@hyperspaceng/neural-ai 0.65.1 → 0.66.2

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.
@@ -1209,6 +1209,23 @@ export const MODELS = {
1209
1209
  contextWindow: 131072,
1210
1210
  maxTokens: 65536,
1211
1211
  },
1212
+ "qwen.qwen3-coder-next": {
1213
+ id: "qwen.qwen3-coder-next",
1214
+ name: "Qwen3 Coder Next",
1215
+ api: "bedrock-converse-stream",
1216
+ provider: "amazon-bedrock",
1217
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1218
+ reasoning: true,
1219
+ input: ["text"],
1220
+ cost: {
1221
+ input: 0.22,
1222
+ output: 1.8,
1223
+ cacheRead: 0,
1224
+ cacheWrite: 0,
1225
+ },
1226
+ contextWindow: 131072,
1227
+ maxTokens: 65536,
1228
+ },
1212
1229
  "qwen.qwen3-next-80b-a3b": {
1213
1230
  id: "qwen.qwen3-next-80b-a3b",
1214
1231
  name: "Qwen/Qwen3-Next-80B-A3B-Instruct",
@@ -3015,7 +3032,7 @@ export const MODELS = {
3015
3032
  },
3016
3033
  "gpt-5.4-mini": {
3017
3034
  id: "gpt-5.4-mini",
3018
- name: "GPT-5.4 mini",
3035
+ name: "GPT-5.4 Mini",
3019
3036
  api: "openai-responses",
3020
3037
  provider: "github-copilot",
3021
3038
  baseUrl: "https://api.individual.githubcopilot.com",
@@ -3477,8 +3494,8 @@ export const MODELS = {
3477
3494
  contextWindow: 131072,
3478
3495
  maxTokens: 8192,
3479
3496
  },
3480
- "gemma-4-26b": {
3481
- id: "gemma-4-26b",
3497
+ "gemma-4-26b-it": {
3498
+ id: "gemma-4-26b-it",
3482
3499
  name: "Gemma 4 26B",
3483
3500
  api: "google-generative-ai",
3484
3501
  provider: "google",
@@ -3494,8 +3511,8 @@ export const MODELS = {
3494
3511
  contextWindow: 256000,
3495
3512
  maxTokens: 8192,
3496
3513
  },
3497
- "gemma-4-31b": {
3498
- id: "gemma-4-31b",
3514
+ "gemma-4-31b-it": {
3515
+ id: "gemma-4-31b-it",
3499
3516
  name: "Gemma 4 31B",
3500
3517
  api: "google-generative-ai",
3501
3518
  provider: "google",
@@ -4627,6 +4644,24 @@ export const MODELS = {
4627
4644
  contextWindow: 202752,
4628
4645
  maxTokens: 131072,
4629
4646
  },
4647
+ "zai-org/GLM-5.1": {
4648
+ id: "zai-org/GLM-5.1",
4649
+ name: "GLM-5.1",
4650
+ api: "openai-completions",
4651
+ provider: "huggingface",
4652
+ baseUrl: "https://router.huggingface.co/v1",
4653
+ compat: { "supportsDeveloperRole": false },
4654
+ reasoning: true,
4655
+ input: ["text"],
4656
+ cost: {
4657
+ input: 1,
4658
+ output: 3.2,
4659
+ cacheRead: 0.2,
4660
+ cacheWrite: 0,
4661
+ },
4662
+ contextWindow: 202752,
4663
+ maxTokens: 131072,
4664
+ },
4630
4665
  },
4631
4666
  "kimi-coding": {
4632
4667
  "k2p5": {
@@ -6239,6 +6274,23 @@ export const MODELS = {
6239
6274
  contextWindow: 204800,
6240
6275
  maxTokens: 131072,
6241
6276
  },
6277
+ "glm-5.1": {
6278
+ id: "glm-5.1",
6279
+ name: "GLM-5.1",
6280
+ api: "openai-completions",
6281
+ provider: "opencode",
6282
+ baseUrl: "https://opencode.ai/zen/v1",
6283
+ reasoning: true,
6284
+ input: ["text"],
6285
+ cost: {
6286
+ input: 1.4,
6287
+ output: 4.4,
6288
+ cacheRead: 0.26,
6289
+ cacheWrite: 0,
6290
+ },
6291
+ contextWindow: 204800,
6292
+ maxTokens: 131072,
6293
+ },
6242
6294
  "gpt-5": {
6243
6295
  id: "gpt-5",
6244
6296
  name: "GPT-5",
@@ -6545,23 +6597,6 @@ export const MODELS = {
6545
6597
  contextWindow: 204800,
6546
6598
  maxTokens: 128000,
6547
6599
  },
6548
- "qwen3.6-plus-free": {
6549
- id: "qwen3.6-plus-free",
6550
- name: "Qwen3.6 Plus Free",
6551
- api: "openai-completions",
6552
- provider: "opencode",
6553
- baseUrl: "https://opencode.ai/zen/v1",
6554
- reasoning: true,
6555
- input: ["text"],
6556
- cost: {
6557
- input: 0,
6558
- output: 0,
6559
- cacheRead: 0,
6560
- cacheWrite: 0,
6561
- },
6562
- contextWindow: 1048576,
6563
- maxTokens: 64000,
6564
- },
6565
6600
  },
6566
6601
  "opencode-go": {
6567
6602
  "glm-5": {
@@ -6581,6 +6616,23 @@ export const MODELS = {
6581
6616
  contextWindow: 204800,
6582
6617
  maxTokens: 131072,
6583
6618
  },
6619
+ "glm-5.1": {
6620
+ id: "glm-5.1",
6621
+ name: "GLM-5.1",
6622
+ api: "openai-completions",
6623
+ provider: "opencode-go",
6624
+ baseUrl: "https://opencode.ai/zen/go/v1",
6625
+ reasoning: true,
6626
+ input: ["text"],
6627
+ cost: {
6628
+ input: 1.4,
6629
+ output: 4.4,
6630
+ cacheRead: 0.26,
6631
+ cacheWrite: 0,
6632
+ },
6633
+ contextWindow: 204800,
6634
+ maxTokens: 131072,
6635
+ },
6584
6636
  "kimi-k2.5": {
6585
6637
  id: "kimi-k2.5",
6586
6638
  name: "Kimi K2.5",
@@ -6635,9 +6687,9 @@ export const MODELS = {
6635
6687
  "minimax-m2.5": {
6636
6688
  id: "minimax-m2.5",
6637
6689
  name: "MiniMax M2.5",
6638
- api: "openai-completions",
6690
+ api: "anthropic-messages",
6639
6691
  provider: "opencode-go",
6640
- baseUrl: "https://opencode.ai/zen/go/v1",
6692
+ baseUrl: "https://opencode.ai/zen/go",
6641
6693
  reasoning: true,
6642
6694
  input: ["text"],
6643
6695
  cost: {
@@ -6853,7 +6905,7 @@ export const MODELS = {
6853
6905
  cacheWrite: 3.75,
6854
6906
  },
6855
6907
  contextWindow: 200000,
6856
- maxTokens: 64000,
6908
+ maxTokens: 128000,
6857
6909
  },
6858
6910
  "anthropic/claude-3.7-sonnet:thinking": {
6859
6911
  id: "anthropic/claude-3.7-sonnet:thinking",
@@ -6957,6 +7009,23 @@ export const MODELS = {
6957
7009
  contextWindow: 1000000,
6958
7010
  maxTokens: 128000,
6959
7011
  },
7012
+ "anthropic/claude-opus-4.6-fast": {
7013
+ id: "anthropic/claude-opus-4.6-fast",
7014
+ name: "Anthropic: Claude Opus 4.6 (Fast)",
7015
+ api: "openai-completions",
7016
+ provider: "openrouter",
7017
+ baseUrl: "https://openrouter.ai/api/v1",
7018
+ reasoning: true,
7019
+ input: ["text", "image"],
7020
+ cost: {
7021
+ input: 30,
7022
+ output: 150,
7023
+ cacheRead: 3,
7024
+ cacheWrite: 37.5,
7025
+ },
7026
+ contextWindow: 1000000,
7027
+ maxTokens: 128000,
7028
+ },
6960
7029
  "anthropic/claude-sonnet-4": {
6961
7030
  id: "anthropic/claude-sonnet-4",
6962
7031
  name: "Anthropic: Claude Sonnet 4",
@@ -6971,7 +7040,7 @@ export const MODELS = {
6971
7040
  cacheRead: 0.3,
6972
7041
  cacheWrite: 3.75,
6973
7042
  },
6974
- contextWindow: 200000,
7043
+ contextWindow: 1000000,
6975
7044
  maxTokens: 64000,
6976
7045
  },
6977
7046
  "anthropic/claude-sonnet-4.5": {
@@ -7059,23 +7128,6 @@ export const MODELS = {
7059
7128
  contextWindow: 131072,
7060
7129
  maxTokens: 131072,
7061
7130
  },
7062
- "arcee-ai/trinity-mini:free": {
7063
- id: "arcee-ai/trinity-mini:free",
7064
- name: "Arcee AI: Trinity Mini (free)",
7065
- api: "openai-completions",
7066
- provider: "openrouter",
7067
- baseUrl: "https://openrouter.ai/api/v1",
7068
- reasoning: true,
7069
- input: ["text"],
7070
- cost: {
7071
- input: 0,
7072
- output: 0,
7073
- cacheRead: 0,
7074
- cacheWrite: 0,
7075
- },
7076
- contextWindow: 131072,
7077
- maxTokens: 4096,
7078
- },
7079
7131
  "arcee-ai/virtuoso-large": {
7080
7132
  id: "arcee-ai/virtuoso-large",
7081
7133
  name: "Arcee AI: Virtuoso Large",
@@ -7612,7 +7664,7 @@ export const MODELS = {
7612
7664
  reasoning: true,
7613
7665
  input: ["text", "image"],
7614
7666
  cost: {
7615
- input: 0.13,
7667
+ input: 0.12,
7616
7668
  output: 0.39999999999999997,
7617
7669
  cacheRead: 0,
7618
7670
  cacheWrite: 0,
@@ -7620,6 +7672,23 @@ export const MODELS = {
7620
7672
  contextWindow: 262144,
7621
7673
  maxTokens: 262144,
7622
7674
  },
7675
+ "google/gemma-4-26b-a4b-it:free": {
7676
+ id: "google/gemma-4-26b-a4b-it:free",
7677
+ name: "Google: Gemma 4 26B A4B (free)",
7678
+ api: "openai-completions",
7679
+ provider: "openrouter",
7680
+ baseUrl: "https://openrouter.ai/api/v1",
7681
+ reasoning: true,
7682
+ input: ["text", "image"],
7683
+ cost: {
7684
+ input: 0,
7685
+ output: 0,
7686
+ cacheRead: 0,
7687
+ cacheWrite: 0,
7688
+ },
7689
+ contextWindow: 262144,
7690
+ maxTokens: 32768,
7691
+ },
7623
7692
  "google/gemma-4-31b-it": {
7624
7693
  id: "google/gemma-4-31b-it",
7625
7694
  name: "Google: Gemma 4 31B",
@@ -7637,6 +7706,23 @@ export const MODELS = {
7637
7706
  contextWindow: 262144,
7638
7707
  maxTokens: 131072,
7639
7708
  },
7709
+ "google/gemma-4-31b-it:free": {
7710
+ id: "google/gemma-4-31b-it:free",
7711
+ name: "Google: Gemma 4 31B (free)",
7712
+ api: "openai-completions",
7713
+ provider: "openrouter",
7714
+ baseUrl: "https://openrouter.ai/api/v1",
7715
+ reasoning: true,
7716
+ input: ["text", "image"],
7717
+ cost: {
7718
+ input: 0,
7719
+ output: 0,
7720
+ cacheRead: 0,
7721
+ cacheWrite: 0,
7722
+ },
7723
+ contextWindow: 262144,
7724
+ maxTokens: 32768,
7725
+ },
7640
7726
  "inception/mercury": {
7641
7727
  id: "inception/mercury",
7642
7728
  name: "Inception: Mercury",
@@ -7884,13 +7970,13 @@ export const MODELS = {
7884
7970
  reasoning: true,
7885
7971
  input: ["text"],
7886
7972
  cost: {
7887
- input: 0.27,
7973
+ input: 0.29,
7888
7974
  output: 0.95,
7889
- cacheRead: 0.0290000007,
7975
+ cacheRead: 0.03,
7890
7976
  cacheWrite: 0,
7891
7977
  },
7892
7978
  contextWindow: 196608,
7893
- maxTokens: 4096,
7979
+ maxTokens: 196608,
7894
7980
  },
7895
7981
  "minimax/minimax-m2.5": {
7896
7982
  id: "minimax/minimax-m2.5",
@@ -8345,11 +8431,11 @@ export const MODELS = {
8345
8431
  cost: {
8346
8432
  input: 0.39999999999999997,
8347
8433
  output: 2,
8348
- cacheRead: 0.15,
8434
+ cacheRead: 0,
8349
8435
  cacheWrite: 0,
8350
8436
  },
8351
- contextWindow: 131072,
8352
- maxTokens: 4096,
8437
+ contextWindow: 262144,
8438
+ maxTokens: 262144,
8353
8439
  },
8354
8440
  "moonshotai/kimi-k2-thinking": {
8355
8441
  id: "moonshotai/kimi-k2-thinking",
@@ -8360,12 +8446,12 @@ export const MODELS = {
8360
8446
  reasoning: true,
8361
8447
  input: ["text"],
8362
8448
  cost: {
8363
- input: 0.47,
8364
- output: 2,
8365
- cacheRead: 0.14100000000000001,
8449
+ input: 0.6,
8450
+ output: 2.5,
8451
+ cacheRead: 0,
8366
8452
  cacheWrite: 0,
8367
8453
  },
8368
- contextWindow: 131072,
8454
+ contextWindow: 262144,
8369
8455
  maxTokens: 4096,
8370
8456
  },
8371
8457
  "moonshotai/kimi-k2.5": {
@@ -8706,7 +8792,7 @@ export const MODELS = {
8706
8792
  cacheWrite: 0,
8707
8793
  },
8708
8794
  contextWindow: 1047576,
8709
- maxTokens: 32768,
8795
+ maxTokens: 4096,
8710
8796
  },
8711
8797
  "openai/gpt-4.1-mini": {
8712
8798
  id: "openai/gpt-4.1-mini",
@@ -8753,7 +8839,7 @@ export const MODELS = {
8753
8839
  cost: {
8754
8840
  input: 2.5,
8755
8841
  output: 10,
8756
- cacheRead: 1.25,
8842
+ cacheRead: 0,
8757
8843
  cacheWrite: 0,
8758
8844
  },
8759
8845
  contextWindow: 128000,
@@ -8974,11 +9060,11 @@ export const MODELS = {
8974
9060
  cost: {
8975
9061
  input: 0.049999999999999996,
8976
9062
  output: 0.39999999999999997,
8977
- cacheRead: 0.005,
9063
+ cacheRead: 0.01,
8978
9064
  cacheWrite: 0,
8979
9065
  },
8980
9066
  contextWindow: 400000,
8981
- maxTokens: 128000,
9067
+ maxTokens: 4096,
8982
9068
  },
8983
9069
  "openai/gpt-5-pro": {
8984
9070
  id: "openai/gpt-5-pro",
@@ -9008,7 +9094,7 @@ export const MODELS = {
9008
9094
  cost: {
9009
9095
  input: 1.25,
9010
9096
  output: 10,
9011
- cacheRead: 0.125,
9097
+ cacheRead: 0.13,
9012
9098
  cacheWrite: 0,
9013
9099
  },
9014
9100
  contextWindow: 400000,
@@ -9076,11 +9162,11 @@ export const MODELS = {
9076
9162
  cost: {
9077
9163
  input: 0.25,
9078
9164
  output: 2,
9079
- cacheRead: 0.024999999999999998,
9165
+ cacheRead: 0.03,
9080
9166
  cacheWrite: 0,
9081
9167
  },
9082
9168
  contextWindow: 400000,
9083
- maxTokens: 100000,
9169
+ maxTokens: 128000,
9084
9170
  },
9085
9171
  "openai/gpt-5.2": {
9086
9172
  id: "openai/gpt-5.2",
@@ -9114,7 +9200,7 @@ export const MODELS = {
9114
9200
  cacheWrite: 0,
9115
9201
  },
9116
9202
  contextWindow: 128000,
9117
- maxTokens: 16384,
9203
+ maxTokens: 32000,
9118
9204
  },
9119
9205
  "openai/gpt-5.2-codex": {
9120
9206
  id: "openai/gpt-5.2-codex",
@@ -9330,12 +9416,12 @@ export const MODELS = {
9330
9416
  input: ["text"],
9331
9417
  cost: {
9332
9418
  input: 0.03,
9333
- output: 0.11,
9334
- cacheRead: 0.015,
9419
+ output: 0.14,
9420
+ cacheRead: 0,
9335
9421
  cacheWrite: 0,
9336
9422
  },
9337
9423
  contextWindow: 131072,
9338
- maxTokens: 131072,
9424
+ maxTokens: 4096,
9339
9425
  },
9340
9426
  "openai/gpt-oss-20b:free": {
9341
9427
  id: "openai/gpt-oss-20b:free",
@@ -10289,17 +10375,17 @@ export const MODELS = {
10289
10375
  contextWindow: 1000000,
10290
10376
  maxTokens: 65536,
10291
10377
  },
10292
- "qwen/qwen3.6-plus:free": {
10293
- id: "qwen/qwen3.6-plus:free",
10294
- name: "Qwen: Qwen3.6 Plus (free)",
10378
+ "qwen/qwen3.6-plus": {
10379
+ id: "qwen/qwen3.6-plus",
10380
+ name: "Qwen: Qwen3.6 Plus",
10295
10381
  api: "openai-completions",
10296
10382
  provider: "openrouter",
10297
10383
  baseUrl: "https://openrouter.ai/api/v1",
10298
10384
  reasoning: true,
10299
10385
  input: ["text", "image"],
10300
10386
  cost: {
10301
- input: 0,
10302
- output: 0,
10387
+ input: 0.325,
10388
+ output: 1.95,
10303
10389
  cacheRead: 0,
10304
10390
  cacheWrite: 0,
10305
10391
  },
@@ -10408,23 +10494,6 @@ export const MODELS = {
10408
10494
  contextWindow: 262144,
10409
10495
  maxTokens: 65536,
10410
10496
  },
10411
- "stepfun/step-3.5-flash:free": {
10412
- id: "stepfun/step-3.5-flash:free",
10413
- name: "StepFun: Step 3.5 Flash (free)",
10414
- api: "openai-completions",
10415
- provider: "openrouter",
10416
- baseUrl: "https://openrouter.ai/api/v1",
10417
- reasoning: true,
10418
- input: ["text"],
10419
- cost: {
10420
- input: 0,
10421
- output: 0,
10422
- cacheRead: 0,
10423
- cacheWrite: 0,
10424
- },
10425
- contextWindow: 256000,
10426
- maxTokens: 256000,
10427
- },
10428
10497
  "thedrummer/rocinante-12b": {
10429
10498
  id: "thedrummer/rocinante-12b",
10430
10499
  name: "TheDrummer: Rocinante 12B",
@@ -10884,6 +10953,23 @@ export const MODELS = {
10884
10953
  contextWindow: 202752,
10885
10954
  maxTokens: 131072,
10886
10955
  },
10956
+ "z-ai/glm-5.1": {
10957
+ id: "z-ai/glm-5.1",
10958
+ name: "Z.ai: GLM 5.1",
10959
+ api: "openai-completions",
10960
+ provider: "openrouter",
10961
+ baseUrl: "https://openrouter.ai/api/v1",
10962
+ reasoning: true,
10963
+ input: ["text"],
10964
+ cost: {
10965
+ input: 0.95,
10966
+ output: 3.15,
10967
+ cacheRead: 0.475,
10968
+ cacheWrite: 0,
10969
+ },
10970
+ contextWindow: 202752,
10971
+ maxTokens: 65535,
10972
+ },
10887
10973
  "z-ai/glm-5v-turbo": {
10888
10974
  id: "z-ai/glm-5v-turbo",
10889
10975
  name: "Z.ai: GLM 5V Turbo",
@@ -10929,13 +11015,13 @@ export const MODELS = {
10929
11015
  reasoning: false,
10930
11016
  input: ["text"],
10931
11017
  cost: {
10932
- input: 0.22,
10933
- output: 0.88,
10934
- cacheRead: 0.11,
11018
+ input: 0.6,
11019
+ output: 1.2,
11020
+ cacheRead: 0.6,
10935
11021
  cacheWrite: 0,
10936
11022
  },
10937
- contextWindow: 32768,
10938
- maxTokens: 16384,
11023
+ contextWindow: 131000,
11024
+ maxTokens: 40000,
10939
11025
  },
10940
11026
  "alibaba/qwen-3-30b": {
10941
11027
  id: "alibaba/qwen-3-30b",
@@ -11170,7 +11256,7 @@ export const MODELS = {
11170
11256
  input: 0.5,
11171
11257
  output: 3,
11172
11258
  cacheRead: 0.09999999999999999,
11173
- cacheWrite: 0.625,
11259
+ cacheWrite: 0,
11174
11260
  },
11175
11261
  contextWindow: 1000000,
11176
11262
  maxTokens: 64000,
@@ -11662,7 +11748,7 @@ export const MODELS = {
11662
11748
  cost: {
11663
11749
  input: 0.25,
11664
11750
  output: 1.5,
11665
- cacheRead: 0,
11751
+ cacheRead: 0.03,
11666
11752
  cacheWrite: 0,
11667
11753
  },
11668
11754
  contextWindow: 1000000,
@@ -11785,7 +11871,7 @@ export const MODELS = {
11785
11871
  cacheWrite: 0,
11786
11872
  },
11787
11873
  contextWindow: 128000,
11788
- maxTokens: 8192,
11874
+ maxTokens: 100000,
11789
11875
  },
11790
11876
  "meta/llama-3.1-70b": {
11791
11877
  id: "meta/llama-3.1-70b",
@@ -12790,23 +12876,6 @@ export const MODELS = {
12790
12876
  contextWindow: 1050000,
12791
12877
  maxTokens: 128000,
12792
12878
  },
12793
- "openai/gpt-oss-120b": {
12794
- id: "openai/gpt-oss-120b",
12795
- name: "gpt-oss-120b",
12796
- api: "anthropic-messages",
12797
- provider: "vercel-ai-gateway",
12798
- baseUrl: "https://ai-gateway.vercel.sh",
12799
- reasoning: true,
12800
- input: ["text"],
12801
- cost: {
12802
- input: 0.15,
12803
- output: 0.6,
12804
- cacheRead: 0,
12805
- cacheWrite: 0,
12806
- },
12807
- contextWindow: 128000,
12808
- maxTokens: 8192,
12809
- },
12810
12879
  "openai/gpt-oss-20b": {
12811
12880
  id: "openai/gpt-oss-20b",
12812
12881
  name: "gpt-oss-20b",
@@ -12994,23 +13063,6 @@ export const MODELS = {
12994
13063
  contextWindow: 131072,
12995
13064
  maxTokens: 131072,
12996
13065
  },
12997
- "xai/grok-2-vision": {
12998
- id: "xai/grok-2-vision",
12999
- name: "Grok 2 Vision",
13000
- api: "anthropic-messages",
13001
- provider: "vercel-ai-gateway",
13002
- baseUrl: "https://ai-gateway.vercel.sh",
13003
- reasoning: false,
13004
- input: ["text", "image"],
13005
- cost: {
13006
- input: 2,
13007
- output: 10,
13008
- cacheRead: 0,
13009
- cacheWrite: 0,
13010
- },
13011
- contextWindow: 32768,
13012
- maxTokens: 32768,
13013
- },
13014
13066
  "xai/grok-3": {
13015
13067
  id: "xai/grok-3",
13016
13068
  name: "Grok 3 Beta",
@@ -13428,13 +13480,13 @@ export const MODELS = {
13428
13480
  reasoning: true,
13429
13481
  input: ["text"],
13430
13482
  cost: {
13431
- input: 0.6,
13432
- output: 2.2,
13433
- cacheRead: 0.11,
13483
+ input: 2.25,
13484
+ output: 2.75,
13485
+ cacheRead: 2.25,
13434
13486
  cacheWrite: 0,
13435
13487
  },
13436
- contextWindow: 200000,
13437
- maxTokens: 120000,
13488
+ contextWindow: 131000,
13489
+ maxTokens: 40000,
13438
13490
  },
13439
13491
  "zai/glm-4.7-flash": {
13440
13492
  id: "zai/glm-4.7-flash",
@@ -13504,6 +13556,23 @@ export const MODELS = {
13504
13556
  contextWindow: 202800,
13505
13557
  maxTokens: 131100,
13506
13558
  },
13559
+ "zai/glm-5.1": {
13560
+ id: "zai/glm-5.1",
13561
+ name: "GLM 5.1",
13562
+ api: "anthropic-messages",
13563
+ provider: "vercel-ai-gateway",
13564
+ baseUrl: "https://ai-gateway.vercel.sh",
13565
+ reasoning: true,
13566
+ input: ["text"],
13567
+ cost: {
13568
+ input: 1.4,
13569
+ output: 4.4,
13570
+ cacheRead: 0.26,
13571
+ cacheWrite: 0,
13572
+ },
13573
+ contextWindow: 202800,
13574
+ maxTokens: 64000,
13575
+ },
13507
13576
  "zai/glm-5v-turbo": {
13508
13577
  id: "zai/glm-5v-turbo",
13509
13578
  name: "GLM 5V Turbo",
@@ -13943,9 +14012,9 @@ export const MODELS = {
13943
14012
  reasoning: true,
13944
14013
  input: ["text"],
13945
14014
  cost: {
13946
- input: 0.6,
13947
- output: 2.2,
13948
- cacheRead: 0.11,
14015
+ input: 0,
14016
+ output: 0,
14017
+ cacheRead: 0,
13949
14018
  cacheWrite: 0,
13950
14019
  },
13951
14020
  contextWindow: 131072,
@@ -13961,9 +14030,9 @@ export const MODELS = {
13961
14030
  reasoning: true,
13962
14031
  input: ["text"],
13963
14032
  cost: {
13964
- input: 0.2,
13965
- output: 1.1,
13966
- cacheRead: 0.03,
14033
+ input: 0,
14034
+ output: 0,
14035
+ cacheRead: 0,
13967
14036
  cacheWrite: 0,
13968
14037
  },
13969
14038
  contextWindow: 131072,
@@ -13997,8 +14066,8 @@ export const MODELS = {
13997
14066
  reasoning: true,
13998
14067
  input: ["text", "image"],
13999
14068
  cost: {
14000
- input: 0.6,
14001
- output: 1.8,
14069
+ input: 0,
14070
+ output: 0,
14002
14071
  cacheRead: 0,
14003
14072
  cacheWrite: 0,
14004
14073
  },
@@ -14015,9 +14084,9 @@ export const MODELS = {
14015
14084
  reasoning: true,
14016
14085
  input: ["text"],
14017
14086
  cost: {
14018
- input: 0.6,
14019
- output: 2.2,
14020
- cacheRead: 0.11,
14087
+ input: 0,
14088
+ output: 0,
14089
+ cacheRead: 0,
14021
14090
  cacheWrite: 0,
14022
14091
  },
14023
14092
  contextWindow: 204800,
@@ -14033,8 +14102,8 @@ export const MODELS = {
14033
14102
  reasoning: true,
14034
14103
  input: ["text", "image"],
14035
14104
  cost: {
14036
- input: 0.3,
14037
- output: 0.9,
14105
+ input: 0,
14106
+ output: 0,
14038
14107
  cacheRead: 0,
14039
14108
  cacheWrite: 0,
14040
14109
  },
@@ -14051,9 +14120,9 @@ export const MODELS = {
14051
14120
  reasoning: true,
14052
14121
  input: ["text"],
14053
14122
  cost: {
14054
- input: 0.6,
14055
- output: 2.2,
14056
- cacheRead: 0.11,
14123
+ input: 0,
14124
+ output: 0,
14125
+ cacheRead: 0,
14057
14126
  cacheWrite: 0,
14058
14127
  },
14059
14128
  contextWindow: 204800,
@@ -14105,9 +14174,9 @@ export const MODELS = {
14105
14174
  reasoning: true,
14106
14175
  input: ["text"],
14107
14176
  cost: {
14108
- input: 1,
14109
- output: 3.2,
14110
- cacheRead: 0.2,
14177
+ input: 0,
14178
+ output: 0,
14179
+ cacheRead: 0,
14111
14180
  cacheWrite: 0,
14112
14181
  },
14113
14182
  contextWindow: 204800,
@@ -14123,9 +14192,27 @@ export const MODELS = {
14123
14192
  reasoning: true,
14124
14193
  input: ["text"],
14125
14194
  cost: {
14126
- input: 1.2,
14127
- output: 4,
14128
- cacheRead: 0.24,
14195
+ input: 0,
14196
+ output: 0,
14197
+ cacheRead: 0,
14198
+ cacheWrite: 0,
14199
+ },
14200
+ contextWindow: 200000,
14201
+ maxTokens: 131072,
14202
+ },
14203
+ "glm-5.1": {
14204
+ id: "glm-5.1",
14205
+ name: "GLM-5.1",
14206
+ api: "openai-completions",
14207
+ provider: "zai",
14208
+ baseUrl: "https://api.z.ai/api/coding/paas/v4",
14209
+ compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
14210
+ reasoning: true,
14211
+ input: ["text"],
14212
+ cost: {
14213
+ input: 0,
14214
+ output: 0,
14215
+ cacheRead: 0,
14129
14216
  cacheWrite: 0,
14130
14217
  },
14131
14218
  contextWindow: 200000,
@@ -14141,9 +14228,9 @@ export const MODELS = {
14141
14228
  reasoning: true,
14142
14229
  input: ["text", "image"],
14143
14230
  cost: {
14144
- input: 1.2,
14145
- output: 4,
14146
- cacheRead: 0.24,
14231
+ input: 0,
14232
+ output: 0,
14233
+ cacheRead: 0,
14147
14234
  cacheWrite: 0,
14148
14235
  },
14149
14236
  contextWindow: 200000,