@dreb/ai 2.15.0 → 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",
@@ -6319,9 +6336,9 @@ export const MODELS = {
6319
6336
  "big-pickle": {
6320
6337
  id: "big-pickle",
6321
6338
  name: "Big Pickle",
6322
- api: "anthropic-messages",
6339
+ api: "openai-completions",
6323
6340
  provider: "opencode",
6324
- baseUrl: "https://opencode.ai/zen",
6341
+ baseUrl: "https://opencode.ai/zen/v1",
6325
6342
  reasoning: true,
6326
6343
  input: ["text"],
6327
6344
  cost: {
@@ -6580,9 +6597,9 @@ export const MODELS = {
6580
6597
  reasoning: true,
6581
6598
  input: ["text", "image"],
6582
6599
  cost: {
6583
- input: 0,
6584
- output: 0,
6585
- cacheRead: 0,
6600
+ input: 0.05,
6601
+ output: 0.4,
6602
+ cacheRead: 0.005,
6586
6603
  cacheWrite: 0,
6587
6604
  },
6588
6605
  contextWindow: 400000,
@@ -6809,23 +6826,6 @@ export const MODELS = {
6809
6826
  contextWindow: 1050000,
6810
6827
  maxTokens: 128000,
6811
6828
  },
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
- },
6829
6829
  "kimi-k2.5": {
6830
6830
  id: "kimi-k2.5",
6831
6831
  name: "Kimi K2.5",
@@ -7051,55 +7051,21 @@ export const MODELS = {
7051
7051
  },
7052
7052
  "kimi-k2.6": {
7053
7053
  id: "kimi-k2.6",
7054
- name: "Kimi K2.6 (3x limits)",
7054
+ name: "Kimi K2.6",
7055
7055
  api: "openai-completions",
7056
7056
  provider: "opencode-go",
7057
7057
  baseUrl: "https://opencode.ai/zen/go/v1",
7058
7058
  reasoning: true,
7059
7059
  input: ["text", "image"],
7060
7060
  cost: {
7061
- input: 0.32,
7062
- output: 1.34,
7063
- cacheRead: 0.054,
7061
+ input: 0.95,
7062
+ output: 4,
7063
+ cacheRead: 0.16,
7064
7064
  cacheWrite: 0,
7065
7065
  },
7066
7066
  contextWindow: 262144,
7067
7067
  maxTokens: 65536,
7068
7068
  },
7069
- "mimo-v2-omni": {
7070
- id: "mimo-v2-omni",
7071
- name: "MiMo V2 Omni",
7072
- api: "openai-completions",
7073
- provider: "opencode-go",
7074
- baseUrl: "https://opencode.ai/zen/go/v1",
7075
- reasoning: true,
7076
- input: ["text", "image"],
7077
- cost: {
7078
- input: 0.4,
7079
- output: 2,
7080
- cacheRead: 0.08,
7081
- cacheWrite: 0,
7082
- },
7083
- contextWindow: 262144,
7084
- maxTokens: 128000,
7085
- },
7086
- "mimo-v2-pro": {
7087
- id: "mimo-v2-pro",
7088
- name: "MiMo V2 Pro",
7089
- api: "openai-completions",
7090
- provider: "opencode-go",
7091
- baseUrl: "https://opencode.ai/zen/go/v1",
7092
- reasoning: true,
7093
- input: ["text"],
7094
- cost: {
7095
- input: 1,
7096
- output: 3,
7097
- cacheRead: 0.2,
7098
- cacheWrite: 0,
7099
- },
7100
- contextWindow: 1048576,
7101
- maxTokens: 128000,
7102
- },
7103
7069
  "mimo-v2.5": {
7104
7070
  id: "mimo-v2.5",
7105
7071
  name: "MiMo V2.5",
@@ -7238,23 +7204,6 @@ export const MODELS = {
7238
7204
  contextWindow: 131072,
7239
7205
  maxTokens: 131072,
7240
7206
  },
7241
- "allenai/olmo-3.1-32b-instruct": {
7242
- id: "allenai/olmo-3.1-32b-instruct",
7243
- name: "AllenAI: Olmo 3.1 32B Instruct",
7244
- api: "openai-completions",
7245
- provider: "openrouter",
7246
- baseUrl: "https://openrouter.ai/api/v1",
7247
- reasoning: false,
7248
- input: ["text"],
7249
- cost: {
7250
- input: 0.19999999999999998,
7251
- output: 0.6,
7252
- cacheRead: 0,
7253
- cacheWrite: 0,
7254
- },
7255
- contextWindow: 65536,
7256
- maxTokens: 16384,
7257
- },
7258
7207
  "amazon/nova-2-lite-v1": {
7259
7208
  id: "amazon/nova-2-lite-v1",
7260
7209
  name: "Amazon: Nova 2 Lite",
@@ -7389,7 +7338,7 @@ export const MODELS = {
7389
7338
  cacheWrite: 3.75,
7390
7339
  },
7391
7340
  contextWindow: 200000,
7392
- maxTokens: 128000,
7341
+ maxTokens: 64000,
7393
7342
  },
7394
7343
  "anthropic/claude-3.7-sonnet:thinking": {
7395
7344
  id: "anthropic/claude-3.7-sonnet:thinking",
@@ -7663,6 +7612,23 @@ export const MODELS = {
7663
7612
  contextWindow: 2000000,
7664
7613
  maxTokens: 30000,
7665
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
+ },
7666
7632
  "baidu/ernie-4.5-21b-a3b": {
7667
7633
  id: "baidu/ernie-4.5-21b-a3b",
7668
7634
  name: "Baidu: ERNIE 4.5 21B A3B",
@@ -7893,8 +7859,8 @@ export const MODELS = {
7893
7859
  reasoning: true,
7894
7860
  input: ["text"],
7895
7861
  cost: {
7896
- input: 0.21,
7897
- output: 0.7899999999999999,
7862
+ input: 0.27,
7863
+ output: 0.95,
7898
7864
  cacheRead: 0.13,
7899
7865
  cacheWrite: 0,
7900
7866
  },
@@ -8000,7 +7966,7 @@ export const MODELS = {
8000
7966
  cacheRead: 0.024999999999999998,
8001
7967
  cacheWrite: 0.08333333333333334,
8002
7968
  },
8003
- contextWindow: 1048576,
7969
+ contextWindow: 1000000,
8004
7970
  maxTokens: 8192,
8005
7971
  },
8006
7972
  "google/gemini-2.0-flash-lite-001": {
@@ -8139,6 +8105,23 @@ export const MODELS = {
8139
8105
  contextWindow: 1048576,
8140
8106
  maxTokens: 65536,
8141
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
+ },
8142
8125
  "google/gemini-3.1-flash-lite-preview": {
8143
8126
  id: "google/gemini-3.1-flash-lite-preview",
8144
8127
  name: "Google: Gemini 3.1 Flash Lite Preview",
@@ -8326,18 +8309,18 @@ export const MODELS = {
8326
8309
  contextWindow: 128000,
8327
8310
  maxTokens: 50000,
8328
8311
  },
8329
- "inclusionai/ling-2.6-1t:free": {
8330
- id: "inclusionai/ling-2.6-1t:free",
8331
- 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",
8332
8315
  api: "openai-completions",
8333
8316
  provider: "openrouter",
8334
8317
  baseUrl: "https://openrouter.ai/api/v1",
8335
8318
  reasoning: false,
8336
8319
  input: ["text"],
8337
8320
  cost: {
8338
- input: 0,
8339
- output: 0,
8340
- cacheRead: 0,
8321
+ input: 0.3,
8322
+ output: 2.5,
8323
+ cacheRead: 0.06,
8341
8324
  cacheWrite: 0,
8342
8325
  },
8343
8326
  contextWindow: 262144,
@@ -8360,39 +8343,39 @@ export const MODELS = {
8360
8343
  contextWindow: 262144,
8361
8344
  maxTokens: 32768,
8362
8345
  },
8363
- "kwaipilot/kat-coder-pro-v2": {
8364
- id: "kwaipilot/kat-coder-pro-v2",
8365
- 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)",
8366
8349
  api: "openai-completions",
8367
8350
  provider: "openrouter",
8368
8351
  baseUrl: "https://openrouter.ai/api/v1",
8369
- reasoning: false,
8352
+ reasoning: true,
8370
8353
  input: ["text"],
8371
8354
  cost: {
8372
- input: 0.3,
8373
- output: 1.2,
8374
- cacheRead: 0.06,
8355
+ input: 0,
8356
+ output: 0,
8357
+ cacheRead: 0,
8375
8358
  cacheWrite: 0,
8376
8359
  },
8377
- contextWindow: 256000,
8378
- maxTokens: 80000,
8360
+ contextWindow: 262144,
8361
+ maxTokens: 65536,
8379
8362
  },
8380
- "meta-llama/llama-3-8b-instruct": {
8381
- id: "meta-llama/llama-3-8b-instruct",
8382
- 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",
8383
8366
  api: "openai-completions",
8384
8367
  provider: "openrouter",
8385
8368
  baseUrl: "https://openrouter.ai/api/v1",
8386
8369
  reasoning: false,
8387
8370
  input: ["text"],
8388
8371
  cost: {
8389
- input: 0.03,
8390
- output: 0.04,
8391
- cacheRead: 0,
8372
+ input: 0.3,
8373
+ output: 1.2,
8374
+ cacheRead: 0.06,
8392
8375
  cacheWrite: 0,
8393
8376
  },
8394
- contextWindow: 8192,
8395
- maxTokens: 16384,
8377
+ contextWindow: 256000,
8378
+ maxTokens: 80000,
8396
8379
  },
8397
8380
  "meta-llama/llama-3.1-70b-instruct": {
8398
8381
  id: "meta-llama/llama-3.1-70b-instruct",
@@ -8541,11 +8524,11 @@ export const MODELS = {
8541
8524
  cost: {
8542
8525
  input: 0.15,
8543
8526
  output: 1.15,
8544
- cacheRead: 0.03,
8527
+ cacheRead: 0,
8545
8528
  cacheWrite: 0,
8546
8529
  },
8547
8530
  contextWindow: 196608,
8548
- maxTokens: 131072,
8531
+ maxTokens: 196608,
8549
8532
  },
8550
8533
  "minimax/minimax-m2.5:free": {
8551
8534
  id: "minimax/minimax-m2.5:free",
@@ -8573,13 +8556,13 @@ export const MODELS = {
8573
8556
  reasoning: true,
8574
8557
  input: ["text"],
8575
8558
  cost: {
8576
- input: 0.3,
8559
+ input: 0.29900000000000004,
8577
8560
  output: 1.2,
8578
- cacheRead: 0.059,
8561
+ cacheRead: 0,
8579
8562
  cacheWrite: 0,
8580
8563
  },
8581
8564
  contextWindow: 196608,
8582
- maxTokens: 4096,
8565
+ maxTokens: 131072,
8583
8566
  },
8584
8567
  "mistralai/codestral-2508": {
8585
8568
  id: "mistralai/codestral-2508",
@@ -8785,6 +8768,23 @@ export const MODELS = {
8785
8768
  contextWindow: 131072,
8786
8769
  maxTokens: 4096,
8787
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
+ },
8788
8788
  "mistralai/mistral-medium-3.1": {
8789
8789
  id: "mistralai/mistral-medium-3.1",
8790
8790
  name: "Mistral: Mistral Medium 3.1",
@@ -8887,23 +8887,6 @@ export const MODELS = {
8887
8887
  contextWindow: 65536,
8888
8888
  maxTokens: 4096,
8889
8889
  },
8890
- "mistralai/mixtral-8x7b-instruct": {
8891
- id: "mistralai/mixtral-8x7b-instruct",
8892
- name: "Mistral: Mixtral 8x7B Instruct",
8893
- api: "openai-completions",
8894
- provider: "openrouter",
8895
- baseUrl: "https://openrouter.ai/api/v1",
8896
- reasoning: false,
8897
- input: ["text"],
8898
- cost: {
8899
- input: 0.54,
8900
- output: 0.54,
8901
- cacheRead: 0,
8902
- cacheWrite: 0,
8903
- },
8904
- contextWindow: 32768,
8905
- maxTokens: 16384,
8906
- },
8907
8890
  "mistralai/pixtral-large-2411": {
8908
8891
  id: "mistralai/pixtral-large-2411",
8909
8892
  name: "Mistral: Pixtral Large 2411",
@@ -9015,13 +8998,13 @@ export const MODELS = {
9015
8998
  reasoning: true,
9016
8999
  input: ["text", "image"],
9017
9000
  cost: {
9018
- input: 0.74,
9019
- output: 3.49,
9020
- cacheRead: 0.14,
9001
+ input: 0.75,
9002
+ output: 3.5,
9003
+ cacheRead: 0.15,
9021
9004
  cacheWrite: 0,
9022
9005
  },
9023
- contextWindow: 262142,
9024
- maxTokens: 262142,
9006
+ contextWindow: 262144,
9007
+ maxTokens: 16384,
9025
9008
  },
9026
9009
  "nex-agi/deepseek-v3.1-nex-n1": {
9027
9010
  id: "nex-agi/deepseek-v3.1-nex-n1",
@@ -9040,23 +9023,6 @@ export const MODELS = {
9040
9023
  contextWindow: 131072,
9041
9024
  maxTokens: 163840,
9042
9025
  },
9043
- "nvidia/llama-3.1-nemotron-70b-instruct": {
9044
- id: "nvidia/llama-3.1-nemotron-70b-instruct",
9045
- name: "NVIDIA: Llama 3.1 Nemotron 70B Instruct",
9046
- api: "openai-completions",
9047
- provider: "openrouter",
9048
- baseUrl: "https://openrouter.ai/api/v1",
9049
- reasoning: false,
9050
- input: ["text"],
9051
- cost: {
9052
- input: 1.2,
9053
- output: 1.2,
9054
- cacheRead: 0,
9055
- cacheWrite: 0,
9056
- },
9057
- contextWindow: 131072,
9058
- maxTokens: 16384,
9059
- },
9060
9026
  "nvidia/llama-3.3-nemotron-super-49b-v1.5": {
9061
9027
  id: "nvidia/llama-3.3-nemotron-super-49b-v1.5",
9062
9028
  name: "NVIDIA: Llama 3.3 Nemotron Super 49B V1.5",
@@ -9924,6 +9890,23 @@ export const MODELS = {
9924
9890
  contextWindow: 128000,
9925
9891
  maxTokens: 16384,
9926
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
+ },
9927
9910
  "openai/gpt-oss-120b": {
9928
9911
  id: "openai/gpt-oss-120b",
9929
9912
  name: "OpenAI: gpt-oss-120b",
@@ -10477,13 +10460,13 @@ export const MODELS = {
10477
10460
  reasoning: true,
10478
10461
  input: ["text"],
10479
10462
  cost: {
10480
- input: 0.08,
10481
- output: 0.28,
10463
+ input: 0.09,
10464
+ output: 0.44999999999999996,
10482
10465
  cacheRead: 0,
10483
10466
  cacheWrite: 0,
10484
10467
  },
10485
10468
  contextWindow: 40960,
10486
- maxTokens: 16384,
10469
+ maxTokens: 20000,
10487
10470
  },
10488
10471
  "qwen/qwen3-30b-a3b-instruct-2507": {
10489
10472
  id: "qwen/qwen3-30b-a3b-instruct-2507",
@@ -10529,12 +10512,12 @@ export const MODELS = {
10529
10512
  input: ["text"],
10530
10513
  cost: {
10531
10514
  input: 0.08,
10532
- output: 0.24,
10533
- cacheRead: 0.04,
10515
+ output: 0.28,
10516
+ cacheRead: 0,
10534
10517
  cacheWrite: 0,
10535
10518
  },
10536
10519
  contextWindow: 40960,
10537
- maxTokens: 40960,
10520
+ maxTokens: 16384,
10538
10521
  },
10539
10522
  "qwen/qwen3-8b": {
10540
10523
  id: "qwen/qwen3-8b",
@@ -10613,7 +10596,7 @@ export const MODELS = {
10613
10596
  reasoning: false,
10614
10597
  input: ["text"],
10615
10598
  cost: {
10616
- input: 0.12,
10599
+ input: 0.11,
10617
10600
  output: 0.7999999999999999,
10618
10601
  cacheRead: 0.07,
10619
10602
  cacheWrite: 0,
@@ -10902,13 +10885,13 @@ export const MODELS = {
10902
10885
  reasoning: true,
10903
10886
  input: ["text", "image"],
10904
10887
  cost: {
10905
- input: 0.1625,
10906
- output: 1.3,
10907
- cacheRead: 0,
10888
+ input: 0.14,
10889
+ output: 1,
10890
+ cacheRead: 0.049999999999999996,
10908
10891
  cacheWrite: 0,
10909
10892
  },
10910
10893
  contextWindow: 262144,
10911
- maxTokens: 65536,
10894
+ maxTokens: 81920,
10912
10895
  },
10913
10896
  "qwen/qwen3.5-397b-a17b": {
10914
10897
  id: "qwen/qwen3.5-397b-a17b",
@@ -10936,13 +10919,13 @@ export const MODELS = {
10936
10919
  reasoning: true,
10937
10920
  input: ["text", "image"],
10938
10921
  cost: {
10939
- input: 0.09999999999999999,
10922
+ input: 0.04,
10940
10923
  output: 0.15,
10941
10924
  cacheRead: 0,
10942
10925
  cacheWrite: 0,
10943
10926
  },
10944
10927
  contextWindow: 262144,
10945
- maxTokens: 4096,
10928
+ maxTokens: 81920,
10946
10929
  },
10947
10930
  "qwen/qwen3.5-flash-02-23": {
10948
10931
  id: "qwen/qwen3.5-flash-02-23",
@@ -11004,13 +10987,30 @@ export const MODELS = {
11004
10987
  reasoning: true,
11005
10988
  input: ["text", "image"],
11006
10989
  cost: {
11007
- input: 0.325,
11008
- output: 3.25,
10990
+ input: 0.32,
10991
+ output: 3.1999999999999997,
11009
10992
  cacheRead: 0,
11010
10993
  cacheWrite: 0,
11011
10994
  },
11012
- contextWindow: 256000,
11013
- 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,
11014
11014
  },
11015
11015
  "qwen/qwen3.6-flash": {
11016
11016
  id: "qwen/qwen3.6-flash",
@@ -11148,18 +11148,18 @@ export const MODELS = {
11148
11148
  contextWindow: 262144,
11149
11149
  maxTokens: 65536,
11150
11150
  },
11151
- "tencent/hy3-preview:free": {
11152
- id: "tencent/hy3-preview:free",
11153
- name: "Tencent: Hy3 preview (free)",
11151
+ "tencent/hy3-preview": {
11152
+ id: "tencent/hy3-preview",
11153
+ name: "Tencent: Hy3 preview",
11154
11154
  api: "openai-completions",
11155
11155
  provider: "openrouter",
11156
11156
  baseUrl: "https://openrouter.ai/api/v1",
11157
11157
  reasoning: true,
11158
11158
  input: ["text"],
11159
11159
  cost: {
11160
- input: 0,
11161
- output: 0,
11162
- cacheRead: 0,
11160
+ input: 0.06599999999999999,
11161
+ output: 0.26,
11162
+ cacheRead: 0.029,
11163
11163
  cacheWrite: 0,
11164
11164
  },
11165
11165
  contextWindow: 262144,
@@ -11199,23 +11199,6 @@ export const MODELS = {
11199
11199
  contextWindow: 32768,
11200
11200
  maxTokens: 32768,
11201
11201
  },
11202
- "tngtech/deepseek-r1t2-chimera": {
11203
- id: "tngtech/deepseek-r1t2-chimera",
11204
- name: "TNG: DeepSeek R1T2 Chimera",
11205
- api: "openai-completions",
11206
- provider: "openrouter",
11207
- baseUrl: "https://openrouter.ai/api/v1",
11208
- reasoning: true,
11209
- input: ["text"],
11210
- cost: {
11211
- input: 0.3,
11212
- output: 1.1,
11213
- cacheRead: 0.15,
11214
- cacheWrite: 0,
11215
- },
11216
- contextWindow: 163840,
11217
- maxTokens: 163840,
11218
- },
11219
11202
  "upstage/solar-pro-3": {
11220
11203
  id: "upstage/solar-pro-3",
11221
11204
  name: "Upstage: Solar Pro 3",
@@ -11412,9 +11395,9 @@ export const MODELS = {
11412
11395
  reasoning: true,
11413
11396
  input: ["text"],
11414
11397
  cost: {
11415
- input: 0.09,
11416
- output: 0.29,
11417
- cacheRead: 0.045,
11398
+ input: 0.09999999999999999,
11399
+ output: 0.3,
11400
+ cacheRead: 0.01,
11418
11401
  cacheWrite: 0,
11419
11402
  },
11420
11403
  contextWindow: 262144,
@@ -11486,7 +11469,7 @@ export const MODELS = {
11486
11469
  cacheWrite: 0,
11487
11470
  },
11488
11471
  contextWindow: 1048576,
11489
- maxTokens: 131072,
11472
+ maxTokens: 16384,
11490
11473
  },
11491
11474
  "z-ai/glm-4-32b": {
11492
11475
  id: "z-ai/glm-4-32b",
@@ -11616,13 +11599,13 @@ export const MODELS = {
11616
11599
  reasoning: true,
11617
11600
  input: ["text"],
11618
11601
  cost: {
11619
- input: 0.38,
11620
- output: 1.74,
11621
- cacheRead: 0,
11602
+ input: 0.39999999999999997,
11603
+ output: 1.75,
11604
+ cacheRead: 0.08,
11622
11605
  cacheWrite: 0,
11623
11606
  },
11624
11607
  contextWindow: 202752,
11625
- maxTokens: 4096,
11608
+ maxTokens: 131072,
11626
11609
  },
11627
11610
  "z-ai/glm-4.7-flash": {
11628
11611
  id: "z-ai/glm-4.7-flash",
@@ -11651,12 +11634,12 @@ export const MODELS = {
11651
11634
  input: ["text"],
11652
11635
  cost: {
11653
11636
  input: 0.6,
11654
- output: 2.08,
11637
+ output: 1.92,
11655
11638
  cacheRead: 0.12,
11656
11639
  cacheWrite: 0,
11657
11640
  },
11658
11641
  contextWindow: 202752,
11659
- maxTokens: 16384,
11642
+ maxTokens: 4096,
11660
11643
  },
11661
11644
  "z-ai/glm-5-turbo": {
11662
11645
  id: "z-ai/glm-5-turbo",
@@ -11803,13 +11786,13 @@ export const MODELS = {
11803
11786
  reasoning: true,
11804
11787
  input: ["text", "image"],
11805
11788
  cost: {
11806
- input: 0.74,
11807
- output: 3.49,
11808
- cacheRead: 0.14,
11789
+ input: 0.75,
11790
+ output: 3.5,
11791
+ cacheRead: 0.15,
11809
11792
  cacheWrite: 0,
11810
11793
  },
11811
- contextWindow: 262142,
11812
- maxTokens: 262142,
11794
+ contextWindow: 262144,
11795
+ maxTokens: 16384,
11813
11796
  },
11814
11797
  "~openai/gpt-latest": {
11815
11798
  id: "~openai/gpt-latest",
@@ -12680,6 +12663,23 @@ export const MODELS = {
12680
12663
  contextWindow: 1000000,
12681
12664
  maxTokens: 64000,
12682
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
+ },
12683
12683
  "google/gemini-3.1-flash-lite-preview": {
12684
12684
  id: "google/gemini-3.1-flash-lite-preview",
12685
12685
  name: "Gemini 3.1 Flash Lite Preview",
@@ -13241,23 +13241,6 @@ export const MODELS = {
13241
13241
  contextWindow: 131072,
13242
13242
  maxTokens: 131072,
13243
13243
  },
13244
- "moonshotai/kimi-k2-0905": {
13245
- id: "moonshotai/kimi-k2-0905",
13246
- name: "Kimi K2 0905",
13247
- api: "anthropic-messages",
13248
- provider: "vercel-ai-gateway",
13249
- baseUrl: "https://ai-gateway.vercel.sh",
13250
- reasoning: false,
13251
- input: ["text"],
13252
- cost: {
13253
- input: 0.6,
13254
- output: 2.5,
13255
- cacheRead: 0.3,
13256
- cacheWrite: 0,
13257
- },
13258
- contextWindow: 256000,
13259
- maxTokens: 128000,
13260
- },
13261
13244
  "moonshotai/kimi-k2-thinking": {
13262
13245
  id: "moonshotai/kimi-k2-thinking",
13263
13246
  name: "Kimi K2 Thinking",
@@ -14202,8 +14185,8 @@ export const MODELS = {
14202
14185
  reasoning: true,
14203
14186
  input: ["text", "image"],
14204
14187
  cost: {
14205
- input: 2,
14206
- output: 6,
14188
+ input: 1.25,
14189
+ output: 2.5,
14207
14190
  cacheRead: 0.19999999999999998,
14208
14191
  cacheWrite: 0,
14209
14192
  },
@@ -14219,8 +14202,8 @@ export const MODELS = {
14219
14202
  reasoning: true,
14220
14203
  input: ["text", "image"],
14221
14204
  cost: {
14222
- input: 2,
14223
- output: 6,
14205
+ input: 1.25,
14206
+ output: 2.5,
14224
14207
  cacheRead: 0.19999999999999998,
14225
14208
  cacheWrite: 0,
14226
14209
  },
@@ -14236,8 +14219,8 @@ export const MODELS = {
14236
14219
  reasoning: false,
14237
14220
  input: ["text", "image"],
14238
14221
  cost: {
14239
- input: 2,
14240
- output: 6,
14222
+ input: 1.25,
14223
+ output: 2.5,
14241
14224
  cacheRead: 0.19999999999999998,
14242
14225
  cacheWrite: 0,
14243
14226
  },
@@ -14253,8 +14236,8 @@ export const MODELS = {
14253
14236
  reasoning: false,
14254
14237
  input: ["text", "image"],
14255
14238
  cost: {
14256
- input: 2,
14257
- output: 6,
14239
+ input: 1.25,
14240
+ output: 2.5,
14258
14241
  cacheRead: 0.19999999999999998,
14259
14242
  cacheWrite: 0,
14260
14243
  },
@@ -14270,8 +14253,8 @@ export const MODELS = {
14270
14253
  reasoning: true,
14271
14254
  input: ["text", "image"],
14272
14255
  cost: {
14273
- input: 2,
14274
- output: 6,
14256
+ input: 1.25,
14257
+ output: 2.5,
14275
14258
  cacheRead: 0.19999999999999998,
14276
14259
  cacheWrite: 0,
14277
14260
  },
@@ -14287,8 +14270,8 @@ export const MODELS = {
14287
14270
  reasoning: true,
14288
14271
  input: ["text", "image"],
14289
14272
  cost: {
14290
- input: 2,
14291
- output: 6,
14273
+ input: 1.25,
14274
+ output: 2.5,
14292
14275
  cacheRead: 0.19999999999999998,
14293
14276
  cacheWrite: 0,
14294
14277
  },