120
  cacheRead: 0,
10172
10121
  cacheWrite: 0,
10173
10122
  },
10174
10123
  contextWindow: 1048576,
10175
- maxTokens: 16384,
10124
+ maxTokens: 4096,
10176
10125
  },
10177
10126
  "meta-llama/llama-4-scout": {
10178
10127
  id: "meta-llama/llama-4-scout",
@@ -10302,9 +10251,9 @@ export const MODELS = {
10302
10251
  reasoning: true,
10303
10252
  input: ["text"],
10304
10253
  cost: {
10305
- input: 0.27,
10306
- output: 1.08,
10307
- cacheRead: 0.054,
10254
+ input: 0.3,
10255
+ output: 1.2,
10256
+ cacheRead: 0.06,
10308
10257
  cacheWrite: 0,
10309
10258
  },
10310
10259
  contextWindow: 204800,
@@ -10797,11 +10746,11 @@ export const MODELS = {
10797
10746
  cost: {
10798
10747
  input: 0.049999999999999996,
10799
10748
  output: 0.19999999999999998,
10800
- cacheRead: 0.03,
10749
+ cacheRead: 0.024999999999999998,
10801
10750
  cacheWrite: 0,
10802
10751
  },
10803
10752
  contextWindow: 262144,
10804
- maxTokens: 262144,
10753
+ maxTokens: 228000,
10805
10754
  },
10806
10755
  "nvidia/nemotron-3-nano-30b-a3b:free": {
10807
10756
  id: "nvidia/nemotron-3-nano-30b-a3b:free",
@@ -11583,7 +11532,7 @@ export const MODELS = {
11583
11532
  cacheWrite: 0,
11584
11533
  },
11585
11534
  contextWindow: 128000,
11586
- maxTokens: 16384,
11535
+ maxTokens: 32000,
11587
11536
  },
11588
11537
  "openai/gpt-5.2-codex": {
11589
11538
  id: "openai/gpt-5.2-codex",
@@ -11653,23 +11602,6 @@ export const MODELS = {
11653
11602
  contextWindow: 400000,
11654
11603
  maxTokens: 128000,
11655
11604
  },
11656
- "openai/gpt-5.3-chat": {
11657
- id: "openai/gpt-5.3-chat",
11658
- name: "OpenAI: GPT-5.3 Chat",
11659
- api: "openai-completions",
11660
- provider: "openrouter",
11661
- baseUrl: "https://openrouter.ai/api/v1",
11662
- reasoning: false,
11663
- input: ["text", "image"],
11664
- cost: {
11665
- input: 1.75,
11666
- output: 14,
11667
- cacheRead: 0.175,
11668
- cacheWrite: 0,
11669
- },
11670
- contextWindow: 128000,
11671
- maxTokens: 16384,
11672
- },
11673
11605
  "openai/gpt-5.3-codex": {
11674
11606
  id: "openai/gpt-5.3-codex",
11675
11607
  name: "OpenAI: GPT-5.3-Codex",
@@ -12682,13 +12614,13 @@ export const MODELS = {
12682
12614
  reasoning: true,
12683
12615
  input: ["text"],
12684
12616
  cost: {
12685
- input: 0.22749999999999998,
12686
- output: 0.9099999999999999,
12617
+ input: 0.12,
12618
+ output: 0.24,
12687
12619
  cacheRead: 0,
12688
12620
  cacheWrite: 0,
12689
12621
  },
12690
12622
  contextWindow: 131072,
12691
- maxTokens: 8192,
12623
+ maxTokens: 16384,
12692
12624
  },
12693
12625
  "qwen/qwen3-235b-a22b": {
12694
12626
  id: "qwen/qwen3-235b-a22b",
@@ -12977,7 +12909,7 @@ export const MODELS = {
12977
12909
  cacheWrite: 0,
12978
12910
  },
12979
12911
  contextWindow: 262144,
12980
- maxTokens: 262144,
12912
+ maxTokens: 32768,
12981
12913
  },
12982
12914
  "qwen/qwen3-vl-235b-a22b-instruct": {
12983
12915
  id: "qwen/qwen3-vl-235b-a22b-instruct",
@@ -13260,7 +13192,7 @@ export const MODELS = {
13260
13192
  reasoning: true,
13261
13193
  input: ["text", "image"],
13262
13194
  cost: {
13263
- input: 0.14,
13195
+ input: 0.15,
13264
13196
  output: 1,
13265
13197
  cacheRead: 0.049999999999999996,
13266
13198
  cacheWrite: 0,
@@ -13549,13 +13481,13 @@ export const MODELS = {
13549
13481
  reasoning: true,
13550
13482
  input: ["text", "image"],
13551
13483
  cost: {
13552
- input: 1,
13484
+ input: 0.95,
13553
13485
  output: 4.05,
13554
- cacheRead: 0.16999999999999998,
13486
+ cacheRead: 0.16,
13555
13487
  cacheWrite: 0,
13556
13488
  },
13557
13489
  contextWindow: 1048576,
13558
- maxTokens: 4096,
13490
+ maxTokens: 262144,
13559
13491
  },
13560
13492
  "thinkingmachines/inkling-small": {
13561
13493
  id: "thinkingmachines/inkling-small",
@@ -13889,13 +13821,13 @@ export const MODELS = {
13889
13821
  reasoning: true,
13890
13822
  input: ["text"],
13891
13823
  cost: {
13892
- input: 0.5166,
13893
- output: 1.6236,
13894
- cacheRead: 0.09594,
13824
+ input: 0.76,
13825
+ output: 2.42,
13826
+ cacheRead: 0.14,
13895
13827
  cacheWrite: 0,
13896
13828
  },
13897
13829
  contextWindow: 1048576,
13898
- maxTokens: 131072,
13830
+ maxTokens: 262144,
13899
13831
  },
13900
13832
  "z-ai/glm-5.2:batch": {
13901
13833
  id: "z-ai/glm-5.2:batch",
@@ -14008,13 +13940,13 @@ export const MODELS = {
14008
13940
  reasoning: true,
14009
13941
  input: ["text"],
14010
13942
  cost: {
14011
- input: 0.09,
14012
- output: 0.18,
14013
- cacheRead: 0.018,
13943
+ input: 0.0798,
13944
+ output: 0.1596,
13945
+ cacheRead: 0.01596,
14014
13946
  cacheWrite: 0,
14015
13947
  },
14016
13948
  contextWindow: 1048576,
14017
- maxTokens: 65536,
13949
+ maxTokens: 131072,
14018
13950
  },
14019
13951
  "~google/gemini-flash-latest": {
14020
13952
  id: "~google/gemini-flash-latest",
@@ -14059,7 +13991,7 @@ export const MODELS = {
14059
13991
  reasoning: true,
14060
13992
  input: ["text", "image"],
14061
13993
  cost: {
14062
- input: 2.5,
13994
+ input: 2.8,
14063
13995
  output: 14,
14064
13996
  cacheRead: 0.29,
14065
13997
  cacheWrite: 0,
@@ -14800,6 +14732,23 @@ export const MODELS = {
14800
14732
  contextWindow: 1000000,
14801
14733
  maxTokens: 128000,
14802
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
+ },
14803
14752
  "anthropic/claude-sonnet-4": {
14804
14753
  id: "anthropic/claude-sonnet-4",
14805
14754
  name: "Claude Sonnet 4",
@@ -15081,9 +15030,9 @@ export const MODELS = {
15081
15030
  reasoning: true,
15082
15031
  input: ["text"],
15083
15032
  cost: {
15084
- input: 0.13,
15085
- output: 0.26,
15086
- cacheRead: 0.028,
15033
+ input: 0.19999999999999998,
15034
+ output: 0.39999999999999997,
15035
+ cacheRead: 0.04,
15087
15036
  cacheWrite: 0,
15088
15037
  },
15089
15038
  contextWindow: 1000000,
@@ -15261,7 +15210,7 @@ export const MODELS = {
15261
15210
  },
15262
15211
  "google/gemma-4-26b-a4b-it": {
15263
15212
  id: "google/gemma-4-26b-a4b-it",
15264
- name: "Gemma 4 26B A4B IT",
15213
+ name: "Google Gemma 4 26B A4B",
15265
15214
  api: "anthropic-messages",
15266
15215
  provider: "vercel-ai-gateway",
15267
15216
  baseUrl: "https://ai-gateway.vercel.sh",
@@ -16432,23 +16381,6 @@ export const MODELS = {
16432
16381
  contextWindow: 400000,
16433
16382
  maxTokens: 128000,
16434
16383
  },
16435
- "openai/gpt-5.1-instant": {
16436
- id: "openai/gpt-5.1-instant",
16437
- name: "GPT-5.1 Instant",
16438
- api: "anthropic-messages",
16439
- provider: "vercel-ai-gateway",
16440
- baseUrl: "https://ai-gateway.vercel.sh",
16441
- reasoning: false,
16442
- input: ["text", "image"],
16443
- cost: {
16444
- input: 1.25,
16445
- output: 10,
16446
- cacheRead: 0.13,
16447
- cacheWrite: 0,
16448
- },
16449
- contextWindow: 128000,
16450
- maxTokens: 16384,
16451
- },
16452
16384
  "openai/gpt-5.1-thinking": {
16453
16385
  id: "openai/gpt-5.1-thinking",
16454
16386
  name: "GPT 5.1 Thinking",
@@ -16517,23 +16449,6 @@ export const MODELS = {
16517
16449
  contextWindow: 400000,
16518
16450
  maxTokens: 128000,
16519
16451
  },
16520
- "openai/gpt-5.3-chat": {
16521
- id: "openai/gpt-5.3-chat",
16522
- name: "GPT-5.3 Chat",
16523
- api: "anthropic-messages",
16524
- provider: "vercel-ai-gateway",
16525
- baseUrl: "https://ai-gateway.vercel.sh",
16526
- reasoning: false,
16527
- input: ["text", "image"],
16528
- cost: {
16529
- input: 1.75,
16530
- output: 14,
16531
- cacheRead: 0.175,
16532
- cacheWrite: 0,
16533
- },
16534
- contextWindow: 128000,
16535
- maxTokens: 16384,
16536
- },
16537
16452
  "openai/gpt-5.3-codex": {
16538
16453
  id: "openai/gpt-5.3-codex",
16539
16454
  name: "GPT 5.3 Codex",