@dreb/ai 2.16.0 → 2.18.0

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.
@@ -1003,7 +1003,7 @@ export const MODELS = {
1003
1003
  cacheWrite: 0,
1004
1004
  },
1005
1005
  contextWindow: 128000,
1006
- maxTokens: 4096,
1006
+ maxTokens: 16384,
1007
1007
  },
1008
1008
  "openai.gpt-oss-20b-1:0": {
1009
1009
  id: "openai.gpt-oss-20b-1:0",
@@ -1020,7 +1020,7 @@ export const MODELS = {
1020
1020
  cacheWrite: 0,
1021
1021
  },
1022
1022
  contextWindow: 128000,
1023
- maxTokens: 4096,
1023
+ maxTokens: 16384,
1024
1024
  },
1025
1025
  "openai.gpt-oss-safeguard-120b": {
1026
1026
  id: "openai.gpt-oss-safeguard-120b",
@@ -1037,7 +1037,7 @@ export const MODELS = {
1037
1037
  cacheWrite: 0,
1038
1038
  },
1039
1039
  contextWindow: 128000,
1040
- maxTokens: 4096,
1040
+ maxTokens: 16384,
1041
1041
  },
1042
1042
  "openai.gpt-oss-safeguard-20b": {
1043
1043
  id: "openai.gpt-oss-safeguard-20b",
@@ -1054,7 +1054,7 @@ export const MODELS = {
1054
1054
  cacheWrite: 0,
1055
1055
  },
1056
1056
  contextWindow: 128000,
1057
- maxTokens: 4096,
1057
+ maxTokens: 16384,
1058
1058
  },
1059
1059
  "qwen.qwen3-235b-a22b-2507-v1:0": {
1060
1060
  id: "qwen.qwen3-235b-a22b-2507-v1:0",
@@ -3057,7 +3057,7 @@ export const MODELS = {
3057
3057
  cost: {
3058
3058
  input: 0.1,
3059
3059
  output: 0.4,
3060
- cacheRead: 0.025,
3060
+ cacheRead: 0.01,
3061
3061
  cacheWrite: 0,
3062
3062
  },
3063
3063
  contextWindow: 1048576,
@@ -3245,7 +3245,7 @@ export const MODELS = {
3245
3245
  input: 0.25,
3246
3246
  output: 1.5,
3247
3247
  cacheRead: 0.025,
3248
- cacheWrite: 1,
3248
+ cacheWrite: 0,
3249
3249
  },
3250
3250
  contextWindow: 1048576,
3251
3251
  maxTokens: 65536,
@@ -3262,7 +3262,7 @@ export const MODELS = {
3262
3262
  input: 0.25,
3263
3263
  output: 1.5,
3264
3264
  cacheRead: 0.025,
3265
- cacheWrite: 1,
3265
+ cacheWrite: 0,
3266
3266
  },
3267
3267
  contextWindow: 1048576,
3268
3268
  maxTokens: 65536,
@@ -6206,6 +6206,23 @@ export const MODELS = {
6206
6206
  contextWindow: 1000000,
6207
6207
  maxTokens: 64000,
6208
6208
  },
6209
+ "deepseek-v4-flash-free": {
6210
+ id: "deepseek-v4-flash-free",
6211
+ name: "DeepSeek V4 Flash Free",
6212
+ api: "openai-completions",
6213
+ provider: "opencode",
6214
+ baseUrl: "https://opencode.ai/zen/v1",
6215
+ reasoning: true,
6216
+ input: ["text"],
6217
+ cost: {
6218
+ input: 0,
6219
+ output: 0,
6220
+ cacheRead: 0,
6221
+ cacheWrite: 0,
6222
+ },
6223
+ contextWindow: 1000000,
6224
+ maxTokens: 384000,
6225
+ },
6209
6226
  "gemini-3-flash": {
6210
6227
  id: "gemini-3-flash",
6211
6228
  name: "Gemini 3 Flash",
@@ -6823,9 +6840,9 @@ export const MODELS = {
6823
6840
  "minimax-m2.5": {
6824
6841
  id: "minimax-m2.5",
6825
6842
  name: "MiniMax M2.5",
6826
- api: "openai-completions",
6843
+ api: "anthropic-messages",
6827
6844
  provider: "opencode-go",
6828
- baseUrl: "https://opencode.ai/zen/go/v1",
6845
+ baseUrl: "https://opencode.ai/zen/go",
6829
6846
  reasoning: true,
6830
6847
  input: ["text"],
6831
6848
  cost: {
@@ -7043,40 +7060,6 @@ export const MODELS = {
7043
7060
  contextWindow: 200000,
7044
7061
  maxTokens: 8192,
7045
7062
  },
7046
- "anthropic/claude-3.7-sonnet": {
7047
- id: "anthropic/claude-3.7-sonnet",
7048
- name: "Anthropic: Claude 3.7 Sonnet",
7049
- api: "openai-completions",
7050
- provider: "openrouter",
7051
- baseUrl: "https://openrouter.ai/api/v1",
7052
- reasoning: true,
7053
- input: ["text", "image"],
7054
- cost: {
7055
- input: 3,
7056
- output: 15,
7057
- cacheRead: 0.3,
7058
- cacheWrite: 3.75,
7059
- },
7060
- contextWindow: 200000,
7061
- maxTokens: 64000,
7062
- },
7063
- "anthropic/claude-3.7-sonnet:thinking": {
7064
- id: "anthropic/claude-3.7-sonnet:thinking",
7065
- name: "Anthropic: Claude 3.7 Sonnet (thinking)",
7066
- api: "openai-completions",
7067
- provider: "openrouter",
7068
- baseUrl: "https://openrouter.ai/api/v1",
7069
- reasoning: true,
7070
- input: ["text", "image"],
7071
- cost: {
7072
- input: 3,
7073
- output: 15,
7074
- cacheRead: 0.3,
7075
- cacheWrite: 3.75,
7076
- },
7077
- contextWindow: 200000,
7078
- maxTokens: 64000,
7079
- },
7080
7063
  "anthropic/claude-haiku-4.5": {
7081
7064
  id: "anthropic/claude-haiku-4.5",
7082
7065
  name: "Anthropic: Claude Haiku 4.5",
@@ -7196,6 +7179,23 @@ export const MODELS = {
7196
7179
  contextWindow: 1000000,
7197
7180
  maxTokens: 128000,
7198
7181
  },
7182
+ "anthropic/claude-opus-4.7-fast": {
7183
+ id: "anthropic/claude-opus-4.7-fast",
7184
+ name: "Anthropic: Claude Opus 4.7 (Fast)",
7185
+ api: "openai-completions",
7186
+ provider: "openrouter",
7187
+ baseUrl: "https://openrouter.ai/api/v1",
7188
+ reasoning: true,
7189
+ input: ["text", "image"],
7190
+ cost: {
7191
+ input: 30,
7192
+ output: 150,
7193
+ cacheRead: 3,
7194
+ cacheWrite: 37.5,
7195
+ },
7196
+ contextWindow: 1000000,
7197
+ maxTokens: 128000,
7198
+ },
7199
7199
  "anthropic/claude-sonnet-4": {
7200
7200
  id: "anthropic/claude-sonnet-4",
7201
7201
  name: "Anthropic: Claude Sonnet 4",
@@ -7281,6 +7281,23 @@ export const MODELS = {
7281
7281
  contextWindow: 262144,
7282
7282
  maxTokens: 262144,
7283
7283
  },
7284
+ "arcee-ai/trinity-large-thinking:free": {
7285
+ id: "arcee-ai/trinity-large-thinking:free",
7286
+ name: "Arcee AI: Trinity Large Thinking (free)",
7287
+ api: "openai-completions",
7288
+ provider: "openrouter",
7289
+ baseUrl: "https://openrouter.ai/api/v1",
7290
+ reasoning: true,
7291
+ input: ["text"],
7292
+ cost: {
7293
+ input: 0,
7294
+ output: 0,
7295
+ cacheRead: 0,
7296
+ cacheWrite: 0,
7297
+ },
7298
+ contextWindow: 262144,
7299
+ maxTokens: 80000,
7300
+ },
7284
7301
  "arcee-ai/trinity-mini": {
7285
7302
  id: "arcee-ai/trinity-mini",
7286
7303
  name: "Arcee AI: Trinity Mini",
@@ -7528,13 +7545,13 @@ export const MODELS = {
7528
7545
  reasoning: true,
7529
7546
  input: ["text"],
7530
7547
  cost: {
7531
- input: 0.15,
7532
- output: 0.75,
7533
- cacheRead: 0,
7548
+ input: 0.21,
7549
+ output: 0.7899999999999999,
7550
+ cacheRead: 0.13,
7534
7551
  cacheWrite: 0,
7535
7552
  },
7536
- contextWindow: 32768,
7537
- maxTokens: 7168,
7553
+ contextWindow: 163840,
7554
+ maxTokens: 32768,
7538
7555
  },
7539
7556
  "deepseek/deepseek-r1": {
7540
7557
  id: "deepseek/deepseek-r1",
@@ -7630,9 +7647,26 @@ export const MODELS = {
7630
7647
  reasoning: true,
7631
7648
  input: ["text"],
7632
7649
  cost: {
7633
- input: 0.14,
7634
- output: 0.28,
7635
- cacheRead: 0.0028,
7650
+ input: 0.126,
7651
+ output: 0.252,
7652
+ cacheRead: 0.0252,
7653
+ cacheWrite: 0,
7654
+ },
7655
+ contextWindow: 1048576,
7656
+ maxTokens: 131072,
7657
+ },
7658
+ "deepseek/deepseek-v4-flash:free": {
7659
+ id: "deepseek/deepseek-v4-flash:free",
7660
+ name: "DeepSeek: DeepSeek V4 Flash (free)",
7661
+ api: "openai-completions",
7662
+ provider: "openrouter",
7663
+ baseUrl: "https://openrouter.ai/api/v1",
7664
+ reasoning: true,
7665
+ input: ["text"],
7666
+ cost: {
7667
+ input: 0,
7668
+ output: 0,
7669
+ cacheRead: 0,
7636
7670
  cacheWrite: 0,
7637
7671
  },
7638
7672
  contextWindow: 1048576,
@@ -7686,7 +7720,7 @@ export const MODELS = {
7686
7720
  cacheRead: 0.024999999999999998,
7687
7721
  cacheWrite: 0.08333333333333334,
7688
7722
  },
7689
- contextWindow: 1000000,
7723
+ contextWindow: 1048576,
7690
7724
  maxTokens: 8192,
7691
7725
  },
7692
7726
  "google/gemini-2.0-flash-lite-001": {
@@ -7970,8 +8004,8 @@ export const MODELS = {
7970
8004
  reasoning: true,
7971
8005
  input: ["text", "image"],
7972
8006
  cost: {
7973
- input: 0.13,
7974
- output: 0.38,
8007
+ input: 0.12,
8008
+ output: 0.37,
7975
8009
  cacheRead: 0,
7976
8010
  cacheWrite: 0,
7977
8011
  },
@@ -8276,13 +8310,13 @@ export const MODELS = {
8276
8310
  reasoning: true,
8277
8311
  input: ["text"],
8278
8312
  cost: {
8279
- input: 0.29900000000000004,
8313
+ input: 0.26,
8280
8314
  output: 1.2,
8281
8315
  cacheRead: 0,
8282
8316
  cacheWrite: 0,
8283
8317
  },
8284
8318
  contextWindow: 196608,
8285
- maxTokens: 131072,
8319
+ maxTokens: 4096,
8286
8320
  },
8287
8321
  "mistralai/codestral-2508": {
8288
8322
  id: "mistralai/codestral-2508",
@@ -8667,8 +8701,8 @@ export const MODELS = {
8667
8701
  reasoning: false,
8668
8702
  input: ["text"],
8669
8703
  cost: {
8670
- input: 0.39999999999999997,
8671
- output: 2,
8704
+ input: 0.6,
8705
+ output: 2.5,
8672
8706
  cacheRead: 0,
8673
8707
  cacheWrite: 0,
8674
8708
  },
@@ -8718,13 +8752,13 @@ export const MODELS = {
8718
8752
  reasoning: true,
8719
8753
  input: ["text", "image"],
8720
8754
  cost: {
8721
- input: 0.75,
8722
- output: 3.5,
8723
- cacheRead: 0.15,
8755
+ input: 0.73,
8756
+ output: 3.49,
8757
+ cacheRead: 0.25,
8724
8758
  cacheWrite: 0,
8725
8759
  },
8726
- contextWindow: 262144,
8727
- maxTokens: 16384,
8760
+ contextWindow: 262142,
8761
+ maxTokens: 262142,
8728
8762
  },
8729
8763
  "nex-agi/deepseek-v3.1-nex-n1": {
8730
8764
  id: "nex-agi/deepseek-v3.1-nex-n1",
@@ -10001,23 +10035,6 @@ export const MODELS = {
10001
10035
  contextWindow: 32768,
10002
10036
  maxTokens: 32768,
10003
10037
  },
10004
- "qwen/qwen-max": {
10005
- id: "qwen/qwen-max",
10006
- name: "Qwen: Qwen-Max ",
10007
- api: "openai-completions",
10008
- provider: "openrouter",
10009
- baseUrl: "https://openrouter.ai/api/v1",
10010
- reasoning: false,
10011
- input: ["text"],
10012
- cost: {
10013
- input: 1.04,
10014
- output: 4.16,
10015
- cacheRead: 0.20800000000000002,
10016
- cacheWrite: 0,
10017
- },
10018
- contextWindow: 32768,
10019
- maxTokens: 8192,
10020
- },
10021
10038
  "qwen/qwen-plus": {
10022
10039
  id: "qwen/qwen-plus",
10023
10040
  name: "Qwen: Qwen-Plus",
@@ -10069,40 +10086,6 @@ export const MODELS = {
10069
10086
  contextWindow: 1000000,
10070
10087
  maxTokens: 32768,
10071
10088
  },
10072
- "qwen/qwen-turbo": {
10073
- id: "qwen/qwen-turbo",
10074
- name: "Qwen: Qwen-Turbo",
10075
- api: "openai-completions",
10076
- provider: "openrouter",
10077
- baseUrl: "https://openrouter.ai/api/v1",
10078
- reasoning: false,
10079
- input: ["text"],
10080
- cost: {
10081
- input: 0.0325,
10082
- output: 0.13,
10083
- cacheRead: 0.006500000000000001,
10084
- cacheWrite: 0,
10085
- },
10086
- contextWindow: 131072,
10087
- maxTokens: 8192,
10088
- },
10089
- "qwen/qwen-vl-max": {
10090
- id: "qwen/qwen-vl-max",
10091
- name: "Qwen: Qwen VL Max",
10092
- api: "openai-completions",
10093
- provider: "openrouter",
10094
- baseUrl: "https://openrouter.ai/api/v1",
10095
- reasoning: false,
10096
- input: ["text", "image"],
10097
- cost: {
10098
- input: 0.52,
10099
- output: 2.08,
10100
- cacheRead: 0,
10101
- cacheWrite: 0,
10102
- },
10103
- contextWindow: 131072,
10104
- maxTokens: 32768,
10105
- },
10106
10089
  "qwen/qwen3-14b": {
10107
10090
  id: "qwen/qwen3-14b",
10108
10091
  name: "Qwen: Qwen3 14B",
@@ -10112,7 +10095,7 @@ export const MODELS = {
10112
10095
  reasoning: true,
10113
10096
  input: ["text"],
10114
10097
  cost: {
10115
- input: 0.06,
10098
+ input: 0.09999999999999999,
10116
10099
  output: 0.24,
10117
10100
  cacheRead: 0,
10118
10101
  cacheWrite: 0,
@@ -11285,13 +11268,13 @@ export const MODELS = {
11285
11268
  reasoning: true,
11286
11269
  input: ["text"],
11287
11270
  cost: {
11288
- input: 0.39,
11289
- output: 1.9,
11290
- cacheRead: 0,
11271
+ input: 0.43,
11272
+ output: 1.74,
11273
+ cacheRead: 0.08,
11291
11274
  cacheWrite: 0,
11292
11275
  },
11293
- contextWindow: 204800,
11294
- maxTokens: 204800,
11276
+ contextWindow: 202752,
11277
+ maxTokens: 131072,
11295
11278
  },
11296
11279
  "z-ai/glm-4.6v": {
11297
11280
  id: "z-ai/glm-4.6v",
@@ -11387,13 +11370,13 @@ export const MODELS = {
11387
11370
  reasoning: true,
11388
11371
  input: ["text"],
11389
11372
  cost: {
11390
- input: 1.0499999999999998,
11391
- output: 3.5,
11392
- cacheRead: 0.5249999999999999,
11373
+ input: 0.98,
11374
+ output: 3.08,
11375
+ cacheRead: 0.182,
11393
11376
  cacheWrite: 0,
11394
11377
  },
11395
11378
  contextWindow: 202752,
11396
- maxTokens: 65535,
11379
+ maxTokens: 4096,
11397
11380
  },
11398
11381
  "z-ai/glm-5v-turbo": {
11399
11382
  id: "z-ai/glm-5v-turbo",
@@ -11506,13 +11489,13 @@ export const MODELS = {
11506
11489
  reasoning: true,
11507
11490
  input: ["text", "image"],
11508
11491
  cost: {
11509
- input: 0.75,
11510
- output: 3.5,
11511
- cacheRead: 0.15,
11492
+ input: 0.73,
11493
+ output: 3.49,
11494
+ cacheRead: 0.25,
11512
11495
  cacheWrite: 0,
11513
11496
  },
11514
- contextWindow: 262144,
11515
- maxTokens: 16384,
11497
+ contextWindow: 262142,
11498
+ maxTokens: 262142,
11516
11499
  },
11517
11500
  "~openai/gpt-latest": {
11518
11501
  id: "~openai/gpt-latest",
@@ -11890,23 +11873,6 @@ export const MODELS = {
11890
11873
  contextWindow: 200000,
11891
11874
  maxTokens: 8192,
11892
11875
  },
11893
- "anthropic/claude-3.7-sonnet": {
11894
- id: "anthropic/claude-3.7-sonnet",
11895
- name: "Claude 3.7 Sonnet",
11896
- api: "anthropic-messages",
11897
- provider: "vercel-ai-gateway",
11898
- baseUrl: "https://ai-gateway.vercel.sh",
11899
- reasoning: true,
11900
- input: ["text", "image"],
11901
- cost: {
11902
- input: 3,
11903
- output: 15,
11904
- cacheRead: 0.3,
11905
- cacheWrite: 3.75,
11906
- },
11907
- contextWindow: 200000,
11908
- maxTokens: 8192,
11909
- },
11910
11876
  "anthropic/claude-haiku-4.5": {
11911
11877
  id: "anthropic/claude-haiku-4.5",
11912
11878
  name: "Claude Haiku 4.5",
@@ -13575,7 +13541,7 @@ export const MODELS = {
13575
13541
  },
13576
13542
  "openai/gpt-oss-20b": {
13577
13543
  id: "openai/gpt-oss-20b",
13578
- name: "GPT OSS 120B",
13544
+ name: "GPT OSS 20B",
13579
13545
  api: "anthropic-messages",
13580
13546
  provider: "vercel-ai-gateway",
13581
13547
  baseUrl: "https://ai-gateway.vercel.sh",