@dreb/ai 2.58.1 → 2.59.1

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.
@@ -10265,13 +10265,13 @@ export const MODELS = {
10265
10265
  reasoning: true,
10266
10266
  input: ["text", "image"],
10267
10267
  cost: {
10268
- input: 0.09999999999999999,
10268
+ input: 0.09,
10269
10269
  output: 0.33999999999999997,
10270
- cacheRead: 0.09999999999999999,
10270
+ cacheRead: 0.049999999999999996,
10271
10271
  cacheWrite: 0,
10272
10272
  },
10273
10273
  contextWindow: 262144,
10274
- maxTokens: 262144,
10274
+ maxTokens: 16384,
10275
10275
  },
10276
10276
  "google/gemma-4-31b-it:free": {
10277
10277
  id: "google/gemma-4-31b-it:free",
@@ -10707,9 +10707,9 @@ export const MODELS = {
10707
10707
  reasoning: true,
10708
10708
  input: ["text", "image"],
10709
10709
  cost: {
10710
- input: 0.15,
10711
- output: 0.6,
10712
- cacheRead: 0.03,
10710
+ input: 0.3,
10711
+ output: 1.2,
10712
+ cacheRead: 0.06,
10713
10713
  cacheWrite: 0,
10714
10714
  },
10715
10715
  contextWindow: 524288,
@@ -11098,9 +11098,9 @@ export const MODELS = {
11098
11098
  reasoning: true,
11099
11099
  input: ["text", "image"],
11100
11100
  cost: {
11101
- input: 0.475,
11102
- output: 2,
11103
- cacheRead: 0.095,
11101
+ input: 0.95,
11102
+ output: 4,
11103
+ cacheRead: 0.19,
11104
11104
  cacheWrite: 0,
11105
11105
  },
11106
11106
  contextWindow: 262144,
@@ -11268,9 +11268,9 @@ export const MODELS = {
11268
11268
  reasoning: true,
11269
11269
  input: ["text"],
11270
11270
  cost: {
11271
- input: 0.3,
11272
- output: 1.7999999999999998,
11273
- cacheRead: 0.09999999999999999,
11271
+ input: 0.6,
11272
+ output: 3.5999999999999996,
11273
+ cacheRead: 0.19999999999999998,
11274
11274
  cacheWrite: 0,
11275
11275
  },
11276
11276
  contextWindow: 512288,
@@ -13342,13 +13342,13 @@ export const MODELS = {
13342
13342
  reasoning: false,
13343
13343
  input: ["text"],
13344
13344
  cost: {
13345
- input: 0.09999999999999999,
13345
+ input: 0.09,
13346
13346
  output: 1.1,
13347
- cacheRead: 0.07,
13347
+ cacheRead: 0,
13348
13348
  cacheWrite: 0,
13349
13349
  },
13350
13350
  contextWindow: 262144,
13351
- maxTokens: 262144,
13351
+ maxTokens: 16384,
13352
13352
  },
13353
13353
  "qwen/qwen3-next-80b-a3b-thinking": {
13354
13354
  id: "qwen/qwen3-next-80b-a3b-thinking",
@@ -13495,13 +13495,13 @@ export const MODELS = {
13495
13495
  reasoning: true,
13496
13496
  input: ["text", "image"],
13497
13497
  cost: {
13498
- input: 0.29,
13499
- output: 2.4,
13498
+ input: 0.26,
13499
+ output: 2.08,
13500
13500
  cacheRead: 0,
13501
13501
  cacheWrite: 0,
13502
13502
  },
13503
13503
  contextWindow: 262144,
13504
- maxTokens: 81920,
13504
+ maxTokens: 262144,
13505
13505
  },
13506
13506
  "qwen/qwen3.5-27b": {
13507
13507
  id: "qwen/qwen3.5-27b",
@@ -13631,13 +13631,13 @@ export const MODELS = {
13631
13631
  reasoning: true,
13632
13632
  input: ["text", "image"],
13633
13633
  cost: {
13634
- input: 0.28900000000000003,
13635
- output: 2.4,
13636
- cacheRead: 0,
13634
+ input: 0.3,
13635
+ output: 2,
13636
+ cacheRead: 0.03,
13637
13637
  cacheWrite: 0,
13638
13638
  },
13639
13639
  contextWindow: 262144,
13640
- maxTokens: 131072,
13640
+ maxTokens: 65536,
13641
13641
  },
13642
13642
  "qwen/qwen3.6-35b-a3b": {
13643
13643
  id: "qwen/qwen3.6-35b-a3b",
@@ -14022,9 +14022,9 @@ export const MODELS = {
14022
14022
  reasoning: true,
14023
14023
  input: ["text", "image"],
14024
14024
  cost: {
14025
- input: 0.5,
14026
- output: 2.025,
14027
- cacheRead: 0.08499999999999999,
14025
+ input: 1,
14026
+ output: 4.05,
14027
+ cacheRead: 0.16999999999999998,
14028
14028
  cacheWrite: 0,
14029
14029
  },
14030
14030
  contextWindow: 524288,
@@ -14362,13 +14362,13 @@ export const MODELS = {
14362
14362
  reasoning: true,
14363
14363
  input: ["text"],
14364
14364
  cost: {
14365
- input: 1.19,
14366
- output: 3.74,
14367
- cacheRead: 0.221,
14365
+ input: 0.966,
14366
+ output: 3.036,
14367
+ cacheRead: 0.1932,
14368
14368
  cacheWrite: 0,
14369
14369
  },
14370
14370
  contextWindow: 1048576,
14371
- maxTokens: 262144,
14371
+ maxTokens: 131072,
14372
14372
  },
14373
14373
  "z-ai/glm-5.2:batch": {
14374
14374
  id: "z-ai/glm-5.2:batch",
@@ -14379,14 +14379,48 @@ export const MODELS = {
14379
14379
  reasoning: true,
14380
14380
  input: ["text"],
14381
14381
  cost: {
14382
- input: 0.7,
14383
- output: 2.2,
14384
- cacheRead: 0.13,
14382
+ input: 1.4,
14383
+ output: 4.4,
14384
+ cacheRead: 0.26,
14385
14385
  cacheWrite: 0,
14386
14386
  },
14387
14387
  contextWindow: 512000,
14388
14388
  maxTokens: 4096,
14389
14389
  },
14390
+ "z-ai/glm-5.2:free": {
14391
+ id: "z-ai/glm-5.2:free",
14392
+ name: "Z.ai: GLM 5.2 (free)",
14393
+ api: "openai-completions",
14394
+ provider: "openrouter",
14395
+ baseUrl: "https://openrouter.ai/api/v1",
14396
+ reasoning: true,
14397
+ input: ["text"],
14398
+ cost: {
14399
+ input: 0,
14400
+ output: 0,
14401
+ cacheRead: 0,
14402
+ cacheWrite: 0,
14403
+ },
14404
+ contextWindow: 256000,
14405
+ maxTokens: 256000,
14406
+ },
14407
+ "z-ai/glm-5.3": {
14408
+ id: "z-ai/glm-5.3",
14409
+ name: "Z.ai: GLM 5.3",
14410
+ api: "openai-completions",
14411
+ provider: "openrouter",
14412
+ baseUrl: "https://openrouter.ai/api/v1",
14413
+ reasoning: true,
14414
+ input: ["text"],
14415
+ cost: {
14416
+ input: 1.4,
14417
+ output: 4.4,
14418
+ cacheRead: 0.26,
14419
+ cacheWrite: 0,
14420
+ },
14421
+ contextWindow: 1048576,
14422
+ maxTokens: 131072,
14423
+ },
14390
14424
  "z-ai/glm-5v-turbo": {
14391
14425
  id: "z-ai/glm-5v-turbo",
14392
14426
  name: "Z.ai: GLM 5V Turbo",
@@ -14481,13 +14515,13 @@ export const MODELS = {
14481
14515
  reasoning: true,
14482
14516
  input: ["text"],
14483
14517
  cost: {
14484
- input: 0.078596,
14485
- output: 0.157192,
14486
- cacheRead: 0.015719200000000003,
14518
+ input: 0.0765,
14519
+ output: 0.153,
14520
+ cacheRead: 0.015300000000000001,
14487
14521
  cacheWrite: 0,
14488
14522
  },
14489
14523
  contextWindow: 1310720,
14490
- maxTokens: 384000,
14524
+ maxTokens: 262144,
14491
14525
  },
14492
14526
  "~google/gemini-flash-latest": {
14493
14527
  id: "~google/gemini-flash-latest",
@@ -16710,9 +16744,9 @@ export const MODELS = {
16710
16744
  reasoning: true,
16711
16745
  input: ["text"],
16712
16746
  cost: {
16713
- input: 0,
16714
- output: 0,
16715
- cacheRead: 0,
16747
+ input: 0.049999999999999996,
16748
+ output: 0.19999999999999998,
16749
+ cacheRead: 0.01,
16716
16750
  cacheWrite: 0,
16717
16751
  },
16718
16752
  contextWindow: 262144,
@@ -18308,9 +18342,9 @@ export const MODELS = {
18308
18342
  reasoning: true,
18309
18343
  input: ["text"],
18310
18344
  cost: {
18311
- input: 1.1,
18312
- output: 3.851,
18313
- cacheRead: 0.275,
18345
+ input: 0.7999999999999999,
18346
+ output: 2.5500000000000003,
18347
+ cacheRead: 0.16,
18314
18348
  cacheWrite: 0,
18315
18349
  },
18316
18350
  contextWindow: 1000000,
@@ -18333,6 +18367,23 @@ export const MODELS = {
18333
18367
  contextWindow: 1000000,
18334
18368
  maxTokens: 128000,
18335
18369
  },
18370
+ "zai/glm-5.3": {
18371
+ id: "zai/glm-5.3",
18372
+ name: "GLM 5.3",
18373
+ api: "anthropic-messages",
18374
+ provider: "vercel-ai-gateway",
18375
+ baseUrl: "https://ai-gateway.vercel.sh",
18376
+ reasoning: true,
18377
+ input: ["text"],
18378
+ cost: {
18379
+ input: 1.4,
18380
+ output: 4.4,
18381
+ cacheRead: 0.26,
18382
+ cacheWrite: 0,
18383
+ },
18384
+ contextWindow: 1000000,
18385
+ maxTokens: 12800,
18386
+ },
18336
18387
  "zai/glm-5v-turbo": {
18337
18388
  id: "zai/glm-5v-turbo",
18338
18389
  name: "GLM 5V Turbo",