@dreb/ai 2.64.3 → 2.64.4

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.
@@ -2896,6 +2896,23 @@ export const MODELS = {
2896
2896
  contextWindow: 1050000,
2897
2897
  maxTokens: 128000,
2898
2898
  },
2899
+ "gpt-6-astra": {
2900
+ id: "gpt-6-astra",
2901
+ name: "GPT-6 Astra",
2902
+ api: "azure-openai-responses",
2903
+ provider: "azure-openai-responses",
2904
+ baseUrl: "",
2905
+ reasoning: true,
2906
+ input: ["text", "image"],
2907
+ cost: {
2908
+ input: 10,
2909
+ output: 50,
2910
+ cacheRead: 1,
2911
+ cacheWrite: 12.5,
2912
+ },
2913
+ contextWindow: 1050000,
2914
+ maxTokens: 128000,
2915
+ },
2899
2916
  "gpt-realtime-2.1": {
2900
2917
  id: "gpt-realtime-2.1",
2901
2918
  name: "GPT-Realtime-2.1",
@@ -3439,6 +3456,25 @@ export const MODELS = {
3439
3456
  contextWindow: 1050000,
3440
3457
  maxTokens: 128000,
3441
3458
  },
3459
+ "gpt-6-astra": {
3460
+ id: "gpt-6-astra",
3461
+ name: "GPT-6 Astra",
3462
+ api: "openai-completions",
3463
+ provider: "github-copilot",
3464
+ baseUrl: "https://api.individual.githubcopilot.com",
3465
+ 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" },
3466
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
3467
+ reasoning: true,
3468
+ input: ["text", "image"],
3469
+ cost: {
3470
+ input: 10,
3471
+ output: 50,
3472
+ cacheRead: 1,
3473
+ cacheWrite: 12.5,
3474
+ },
3475
+ contextWindow: 1050000,
3476
+ maxTokens: 128000,
3477
+ },
3442
3478
  "grok-4.5": {
3443
3479
  id: "grok-4.5",
3444
3480
  name: "Grok 4.5",
@@ -7136,6 +7172,23 @@ export const MODELS = {
7136
7172
  contextWindow: 1050000,
7137
7173
  maxTokens: 128000,
7138
7174
  },
7175
+ "gpt-6-astra": {
7176
+ id: "gpt-6-astra",
7177
+ name: "GPT-6 Astra",
7178
+ api: "openai-responses",
7179
+ provider: "openai",
7180
+ baseUrl: "https://api.openai.com/v1",
7181
+ reasoning: true,
7182
+ input: ["text", "image"],
7183
+ cost: {
7184
+ input: 10,
7185
+ output: 50,
7186
+ cacheRead: 1,
7187
+ cacheWrite: 12.5,
7188
+ },
7189
+ contextWindow: 1050000,
7190
+ maxTokens: 128000,
7191
+ },
7139
7192
  "gpt-realtime-2.1": {
7140
7193
  id: "gpt-realtime-2.1",
7141
7194
  name: "GPT-Realtime-2.1",
@@ -7684,6 +7737,23 @@ export const MODELS = {
7684
7737
  contextWindow: 1000000,
7685
7738
  maxTokens: 384000,
7686
7739
  },
7740
+ "deepseek-v4-flash-vision-exp": {
7741
+ id: "deepseek-v4-flash-vision-exp",
7742
+ name: "DeepSeek V4 Flash Vision Exp",
7743
+ api: "openai-completions",
7744
+ provider: "opencode",
7745
+ baseUrl: "https://opencode.ai/zen/v1",
7746
+ reasoning: true,
7747
+ input: ["text", "image"],
7748
+ cost: {
7749
+ input: 0.14,
7750
+ output: 0.28,
7751
+ cacheRead: 0.028,
7752
+ cacheWrite: 0,
7753
+ },
7754
+ contextWindow: 1000000,
7755
+ maxTokens: 384000,
7756
+ },
7687
7757
  "deepseek-v4-pro": {
7688
7758
  id: "deepseek-v4-pro",
7689
7759
  name: "DeepSeek V4 Pro",
@@ -7871,6 +7941,40 @@ export const MODELS = {
7871
7941
  contextWindow: 1000000,
7872
7942
  maxTokens: 131072,
7873
7943
  },
7944
+ "glm-5.3": {
7945
+ id: "glm-5.3",
7946
+ name: "GLM-5.3",
7947
+ api: "openai-completions",
7948
+ provider: "opencode",
7949
+ baseUrl: "https://opencode.ai/zen/v1",
7950
+ reasoning: true,
7951
+ input: ["text"],
7952
+ cost: {
7953
+ input: 1.4,
7954
+ output: 4.4,
7955
+ cacheRead: 0.26,
7956
+ cacheWrite: 0,
7957
+ },
7958
+ contextWindow: 1000000,
7959
+ maxTokens: 131072,
7960
+ },
7961
+ "glm-5.3-flash": {
7962
+ id: "glm-5.3-flash",
7963
+ name: "GLM-5.3-Flash",
7964
+ api: "openai-completions",
7965
+ provider: "opencode",
7966
+ baseUrl: "https://opencode.ai/zen/v1",
7967
+ reasoning: true,
7968
+ input: ["text", "image"],
7969
+ cost: {
7970
+ input: 0.15,
7971
+ output: 0.5,
7972
+ cacheRead: 0.03,
7973
+ cacheWrite: 0,
7974
+ },
7975
+ contextWindow: 1000000,
7976
+ maxTokens: 131072,
7977
+ },
7874
7978
  "gpt-5": {
7875
7979
  id: "gpt-5",
7876
7980
  name: "GPT-5",
@@ -8194,6 +8298,23 @@ export const MODELS = {
8194
8298
  contextWindow: 1050000,
8195
8299
  maxTokens: 128000,
8196
8300
  },
8301
+ "gpt-6-astra": {
8302
+ id: "gpt-6-astra",
8303
+ name: "GPT-6 Astra",
8304
+ api: "openai-responses",
8305
+ provider: "opencode",
8306
+ baseUrl: "https://opencode.ai/zen/v1",
8307
+ reasoning: true,
8308
+ input: ["text", "image"],
8309
+ cost: {
8310
+ input: 10,
8311
+ output: 50,
8312
+ cacheRead: 1,
8313
+ cacheWrite: 12.5,
8314
+ },
8315
+ contextWindow: 1050000,
8316
+ maxTokens: 128000,
8317
+ },
8197
8318
  "grok-4.5": {
8198
8319
  id: "grok-4.5",
8199
8320
  name: "Grok 4.5",
@@ -8432,6 +8553,23 @@ export const MODELS = {
8432
8553
  contextWindow: 1048576,
8433
8554
  maxTokens: 131072,
8434
8555
  },
8556
+ "muse-spark-1.3": {
8557
+ id: "muse-spark-1.3",
8558
+ name: "Muse Spark 1.3",
8559
+ api: "openai-responses",
8560
+ provider: "opencode",
8561
+ baseUrl: "https://opencode.ai/zen/v1",
8562
+ reasoning: true,
8563
+ input: ["text", "image"],
8564
+ cost: {
8565
+ input: 1.25,
8566
+ output: 4.25,
8567
+ cacheRead: 0.15,
8568
+ cacheWrite: 0,
8569
+ },
8570
+ contextWindow: 1048576,
8571
+ maxTokens: 131072,
8572
+ },
8435
8573
  "muse-spark-1.3-contributor-free": {
8436
8574
  id: "muse-spark-1.3-contributor-free",
8437
8575
  name: "Muse Spark 1.3 Free",
@@ -9907,9 +10045,9 @@ export const MODELS = {
9907
10045
  reasoning: true,
9908
10046
  input: ["text"],
9909
10047
  cost: {
9910
- input: 0.0875,
9911
- output: 0.175,
9912
- cacheRead: 0.0175,
10048
+ input: 0.08078,
10049
+ output: 0.16156,
10050
+ cacheRead: 0.016156,
9913
10051
  cacheWrite: 0,
9914
10052
  },
9915
10053
  contextWindow: 1048576,
@@ -9924,13 +10062,13 @@ export const MODELS = {
9924
10062
  reasoning: true,
9925
10063
  input: ["text"],
9926
10064
  cost: {
9927
- input: 0.065,
9928
- output: 0.18,
9929
- cacheRead: 0.016,
10065
+ input: 0.049980000000000004,
10066
+ output: 0.09996000000000001,
10067
+ cacheRead: 0.009996000000000001,
9930
10068
  cacheWrite: 0,
9931
10069
  },
9932
10070
  contextWindow: 1310720,
9933
- maxTokens: 943718,
10071
+ maxTokens: 131072,
9934
10072
  },
9935
10073
  "deepseek/deepseek-v4-flash-0731:batch": {
9936
10074
  id: "deepseek/deepseek-v4-flash-0731:batch",
@@ -9975,9 +10113,9 @@ export const MODELS = {
9975
10113
  reasoning: true,
9976
10114
  input: ["text"],
9977
10115
  cost: {
9978
- input: 0.9918,
9979
- output: 1.9836,
9980
- cacheRead: 0.08265,
10116
+ input: 0.69774,
10117
+ output: 1.39548,
10118
+ cacheRead: 0.058145,
9981
10119
  cacheWrite: 0,
9982
10120
  },
9983
10121
  contextWindow: 1048576,
@@ -9992,9 +10130,9 @@ export const MODELS = {
9992
10130
  reasoning: true,
9993
10131
  input: ["text"],
9994
10132
  cost: {
9995
- input: 0.57948,
9996
- output: 1.73844,
9997
- cacheRead: 0.019316,
10133
+ input: 1.12068,
10134
+ output: 3.36204,
10135
+ cacheRead: 0.037356,
9998
10136
  cacheWrite: 0,
9999
10137
  },
10000
10138
  contextWindow: 1048576,
@@ -12890,6 +13028,74 @@ export const MODELS = {
12890
13028
  contextWindow: 400000,
12891
13029
  maxTokens: 128000,
12892
13030
  },
13031
+ "openai/gpt-6-astra": {
13032
+ id: "openai/gpt-6-astra",
13033
+ name: "OpenAI: GPT-6 Astra",
13034
+ api: "openai-completions",
13035
+ provider: "openrouter",
13036
+ baseUrl: "https://openrouter.ai/api/v1",
13037
+ reasoning: true,
13038
+ input: ["text", "image"],
13039
+ cost: {
13040
+ input: 10,
13041
+ output: 50,
13042
+ cacheRead: 1,
13043
+ cacheWrite: 12.5,
13044
+ },
13045
+ contextWindow: 1050000,
13046
+ maxTokens: 128000,
13047
+ },
13048
+ "openai/gpt-6-astra-pro": {
13049
+ id: "openai/gpt-6-astra-pro",
13050
+ name: "OpenAI: GPT-6 Astra Pro",
13051
+ api: "openai-completions",
13052
+ provider: "openrouter",
13053
+ baseUrl: "https://openrouter.ai/api/v1",
13054
+ reasoning: true,
13055
+ input: ["text", "image"],
13056
+ cost: {
13057
+ input: 10,
13058
+ output: 50,
13059
+ cacheRead: 1,
13060
+ cacheWrite: 12.5,
13061
+ },
13062
+ contextWindow: 1050000,
13063
+ maxTokens: 128000,
13064
+ },
13065
+ "openai/gpt-6-astra-pro:batch": {
13066
+ id: "openai/gpt-6-astra-pro:batch",
13067
+ name: "OpenAI: GPT-6 Astra Pro (batch)",
13068
+ api: "openai-completions",
13069
+ provider: "openrouter",
13070
+ baseUrl: "https://openrouter.ai/api/v1",
13071
+ reasoning: true,
13072
+ input: ["text", "image"],
13073
+ cost: {
13074
+ input: 5,
13075
+ output: 25,
13076
+ cacheRead: 0.5,
13077
+ cacheWrite: 6.25,
13078
+ },
13079
+ contextWindow: 1050000,
13080
+ maxTokens: 128000,
13081
+ },
13082
+ "openai/gpt-6-astra:batch": {
13083
+ id: "openai/gpt-6-astra:batch",
13084
+ name: "OpenAI: GPT-6 Astra (batch)",
13085
+ api: "openai-completions",
13086
+ provider: "openrouter",
13087
+ baseUrl: "https://openrouter.ai/api/v1",
13088
+ reasoning: true,
13089
+ input: ["text", "image"],
13090
+ cost: {
13091
+ input: 5,
13092
+ output: 25,
13093
+ cacheRead: 0.5,
13094
+ cacheWrite: 6.25,
13095
+ },
13096
+ contextWindow: 1050000,
13097
+ maxTokens: 128000,
13098
+ },
12893
13099
  "openai/gpt-audio": {
12894
13100
  id: "openai/gpt-audio",
12895
13101
  name: "OpenAI: GPT Audio",
@@ -13409,13 +13615,13 @@ export const MODELS = {
13409
13615
  reasoning: false,
13410
13616
  input: ["text"],
13411
13617
  cost: {
13412
- input: 0.0875,
13413
- output: 0.35,
13414
- cacheRead: 0.0175,
13618
+ input: 0.09,
13619
+ output: 0.55,
13620
+ cacheRead: 0,
13415
13621
  cacheWrite: 0,
13416
13622
  },
13417
13623
  contextWindow: 262144,
13418
- maxTokens: 235929,
13624
+ maxTokens: 16384,
13419
13625
  },
13420
13626
  "qwen/qwen3-235b-a22b-thinking-2507": {
13421
13627
  id: "qwen/qwen3-235b-a22b-thinking-2507",
@@ -13834,9 +14040,9 @@ export const MODELS = {
13834
14040
  reasoning: true,
13835
14041
  input: ["text", "image"],
13836
14042
  cost: {
13837
- input: 0.08,
13838
- output: 0.75,
13839
- cacheRead: 0,
14043
+ input: 0.3125,
14044
+ output: 1.25,
14045
+ cacheRead: 0.15625,
13840
14046
  cacheWrite: 0,
13841
14047
  },
13842
14048
  contextWindow: 262144,
@@ -14148,9 +14354,9 @@ export const MODELS = {
14148
14354
  contextWindow: 1000000,
14149
14355
  maxTokens: 131072,
14150
14356
  },
14151
- "qwen/qwen3.8-max": {
14152
- id: "qwen/qwen3.8-max",
14153
- name: "Qwen: Qwen3.8 Max",
14357
+ "qwen/qwen3.8-max-0902": {
14358
+ id: "qwen/qwen3.8-max-0902",
14359
+ name: "Qwen: Qwen3.8 Max (0902)",
14154
14360
  api: "openai-completions",
14155
14361
  provider: "openrouter",
14156
14362
  baseUrl: "https://openrouter.ai/api/v1",
@@ -14293,9 +14499,9 @@ export const MODELS = {
14293
14499
  reasoning: true,
14294
14500
  input: ["text"],
14295
14501
  cost: {
14296
- input: 0.0825,
14297
- output: 0.33,
14298
- cacheRead: 0.020625,
14502
+ input: 0.13199999999999998,
14503
+ output: 0.5279999999999999,
14504
+ cacheRead: 0.032999999999999995,
14299
14505
  cacheWrite: 0,
14300
14506
  },
14301
14507
  contextWindow: 262144,
@@ -14350,7 +14556,7 @@ export const MODELS = {
14350
14556
  cacheWrite: 0,
14351
14557
  },
14352
14558
  contextWindow: 1024000,
14353
- maxTokens: 26214,
14559
+ maxTokens: 819200,
14354
14560
  },
14355
14561
  "thinkingmachines/inkling": {
14356
14562
  id: "thinkingmachines/inkling",
@@ -14973,13 +15179,13 @@ export const MODELS = {
14973
15179
  reasoning: true,
14974
15180
  input: ["text"],
14975
15181
  cost: {
14976
- input: 0.049980000000000004,
14977
- output: 0.09996000000000001,
14978
- cacheRead: 0.009996000000000001,
15182
+ input: 0.045,
15183
+ output: 0.09,
15184
+ cacheRead: 0.009,
14979
15185
  cacheWrite: 0,
14980
15186
  },
14981
15187
  contextWindow: 1310720,
14982
- maxTokens: 131072,
15188
+ maxTokens: 943718,
14983
15189
  },
14984
15190
  "~google/gemini-flash-latest": {
14985
15191
  id: "~google/gemini-flash-latest",
@@ -15024,9 +15230,9 @@ export const MODELS = {
15024
15230
  reasoning: true,
15025
15231
  input: ["text", "image"],
15026
15232
  cost: {
15027
- input: 2.5,
15028
- output: 14,
15029
- cacheRead: 0.29,
15233
+ input: 2.5500000000000003,
15234
+ output: 12.75,
15235
+ cacheRead: 0.25599998999999996,
15030
15236
  cacheWrite: 0,
15031
15237
  },
15032
15238
  contextWindow: 1048576,
@@ -15109,9 +15315,9 @@ export const MODELS = {
15109
15315
  reasoning: true,
15110
15316
  input: ["text"],
15111
15317
  cost: {
15112
- input: 1.15,
15113
- output: 3.5,
15114
- cacheRead: 0.09999999999999999,
15318
+ input: 1.17,
15319
+ output: 3.9600000000000004,
15320
+ cacheRead: 0.234,
15115
15321
  cacheWrite: 0,
15116
15322
  },
15117
15323
  contextWindow: 1310720,
@@ -18140,7 +18346,7 @@ export const MODELS = {
18140
18346
  input: 0.39999999999999997,
18141
18347
  output: 2.4,
18142
18348
  cacheRead: 0.04,
18143
- cacheWrite: 0.25,
18349
+ cacheWrite: 0.5,
18144
18350
  },
18145
18351
  contextWindow: 1050000,
18146
18352
  maxTokens: 128000,
@@ -18174,7 +18380,7 @@ export const MODELS = {
18174
18380
  input: 4,
18175
18381
  output: 20,
18176
18382
  cacheRead: 0.39999999999999997,
18177
- cacheWrite: 2.5,
18383
+ cacheWrite: 5,
18178
18384
  },
18179
18385
  contextWindow: 1050000,
18180
18386
  maxTokens: 128000,
@@ -18208,7 +18414,41 @@ export const MODELS = {
18208
18414
  input: 4,
18209
18415
  output: 24,
18210
18416
  cacheRead: 0.39999999999999997,
18211
- cacheWrite: 2.5,
18417
+ cacheWrite: 5,
18418
+ },
18419
+ contextWindow: 1050000,
18420
+ maxTokens: 128000,
18421
+ },
18422
+ "openai/gpt-6-astra": {
18423
+ id: "openai/gpt-6-astra",
18424
+ name: "GPT-6 Astra",
18425
+ api: "anthropic-messages",
18426
+ provider: "vercel-ai-gateway",
18427
+ baseUrl: "https://ai-gateway.vercel.sh",
18428
+ reasoning: true,
18429
+ input: ["text", "image"],
18430
+ cost: {
18431
+ input: 10,
18432
+ output: 50,
18433
+ cacheRead: 1,
18434
+ cacheWrite: 12.5,
18435
+ },
18436
+ contextWindow: 1050000,
18437
+ maxTokens: 128000,
18438
+ },
18439
+ "openai/gpt-6-astra-fast": {
18440
+ id: "openai/gpt-6-astra-fast",
18441
+ name: "GPT-6 Astra (Fast)",
18442
+ api: "anthropic-messages",
18443
+ provider: "vercel-ai-gateway",
18444
+ baseUrl: "https://ai-gateway.vercel.sh",
18445
+ reasoning: true,
18446
+ input: ["text", "image"],
18447
+ cost: {
18448
+ input: 20,
18449
+ output: 100,
18450
+ cacheRead: 2,
18451
+ cacheWrite: 25,
18212
18452
  },
18213
18453
  contextWindow: 1050000,
18214
18454
  maxTokens: 128000,