@dreb/ai 2.56.0 → 2.57.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -3761,6 +3761,23 @@ export const MODELS = {
3761
3761
  contextWindow: 1048576,
3762
3762
  maxTokens: 65536,
3763
3763
  },
3764
+ "gemini-3.7-flash": {
3765
+ id: "gemini-3.7-flash",
3766
+ name: "Gemini 3.7 Flash",
3767
+ api: "google-generative-ai",
3768
+ provider: "google",
3769
+ baseUrl: "https://generativelanguage.googleapis.com/v1beta",
3770
+ reasoning: true,
3771
+ input: ["text", "image"],
3772
+ cost: {
3773
+ input: 0.75,
3774
+ output: 3.75,
3775
+ cacheRead: 0.075,
3776
+ cacheWrite: 0,
3777
+ },
3778
+ contextWindow: 1048576,
3779
+ maxTokens: 65536,
3780
+ },
3764
3781
  "gemini-flash-latest": {
3765
3782
  id: "gemini-flash-latest",
3766
3783
  name: "Gemini Flash Latest",
@@ -7435,6 +7452,23 @@ export const MODELS = {
7435
7452
  contextWindow: 1048576,
7436
7453
  maxTokens: 65536,
7437
7454
  },
7455
+ "gemini-3.7-flash": {
7456
+ id: "gemini-3.7-flash",
7457
+ name: "Gemini 3.7 Flash",
7458
+ api: "google-generative-ai",
7459
+ provider: "opencode",
7460
+ baseUrl: "https://opencode.ai/zen/v1",
7461
+ reasoning: true,
7462
+ input: ["text", "image"],
7463
+ cost: {
7464
+ input: 1.5,
7465
+ output: 7.5,
7466
+ cacheRead: 0.15,
7467
+ cacheWrite: 0,
7468
+ },
7469
+ contextWindow: 1048576,
7470
+ maxTokens: 65536,
7471
+ },
7438
7472
  "glm-5": {
7439
7473
  id: "glm-5",
7440
7474
  name: "GLM-5",
@@ -7962,23 +7996,6 @@ export const MODELS = {
7962
7996
  contextWindow: 256000,
7963
7997
  maxTokens: 32000,
7964
7998
  },
7965
- "ling-3.0-tiny-free": {
7966
- id: "ling-3.0-tiny-free",
7967
- name: "Ling-3.0-tiny Free",
7968
- api: "openai-completions",
7969
- provider: "opencode",
7970
- baseUrl: "https://opencode.ai/zen/v1",
7971
- reasoning: true,
7972
- input: ["text"],
7973
- cost: {
7974
- input: 0,
7975
- output: 0,
7976
- cacheRead: 0,
7977
- cacheWrite: 0,
7978
- },
7979
- contextWindow: 262144,
7980
- maxTokens: 32768,
7981
- },
7982
7999
  "mimo-v2.5-free": {
7983
8000
  id: "mimo-v2.5-free",
7984
8001
  name: "MiMo V2.5 Free",
@@ -9323,7 +9340,7 @@ export const MODELS = {
9323
9340
  cacheRead: 0,
9324
9341
  cacheWrite: 0,
9325
9342
  },
9326
- contextWindow: 163840,
9343
+ contextWindow: 64000,
9327
9344
  maxTokens: 16000,
9328
9345
  },
9329
9346
  "deepseek/deepseek-r1-0528": {
@@ -9828,10 +9845,10 @@ export const MODELS = {
9828
9845
  reasoning: true,
9829
9846
  input: ["text", "image"],
9830
9847
  cost: {
9831
- input: 1.5,
9832
- output: 7.5,
9833
- cacheRead: 0.15,
9834
- cacheWrite: 0.0833333333333333,
9848
+ input: 0.75,
9849
+ output: 3.75,
9850
+ cacheRead: 0.075,
9851
+ cacheWrite: 0.0416666666666667,
9835
9852
  },
9836
9853
  contextWindow: 1048576,
9837
9854
  maxTokens: 65536,
@@ -9845,10 +9862,44 @@ export const MODELS = {
9845
9862
  reasoning: true,
9846
9863
  input: ["text", "image"],
9847
9864
  cost: {
9848
- input: 0.75,
9849
- output: 3.75,
9850
- cacheRead: 0.075,
9851
- cacheWrite: 0.0833333333333333,
9865
+ input: 0.375,
9866
+ output: 1.875,
9867
+ cacheRead: 0.0375,
9868
+ cacheWrite: 0.0416666666666667,
9869
+ },
9870
+ contextWindow: 1048576,
9871
+ maxTokens: 65536,
9872
+ },
9873
+ "google/gemini-3.7-flash": {
9874
+ id: "google/gemini-3.7-flash",
9875
+ name: "Google: Gemini 3.7 Flash",
9876
+ api: "openai-completions",
9877
+ provider: "openrouter",
9878
+ baseUrl: "https://openrouter.ai/api/v1",
9879
+ reasoning: true,
9880
+ input: ["text", "image"],
9881
+ cost: {
9882
+ input: 0.375,
9883
+ output: 1.875,
9884
+ cacheRead: 0.0375,
9885
+ cacheWrite: 0.0208333333333333,
9886
+ },
9887
+ contextWindow: 1048576,
9888
+ maxTokens: 65536,
9889
+ },
9890
+ "google/gemini-3.7-flash:batch": {
9891
+ id: "google/gemini-3.7-flash:batch",
9892
+ name: "Google: Gemini 3.7 Flash (batch)",
9893
+ api: "openai-completions",
9894
+ provider: "openrouter",
9895
+ baseUrl: "https://openrouter.ai/api/v1",
9896
+ reasoning: true,
9897
+ input: ["text", "image"],
9898
+ cost: {
9899
+ input: 0.1875,
9900
+ output: 0.9375,
9901
+ cacheRead: 0.01875,
9902
+ cacheWrite: 0.0208333333333333,
9852
9903
  },
9853
9904
  contextWindow: 1048576,
9854
9905
  maxTokens: 65536,
@@ -10040,23 +10091,6 @@ export const MODELS = {
10040
10091
  contextWindow: 262144,
10041
10092
  maxTokens: 32768,
10042
10093
  },
10043
- "inclusionai/ling-3.0-tiny:free": {
10044
- id: "inclusionai/ling-3.0-tiny:free",
10045
- name: "inclusionAI: Ling 3.0 Tiny (free)",
10046
- api: "openai-completions",
10047
- provider: "openrouter",
10048
- baseUrl: "https://openrouter.ai/api/v1",
10049
- reasoning: true,
10050
- input: ["text"],
10051
- cost: {
10052
- input: 0,
10053
- output: 0,
10054
- cacheRead: 0,
10055
- cacheWrite: 0,
10056
- },
10057
- contextWindow: 262144,
10058
- maxTokens: 32768,
10059
- },
10060
10094
  "inclusionai/ring-2.6-1t": {
10061
10095
  id: "inclusionai/ring-2.6-1t",
10062
10096
  name: "inclusionAI: Ring-2.6-1T",
@@ -10763,9 +10797,9 @@ export const MODELS = {
10763
10797
  reasoning: true,
10764
10798
  input: ["text", "image"],
10765
10799
  cost: {
10766
- input: 0.5795,
10767
- output: 2.44,
10768
- cacheRead: 0.0976,
10800
+ input: 0.5605,
10801
+ output: 2.36,
10802
+ cacheRead: 0.0944,
10769
10803
  cacheWrite: 0,
10770
10804
  },
10771
10805
  contextWindow: 262144,
@@ -10992,6 +11026,23 @@ export const MODELS = {
10992
11026
  contextWindow: 1000000,
10993
11027
  maxTokens: 65536,
10994
11028
  },
11029
+ "nvidia/nemotron-3.5-lightning": {
11030
+ id: "nvidia/nemotron-3.5-lightning",
11031
+ name: "NVIDIA: Nemotron 3.5 Lightning",
11032
+ api: "openai-completions",
11033
+ provider: "openrouter",
11034
+ baseUrl: "https://openrouter.ai/api/v1",
11035
+ reasoning: true,
11036
+ input: ["text"],
11037
+ cost: {
11038
+ input: 0.09999999999999999,
11039
+ output: 0.25,
11040
+ cacheRead: 0.049999999999999996,
11041
+ cacheWrite: 0,
11042
+ },
11043
+ contextWindow: 1000000,
11044
+ maxTokens: 262144,
11045
+ },
10995
11046
  "nvidia/nemotron-3.5-lightning:free": {
10996
11047
  id: "nvidia/nemotron-3.5-lightning:free",
10997
11048
  name: "NVIDIA: Nemotron 3.5 Lightning (free)",
@@ -13024,13 +13075,13 @@ export const MODELS = {
13024
13075
  reasoning: false,
13025
13076
  input: ["text"],
13026
13077
  cost: {
13027
- input: 0.09,
13078
+ input: 0.09999999999999999,
13028
13079
  output: 1.1,
13029
- cacheRead: 0,
13080
+ cacheRead: 0.07,
13030
13081
  cacheWrite: 0,
13031
13082
  },
13032
13083
  contextWindow: 262144,
13033
- maxTokens: 16384,
13084
+ maxTokens: 262144,
13034
13085
  },
13035
13086
  "qwen/qwen3-next-80b-a3b-thinking": {
13036
13087
  id: "qwen/qwen3-next-80b-a3b-thinking",
@@ -13047,7 +13098,7 @@ export const MODELS = {
13047
13098
  cacheWrite: 0,
13048
13099
  },
13049
13100
  contextWindow: 262144,
13050
- maxTokens: 262144,
13101
+ maxTokens: 32768,
13051
13102
  },
13052
13103
  "qwen/qwen3-vl-235b-a22b-instruct": {
13053
13104
  id: "qwen/qwen3-vl-235b-a22b-instruct",
@@ -13211,9 +13262,9 @@ export const MODELS = {
13211
13262
  reasoning: true,
13212
13263
  input: ["text", "image"],
13213
13264
  cost: {
13214
- input: 0.14,
13215
- output: 1,
13216
- cacheRead: 0,
13265
+ input: 0.25,
13266
+ output: 1.25,
13267
+ cacheRead: 0.25,
13217
13268
  cacheWrite: 0,
13218
13269
  },
13219
13270
  contextWindow: 262144,
@@ -13451,11 +13502,11 @@ export const MODELS = {
13451
13502
  cost: {
13452
13503
  input: 2,
13453
13504
  output: 6,
13454
- cacheRead: 0.19999999999999998,
13505
+ cacheRead: 0.25,
13455
13506
  cacheWrite: 0,
13456
13507
  },
13457
- contextWindow: 262144,
13458
- maxTokens: 52429,
13508
+ contextWindow: 1000000,
13509
+ maxTokens: 262144,
13459
13510
  },
13460
13511
  "qwen/qwen3.8-max": {
13461
13512
  id: "qwen/qwen3.8-max",
@@ -13908,9 +13959,9 @@ export const MODELS = {
13908
13959
  reasoning: true,
13909
13960
  input: ["text"],
13910
13961
  cost: {
13911
- input: 0.55,
13912
- output: 2.2,
13913
- cacheRead: 0.11,
13962
+ input: 0.5,
13963
+ output: 2,
13964
+ cacheRead: 0.09999999999999999,
13914
13965
  cacheWrite: 0,
13915
13966
  },
13916
13967
  contextWindow: 204800,
@@ -14010,9 +14061,9 @@ export const MODELS = {
14010
14061
  reasoning: true,
14011
14062
  input: ["text"],
14012
14063
  cost: {
14013
- input: 1.4,
14014
- output: 4.4,
14015
- cacheRead: 0.26,
14064
+ input: 0.952,
14065
+ output: 2.992,
14066
+ cacheRead: 0.17679999999999998,
14016
14067
  cacheWrite: 0,
14017
14068
  },
14018
14069
  contextWindow: 204800,
@@ -14027,9 +14078,9 @@ export const MODELS = {
14027
14078
  reasoning: true,
14028
14079
  input: ["text"],
14029
14080
  cost: {
14030
- input: 0.49,
14031
- output: 1.54,
14032
- cacheRead: 0.091,
14081
+ input: 0.392,
14082
+ output: 1.232,
14083
+ cacheRead: 0.0728,
14033
14084
  cacheWrite: 0,
14034
14085
  },
14035
14086
  contextWindow: 1048576,
@@ -14146,13 +14197,13 @@ export const MODELS = {
14146
14197
  reasoning: true,
14147
14198
  input: ["text"],
14148
14199
  cost: {
14149
- input: 0.079996,
14150
- output: 0.252,
14151
- cacheRead: 0.0252,
14200
+ input: 0.072,
14201
+ output: 0.144,
14202
+ cacheRead: 0.016,
14152
14203
  cacheWrite: 0,
14153
14204
  },
14154
14205
  contextWindow: 1048576,
14155
- maxTokens: 4096,
14206
+ maxTokens: 262144,
14156
14207
  },
14157
14208
  "~google/gemini-flash-latest": {
14158
14209
  id: "~google/gemini-flash-latest",
@@ -14163,10 +14214,10 @@ export const MODELS = {
14163
14214
  reasoning: true,
14164
14215
  input: ["text", "image"],
14165
14216
  cost: {
14166
- input: 1.5,
14167
- output: 7.5,
14168
- cacheRead: 0.15,
14169
- cacheWrite: 0.0833333333333333,
14217
+ input: 0.375,
14218
+ output: 1.875,
14219
+ cacheRead: 0.0375,
14220
+ cacheWrite: 0.0208333333333333,
14170
14221
  },
14171
14222
  contextWindow: 1048576,
14172
14223
  maxTokens: 65536,
@@ -14197,13 +14248,13 @@ export const MODELS = {
14197
14248
  reasoning: true,
14198
14249
  input: ["text", "image"],
14199
14250
  cost: {
14200
- input: 2.8,
14201
- output: 14,
14202
- cacheRead: 0.29,
14251
+ input: 2.4,
14252
+ output: 12,
14253
+ cacheRead: 0.24,
14203
14254
  cacheWrite: 0,
14204
14255
  },
14205
14256
  contextWindow: 1048576,
14206
- maxTokens: 1048576,
14257
+ maxTokens: 974842,
14207
14258
  },
14208
14259
  "~openai/gpt-latest": {
14209
14260
  id: "~openai/gpt-latest",
@@ -14683,6 +14734,23 @@ export const MODELS = {
14683
14734
  contextWindow: 1000000,
14684
14735
  maxTokens: 64000,
14685
14736
  },
14737
+ "alibaba/qwen3.8-2.4t-a95b": {
14738
+ id: "alibaba/qwen3.8-2.4t-a95b",
14739
+ name: "Qwen3.8 2.4T A95B",
14740
+ api: "anthropic-messages",
14741
+ provider: "vercel-ai-gateway",
14742
+ baseUrl: "https://ai-gateway.vercel.sh",
14743
+ reasoning: true,
14744
+ input: ["text"],
14745
+ cost: {
14746
+ input: 2,
14747
+ output: 6,
14748
+ cacheRead: 0.25,
14749
+ cacheWrite: 0,
14750
+ },
14751
+ contextWindow: 262144,
14752
+ maxTokens: 131072,
14753
+ },
14686
14754
  "alibaba/qwen3.8-max": {
14687
14755
  id: "alibaba/qwen3.8-max",
14688
14756
  name: "Qwen 3.8 Max",
@@ -15431,6 +15499,23 @@ export const MODELS = {
15431
15499
  contextWindow: 1000000,
15432
15500
  maxTokens: 64000,
15433
15501
  },
15502
+ "google/gemini-3.7-flash": {
15503
+ id: "google/gemini-3.7-flash",
15504
+ name: "Gemini 3.7 Flash",
15505
+ api: "anthropic-messages",
15506
+ provider: "vercel-ai-gateway",
15507
+ baseUrl: "https://ai-gateway.vercel.sh",
15508
+ reasoning: true,
15509
+ input: ["text", "image"],
15510
+ cost: {
15511
+ input: 0.75,
15512
+ output: 3.75,
15513
+ cacheRead: 0.075,
15514
+ cacheWrite: 0,
15515
+ },
15516
+ contextWindow: 1000000,
15517
+ maxTokens: 65536,
15518
+ },
15434
15519
  "google/gemma-4-26b-a4b-it": {
15435
15520
  id: "google/gemma-4-26b-a4b-it",
15436
15521
  name: "Google Gemma 4 26B A4B",
@@ -15462,7 +15547,7 @@ export const MODELS = {
15462
15547
  cacheRead: 0,
15463
15548
  cacheWrite: 0,
15464
15549
  },
15465
- contextWindow: 256000,
15550
+ contextWindow: 262144,
15466
15551
  maxTokens: 131072,
15467
15552
  },
15468
15553
  "inception/mercury-2": {