@dreb/ai 2.12.0 → 2.13.0

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",
@@ -6776,9 +6948,9 @@ export const MODELS = {
6776
6948
  "qwen3.5-plus": {
6777
6949
  id: "qwen3.5-plus",
6778
6950
  name: "Qwen3.5 Plus",
6779
- api: "openai-completions",
6951
+ api: "anthropic-messages",
6780
6952
  provider: "opencode",
6781
- baseUrl: "https://opencode.ai/zen/v1",
6953
+ baseUrl: "https://opencode.ai/zen",
6782
6954
  reasoning: true,
6783
6955
  input: ["text", "image"],
6784
6956
  cost: {
@@ -6793,9 +6965,9 @@ export const MODELS = {
6793
6965
  "qwen3.6-plus": {
6794
6966
  id: "qwen3.6-plus",
6795
6967
  name: "Qwen3.6 Plus",
6796
- api: "openai-completions",
6968
+ api: "anthropic-messages",
6797
6969
  provider: "opencode",
6798
- baseUrl: "https://opencode.ai/zen/v1",
6970
+ baseUrl: "https://opencode.ai/zen",
6799
6971
  reasoning: true,
6800
6972
  input: ["text", "image"],
6801
6973
  cost: {
@@ -6809,6 +6981,40 @@ export const MODELS = {
6809
6981
  },
6810
6982
  },
6811
6983
  "opencode-go": {
6984
+ "deepseek-v4-flash": {
6985
+ id: "deepseek-v4-flash",
6986
+ name: "DeepSeek V4 Flash",
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: 0.14,
6994
+ output: 0.28,
6995
+ cacheRead: 0.0028,
6996
+ cacheWrite: 0,
6997
+ },
6998
+ contextWindow: 1000000,
6999
+ maxTokens: 384000,
7000
+ },
7001
+ "deepseek-v4-pro": {
7002
+ id: "deepseek-v4-pro",
7003
+ name: "DeepSeek V4 Pro",
7004
+ api: "openai-completions",
7005
+ provider: "opencode-go",
7006
+ baseUrl: "https://opencode.ai/zen/go/v1",
7007
+ reasoning: true,
7008
+ input: ["text"],
7009
+ cost: {
7010
+ input: 1.74,
7011
+ output: 3.48,
7012
+ cacheRead: 0.0145,
7013
+ cacheWrite: 0,
7014
+ },
7015
+ contextWindow: 1000000,
7016
+ maxTokens: 384000,
7017
+ },
6812
7018
  "glm-5": {
6813
7019
  id: "glm-5",
6814
7020
  name: "GLM-5",
@@ -6823,8 +7029,8 @@ export const MODELS = {
6823
7029
  cacheRead: 0.2,
6824
7030
  cacheWrite: 0,
6825
7031
  },
6826
- contextWindow: 204800,
6827
- maxTokens: 131072,
7032
+ contextWindow: 202752,
7033
+ maxTokens: 32768,
6828
7034
  },
6829
7035
  "glm-5.1": {
6830
7036
  id: "glm-5.1",
@@ -6840,8 +7046,8 @@ export const MODELS = {
6840
7046
  cacheRead: 0.26,
6841
7047
  cacheWrite: 0,
6842
7048
  },
6843
- contextWindow: 204800,
6844
- maxTokens: 131072,
7049
+ contextWindow: 202752,
7050
+ maxTokens: 32768,
6845
7051
  },
6846
7052
  "kimi-k2.5": {
6847
7053
  id: "kimi-k2.5",
@@ -6892,7 +7098,7 @@ export const MODELS = {
6892
7098
  cacheWrite: 0,
6893
7099
  },
6894
7100
  contextWindow: 262144,
6895
- maxTokens: 64000,
7101
+ maxTokens: 128000,
6896
7102
  },
6897
7103
  "mimo-v2-pro": {
6898
7104
  id: "mimo-v2-pro",
@@ -6909,7 +7115,41 @@ export const MODELS = {
6909
7115
  cacheWrite: 0,
6910
7116
  },
6911
7117
  contextWindow: 1048576,
6912
- maxTokens: 64000,
7118
+ maxTokens: 128000,
7119
+ },
7120
+ "mimo-v2.5": {
7121
+ id: "mimo-v2.5",
7122
+ name: "MiMo V2.5",
7123
+ api: "openai-completions",
7124
+ provider: "opencode-go",
7125
+ baseUrl: "https://opencode.ai/zen/go/v1",
7126
+ reasoning: true,
7127
+ input: ["text", "image"],
7128
+ cost: {
7129
+ input: 0.4,
7130
+ output: 2,
7131
+ cacheRead: 0.08,
7132
+ cacheWrite: 0,
7133
+ },
7134
+ contextWindow: 1000000,
7135
+ maxTokens: 128000,
7136
+ },
7137
+ "mimo-v2.5-pro": {
7138
+ id: "mimo-v2.5-pro",
7139
+ name: "MiMo V2.5 Pro",
7140
+ api: "openai-completions",
7141
+ provider: "opencode-go",
7142
+ baseUrl: "https://opencode.ai/zen/go/v1",
7143
+ reasoning: true,
7144
+ input: ["text"],
7145
+ cost: {
7146
+ input: 1,
7147
+ output: 3,
7148
+ cacheRead: 0.2,
7149
+ cacheWrite: 0,
7150
+ },
7151
+ contextWindow: 1048576,
7152
+ maxTokens: 128000,
6913
7153
  },
6914
7154
  "minimax-m2.5": {
6915
7155
  id: "minimax-m2.5",
@@ -6948,9 +7188,9 @@ export const MODELS = {
6948
7188
  "qwen3.5-plus": {
6949
7189
  id: "qwen3.5-plus",
6950
7190
  name: "Qwen3.5 Plus",
6951
- api: "openai-completions",
7191
+ api: "anthropic-messages",
6952
7192
  provider: "opencode-go",
6953
- baseUrl: "https://opencode.ai/zen/go/v1",
7193
+ baseUrl: "https://opencode.ai/zen/go",
6954
7194
  reasoning: true,
6955
7195
  input: ["text", "image"],
6956
7196
  cost: {
@@ -6965,9 +7205,9 @@ export const MODELS = {
6965
7205
  "qwen3.6-plus": {
6966
7206
  id: "qwen3.6-plus",
6967
7207
  name: "Qwen3.6 Plus",
6968
- api: "openai-completions",
7208
+ api: "anthropic-messages",
6969
7209
  provider: "opencode-go",
6970
- baseUrl: "https://opencode.ai/zen/go/v1",
7210
+ baseUrl: "https://opencode.ai/zen/go",
6971
7211
  reasoning: true,
6972
7212
  input: ["text", "image"],
6973
7213
  cost: {
@@ -7030,7 +7270,7 @@ export const MODELS = {
7030
7270
  cacheWrite: 0,
7031
7271
  },
7032
7272
  contextWindow: 65536,
7033
- maxTokens: 4096,
7273
+ maxTokens: 16384,
7034
7274
  },
7035
7275
  "amazon/nova-2-lite-v1": {
7036
7276
  id: "amazon/nova-2-lite-v1",
@@ -7355,17 +7595,17 @@ export const MODELS = {
7355
7595
  contextWindow: 1000000,
7356
7596
  maxTokens: 128000,
7357
7597
  },
7358
- "arcee-ai/trinity-large-preview:free": {
7359
- id: "arcee-ai/trinity-large-preview:free",
7360
- name: "Arcee AI: Trinity Large Preview (free)",
7598
+ "arcee-ai/trinity-large-preview": {
7599
+ id: "arcee-ai/trinity-large-preview",
7600
+ name: "Arcee AI: Trinity Large Preview",
7361
7601
  api: "openai-completions",
7362
7602
  provider: "openrouter",
7363
7603
  baseUrl: "https://openrouter.ai/api/v1",
7364
7604
  reasoning: false,
7365
7605
  input: ["text"],
7366
7606
  cost: {
7367
- input: 0,
7368
- output: 0,
7607
+ input: 0.15,
7608
+ output: 0.44999999999999996,
7369
7609
  cacheRead: 0,
7370
7610
  cacheWrite: 0,
7371
7611
  },
@@ -7591,7 +7831,7 @@ export const MODELS = {
7591
7831
  cacheWrite: 0,
7592
7832
  },
7593
7833
  contextWindow: 163840,
7594
- maxTokens: 163840,
7834
+ maxTokens: 16384,
7595
7835
  },
7596
7836
  "deepseek/deepseek-chat-v3-0324": {
7597
7837
  id: "deepseek/deepseek-chat-v3-0324",
@@ -7608,7 +7848,7 @@ export const MODELS = {
7608
7848
  cacheWrite: 0,
7609
7849
  },
7610
7850
  contextWindow: 163840,
7611
- maxTokens: 4096,
7851
+ maxTokens: 16384,
7612
7852
  },
7613
7853
  "deepseek/deepseek-chat-v3.1": {
7614
7854
  id: "deepseek/deepseek-chat-v3.1",
@@ -7659,7 +7899,7 @@ export const MODELS = {
7659
7899
  cacheWrite: 0,
7660
7900
  },
7661
7901
  contextWindow: 163840,
7662
- maxTokens: 4096,
7902
+ maxTokens: 32768,
7663
7903
  },
7664
7904
  "deepseek/deepseek-v3.1-terminus": {
7665
7905
  id: "deepseek/deepseek-v3.1-terminus",
@@ -7672,11 +7912,11 @@ export const MODELS = {
7672
7912
  cost: {
7673
7913
  input: 0.21,
7674
7914
  output: 0.7899999999999999,
7675
- cacheRead: 0.1300000002,
7915
+ cacheRead: 0.13,
7676
7916
  cacheWrite: 0,
7677
7917
  },
7678
7918
  contextWindow: 163840,
7679
- maxTokens: 4096,
7919
+ maxTokens: 32768,
7680
7920
  },
7681
7921
  "deepseek/deepseek-v3.2": {
7682
7922
  id: "deepseek/deepseek-v3.2",
@@ -7693,7 +7933,7 @@ export const MODELS = {
7693
7933
  cacheWrite: 0,
7694
7934
  },
7695
7935
  contextWindow: 131072,
7696
- maxTokens: 32768,
7936
+ maxTokens: 65536,
7697
7937
  },
7698
7938
  "deepseek/deepseek-v3.2-exp": {
7699
7939
  id: "deepseek/deepseek-v3.2-exp",
@@ -7712,6 +7952,40 @@ export const MODELS = {
7712
7952
  contextWindow: 163840,
7713
7953
  maxTokens: 65536,
7714
7954
  },
7955
+ "deepseek/deepseek-v4-flash": {
7956
+ id: "deepseek/deepseek-v4-flash",
7957
+ name: "DeepSeek: DeepSeek V4 Flash",
7958
+ api: "openai-completions",
7959
+ provider: "openrouter",
7960
+ baseUrl: "https://openrouter.ai/api/v1",
7961
+ reasoning: true,
7962
+ input: ["text"],
7963
+ cost: {
7964
+ input: 0.14,
7965
+ output: 0.28,
7966
+ cacheRead: 0.0028,
7967
+ cacheWrite: 0,
7968
+ },
7969
+ contextWindow: 1048576,
7970
+ maxTokens: 384000,
7971
+ },
7972
+ "deepseek/deepseek-v4-pro": {
7973
+ id: "deepseek/deepseek-v4-pro",
7974
+ name: "DeepSeek: DeepSeek V4 Pro",
7975
+ api: "openai-completions",
7976
+ provider: "openrouter",
7977
+ baseUrl: "https://openrouter.ai/api/v1",
7978
+ reasoning: true,
7979
+ input: ["text"],
7980
+ cost: {
7981
+ input: 0.435,
7982
+ output: 0.87,
7983
+ cacheRead: 0.003625,
7984
+ cacheWrite: 0,
7985
+ },
7986
+ contextWindow: 1048576,
7987
+ maxTokens: 384000,
7988
+ },
7715
7989
  "essentialai/rnj-1-instruct": {
7716
7990
  id: "essentialai/rnj-1-instruct",
7717
7991
  name: "EssentialAI: Rnj 1 Instruct",
@@ -7933,6 +8207,40 @@ export const MODELS = {
7933
8207
  contextWindow: 1048576,
7934
8208
  maxTokens: 65536,
7935
8209
  },
8210
+ "google/gemma-3-12b-it": {
8211
+ id: "google/gemma-3-12b-it",
8212
+ name: "Google: Gemma 3 12B",
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: 0.04,
8220
+ output: 0.13,
8221
+ cacheRead: 0,
8222
+ cacheWrite: 0,
8223
+ },
8224
+ contextWindow: 131072,
8225
+ maxTokens: 16384,
8226
+ },
8227
+ "google/gemma-3-27b-it": {
8228
+ id: "google/gemma-3-27b-it",
8229
+ name: "Google: Gemma 3 27B",
8230
+ api: "openai-completions",
8231
+ provider: "openrouter",
8232
+ baseUrl: "https://openrouter.ai/api/v1",
8233
+ reasoning: false,
8234
+ input: ["text", "image"],
8235
+ cost: {
8236
+ input: 0.08,
8237
+ output: 0.16,
8238
+ cacheRead: 0,
8239
+ cacheWrite: 0,
8240
+ },
8241
+ contextWindow: 131072,
8242
+ maxTokens: 16384,
8243
+ },
7936
8244
  "google/gemma-4-26b-a4b-it": {
7937
8245
  id: "google/gemma-4-26b-a4b-it",
7938
8246
  name: "Google: Gemma 4 26B A4B ",
@@ -7942,13 +8250,13 @@ export const MODELS = {
7942
8250
  reasoning: true,
7943
8251
  input: ["text", "image"],
7944
8252
  cost: {
7945
- input: 0.07,
7946
- output: 0.35,
7947
- cacheRead: 0.04,
8253
+ input: 0.06,
8254
+ output: 0.33,
8255
+ cacheRead: 0,
7948
8256
  cacheWrite: 0,
7949
8257
  },
7950
8258
  contextWindow: 262144,
7951
- maxTokens: 262144,
8259
+ maxTokens: 4096,
7952
8260
  },
7953
8261
  "google/gemma-4-26b-a4b-it:free": {
7954
8262
  id: "google/gemma-4-26b-a4b-it:free",
@@ -7978,11 +8286,11 @@ export const MODELS = {
7978
8286
  cost: {
7979
8287
  input: 0.13,
7980
8288
  output: 0.38,
7981
- cacheRead: 0.019999999499999997,
8289
+ cacheRead: 0,
7982
8290
  cacheWrite: 0,
7983
8291
  },
7984
8292
  contextWindow: 262144,
7985
- maxTokens: 4096,
8293
+ maxTokens: 16384,
7986
8294
  },
7987
8295
  "google/gemma-4-31b-it:free": {
7988
8296
  id: "google/gemma-4-31b-it:free",
@@ -8018,6 +8326,40 @@ export const MODELS = {
8018
8326
  contextWindow: 128000,
8019
8327
  maxTokens: 50000,
8020
8328
  },
8329
+ "inclusionai/ling-2.6-1t:free": {
8330
+ id: "inclusionai/ling-2.6-1t:free",
8331
+ name: "inclusionAI: Ling-2.6-1T (free)",
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,
8339
+ output: 0,
8340
+ cacheRead: 0,
8341
+ cacheWrite: 0,
8342
+ },
8343
+ contextWindow: 262144,
8344
+ maxTokens: 32768,
8345
+ },
8346
+ "inclusionai/ling-2.6-flash": {
8347
+ id: "inclusionai/ling-2.6-flash",
8348
+ name: "inclusionAI: Ling-2.6-flash",
8349
+ api: "openai-completions",
8350
+ provider: "openrouter",
8351
+ baseUrl: "https://openrouter.ai/api/v1",
8352
+ reasoning: false,
8353
+ input: ["text"],
8354
+ cost: {
8355
+ input: 0.08,
8356
+ output: 0.24,
8357
+ cacheRead: 0.016,
8358
+ cacheWrite: 0,
8359
+ },
8360
+ contextWindow: 262144,
8361
+ maxTokens: 32768,
8362
+ },
8021
8363
  "inclusionai/ling-2.6-flash:free": {
8022
8364
  id: "inclusionai/ling-2.6-flash:free",
8023
8365
  name: "inclusionAI: Ling-2.6-flash (free)",
@@ -8084,7 +8426,7 @@ export const MODELS = {
8084
8426
  cacheWrite: 0,
8085
8427
  },
8086
8428
  contextWindow: 131072,
8087
- maxTokens: 4096,
8429
+ maxTokens: 16384,
8088
8430
  },
8089
8431
  "meta-llama/llama-3.1-8b-instruct": {
8090
8432
  id: "meta-llama/llama-3.1-8b-instruct",
@@ -8112,13 +8454,13 @@ export const MODELS = {
8112
8454
  reasoning: false,
8113
8455
  input: ["text"],
8114
8456
  cost: {
8115
- input: 0.12,
8116
- output: 0.38,
8457
+ input: 0.09999999999999999,
8458
+ output: 0.32,
8117
8459
  cacheRead: 0,
8118
8460
  cacheWrite: 0,
8119
8461
  },
8120
8462
  contextWindow: 131072,
8121
- maxTokens: 131072,
8463
+ maxTokens: 16384,
8122
8464
  },
8123
8465
  "meta-llama/llama-3.3-70b-instruct:free": {
8124
8466
  id: "meta-llama/llama-3.3-70b-instruct:free",
@@ -8215,12 +8557,12 @@ export const MODELS = {
8215
8557
  input: ["text"],
8216
8558
  cost: {
8217
8559
  input: 0.15,
8218
- output: 1.2,
8219
- cacheRead: 0.075,
8560
+ output: 1.15,
8561
+ cacheRead: 0.03,
8220
8562
  cacheWrite: 0,
8221
8563
  },
8222
8564
  contextWindow: 196608,
8223
- maxTokens: 65536,
8565
+ maxTokens: 131072,
8224
8566
  },
8225
8567
  "minimax/minimax-m2.5:free": {
8226
8568
  id: "minimax/minimax-m2.5:free",
@@ -8543,7 +8885,7 @@ export const MODELS = {
8543
8885
  cacheWrite: 0,
8544
8886
  },
8545
8887
  contextWindow: 128000,
8546
- maxTokens: 4096,
8888
+ maxTokens: 16384,
8547
8889
  },
8548
8890
  "mistralai/mistral-small-creative": {
8549
8891
  id: "mistralai/mistral-small-creative",
@@ -8707,13 +9049,13 @@ export const MODELS = {
8707
9049
  reasoning: true,
8708
9050
  input: ["text", "image"],
8709
9051
  cost: {
8710
- input: 0.6,
8711
- output: 2.8,
8712
- cacheRead: 0.19999999999999998,
9052
+ input: 0.7448,
9053
+ output: 4.655,
9054
+ cacheRead: 0.1463,
8713
9055
  cacheWrite: 0,
8714
9056
  },
8715
- contextWindow: 262144,
8716
- maxTokens: 262144,
9057
+ contextWindow: 256000,
9058
+ maxTokens: 65536,
8717
9059
  },
8718
9060
  "nex-agi/deepseek-v3.1-nex-n1": {
8719
9061
  id: "nex-agi/deepseek-v3.1-nex-n1",
@@ -8764,7 +9106,7 @@ export const MODELS = {
8764
9106
  cacheWrite: 0,
8765
9107
  },
8766
9108
  contextWindow: 131072,
8767
- maxTokens: 4096,
9109
+ maxTokens: 16384,
8768
9110
  },
8769
9111
  "nvidia/nemotron-3-nano-30b-a3b": {
8770
9112
  id: "nvidia/nemotron-3-nano-30b-a3b",
@@ -8781,7 +9123,7 @@ export const MODELS = {
8781
9123
  cacheWrite: 0,
8782
9124
  },
8783
9125
  contextWindow: 262144,
8784
- maxTokens: 4096,
9126
+ maxTokens: 228000,
8785
9127
  },
8786
9128
  "nvidia/nemotron-3-nano-30b-a3b:free": {
8787
9129
  id: "nvidia/nemotron-3-nano-30b-a3b:free",
@@ -8800,6 +9142,23 @@ export const MODELS = {
8800
9142
  contextWindow: 256000,
8801
9143
  maxTokens: 4096,
8802
9144
  },
9145
+ "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free": {
9146
+ id: "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
9147
+ name: "NVIDIA: Nemotron 3 Nano Omni (free)",
9148
+ api: "openai-completions",
9149
+ provider: "openrouter",
9150
+ baseUrl: "https://openrouter.ai/api/v1",
9151
+ reasoning: true,
9152
+ input: ["text", "image"],
9153
+ cost: {
9154
+ input: 0,
9155
+ output: 0,
9156
+ cacheRead: 0,
9157
+ cacheWrite: 0,
9158
+ },
9159
+ contextWindow: 256000,
9160
+ maxTokens: 65536,
9161
+ },
8803
9162
  "nvidia/nemotron-3-super-120b-a12b": {
8804
9163
  id: "nvidia/nemotron-3-super-120b-a12b",
8805
9164
  name: "NVIDIA: Nemotron 3 Super",
@@ -8866,7 +9225,7 @@ export const MODELS = {
8866
9225
  cacheWrite: 0,
8867
9226
  },
8868
9227
  contextWindow: 131072,
8869
- maxTokens: 4096,
9228
+ maxTokens: 16384,
8870
9229
  },
8871
9230
  "nvidia/nemotron-nano-9b-v2:free": {
8872
9231
  id: "nvidia/nemotron-nano-9b-v2:free",
@@ -9225,40 +9584,6 @@ export const MODELS = {
9225
9584
  contextWindow: 400000,
9226
9585
  maxTokens: 128000,
9227
9586
  },
9228
- "openai/gpt-5-image": {
9229
- id: "openai/gpt-5-image",
9230
- name: "OpenAI: GPT-5 Image",
9231
- api: "openai-completions",
9232
- provider: "openrouter",
9233
- baseUrl: "https://openrouter.ai/api/v1",
9234
- reasoning: true,
9235
- input: ["text", "image"],
9236
- cost: {
9237
- input: 10,
9238
- output: 10,
9239
- cacheRead: 1.25,
9240
- cacheWrite: 0,
9241
- },
9242
- contextWindow: 400000,
9243
- maxTokens: 128000,
9244
- },
9245
- "openai/gpt-5-image-mini": {
9246
- id: "openai/gpt-5-image-mini",
9247
- name: "OpenAI: GPT-5 Image Mini",
9248
- api: "openai-completions",
9249
- provider: "openrouter",
9250
- baseUrl: "https://openrouter.ai/api/v1",
9251
- reasoning: true,
9252
- input: ["text", "image"],
9253
- cost: {
9254
- input: 2.5,
9255
- output: 2,
9256
- cacheRead: 0.25,
9257
- cacheWrite: 0,
9258
- },
9259
- contextWindow: 400000,
9260
- maxTokens: 128000,
9261
- },
9262
9587
  "openai/gpt-5-mini": {
9263
9588
  id: "openai/gpt-5-mini",
9264
9589
  name: "OpenAI: GPT-5 Mini",
@@ -9565,6 +9890,40 @@ export const MODELS = {
9565
9890
  contextWindow: 1050000,
9566
9891
  maxTokens: 128000,
9567
9892
  },
9893
+ "openai/gpt-5.5": {
9894
+ id: "openai/gpt-5.5",
9895
+ name: "OpenAI: GPT-5.5",
9896
+ api: "openai-completions",
9897
+ provider: "openrouter",
9898
+ baseUrl: "https://openrouter.ai/api/v1",
9899
+ reasoning: true,
9900
+ input: ["text", "image"],
9901
+ cost: {
9902
+ input: 5,
9903
+ output: 30,
9904
+ cacheRead: 0.5,
9905
+ cacheWrite: 0,
9906
+ },
9907
+ contextWindow: 1050000,
9908
+ maxTokens: 128000,
9909
+ },
9910
+ "openai/gpt-5.5-pro": {
9911
+ id: "openai/gpt-5.5-pro",
9912
+ name: "OpenAI: GPT-5.5 Pro",
9913
+ api: "openai-completions",
9914
+ provider: "openrouter",
9915
+ baseUrl: "https://openrouter.ai/api/v1",
9916
+ reasoning: true,
9917
+ input: ["text", "image"],
9918
+ cost: {
9919
+ input: 30,
9920
+ output: 180,
9921
+ cacheRead: 0,
9922
+ cacheWrite: 0,
9923
+ },
9924
+ contextWindow: 1050000,
9925
+ maxTokens: 128000,
9926
+ },
9568
9927
  "openai/gpt-audio": {
9569
9928
  id: "openai/gpt-audio",
9570
9929
  name: "OpenAI: GPT Audio",
@@ -9614,7 +9973,7 @@ export const MODELS = {
9614
9973
  cacheWrite: 0,
9615
9974
  },
9616
9975
  contextWindow: 131072,
9617
- maxTokens: 4096,
9976
+ maxTokens: 131072,
9618
9977
  },
9619
9978
  "openai/gpt-oss-120b:free": {
9620
9979
  id: "openai/gpt-oss-120b:free",
@@ -9648,7 +10007,7 @@ export const MODELS = {
9648
10007
  cacheWrite: 0,
9649
10008
  },
9650
10009
  contextWindow: 131072,
9651
- maxTokens: 4096,
10010
+ maxTokens: 131072,
9652
10011
  },
9653
10012
  "openai/gpt-oss-20b:free": {
9654
10013
  id: "openai/gpt-oss-20b:free",
@@ -9871,6 +10230,40 @@ export const MODELS = {
9871
10230
  contextWindow: 200000,
9872
10231
  maxTokens: 4096,
9873
10232
  },
10233
+ "poolside/laguna-m.1:free": {
10234
+ id: "poolside/laguna-m.1:free",
10235
+ name: "Poolside: Laguna M.1 (free)",
10236
+ api: "openai-completions",
10237
+ provider: "openrouter",
10238
+ baseUrl: "https://openrouter.ai/api/v1",
10239
+ reasoning: true,
10240
+ input: ["text"],
10241
+ cost: {
10242
+ input: 0,
10243
+ output: 0,
10244
+ cacheRead: 0,
10245
+ cacheWrite: 0,
10246
+ },
10247
+ contextWindow: 131072,
10248
+ maxTokens: 8192,
10249
+ },
10250
+ "poolside/laguna-xs.2:free": {
10251
+ id: "poolside/laguna-xs.2:free",
10252
+ name: "Poolside: Laguna XS.2 (free)",
10253
+ api: "openai-completions",
10254
+ provider: "openrouter",
10255
+ baseUrl: "https://openrouter.ai/api/v1",
10256
+ reasoning: true,
10257
+ input: ["text"],
10258
+ cost: {
10259
+ input: 0,
10260
+ output: 0,
10261
+ cacheRead: 0,
10262
+ cacheWrite: 0,
10263
+ },
10264
+ contextWindow: 131072,
10265
+ maxTokens: 8192,
10266
+ },
9874
10267
  "prime-intellect/intellect-3": {
9875
10268
  id: "prime-intellect/intellect-3",
9876
10269
  name: "Prime Intellect: INTELLECT-3",
@@ -9897,8 +10290,8 @@ export const MODELS = {
9897
10290
  reasoning: false,
9898
10291
  input: ["text"],
9899
10292
  cost: {
9900
- input: 0.12,
9901
- output: 0.39,
10293
+ input: 0.36,
10294
+ output: 0.39999999999999997,
9902
10295
  cacheRead: 0,
9903
10296
  cacheWrite: 0,
9904
10297
  },
@@ -10073,7 +10466,7 @@ export const MODELS = {
10073
10466
  cacheWrite: 0,
10074
10467
  },
10075
10468
  contextWindow: 262144,
10076
- maxTokens: 4096,
10469
+ maxTokens: 16384,
10077
10470
  },
10078
10471
  "qwen/qwen3-235b-a22b-thinking-2507": {
10079
10472
  id: "qwen/qwen3-235b-a22b-thinking-2507",
@@ -10084,13 +10477,13 @@ export const MODELS = {
10084
10477
  reasoning: true,
10085
10478
  input: ["text"],
10086
10479
  cost: {
10087
- input: 0.13,
10088
- output: 0.6,
10480
+ input: 0.14950000000000002,
10481
+ output: 1.495,
10089
10482
  cacheRead: 0,
10090
10483
  cacheWrite: 0,
10091
10484
  },
10092
- contextWindow: 262144,
10093
- maxTokens: 262144,
10485
+ contextWindow: 131072,
10486
+ maxTokens: 4096,
10094
10487
  },
10095
10488
  "qwen/qwen3-30b-a3b": {
10096
10489
  id: "qwen/qwen3-30b-a3b",
@@ -10107,7 +10500,7 @@ export const MODELS = {
10107
10500
  cacheWrite: 0,
10108
10501
  },
10109
10502
  contextWindow: 40960,
10110
- maxTokens: 40960,
10503
+ maxTokens: 16384,
10111
10504
  },
10112
10505
  "qwen/qwen3-30b-a3b-instruct-2507": {
10113
10506
  id: "qwen/qwen3-30b-a3b-instruct-2507",
@@ -10187,12 +10580,12 @@ export const MODELS = {
10187
10580
  input: ["text"],
10188
10581
  cost: {
10189
10582
  input: 0.22,
10190
- output: 1,
10191
- cacheRead: 0.022,
10583
+ output: 1.7999999999999998,
10584
+ cacheRead: 0,
10192
10585
  cacheWrite: 0,
10193
10586
  },
10194
10587
  contextWindow: 262144,
10195
- maxTokens: 4096,
10588
+ maxTokens: 65536,
10196
10589
  },
10197
10590
  "qwen/qwen3-coder-30b-a3b-instruct": {
10198
10591
  id: "qwen/qwen3-coder-30b-a3b-instruct",
@@ -10237,9 +10630,9 @@ export const MODELS = {
10237
10630
  reasoning: false,
10238
10631
  input: ["text"],
10239
10632
  cost: {
10240
- input: 0.15,
10633
+ input: 0.14,
10241
10634
  output: 0.7999999999999999,
10242
- cacheRead: 0.11,
10635
+ cacheRead: 0.09,
10243
10636
  cacheWrite: 0,
10244
10637
  },
10245
10638
  contextWindow: 262144,
@@ -10328,7 +10721,7 @@ export const MODELS = {
10328
10721
  cacheWrite: 0,
10329
10722
  },
10330
10723
  contextWindow: 262144,
10331
- maxTokens: 4096,
10724
+ maxTokens: 16384,
10332
10725
  },
10333
10726
  "qwen/qwen3-next-80b-a3b-instruct:free": {
10334
10727
  id: "qwen/qwen3-next-80b-a3b-instruct:free",
@@ -10379,7 +10772,7 @@ export const MODELS = {
10379
10772
  cacheWrite: 0,
10380
10773
  },
10381
10774
  contextWindow: 262144,
10382
- maxTokens: 4096,
10775
+ maxTokens: 16384,
10383
10776
  },
10384
10777
  "qwen/qwen3-vl-235b-a22b-thinking": {
10385
10778
  id: "qwen/qwen3-vl-235b-a22b-thinking",
@@ -10602,6 +10995,74 @@ export const MODELS = {
10602
10995
  contextWindow: 1000000,
10603
10996
  maxTokens: 65536,
10604
10997
  },
10998
+ "qwen/qwen3.5-plus-20260420": {
10999
+ id: "qwen/qwen3.5-plus-20260420",
11000
+ name: "Qwen: Qwen3.5 Plus 2026-04-20",
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: 0.39999999999999997,
11008
+ output: 2.4,
11009
+ cacheRead: 0,
11010
+ cacheWrite: 0,
11011
+ },
11012
+ contextWindow: 1000000,
11013
+ maxTokens: 65536,
11014
+ },
11015
+ "qwen/qwen3.6-27b": {
11016
+ id: "qwen/qwen3.6-27b",
11017
+ name: "Qwen: Qwen3.6 27B",
11018
+ api: "openai-completions",
11019
+ provider: "openrouter",
11020
+ baseUrl: "https://openrouter.ai/api/v1",
11021
+ reasoning: true,
11022
+ input: ["text", "image"],
11023
+ cost: {
11024
+ input: 0.325,
11025
+ output: 3.25,
11026
+ cacheRead: 0,
11027
+ cacheWrite: 0,
11028
+ },
11029
+ contextWindow: 256000,
11030
+ maxTokens: 65536,
11031
+ },
11032
+ "qwen/qwen3.6-flash": {
11033
+ id: "qwen/qwen3.6-flash",
11034
+ name: "Qwen: Qwen3.6 Flash",
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: 0.25,
11042
+ output: 1.5,
11043
+ cacheRead: 0,
11044
+ cacheWrite: 0.3125,
11045
+ },
11046
+ contextWindow: 1000000,
11047
+ maxTokens: 65536,
11048
+ },
11049
+ "qwen/qwen3.6-max-preview": {
11050
+ id: "qwen/qwen3.6-max-preview",
11051
+ name: "Qwen: Qwen3.6 Max Preview",
11052
+ api: "openai-completions",
11053
+ provider: "openrouter",
11054
+ baseUrl: "https://openrouter.ai/api/v1",
11055
+ reasoning: true,
11056
+ input: ["text"],
11057
+ cost: {
11058
+ input: 1.04,
11059
+ output: 6.24,
11060
+ cacheRead: 0,
11061
+ cacheWrite: 1.3,
11062
+ },
11063
+ contextWindow: 262144,
11064
+ maxTokens: 65536,
11065
+ },
10605
11066
  "qwen/qwen3.6-plus": {
10606
11067
  id: "qwen/qwen3.6-plus",
10607
11068
  name: "Qwen: Qwen3.6 Plus",
@@ -10721,6 +11182,23 @@ export const MODELS = {
10721
11182
  contextWindow: 262144,
10722
11183
  maxTokens: 65536,
10723
11184
  },
11185
+ "tencent/hy3-preview:free": {
11186
+ id: "tencent/hy3-preview:free",
11187
+ name: "Tencent: Hy3 preview (free)",
11188
+ api: "openai-completions",
11189
+ provider: "openrouter",
11190
+ baseUrl: "https://openrouter.ai/api/v1",
11191
+ reasoning: true,
11192
+ input: ["text"],
11193
+ cost: {
11194
+ input: 0,
11195
+ output: 0,
11196
+ cacheRead: 0,
11197
+ cacheWrite: 0,
11198
+ },
11199
+ contextWindow: 262144,
11200
+ maxTokens: 262144,
11201
+ },
10724
11202
  "thedrummer/rocinante-12b": {
10725
11203
  id: "thedrummer/rocinante-12b",
10726
11204
  name: "TheDrummer: Rocinante 12B",
@@ -10993,6 +11471,40 @@ export const MODELS = {
10993
11471
  contextWindow: 1048576,
10994
11472
  maxTokens: 131072,
10995
11473
  },
11474
+ "xiaomi/mimo-v2.5": {
11475
+ id: "xiaomi/mimo-v2.5",
11476
+ name: "Xiaomi: MiMo-V2.5",
11477
+ api: "openai-completions",
11478
+ provider: "openrouter",
11479
+ baseUrl: "https://openrouter.ai/api/v1",
11480
+ reasoning: true,
11481
+ input: ["text", "image"],
11482
+ cost: {
11483
+ input: 0.39999999999999997,
11484
+ output: 2,
11485
+ cacheRead: 0.08,
11486
+ cacheWrite: 0,
11487
+ },
11488
+ contextWindow: 1048576,
11489
+ maxTokens: 131072,
11490
+ },
11491
+ "xiaomi/mimo-v2.5-pro": {
11492
+ id: "xiaomi/mimo-v2.5-pro",
11493
+ name: "Xiaomi: MiMo-V2.5-Pro",
11494
+ api: "openai-completions",
11495
+ provider: "openrouter",
11496
+ baseUrl: "https://openrouter.ai/api/v1",
11497
+ reasoning: true,
11498
+ input: ["text"],
11499
+ cost: {
11500
+ input: 1,
11501
+ output: 3,
11502
+ cacheRead: 0.19999999999999998,
11503
+ cacheWrite: 0,
11504
+ },
11505
+ contextWindow: 1048576,
11506
+ maxTokens: 131072,
11507
+ },
10996
11508
  "z-ai/glm-4-32b": {
10997
11509
  id: "z-ai/glm-4-32b",
10998
11510
  name: "Z.ai: GLM 4 32B ",
@@ -11106,11 +11618,11 @@ export const MODELS = {
11106
11618
  cost: {
11107
11619
  input: 0.3,
11108
11620
  output: 0.8999999999999999,
11109
- cacheRead: 0,
11621
+ cacheRead: 0.049999999999999996,
11110
11622
  cacheWrite: 0,
11111
11623
  },
11112
11624
  contextWindow: 131072,
11113
- maxTokens: 131072,
11625
+ maxTokens: 24000,
11114
11626
  },
11115
11627
  "z-ai/glm-4.7": {
11116
11628
  id: "z-ai/glm-4.7",
@@ -11140,11 +11652,11 @@ export const MODELS = {
11140
11652
  cost: {
11141
11653
  input: 0.06,
11142
11654
  output: 0.39999999999999997,
11143
- cacheRead: 0.0100000002,
11655
+ cacheRead: 0.01,
11144
11656
  cacheWrite: 0,
11145
11657
  },
11146
11658
  contextWindow: 202752,
11147
- maxTokens: 4096,
11659
+ maxTokens: 16384,
11148
11660
  },
11149
11661
  "z-ai/glm-5": {
11150
11662
  id: "z-ai/glm-5",
@@ -11155,13 +11667,13 @@ export const MODELS = {
11155
11667
  reasoning: true,
11156
11668
  input: ["text"],
11157
11669
  cost: {
11158
- input: 0.65,
11670
+ input: 0.6,
11159
11671
  output: 2.08,
11160
- cacheRead: 0.13,
11672
+ cacheRead: 0.12,
11161
11673
  cacheWrite: 0,
11162
11674
  },
11163
11675
  contextWindow: 202752,
11164
- maxTokens: 4096,
11676
+ maxTokens: 16384,
11165
11677
  },
11166
11678
  "z-ai/glm-5-turbo": {
11167
11679
  id: "z-ai/glm-5-turbo",
@@ -11214,6 +11726,23 @@ export const MODELS = {
11214
11726
  contextWindow: 202752,
11215
11727
  maxTokens: 131072,
11216
11728
  },
11729
+ "~anthropic/claude-haiku-latest": {
11730
+ id: "~anthropic/claude-haiku-latest",
11731
+ name: "Anthropic Claude Haiku 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: 1,
11739
+ output: 5,
11740
+ cacheRead: 0.09999999999999999,
11741
+ cacheWrite: 1.25,
11742
+ },
11743
+ contextWindow: 200000,
11744
+ maxTokens: 64000,
11745
+ },
11217
11746
  "~anthropic/claude-opus-latest": {
11218
11747
  id: "~anthropic/claude-opus-latest",
11219
11748
  name: "Anthropic: Claude Opus Latest",
@@ -11231,6 +11760,108 @@ export const MODELS = {
11231
11760
  contextWindow: 1000000,
11232
11761
  maxTokens: 128000,
11233
11762
  },
11763
+ "~anthropic/claude-sonnet-latest": {
11764
+ id: "~anthropic/claude-sonnet-latest",
11765
+ name: "Anthropic Claude Sonnet 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: 3,
11773
+ output: 15,
11774
+ cacheRead: 0.3,
11775
+ cacheWrite: 3.75,
11776
+ },
11777
+ contextWindow: 1000000,
11778
+ maxTokens: 128000,
11779
+ },
11780
+ "~google/gemini-flash-latest": {
11781
+ id: "~google/gemini-flash-latest",
11782
+ name: "Google Gemini Flash 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: 0.5,
11790
+ output: 3,
11791
+ cacheRead: 0.049999999999999996,
11792
+ cacheWrite: 0.08333333333333334,
11793
+ },
11794
+ contextWindow: 1048576,
11795
+ maxTokens: 65536,
11796
+ },
11797
+ "~google/gemini-pro-latest": {
11798
+ id: "~google/gemini-pro-latest",
11799
+ name: "Google Gemini Pro 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: 2,
11807
+ output: 12,
11808
+ cacheRead: 0.19999999999999998,
11809
+ cacheWrite: 0.375,
11810
+ },
11811
+ contextWindow: 1048576,
11812
+ maxTokens: 65536,
11813
+ },
11814
+ "~moonshotai/kimi-latest": {
11815
+ id: "~moonshotai/kimi-latest",
11816
+ name: "MoonshotAI Kimi Latest",
11817
+ api: "openai-completions",
11818
+ provider: "openrouter",
11819
+ baseUrl: "https://openrouter.ai/api/v1",
11820
+ reasoning: true,
11821
+ input: ["text", "image"],
11822
+ cost: {
11823
+ input: 0.7448,
11824
+ output: 4.655,
11825
+ cacheRead: 0.1463,
11826
+ cacheWrite: 0,
11827
+ },
11828
+ contextWindow: 256000,
11829
+ maxTokens: 65536,
11830
+ },
11831
+ "~openai/gpt-latest": {
11832
+ id: "~openai/gpt-latest",
11833
+ name: "OpenAI GPT Latest",
11834
+ api: "openai-completions",
11835
+ provider: "openrouter",
11836
+ baseUrl: "https://openrouter.ai/api/v1",
11837
+ reasoning: true,
11838
+ input: ["text", "image"],
11839
+ cost: {
11840
+ input: 5,
11841
+ output: 30,
11842
+ cacheRead: 0.5,
11843
+ cacheWrite: 0,
11844
+ },
11845
+ contextWindow: 1050000,
11846
+ maxTokens: 128000,
11847
+ },
11848
+ "~openai/gpt-mini-latest": {
11849
+ id: "~openai/gpt-mini-latest",
11850
+ name: "OpenAI GPT Mini Latest",
11851
+ api: "openai-completions",
11852
+ provider: "openrouter",
11853
+ baseUrl: "https://openrouter.ai/api/v1",
11854
+ reasoning: true,
11855
+ input: ["text", "image"],
11856
+ cost: {
11857
+ input: 0.75,
11858
+ output: 4.5,
11859
+ cacheRead: 0.075,
11860
+ cacheWrite: 0,
11861
+ },
11862
+ contextWindow: 400000,
11863
+ maxTokens: 128000,
11864
+ },
11234
11865
  },
11235
11866
  "vercel-ai-gateway": {
11236
11867
  "alibaba/qwen-3-14b": {
@@ -11517,7 +12148,7 @@ export const MODELS = {
11517
12148
  input: 0.5,
11518
12149
  output: 3,
11519
12150
  cacheRead: 0.09999999999999999,
11520
- cacheWrite: 0,
12151
+ cacheWrite: 0.625,
11521
12152
  },
11522
12153
  contextWindow: 1000000,
11523
12154
  maxTokens: 64000,
@@ -11896,6 +12527,40 @@ export const MODELS = {
11896
12527
  contextWindow: 128000,
11897
12528
  maxTokens: 64000,
11898
12529
  },
12530
+ "deepseek/deepseek-v4-flash": {
12531
+ id: "deepseek/deepseek-v4-flash",
12532
+ name: "DeepSeek V4 Flash",
12533
+ api: "anthropic-messages",
12534
+ provider: "vercel-ai-gateway",
12535
+ baseUrl: "https://ai-gateway.vercel.sh",
12536
+ reasoning: true,
12537
+ input: ["text"],
12538
+ cost: {
12539
+ input: 0.14,
12540
+ output: 0.28,
12541
+ cacheRead: 0.0028,
12542
+ cacheWrite: 0,
12543
+ },
12544
+ contextWindow: 1000000,
12545
+ maxTokens: 384000,
12546
+ },
12547
+ "deepseek/deepseek-v4-pro": {
12548
+ id: "deepseek/deepseek-v4-pro",
12549
+ name: "DeepSeek V4 Pro",
12550
+ api: "anthropic-messages",
12551
+ provider: "vercel-ai-gateway",
12552
+ baseUrl: "https://ai-gateway.vercel.sh",
12553
+ reasoning: true,
12554
+ input: ["text"],
12555
+ cost: {
12556
+ input: 0.435,
12557
+ output: 0.87,
12558
+ cacheRead: 0.0036,
12559
+ cacheWrite: 0,
12560
+ },
12561
+ contextWindow: 1000000,
12562
+ maxTokens: 384000,
12563
+ },
11899
12564
  "google/gemini-2.0-flash": {
11900
12565
  id: "google/gemini-2.0-flash",
11901
12566
  name: "Gemini 2.0 Flash",
@@ -13171,6 +13836,40 @@ export const MODELS = {
13171
13836
  contextWindow: 1050000,
13172
13837
  maxTokens: 128000,
13173
13838
  },
13839
+ "openai/gpt-5.5": {
13840
+ id: "openai/gpt-5.5",
13841
+ name: "GPT 5.5",
13842
+ api: "anthropic-messages",
13843
+ provider: "vercel-ai-gateway",
13844
+ baseUrl: "https://ai-gateway.vercel.sh",
13845
+ reasoning: true,
13846
+ input: ["text", "image"],
13847
+ cost: {
13848
+ input: 5,
13849
+ output: 30,
13850
+ cacheRead: 0.5,
13851
+ cacheWrite: 0,
13852
+ },
13853
+ contextWindow: 1000000,
13854
+ maxTokens: 128000,
13855
+ },
13856
+ "openai/gpt-5.5-pro": {
13857
+ id: "openai/gpt-5.5-pro",
13858
+ name: "GPT 5.5 Pro",
13859
+ api: "anthropic-messages",
13860
+ provider: "vercel-ai-gateway",
13861
+ baseUrl: "https://ai-gateway.vercel.sh",
13862
+ reasoning: true,
13863
+ input: ["text", "image"],
13864
+ cost: {
13865
+ input: 30,
13866
+ output: 180,
13867
+ cacheRead: 0,
13868
+ cacheWrite: 0,
13869
+ },
13870
+ contextWindow: 1000000,
13871
+ maxTokens: 128000,
13872
+ },
13174
13873
  "openai/gpt-oss-20b": {
13175
13874
  id: "openai/gpt-oss-20b",
13176
13875
  name: "GPT OSS 120B",
@@ -13639,9 +14338,9 @@ export const MODELS = {
13639
14338
  reasoning: true,
13640
14339
  input: ["text"],
13641
14340
  cost: {
13642
- input: 0.09,
13643
- output: 0.29,
13644
- cacheRead: 0.045,
14341
+ input: 0.09999999999999999,
14342
+ output: 0.3,
14343
+ cacheRead: 0.01,
13645
14344
  cacheWrite: 0,
13646
14345
  },
13647
14346
  contextWindow: 262144,
@@ -13858,15 +14557,15 @@ export const MODELS = {
13858
14557
  provider: "vercel-ai-gateway",
13859
14558
  baseUrl: "https://ai-gateway.vercel.sh",
13860
14559
  reasoning: true,
13861
- input: ["text", "image"],
14560
+ input: ["text"],
13862
14561
  cost: {
13863
14562
  input: 1.4,
13864
14563
  output: 4.4,
13865
14564
  cacheRead: 0.26,
13866
14565
  cacheWrite: 0,
13867
14566
  },
13868
- contextWindow: 202752,
13869
- maxTokens: 202752,
14567
+ contextWindow: 202800,
14568
+ maxTokens: 64000,
13870
14569
  },
13871
14570
  "zai/glm-5v-turbo": {
13872
14571
  id: "zai/glm-5v-turbo",