@avadisabelle/ava-pi-ai 0.65.0 → 0.65.2

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.
@@ -325,6 +325,40 @@ export const MODELS = {
325
325
  contextWindow: 1000000,
326
326
  maxTokens: 64000,
327
327
  },
328
+ "au.anthropic.claude-opus-4-6-v1": {
329
+ id: "au.anthropic.claude-opus-4-6-v1",
330
+ name: "AU Anthropic Claude Opus 4.6",
331
+ api: "bedrock-converse-stream",
332
+ provider: "amazon-bedrock",
333
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
334
+ reasoning: true,
335
+ input: ["text", "image"],
336
+ cost: {
337
+ input: 16.5,
338
+ output: 82.5,
339
+ cacheRead: 0.5,
340
+ cacheWrite: 6.25,
341
+ },
342
+ contextWindow: 1000000,
343
+ maxTokens: 128000,
344
+ },
345
+ "au.anthropic.claude-sonnet-4-6": {
346
+ id: "au.anthropic.claude-sonnet-4-6",
347
+ name: "AU Anthropic Claude Sonnet 4.6",
348
+ api: "bedrock-converse-stream",
349
+ provider: "amazon-bedrock",
350
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
351
+ reasoning: true,
352
+ input: ["text", "image"],
353
+ cost: {
354
+ input: 3.3,
355
+ output: 16.5,
356
+ cacheRead: 0.33,
357
+ cacheWrite: 4.125,
358
+ },
359
+ contextWindow: 1000000,
360
+ maxTokens: 128000,
361
+ },
328
362
  "deepseek.r1-v1:0": {
329
363
  id: "deepseek.r1-v1:0",
330
364
  name: "DeepSeek-R1",
@@ -2488,6 +2522,23 @@ export const MODELS = {
2488
2522
  contextWindow: 1050000,
2489
2523
  maxTokens: 128000,
2490
2524
  },
2525
+ "gpt-5.5": {
2526
+ id: "gpt-5.5",
2527
+ name: "GPT-5.5",
2528
+ api: "azure-openai-responses",
2529
+ provider: "azure-openai-responses",
2530
+ baseUrl: "",
2531
+ reasoning: true,
2532
+ input: ["text", "image"],
2533
+ cost: {
2534
+ input: 5,
2535
+ output: 30,
2536
+ cacheRead: 0.5,
2537
+ cacheWrite: 0,
2538
+ },
2539
+ contextWindow: 1050000,
2540
+ maxTokens: 128000,
2541
+ },
2491
2542
  "o1": {
2492
2543
  id: "o1",
2493
2544
  name: "o1",
@@ -3134,6 +3185,24 @@ export const MODELS = {
3134
3185
  contextWindow: 400000,
3135
3186
  maxTokens: 128000,
3136
3187
  },
3188
+ "gpt-5.5": {
3189
+ id: "gpt-5.5",
3190
+ name: "GPT-5.5",
3191
+ api: "openai-responses",
3192
+ provider: "github-copilot",
3193
+ baseUrl: "https://api.individual.githubcopilot.com",
3194
+ 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" },
3195
+ reasoning: true,
3196
+ input: ["text", "image"],
3197
+ cost: {
3198
+ input: 0,
3199
+ output: 0,
3200
+ cacheRead: 0,
3201
+ cacheWrite: 0,
3202
+ },
3203
+ contextWindow: 400000,
3204
+ maxTokens: 128000,
3205
+ },
3137
3206
  "grok-code-fast-1": {
3138
3207
  id: "grok-code-fast-1",
3139
3208
  name: "Grok Code Fast 1",
@@ -3251,7 +3320,7 @@ export const MODELS = {
3251
3320
  cost: {
3252
3321
  input: 0.3,
3253
3322
  output: 2.5,
3254
- cacheRead: 0.075,
3323
+ cacheRead: 0.03,
3255
3324
  cacheWrite: 0,
3256
3325
  },
3257
3326
  contextWindow: 1048576,
@@ -3370,7 +3439,7 @@ export const MODELS = {
3370
3439
  cost: {
3371
3440
  input: 1.25,
3372
3441
  output: 10,
3373
- cacheRead: 0.31,
3442
+ cacheRead: 0.125,
3374
3443
  cacheWrite: 0,
3375
3444
  },
3376
3445
  contextWindow: 1048576,
@@ -3580,8 +3649,8 @@ export const MODELS = {
3580
3649
  contextWindow: 131072,
3581
3650
  maxTokens: 8192,
3582
3651
  },
3583
- "gemma-4-26b-it": {
3584
- id: "gemma-4-26b-it",
3652
+ "gemma-4-26b-a4b-it": {
3653
+ id: "gemma-4-26b-a4b-it",
3585
3654
  name: "Gemma 4 26B",
3586
3655
  api: "google-generative-ai",
3587
3656
  provider: "google",
@@ -4622,6 +4691,24 @@ export const MODELS = {
4622
4691
  contextWindow: 163840,
4623
4692
  maxTokens: 65536,
4624
4693
  },
4694
+ "deepseek-ai/DeepSeek-V4-Pro": {
4695
+ id: "deepseek-ai/DeepSeek-V4-Pro",
4696
+ name: "DeepSeek V4 Pro",
4697
+ api: "openai-completions",
4698
+ provider: "huggingface",
4699
+ baseUrl: "https://router.huggingface.co/v1",
4700
+ compat: { "supportsDeveloperRole": false },
4701
+ reasoning: true,
4702
+ input: ["text"],
4703
+ cost: {
4704
+ input: 1.74,
4705
+ output: 3.48,
4706
+ cacheRead: 0.145,
4707
+ cacheWrite: 0,
4708
+ },
4709
+ contextWindow: 1048576,
4710
+ maxTokens: 393216,
4711
+ },
4625
4712
  "moonshotai/Kimi-K2-Instruct": {
4626
4713
  id: "moonshotai/Kimi-K2-Instruct",
4627
4714
  name: "Kimi-K2-Instruct",
@@ -4694,6 +4781,24 @@ export const MODELS = {
4694
4781
  contextWindow: 262144,
4695
4782
  maxTokens: 262144,
4696
4783
  },
4784
+ "moonshotai/Kimi-K2.6": {
4785
+ id: "moonshotai/Kimi-K2.6",
4786
+ name: "Kimi-K2.6",
4787
+ api: "openai-completions",
4788
+ provider: "huggingface",
4789
+ baseUrl: "https://router.huggingface.co/v1",
4790
+ compat: { "supportsDeveloperRole": false },
4791
+ reasoning: true,
4792
+ input: ["text", "image"],
4793
+ cost: {
4794
+ input: 0.95,
4795
+ output: 4,
4796
+ cacheRead: 0.16,
4797
+ cacheWrite: 0,
4798
+ },
4799
+ contextWindow: 262144,
4800
+ maxTokens: 262144,
4801
+ },
4697
4802
  "zai-org/GLM-4.7": {
4698
4803
  id: "zai-org/GLM-4.7",
4699
4804
  name: "GLM-4.7",
@@ -4768,6 +4873,23 @@ export const MODELS = {
4768
4873
  },
4769
4874
  },
4770
4875
  "kimi-coding": {
4876
+ "k2p6": {
4877
+ id: "k2p6",
4878
+ name: "Kimi K2.6",
4879
+ api: "anthropic-messages",
4880
+ provider: "kimi-coding",
4881
+ baseUrl: "https://api.kimi.com/coding",
4882
+ reasoning: true,
4883
+ input: ["text", "image"],
4884
+ cost: {
4885
+ input: 0,
4886
+ output: 0,
4887
+ cacheRead: 0,
4888
+ cacheWrite: 0,
4889
+ },
4890
+ contextWindow: 262144,
4891
+ maxTokens: 32768,
4892
+ },
4771
4893
  "kimi-for-coding": {
4772
4894
  id: "kimi-for-coding",
4773
4895
  name: "Kimi For Coding",
@@ -5864,6 +5986,23 @@ export const MODELS = {
5864
5986
  contextWindow: 1050000,
5865
5987
  maxTokens: 128000,
5866
5988
  },
5989
+ "gpt-5.5": {
5990
+ id: "gpt-5.5",
5991
+ name: "GPT-5.5",
5992
+ api: "openai-responses",
5993
+ provider: "openai",
5994
+ baseUrl: "https://api.openai.com/v1",
5995
+ reasoning: true,
5996
+ input: ["text", "image"],
5997
+ cost: {
5998
+ input: 5,
5999
+ output: 30,
6000
+ cacheRead: 0.5,
6001
+ cacheWrite: 0,
6002
+ },
6003
+ contextWindow: 1050000,
6004
+ maxTokens: 128000,
6005
+ },
5867
6006
  "o1": {
5868
6007
  id: "o1",
5869
6008
  name: "o1",
@@ -6174,23 +6313,6 @@ export const MODELS = {
6174
6313
  contextWindow: 200000,
6175
6314
  maxTokens: 128000,
6176
6315
  },
6177
- "claude-3-5-haiku": {
6178
- id: "claude-3-5-haiku",
6179
- name: "Claude Haiku 3.5",
6180
- api: "anthropic-messages",
6181
- provider: "opencode",
6182
- baseUrl: "https://opencode.ai/zen",
6183
- reasoning: false,
6184
- input: ["text", "image"],
6185
- cost: {
6186
- input: 0.8,
6187
- output: 4,
6188
- cacheRead: 0.08,
6189
- cacheWrite: 1,
6190
- },
6191
- contextWindow: 200000,
6192
- maxTokens: 8192,
6193
- },
6194
6316
  "claude-haiku-4-5": {
6195
6317
  id: "claude-haiku-4-5",
6196
6318
  name: "Claude Haiku 4.5",
@@ -6633,6 +6755,57 @@ export const MODELS = {
6633
6755
  contextWindow: 1050000,
6634
6756
  maxTokens: 128000,
6635
6757
  },
6758
+ "gpt-5.5": {
6759
+ id: "gpt-5.5",
6760
+ name: "GPT-5.5",
6761
+ api: "openai-responses",
6762
+ provider: "opencode",
6763
+ baseUrl: "https://opencode.ai/zen/v1",
6764
+ reasoning: true,
6765
+ input: ["text", "image"],
6766
+ cost: {
6767
+ input: 5,
6768
+ output: 30,
6769
+ cacheRead: 0.5,
6770
+ cacheWrite: 0,
6771
+ },
6772
+ contextWindow: 1050000,
6773
+ maxTokens: 128000,
6774
+ },
6775
+ "gpt-5.5-pro": {
6776
+ id: "gpt-5.5-pro",
6777
+ name: "GPT-5.5 Pro",
6778
+ api: "openai-responses",
6779
+ provider: "opencode",
6780
+ baseUrl: "https://opencode.ai/zen/v1",
6781
+ reasoning: true,
6782
+ input: ["text", "image"],
6783
+ cost: {
6784
+ input: 30,
6785
+ output: 180,
6786
+ cacheRead: 30,
6787
+ cacheWrite: 0,
6788
+ },
6789
+ contextWindow: 1050000,
6790
+ maxTokens: 128000,
6791
+ },
6792
+ "hy3-preview-free": {
6793
+ id: "hy3-preview-free",
6794
+ name: "Hy3 preview Free",
6795
+ api: "openai-completions",
6796
+ provider: "opencode",
6797
+ baseUrl: "https://opencode.ai/zen/v1",
6798
+ reasoning: true,
6799
+ input: ["text"],
6800
+ cost: {
6801
+ input: 0,
6802
+ output: 0,
6803
+ cacheRead: 0,
6804
+ cacheWrite: 0,
6805
+ },
6806
+ contextWindow: 256000,
6807
+ maxTokens: 64000,
6808
+ },
6636
6809
  "kimi-k2.5": {
6637
6810
  id: "kimi-k2.5",
6638
6811
  name: "Kimi K2.5",
@@ -6650,6 +6823,40 @@ export const MODELS = {
6650
6823
  contextWindow: 262144,
6651
6824
  maxTokens: 65536,
6652
6825
  },
6826
+ "kimi-k2.6": {
6827
+ id: "kimi-k2.6",
6828
+ name: "Kimi K2.6",
6829
+ api: "openai-completions",
6830
+ provider: "opencode",
6831
+ baseUrl: "https://opencode.ai/zen/v1",
6832
+ reasoning: true,
6833
+ input: ["text", "image"],
6834
+ cost: {
6835
+ input: 0.95,
6836
+ output: 4,
6837
+ cacheRead: 0.16,
6838
+ cacheWrite: 0,
6839
+ },
6840
+ contextWindow: 262144,
6841
+ maxTokens: 65536,
6842
+ },
6843
+ "ling-2.6-flash-free": {
6844
+ id: "ling-2.6-flash-free",
6845
+ name: "Ling 2.6 Flash Free",
6846
+ api: "openai-completions",
6847
+ provider: "opencode",
6848
+ baseUrl: "https://opencode.ai/zen/v1",
6849
+ reasoning: false,
6850
+ input: ["text"],
6851
+ cost: {
6852
+ input: 0,
6853
+ output: 0,
6854
+ cacheRead: 0,
6855
+ cacheWrite: 0,
6856
+ },
6857
+ contextWindow: 262100,
6858
+ maxTokens: 32800,
6859
+ },
6653
6860
  "minimax-m2.5": {
6654
6861
  id: "minimax-m2.5",
6655
6862
  name: "MiniMax M2.5",
@@ -6684,6 +6891,23 @@ export const MODELS = {
6684
6891
  contextWindow: 204800,
6685
6892
  maxTokens: 131072,
6686
6893
  },
6894
+ "minimax-m2.7": {
6895
+ id: "minimax-m2.7",
6896
+ name: "MiniMax M2.7",
6897
+ api: "openai-completions",
6898
+ provider: "opencode",
6899
+ baseUrl: "https://opencode.ai/zen/v1",
6900
+ reasoning: true,
6901
+ input: ["text"],
6902
+ cost: {
6903
+ input: 0.3,
6904
+ output: 1.2,
6905
+ cacheRead: 0.06,
6906
+ cacheWrite: 0,
6907
+ },
6908
+ contextWindow: 204800,
6909
+ maxTokens: 131072,
6910
+ },
6687
6911
  "nemotron-3-super-free": {
6688
6912
  id: "nemotron-3-super-free",
6689
6913
  name: "Nemotron 3 Super Free",
@@ -6704,9 +6928,9 @@ export const MODELS = {
6704
6928
  "qwen3.5-plus": {
6705
6929
  id: "qwen3.5-plus",
6706
6930
  name: "Qwen3.5 Plus",
6707
- api: "openai-completions",
6931
+ api: "anthropic-messages",
6708
6932
  provider: "opencode",
6709
- baseUrl: "https://opencode.ai/zen/v1",
6933
+ baseUrl: "https://opencode.ai/zen",
6710
6934
  reasoning: true,
6711
6935
  input: ["text", "image"],
6712
6936
  cost: {
@@ -6721,9 +6945,9 @@ export const MODELS = {
6721
6945
  "qwen3.6-plus": {
6722
6946
  id: "qwen3.6-plus",
6723
6947
  name: "Qwen3.6 Plus",
6724
- api: "openai-completions",
6948
+ api: "anthropic-messages",
6725
6949
  provider: "opencode",
6726
- baseUrl: "https://opencode.ai/zen/v1",
6950
+ baseUrl: "https://opencode.ai/zen",
6727
6951
  reasoning: true,
6728
6952
  input: ["text", "image"],
6729
6953
  cost: {
@@ -6737,6 +6961,40 @@ export const MODELS = {
6737
6961
  },
6738
6962
  },
6739
6963
  "opencode-go": {
6964
+ "deepseek-v4-flash": {
6965
+ id: "deepseek-v4-flash",
6966
+ name: "DeepSeek V4 Flash",
6967
+ api: "openai-completions",
6968
+ provider: "opencode-go",
6969
+ baseUrl: "https://opencode.ai/zen/go/v1",
6970
+ reasoning: true,
6971
+ input: ["text"],
6972
+ cost: {
6973
+ input: 0.14,
6974
+ output: 0.28,
6975
+ cacheRead: 0.0028,
6976
+ cacheWrite: 0,
6977
+ },
6978
+ contextWindow: 1000000,
6979
+ maxTokens: 384000,
6980
+ },
6981
+ "deepseek-v4-pro": {
6982
+ id: "deepseek-v4-pro",
6983
+ name: "DeepSeek V4 Pro",
6984
+ api: "openai-completions",
6985
+ provider: "opencode-go",
6986
+ baseUrl: "https://opencode.ai/zen/go/v1",
6987
+ reasoning: true,
6988
+ input: ["text"],
6989
+ cost: {
6990
+ input: 1.74,
6991
+ output: 3.48,
6992
+ cacheRead: 0.0145,
6993
+ cacheWrite: 0,
6994
+ },
6995
+ contextWindow: 1000000,
6996
+ maxTokens: 384000,
6997
+ },
6740
6998
  "glm-5": {
6741
6999
  id: "glm-5",
6742
7000
  name: "GLM-5",
@@ -6788,6 +7046,23 @@ export const MODELS = {
6788
7046
  contextWindow: 262144,
6789
7047
  maxTokens: 65536,
6790
7048
  },
7049
+ "kimi-k2.6": {
7050
+ id: "kimi-k2.6",
7051
+ name: "Kimi K2.6 (3x limits)",
7052
+ api: "openai-completions",
7053
+ provider: "opencode-go",
7054
+ baseUrl: "https://opencode.ai/zen/go/v1",
7055
+ reasoning: true,
7056
+ input: ["text", "image"],
7057
+ cost: {
7058
+ input: 0.32,
7059
+ output: 1.34,
7060
+ cacheRead: 0.054,
7061
+ cacheWrite: 0,
7062
+ },
7063
+ contextWindow: 262144,
7064
+ maxTokens: 65536,
7065
+ },
6791
7066
  "mimo-v2-omni": {
6792
7067
  id: "mimo-v2-omni",
6793
7068
  name: "MiMo V2 Omni",
@@ -6803,7 +7078,7 @@ export const MODELS = {
6803
7078
  cacheWrite: 0,
6804
7079
  },
6805
7080
  contextWindow: 262144,
6806
- maxTokens: 64000,
7081
+ maxTokens: 128000,
6807
7082
  },
6808
7083
  "mimo-v2-pro": {
6809
7084
  id: "mimo-v2-pro",
@@ -6820,10 +7095,44 @@ export const MODELS = {
6820
7095
  cacheWrite: 0,
6821
7096
  },
6822
7097
  contextWindow: 1048576,
6823
- maxTokens: 64000,
7098
+ maxTokens: 128000,
6824
7099
  },
6825
- "minimax-m2.5": {
6826
- id: "minimax-m2.5",
7100
+ "mimo-v2.5": {
7101
+ id: "mimo-v2.5",
7102
+ name: "MiMo V2.5",
7103
+ api: "openai-completions",
7104
+ provider: "opencode-go",
7105
+ baseUrl: "https://opencode.ai/zen/go/v1",
7106
+ reasoning: true,
7107
+ input: ["text", "image"],
7108
+ cost: {
7109
+ input: 0.4,
7110
+ output: 2,
7111
+ cacheRead: 0.08,
7112
+ cacheWrite: 0,
7113
+ },
7114
+ contextWindow: 1000000,
7115
+ maxTokens: 128000,
7116
+ },
7117
+ "mimo-v2.5-pro": {
7118
+ id: "mimo-v2.5-pro",
7119
+ name: "MiMo V2.5 Pro",
7120
+ api: "openai-completions",
7121
+ provider: "opencode-go",
7122
+ baseUrl: "https://opencode.ai/zen/go/v1",
7123
+ reasoning: true,
7124
+ input: ["text"],
7125
+ cost: {
7126
+ input: 1,
7127
+ output: 3,
7128
+ cacheRead: 0.2,
7129
+ cacheWrite: 0,
7130
+ },
7131
+ contextWindow: 1048576,
7132
+ maxTokens: 128000,
7133
+ },
7134
+ "minimax-m2.5": {
7135
+ id: "minimax-m2.5",
6827
7136
  name: "MiniMax M2.5",
6828
7137
  api: "openai-completions",
6829
7138
  provider: "opencode-go",
@@ -6859,9 +7168,9 @@ export const MODELS = {
6859
7168
  "qwen3.5-plus": {
6860
7169
  id: "qwen3.5-plus",
6861
7170
  name: "Qwen3.5 Plus",
6862
- api: "openai-completions",
7171
+ api: "anthropic-messages",
6863
7172
  provider: "opencode-go",
6864
- baseUrl: "https://opencode.ai/zen/go/v1",
7173
+ baseUrl: "https://opencode.ai/zen/go",
6865
7174
  reasoning: true,
6866
7175
  input: ["text", "image"],
6867
7176
  cost: {
@@ -6876,9 +7185,9 @@ export const MODELS = {
6876
7185
  "qwen3.6-plus": {
6877
7186
  id: "qwen3.6-plus",
6878
7187
  name: "Qwen3.6 Plus",
6879
- api: "openai-completions",
7188
+ api: "anthropic-messages",
6880
7189
  provider: "opencode-go",
6881
- baseUrl: "https://opencode.ai/zen/go/v1",
7190
+ baseUrl: "https://opencode.ai/zen/go",
6882
7191
  reasoning: true,
6883
7192
  input: ["text", "image"],
6884
7193
  cost: {
@@ -6941,7 +7250,7 @@ export const MODELS = {
6941
7250
  cacheWrite: 0,
6942
7251
  },
6943
7252
  contextWindow: 65536,
6944
- maxTokens: 4096,
7253
+ maxTokens: 16384,
6945
7254
  },
6946
7255
  "amazon/nova-2-lite-v1": {
6947
7256
  id: "amazon/nova-2-lite-v1",
@@ -7266,17 +7575,17 @@ export const MODELS = {
7266
7575
  contextWindow: 1000000,
7267
7576
  maxTokens: 128000,
7268
7577
  },
7269
- "arcee-ai/trinity-large-preview:free": {
7270
- id: "arcee-ai/trinity-large-preview:free",
7271
- name: "Arcee AI: Trinity Large Preview (free)",
7578
+ "arcee-ai/trinity-large-preview": {
7579
+ id: "arcee-ai/trinity-large-preview",
7580
+ name: "Arcee AI: Trinity Large Preview",
7272
7581
  api: "openai-completions",
7273
7582
  provider: "openrouter",
7274
7583
  baseUrl: "https://openrouter.ai/api/v1",
7275
7584
  reasoning: false,
7276
7585
  input: ["text"],
7277
7586
  cost: {
7278
- input: 0,
7279
- output: 0,
7587
+ input: 0.15,
7588
+ output: 0.44999999999999996,
7280
7589
  cacheRead: 0,
7281
7590
  cacheWrite: 0,
7282
7591
  },
@@ -7502,7 +7811,7 @@ export const MODELS = {
7502
7811
  cacheWrite: 0,
7503
7812
  },
7504
7813
  contextWindow: 163840,
7505
- maxTokens: 163840,
7814
+ maxTokens: 16384,
7506
7815
  },
7507
7816
  "deepseek/deepseek-chat-v3-0324": {
7508
7817
  id: "deepseek/deepseek-chat-v3-0324",
@@ -7519,7 +7828,7 @@ export const MODELS = {
7519
7828
  cacheWrite: 0,
7520
7829
  },
7521
7830
  contextWindow: 163840,
7522
- maxTokens: 4096,
7831
+ maxTokens: 16384,
7523
7832
  },
7524
7833
  "deepseek/deepseek-chat-v3.1": {
7525
7834
  id: "deepseek/deepseek-chat-v3.1",
@@ -7570,7 +7879,7 @@ export const MODELS = {
7570
7879
  cacheWrite: 0,
7571
7880
  },
7572
7881
  contextWindow: 163840,
7573
- maxTokens: 4096,
7882
+ maxTokens: 32768,
7574
7883
  },
7575
7884
  "deepseek/deepseek-v3.1-terminus": {
7576
7885
  id: "deepseek/deepseek-v3.1-terminus",
@@ -7583,11 +7892,11 @@ export const MODELS = {
7583
7892
  cost: {
7584
7893
  input: 0.21,
7585
7894
  output: 0.7899999999999999,
7586
- cacheRead: 0.1300000002,
7895
+ cacheRead: 0.13,
7587
7896
  cacheWrite: 0,
7588
7897
  },
7589
7898
  contextWindow: 163840,
7590
- maxTokens: 4096,
7899
+ maxTokens: 32768,
7591
7900
  },
7592
7901
  "deepseek/deepseek-v3.2": {
7593
7902
  id: "deepseek/deepseek-v3.2",
@@ -7598,13 +7907,13 @@ export const MODELS = {
7598
7907
  reasoning: true,
7599
7908
  input: ["text"],
7600
7909
  cost: {
7601
- input: 0.25899999999999995,
7602
- output: 0.42,
7603
- cacheRead: 0.135,
7910
+ input: 0.252,
7911
+ output: 0.378,
7912
+ cacheRead: 0.0252,
7604
7913
  cacheWrite: 0,
7605
7914
  },
7606
- contextWindow: 163840,
7607
- maxTokens: 163840,
7915
+ contextWindow: 131072,
7916
+ maxTokens: 65536,
7608
7917
  },
7609
7918
  "deepseek/deepseek-v3.2-exp": {
7610
7919
  id: "deepseek/deepseek-v3.2-exp",
@@ -7623,6 +7932,40 @@ export const MODELS = {
7623
7932
  contextWindow: 163840,
7624
7933
  maxTokens: 65536,
7625
7934
  },
7935
+ "deepseek/deepseek-v4-flash": {
7936
+ id: "deepseek/deepseek-v4-flash",
7937
+ name: "DeepSeek: DeepSeek V4 Flash",
7938
+ api: "openai-completions",
7939
+ provider: "openrouter",
7940
+ baseUrl: "https://openrouter.ai/api/v1",
7941
+ reasoning: true,
7942
+ input: ["text"],
7943
+ cost: {
7944
+ input: 0.14,
7945
+ output: 0.28,
7946
+ cacheRead: 0.0028,
7947
+ cacheWrite: 0,
7948
+ },
7949
+ contextWindow: 1048576,
7950
+ maxTokens: 384000,
7951
+ },
7952
+ "deepseek/deepseek-v4-pro": {
7953
+ id: "deepseek/deepseek-v4-pro",
7954
+ name: "DeepSeek: DeepSeek V4 Pro",
7955
+ api: "openai-completions",
7956
+ provider: "openrouter",
7957
+ baseUrl: "https://openrouter.ai/api/v1",
7958
+ reasoning: true,
7959
+ input: ["text"],
7960
+ cost: {
7961
+ input: 0.435,
7962
+ output: 0.87,
7963
+ cacheRead: 0.003625,
7964
+ cacheWrite: 0,
7965
+ },
7966
+ contextWindow: 1048576,
7967
+ maxTokens: 384000,
7968
+ },
7626
7969
  "essentialai/rnj-1-instruct": {
7627
7970
  id: "essentialai/rnj-1-instruct",
7628
7971
  name: "EssentialAI: Rnj 1 Instruct",
@@ -7654,7 +7997,7 @@ export const MODELS = {
7654
7997
  cacheRead: 0.024999999999999998,
7655
7998
  cacheWrite: 0.08333333333333334,
7656
7999
  },
7657
- contextWindow: 1048576,
8000
+ contextWindow: 1000000,
7658
8001
  maxTokens: 8192,
7659
8002
  },
7660
8003
  "google/gemini-2.0-flash-lite-001": {
@@ -7844,6 +8187,40 @@ export const MODELS = {
7844
8187
  contextWindow: 1048576,
7845
8188
  maxTokens: 65536,
7846
8189
  },
8190
+ "google/gemma-3-12b-it": {
8191
+ id: "google/gemma-3-12b-it",
8192
+ name: "Google: Gemma 3 12B",
8193
+ api: "openai-completions",
8194
+ provider: "openrouter",
8195
+ baseUrl: "https://openrouter.ai/api/v1",
8196
+ reasoning: false,
8197
+ input: ["text", "image"],
8198
+ cost: {
8199
+ input: 0.04,
8200
+ output: 0.13,
8201
+ cacheRead: 0,
8202
+ cacheWrite: 0,
8203
+ },
8204
+ contextWindow: 131072,
8205
+ maxTokens: 16384,
8206
+ },
8207
+ "google/gemma-3-27b-it": {
8208
+ id: "google/gemma-3-27b-it",
8209
+ name: "Google: Gemma 3 27B",
8210
+ api: "openai-completions",
8211
+ provider: "openrouter",
8212
+ baseUrl: "https://openrouter.ai/api/v1",
8213
+ reasoning: false,
8214
+ input: ["text", "image"],
8215
+ cost: {
8216
+ input: 0.08,
8217
+ output: 0.16,
8218
+ cacheRead: 0,
8219
+ cacheWrite: 0,
8220
+ },
8221
+ contextWindow: 131072,
8222
+ maxTokens: 16384,
8223
+ },
7847
8224
  "google/gemma-4-26b-a4b-it": {
7848
8225
  id: "google/gemma-4-26b-a4b-it",
7849
8226
  name: "Google: Gemma 4 26B A4B ",
@@ -7853,9 +8230,9 @@ export const MODELS = {
7853
8230
  reasoning: true,
7854
8231
  input: ["text", "image"],
7855
8232
  cost: {
7856
- input: 0.08,
7857
- output: 0.35,
7858
- cacheRead: 0.01,
8233
+ input: 0.06,
8234
+ output: 0.33,
8235
+ cacheRead: 0,
7859
8236
  cacheWrite: 0,
7860
8237
  },
7861
8238
  contextWindow: 262144,
@@ -7889,11 +8266,11 @@ export const MODELS = {
7889
8266
  cost: {
7890
8267
  input: 0.13,
7891
8268
  output: 0.38,
7892
- cacheRead: 0.019999999499999997,
8269
+ cacheRead: 0,
7893
8270
  cacheWrite: 0,
7894
8271
  },
7895
8272
  contextWindow: 262144,
7896
- maxTokens: 4096,
8273
+ maxTokens: 16384,
7897
8274
  },
7898
8275
  "google/gemma-4-31b-it:free": {
7899
8276
  id: "google/gemma-4-31b-it:free",
@@ -7929,6 +8306,40 @@ export const MODELS = {
7929
8306
  contextWindow: 128000,
7930
8307
  maxTokens: 50000,
7931
8308
  },
8309
+ "inclusionai/ling-2.6-1t:free": {
8310
+ id: "inclusionai/ling-2.6-1t:free",
8311
+ name: "inclusionAI: Ling-2.6-1T (free)",
8312
+ api: "openai-completions",
8313
+ provider: "openrouter",
8314
+ baseUrl: "https://openrouter.ai/api/v1",
8315
+ reasoning: false,
8316
+ input: ["text"],
8317
+ cost: {
8318
+ input: 0,
8319
+ output: 0,
8320
+ cacheRead: 0,
8321
+ cacheWrite: 0,
8322
+ },
8323
+ contextWindow: 262144,
8324
+ maxTokens: 32768,
8325
+ },
8326
+ "inclusionai/ling-2.6-flash:free": {
8327
+ id: "inclusionai/ling-2.6-flash:free",
8328
+ name: "inclusionAI: Ling-2.6-flash (free)",
8329
+ api: "openai-completions",
8330
+ provider: "openrouter",
8331
+ baseUrl: "https://openrouter.ai/api/v1",
8332
+ reasoning: false,
8333
+ input: ["text"],
8334
+ cost: {
8335
+ input: 0,
8336
+ output: 0,
8337
+ cacheRead: 0,
8338
+ cacheWrite: 0,
8339
+ },
8340
+ contextWindow: 262144,
8341
+ maxTokens: 32768,
8342
+ },
7932
8343
  "kwaipilot/kat-coder-pro-v2": {
7933
8344
  id: "kwaipilot/kat-coder-pro-v2",
7934
8345
  name: "Kwaipilot: KAT-Coder-Pro V2",
@@ -7978,7 +8389,7 @@ export const MODELS = {
7978
8389
  cacheWrite: 0,
7979
8390
  },
7980
8391
  contextWindow: 131072,
7981
- maxTokens: 4096,
8392
+ maxTokens: 16384,
7982
8393
  },
7983
8394
  "meta-llama/llama-3.1-8b-instruct": {
7984
8395
  id: "meta-llama/llama-3.1-8b-instruct",
@@ -8006,13 +8417,13 @@ export const MODELS = {
8006
8417
  reasoning: false,
8007
8418
  input: ["text"],
8008
8419
  cost: {
8009
- input: 0.12,
8010
- output: 0.38,
8420
+ input: 0.09999999999999999,
8421
+ output: 0.32,
8011
8422
  cacheRead: 0,
8012
8423
  cacheWrite: 0,
8013
8424
  },
8014
8425
  contextWindow: 131072,
8015
- maxTokens: 131072,
8426
+ maxTokens: 16384,
8016
8427
  },
8017
8428
  "meta-llama/llama-3.3-70b-instruct:free": {
8018
8429
  id: "meta-llama/llama-3.3-70b-instruct:free",
@@ -8108,13 +8519,13 @@ export const MODELS = {
8108
8519
  reasoning: true,
8109
8520
  input: ["text"],
8110
8521
  cost: {
8111
- input: 0.118,
8112
- output: 0.9900000000000001,
8113
- cacheRead: 0.059,
8522
+ input: 0.15,
8523
+ output: 1.15,
8524
+ cacheRead: 0.03,
8114
8525
  cacheWrite: 0,
8115
8526
  },
8116
8527
  contextWindow: 196608,
8117
- maxTokens: 65536,
8528
+ maxTokens: 131072,
8118
8529
  },
8119
8530
  "minimax/minimax-m2.5:free": {
8120
8531
  id: "minimax/minimax-m2.5:free",
@@ -8437,7 +8848,7 @@ export const MODELS = {
8437
8848
  cacheWrite: 0,
8438
8849
  },
8439
8850
  contextWindow: 128000,
8440
- maxTokens: 4096,
8851
+ maxTokens: 16384,
8441
8852
  },
8442
8853
  "mistralai/mistral-small-creative": {
8443
8854
  id: "mistralai/mistral-small-creative",
@@ -8592,6 +9003,23 @@ export const MODELS = {
8592
9003
  contextWindow: 262144,
8593
9004
  maxTokens: 4096,
8594
9005
  },
9006
+ "moonshotai/kimi-k2.6": {
9007
+ id: "moonshotai/kimi-k2.6",
9008
+ name: "MoonshotAI: Kimi K2.6",
9009
+ api: "openai-completions",
9010
+ provider: "openrouter",
9011
+ baseUrl: "https://openrouter.ai/api/v1",
9012
+ reasoning: true,
9013
+ input: ["text", "image"],
9014
+ cost: {
9015
+ input: 0.7448,
9016
+ output: 4.655,
9017
+ cacheRead: 0.1463,
9018
+ cacheWrite: 0,
9019
+ },
9020
+ contextWindow: 256000,
9021
+ maxTokens: 65536,
9022
+ },
8595
9023
  "nex-agi/deepseek-v3.1-nex-n1": {
8596
9024
  id: "nex-agi/deepseek-v3.1-nex-n1",
8597
9025
  name: "Nex AGI: DeepSeek V3.1 Nex N1",
@@ -8641,7 +9069,7 @@ export const MODELS = {
8641
9069
  cacheWrite: 0,
8642
9070
  },
8643
9071
  contextWindow: 131072,
8644
- maxTokens: 4096,
9072
+ maxTokens: 16384,
8645
9073
  },
8646
9074
  "nvidia/nemotron-3-nano-30b-a3b": {
8647
9075
  id: "nvidia/nemotron-3-nano-30b-a3b",
@@ -8658,7 +9086,7 @@ export const MODELS = {
8658
9086
  cacheWrite: 0,
8659
9087
  },
8660
9088
  contextWindow: 262144,
8661
- maxTokens: 4096,
9089
+ maxTokens: 228000,
8662
9090
  },
8663
9091
  "nvidia/nemotron-3-nano-30b-a3b:free": {
8664
9092
  id: "nvidia/nemotron-3-nano-30b-a3b:free",
@@ -8743,7 +9171,7 @@ export const MODELS = {
8743
9171
  cacheWrite: 0,
8744
9172
  },
8745
9173
  contextWindow: 131072,
8746
- maxTokens: 4096,
9174
+ maxTokens: 16384,
8747
9175
  },
8748
9176
  "nvidia/nemotron-nano-9b-v2:free": {
8749
9177
  id: "nvidia/nemotron-nano-9b-v2:free",
@@ -9102,40 +9530,6 @@ export const MODELS = {
9102
9530
  contextWindow: 400000,
9103
9531
  maxTokens: 128000,
9104
9532
  },
9105
- "openai/gpt-5-image": {
9106
- id: "openai/gpt-5-image",
9107
- name: "OpenAI: GPT-5 Image",
9108
- api: "openai-completions",
9109
- provider: "openrouter",
9110
- baseUrl: "https://openrouter.ai/api/v1",
9111
- reasoning: true,
9112
- input: ["text", "image"],
9113
- cost: {
9114
- input: 10,
9115
- output: 10,
9116
- cacheRead: 1.25,
9117
- cacheWrite: 0,
9118
- },
9119
- contextWindow: 400000,
9120
- maxTokens: 128000,
9121
- },
9122
- "openai/gpt-5-image-mini": {
9123
- id: "openai/gpt-5-image-mini",
9124
- name: "OpenAI: GPT-5 Image Mini",
9125
- api: "openai-completions",
9126
- provider: "openrouter",
9127
- baseUrl: "https://openrouter.ai/api/v1",
9128
- reasoning: true,
9129
- input: ["text", "image"],
9130
- cost: {
9131
- input: 2.5,
9132
- output: 2,
9133
- cacheRead: 0.25,
9134
- cacheWrite: 0,
9135
- },
9136
- contextWindow: 400000,
9137
- maxTokens: 128000,
9138
- },
9139
9533
  "openai/gpt-5-mini": {
9140
9534
  id: "openai/gpt-5-mini",
9141
9535
  name: "OpenAI: GPT-5 Mini",
@@ -9442,6 +9836,40 @@ export const MODELS = {
9442
9836
  contextWindow: 1050000,
9443
9837
  maxTokens: 128000,
9444
9838
  },
9839
+ "openai/gpt-5.5": {
9840
+ id: "openai/gpt-5.5",
9841
+ name: "OpenAI: GPT-5.5",
9842
+ api: "openai-completions",
9843
+ provider: "openrouter",
9844
+ baseUrl: "https://openrouter.ai/api/v1",
9845
+ reasoning: true,
9846
+ input: ["text", "image"],
9847
+ cost: {
9848
+ input: 5,
9849
+ output: 30,
9850
+ cacheRead: 0.5,
9851
+ cacheWrite: 0,
9852
+ },
9853
+ contextWindow: 1050000,
9854
+ maxTokens: 128000,
9855
+ },
9856
+ "openai/gpt-5.5-pro": {
9857
+ id: "openai/gpt-5.5-pro",
9858
+ name: "OpenAI: GPT-5.5 Pro",
9859
+ api: "openai-completions",
9860
+ provider: "openrouter",
9861
+ baseUrl: "https://openrouter.ai/api/v1",
9862
+ reasoning: true,
9863
+ input: ["text", "image"],
9864
+ cost: {
9865
+ input: 30,
9866
+ output: 180,
9867
+ cacheRead: 0,
9868
+ cacheWrite: 0,
9869
+ },
9870
+ contextWindow: 1050000,
9871
+ maxTokens: 128000,
9872
+ },
9445
9873
  "openai/gpt-audio": {
9446
9874
  id: "openai/gpt-audio",
9447
9875
  name: "OpenAI: GPT Audio",
@@ -9491,7 +9919,7 @@ export const MODELS = {
9491
9919
  cacheWrite: 0,
9492
9920
  },
9493
9921
  contextWindow: 131072,
9494
- maxTokens: 4096,
9922
+ maxTokens: 131072,
9495
9923
  },
9496
9924
  "openai/gpt-oss-120b:free": {
9497
9925
  id: "openai/gpt-oss-120b:free",
@@ -9525,7 +9953,7 @@ export const MODELS = {
9525
9953
  cacheWrite: 0,
9526
9954
  },
9527
9955
  contextWindow: 131072,
9528
- maxTokens: 4096,
9956
+ maxTokens: 131072,
9529
9957
  },
9530
9958
  "openai/gpt-oss-20b:free": {
9531
9959
  id: "openai/gpt-oss-20b:free",
@@ -9731,23 +10159,6 @@ export const MODELS = {
9731
10159
  contextWindow: 2000000,
9732
10160
  maxTokens: 4096,
9733
10161
  },
9734
- "openrouter/elephant-alpha": {
9735
- id: "openrouter/elephant-alpha",
9736
- name: "Elephant",
9737
- api: "openai-completions",
9738
- provider: "openrouter",
9739
- baseUrl: "https://openrouter.ai/api/v1",
9740
- reasoning: false,
9741
- input: ["text"],
9742
- cost: {
9743
- input: 0,
9744
- output: 0,
9745
- cacheRead: 0,
9746
- cacheWrite: 0,
9747
- },
9748
- contextWindow: 262144,
9749
- maxTokens: 32768,
9750
- },
9751
10162
  "openrouter/free": {
9752
10163
  id: "openrouter/free",
9753
10164
  name: "Free Models Router",
@@ -9791,8 +10202,8 @@ export const MODELS = {
9791
10202
  reasoning: false,
9792
10203
  input: ["text"],
9793
10204
  cost: {
9794
- input: 0.12,
9795
- output: 0.39,
10205
+ input: 0.36,
10206
+ output: 0.39999999999999997,
9796
10207
  cacheRead: 0,
9797
10208
  cacheWrite: 0,
9798
10209
  },
@@ -9967,7 +10378,7 @@ export const MODELS = {
9967
10378
  cacheWrite: 0,
9968
10379
  },
9969
10380
  contextWindow: 262144,
9970
- maxTokens: 4096,
10381
+ maxTokens: 16384,
9971
10382
  },
9972
10383
  "qwen/qwen3-235b-a22b-thinking-2507": {
9973
10384
  id: "qwen/qwen3-235b-a22b-thinking-2507",
@@ -9978,13 +10389,13 @@ export const MODELS = {
9978
10389
  reasoning: true,
9979
10390
  input: ["text"],
9980
10391
  cost: {
9981
- input: 0.13,
9982
- output: 0.6,
10392
+ input: 0.14950000000000002,
10393
+ output: 1.495,
9983
10394
  cacheRead: 0,
9984
10395
  cacheWrite: 0,
9985
10396
  },
9986
- contextWindow: 262144,
9987
- maxTokens: 262144,
10397
+ contextWindow: 131072,
10398
+ maxTokens: 4096,
9988
10399
  },
9989
10400
  "qwen/qwen3-30b-a3b": {
9990
10401
  id: "qwen/qwen3-30b-a3b",
@@ -10001,7 +10412,7 @@ export const MODELS = {
10001
10412
  cacheWrite: 0,
10002
10413
  },
10003
10414
  contextWindow: 40960,
10004
- maxTokens: 40960,
10415
+ maxTokens: 16384,
10005
10416
  },
10006
10417
  "qwen/qwen3-30b-a3b-instruct-2507": {
10007
10418
  id: "qwen/qwen3-30b-a3b-instruct-2507",
@@ -10081,12 +10492,12 @@ export const MODELS = {
10081
10492
  input: ["text"],
10082
10493
  cost: {
10083
10494
  input: 0.22,
10084
- output: 1,
10085
- cacheRead: 0.022,
10495
+ output: 1.7999999999999998,
10496
+ cacheRead: 0,
10086
10497
  cacheWrite: 0,
10087
10498
  },
10088
10499
  contextWindow: 262144,
10089
- maxTokens: 4096,
10500
+ maxTokens: 65536,
10090
10501
  },
10091
10502
  "qwen/qwen3-coder-30b-a3b-instruct": {
10092
10503
  id: "qwen/qwen3-coder-30b-a3b-instruct",
@@ -10131,9 +10542,9 @@ export const MODELS = {
10131
10542
  reasoning: false,
10132
10543
  input: ["text"],
10133
10544
  cost: {
10134
- input: 0.15,
10545
+ input: 0.14,
10135
10546
  output: 0.7999999999999999,
10136
- cacheRead: 0.12,
10547
+ cacheRead: 0.09,
10137
10548
  cacheWrite: 0,
10138
10549
  },
10139
10550
  contextWindow: 262144,
@@ -10222,7 +10633,7 @@ export const MODELS = {
10222
10633
  cacheWrite: 0,
10223
10634
  },
10224
10635
  contextWindow: 262144,
10225
- maxTokens: 4096,
10636
+ maxTokens: 16384,
10226
10637
  },
10227
10638
  "qwen/qwen3-next-80b-a3b-instruct:free": {
10228
10639
  id: "qwen/qwen3-next-80b-a3b-instruct:free",
@@ -10273,7 +10684,7 @@ export const MODELS = {
10273
10684
  cacheWrite: 0,
10274
10685
  },
10275
10686
  contextWindow: 262144,
10276
- maxTokens: 4096,
10687
+ maxTokens: 16384,
10277
10688
  },
10278
10689
  "qwen/qwen3-vl-235b-a22b-thinking": {
10279
10690
  id: "qwen/qwen3-vl-235b-a22b-thinking",
@@ -10496,6 +10907,74 @@ export const MODELS = {
10496
10907
  contextWindow: 1000000,
10497
10908
  maxTokens: 65536,
10498
10909
  },
10910
+ "qwen/qwen3.5-plus-20260420": {
10911
+ id: "qwen/qwen3.5-plus-20260420",
10912
+ name: "Qwen: Qwen3.5 Plus 2026-04-20",
10913
+ api: "openai-completions",
10914
+ provider: "openrouter",
10915
+ baseUrl: "https://openrouter.ai/api/v1",
10916
+ reasoning: true,
10917
+ input: ["text", "image"],
10918
+ cost: {
10919
+ input: 0.39999999999999997,
10920
+ output: 2.4,
10921
+ cacheRead: 0,
10922
+ cacheWrite: 0,
10923
+ },
10924
+ contextWindow: 1000000,
10925
+ maxTokens: 65536,
10926
+ },
10927
+ "qwen/qwen3.6-27b": {
10928
+ id: "qwen/qwen3.6-27b",
10929
+ name: "Qwen: Qwen3.6 27B",
10930
+ api: "openai-completions",
10931
+ provider: "openrouter",
10932
+ baseUrl: "https://openrouter.ai/api/v1",
10933
+ reasoning: true,
10934
+ input: ["text", "image"],
10935
+ cost: {
10936
+ input: 0.5,
10937
+ output: 2,
10938
+ cacheRead: 0.25,
10939
+ cacheWrite: 0,
10940
+ },
10941
+ contextWindow: 262144,
10942
+ maxTokens: 65536,
10943
+ },
10944
+ "qwen/qwen3.6-flash": {
10945
+ id: "qwen/qwen3.6-flash",
10946
+ name: "Qwen: Qwen3.6 Flash",
10947
+ api: "openai-completions",
10948
+ provider: "openrouter",
10949
+ baseUrl: "https://openrouter.ai/api/v1",
10950
+ reasoning: true,
10951
+ input: ["text", "image"],
10952
+ cost: {
10953
+ input: 0.25,
10954
+ output: 1.5,
10955
+ cacheRead: 0,
10956
+ cacheWrite: 0.3125,
10957
+ },
10958
+ contextWindow: 1000000,
10959
+ maxTokens: 65536,
10960
+ },
10961
+ "qwen/qwen3.6-max-preview": {
10962
+ id: "qwen/qwen3.6-max-preview",
10963
+ name: "Qwen: Qwen3.6 Max Preview",
10964
+ api: "openai-completions",
10965
+ provider: "openrouter",
10966
+ baseUrl: "https://openrouter.ai/api/v1",
10967
+ reasoning: true,
10968
+ input: ["text"],
10969
+ cost: {
10970
+ input: 1.3,
10971
+ output: 7.8,
10972
+ cacheRead: 0,
10973
+ cacheWrite: 1.625,
10974
+ },
10975
+ contextWindow: 262144,
10976
+ maxTokens: 65536,
10977
+ },
10499
10978
  "qwen/qwen3.6-plus": {
10500
10979
  id: "qwen/qwen3.6-plus",
10501
10980
  name: "Qwen: Qwen3.6 Plus",
@@ -10615,6 +11094,23 @@ export const MODELS = {
10615
11094
  contextWindow: 262144,
10616
11095
  maxTokens: 65536,
10617
11096
  },
11097
+ "tencent/hy3-preview:free": {
11098
+ id: "tencent/hy3-preview:free",
11099
+ name: "Tencent: Hy3 preview (free)",
11100
+ api: "openai-completions",
11101
+ provider: "openrouter",
11102
+ baseUrl: "https://openrouter.ai/api/v1",
11103
+ reasoning: true,
11104
+ input: ["text"],
11105
+ cost: {
11106
+ input: 0,
11107
+ output: 0,
11108
+ cacheRead: 0,
11109
+ cacheWrite: 0,
11110
+ },
11111
+ contextWindow: 262144,
11112
+ maxTokens: 262144,
11113
+ },
10618
11114
  "thedrummer/rocinante-12b": {
10619
11115
  id: "thedrummer/rocinante-12b",
10620
11116
  name: "TheDrummer: Rocinante 12B",
@@ -10887,6 +11383,40 @@ export const MODELS = {
10887
11383
  contextWindow: 1048576,
10888
11384
  maxTokens: 131072,
10889
11385
  },
11386
+ "xiaomi/mimo-v2.5": {
11387
+ id: "xiaomi/mimo-v2.5",
11388
+ name: "Xiaomi: MiMo-V2.5",
11389
+ api: "openai-completions",
11390
+ provider: "openrouter",
11391
+ baseUrl: "https://openrouter.ai/api/v1",
11392
+ reasoning: true,
11393
+ input: ["text", "image"],
11394
+ cost: {
11395
+ input: 0.39999999999999997,
11396
+ output: 2,
11397
+ cacheRead: 0.08,
11398
+ cacheWrite: 0,
11399
+ },
11400
+ contextWindow: 1048576,
11401
+ maxTokens: 131072,
11402
+ },
11403
+ "xiaomi/mimo-v2.5-pro": {
11404
+ id: "xiaomi/mimo-v2.5-pro",
11405
+ name: "Xiaomi: MiMo-V2.5-Pro",
11406
+ api: "openai-completions",
11407
+ provider: "openrouter",
11408
+ baseUrl: "https://openrouter.ai/api/v1",
11409
+ reasoning: true,
11410
+ input: ["text"],
11411
+ cost: {
11412
+ input: 1,
11413
+ output: 3,
11414
+ cacheRead: 0.19999999999999998,
11415
+ cacheWrite: 0,
11416
+ },
11417
+ contextWindow: 1048576,
11418
+ maxTokens: 131072,
11419
+ },
10890
11420
  "z-ai/glm-4-32b": {
10891
11421
  id: "z-ai/glm-4-32b",
10892
11422
  name: "Z.ai: GLM 4 32B ",
@@ -11000,11 +11530,11 @@ export const MODELS = {
11000
11530
  cost: {
11001
11531
  input: 0.3,
11002
11532
  output: 0.8999999999999999,
11003
- cacheRead: 0,
11533
+ cacheRead: 0.049999999999999996,
11004
11534
  cacheWrite: 0,
11005
11535
  },
11006
11536
  contextWindow: 131072,
11007
- maxTokens: 131072,
11537
+ maxTokens: 24000,
11008
11538
  },
11009
11539
  "z-ai/glm-4.7": {
11010
11540
  id: "z-ai/glm-4.7",
@@ -11015,13 +11545,13 @@ export const MODELS = {
11015
11545
  reasoning: true,
11016
11546
  input: ["text"],
11017
11547
  cost: {
11018
- input: 0.39,
11019
- output: 1.75,
11020
- cacheRead: 0.195,
11548
+ input: 0.38,
11549
+ output: 1.74,
11550
+ cacheRead: 0,
11021
11551
  cacheWrite: 0,
11022
11552
  },
11023
11553
  contextWindow: 202752,
11024
- maxTokens: 65535,
11554
+ maxTokens: 4096,
11025
11555
  },
11026
11556
  "z-ai/glm-4.7-flash": {
11027
11557
  id: "z-ai/glm-4.7-flash",
@@ -11034,11 +11564,11 @@ export const MODELS = {
11034
11564
  cost: {
11035
11565
  input: 0.06,
11036
11566
  output: 0.39999999999999997,
11037
- cacheRead: 0.0100000002,
11567
+ cacheRead: 0.01,
11038
11568
  cacheWrite: 0,
11039
11569
  },
11040
11570
  contextWindow: 202752,
11041
- maxTokens: 4096,
11571
+ maxTokens: 16384,
11042
11572
  },
11043
11573
  "z-ai/glm-5": {
11044
11574
  id: "z-ai/glm-5",
@@ -11054,8 +11584,8 @@ export const MODELS = {
11054
11584
  cacheRead: 0.119,
11055
11585
  cacheWrite: 0,
11056
11586
  },
11057
- contextWindow: 80000,
11058
- maxTokens: 131072,
11587
+ contextWindow: 202752,
11588
+ maxTokens: 16384,
11059
11589
  },
11060
11590
  "z-ai/glm-5-turbo": {
11061
11591
  id: "z-ai/glm-5-turbo",
@@ -11074,39 +11604,175 @@ export const MODELS = {
11074
11604
  contextWindow: 202752,
11075
11605
  maxTokens: 131072,
11076
11606
  },
11077
- "z-ai/glm-5.1": {
11078
- id: "z-ai/glm-5.1",
11079
- name: "Z.ai: GLM 5.1",
11607
+ "z-ai/glm-5.1": {
11608
+ id: "z-ai/glm-5.1",
11609
+ name: "Z.ai: GLM 5.1",
11610
+ api: "openai-completions",
11611
+ provider: "openrouter",
11612
+ baseUrl: "https://openrouter.ai/api/v1",
11613
+ reasoning: true,
11614
+ input: ["text"],
11615
+ cost: {
11616
+ input: 1.0499999999999998,
11617
+ output: 3.5,
11618
+ cacheRead: 0.5249999999999999,
11619
+ cacheWrite: 0,
11620
+ },
11621
+ contextWindow: 202752,
11622
+ maxTokens: 65535,
11623
+ },
11624
+ "z-ai/glm-5v-turbo": {
11625
+ id: "z-ai/glm-5v-turbo",
11626
+ name: "Z.ai: GLM 5V Turbo",
11627
+ api: "openai-completions",
11628
+ provider: "openrouter",
11629
+ baseUrl: "https://openrouter.ai/api/v1",
11630
+ reasoning: true,
11631
+ input: ["text", "image"],
11632
+ cost: {
11633
+ input: 1.2,
11634
+ output: 4,
11635
+ cacheRead: 0.24,
11636
+ cacheWrite: 0,
11637
+ },
11638
+ contextWindow: 202752,
11639
+ maxTokens: 131072,
11640
+ },
11641
+ "~anthropic/claude-haiku-latest": {
11642
+ id: "~anthropic/claude-haiku-latest",
11643
+ name: "Anthropic Claude Haiku Latest",
11644
+ api: "openai-completions",
11645
+ provider: "openrouter",
11646
+ baseUrl: "https://openrouter.ai/api/v1",
11647
+ reasoning: true,
11648
+ input: ["text", "image"],
11649
+ cost: {
11650
+ input: 1,
11651
+ output: 5,
11652
+ cacheRead: 0.09999999999999999,
11653
+ cacheWrite: 1.25,
11654
+ },
11655
+ contextWindow: 200000,
11656
+ maxTokens: 64000,
11657
+ },
11658
+ "~anthropic/claude-opus-latest": {
11659
+ id: "~anthropic/claude-opus-latest",
11660
+ name: "Anthropic: Claude Opus Latest",
11661
+ api: "openai-completions",
11662
+ provider: "openrouter",
11663
+ baseUrl: "https://openrouter.ai/api/v1",
11664
+ reasoning: true,
11665
+ input: ["text", "image"],
11666
+ cost: {
11667
+ input: 5,
11668
+ output: 25,
11669
+ cacheRead: 0.5,
11670
+ cacheWrite: 6.25,
11671
+ },
11672
+ contextWindow: 1000000,
11673
+ maxTokens: 128000,
11674
+ },
11675
+ "~anthropic/claude-sonnet-latest": {
11676
+ id: "~anthropic/claude-sonnet-latest",
11677
+ name: "Anthropic Claude Sonnet Latest",
11678
+ api: "openai-completions",
11679
+ provider: "openrouter",
11680
+ baseUrl: "https://openrouter.ai/api/v1",
11681
+ reasoning: true,
11682
+ input: ["text", "image"],
11683
+ cost: {
11684
+ input: 3,
11685
+ output: 15,
11686
+ cacheRead: 0.3,
11687
+ cacheWrite: 3.75,
11688
+ },
11689
+ contextWindow: 1000000,
11690
+ maxTokens: 128000,
11691
+ },
11692
+ "~google/gemini-flash-latest": {
11693
+ id: "~google/gemini-flash-latest",
11694
+ name: "Google Gemini Flash Latest",
11695
+ api: "openai-completions",
11696
+ provider: "openrouter",
11697
+ baseUrl: "https://openrouter.ai/api/v1",
11698
+ reasoning: true,
11699
+ input: ["text", "image"],
11700
+ cost: {
11701
+ input: 0.5,
11702
+ output: 3,
11703
+ cacheRead: 0.049999999999999996,
11704
+ cacheWrite: 0.08333333333333334,
11705
+ },
11706
+ contextWindow: 1048576,
11707
+ maxTokens: 65536,
11708
+ },
11709
+ "~google/gemini-pro-latest": {
11710
+ id: "~google/gemini-pro-latest",
11711
+ name: "Google Gemini Pro Latest",
11712
+ api: "openai-completions",
11713
+ provider: "openrouter",
11714
+ baseUrl: "https://openrouter.ai/api/v1",
11715
+ reasoning: true,
11716
+ input: ["text", "image"],
11717
+ cost: {
11718
+ input: 2,
11719
+ output: 12,
11720
+ cacheRead: 0.19999999999999998,
11721
+ cacheWrite: 0.375,
11722
+ },
11723
+ contextWindow: 1048576,
11724
+ maxTokens: 65536,
11725
+ },
11726
+ "~moonshotai/kimi-latest": {
11727
+ id: "~moonshotai/kimi-latest",
11728
+ name: "MoonshotAI Kimi Latest",
11729
+ api: "openai-completions",
11730
+ provider: "openrouter",
11731
+ baseUrl: "https://openrouter.ai/api/v1",
11732
+ reasoning: true,
11733
+ input: ["text", "image"],
11734
+ cost: {
11735
+ input: 0.7448,
11736
+ output: 4.655,
11737
+ cacheRead: 0.1463,
11738
+ cacheWrite: 0,
11739
+ },
11740
+ contextWindow: 256000,
11741
+ maxTokens: 65536,
11742
+ },
11743
+ "~openai/gpt-latest": {
11744
+ id: "~openai/gpt-latest",
11745
+ name: "OpenAI GPT Latest",
11080
11746
  api: "openai-completions",
11081
11747
  provider: "openrouter",
11082
11748
  baseUrl: "https://openrouter.ai/api/v1",
11083
11749
  reasoning: true,
11084
- input: ["text"],
11750
+ input: ["text", "image"],
11085
11751
  cost: {
11086
- input: 0.95,
11087
- output: 3.15,
11088
- cacheRead: 0.475,
11752
+ input: 5,
11753
+ output: 30,
11754
+ cacheRead: 0.5,
11089
11755
  cacheWrite: 0,
11090
11756
  },
11091
- contextWindow: 202752,
11092
- maxTokens: 65535,
11757
+ contextWindow: 1050000,
11758
+ maxTokens: 128000,
11093
11759
  },
11094
- "z-ai/glm-5v-turbo": {
11095
- id: "z-ai/glm-5v-turbo",
11096
- name: "Z.ai: GLM 5V Turbo",
11760
+ "~openai/gpt-mini-latest": {
11761
+ id: "~openai/gpt-mini-latest",
11762
+ name: "OpenAI GPT Mini Latest",
11097
11763
  api: "openai-completions",
11098
11764
  provider: "openrouter",
11099
11765
  baseUrl: "https://openrouter.ai/api/v1",
11100
11766
  reasoning: true,
11101
11767
  input: ["text", "image"],
11102
11768
  cost: {
11103
- input: 1.2,
11104
- output: 4,
11105
- cacheRead: 0.24,
11769
+ input: 0.75,
11770
+ output: 4.5,
11771
+ cacheRead: 0.075,
11106
11772
  cacheWrite: 0,
11107
11773
  },
11108
- contextWindow: 202752,
11109
- maxTokens: 131072,
11774
+ contextWindow: 400000,
11775
+ maxTokens: 128000,
11110
11776
  },
11111
11777
  },
11112
11778
  "vercel-ai-gateway": {
@@ -11178,6 +11844,23 @@ export const MODELS = {
11178
11844
  contextWindow: 128000,
11179
11845
  maxTokens: 8192,
11180
11846
  },
11847
+ "alibaba/qwen-3.6-max-preview": {
11848
+ id: "alibaba/qwen-3.6-max-preview",
11849
+ name: "Qwen 3.6 Max Preview",
11850
+ api: "anthropic-messages",
11851
+ provider: "vercel-ai-gateway",
11852
+ baseUrl: "https://ai-gateway.vercel.sh",
11853
+ reasoning: true,
11854
+ input: ["text", "image"],
11855
+ cost: {
11856
+ input: 1.3,
11857
+ output: 7.8,
11858
+ cacheRead: 0.26,
11859
+ cacheWrite: 1.625,
11860
+ },
11861
+ contextWindow: 240000,
11862
+ maxTokens: 64000,
11863
+ },
11181
11864
  "alibaba/qwen3-235b-a22b-thinking": {
11182
11865
  id: "alibaba/qwen3-235b-a22b-thinking",
11183
11866
  name: "Qwen3 235B A22B Thinking 2507",
@@ -11377,7 +12060,7 @@ export const MODELS = {
11377
12060
  input: 0.5,
11378
12061
  output: 3,
11379
12062
  cacheRead: 0.09999999999999999,
11380
- cacheWrite: 0,
12063
+ cacheWrite: 0.625,
11381
12064
  },
11382
12065
  contextWindow: 1000000,
11383
12066
  maxTokens: 64000,
@@ -11756,6 +12439,40 @@ export const MODELS = {
11756
12439
  contextWindow: 128000,
11757
12440
  maxTokens: 64000,
11758
12441
  },
12442
+ "deepseek/deepseek-v4-flash": {
12443
+ id: "deepseek/deepseek-v4-flash",
12444
+ name: "DeepSeek V4 Flash",
12445
+ api: "anthropic-messages",
12446
+ provider: "vercel-ai-gateway",
12447
+ baseUrl: "https://ai-gateway.vercel.sh",
12448
+ reasoning: true,
12449
+ input: ["text"],
12450
+ cost: {
12451
+ input: 0.14,
12452
+ output: 0.28,
12453
+ cacheRead: 0.028,
12454
+ cacheWrite: 0,
12455
+ },
12456
+ contextWindow: 1000000,
12457
+ maxTokens: 384000,
12458
+ },
12459
+ "deepseek/deepseek-v4-pro": {
12460
+ id: "deepseek/deepseek-v4-pro",
12461
+ name: "DeepSeek V4 Pro",
12462
+ api: "anthropic-messages",
12463
+ provider: "vercel-ai-gateway",
12464
+ baseUrl: "https://ai-gateway.vercel.sh",
12465
+ reasoning: true,
12466
+ input: ["text"],
12467
+ cost: {
12468
+ input: 0.435,
12469
+ output: 0.87,
12470
+ cacheRead: 0.0036,
12471
+ cacheWrite: 0,
12472
+ },
12473
+ contextWindow: 1000000,
12474
+ maxTokens: 384000,
12475
+ },
11759
12476
  "google/gemini-2.0-flash": {
11760
12477
  id: "google/gemini-2.0-flash",
11761
12478
  name: "Gemini 2.0 Flash",
@@ -12521,6 +13238,23 @@ export const MODELS = {
12521
13238
  contextWindow: 262114,
12522
13239
  maxTokens: 262114,
12523
13240
  },
13241
+ "moonshotai/kimi-k2.6": {
13242
+ id: "moonshotai/kimi-k2.6",
13243
+ name: "Kimi K2.6",
13244
+ api: "anthropic-messages",
13245
+ provider: "vercel-ai-gateway",
13246
+ baseUrl: "https://ai-gateway.vercel.sh",
13247
+ reasoning: true,
13248
+ input: ["text", "image"],
13249
+ cost: {
13250
+ input: 0.95,
13251
+ output: 4,
13252
+ cacheRead: 0.16,
13253
+ cacheWrite: 0,
13254
+ },
13255
+ contextWindow: 262000,
13256
+ maxTokens: 262000,
13257
+ },
12524
13258
  "nvidia/nemotron-nano-12b-v2-vl": {
12525
13259
  id: "nvidia/nemotron-nano-12b-v2-vl",
12526
13260
  name: "Nvidia Nemotron Nano 12B V2 VL",
@@ -13014,6 +13748,40 @@ export const MODELS = {
13014
13748
  contextWindow: 1050000,
13015
13749
  maxTokens: 128000,
13016
13750
  },
13751
+ "openai/gpt-5.5": {
13752
+ id: "openai/gpt-5.5",
13753
+ name: "GPT 5.5",
13754
+ api: "anthropic-messages",
13755
+ provider: "vercel-ai-gateway",
13756
+ baseUrl: "https://ai-gateway.vercel.sh",
13757
+ reasoning: true,
13758
+ input: ["text", "image"],
13759
+ cost: {
13760
+ input: 5,
13761
+ output: 30,
13762
+ cacheRead: 0.5,
13763
+ cacheWrite: 0,
13764
+ },
13765
+ contextWindow: 1000000,
13766
+ maxTokens: 128000,
13767
+ },
13768
+ "openai/gpt-5.5-pro": {
13769
+ id: "openai/gpt-5.5-pro",
13770
+ name: "GPT 5.5 Pro",
13771
+ api: "anthropic-messages",
13772
+ provider: "vercel-ai-gateway",
13773
+ baseUrl: "https://ai-gateway.vercel.sh",
13774
+ reasoning: true,
13775
+ input: ["text", "image"],
13776
+ cost: {
13777
+ input: 30,
13778
+ output: 180,
13779
+ cacheRead: 0,
13780
+ cacheWrite: 0,
13781
+ },
13782
+ contextWindow: 1000000,
13783
+ maxTokens: 128000,
13784
+ },
13017
13785
  "openai/gpt-oss-20b": {
13018
13786
  id: "openai/gpt-oss-20b",
13019
13787
  name: "GPT OSS 120B",
@@ -13482,9 +14250,9 @@ export const MODELS = {
13482
14250
  reasoning: true,
13483
14251
  input: ["text"],
13484
14252
  cost: {
13485
- input: 0.09,
13486
- output: 0.29,
13487
- cacheRead: 0.045,
14253
+ input: 0.09999999999999999,
14254
+ output: 0.3,
14255
+ cacheRead: 0.01,
13488
14256
  cacheWrite: 0,
13489
14257
  },
13490
14258
  contextWindow: 262144,
@@ -13701,15 +14469,15 @@ export const MODELS = {
13701
14469
  provider: "vercel-ai-gateway",
13702
14470
  baseUrl: "https://ai-gateway.vercel.sh",
13703
14471
  reasoning: true,
13704
- input: ["text", "image"],
14472
+ input: ["text"],
13705
14473
  cost: {
13706
14474
  input: 1.4,
13707
14475
  output: 4.4,
13708
14476
  cacheRead: 0.26,
13709
14477
  cacheWrite: 0,
13710
14478
  },
13711
- contextWindow: 202752,
13712
- maxTokens: 202752,
14479
+ contextWindow: 202800,
14480
+ maxTokens: 64000,
13713
14481
  },
13714
14482
  "zai/glm-5v-turbo": {
13715
14483
  id: "zai/glm-5v-turbo",
@@ -14140,24 +14908,6 @@ export const MODELS = {
14140
14908
  },
14141
14909
  },
14142
14910
  "zai": {
14143
- "glm-4.5": {
14144
- id: "glm-4.5",
14145
- name: "GLM-4.5",
14146
- api: "openai-completions",
14147
- provider: "zai",
14148
- baseUrl: "https://api.z.ai/api/coding/paas/v4",
14149
- compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai" },
14150
- reasoning: true,
14151
- input: ["text"],
14152
- cost: {
14153
- input: 0,
14154
- output: 0,
14155
- cacheRead: 0,
14156
- cacheWrite: 0,
14157
- },
14158
- contextWindow: 131072,
14159
- maxTokens: 98304,
14160
- },
14161
14911
  "glm-4.5-air": {
14162
14912
  id: "glm-4.5-air",
14163
14913
  name: "GLM-4.5-Air",
@@ -14176,78 +14926,6 @@ export const MODELS = {
14176
14926
  contextWindow: 131072,
14177
14927
  maxTokens: 98304,
14178
14928
  },
14179
- "glm-4.5-flash": {
14180
- id: "glm-4.5-flash",
14181
- name: "GLM-4.5-Flash",
14182
- api: "openai-completions",
14183
- provider: "zai",
14184
- baseUrl: "https://api.z.ai/api/coding/paas/v4",
14185
- compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai" },
14186
- reasoning: true,
14187
- input: ["text"],
14188
- cost: {
14189
- input: 0,
14190
- output: 0,
14191
- cacheRead: 0,
14192
- cacheWrite: 0,
14193
- },
14194
- contextWindow: 131072,
14195
- maxTokens: 98304,
14196
- },
14197
- "glm-4.5v": {
14198
- id: "glm-4.5v",
14199
- name: "GLM-4.5V",
14200
- api: "openai-completions",
14201
- provider: "zai",
14202
- baseUrl: "https://api.z.ai/api/coding/paas/v4",
14203
- compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai" },
14204
- reasoning: true,
14205
- input: ["text", "image"],
14206
- cost: {
14207
- input: 0,
14208
- output: 0,
14209
- cacheRead: 0,
14210
- cacheWrite: 0,
14211
- },
14212
- contextWindow: 64000,
14213
- maxTokens: 16384,
14214
- },
14215
- "glm-4.6": {
14216
- id: "glm-4.6",
14217
- name: "GLM-4.6",
14218
- api: "openai-completions",
14219
- provider: "zai",
14220
- baseUrl: "https://api.z.ai/api/coding/paas/v4",
14221
- compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
14222
- reasoning: true,
14223
- input: ["text"],
14224
- cost: {
14225
- input: 0,
14226
- output: 0,
14227
- cacheRead: 0,
14228
- cacheWrite: 0,
14229
- },
14230
- contextWindow: 204800,
14231
- maxTokens: 131072,
14232
- },
14233
- "glm-4.6v": {
14234
- id: "glm-4.6v",
14235
- name: "GLM-4.6V",
14236
- api: "openai-completions",
14237
- provider: "zai",
14238
- baseUrl: "https://api.z.ai/api/coding/paas/v4",
14239
- compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
14240
- reasoning: true,
14241
- input: ["text", "image"],
14242
- cost: {
14243
- input: 0,
14244
- output: 0,
14245
- cacheRead: 0,
14246
- cacheWrite: 0,
14247
- },
14248
- contextWindow: 128000,
14249
- maxTokens: 32768,
14250
- },
14251
14929
  "glm-4.7": {
14252
14930
  id: "glm-4.7",
14253
14931
  name: "GLM-4.7",
@@ -14266,60 +14944,6 @@ export const MODELS = {
14266
14944
  contextWindow: 204800,
14267
14945
  maxTokens: 131072,
14268
14946
  },
14269
- "glm-4.7-flash": {
14270
- id: "glm-4.7-flash",
14271
- name: "GLM-4.7-Flash",
14272
- api: "openai-completions",
14273
- provider: "zai",
14274
- baseUrl: "https://api.z.ai/api/coding/paas/v4",
14275
- compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
14276
- reasoning: true,
14277
- input: ["text"],
14278
- cost: {
14279
- input: 0,
14280
- output: 0,
14281
- cacheRead: 0,
14282
- cacheWrite: 0,
14283
- },
14284
- contextWindow: 200000,
14285
- maxTokens: 131072,
14286
- },
14287
- "glm-4.7-flashx": {
14288
- id: "glm-4.7-flashx",
14289
- name: "GLM-4.7-FlashX",
14290
- api: "openai-completions",
14291
- provider: "zai",
14292
- baseUrl: "https://api.z.ai/api/coding/paas/v4",
14293
- compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
14294
- reasoning: true,
14295
- input: ["text"],
14296
- cost: {
14297
- input: 0.07,
14298
- output: 0.4,
14299
- cacheRead: 0.01,
14300
- cacheWrite: 0,
14301
- },
14302
- contextWindow: 200000,
14303
- maxTokens: 131072,
14304
- },
14305
- "glm-5": {
14306
- id: "glm-5",
14307
- name: "GLM-5",
14308
- api: "openai-completions",
14309
- provider: "zai",
14310
- baseUrl: "https://api.z.ai/api/coding/paas/v4",
14311
- compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
14312
- reasoning: true,
14313
- input: ["text"],
14314
- cost: {
14315
- input: 0,
14316
- output: 0,
14317
- cacheRead: 0,
14318
- cacheWrite: 0,
14319
- },
14320
- contextWindow: 204800,
14321
- maxTokens: 131072,
14322
- },
14323
14947
  "glm-5-turbo": {
14324
14948
  id: "glm-5-turbo",
14325
14949
  name: "GLM-5-Turbo",
@@ -14356,24 +14980,6 @@ export const MODELS = {
14356
14980
  contextWindow: 200000,
14357
14981
  maxTokens: 131072,
14358
14982
  },
14359
- "glm-5v-turbo": {
14360
- id: "glm-5v-turbo",
14361
- name: "glm-5v-turbo",
14362
- api: "openai-completions",
14363
- provider: "zai",
14364
- baseUrl: "https://api.z.ai/api/coding/paas/v4",
14365
- compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
14366
- reasoning: true,
14367
- input: ["text", "image"],
14368
- cost: {
14369
- input: 0,
14370
- output: 0,
14371
- cacheRead: 0,
14372
- cacheWrite: 0,
14373
- },
14374
- contextWindow: 200000,
14375
- maxTokens: 131072,
14376
- },
14377
14983
  },
14378
14984
  };
14379
14985
  //# sourceMappingURL=models.generated.js.map