@dreb/ai 2.14.1 → 2.15.1

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.
@@ -3513,6 +3513,23 @@ export const MODELS = {
3513
3513
  contextWindow: 1000000,
3514
3514
  maxTokens: 64000,
3515
3515
  },
3516
+ "gemini-3.1-flash-lite": {
3517
+ id: "gemini-3.1-flash-lite",
3518
+ name: "Gemini 3.1 Flash Lite",
3519
+ api: "google-generative-ai",
3520
+ provider: "google",
3521
+ baseUrl: "https://generativelanguage.googleapis.com/v1beta",
3522
+ reasoning: true,
3523
+ input: ["text", "image"],
3524
+ cost: {
3525
+ input: 0.25,
3526
+ output: 1.5,
3527
+ cacheRead: 0.025,
3528
+ cacheWrite: 1,
3529
+ },
3530
+ contextWindow: 1048576,
3531
+ maxTokens: 65536,
3532
+ },
3516
3533
  "gemini-3.1-flash-lite-preview": {
3517
3534
  id: "gemini-3.1-flash-lite-preview",
3518
3535
  name: "Gemini 3.1 Flash Lite Preview",
@@ -6229,40 +6246,6 @@ export const MODELS = {
6229
6246
  contextWindow: 272000,
6230
6247
  maxTokens: 128000,
6231
6248
  },
6232
- "gpt-5.2": {
6233
- id: "gpt-5.2",
6234
- name: "GPT-5.2",
6235
- api: "openai-codex-responses",
6236
- provider: "openai-codex",
6237
- baseUrl: "https://chatgpt.com/backend-api",
6238
- reasoning: true,
6239
- input: ["text", "image"],
6240
- cost: {
6241
- input: 1.75,
6242
- output: 14,
6243
- cacheRead: 0.175,
6244
- cacheWrite: 0,
6245
- },
6246
- contextWindow: 272000,
6247
- maxTokens: 128000,
6248
- },
6249
- "gpt-5.2-codex": {
6250
- id: "gpt-5.2-codex",
6251
- name: "GPT-5.2 Codex",
6252
- api: "openai-codex-responses",
6253
- provider: "openai-codex",
6254
- baseUrl: "https://chatgpt.com/backend-api",
6255
- reasoning: true,
6256
- input: ["text", "image"],
6257
- cost: {
6258
- input: 1.75,
6259
- output: 14,
6260
- cacheRead: 0.175,
6261
- cacheWrite: 0,
6262
- },
6263
- contextWindow: 272000,
6264
- maxTokens: 128000,
6265
- },
6266
6249
  "gpt-5.3-codex": {
6267
6250
  id: "gpt-5.3-codex",
6268
6251
  name: "GPT-5.3 Codex",
@@ -6331,14 +6314,31 @@ export const MODELS = {
6331
6314
  contextWindow: 272000,
6332
6315
  maxTokens: 128000,
6333
6316
  },
6317
+ "gpt-5.5": {
6318
+ id: "gpt-5.5",
6319
+ name: "GPT-5.5",
6320
+ api: "openai-codex-responses",
6321
+ provider: "openai-codex",
6322
+ baseUrl: "https://chatgpt.com/backend-api",
6323
+ reasoning: true,
6324
+ input: ["text", "image"],
6325
+ cost: {
6326
+ input: 5,
6327
+ output: 30,
6328
+ cacheRead: 0.5,
6329
+ cacheWrite: 0,
6330
+ },
6331
+ contextWindow: 400000,
6332
+ maxTokens: 128000,
6333
+ },
6334
6334
  },
6335
6335
  "opencode": {
6336
6336
  "big-pickle": {
6337
6337
  id: "big-pickle",
6338
6338
  name: "Big Pickle",
6339
- api: "anthropic-messages",
6339
+ api: "openai-completions",
6340
6340
  provider: "opencode",
6341
- baseUrl: "https://opencode.ai/zen",
6341
+ baseUrl: "https://opencode.ai/zen/v1",
6342
6342
  reasoning: true,
6343
6343
  input: ["text"],
6344
6344
  cost: {
@@ -6597,9 +6597,9 @@ export const MODELS = {
6597
6597
  reasoning: true,
6598
6598
  input: ["text", "image"],
6599
6599
  cost: {
6600
- input: 0,
6601
- output: 0,
6602
- cacheRead: 0,
6600
+ input: 0.05,
6601
+ output: 0.4,
6602
+ cacheRead: 0.005,
6603
6603
  cacheWrite: 0,
6604
6604
  },
6605
6605
  contextWindow: 400000,
@@ -6826,23 +6826,6 @@ export const MODELS = {
6826
6826
  contextWindow: 1050000,
6827
6827
  maxTokens: 128000,
6828
6828
  },
6829
- "hy3-preview-free": {
6830
- id: "hy3-preview-free",
6831
- name: "Hy3 preview Free",
6832
- api: "openai-completions",
6833
- provider: "opencode",
6834
- baseUrl: "https://opencode.ai/zen/v1",
6835
- reasoning: true,
6836
- input: ["text"],
6837
- cost: {
6838
- input: 0,
6839
- output: 0,
6840
- cacheRead: 0,
6841
- cacheWrite: 0,
6842
- },
6843
- contextWindow: 256000,
6844
- maxTokens: 64000,
6845
- },
6846
6829
  "kimi-k2.5": {
6847
6830
  id: "kimi-k2.5",
6848
6831
  name: "Kimi K2.5",
@@ -7068,55 +7051,21 @@ export const MODELS = {
7068
7051
  },
7069
7052
  "kimi-k2.6": {
7070
7053
  id: "kimi-k2.6",
7071
- name: "Kimi K2.6 (3x limits)",
7054
+ name: "Kimi K2.6",
7072
7055
  api: "openai-completions",
7073
7056
  provider: "opencode-go",
7074
7057
  baseUrl: "https://opencode.ai/zen/go/v1",
7075
7058
  reasoning: true,
7076
7059
  input: ["text", "image"],
7077
7060
  cost: {
7078
- input: 0.32,
7079
- output: 1.34,
7080
- cacheRead: 0.054,
7061
+ input: 0.95,
7062
+ output: 4,
7063
+ cacheRead: 0.16,
7081
7064
  cacheWrite: 0,
7082
7065
  },
7083
7066
  contextWindow: 262144,
7084
7067
  maxTokens: 65536,
7085
7068
  },
7086
- "mimo-v2-omni": {
7087
- id: "mimo-v2-omni",
7088
- name: "MiMo V2 Omni",
7089
- api: "openai-completions",
7090
- provider: "opencode-go",
7091
- baseUrl: "https://opencode.ai/zen/go/v1",
7092
- reasoning: true,
7093
- input: ["text", "image"],
7094
- cost: {
7095
- input: 0.4,
7096
- output: 2,
7097
- cacheRead: 0.08,
7098
- cacheWrite: 0,
7099
- },
7100
- contextWindow: 262144,
7101
- maxTokens: 128000,
7102
- },
7103
- "mimo-v2-pro": {
7104
- id: "mimo-v2-pro",
7105
- name: "MiMo V2 Pro",
7106
- api: "openai-completions",
7107
- provider: "opencode-go",
7108
- baseUrl: "https://opencode.ai/zen/go/v1",
7109
- reasoning: true,
7110
- input: ["text"],
7111
- cost: {
7112
- input: 1,
7113
- output: 3,
7114
- cacheRead: 0.2,
7115
- cacheWrite: 0,
7116
- },
7117
- contextWindow: 1048576,
7118
- maxTokens: 128000,
7119
- },
7120
7069
  "mimo-v2.5": {
7121
7070
  id: "mimo-v2.5",
7122
7071
  name: "MiMo V2.5",
@@ -7255,23 +7204,6 @@ export const MODELS = {
7255
7204
  contextWindow: 131072,
7256
7205
  maxTokens: 131072,
7257
7206
  },
7258
- "allenai/olmo-3.1-32b-instruct": {
7259
- id: "allenai/olmo-3.1-32b-instruct",
7260
- name: "AllenAI: Olmo 3.1 32B Instruct",
7261
- api: "openai-completions",
7262
- provider: "openrouter",
7263
- baseUrl: "https://openrouter.ai/api/v1",
7264
- reasoning: false,
7265
- input: ["text"],
7266
- cost: {
7267
- input: 0.19999999999999998,
7268
- output: 0.6,
7269
- cacheRead: 0,
7270
- cacheWrite: 0,
7271
- },
7272
- contextWindow: 65536,
7273
- maxTokens: 16384,
7274
- },
7275
7207
  "amazon/nova-2-lite-v1": {
7276
7208
  id: "amazon/nova-2-lite-v1",
7277
7209
  name: "Amazon: Nova 2 Lite",
@@ -7406,7 +7338,7 @@ export const MODELS = {
7406
7338
  cacheWrite: 3.75,
7407
7339
  },
7408
7340
  contextWindow: 200000,
7409
- maxTokens: 128000,
7341
+ maxTokens: 64000,
7410
7342
  },
7411
7343
  "anthropic/claude-3.7-sonnet:thinking": {
7412
7344
  id: "anthropic/claude-3.7-sonnet:thinking",
@@ -7680,6 +7612,23 @@ export const MODELS = {
7680
7612
  contextWindow: 2000000,
7681
7613
  maxTokens: 30000,
7682
7614
  },
7615
+ "baidu/cobuddy:free": {
7616
+ id: "baidu/cobuddy:free",
7617
+ name: "Baidu Qianfan: CoBuddy (free)",
7618
+ api: "openai-completions",
7619
+ provider: "openrouter",
7620
+ baseUrl: "https://openrouter.ai/api/v1",
7621
+ reasoning: true,
7622
+ input: ["text"],
7623
+ cost: {
7624
+ input: 0,
7625
+ output: 0,
7626
+ cacheRead: 0,
7627
+ cacheWrite: 0,
7628
+ },
7629
+ contextWindow: 131072,
7630
+ maxTokens: 65536,
7631
+ },
7683
7632
  "baidu/ernie-4.5-21b-a3b": {
7684
7633
  id: "baidu/ernie-4.5-21b-a3b",
7685
7634
  name: "Baidu: ERNIE 4.5 21B A3B",
@@ -7910,8 +7859,8 @@ export const MODELS = {
7910
7859
  reasoning: true,
7911
7860
  input: ["text"],
7912
7861
  cost: {
7913
- input: 0.21,
7914
- output: 0.7899999999999999,
7862
+ input: 0.27,
7863
+ output: 0.95,
7915
7864
  cacheRead: 0.13,
7916
7865
  cacheWrite: 0,
7917
7866
  },
@@ -8156,6 +8105,23 @@ export const MODELS = {
8156
8105
  contextWindow: 1048576,
8157
8106
  maxTokens: 65536,
8158
8107
  },
8108
+ "google/gemini-3.1-flash-lite": {
8109
+ id: "google/gemini-3.1-flash-lite",
8110
+ name: "Google: Gemini 3.1 Flash Lite",
8111
+ api: "openai-completions",
8112
+ provider: "openrouter",
8113
+ baseUrl: "https://openrouter.ai/api/v1",
8114
+ reasoning: true,
8115
+ input: ["text", "image"],
8116
+ cost: {
8117
+ input: 0.25,
8118
+ output: 1.5,
8119
+ cacheRead: 0.024999999999999998,
8120
+ cacheWrite: 0.08333333333333334,
8121
+ },
8122
+ contextWindow: 1048576,
8123
+ maxTokens: 65536,
8124
+ },
8159
8125
  "google/gemini-3.1-flash-lite-preview": {
8160
8126
  id: "google/gemini-3.1-flash-lite-preview",
8161
8127
  name: "Google: Gemini 3.1 Flash Lite Preview",
@@ -8343,18 +8309,18 @@ export const MODELS = {
8343
8309
  contextWindow: 128000,
8344
8310
  maxTokens: 50000,
8345
8311
  },
8346
- "inclusionai/ling-2.6-1t:free": {
8347
- id: "inclusionai/ling-2.6-1t:free",
8348
- name: "inclusionAI: Ling-2.6-1T (free)",
8312
+ "inclusionai/ling-2.6-1t": {
8313
+ id: "inclusionai/ling-2.6-1t",
8314
+ name: "inclusionAI: Ling-2.6-1T",
8349
8315
  api: "openai-completions",
8350
8316
  provider: "openrouter",
8351
8317
  baseUrl: "https://openrouter.ai/api/v1",
8352
8318
  reasoning: false,
8353
8319
  input: ["text"],
8354
8320
  cost: {
8355
- input: 0,
8356
- output: 0,
8357
- cacheRead: 0,
8321
+ input: 0.3,
8322
+ output: 2.5,
8323
+ cacheRead: 0.06,
8358
8324
  cacheWrite: 0,
8359
8325
  },
8360
8326
  contextWindow: 262144,
@@ -8377,39 +8343,39 @@ export const MODELS = {
8377
8343
  contextWindow: 262144,
8378
8344
  maxTokens: 32768,
8379
8345
  },
8380
- "kwaipilot/kat-coder-pro-v2": {
8381
- id: "kwaipilot/kat-coder-pro-v2",
8382
- name: "Kwaipilot: KAT-Coder-Pro V2",
8346
+ "inclusionai/ring-2.6-1t:free": {
8347
+ id: "inclusionai/ring-2.6-1t:free",
8348
+ name: "inclusionAI: Ring-2.6-1T (free)",
8383
8349
  api: "openai-completions",
8384
8350
  provider: "openrouter",
8385
8351
  baseUrl: "https://openrouter.ai/api/v1",
8386
- reasoning: false,
8352
+ reasoning: true,
8387
8353
  input: ["text"],
8388
8354
  cost: {
8389
- input: 0.3,
8390
- output: 1.2,
8391
- cacheRead: 0.06,
8355
+ input: 0,
8356
+ output: 0,
8357
+ cacheRead: 0,
8392
8358
  cacheWrite: 0,
8393
8359
  },
8394
- contextWindow: 256000,
8395
- maxTokens: 80000,
8360
+ contextWindow: 262144,
8361
+ maxTokens: 65536,
8396
8362
  },
8397
- "meta-llama/llama-3-8b-instruct": {
8398
- id: "meta-llama/llama-3-8b-instruct",
8399
- name: "Meta: Llama 3 8B Instruct",
8363
+ "kwaipilot/kat-coder-pro-v2": {
8364
+ id: "kwaipilot/kat-coder-pro-v2",
8365
+ name: "Kwaipilot: KAT-Coder-Pro V2",
8400
8366
  api: "openai-completions",
8401
8367
  provider: "openrouter",
8402
8368
  baseUrl: "https://openrouter.ai/api/v1",
8403
8369
  reasoning: false,
8404
8370
  input: ["text"],
8405
8371
  cost: {
8406
- input: 0.03,
8407
- output: 0.04,
8408
- cacheRead: 0,
8372
+ input: 0.3,
8373
+ output: 1.2,
8374
+ cacheRead: 0.06,
8409
8375
  cacheWrite: 0,
8410
8376
  },
8411
- contextWindow: 8192,
8412
- maxTokens: 16384,
8377
+ contextWindow: 256000,
8378
+ maxTokens: 80000,
8413
8379
  },
8414
8380
  "meta-llama/llama-3.1-70b-instruct": {
8415
8381
  id: "meta-llama/llama-3.1-70b-instruct",
@@ -8558,11 +8524,11 @@ export const MODELS = {
8558
8524
  cost: {
8559
8525
  input: 0.15,
8560
8526
  output: 1.15,
8561
- cacheRead: 0.03,
8527
+ cacheRead: 0,
8562
8528
  cacheWrite: 0,
8563
8529
  },
8564
8530
  contextWindow: 196608,
8565
- maxTokens: 131072,
8531
+ maxTokens: 196608,
8566
8532
  },
8567
8533
  "minimax/minimax-m2.5:free": {
8568
8534
  id: "minimax/minimax-m2.5:free",
@@ -8590,13 +8556,13 @@ export const MODELS = {
8590
8556
  reasoning: true,
8591
8557
  input: ["text"],
8592
8558
  cost: {
8593
- input: 0.3,
8559
+ input: 0.29900000000000004,
8594
8560
  output: 1.2,
8595
- cacheRead: 0.059,
8561
+ cacheRead: 0,
8596
8562
  cacheWrite: 0,
8597
8563
  },
8598
8564
  contextWindow: 196608,
8599
- maxTokens: 4096,
8565
+ maxTokens: 131072,
8600
8566
  },
8601
8567
  "mistralai/codestral-2508": {
8602
8568
  id: "mistralai/codestral-2508",
@@ -8802,6 +8768,23 @@ export const MODELS = {
8802
8768
  contextWindow: 131072,
8803
8769
  maxTokens: 4096,
8804
8770
  },
8771
+ "mistralai/mistral-medium-3-5": {
8772
+ id: "mistralai/mistral-medium-3-5",
8773
+ name: "Mistral: Mistral Medium 3.5",
8774
+ api: "openai-completions",
8775
+ provider: "openrouter",
8776
+ baseUrl: "https://openrouter.ai/api/v1",
8777
+ reasoning: true,
8778
+ input: ["text", "image"],
8779
+ cost: {
8780
+ input: 1.5,
8781
+ output: 7.5,
8782
+ cacheRead: 0,
8783
+ cacheWrite: 0,
8784
+ },
8785
+ contextWindow: 262144,
8786
+ maxTokens: 4096,
8787
+ },
8805
8788
  "mistralai/mistral-medium-3.1": {
8806
8789
  id: "mistralai/mistral-medium-3.1",
8807
8790
  name: "Mistral: Mistral Medium 3.1",
@@ -8904,23 +8887,6 @@ export const MODELS = {
8904
8887
  contextWindow: 65536,
8905
8888
  maxTokens: 4096,
8906
8889
  },
8907
- "mistralai/mixtral-8x7b-instruct": {
8908
- id: "mistralai/mixtral-8x7b-instruct",
8909
- name: "Mistral: Mixtral 8x7B Instruct",
8910
- api: "openai-completions",
8911
- provider: "openrouter",
8912
- baseUrl: "https://openrouter.ai/api/v1",
8913
- reasoning: false,
8914
- input: ["text"],
8915
- cost: {
8916
- input: 0.54,
8917
- output: 0.54,
8918
- cacheRead: 0,
8919
- cacheWrite: 0,
8920
- },
8921
- contextWindow: 32768,
8922
- maxTokens: 16384,
8923
- },
8924
8890
  "mistralai/pixtral-large-2411": {
8925
8891
  id: "mistralai/pixtral-large-2411",
8926
8892
  name: "Mistral: Pixtral Large 2411",
@@ -9032,13 +8998,13 @@ export const MODELS = {
9032
8998
  reasoning: true,
9033
8999
  input: ["text", "image"],
9034
9000
  cost: {
9035
- input: 0.74,
9036
- output: 3.49,
9037
- cacheRead: 0.14,
9001
+ input: 0.75,
9002
+ output: 3.5,
9003
+ cacheRead: 0.15,
9038
9004
  cacheWrite: 0,
9039
9005
  },
9040
- contextWindow: 262142,
9041
- maxTokens: 262142,
9006
+ contextWindow: 262144,
9007
+ maxTokens: 16384,
9042
9008
  },
9043
9009
  "nex-agi/deepseek-v3.1-nex-n1": {
9044
9010
  id: "nex-agi/deepseek-v3.1-nex-n1",
@@ -9057,23 +9023,6 @@ export const MODELS = {
9057
9023
  contextWindow: 131072,
9058
9024
  maxTokens: 163840,
9059
9025
  },
9060
- "nvidia/llama-3.1-nemotron-70b-instruct": {
9061
- id: "nvidia/llama-3.1-nemotron-70b-instruct",
9062
- name: "NVIDIA: Llama 3.1 Nemotron 70B Instruct",
9063
- api: "openai-completions",
9064
- provider: "openrouter",
9065
- baseUrl: "https://openrouter.ai/api/v1",
9066
- reasoning: false,
9067
- input: ["text"],
9068
- cost: {
9069
- input: 1.2,
9070
- output: 1.2,
9071
- cacheRead: 0,
9072
- cacheWrite: 0,
9073
- },
9074
- contextWindow: 131072,
9075
- maxTokens: 16384,
9076
- },
9077
9026
  "nvidia/llama-3.3-nemotron-super-49b-v1.5": {
9078
9027
  id: "nvidia/llama-3.3-nemotron-super-49b-v1.5",
9079
9028
  name: "NVIDIA: Llama 3.3 Nemotron Super 49B V1.5",
@@ -9941,6 +9890,23 @@ export const MODELS = {
9941
9890
  contextWindow: 128000,
9942
9891
  maxTokens: 16384,
9943
9892
  },
9893
+ "openai/gpt-chat-latest": {
9894
+ id: "openai/gpt-chat-latest",
9895
+ name: "OpenAI: GPT Chat Latest",
9896
+ api: "openai-completions",
9897
+ provider: "openrouter",
9898
+ baseUrl: "https://openrouter.ai/api/v1",
9899
+ reasoning: false,
9900
+ input: ["text", "image"],
9901
+ cost: {
9902
+ input: 5,
9903
+ output: 30,
9904
+ cacheRead: 0.5,
9905
+ cacheWrite: 0,
9906
+ },
9907
+ contextWindow: 400000,
9908
+ maxTokens: 128000,
9909
+ },
9944
9910
  "openai/gpt-oss-120b": {
9945
9911
  id: "openai/gpt-oss-120b",
9946
9912
  name: "OpenAI: gpt-oss-120b",
@@ -10494,13 +10460,13 @@ export const MODELS = {
10494
10460
  reasoning: true,
10495
10461
  input: ["text"],
10496
10462
  cost: {
10497
- input: 0.08,
10498
- output: 0.28,
10463
+ input: 0.09,
10464
+ output: 0.44999999999999996,
10499
10465
  cacheRead: 0,
10500
10466
  cacheWrite: 0,
10501
10467
  },
10502
10468
  contextWindow: 40960,
10503
- maxTokens: 16384,
10469
+ maxTokens: 20000,
10504
10470
  },
10505
10471
  "qwen/qwen3-30b-a3b-instruct-2507": {
10506
10472
  id: "qwen/qwen3-30b-a3b-instruct-2507",
@@ -10546,12 +10512,12 @@ export const MODELS = {
10546
10512
  input: ["text"],
10547
10513
  cost: {
10548
10514
  input: 0.08,
10549
- output: 0.24,
10550
- cacheRead: 0.04,
10515
+ output: 0.28,
10516
+ cacheRead: 0,
10551
10517
  cacheWrite: 0,
10552
10518
  },
10553
10519
  contextWindow: 40960,
10554
- maxTokens: 40960,
10520
+ maxTokens: 16384,
10555
10521
  },
10556
10522
  "qwen/qwen3-8b": {
10557
10523
  id: "qwen/qwen3-8b",
@@ -10630,7 +10596,7 @@ export const MODELS = {
10630
10596
  reasoning: false,
10631
10597
  input: ["text"],
10632
10598
  cost: {
10633
- input: 0.12,
10599
+ input: 0.11,
10634
10600
  output: 0.7999999999999999,
10635
10601
  cacheRead: 0.07,
10636
10602
  cacheWrite: 0,
@@ -10919,13 +10885,13 @@ export const MODELS = {
10919
10885
  reasoning: true,
10920
10886
  input: ["text", "image"],
10921
10887
  cost: {
10922
- input: 0.1625,
10923
- output: 1.3,
10924
- cacheRead: 0,
10888
+ input: 0.14,
10889
+ output: 1,
10890
+ cacheRead: 0.049999999999999996,
10925
10891
  cacheWrite: 0,
10926
10892
  },
10927
10893
  contextWindow: 262144,
10928
- maxTokens: 65536,
10894
+ maxTokens: 81920,
10929
10895
  },
10930
10896
  "qwen/qwen3.5-397b-a17b": {
10931
10897
  id: "qwen/qwen3.5-397b-a17b",
@@ -10953,13 +10919,13 @@ export const MODELS = {
10953
10919
  reasoning: true,
10954
10920
  input: ["text", "image"],
10955
10921
  cost: {
10956
- input: 0.09999999999999999,
10922
+ input: 0.04,
10957
10923
  output: 0.15,
10958
10924
  cacheRead: 0,
10959
10925
  cacheWrite: 0,
10960
10926
  },
10961
10927
  contextWindow: 262144,
10962
- maxTokens: 4096,
10928
+ maxTokens: 81920,
10963
10929
  },
10964
10930
  "qwen/qwen3.5-flash-02-23": {
10965
10931
  id: "qwen/qwen3.5-flash-02-23",
@@ -11021,13 +10987,30 @@ export const MODELS = {
11021
10987
  reasoning: true,
11022
10988
  input: ["text", "image"],
11023
10989
  cost: {
11024
- input: 0.325,
11025
- output: 3.25,
10990
+ input: 0.32,
10991
+ output: 3.1999999999999997,
11026
10992
  cacheRead: 0,
11027
10993
  cacheWrite: 0,
11028
10994
  },
11029
- contextWindow: 256000,
11030
- maxTokens: 65536,
10995
+ contextWindow: 262144,
10996
+ maxTokens: 81920,
10997
+ },
10998
+ "qwen/qwen3.6-35b-a3b": {
10999
+ id: "qwen/qwen3.6-35b-a3b",
11000
+ name: "Qwen: Qwen3.6 35B A3B",
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: 0.15,
11008
+ output: 1,
11009
+ cacheRead: 0.049999999999999996,
11010
+ cacheWrite: 0,
11011
+ },
11012
+ contextWindow: 262144,
11013
+ maxTokens: 262144,
11031
11014
  },
11032
11015
  "qwen/qwen3.6-flash": {
11033
11016
  id: "qwen/qwen3.6-flash",
@@ -11165,18 +11148,18 @@ export const MODELS = {
11165
11148
  contextWindow: 262144,
11166
11149
  maxTokens: 65536,
11167
11150
  },
11168
- "tencent/hy3-preview:free": {
11169
- id: "tencent/hy3-preview:free",
11170
- name: "Tencent: Hy3 preview (free)",
11151
+ "tencent/hy3-preview": {
11152
+ id: "tencent/hy3-preview",
11153
+ name: "Tencent: Hy3 preview",
11171
11154
  api: "openai-completions",
11172
11155
  provider: "openrouter",
11173
11156
  baseUrl: "https://openrouter.ai/api/v1",
11174
11157
  reasoning: true,
11175
11158
  input: ["text"],
11176
11159
  cost: {
11177
- input: 0,
11178
- output: 0,
11179
- cacheRead: 0,
11160
+ input: 0.06599999999999999,
11161
+ output: 0.26,
11162
+ cacheRead: 0.029,
11180
11163
  cacheWrite: 0,
11181
11164
  },
11182
11165
  contextWindow: 262144,
@@ -11216,23 +11199,6 @@ export const MODELS = {
11216
11199
  contextWindow: 32768,
11217
11200
  maxTokens: 32768,
11218
11201
  },
11219
- "tngtech/deepseek-r1t2-chimera": {
11220
- id: "tngtech/deepseek-r1t2-chimera",
11221
- name: "TNG: DeepSeek R1T2 Chimera",
11222
- api: "openai-completions",
11223
- provider: "openrouter",
11224
- baseUrl: "https://openrouter.ai/api/v1",
11225
- reasoning: true,
11226
- input: ["text"],
11227
- cost: {
11228
- input: 0.3,
11229
- output: 1.1,
11230
- cacheRead: 0.15,
11231
- cacheWrite: 0,
11232
- },
11233
- contextWindow: 163840,
11234
- maxTokens: 163840,
11235
- },
11236
11202
  "upstage/solar-pro-3": {
11237
11203
  id: "upstage/solar-pro-3",
11238
11204
  name: "Upstage: Solar Pro 3",
@@ -11429,9 +11395,9 @@ export const MODELS = {
11429
11395
  reasoning: true,
11430
11396
  input: ["text"],
11431
11397
  cost: {
11432
- input: 0.09,
11433
- output: 0.29,
11434
- cacheRead: 0.045,
11398
+ input: 0.09999999999999999,
11399
+ output: 0.3,
11400
+ cacheRead: 0.01,
11435
11401
  cacheWrite: 0,
11436
11402
  },
11437
11403
  contextWindow: 262144,
@@ -11503,7 +11469,7 @@ export const MODELS = {
11503
11469
  cacheWrite: 0,
11504
11470
  },
11505
11471
  contextWindow: 1048576,
11506
- maxTokens: 131072,
11472
+ maxTokens: 16384,
11507
11473
  },
11508
11474
  "z-ai/glm-4-32b": {
11509
11475
  id: "z-ai/glm-4-32b",
@@ -11633,13 +11599,13 @@ export const MODELS = {
11633
11599
  reasoning: true,
11634
11600
  input: ["text"],
11635
11601
  cost: {
11636
- input: 0.38,
11637
- output: 1.74,
11638
- cacheRead: 0,
11602
+ input: 0.39999999999999997,
11603
+ output: 1.75,
11604
+ cacheRead: 0.08,
11639
11605
  cacheWrite: 0,
11640
11606
  },
11641
11607
  contextWindow: 202752,
11642
- maxTokens: 4096,
11608
+ maxTokens: 131072,
11643
11609
  },
11644
11610
  "z-ai/glm-4.7-flash": {
11645
11611
  id: "z-ai/glm-4.7-flash",
@@ -11668,12 +11634,12 @@ export const MODELS = {
11668
11634
  input: ["text"],
11669
11635
  cost: {
11670
11636
  input: 0.6,
11671
- output: 2.08,
11637
+ output: 1.92,
11672
11638
  cacheRead: 0.12,
11673
11639
  cacheWrite: 0,
11674
11640
  },
11675
11641
  contextWindow: 202752,
11676
- maxTokens: 16384,
11642
+ maxTokens: 4096,
11677
11643
  },
11678
11644
  "z-ai/glm-5-turbo": {
11679
11645
  id: "z-ai/glm-5-turbo",
@@ -11820,13 +11786,13 @@ export const MODELS = {
11820
11786
  reasoning: true,
11821
11787
  input: ["text", "image"],
11822
11788
  cost: {
11823
- input: 0.74,
11824
- output: 3.49,
11825
- cacheRead: 0.14,
11789
+ input: 0.75,
11790
+ output: 3.5,
11791
+ cacheRead: 0.15,
11826
11792
  cacheWrite: 0,
11827
11793
  },
11828
- contextWindow: 262142,
11829
- maxTokens: 262142,
11794
+ contextWindow: 262144,
11795
+ maxTokens: 16384,
11830
11796
  },
11831
11797
  "~openai/gpt-latest": {
11832
11798
  id: "~openai/gpt-latest",
@@ -12697,6 +12663,23 @@ export const MODELS = {
12697
12663
  contextWindow: 1000000,
12698
12664
  maxTokens: 64000,
12699
12665
  },
12666
+ "google/gemini-3.1-flash-lite": {
12667
+ id: "google/gemini-3.1-flash-lite",
12668
+ name: "Gemini 3.1 Flash Lite",
12669
+ api: "anthropic-messages",
12670
+ provider: "vercel-ai-gateway",
12671
+ baseUrl: "https://ai-gateway.vercel.sh",
12672
+ reasoning: true,
12673
+ input: ["text", "image"],
12674
+ cost: {
12675
+ input: 0.25,
12676
+ output: 1.5,
12677
+ cacheRead: 0.03,
12678
+ cacheWrite: 0,
12679
+ },
12680
+ contextWindow: 1000000,
12681
+ maxTokens: 65000,
12682
+ },
12700
12683
  "google/gemini-3.1-flash-lite-preview": {
12701
12684
  id: "google/gemini-3.1-flash-lite-preview",
12702
12685
  name: "Gemini 3.1 Flash Lite Preview",
@@ -13258,23 +13241,6 @@ export const MODELS = {
13258
13241
  contextWindow: 131072,
13259
13242
  maxTokens: 131072,
13260
13243
  },
13261
- "moonshotai/kimi-k2-0905": {
13262
- id: "moonshotai/kimi-k2-0905",
13263
- name: "Kimi K2 0905",
13264
- api: "anthropic-messages",
13265
- provider: "vercel-ai-gateway",
13266
- baseUrl: "https://ai-gateway.vercel.sh",
13267
- reasoning: false,
13268
- input: ["text"],
13269
- cost: {
13270
- input: 0.6,
13271
- output: 2.5,
13272
- cacheRead: 0.3,
13273
- cacheWrite: 0,
13274
- },
13275
- contextWindow: 256000,
13276
- maxTokens: 128000,
13277
- },
13278
13244
  "moonshotai/kimi-k2-thinking": {
13279
13245
  id: "moonshotai/kimi-k2-thinking",
13280
13246
  name: "Kimi K2 Thinking",
@@ -14219,8 +14185,8 @@ export const MODELS = {
14219
14185
  reasoning: true,
14220
14186
  input: ["text", "image"],
14221
14187
  cost: {
14222
- input: 2,
14223
- output: 6,
14188
+ input: 1.25,
14189
+ output: 2.5,
14224
14190
  cacheRead: 0.19999999999999998,
14225
14191
  cacheWrite: 0,
14226
14192
  },
@@ -14236,8 +14202,8 @@ export const MODELS = {
14236
14202
  reasoning: true,
14237
14203
  input: ["text", "image"],
14238
14204
  cost: {
14239
- input: 2,
14240
- output: 6,
14205
+ input: 1.25,
14206
+ output: 2.5,
14241
14207
  cacheRead: 0.19999999999999998,
14242
14208
  cacheWrite: 0,
14243
14209
  },
@@ -14253,8 +14219,8 @@ export const MODELS = {
14253
14219
  reasoning: false,
14254
14220
  input: ["text", "image"],
14255
14221
  cost: {
14256
- input: 2,
14257
- output: 6,
14222
+ input: 1.25,
14223
+ output: 2.5,
14258
14224
  cacheRead: 0.19999999999999998,
14259
14225
  cacheWrite: 0,
14260
14226
  },
@@ -14270,8 +14236,8 @@ export const MODELS = {
14270
14236
  reasoning: false,
14271
14237
  input: ["text", "image"],
14272
14238
  cost: {
14273
- input: 2,
14274
- output: 6,
14239
+ input: 1.25,
14240
+ output: 2.5,
14275
14241
  cacheRead: 0.19999999999999998,
14276
14242
  cacheWrite: 0,
14277
14243
  },
@@ -14287,8 +14253,8 @@ export const MODELS = {
14287
14253
  reasoning: true,
14288
14254
  input: ["text", "image"],
14289
14255
  cost: {
14290
- input: 2,
14291
- output: 6,
14256
+ input: 1.25,
14257
+ output: 2.5,
14292
14258
  cacheRead: 0.19999999999999998,
14293
14259
  cacheWrite: 0,
14294
14260
  },
@@ -14304,8 +14270,8 @@ export const MODELS = {
14304
14270
  reasoning: true,
14305
14271
  input: ["text", "image"],
14306
14272
  cost: {
14307
- input: 2,
14308
- output: 6,
14273
+ input: 1.25,
14274
+ output: 2.5,
14309
14275
  cacheRead: 0.19999999999999998,
14310
14276
  cacheWrite: 0,
14311
14277
  },