@hyperspaceng/neural-ai 0.65.3 → 0.67.2

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",
@@ -4339,6 +4356,24 @@ export const MODELS = {
4339
4356
  contextWindow: 204800,
4340
4357
  maxTokens: 131072,
4341
4358
  },
4359
+ "MiniMaxAI/MiniMax-M2.7": {
4360
+ id: "MiniMaxAI/MiniMax-M2.7",
4361
+ name: "MiniMax-M2.7",
4362
+ api: "openai-completions",
4363
+ provider: "huggingface",
4364
+ baseUrl: "https://router.huggingface.co/v1",
4365
+ compat: { "supportsDeveloperRole": false },
4366
+ reasoning: true,
4367
+ input: ["text"],
4368
+ cost: {
4369
+ input: 0.3,
4370
+ output: 1.2,
4371
+ cacheRead: 0.06,
4372
+ cacheWrite: 0,
4373
+ },
4374
+ contextWindow: 204800,
4375
+ maxTokens: 131072,
4376
+ },
4342
4377
  "Qwen/Qwen3-235B-A22B-Thinking-2507": {
4343
4378
  id: "Qwen/Qwen3-235B-A22B-Thinking-2507",
4344
4379
  name: "Qwen3-235B-A22B-Thinking-2507",
@@ -4627,6 +4662,24 @@ export const MODELS = {
4627
4662
  contextWindow: 202752,
4628
4663
  maxTokens: 131072,
4629
4664
  },
4665
+ "zai-org/GLM-5.1": {
4666
+ id: "zai-org/GLM-5.1",
4667
+ name: "GLM-5.1",
4668
+ api: "openai-completions",
4669
+ provider: "huggingface",
4670
+ baseUrl: "https://router.huggingface.co/v1",
4671
+ compat: { "supportsDeveloperRole": false },
4672
+ reasoning: true,
4673
+ input: ["text"],
4674
+ cost: {
4675
+ input: 1,
4676
+ output: 3.2,
4677
+ cacheRead: 0.2,
4678
+ cacheWrite: 0,
4679
+ },
4680
+ contextWindow: 202752,
4681
+ maxTokens: 131072,
4682
+ },
4630
4683
  },
4631
4684
  "kimi-coding": {
4632
4685
  "k2p5": {
@@ -6239,6 +6292,23 @@ export const MODELS = {
6239
6292
  contextWindow: 204800,
6240
6293
  maxTokens: 131072,
6241
6294
  },
6295
+ "glm-5.1": {
6296
+ id: "glm-5.1",
6297
+ name: "GLM-5.1",
6298
+ api: "openai-completions",
6299
+ provider: "opencode",
6300
+ baseUrl: "https://opencode.ai/zen/v1",
6301
+ reasoning: true,
6302
+ input: ["text"],
6303
+ cost: {
6304
+ input: 1.4,
6305
+ output: 4.4,
6306
+ cacheRead: 0.26,
6307
+ cacheWrite: 0,
6308
+ },
6309
+ contextWindow: 204800,
6310
+ maxTokens: 131072,
6311
+ },
6242
6312
  "gpt-5": {
6243
6313
  id: "gpt-5",
6244
6314
  name: "GPT-5",
@@ -6545,23 +6615,6 @@ export const MODELS = {
6545
6615
  contextWindow: 204800,
6546
6616
  maxTokens: 128000,
6547
6617
  },
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
6618
  },
6566
6619
  "opencode-go": {
6567
6620
  "glm-5": {
@@ -6581,6 +6634,23 @@ export const MODELS = {
6581
6634
  contextWindow: 204800,
6582
6635
  maxTokens: 131072,
6583
6636
  },
6637
+ "glm-5.1": {
6638
+ id: "glm-5.1",
6639
+ name: "GLM-5.1",
6640
+ api: "openai-completions",
6641
+ provider: "opencode-go",
6642
+ baseUrl: "https://opencode.ai/zen/go/v1",
6643
+ reasoning: true,
6644
+ input: ["text"],
6645
+ cost: {
6646
+ input: 1.4,
6647
+ output: 4.4,
6648
+ cacheRead: 0.26,
6649
+ cacheWrite: 0,
6650
+ },
6651
+ contextWindow: 204800,
6652
+ maxTokens: 131072,
6653
+ },
6584
6654
  "kimi-k2.5": {
6585
6655
  id: "kimi-k2.5",
6586
6656
  name: "Kimi K2.5",
@@ -6635,9 +6705,9 @@ export const MODELS = {
6635
6705
  "minimax-m2.5": {
6636
6706
  id: "minimax-m2.5",
6637
6707
  name: "MiniMax M2.5",
6638
- api: "openai-completions",
6708
+ api: "anthropic-messages",
6639
6709
  provider: "opencode-go",
6640
- baseUrl: "https://opencode.ai/zen/go/v1",
6710
+ baseUrl: "https://opencode.ai/zen/go",
6641
6711
  reasoning: true,
6642
6712
  input: ["text"],
6643
6713
  cost: {
@@ -6853,7 +6923,7 @@ export const MODELS = {
6853
6923
  cacheWrite: 3.75,
6854
6924
  },
6855
6925
  contextWindow: 200000,
6856
- maxTokens: 64000,
6926
+ maxTokens: 128000,
6857
6927
  },
6858
6928
  "anthropic/claude-3.7-sonnet:thinking": {
6859
6929
  id: "anthropic/claude-3.7-sonnet:thinking",
@@ -6957,6 +7027,23 @@ export const MODELS = {
6957
7027
  contextWindow: 1000000,
6958
7028
  maxTokens: 128000,
6959
7029
  },
7030
+ "anthropic/claude-opus-4.6-fast": {
7031
+ id: "anthropic/claude-opus-4.6-fast",
7032
+ name: "Anthropic: Claude Opus 4.6 (Fast)",
7033
+ api: "openai-completions",
7034
+ provider: "openrouter",
7035
+ baseUrl: "https://openrouter.ai/api/v1",
7036
+ reasoning: true,
7037
+ input: ["text", "image"],
7038
+ cost: {
7039
+ input: 30,
7040
+ output: 150,
7041
+ cacheRead: 3,
7042
+ cacheWrite: 37.5,
7043
+ },
7044
+ contextWindow: 1000000,
7045
+ maxTokens: 128000,
7046
+ },
6960
7047
  "anthropic/claude-sonnet-4": {
6961
7048
  id: "anthropic/claude-sonnet-4",
6962
7049
  name: "Anthropic: Claude Sonnet 4",
@@ -6971,7 +7058,7 @@ export const MODELS = {
6971
7058
  cacheRead: 0.3,
6972
7059
  cacheWrite: 3.75,
6973
7060
  },
6974
- contextWindow: 200000,
7061
+ contextWindow: 1000000,
6975
7062
  maxTokens: 64000,
6976
7063
  },
6977
7064
  "anthropic/claude-sonnet-4.5": {
@@ -7036,7 +7123,7 @@ export const MODELS = {
7036
7123
  cost: {
7037
7124
  input: 0.22,
7038
7125
  output: 0.85,
7039
- cacheRead: 0,
7126
+ cacheRead: 0.06,
7040
7127
  cacheWrite: 0,
7041
7128
  },
7042
7129
  contextWindow: 262144,
@@ -7059,23 +7146,6 @@ export const MODELS = {
7059
7146
  contextWindow: 131072,
7060
7147
  maxTokens: 131072,
7061
7148
  },
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
7149
  "arcee-ai/virtuoso-large": {
7080
7150
  id: "arcee-ai/virtuoso-large",
7081
7151
  name: "Arcee AI: Virtuoso Large",
@@ -7323,13 +7393,13 @@ export const MODELS = {
7323
7393
  reasoning: true,
7324
7394
  input: ["text"],
7325
7395
  cost: {
7326
- input: 0.44999999999999996,
7396
+ input: 0.5,
7327
7397
  output: 2.1500000000000004,
7328
- cacheRead: 0.22499999999999998,
7398
+ cacheRead: 0.35,
7329
7399
  cacheWrite: 0,
7330
7400
  },
7331
7401
  contextWindow: 163840,
7332
- maxTokens: 65536,
7402
+ maxTokens: 4096,
7333
7403
  },
7334
7404
  "deepseek/deepseek-v3.1-terminus": {
7335
7405
  id: "deepseek/deepseek-v3.1-terminus",
@@ -7612,72 +7682,72 @@ export const MODELS = {
7612
7682
  reasoning: true,
7613
7683
  input: ["text", "image"],
7614
7684
  cost: {
7615
- input: 0.13,
7616
- output: 0.39999999999999997,
7617
- cacheRead: 0,
7685
+ input: 0.08,
7686
+ output: 0.35,
7687
+ cacheRead: 0.01,
7618
7688
  cacheWrite: 0,
7619
7689
  },
7620
7690
  contextWindow: 262144,
7621
- maxTokens: 262144,
7691
+ maxTokens: 4096,
7622
7692
  },
7623
- "google/gemma-4-31b-it": {
7624
- id: "google/gemma-4-31b-it",
7625
- name: "Google: Gemma 4 31B",
7693
+ "google/gemma-4-26b-a4b-it:free": {
7694
+ id: "google/gemma-4-26b-a4b-it:free",
7695
+ name: "Google: Gemma 4 26B A4B (free)",
7626
7696
  api: "openai-completions",
7627
7697
  provider: "openrouter",
7628
7698
  baseUrl: "https://openrouter.ai/api/v1",
7629
7699
  reasoning: true,
7630
7700
  input: ["text", "image"],
7631
7701
  cost: {
7632
- input: 0.14,
7633
- output: 0.39999999999999997,
7702
+ input: 0,
7703
+ output: 0,
7634
7704
  cacheRead: 0,
7635
7705
  cacheWrite: 0,
7636
7706
  },
7637
7707
  contextWindow: 262144,
7638
- maxTokens: 131072,
7708
+ maxTokens: 32768,
7639
7709
  },
7640
- "inception/mercury": {
7641
- id: "inception/mercury",
7642
- name: "Inception: Mercury",
7710
+ "google/gemma-4-31b-it": {
7711
+ id: "google/gemma-4-31b-it",
7712
+ name: "Google: Gemma 4 31B",
7643
7713
  api: "openai-completions",
7644
7714
  provider: "openrouter",
7645
7715
  baseUrl: "https://openrouter.ai/api/v1",
7646
- reasoning: false,
7647
- input: ["text"],
7716
+ reasoning: true,
7717
+ input: ["text", "image"],
7648
7718
  cost: {
7649
- input: 0.25,
7650
- output: 0.75,
7651
- cacheRead: 0.024999999999999998,
7719
+ input: 0.13,
7720
+ output: 0.38,
7721
+ cacheRead: 0.019999999499999997,
7652
7722
  cacheWrite: 0,
7653
7723
  },
7654
- contextWindow: 128000,
7655
- maxTokens: 32000,
7724
+ contextWindow: 262144,
7725
+ maxTokens: 4096,
7656
7726
  },
7657
- "inception/mercury-2": {
7658
- id: "inception/mercury-2",
7659
- name: "Inception: Mercury 2",
7727
+ "google/gemma-4-31b-it:free": {
7728
+ id: "google/gemma-4-31b-it:free",
7729
+ name: "Google: Gemma 4 31B (free)",
7660
7730
  api: "openai-completions",
7661
7731
  provider: "openrouter",
7662
7732
  baseUrl: "https://openrouter.ai/api/v1",
7663
7733
  reasoning: true,
7664
- input: ["text"],
7734
+ input: ["text", "image"],
7665
7735
  cost: {
7666
- input: 0.25,
7667
- output: 0.75,
7668
- cacheRead: 0.024999999999999998,
7736
+ input: 0,
7737
+ output: 0,
7738
+ cacheRead: 0,
7669
7739
  cacheWrite: 0,
7670
7740
  },
7671
- contextWindow: 128000,
7672
- maxTokens: 50000,
7741
+ contextWindow: 262144,
7742
+ maxTokens: 32768,
7673
7743
  },
7674
- "inception/mercury-coder": {
7675
- id: "inception/mercury-coder",
7676
- name: "Inception: Mercury Coder",
7744
+ "inception/mercury-2": {
7745
+ id: "inception/mercury-2",
7746
+ name: "Inception: Mercury 2",
7677
7747
  api: "openai-completions",
7678
7748
  provider: "openrouter",
7679
7749
  baseUrl: "https://openrouter.ai/api/v1",
7680
- reasoning: false,
7750
+ reasoning: true,
7681
7751
  input: ["text"],
7682
7752
  cost: {
7683
7753
  input: 0.25,
@@ -7686,7 +7756,7 @@ export const MODELS = {
7686
7756
  cacheWrite: 0,
7687
7757
  },
7688
7758
  contextWindow: 128000,
7689
- maxTokens: 32000,
7759
+ maxTokens: 50000,
7690
7760
  },
7691
7761
  "kwaipilot/kat-coder-pro-v2": {
7692
7762
  id: "kwaipilot/kat-coder-pro-v2",
@@ -7705,23 +7775,6 @@ export const MODELS = {
7705
7775
  contextWindow: 256000,
7706
7776
  maxTokens: 80000,
7707
7777
  },
7708
- "meituan/longcat-flash-chat": {
7709
- id: "meituan/longcat-flash-chat",
7710
- name: "Meituan: LongCat Flash Chat",
7711
- api: "openai-completions",
7712
- provider: "openrouter",
7713
- baseUrl: "https://openrouter.ai/api/v1",
7714
- reasoning: false,
7715
- input: ["text"],
7716
- cost: {
7717
- input: 0.19999999999999998,
7718
- output: 0.7999999999999999,
7719
- cacheRead: 0.19999999999999998,
7720
- cacheWrite: 0,
7721
- },
7722
- contextWindow: 131072,
7723
- maxTokens: 131072,
7724
- },
7725
7778
  "meta-llama/llama-3-8b-instruct": {
7726
7779
  id: "meta-llama/llama-3-8b-instruct",
7727
7780
  name: "Meta: Llama 3 8B Instruct",
@@ -7884,13 +7937,13 @@ export const MODELS = {
7884
7937
  reasoning: true,
7885
7938
  input: ["text"],
7886
7939
  cost: {
7887
- input: 0.27,
7940
+ input: 0.29,
7888
7941
  output: 0.95,
7889
- cacheRead: 0.0290000007,
7942
+ cacheRead: 0.03,
7890
7943
  cacheWrite: 0,
7891
7944
  },
7892
7945
  contextWindow: 196608,
7893
- maxTokens: 4096,
7946
+ maxTokens: 196608,
7894
7947
  },
7895
7948
  "minimax/minimax-m2.5": {
7896
7949
  id: "minimax/minimax-m2.5",
@@ -7924,7 +7977,7 @@ export const MODELS = {
7924
7977
  cacheWrite: 0,
7925
7978
  },
7926
7979
  contextWindow: 196608,
7927
- maxTokens: 196608,
7980
+ maxTokens: 8192,
7928
7981
  },
7929
7982
  "minimax/minimax-m2.7": {
7930
7983
  id: "minimax/minimax-m2.7",
@@ -7937,11 +7990,11 @@ export const MODELS = {
7937
7990
  cost: {
7938
7991
  input: 0.3,
7939
7992
  output: 1.2,
7940
- cacheRead: 0.06,
7993
+ cacheRead: 0.059,
7941
7994
  cacheWrite: 0,
7942
7995
  },
7943
- contextWindow: 204800,
7944
- maxTokens: 131072,
7996
+ contextWindow: 196608,
7997
+ maxTokens: 4096,
7945
7998
  },
7946
7999
  "mistralai/codestral-2508": {
7947
8000
  id: "mistralai/codestral-2508",
@@ -8345,11 +8398,11 @@ export const MODELS = {
8345
8398
  cost: {
8346
8399
  input: 0.39999999999999997,
8347
8400
  output: 2,
8348
- cacheRead: 0.15,
8401
+ cacheRead: 0,
8349
8402
  cacheWrite: 0,
8350
8403
  },
8351
- contextWindow: 131072,
8352
- maxTokens: 4096,
8404
+ contextWindow: 262144,
8405
+ maxTokens: 262144,
8353
8406
  },
8354
8407
  "moonshotai/kimi-k2-thinking": {
8355
8408
  id: "moonshotai/kimi-k2-thinking",
@@ -8360,13 +8413,13 @@ export const MODELS = {
8360
8413
  reasoning: true,
8361
8414
  input: ["text"],
8362
8415
  cost: {
8363
- input: 0.47,
8364
- output: 2,
8365
- cacheRead: 0.14100000000000001,
8416
+ input: 0.6,
8417
+ output: 2.5,
8418
+ cacheRead: 0.15,
8366
8419
  cacheWrite: 0,
8367
8420
  },
8368
- contextWindow: 131072,
8369
- maxTokens: 4096,
8421
+ contextWindow: 262144,
8422
+ maxTokens: 262144,
8370
8423
  },
8371
8424
  "moonshotai/kimi-k2.5": {
8372
8425
  id: "moonshotai/kimi-k2.5",
@@ -8706,7 +8759,7 @@ export const MODELS = {
8706
8759
  cacheWrite: 0,
8707
8760
  },
8708
8761
  contextWindow: 1047576,
8709
- maxTokens: 32768,
8762
+ maxTokens: 4096,
8710
8763
  },
8711
8764
  "openai/gpt-4.1-mini": {
8712
8765
  id: "openai/gpt-4.1-mini",
@@ -8753,7 +8806,7 @@ export const MODELS = {
8753
8806
  cost: {
8754
8807
  input: 2.5,
8755
8808
  output: 10,
8756
- cacheRead: 1.25,
8809
+ cacheRead: 0,
8757
8810
  cacheWrite: 0,
8758
8811
  },
8759
8812
  contextWindow: 128000,
@@ -8974,11 +9027,11 @@ export const MODELS = {
8974
9027
  cost: {
8975
9028
  input: 0.049999999999999996,
8976
9029
  output: 0.39999999999999997,
8977
- cacheRead: 0.005,
9030
+ cacheRead: 0.01,
8978
9031
  cacheWrite: 0,
8979
9032
  },
8980
9033
  contextWindow: 400000,
8981
- maxTokens: 128000,
9034
+ maxTokens: 4096,
8982
9035
  },
8983
9036
  "openai/gpt-5-pro": {
8984
9037
  id: "openai/gpt-5-pro",
@@ -9008,7 +9061,7 @@ export const MODELS = {
9008
9061
  cost: {
9009
9062
  input: 1.25,
9010
9063
  output: 10,
9011
- cacheRead: 0.125,
9064
+ cacheRead: 0.13,
9012
9065
  cacheWrite: 0,
9013
9066
  },
9014
9067
  contextWindow: 400000,
@@ -9076,11 +9129,11 @@ export const MODELS = {
9076
9129
  cost: {
9077
9130
  input: 0.25,
9078
9131
  output: 2,
9079
- cacheRead: 0.024999999999999998,
9132
+ cacheRead: 0.03,
9080
9133
  cacheWrite: 0,
9081
9134
  },
9082
9135
  contextWindow: 400000,
9083
- maxTokens: 100000,
9136
+ maxTokens: 128000,
9084
9137
  },
9085
9138
  "openai/gpt-5.2": {
9086
9139
  id: "openai/gpt-5.2",
@@ -9114,7 +9167,7 @@ export const MODELS = {
9114
9167
  cacheWrite: 0,
9115
9168
  },
9116
9169
  contextWindow: 128000,
9117
- maxTokens: 16384,
9170
+ maxTokens: 32000,
9118
9171
  },
9119
9172
  "openai/gpt-5.2-codex": {
9120
9173
  id: "openai/gpt-5.2-codex",
@@ -9330,12 +9383,12 @@ export const MODELS = {
9330
9383
  input: ["text"],
9331
9384
  cost: {
9332
9385
  input: 0.03,
9333
- output: 0.11,
9334
- cacheRead: 0.015,
9386
+ output: 0.14,
9387
+ cacheRead: 0,
9335
9388
  cacheWrite: 0,
9336
9389
  },
9337
9390
  contextWindow: 131072,
9338
- maxTokens: 131072,
9391
+ maxTokens: 4096,
9339
9392
  },
9340
9393
  "openai/gpt-oss-20b:free": {
9341
9394
  id: "openai/gpt-oss-20b:free",
@@ -9352,7 +9405,7 @@ export const MODELS = {
9352
9405
  cacheWrite: 0,
9353
9406
  },
9354
9407
  contextWindow: 131072,
9355
- maxTokens: 131072,
9408
+ maxTokens: 8192,
9356
9409
  },
9357
9410
  "openai/gpt-oss-safeguard-20b": {
9358
9411
  id: "openai/gpt-oss-safeguard-20b",
@@ -9541,6 +9594,23 @@ export const MODELS = {
9541
9594
  contextWindow: 2000000,
9542
9595
  maxTokens: 4096,
9543
9596
  },
9597
+ "openrouter/elephant-alpha": {
9598
+ id: "openrouter/elephant-alpha",
9599
+ name: "Elephant",
9600
+ api: "openai-completions",
9601
+ provider: "openrouter",
9602
+ baseUrl: "https://openrouter.ai/api/v1",
9603
+ reasoning: false,
9604
+ input: ["text"],
9605
+ cost: {
9606
+ input: 0,
9607
+ output: 0,
9608
+ cacheRead: 0,
9609
+ cacheWrite: 0,
9610
+ },
9611
+ contextWindow: 262144,
9612
+ maxTokens: 32768,
9613
+ },
9544
9614
  "openrouter/free": {
9545
9615
  id: "openrouter/free",
9546
9616
  name: "Free Models Router",
@@ -9924,13 +9994,13 @@ export const MODELS = {
9924
9994
  reasoning: false,
9925
9995
  input: ["text"],
9926
9996
  cost: {
9927
- input: 0.12,
9928
- output: 0.75,
9929
- cacheRead: 0.06,
9997
+ input: 0.15,
9998
+ output: 0.7999999999999999,
9999
+ cacheRead: 0.12,
9930
10000
  cacheWrite: 0,
9931
10001
  },
9932
10002
  contextWindow: 262144,
9933
- maxTokens: 65536,
10003
+ maxTokens: 262144,
9934
10004
  },
9935
10005
  "qwen/qwen3-coder-plus": {
9936
10006
  id: "qwen/qwen3-coder-plus",
@@ -10289,17 +10359,17 @@ export const MODELS = {
10289
10359
  contextWindow: 1000000,
10290
10360
  maxTokens: 65536,
10291
10361
  },
10292
- "qwen/qwen3.6-plus:free": {
10293
- id: "qwen/qwen3.6-plus:free",
10294
- name: "Qwen: Qwen3.6 Plus (free)",
10362
+ "qwen/qwen3.6-plus": {
10363
+ id: "qwen/qwen3.6-plus",
10364
+ name: "Qwen: Qwen3.6 Plus",
10295
10365
  api: "openai-completions",
10296
10366
  provider: "openrouter",
10297
10367
  baseUrl: "https://openrouter.ai/api/v1",
10298
10368
  reasoning: true,
10299
10369
  input: ["text", "image"],
10300
10370
  cost: {
10301
- input: 0,
10302
- output: 0,
10371
+ input: 0.325,
10372
+ output: 1.95,
10303
10373
  cacheRead: 0,
10304
10374
  cacheWrite: 0,
10305
10375
  },
@@ -10408,23 +10478,6 @@ export const MODELS = {
10408
10478
  contextWindow: 262144,
10409
10479
  maxTokens: 65536,
10410
10480
  },
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
10481
  "thedrummer/rocinante-12b": {
10429
10482
  id: "thedrummer/rocinante-12b",
10430
10483
  name: "TheDrummer: Rocinante 12B",
@@ -10884,6 +10937,23 @@ export const MODELS = {
10884
10937
  contextWindow: 202752,
10885
10938
  maxTokens: 131072,
10886
10939
  },
10940
+ "z-ai/glm-5.1": {
10941
+ id: "z-ai/glm-5.1",
10942
+ name: "Z.ai: GLM 5.1",
10943
+ api: "openai-completions",
10944
+ provider: "openrouter",
10945
+ baseUrl: "https://openrouter.ai/api/v1",
10946
+ reasoning: true,
10947
+ input: ["text"],
10948
+ cost: {
10949
+ input: 0.95,
10950
+ output: 3.15,
10951
+ cacheRead: 0.475,
10952
+ cacheWrite: 0,
10953
+ },
10954
+ contextWindow: 202752,
10955
+ maxTokens: 65535,
10956
+ },
10887
10957
  "z-ai/glm-5v-turbo": {
10888
10958
  id: "z-ai/glm-5v-turbo",
10889
10959
  name: "Z.ai: GLM 5V Turbo",
@@ -10929,13 +10999,13 @@ export const MODELS = {
10929
10999
  reasoning: false,
10930
11000
  input: ["text"],
10931
11001
  cost: {
10932
- input: 0.22,
10933
- output: 0.88,
10934
- cacheRead: 0.11,
11002
+ input: 0.6,
11003
+ output: 1.2,
11004
+ cacheRead: 0.6,
10935
11005
  cacheWrite: 0,
10936
11006
  },
10937
- contextWindow: 32768,
10938
- maxTokens: 16384,
11007
+ contextWindow: 131000,
11008
+ maxTokens: 40000,
10939
11009
  },
10940
11010
  "alibaba/qwen-3-30b": {
10941
11011
  id: "alibaba/qwen-3-30b",
@@ -11170,7 +11240,7 @@ export const MODELS = {
11170
11240
  input: 0.5,
11171
11241
  output: 3,
11172
11242
  cacheRead: 0.09999999999999999,
11173
- cacheWrite: 0.625,
11243
+ cacheWrite: 0,
11174
11244
  },
11175
11245
  contextWindow: 1000000,
11176
11246
  maxTokens: 64000,
@@ -11662,7 +11732,7 @@ export const MODELS = {
11662
11732
  cost: {
11663
11733
  input: 0.25,
11664
11734
  output: 1.5,
11665
- cacheRead: 0,
11735
+ cacheRead: 0.03,
11666
11736
  cacheWrite: 0,
11667
11737
  },
11668
11738
  contextWindow: 1000000,
@@ -11785,7 +11855,7 @@ export const MODELS = {
11785
11855
  cacheWrite: 0,
11786
11856
  },
11787
11857
  contextWindow: 128000,
11788
- maxTokens: 8192,
11858
+ maxTokens: 100000,
11789
11859
  },
11790
11860
  "meta/llama-3.1-70b": {
11791
11861
  id: "meta/llama-3.1-70b",
@@ -12790,23 +12860,6 @@ export const MODELS = {
12790
12860
  contextWindow: 1050000,
12791
12861
  maxTokens: 128000,
12792
12862
  },
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
12863
  "openai/gpt-oss-20b": {
12811
12864
  id: "openai/gpt-oss-20b",
12812
12865
  name: "gpt-oss-20b",
@@ -12994,23 +13047,6 @@ export const MODELS = {
12994
13047
  contextWindow: 131072,
12995
13048
  maxTokens: 131072,
12996
13049
  },
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
13050
  "xai/grok-3": {
13015
13051
  id: "xai/grok-3",
13016
13052
  name: "Grok 3 Beta",
@@ -13428,13 +13464,13 @@ export const MODELS = {
13428
13464
  reasoning: true,
13429
13465
  input: ["text"],
13430
13466
  cost: {
13431
- input: 0.6,
13432
- output: 2.2,
13433
- cacheRead: 0.11,
13467
+ input: 2.25,
13468
+ output: 2.75,
13469
+ cacheRead: 2.25,
13434
13470
  cacheWrite: 0,
13435
13471
  },
13436
- contextWindow: 200000,
13437
- maxTokens: 120000,
13472
+ contextWindow: 131000,
13473
+ maxTokens: 40000,
13438
13474
  },
13439
13475
  "zai/glm-4.7-flash": {
13440
13476
  id: "zai/glm-4.7-flash",
@@ -13504,6 +13540,23 @@ export const MODELS = {
13504
13540
  contextWindow: 202800,
13505
13541
  maxTokens: 131100,
13506
13542
  },
13543
+ "zai/glm-5.1": {
13544
+ id: "zai/glm-5.1",
13545
+ name: "GLM 5.1",
13546
+ api: "anthropic-messages",
13547
+ provider: "vercel-ai-gateway",
13548
+ baseUrl: "https://ai-gateway.vercel.sh",
13549
+ reasoning: true,
13550
+ input: ["text"],
13551
+ cost: {
13552
+ input: 1.4,
13553
+ output: 4.4,
13554
+ cacheRead: 0.26,
13555
+ cacheWrite: 0,
13556
+ },
13557
+ contextWindow: 202800,
13558
+ maxTokens: 64000,
13559
+ },
13507
13560
  "zai/glm-5v-turbo": {
13508
13561
  id: "zai/glm-5v-turbo",
13509
13562
  name: "GLM 5V Turbo",