@dreb/ai 2.12.1 → 2.14.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -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 +2522,40 @@ 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
+ },
2542
+ "gpt-5.5-pro": {
2543
+ id: "gpt-5.5-pro",
2544
+ name: "GPT-5.5 Pro",
2545
+ api: "azure-openai-responses",
2546
+ provider: "azure-openai-responses",
2547
+ baseUrl: "",
2548
+ reasoning: true,
2549
+ input: ["text", "image"],
2550
+ cost: {
2551
+ input: 30,
2552
+ output: 180,
2553
+ cacheRead: 0,
2554
+ cacheWrite: 0,
2555
+ },
2556
+ contextWindow: 1050000,
2557
+ maxTokens: 128000,
2558
+ },
2491
2559
  "o1": {
2492
2560
  id: "o1",
2493
2561
  name: "o1",
@@ -3117,6 +3185,24 @@ export const MODELS = {
3117
3185
  contextWindow: 400000,
3118
3186
  maxTokens: 128000,
3119
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
+ },
3120
3206
  "grok-code-fast-1": {
3121
3207
  id: "grok-code-fast-1",
3122
3208
  name: "Grok Code Fast 1",
@@ -3563,8 +3649,8 @@ export const MODELS = {
3563
3649
  contextWindow: 131072,
3564
3650
  maxTokens: 8192,
3565
3651
  },
3566
- "gemma-4-26b-it": {
3567
- id: "gemma-4-26b-it",
3652
+ "gemma-4-26b-a4b-it": {
3653
+ id: "gemma-4-26b-a4b-it",
3568
3654
  name: "Gemma 4 26B",
3569
3655
  api: "google-generative-ai",
3570
3656
  provider: "google",
@@ -4588,6 +4674,24 @@ export const MODELS = {
4588
4674
  contextWindow: 163840,
4589
4675
  maxTokens: 65536,
4590
4676
  },
4677
+ "deepseek-ai/DeepSeek-V4-Pro": {
4678
+ id: "deepseek-ai/DeepSeek-V4-Pro",
4679
+ name: "DeepSeek V4 Pro",
4680
+ api: "openai-completions",
4681
+ provider: "huggingface",
4682
+ baseUrl: "https://router.huggingface.co/v1",
4683
+ compat: { "supportsDeveloperRole": false },
4684
+ reasoning: true,
4685
+ input: ["text"],
4686
+ cost: {
4687
+ input: 1.74,
4688
+ output: 3.48,
4689
+ cacheRead: 0.145,
4690
+ cacheWrite: 0,
4691
+ },
4692
+ contextWindow: 1048576,
4693
+ maxTokens: 393216,
4694
+ },
4591
4695
  "moonshotai/Kimi-K2-Instruct": {
4592
4696
  id: "moonshotai/Kimi-K2-Instruct",
4593
4697
  name: "Kimi-K2-Instruct",
@@ -5885,6 +5989,40 @@ export const MODELS = {
5885
5989
  contextWindow: 1050000,
5886
5990
  maxTokens: 128000,
5887
5991
  },
5992
+ "gpt-5.5": {
5993
+ id: "gpt-5.5",
5994
+ name: "GPT-5.5",
5995
+ api: "openai-responses",
5996
+ provider: "openai",
5997
+ baseUrl: "https://api.openai.com/v1",
5998
+ reasoning: true,
5999
+ input: ["text", "image"],
6000
+ cost: {
6001
+ input: 5,
6002
+ output: 30,
6003
+ cacheRead: 0.5,
6004
+ cacheWrite: 0,
6005
+ },
6006
+ contextWindow: 1050000,
6007
+ maxTokens: 128000,
6008
+ },
6009
+ "gpt-5.5-pro": {
6010
+ id: "gpt-5.5-pro",
6011
+ name: "GPT-5.5 Pro",
6012
+ api: "openai-responses",
6013
+ provider: "openai",
6014
+ baseUrl: "https://api.openai.com/v1",
6015
+ reasoning: true,
6016
+ input: ["text", "image"],
6017
+ cost: {
6018
+ input: 30,
6019
+ output: 180,
6020
+ cacheRead: 0,
6021
+ cacheWrite: 0,
6022
+ },
6023
+ contextWindow: 1050000,
6024
+ maxTokens: 128000,
6025
+ },
5888
6026
  "o1": {
5889
6027
  id: "o1",
5890
6028
  name: "o1",
@@ -6195,23 +6333,6 @@ export const MODELS = {
6195
6333
  contextWindow: 200000,
6196
6334
  maxTokens: 128000,
6197
6335
  },
6198
- "claude-3-5-haiku": {
6199
- id: "claude-3-5-haiku",
6200
- name: "Claude Haiku 3.5",
6201
- api: "anthropic-messages",
6202
- provider: "opencode",
6203
- baseUrl: "https://opencode.ai/zen",
6204
- reasoning: false,
6205
- input: ["text", "image"],
6206
- cost: {
6207
- input: 0.8,
6208
- output: 4,
6209
- cacheRead: 0.08,
6210
- cacheWrite: 1,
6211
- },
6212
- contextWindow: 200000,
6213
- maxTokens: 8192,
6214
- },
6215
6336
  "claude-haiku-4-5": {
6216
6337
  id: "claude-haiku-4-5",
6217
6338
  name: "Claude Haiku 4.5",
@@ -6654,6 +6775,57 @@ export const MODELS = {
6654
6775
  contextWindow: 1050000,
6655
6776
  maxTokens: 128000,
6656
6777
  },
6778
+ "gpt-5.5": {
6779
+ id: "gpt-5.5",
6780
+ name: "GPT-5.5",
6781
+ api: "openai-responses",
6782
+ provider: "opencode",
6783
+ baseUrl: "https://opencode.ai/zen/v1",
6784
+ reasoning: true,
6785
+ input: ["text", "image"],
6786
+ cost: {
6787
+ input: 5,
6788
+ output: 30,
6789
+ cacheRead: 0.5,
6790
+ cacheWrite: 0,
6791
+ },
6792
+ contextWindow: 1050000,
6793
+ maxTokens: 128000,
6794
+ },
6795
+ "gpt-5.5-pro": {
6796
+ id: "gpt-5.5-pro",
6797
+ name: "GPT-5.5 Pro",
6798
+ api: "openai-responses",
6799
+ provider: "opencode",
6800
+ baseUrl: "https://opencode.ai/zen/v1",
6801
+ reasoning: true,
6802
+ input: ["text", "image"],
6803
+ cost: {
6804
+ input: 30,
6805
+ output: 180,
6806
+ cacheRead: 30,
6807
+ cacheWrite: 0,
6808
+ },
6809
+ contextWindow: 1050000,
6810
+ maxTokens: 128000,
6811
+ },
6812
+ "hy3-preview-free": {
6813
+ id: "hy3-preview-free",
6814
+ name: "Hy3 preview Free",
6815
+ api: "openai-completions",
6816
+ provider: "opencode",
6817
+ baseUrl: "https://opencode.ai/zen/v1",
6818
+ reasoning: true,
6819
+ input: ["text"],
6820
+ cost: {
6821
+ input: 0,
6822
+ output: 0,
6823
+ cacheRead: 0,
6824
+ cacheWrite: 0,
6825
+ },
6826
+ contextWindow: 256000,
6827
+ maxTokens: 64000,
6828
+ },
6657
6829
  "kimi-k2.5": {
6658
6830
  id: "kimi-k2.5",
6659
6831
  name: "Kimi K2.5",
@@ -6688,23 +6860,6 @@ export const MODELS = {
6688
6860
  contextWindow: 262144,
6689
6861
  maxTokens: 65536,
6690
6862
  },
6691
- "ling-2.6-flash-free": {
6692
- id: "ling-2.6-flash-free",
6693
- name: "Ling 2.6 Flash Free",
6694
- api: "openai-completions",
6695
- provider: "opencode",
6696
- baseUrl: "https://opencode.ai/zen/v1",
6697
- reasoning: false,
6698
- input: ["text"],
6699
- cost: {
6700
- input: 0,
6701
- output: 0,
6702
- cacheRead: 0,
6703
- cacheWrite: 0,
6704
- },
6705
- contextWindow: 262100,
6706
- maxTokens: 32800,
6707
- },
6708
6863
  "minimax-m2.5": {
6709
6864
  id: "minimax-m2.5",
6710
6865
  name: "MiniMax M2.5",
@@ -6809,6 +6964,40 @@ export const MODELS = {
6809
6964
  },
6810
6965
  },
6811
6966
  "opencode-go": {
6967
+ "deepseek-v4-flash": {
6968
+ id: "deepseek-v4-flash",
6969
+ name: "DeepSeek V4 Flash",
6970
+ api: "openai-completions",
6971
+ provider: "opencode-go",
6972
+ baseUrl: "https://opencode.ai/zen/go/v1",
6973
+ reasoning: true,
6974
+ input: ["text"],
6975
+ cost: {
6976
+ input: 0.14,
6977
+ output: 0.28,
6978
+ cacheRead: 0.0028,
6979
+ cacheWrite: 0,
6980
+ },
6981
+ contextWindow: 1000000,
6982
+ maxTokens: 384000,
6983
+ },
6984
+ "deepseek-v4-pro": {
6985
+ id: "deepseek-v4-pro",
6986
+ name: "DeepSeek V4 Pro",
6987
+ api: "openai-completions",
6988
+ provider: "opencode-go",
6989
+ baseUrl: "https://opencode.ai/zen/go/v1",
6990
+ reasoning: true,
6991
+ input: ["text"],
6992
+ cost: {
6993
+ input: 1.74,
6994
+ output: 3.48,
6995
+ cacheRead: 0.0145,
6996
+ cacheWrite: 0,
6997
+ },
6998
+ contextWindow: 1000000,
6999
+ maxTokens: 384000,
7000
+ },
6812
7001
  "glm-5": {
6813
7002
  id: "glm-5",
6814
7003
  name: "GLM-5",
@@ -6823,8 +7012,8 @@ export const MODELS = {
6823
7012
  cacheRead: 0.2,
6824
7013
  cacheWrite: 0,
6825
7014
  },
6826
- contextWindow: 204800,
6827
- maxTokens: 131072,
7015
+ contextWindow: 202752,
7016
+ maxTokens: 32768,
6828
7017
  },
6829
7018
  "glm-5.1": {
6830
7019
  id: "glm-5.1",
@@ -6840,8 +7029,8 @@ export const MODELS = {
6840
7029
  cacheRead: 0.26,
6841
7030
  cacheWrite: 0,
6842
7031
  },
6843
- contextWindow: 204800,
6844
- maxTokens: 131072,
7032
+ contextWindow: 202752,
7033
+ maxTokens: 32768,
6845
7034
  },
6846
7035
  "kimi-k2.5": {
6847
7036
  id: "kimi-k2.5",
@@ -6892,7 +7081,7 @@ export const MODELS = {
6892
7081
  cacheWrite: 0,
6893
7082
  },
6894
7083
  contextWindow: 262144,
6895
- maxTokens: 64000,
7084
+ maxTokens: 128000,
6896
7085
  },
6897
7086
  "mimo-v2-pro": {
6898
7087
  id: "mimo-v2-pro",
@@ -6909,7 +7098,41 @@ export const MODELS = {
6909
7098
  cacheWrite: 0,
6910
7099
  },
6911
7100
  contextWindow: 1048576,
6912
- maxTokens: 64000,
7101
+ maxTokens: 128000,
7102
+ },
7103
+ "mimo-v2.5": {
7104
+ id: "mimo-v2.5",
7105
+ name: "MiMo V2.5",
7106
+ api: "openai-completions",
7107
+ provider: "opencode-go",
7108
+ baseUrl: "https://opencode.ai/zen/go/v1",
7109
+ reasoning: true,
7110
+ input: ["text", "image"],
7111
+ cost: {
7112
+ input: 0.4,
7113
+ output: 2,
7114
+ cacheRead: 0.08,
7115
+ cacheWrite: 0,
7116
+ },
7117
+ contextWindow: 1000000,
7118
+ maxTokens: 128000,
7119
+ },
7120
+ "mimo-v2.5-pro": {
7121
+ id: "mimo-v2.5-pro",
7122
+ name: "MiMo V2.5 Pro",
7123
+ api: "openai-completions",
7124
+ provider: "opencode-go",
7125
+ baseUrl: "https://opencode.ai/zen/go/v1",
7126
+ reasoning: true,
7127
+ input: ["text"],
7128
+ cost: {
7129
+ input: 1,
7130
+ output: 3,
7131
+ cacheRead: 0.2,
7132
+ cacheWrite: 0,
7133
+ },
7134
+ contextWindow: 1048576,
7135
+ maxTokens: 128000,
6913
7136
  },
6914
7137
  "minimax-m2.5": {
6915
7138
  id: "minimax-m2.5",
@@ -7030,7 +7253,7 @@ export const MODELS = {
7030
7253
  cacheWrite: 0,
7031
7254
  },
7032
7255
  contextWindow: 65536,
7033
- maxTokens: 4096,
7256
+ maxTokens: 16384,
7034
7257
  },
7035
7258
  "amazon/nova-2-lite-v1": {
7036
7259
  id: "amazon/nova-2-lite-v1",
@@ -7355,17 +7578,17 @@ export const MODELS = {
7355
7578
  contextWindow: 1000000,
7356
7579
  maxTokens: 128000,
7357
7580
  },
7358
- "arcee-ai/trinity-large-preview:free": {
7359
- id: "arcee-ai/trinity-large-preview:free",
7360
- name: "Arcee AI: Trinity Large Preview (free)",
7581
+ "arcee-ai/trinity-large-preview": {
7582
+ id: "arcee-ai/trinity-large-preview",
7583
+ name: "Arcee AI: Trinity Large Preview",
7361
7584
  api: "openai-completions",
7362
7585
  provider: "openrouter",
7363
7586
  baseUrl: "https://openrouter.ai/api/v1",
7364
7587
  reasoning: false,
7365
7588
  input: ["text"],
7366
7589
  cost: {
7367
- input: 0,
7368
- output: 0,
7590
+ input: 0.15,
7591
+ output: 0.44999999999999996,
7369
7592
  cacheRead: 0,
7370
7593
  cacheWrite: 0,
7371
7594
  },
@@ -7591,7 +7814,7 @@ export const MODELS = {
7591
7814
  cacheWrite: 0,
7592
7815
  },
7593
7816
  contextWindow: 163840,
7594
- maxTokens: 163840,
7817
+ maxTokens: 16384,
7595
7818
  },
7596
7819
  "deepseek/deepseek-chat-v3-0324": {
7597
7820
  id: "deepseek/deepseek-chat-v3-0324",
@@ -7608,7 +7831,7 @@ export const MODELS = {
7608
7831
  cacheWrite: 0,
7609
7832
  },
7610
7833
  contextWindow: 163840,
7611
- maxTokens: 4096,
7834
+ maxTokens: 16384,
7612
7835
  },
7613
7836
  "deepseek/deepseek-chat-v3.1": {
7614
7837
  id: "deepseek/deepseek-chat-v3.1",
@@ -7659,7 +7882,7 @@ export const MODELS = {
7659
7882
  cacheWrite: 0,
7660
7883
  },
7661
7884
  contextWindow: 163840,
7662
- maxTokens: 4096,
7885
+ maxTokens: 32768,
7663
7886
  },
7664
7887
  "deepseek/deepseek-v3.1-terminus": {
7665
7888
  id: "deepseek/deepseek-v3.1-terminus",
@@ -7672,11 +7895,11 @@ export const MODELS = {
7672
7895
  cost: {
7673
7896
  input: 0.21,
7674
7897
  output: 0.7899999999999999,
7675
- cacheRead: 0.1300000002,
7898
+ cacheRead: 0.13,
7676
7899
  cacheWrite: 0,
7677
7900
  },
7678
7901
  contextWindow: 163840,
7679
- maxTokens: 4096,
7902
+ maxTokens: 32768,
7680
7903
  },
7681
7904
  "deepseek/deepseek-v3.2": {
7682
7905
  id: "deepseek/deepseek-v3.2",
@@ -7693,7 +7916,7 @@ export const MODELS = {
7693
7916
  cacheWrite: 0,
7694
7917
  },
7695
7918
  contextWindow: 131072,
7696
- maxTokens: 32768,
7919
+ maxTokens: 65536,
7697
7920
  },
7698
7921
  "deepseek/deepseek-v3.2-exp": {
7699
7922
  id: "deepseek/deepseek-v3.2-exp",
@@ -7712,7 +7935,41 @@ export const MODELS = {
7712
7935
  contextWindow: 163840,
7713
7936
  maxTokens: 65536,
7714
7937
  },
7715
- "essentialai/rnj-1-instruct": {
7938
+ "deepseek/deepseek-v4-flash": {
7939
+ id: "deepseek/deepseek-v4-flash",
7940
+ name: "DeepSeek: DeepSeek V4 Flash",
7941
+ api: "openai-completions",
7942
+ provider: "openrouter",
7943
+ baseUrl: "https://openrouter.ai/api/v1",
7944
+ reasoning: true,
7945
+ input: ["text"],
7946
+ cost: {
7947
+ input: 0.14,
7948
+ output: 0.28,
7949
+ cacheRead: 0.0028,
7950
+ cacheWrite: 0,
7951
+ },
7952
+ contextWindow: 1048576,
7953
+ maxTokens: 384000,
7954
+ },
7955
+ "deepseek/deepseek-v4-pro": {
7956
+ id: "deepseek/deepseek-v4-pro",
7957
+ name: "DeepSeek: DeepSeek V4 Pro",
7958
+ api: "openai-completions",
7959
+ provider: "openrouter",
7960
+ baseUrl: "https://openrouter.ai/api/v1",
7961
+ reasoning: true,
7962
+ input: ["text"],
7963
+ cost: {
7964
+ input: 0.435,
7965
+ output: 0.87,
7966
+ cacheRead: 0.003625,
7967
+ cacheWrite: 0,
7968
+ },
7969
+ contextWindow: 1048576,
7970
+ maxTokens: 384000,
7971
+ },
7972
+ "essentialai/rnj-1-instruct": {
7716
7973
  id: "essentialai/rnj-1-instruct",
7717
7974
  name: "EssentialAI: Rnj 1 Instruct",
7718
7975
  api: "openai-completions",
@@ -7743,7 +8000,7 @@ export const MODELS = {
7743
8000
  cacheRead: 0.024999999999999998,
7744
8001
  cacheWrite: 0.08333333333333334,
7745
8002
  },
7746
- contextWindow: 1000000,
8003
+ contextWindow: 1048576,
7747
8004
  maxTokens: 8192,
7748
8005
  },
7749
8006
  "google/gemini-2.0-flash-lite-001": {
@@ -7933,6 +8190,40 @@ export const MODELS = {
7933
8190
  contextWindow: 1048576,
7934
8191
  maxTokens: 65536,
7935
8192
  },
8193
+ "google/gemma-3-12b-it": {
8194
+ id: "google/gemma-3-12b-it",
8195
+ name: "Google: Gemma 3 12B",
8196
+ api: "openai-completions",
8197
+ provider: "openrouter",
8198
+ baseUrl: "https://openrouter.ai/api/v1",
8199
+ reasoning: false,
8200
+ input: ["text", "image"],
8201
+ cost: {
8202
+ input: 0.04,
8203
+ output: 0.13,
8204
+ cacheRead: 0,
8205
+ cacheWrite: 0,
8206
+ },
8207
+ contextWindow: 131072,
8208
+ maxTokens: 16384,
8209
+ },
8210
+ "google/gemma-3-27b-it": {
8211
+ id: "google/gemma-3-27b-it",
8212
+ name: "Google: Gemma 3 27B",
8213
+ api: "openai-completions",
8214
+ provider: "openrouter",
8215
+ baseUrl: "https://openrouter.ai/api/v1",
8216
+ reasoning: false,
8217
+ input: ["text", "image"],
8218
+ cost: {
8219
+ input: 0.08,
8220
+ output: 0.16,
8221
+ cacheRead: 0,
8222
+ cacheWrite: 0,
8223
+ },
8224
+ contextWindow: 131072,
8225
+ maxTokens: 16384,
8226
+ },
7936
8227
  "google/gemma-4-26b-a4b-it": {
7937
8228
  id: "google/gemma-4-26b-a4b-it",
7938
8229
  name: "Google: Gemma 4 26B A4B ",
@@ -7942,13 +8233,13 @@ export const MODELS = {
7942
8233
  reasoning: true,
7943
8234
  input: ["text", "image"],
7944
8235
  cost: {
7945
- input: 0.07,
7946
- output: 0.35,
7947
- cacheRead: 0.04,
8236
+ input: 0.06,
8237
+ output: 0.33,
8238
+ cacheRead: 0,
7948
8239
  cacheWrite: 0,
7949
8240
  },
7950
8241
  contextWindow: 262144,
7951
- maxTokens: 262144,
8242
+ maxTokens: 4096,
7952
8243
  },
7953
8244
  "google/gemma-4-26b-a4b-it:free": {
7954
8245
  id: "google/gemma-4-26b-a4b-it:free",
@@ -7978,11 +8269,11 @@ export const MODELS = {
7978
8269
  cost: {
7979
8270
  input: 0.13,
7980
8271
  output: 0.38,
7981
- cacheRead: 0.019999999499999997,
8272
+ cacheRead: 0,
7982
8273
  cacheWrite: 0,
7983
8274
  },
7984
8275
  contextWindow: 262144,
7985
- maxTokens: 4096,
8276
+ maxTokens: 16384,
7986
8277
  },
7987
8278
  "google/gemma-4-31b-it:free": {
7988
8279
  id: "google/gemma-4-31b-it:free",
@@ -8018,9 +8309,9 @@ export const MODELS = {
8018
8309
  contextWindow: 128000,
8019
8310
  maxTokens: 50000,
8020
8311
  },
8021
- "inclusionai/ling-2.6-flash:free": {
8022
- id: "inclusionai/ling-2.6-flash:free",
8023
- name: "inclusionAI: Ling-2.6-flash (free)",
8312
+ "inclusionai/ling-2.6-1t:free": {
8313
+ id: "inclusionai/ling-2.6-1t:free",
8314
+ name: "inclusionAI: Ling-2.6-1T (free)",
8024
8315
  api: "openai-completions",
8025
8316
  provider: "openrouter",
8026
8317
  baseUrl: "https://openrouter.ai/api/v1",
@@ -8035,6 +8326,23 @@ export const MODELS = {
8035
8326
  contextWindow: 262144,
8036
8327
  maxTokens: 32768,
8037
8328
  },
8329
+ "inclusionai/ling-2.6-flash": {
8330
+ id: "inclusionai/ling-2.6-flash",
8331
+ name: "inclusionAI: Ling-2.6-flash",
8332
+ api: "openai-completions",
8333
+ provider: "openrouter",
8334
+ baseUrl: "https://openrouter.ai/api/v1",
8335
+ reasoning: false,
8336
+ input: ["text"],
8337
+ cost: {
8338
+ input: 0.08,
8339
+ output: 0.24,
8340
+ cacheRead: 0.016,
8341
+ cacheWrite: 0,
8342
+ },
8343
+ contextWindow: 262144,
8344
+ maxTokens: 32768,
8345
+ },
8038
8346
  "kwaipilot/kat-coder-pro-v2": {
8039
8347
  id: "kwaipilot/kat-coder-pro-v2",
8040
8348
  name: "Kwaipilot: KAT-Coder-Pro V2",
@@ -8084,7 +8392,7 @@ export const MODELS = {
8084
8392
  cacheWrite: 0,
8085
8393
  },
8086
8394
  contextWindow: 131072,
8087
- maxTokens: 4096,
8395
+ maxTokens: 16384,
8088
8396
  },
8089
8397
  "meta-llama/llama-3.1-8b-instruct": {
8090
8398
  id: "meta-llama/llama-3.1-8b-instruct",
@@ -8215,12 +8523,12 @@ export const MODELS = {
8215
8523
  input: ["text"],
8216
8524
  cost: {
8217
8525
  input: 0.15,
8218
- output: 1.2,
8219
- cacheRead: 0.075,
8526
+ output: 1.15,
8527
+ cacheRead: 0.03,
8220
8528
  cacheWrite: 0,
8221
8529
  },
8222
8530
  contextWindow: 196608,
8223
- maxTokens: 65536,
8531
+ maxTokens: 131072,
8224
8532
  },
8225
8533
  "minimax/minimax-m2.5:free": {
8226
8534
  id: "minimax/minimax-m2.5:free",
@@ -8487,12 +8795,12 @@ export const MODELS = {
8487
8795
  input: ["text"],
8488
8796
  cost: {
8489
8797
  input: 0.02,
8490
- output: 0.04,
8798
+ output: 0.03,
8491
8799
  cacheRead: 0,
8492
8800
  cacheWrite: 0,
8493
8801
  },
8494
8802
  contextWindow: 131072,
8495
- maxTokens: 16384,
8803
+ maxTokens: 4096,
8496
8804
  },
8497
8805
  "mistralai/mistral-saba": {
8498
8806
  id: "mistralai/mistral-saba",
@@ -8543,24 +8851,7 @@ export const MODELS = {
8543
8851
  cacheWrite: 0,
8544
8852
  },
8545
8853
  contextWindow: 128000,
8546
- maxTokens: 4096,
8547
- },
8548
- "mistralai/mistral-small-creative": {
8549
- id: "mistralai/mistral-small-creative",
8550
- name: "Mistral: Mistral Small Creative",
8551
- api: "openai-completions",
8552
- provider: "openrouter",
8553
- baseUrl: "https://openrouter.ai/api/v1",
8554
- reasoning: false,
8555
- input: ["text"],
8556
- cost: {
8557
- input: 0.09999999999999999,
8558
- output: 0.3,
8559
- cacheRead: 0.01,
8560
- cacheWrite: 0,
8561
- },
8562
- contextWindow: 32768,
8563
- maxTokens: 4096,
8854
+ maxTokens: 16384,
8564
8855
  },
8565
8856
  "mistralai/mixtral-8x22b-instruct": {
8566
8857
  id: "mistralai/mixtral-8x22b-instruct",
@@ -8707,13 +8998,13 @@ export const MODELS = {
8707
8998
  reasoning: true,
8708
8999
  input: ["text", "image"],
8709
9000
  cost: {
8710
- input: 0.7999999999999999,
8711
- output: 3.5,
8712
- cacheRead: 0.19999999999999998,
9001
+ input: 0.74,
9002
+ output: 3.49,
9003
+ cacheRead: 0.14,
8713
9004
  cacheWrite: 0,
8714
9005
  },
8715
- contextWindow: 262144,
8716
- maxTokens: 262144,
9006
+ contextWindow: 262142,
9007
+ maxTokens: 262142,
8717
9008
  },
8718
9009
  "nex-agi/deepseek-v3.1-nex-n1": {
8719
9010
  id: "nex-agi/deepseek-v3.1-nex-n1",
@@ -8764,7 +9055,7 @@ export const MODELS = {
8764
9055
  cacheWrite: 0,
8765
9056
  },
8766
9057
  contextWindow: 131072,
8767
- maxTokens: 4096,
9058
+ maxTokens: 16384,
8768
9059
  },
8769
9060
  "nvidia/nemotron-3-nano-30b-a3b": {
8770
9061
  id: "nvidia/nemotron-3-nano-30b-a3b",
@@ -8781,7 +9072,7 @@ export const MODELS = {
8781
9072
  cacheWrite: 0,
8782
9073
  },
8783
9074
  contextWindow: 262144,
8784
- maxTokens: 4096,
9075
+ maxTokens: 228000,
8785
9076
  },
8786
9077
  "nvidia/nemotron-3-nano-30b-a3b:free": {
8787
9078
  id: "nvidia/nemotron-3-nano-30b-a3b:free",
@@ -8800,6 +9091,23 @@ export const MODELS = {
8800
9091
  contextWindow: 256000,
8801
9092
  maxTokens: 4096,
8802
9093
  },
9094
+ "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free": {
9095
+ id: "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
9096
+ name: "NVIDIA: Nemotron 3 Nano Omni (free)",
9097
+ api: "openai-completions",
9098
+ provider: "openrouter",
9099
+ baseUrl: "https://openrouter.ai/api/v1",
9100
+ reasoning: true,
9101
+ input: ["text", "image"],
9102
+ cost: {
9103
+ input: 0,
9104
+ output: 0,
9105
+ cacheRead: 0,
9106
+ cacheWrite: 0,
9107
+ },
9108
+ contextWindow: 256000,
9109
+ maxTokens: 65536,
9110
+ },
8803
9111
  "nvidia/nemotron-3-super-120b-a12b": {
8804
9112
  id: "nvidia/nemotron-3-super-120b-a12b",
8805
9113
  name: "NVIDIA: Nemotron 3 Super",
@@ -8866,7 +9174,7 @@ export const MODELS = {
8866
9174
  cacheWrite: 0,
8867
9175
  },
8868
9176
  contextWindow: 131072,
8869
- maxTokens: 4096,
9177
+ maxTokens: 16384,
8870
9178
  },
8871
9179
  "nvidia/nemotron-nano-9b-v2:free": {
8872
9180
  id: "nvidia/nemotron-nano-9b-v2:free",
@@ -9531,6 +9839,40 @@ export const MODELS = {
9531
9839
  contextWindow: 1050000,
9532
9840
  maxTokens: 128000,
9533
9841
  },
9842
+ "openai/gpt-5.5": {
9843
+ id: "openai/gpt-5.5",
9844
+ name: "OpenAI: GPT-5.5",
9845
+ api: "openai-completions",
9846
+ provider: "openrouter",
9847
+ baseUrl: "https://openrouter.ai/api/v1",
9848
+ reasoning: true,
9849
+ input: ["text", "image"],
9850
+ cost: {
9851
+ input: 5,
9852
+ output: 30,
9853
+ cacheRead: 0.5,
9854
+ cacheWrite: 0,
9855
+ },
9856
+ contextWindow: 1050000,
9857
+ maxTokens: 128000,
9858
+ },
9859
+ "openai/gpt-5.5-pro": {
9860
+ id: "openai/gpt-5.5-pro",
9861
+ name: "OpenAI: GPT-5.5 Pro",
9862
+ api: "openai-completions",
9863
+ provider: "openrouter",
9864
+ baseUrl: "https://openrouter.ai/api/v1",
9865
+ reasoning: true,
9866
+ input: ["text", "image"],
9867
+ cost: {
9868
+ input: 30,
9869
+ output: 180,
9870
+ cacheRead: 0,
9871
+ cacheWrite: 0,
9872
+ },
9873
+ contextWindow: 1050000,
9874
+ maxTokens: 128000,
9875
+ },
9534
9876
  "openai/gpt-audio": {
9535
9877
  id: "openai/gpt-audio",
9536
9878
  name: "OpenAI: GPT Audio",
@@ -9580,7 +9922,7 @@ export const MODELS = {
9580
9922
  cacheWrite: 0,
9581
9923
  },
9582
9924
  contextWindow: 131072,
9583
- maxTokens: 4096,
9925
+ maxTokens: 131072,
9584
9926
  },
9585
9927
  "openai/gpt-oss-120b:free": {
9586
9928
  id: "openai/gpt-oss-120b:free",
@@ -9614,7 +9956,7 @@ export const MODELS = {
9614
9956
  cacheWrite: 0,
9615
9957
  },
9616
9958
  contextWindow: 131072,
9617
- maxTokens: 4096,
9959
+ maxTokens: 131072,
9618
9960
  },
9619
9961
  "openai/gpt-oss-20b:free": {
9620
9962
  id: "openai/gpt-oss-20b:free",
@@ -9837,6 +10179,57 @@ export const MODELS = {
9837
10179
  contextWindow: 200000,
9838
10180
  maxTokens: 4096,
9839
10181
  },
10182
+ "openrouter/owl-alpha": {
10183
+ id: "openrouter/owl-alpha",
10184
+ name: "Owl Alpha",
10185
+ api: "openai-completions",
10186
+ provider: "openrouter",
10187
+ baseUrl: "https://openrouter.ai/api/v1",
10188
+ reasoning: false,
10189
+ input: ["text"],
10190
+ cost: {
10191
+ input: 0,
10192
+ output: 0,
10193
+ cacheRead: 0,
10194
+ cacheWrite: 0,
10195
+ },
10196
+ contextWindow: 1048756,
10197
+ maxTokens: 262144,
10198
+ },
10199
+ "poolside/laguna-m.1:free": {
10200
+ id: "poolside/laguna-m.1:free",
10201
+ name: "Poolside: Laguna M.1 (free)",
10202
+ api: "openai-completions",
10203
+ provider: "openrouter",
10204
+ baseUrl: "https://openrouter.ai/api/v1",
10205
+ reasoning: true,
10206
+ input: ["text"],
10207
+ cost: {
10208
+ input: 0,
10209
+ output: 0,
10210
+ cacheRead: 0,
10211
+ cacheWrite: 0,
10212
+ },
10213
+ contextWindow: 131072,
10214
+ maxTokens: 8192,
10215
+ },
10216
+ "poolside/laguna-xs.2:free": {
10217
+ id: "poolside/laguna-xs.2:free",
10218
+ name: "Poolside: Laguna XS.2 (free)",
10219
+ api: "openai-completions",
10220
+ provider: "openrouter",
10221
+ baseUrl: "https://openrouter.ai/api/v1",
10222
+ reasoning: true,
10223
+ input: ["text"],
10224
+ cost: {
10225
+ input: 0,
10226
+ output: 0,
10227
+ cacheRead: 0,
10228
+ cacheWrite: 0,
10229
+ },
10230
+ contextWindow: 131072,
10231
+ maxTokens: 8192,
10232
+ },
9840
10233
  "prime-intellect/intellect-3": {
9841
10234
  id: "prime-intellect/intellect-3",
9842
10235
  name: "Prime Intellect: INTELLECT-3",
@@ -9863,8 +10256,8 @@ export const MODELS = {
9863
10256
  reasoning: false,
9864
10257
  input: ["text"],
9865
10258
  cost: {
9866
- input: 0.12,
9867
- output: 0.39,
10259
+ input: 0.36,
10260
+ output: 0.39999999999999997,
9868
10261
  cacheRead: 0,
9869
10262
  cacheWrite: 0,
9870
10263
  },
@@ -10039,7 +10432,7 @@ export const MODELS = {
10039
10432
  cacheWrite: 0,
10040
10433
  },
10041
10434
  contextWindow: 262144,
10042
- maxTokens: 4096,
10435
+ maxTokens: 16384,
10043
10436
  },
10044
10437
  "qwen/qwen3-235b-a22b-thinking-2507": {
10045
10438
  id: "qwen/qwen3-235b-a22b-thinking-2507",
@@ -10050,13 +10443,13 @@ export const MODELS = {
10050
10443
  reasoning: true,
10051
10444
  input: ["text"],
10052
10445
  cost: {
10053
- input: 0.13,
10054
- output: 0.6,
10446
+ input: 0.14950000000000002,
10447
+ output: 1.495,
10055
10448
  cacheRead: 0,
10056
10449
  cacheWrite: 0,
10057
10450
  },
10058
- contextWindow: 262144,
10059
- maxTokens: 262144,
10451
+ contextWindow: 131072,
10452
+ maxTokens: 4096,
10060
10453
  },
10061
10454
  "qwen/qwen3-30b-a3b": {
10062
10455
  id: "qwen/qwen3-30b-a3b",
@@ -10073,7 +10466,7 @@ export const MODELS = {
10073
10466
  cacheWrite: 0,
10074
10467
  },
10075
10468
  contextWindow: 40960,
10076
- maxTokens: 40960,
10469
+ maxTokens: 16384,
10077
10470
  },
10078
10471
  "qwen/qwen3-30b-a3b-instruct-2507": {
10079
10472
  id: "qwen/qwen3-30b-a3b-instruct-2507",
@@ -10153,12 +10546,12 @@ export const MODELS = {
10153
10546
  input: ["text"],
10154
10547
  cost: {
10155
10548
  input: 0.22,
10156
- output: 1,
10157
- cacheRead: 0.022,
10549
+ output: 1.7999999999999998,
10550
+ cacheRead: 0,
10158
10551
  cacheWrite: 0,
10159
10552
  },
10160
10553
  contextWindow: 262144,
10161
- maxTokens: 4096,
10554
+ maxTokens: 65536,
10162
10555
  },
10163
10556
  "qwen/qwen3-coder-30b-a3b-instruct": {
10164
10557
  id: "qwen/qwen3-coder-30b-a3b-instruct",
@@ -10203,9 +10596,9 @@ export const MODELS = {
10203
10596
  reasoning: false,
10204
10597
  input: ["text"],
10205
10598
  cost: {
10206
- input: 0.15,
10599
+ input: 0.14,
10207
10600
  output: 0.7999999999999999,
10208
- cacheRead: 0.11,
10601
+ cacheRead: 0.09,
10209
10602
  cacheWrite: 0,
10210
10603
  },
10211
10604
  contextWindow: 262144,
@@ -10294,7 +10687,7 @@ export const MODELS = {
10294
10687
  cacheWrite: 0,
10295
10688
  },
10296
10689
  contextWindow: 262144,
10297
- maxTokens: 4096,
10690
+ maxTokens: 16384,
10298
10691
  },
10299
10692
  "qwen/qwen3-next-80b-a3b-instruct:free": {
10300
10693
  id: "qwen/qwen3-next-80b-a3b-instruct:free",
@@ -10345,7 +10738,7 @@ export const MODELS = {
10345
10738
  cacheWrite: 0,
10346
10739
  },
10347
10740
  contextWindow: 262144,
10348
- maxTokens: 4096,
10741
+ maxTokens: 16384,
10349
10742
  },
10350
10743
  "qwen/qwen3-vl-235b-a22b-thinking": {
10351
10744
  id: "qwen/qwen3-vl-235b-a22b-thinking",
@@ -10568,9 +10961,26 @@ export const MODELS = {
10568
10961
  contextWindow: 1000000,
10569
10962
  maxTokens: 65536,
10570
10963
  },
10571
- "qwen/qwen3.6-plus": {
10572
- id: "qwen/qwen3.6-plus",
10573
- name: "Qwen: Qwen3.6 Plus",
10964
+ "qwen/qwen3.5-plus-20260420": {
10965
+ id: "qwen/qwen3.5-plus-20260420",
10966
+ name: "Qwen: Qwen3.5 Plus 2026-04-20",
10967
+ api: "openai-completions",
10968
+ provider: "openrouter",
10969
+ baseUrl: "https://openrouter.ai/api/v1",
10970
+ reasoning: true,
10971
+ input: ["text", "image"],
10972
+ cost: {
10973
+ input: 0.39999999999999997,
10974
+ output: 2.4,
10975
+ cacheRead: 0,
10976
+ cacheWrite: 0,
10977
+ },
10978
+ contextWindow: 1000000,
10979
+ maxTokens: 65536,
10980
+ },
10981
+ "qwen/qwen3.6-27b": {
10982
+ id: "qwen/qwen3.6-27b",
10983
+ name: "Qwen: Qwen3.6 27B",
10574
10984
  api: "openai-completions",
10575
10985
  provider: "openrouter",
10576
10986
  baseUrl: "https://openrouter.ai/api/v1",
@@ -10578,29 +10988,63 @@ export const MODELS = {
10578
10988
  input: ["text", "image"],
10579
10989
  cost: {
10580
10990
  input: 0.325,
10581
- output: 1.95,
10991
+ output: 3.25,
10582
10992
  cacheRead: 0,
10583
- cacheWrite: 0.40625,
10993
+ cacheWrite: 0,
10994
+ },
10995
+ contextWindow: 256000,
10996
+ maxTokens: 65536,
10997
+ },
10998
+ "qwen/qwen3.6-flash": {
10999
+ id: "qwen/qwen3.6-flash",
11000
+ name: "Qwen: Qwen3.6 Flash",
11001
+ api: "openai-completions",
11002
+ provider: "openrouter",
11003
+ baseUrl: "https://openrouter.ai/api/v1",
11004
+ reasoning: true,
11005
+ input: ["text", "image"],
11006
+ cost: {
11007
+ input: 0.25,
11008
+ output: 1.5,
11009
+ cacheRead: 0,
11010
+ cacheWrite: 0.3125,
10584
11011
  },
10585
11012
  contextWindow: 1000000,
10586
11013
  maxTokens: 65536,
10587
11014
  },
10588
- "qwen/qwq-32b": {
10589
- id: "qwen/qwq-32b",
10590
- name: "Qwen: QwQ 32B",
11015
+ "qwen/qwen3.6-max-preview": {
11016
+ id: "qwen/qwen3.6-max-preview",
11017
+ name: "Qwen: Qwen3.6 Max Preview",
10591
11018
  api: "openai-completions",
10592
11019
  provider: "openrouter",
10593
11020
  baseUrl: "https://openrouter.ai/api/v1",
10594
11021
  reasoning: true,
10595
11022
  input: ["text"],
10596
11023
  cost: {
10597
- input: 0.15,
10598
- output: 0.58,
11024
+ input: 1.04,
11025
+ output: 6.24,
10599
11026
  cacheRead: 0,
10600
- cacheWrite: 0,
11027
+ cacheWrite: 1.3,
10601
11028
  },
10602
- contextWindow: 131072,
10603
- maxTokens: 131072,
11029
+ contextWindow: 262144,
11030
+ maxTokens: 65536,
11031
+ },
11032
+ "qwen/qwen3.6-plus": {
11033
+ id: "qwen/qwen3.6-plus",
11034
+ name: "Qwen: Qwen3.6 Plus",
11035
+ api: "openai-completions",
11036
+ provider: "openrouter",
11037
+ baseUrl: "https://openrouter.ai/api/v1",
11038
+ reasoning: true,
11039
+ input: ["text", "image"],
11040
+ cost: {
11041
+ input: 0.325,
11042
+ output: 1.95,
11043
+ cacheRead: 0,
11044
+ cacheWrite: 0.40625,
11045
+ },
11046
+ contextWindow: 1000000,
11047
+ maxTokens: 65536,
10604
11048
  },
10605
11049
  "rekaai/reka-edge": {
10606
11050
  id: "rekaai/reka-edge",
@@ -10687,6 +11131,23 @@ export const MODELS = {
10687
11131
  contextWindow: 262144,
10688
11132
  maxTokens: 65536,
10689
11133
  },
11134
+ "tencent/hy3-preview:free": {
11135
+ id: "tencent/hy3-preview:free",
11136
+ name: "Tencent: Hy3 preview (free)",
11137
+ api: "openai-completions",
11138
+ provider: "openrouter",
11139
+ baseUrl: "https://openrouter.ai/api/v1",
11140
+ reasoning: true,
11141
+ input: ["text"],
11142
+ cost: {
11143
+ input: 0,
11144
+ output: 0,
11145
+ cacheRead: 0,
11146
+ cacheWrite: 0,
11147
+ },
11148
+ contextWindow: 262144,
11149
+ maxTokens: 262144,
11150
+ },
10690
11151
  "thedrummer/rocinante-12b": {
10691
11152
  id: "thedrummer/rocinante-12b",
10692
11153
  name: "TheDrummer: Rocinante 12B",
@@ -10908,26 +11369,60 @@ export const MODELS = {
10908
11369
  contextWindow: 256000,
10909
11370
  maxTokens: 10000,
10910
11371
  },
10911
- "xiaomi/mimo-v2-flash": {
10912
- id: "xiaomi/mimo-v2-flash",
10913
- name: "Xiaomi: MiMo-V2-Flash",
11372
+ "xiaomi/mimo-v2-flash": {
11373
+ id: "xiaomi/mimo-v2-flash",
11374
+ name: "Xiaomi: MiMo-V2-Flash",
11375
+ api: "openai-completions",
11376
+ provider: "openrouter",
11377
+ baseUrl: "https://openrouter.ai/api/v1",
11378
+ reasoning: true,
11379
+ input: ["text"],
11380
+ cost: {
11381
+ input: 0.09,
11382
+ output: 0.29,
11383
+ cacheRead: 0.045,
11384
+ cacheWrite: 0,
11385
+ },
11386
+ contextWindow: 262144,
11387
+ maxTokens: 65536,
11388
+ },
11389
+ "xiaomi/mimo-v2-omni": {
11390
+ id: "xiaomi/mimo-v2-omni",
11391
+ name: "Xiaomi: MiMo-V2-Omni",
11392
+ api: "openai-completions",
11393
+ provider: "openrouter",
11394
+ baseUrl: "https://openrouter.ai/api/v1",
11395
+ reasoning: true,
11396
+ input: ["text", "image"],
11397
+ cost: {
11398
+ input: 0.39999999999999997,
11399
+ output: 2,
11400
+ cacheRead: 0.08,
11401
+ cacheWrite: 0,
11402
+ },
11403
+ contextWindow: 262144,
11404
+ maxTokens: 65536,
11405
+ },
11406
+ "xiaomi/mimo-v2-pro": {
11407
+ id: "xiaomi/mimo-v2-pro",
11408
+ name: "Xiaomi: MiMo-V2-Pro",
10914
11409
  api: "openai-completions",
10915
11410
  provider: "openrouter",
10916
11411
  baseUrl: "https://openrouter.ai/api/v1",
10917
11412
  reasoning: true,
10918
11413
  input: ["text"],
10919
11414
  cost: {
10920
- input: 0.09,
10921
- output: 0.29,
10922
- cacheRead: 0.045,
11415
+ input: 1,
11416
+ output: 3,
11417
+ cacheRead: 0.19999999999999998,
10923
11418
  cacheWrite: 0,
10924
11419
  },
10925
- contextWindow: 262144,
10926
- maxTokens: 65536,
11420
+ contextWindow: 1048576,
11421
+ maxTokens: 131072,
10927
11422
  },
10928
- "xiaomi/mimo-v2-omni": {
10929
- id: "xiaomi/mimo-v2-omni",
10930
- name: "Xiaomi: MiMo-V2-Omni",
11423
+ "xiaomi/mimo-v2.5": {
11424
+ id: "xiaomi/mimo-v2.5",
11425
+ name: "Xiaomi: MiMo-V2.5",
10931
11426
  api: "openai-completions",
10932
11427
  provider: "openrouter",
10933
11428
  baseUrl: "https://openrouter.ai/api/v1",
@@ -10939,12 +11434,12 @@ export const MODELS = {
10939
11434
  cacheRead: 0.08,
10940
11435
  cacheWrite: 0,
10941
11436
  },
10942
- contextWindow: 262144,
10943
- maxTokens: 65536,
11437
+ contextWindow: 1048576,
11438
+ maxTokens: 131072,
10944
11439
  },
10945
- "xiaomi/mimo-v2-pro": {
10946
- id: "xiaomi/mimo-v2-pro",
10947
- name: "Xiaomi: MiMo-V2-Pro",
11440
+ "xiaomi/mimo-v2.5-pro": {
11441
+ id: "xiaomi/mimo-v2.5-pro",
11442
+ name: "Xiaomi: MiMo-V2.5-Pro",
10948
11443
  api: "openai-completions",
10949
11444
  provider: "openrouter",
10950
11445
  baseUrl: "https://openrouter.ai/api/v1",
@@ -11072,11 +11567,11 @@ export const MODELS = {
11072
11567
  cost: {
11073
11568
  input: 0.3,
11074
11569
  output: 0.8999999999999999,
11075
- cacheRead: 0,
11570
+ cacheRead: 0.049999999999999996,
11076
11571
  cacheWrite: 0,
11077
11572
  },
11078
11573
  contextWindow: 131072,
11079
- maxTokens: 131072,
11574
+ maxTokens: 24000,
11080
11575
  },
11081
11576
  "z-ai/glm-4.7": {
11082
11577
  id: "z-ai/glm-4.7",
@@ -11106,11 +11601,11 @@ export const MODELS = {
11106
11601
  cost: {
11107
11602
  input: 0.06,
11108
11603
  output: 0.39999999999999997,
11109
- cacheRead: 0.0100000002,
11604
+ cacheRead: 0.01,
11110
11605
  cacheWrite: 0,
11111
11606
  },
11112
11607
  contextWindow: 202752,
11113
- maxTokens: 4096,
11608
+ maxTokens: 16384,
11114
11609
  },
11115
11610
  "z-ai/glm-5": {
11116
11611
  id: "z-ai/glm-5",
@@ -11121,13 +11616,13 @@ export const MODELS = {
11121
11616
  reasoning: true,
11122
11617
  input: ["text"],
11123
11618
  cost: {
11124
- input: 0.65,
11619
+ input: 0.6,
11125
11620
  output: 2.08,
11126
- cacheRead: 0.13,
11621
+ cacheRead: 0.12,
11127
11622
  cacheWrite: 0,
11128
11623
  },
11129
11624
  contextWindow: 202752,
11130
- maxTokens: 4096,
11625
+ maxTokens: 16384,
11131
11626
  },
11132
11627
  "z-ai/glm-5-turbo": {
11133
11628
  id: "z-ai/glm-5-turbo",
@@ -11180,6 +11675,23 @@ export const MODELS = {
11180
11675
  contextWindow: 202752,
11181
11676
  maxTokens: 131072,
11182
11677
  },
11678
+ "~anthropic/claude-haiku-latest": {
11679
+ id: "~anthropic/claude-haiku-latest",
11680
+ name: "Anthropic Claude Haiku Latest",
11681
+ api: "openai-completions",
11682
+ provider: "openrouter",
11683
+ baseUrl: "https://openrouter.ai/api/v1",
11684
+ reasoning: true,
11685
+ input: ["text", "image"],
11686
+ cost: {
11687
+ input: 1,
11688
+ output: 5,
11689
+ cacheRead: 0.09999999999999999,
11690
+ cacheWrite: 1.25,
11691
+ },
11692
+ contextWindow: 200000,
11693
+ maxTokens: 64000,
11694
+ },
11183
11695
  "~anthropic/claude-opus-latest": {
11184
11696
  id: "~anthropic/claude-opus-latest",
11185
11697
  name: "Anthropic: Claude Opus Latest",
@@ -11197,6 +11709,108 @@ export const MODELS = {
11197
11709
  contextWindow: 1000000,
11198
11710
  maxTokens: 128000,
11199
11711
  },
11712
+ "~anthropic/claude-sonnet-latest": {
11713
+ id: "~anthropic/claude-sonnet-latest",
11714
+ name: "Anthropic Claude Sonnet Latest",
11715
+ api: "openai-completions",
11716
+ provider: "openrouter",
11717
+ baseUrl: "https://openrouter.ai/api/v1",
11718
+ reasoning: true,
11719
+ input: ["text", "image"],
11720
+ cost: {
11721
+ input: 3,
11722
+ output: 15,
11723
+ cacheRead: 0.3,
11724
+ cacheWrite: 3.75,
11725
+ },
11726
+ contextWindow: 1000000,
11727
+ maxTokens: 128000,
11728
+ },
11729
+ "~google/gemini-flash-latest": {
11730
+ id: "~google/gemini-flash-latest",
11731
+ name: "Google Gemini Flash Latest",
11732
+ api: "openai-completions",
11733
+ provider: "openrouter",
11734
+ baseUrl: "https://openrouter.ai/api/v1",
11735
+ reasoning: true,
11736
+ input: ["text", "image"],
11737
+ cost: {
11738
+ input: 0.5,
11739
+ output: 3,
11740
+ cacheRead: 0.049999999999999996,
11741
+ cacheWrite: 0.08333333333333334,
11742
+ },
11743
+ contextWindow: 1048576,
11744
+ maxTokens: 65536,
11745
+ },
11746
+ "~google/gemini-pro-latest": {
11747
+ id: "~google/gemini-pro-latest",
11748
+ name: "Google Gemini Pro Latest",
11749
+ api: "openai-completions",
11750
+ provider: "openrouter",
11751
+ baseUrl: "https://openrouter.ai/api/v1",
11752
+ reasoning: true,
11753
+ input: ["text", "image"],
11754
+ cost: {
11755
+ input: 2,
11756
+ output: 12,
11757
+ cacheRead: 0.19999999999999998,
11758
+ cacheWrite: 0.375,
11759
+ },
11760
+ contextWindow: 1048576,
11761
+ maxTokens: 65536,
11762
+ },
11763
+ "~moonshotai/kimi-latest": {
11764
+ id: "~moonshotai/kimi-latest",
11765
+ name: "MoonshotAI Kimi Latest",
11766
+ api: "openai-completions",
11767
+ provider: "openrouter",
11768
+ baseUrl: "https://openrouter.ai/api/v1",
11769
+ reasoning: true,
11770
+ input: ["text", "image"],
11771
+ cost: {
11772
+ input: 0.74,
11773
+ output: 3.49,
11774
+ cacheRead: 0.14,
11775
+ cacheWrite: 0,
11776
+ },
11777
+ contextWindow: 262142,
11778
+ maxTokens: 262142,
11779
+ },
11780
+ "~openai/gpt-latest": {
11781
+ id: "~openai/gpt-latest",
11782
+ name: "OpenAI GPT Latest",
11783
+ api: "openai-completions",
11784
+ provider: "openrouter",
11785
+ baseUrl: "https://openrouter.ai/api/v1",
11786
+ reasoning: true,
11787
+ input: ["text", "image"],
11788
+ cost: {
11789
+ input: 5,
11790
+ output: 30,
11791
+ cacheRead: 0.5,
11792
+ cacheWrite: 0,
11793
+ },
11794
+ contextWindow: 1050000,
11795
+ maxTokens: 128000,
11796
+ },
11797
+ "~openai/gpt-mini-latest": {
11798
+ id: "~openai/gpt-mini-latest",
11799
+ name: "OpenAI GPT Mini Latest",
11800
+ api: "openai-completions",
11801
+ provider: "openrouter",
11802
+ baseUrl: "https://openrouter.ai/api/v1",
11803
+ reasoning: true,
11804
+ input: ["text", "image"],
11805
+ cost: {
11806
+ input: 0.75,
11807
+ output: 4.5,
11808
+ cacheRead: 0.075,
11809
+ cacheWrite: 0,
11810
+ },
11811
+ contextWindow: 400000,
11812
+ maxTokens: 128000,
11813
+ },
11200
11814
  },
11201
11815
  "vercel-ai-gateway": {
11202
11816
  "alibaba/qwen-3-14b": {
@@ -11286,20 +11900,20 @@ export const MODELS = {
11286
11900
  },
11287
11901
  "alibaba/qwen3-235b-a22b-thinking": {
11288
11902
  id: "alibaba/qwen3-235b-a22b-thinking",
11289
- name: "Qwen3 235B A22B Thinking 2507",
11903
+ name: "Qwen3 VL 235B A22B Thinking",
11290
11904
  api: "anthropic-messages",
11291
11905
  provider: "vercel-ai-gateway",
11292
11906
  baseUrl: "https://ai-gateway.vercel.sh",
11293
11907
  reasoning: true,
11294
11908
  input: ["text", "image"],
11295
11909
  cost: {
11296
- input: 0.22999999999999998,
11297
- output: 2.3,
11298
- cacheRead: 0.19999999999999998,
11910
+ input: 0.39999999999999997,
11911
+ output: 4,
11912
+ cacheRead: 0,
11299
11913
  cacheWrite: 0,
11300
11914
  },
11301
- contextWindow: 262114,
11302
- maxTokens: 262114,
11915
+ contextWindow: 131072,
11916
+ maxTokens: 32768,
11303
11917
  },
11304
11918
  "alibaba/qwen3-coder": {
11305
11919
  id: "alibaba/qwen3-coder",
@@ -11471,6 +12085,23 @@ export const MODELS = {
11471
12085
  contextWindow: 1000000,
11472
12086
  maxTokens: 64000,
11473
12087
  },
12088
+ "alibaba/qwen3.6-27b": {
12089
+ id: "alibaba/qwen3.6-27b",
12090
+ name: "Qwen 3.6 27B",
12091
+ api: "anthropic-messages",
12092
+ provider: "vercel-ai-gateway",
12093
+ baseUrl: "https://ai-gateway.vercel.sh",
12094
+ reasoning: true,
12095
+ input: ["text", "image"],
12096
+ cost: {
12097
+ input: 0.6,
12098
+ output: 3.5999999999999996,
12099
+ cacheRead: 0,
12100
+ cacheWrite: 0,
12101
+ },
12102
+ contextWindow: 256000,
12103
+ maxTokens: 256000,
12104
+ },
11474
12105
  "alibaba/qwen3.6-plus": {
11475
12106
  id: "alibaba/qwen3.6-plus",
11476
12107
  name: "Qwen 3.6 Plus",
@@ -11483,7 +12114,7 @@ export const MODELS = {
11483
12114
  input: 0.5,
11484
12115
  output: 3,
11485
12116
  cacheRead: 0.09999999999999999,
11486
- cacheWrite: 0,
12117
+ cacheWrite: 0.625,
11487
12118
  },
11488
12119
  contextWindow: 1000000,
11489
12120
  maxTokens: 64000,
@@ -11851,16 +12482,50 @@ export const MODELS = {
11851
12482
  api: "anthropic-messages",
11852
12483
  provider: "vercel-ai-gateway",
11853
12484
  baseUrl: "https://ai-gateway.vercel.sh",
11854
- reasoning: true,
12485
+ reasoning: false,
11855
12486
  input: ["text"],
11856
12487
  cost: {
11857
- input: 0.28,
11858
- output: 0.42,
11859
- cacheRead: 0.028,
12488
+ input: 0.62,
12489
+ output: 1.85,
12490
+ cacheRead: 0,
11860
12491
  cacheWrite: 0,
11861
12492
  },
11862
12493
  contextWindow: 128000,
11863
- maxTokens: 64000,
12494
+ maxTokens: 8000,
12495
+ },
12496
+ "deepseek/deepseek-v4-flash": {
12497
+ id: "deepseek/deepseek-v4-flash",
12498
+ name: "DeepSeek V4 Flash",
12499
+ api: "anthropic-messages",
12500
+ provider: "vercel-ai-gateway",
12501
+ baseUrl: "https://ai-gateway.vercel.sh",
12502
+ reasoning: true,
12503
+ input: ["text"],
12504
+ cost: {
12505
+ input: 0.14,
12506
+ output: 0.28,
12507
+ cacheRead: 0.0028,
12508
+ cacheWrite: 0,
12509
+ },
12510
+ contextWindow: 1000000,
12511
+ maxTokens: 384000,
12512
+ },
12513
+ "deepseek/deepseek-v4-pro": {
12514
+ id: "deepseek/deepseek-v4-pro",
12515
+ name: "DeepSeek V4 Pro",
12516
+ api: "anthropic-messages",
12517
+ provider: "vercel-ai-gateway",
12518
+ baseUrl: "https://ai-gateway.vercel.sh",
12519
+ reasoning: true,
12520
+ input: ["text"],
12521
+ cost: {
12522
+ input: 0.435,
12523
+ output: 0.87,
12524
+ cacheRead: 0.0036,
12525
+ cacheWrite: 0,
12526
+ },
12527
+ contextWindow: 1000000,
12528
+ maxTokens: 384000,
11864
12529
  },
11865
12530
  "google/gemini-2.0-flash": {
11866
12531
  id: "google/gemini-2.0-flash",
@@ -13137,6 +13802,40 @@ export const MODELS = {
13137
13802
  contextWindow: 1050000,
13138
13803
  maxTokens: 128000,
13139
13804
  },
13805
+ "openai/gpt-5.5": {
13806
+ id: "openai/gpt-5.5",
13807
+ name: "GPT 5.5",
13808
+ api: "anthropic-messages",
13809
+ provider: "vercel-ai-gateway",
13810
+ baseUrl: "https://ai-gateway.vercel.sh",
13811
+ reasoning: true,
13812
+ input: ["text", "image"],
13813
+ cost: {
13814
+ input: 5,
13815
+ output: 30,
13816
+ cacheRead: 0.5,
13817
+ cacheWrite: 0,
13818
+ },
13819
+ contextWindow: 1000000,
13820
+ maxTokens: 128000,
13821
+ },
13822
+ "openai/gpt-5.5-pro": {
13823
+ id: "openai/gpt-5.5-pro",
13824
+ name: "GPT 5.5 Pro",
13825
+ api: "anthropic-messages",
13826
+ provider: "vercel-ai-gateway",
13827
+ baseUrl: "https://ai-gateway.vercel.sh",
13828
+ reasoning: true,
13829
+ input: ["text", "image"],
13830
+ cost: {
13831
+ input: 30,
13832
+ output: 180,
13833
+ cacheRead: 0,
13834
+ cacheWrite: 0,
13835
+ },
13836
+ contextWindow: 1000000,
13837
+ maxTokens: 128000,
13838
+ },
13140
13839
  "openai/gpt-oss-20b": {
13141
13840
  id: "openai/gpt-oss-20b",
13142
13841
  name: "GPT OSS 120B",
@@ -13605,9 +14304,9 @@ export const MODELS = {
13605
14304
  reasoning: true,
13606
14305
  input: ["text"],
13607
14306
  cost: {
13608
- input: 0.09,
13609
- output: 0.29,
13610
- cacheRead: 0.045,
14307
+ input: 0.09999999999999999,
14308
+ output: 0.3,
14309
+ cacheRead: 0.01,
13611
14310
  cacheWrite: 0,
13612
14311
  },
13613
14312
  contextWindow: 262144,
@@ -13630,6 +14329,40 @@ export const MODELS = {
13630
14329
  contextWindow: 1000000,
13631
14330
  maxTokens: 128000,
13632
14331
  },
14332
+ "xiaomi/mimo-v2.5": {
14333
+ id: "xiaomi/mimo-v2.5",
14334
+ name: "MiMo M2.5",
14335
+ api: "anthropic-messages",
14336
+ provider: "vercel-ai-gateway",
14337
+ baseUrl: "https://ai-gateway.vercel.sh",
14338
+ reasoning: true,
14339
+ input: ["text", "image"],
14340
+ cost: {
14341
+ input: 0.39999999999999997,
14342
+ output: 2,
14343
+ cacheRead: 0.08,
14344
+ cacheWrite: 0,
14345
+ },
14346
+ contextWindow: 1050000,
14347
+ maxTokens: 131100,
14348
+ },
14349
+ "xiaomi/mimo-v2.5-pro": {
14350
+ id: "xiaomi/mimo-v2.5-pro",
14351
+ name: "MiMo V2.5 Pro",
14352
+ api: "anthropic-messages",
14353
+ provider: "vercel-ai-gateway",
14354
+ baseUrl: "https://ai-gateway.vercel.sh",
14355
+ reasoning: true,
14356
+ input: ["text", "image"],
14357
+ cost: {
14358
+ input: 1,
14359
+ output: 3,
14360
+ cacheRead: 0.19999999999999998,
14361
+ cacheWrite: 0,
14362
+ },
14363
+ contextWindow: 1050000,
14364
+ maxTokens: 131000,
14365
+ },
13633
14366
  "zai/glm-4.5": {
13634
14367
  id: "zai/glm-4.5",
13635
14368
  name: "GLM-4.5",
@@ -13824,15 +14557,15 @@ export const MODELS = {
13824
14557
  provider: "vercel-ai-gateway",
13825
14558
  baseUrl: "https://ai-gateway.vercel.sh",
13826
14559
  reasoning: true,
13827
- input: ["text", "image"],
14560
+ input: ["text"],
13828
14561
  cost: {
13829
14562
  input: 1.4,
13830
14563
  output: 4.4,
13831
14564
  cacheRead: 0.26,
13832
14565
  cacheWrite: 0,
13833
14566
  },
13834
- contextWindow: 202752,
13835
- maxTokens: 202752,
14567
+ contextWindow: 202800,
14568
+ maxTokens: 64000,
13836
14569
  },
13837
14570
  "zai/glm-5v-turbo": {
13838
14571
  id: "zai/glm-5v-turbo",