@dreb/ai 2.32.1 → 2.34.0

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.
@@ -4403,6 +4403,24 @@ export const MODELS = {
4403
4403
  contextWindow: 262144,
4404
4404
  maxTokens: 65536,
4405
4405
  },
4406
+ "Qwen/Qwen3.6-27B": {
4407
+ id: "Qwen/Qwen3.6-27B",
4408
+ name: "Qwen3.6 27B",
4409
+ api: "openai-completions",
4410
+ provider: "huggingface",
4411
+ baseUrl: "https://router.huggingface.co/v1",
4412
+ compat: { "supportsDeveloperRole": false },
4413
+ reasoning: true,
4414
+ input: ["text", "image"],
4415
+ cost: {
4416
+ input: 0.47,
4417
+ output: 3.19,
4418
+ cacheRead: 0,
4419
+ cacheWrite: 0,
4420
+ },
4421
+ contextWindow: 262144,
4422
+ maxTokens: 65536,
4423
+ },
4406
4424
  "Qwen/Qwen3.6-35B-A3B": {
4407
4425
  id: "Qwen/Qwen3.6-35B-A3B",
4408
4426
  name: "Qwen3.6 35B-A3B",
@@ -4439,6 +4457,24 @@ export const MODELS = {
4439
4457
  contextWindow: 262144,
4440
4458
  maxTokens: 4096,
4441
4459
  },
4460
+ "XiaomiMiMo/MiMo-V2.5-Pro": {
4461
+ id: "XiaomiMiMo/MiMo-V2.5-Pro",
4462
+ name: "MiMo-V2.5-Pro",
4463
+ api: "openai-completions",
4464
+ provider: "huggingface",
4465
+ baseUrl: "https://router.huggingface.co/v1",
4466
+ compat: { "supportsDeveloperRole": false },
4467
+ reasoning: true,
4468
+ input: ["text"],
4469
+ cost: {
4470
+ input: 1,
4471
+ output: 3,
4472
+ cacheRead: 0,
4473
+ cacheWrite: 0,
4474
+ },
4475
+ contextWindow: 1048576,
4476
+ maxTokens: 131072,
4477
+ },
4442
4478
  "deepseek-ai/DeepSeek-R1": {
4443
4479
  id: "deepseek-ai/DeepSeek-R1",
4444
4480
  name: "DeepSeek-R1",
@@ -4709,6 +4745,24 @@ export const MODELS = {
4709
4745
  contextWindow: 262144,
4710
4746
  maxTokens: 256000,
4711
4747
  },
4748
+ "stepfun-ai/Step-3.7-Flash": {
4749
+ id: "stepfun-ai/Step-3.7-Flash",
4750
+ name: "Step 3.7 Flash",
4751
+ api: "openai-completions",
4752
+ provider: "huggingface",
4753
+ baseUrl: "https://router.huggingface.co/v1",
4754
+ compat: { "supportsDeveloperRole": false },
4755
+ reasoning: true,
4756
+ input: ["text", "image"],
4757
+ cost: {
4758
+ input: 0.2,
4759
+ output: 1.15,
4760
+ cacheRead: 0,
4761
+ cacheWrite: 0,
4762
+ },
4763
+ contextWindow: 262144,
4764
+ maxTokens: 256000,
4765
+ },
4712
4766
  "zai-org/GLM-4.5": {
4713
4767
  id: "zai-org/GLM-4.5",
4714
4768
  name: "GLM-4.5",
@@ -7318,7 +7372,7 @@ export const MODELS = {
7318
7372
  cacheRead: 0.02,
7319
7373
  cacheWrite: 0,
7320
7374
  },
7321
- contextWindow: 512000,
7375
+ contextWindow: 1000000,
7322
7376
  maxTokens: 131072,
7323
7377
  },
7324
7378
  "qwen3.6-plus": {
@@ -8031,7 +8085,7 @@ export const MODELS = {
8031
8085
  cost: {
8032
8086
  input: 0.2288,
8033
8087
  output: 0.3432,
8034
- cacheRead: 0,
8088
+ cacheRead: 0.02288,
8035
8089
  cacheWrite: 0,
8036
8090
  },
8037
8091
  contextWindow: 131072,
@@ -8692,9 +8746,9 @@ export const MODELS = {
8692
8746
  reasoning: true,
8693
8747
  input: ["text"],
8694
8748
  cost: {
8695
- input: 0.15,
8696
- output: 0.8999999999999999,
8697
- cacheRead: 0.049999999999999996,
8749
+ input: 0.12,
8750
+ output: 0.48,
8751
+ cacheRead: 0,
8698
8752
  cacheWrite: 0,
8699
8753
  },
8700
8754
  contextWindow: 204800,
@@ -8709,8 +8763,8 @@ export const MODELS = {
8709
8763
  reasoning: true,
8710
8764
  input: ["text"],
8711
8765
  cost: {
8712
- input: 0.24,
8713
- output: 0.96,
8766
+ input: 0.18,
8767
+ output: 0.72,
8714
8768
  cacheRead: 0,
8715
8769
  cacheWrite: 0,
8716
8770
  },
@@ -9068,7 +9122,7 @@ export const MODELS = {
9068
9122
  cost: {
9069
9123
  input: 0.6,
9070
9124
  output: 2.5,
9071
- cacheRead: 0,
9125
+ cacheRead: 0.6,
9072
9126
  cacheWrite: 0,
9073
9127
  },
9074
9128
  contextWindow: 262144,
@@ -9202,13 +9256,13 @@ export const MODELS = {
9202
9256
  reasoning: true,
9203
9257
  input: ["text"],
9204
9258
  cost: {
9205
- input: 0.09,
9206
- output: 0.44999999999999996,
9259
+ input: 0.08499999999999999,
9260
+ output: 0.39999999999999997,
9207
9261
  cacheRead: 0,
9208
9262
  cacheWrite: 0,
9209
9263
  },
9210
9264
  contextWindow: 1000000,
9211
- maxTokens: 4096,
9265
+ maxTokens: 16384,
9212
9266
  },
9213
9267
  "nvidia/nemotron-3-super-120b-a12b:free": {
9214
9268
  id: "nvidia/nemotron-3-super-120b-a12b:free",
@@ -9984,13 +10038,13 @@ export const MODELS = {
9984
10038
  reasoning: true,
9985
10039
  input: ["text"],
9986
10040
  cost: {
9987
- input: 0.039,
9988
- output: 0.18,
10041
+ input: 0.03,
10042
+ output: 0.15,
9989
10043
  cacheRead: 0,
9990
10044
  cacheWrite: 0,
9991
10045
  },
9992
10046
  contextWindow: 131072,
9993
- maxTokens: 4096,
10047
+ maxTokens: 131072,
9994
10048
  },
9995
10049
  "openai/gpt-oss-120b:free": {
9996
10050
  id: "openai/gpt-oss-120b:free",
@@ -10921,11 +10975,11 @@ export const MODELS = {
10921
10975
  cost: {
10922
10976
  input: 0.14,
10923
10977
  output: 1,
10924
- cacheRead: 0,
10978
+ cacheRead: 0.049999999999999996,
10925
10979
  cacheWrite: 0,
10926
10980
  },
10927
10981
  contextWindow: 262144,
10928
- maxTokens: 262144,
10982
+ maxTokens: 81920,
10929
10983
  },
10930
10984
  "qwen/qwen3.5-397b-a17b": {
10931
10985
  id: "qwen/qwen3.5-397b-a17b",
@@ -11533,11 +11587,11 @@ export const MODELS = {
11533
11587
  cost: {
11534
11588
  input: 0.98,
11535
11589
  output: 3.08,
11536
- cacheRead: 0.49,
11590
+ cacheRead: 0.182,
11537
11591
  cacheWrite: 0,
11538
11592
  },
11539
11593
  contextWindow: 202752,
11540
- maxTokens: 65535,
11594
+ maxTokens: 4096,
11541
11595
  },
11542
11596
  "z-ai/glm-5.2": {
11543
11597
  id: "z-ai/glm-5.2",