@fleetagent/pi-ai 0.2.6 → 0.2.7

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.
@@ -7984,80 +7984,6 @@ export const MODELS = {
7984
7984
  maxTokens: 131072,
7985
7985
  },
7986
7986
  },
7987
- "kimi-coding": {
7988
- "k3": {
7989
- id: "k3",
7990
- name: "Kimi K3",
7991
- api: "anthropic-messages",
7992
- provider: "kimi-coding",
7993
- baseUrl: "https://api.kimi.com/coding",
7994
- headers: { "User-Agent": "KimiCLI/1.5" },
7995
- reasoning: true,
7996
- input: ["text", "image"],
7997
- cost: {
7998
- input: 0,
7999
- output: 0,
8000
- cacheRead: 0,
8001
- cacheWrite: 0,
8002
- },
8003
- contextWindow: 1048576,
8004
- maxTokens: 131072,
8005
- },
8006
- "k3-256k": {
8007
- id: "k3-256k",
8008
- name: "Kimi K3-256K",
8009
- api: "anthropic-messages",
8010
- provider: "kimi-coding",
8011
- baseUrl: "https://api.kimi.com/coding",
8012
- headers: { "User-Agent": "KimiCLI/1.5" },
8013
- reasoning: true,
8014
- input: ["text", "image"],
8015
- cost: {
8016
- input: 0,
8017
- output: 0,
8018
- cacheRead: 0,
8019
- cacheWrite: 0,
8020
- },
8021
- contextWindow: 262144,
8022
- maxTokens: 131072,
8023
- },
8024
- "kimi-for-coding": {
8025
- id: "kimi-for-coding",
8026
- name: "kimi-for-coding",
8027
- api: "anthropic-messages",
8028
- provider: "kimi-coding",
8029
- baseUrl: "https://api.kimi.com/coding",
8030
- headers: { "User-Agent": "KimiCLI/1.5" },
8031
- reasoning: true,
8032
- input: ["text", "image"],
8033
- cost: {
8034
- input: 0,
8035
- output: 0,
8036
- cacheRead: 0,
8037
- cacheWrite: 0,
8038
- },
8039
- contextWindow: 1048576,
8040
- maxTokens: 32768,
8041
- },
8042
- "kimi-for-coding-highspeed": {
8043
- id: "kimi-for-coding-highspeed",
8044
- name: "Kimi For Coding HighSpeed",
8045
- api: "anthropic-messages",
8046
- provider: "kimi-coding",
8047
- baseUrl: "https://api.kimi.com/coding",
8048
- headers: { "User-Agent": "KimiCLI/1.5" },
8049
- reasoning: true,
8050
- input: ["text", "image"],
8051
- cost: {
8052
- input: 0,
8053
- output: 0,
8054
- cacheRead: 0,
8055
- cacheWrite: 0,
8056
- },
8057
- contextWindow: 262144,
8058
- maxTokens: 32768,
8059
- },
8060
- },
8061
7987
  "minimax": {
8062
7988
  "MiniMax-M2.7": {
8063
7989
  id: "MiniMax-M2.7",
@@ -8675,6 +8601,23 @@ export const MODELS = {
8675
8601
  contextWindow: 1000000,
8676
8602
  maxTokens: 131072,
8677
8603
  },
8604
+ "zai-glm-5-3": {
8605
+ id: "zai-glm-5-3",
8606
+ name: "GLM-5.3",
8607
+ api: "mistral-conversations",
8608
+ provider: "mistral",
8609
+ baseUrl: "https://api.mistral.ai",
8610
+ reasoning: true,
8611
+ input: ["text"],
8612
+ cost: {
8613
+ input: 1.4,
8614
+ output: 4.4,
8615
+ cacheRead: 0.14,
8616
+ cacheWrite: 0,
8617
+ },
8618
+ contextWindow: 1000000,
8619
+ maxTokens: 131072,
8620
+ },
8678
8621
  },
8679
8622
  "moonshotai": {
8680
8623
  "kimi-k2.6": {
@@ -10050,6 +9993,25 @@ export const MODELS = {
10050
9993
  contextWindow: 1000000,
10051
9994
  maxTokens: 384000,
10052
9995
  },
9996
+ "deepseek-v4.1-flash": {
9997
+ id: "deepseek-v4.1-flash",
9998
+ name: "DeepSeek V4.1 Flash",
9999
+ api: "openai-completions",
10000
+ provider: "opencode",
10001
+ baseUrl: "https://opencode.ai/zen/v1",
10002
+ compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
10003
+ reasoning: true,
10004
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
10005
+ input: ["text", "image"],
10006
+ cost: {
10007
+ input: 0.3,
10008
+ output: 1.2,
10009
+ cacheRead: 0.006,
10010
+ cacheWrite: 0,
10011
+ },
10012
+ contextWindow: 1000000,
10013
+ maxTokens: 384000,
10014
+ },
10053
10015
  "gemini-3-flash": {
10054
10016
  id: "gemini-3-flash",
10055
10017
  name: "Gemini 3 Flash",
@@ -10569,7 +10531,7 @@ export const MODELS = {
10569
10531
  },
10570
10532
  "gpt-5.6-sol": {
10571
10533
  id: "gpt-5.6-sol",
10572
- name: "GPT-5.6 Sol (50% Off)",
10534
+ name: "GPT-5.6 Sol",
10573
10535
  api: "openai-responses",
10574
10536
  provider: "opencode",
10575
10537
  baseUrl: "https://opencode.ai/zen/v1",
@@ -10577,10 +10539,10 @@ export const MODELS = {
10577
10539
  thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
10578
10540
  input: ["text", "image"],
10579
10541
  cost: {
10580
- input: 2,
10581
- output: 10,
10582
- cacheRead: 0.2,
10583
- cacheWrite: 2.5,
10542
+ input: 4,
10543
+ output: 20,
10544
+ cacheRead: 0.4,
10545
+ cacheWrite: 5,
10584
10546
  },
10585
10547
  contextWindow: 1050000,
10586
10548
  maxTokens: 128000,
@@ -10964,21 +10926,21 @@ export const MODELS = {
10964
10926
  contextWindow: 262144,
10965
10927
  maxTokens: 65536,
10966
10928
  },
10967
- "union-alpha": {
10968
- id: "union-alpha",
10969
- name: "Union Alpha Free",
10929
+ "qwen3.8-flash": {
10930
+ id: "qwen3.8-flash",
10931
+ name: "Qwen3.8 Flash",
10970
10932
  api: "anthropic-messages",
10971
10933
  provider: "opencode",
10972
10934
  baseUrl: "https://opencode.ai/zen",
10973
10935
  reasoning: true,
10974
10936
  input: ["text", "image"],
10975
10937
  cost: {
10976
- input: 0,
10977
- output: 0,
10978
- cacheRead: 0,
10979
- cacheWrite: 0,
10938
+ input: 0.15,
10939
+ output: 0.47,
10940
+ cacheRead: 0.016,
10941
+ cacheWrite: 0.2,
10980
10942
  },
10981
- contextWindow: 262144,
10943
+ contextWindow: 1000000,
10982
10944
  maxTokens: 131072,
10983
10945
  },
10984
10946
  },
@@ -11454,23 +11416,6 @@ export const MODELS = {
11454
11416
  contextWindow: 1000000,
11455
11417
  maxTokens: 131072,
11456
11418
  },
11457
- "union-alpha": {
11458
- id: "union-alpha",
11459
- name: "Union Alpha Free",
11460
- api: "anthropic-messages",
11461
- provider: "opencode-go",
11462
- baseUrl: "https://opencode.ai/zen/go",
11463
- reasoning: true,
11464
- input: ["text", "image"],
11465
- cost: {
11466
- input: 0,
11467
- output: 0,
11468
- cacheRead: 0,
11469
- cacheWrite: 0,
11470
- },
11471
- contextWindow: 262144,
11472
- maxTokens: 131072,
11473
- },
11474
11419
  },
11475
11420
  "openrouter": {
11476
11421
  "aion-labs/aion-2.0": {
@@ -12268,13 +12213,13 @@ export const MODELS = {
12268
12213
  reasoning: false,
12269
12214
  input: ["text"],
12270
12215
  cost: {
12271
- input: 0.2574,
12272
- output: 1.0287,
12216
+ input: 0.32,
12217
+ output: 0.8899999999999999,
12273
12218
  cacheRead: 0,
12274
12219
  cacheWrite: 0,
12275
12220
  },
12276
12221
  contextWindow: 163840,
12277
- maxTokens: 16000,
12222
+ maxTokens: 16384,
12278
12223
  },
12279
12224
  "deepseek/deepseek-chat-v3-0324": {
12280
12225
  id: "deepseek/deepseek-chat-v3-0324",
@@ -12406,9 +12351,9 @@ export const MODELS = {
12406
12351
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
12407
12352
  input: ["text"],
12408
12353
  cost: {
12409
- input: 0.07,
12410
- output: 0.14,
12411
- cacheRead: 0.014,
12354
+ input: 0.04396,
12355
+ output: 0.08792,
12356
+ cacheRead: 0.008792,
12412
12357
  cacheWrite: 0,
12413
12358
  },
12414
12359
  contextWindow: 1048576,
@@ -12425,9 +12370,9 @@ export const MODELS = {
12425
12370
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
12426
12371
  input: ["text"],
12427
12372
  cost: {
12428
- input: 0.06,
12429
- output: 0.12,
12430
- cacheRead: 0.012,
12373
+ input: 0.04,
12374
+ output: 0.08,
12375
+ cacheRead: 0.016,
12431
12376
  cacheWrite: 0,
12432
12377
  },
12433
12378
  contextWindow: 1310720,
@@ -12452,6 +12397,25 @@ export const MODELS = {
12452
12397
  contextWindow: 1048576,
12453
12398
  maxTokens: 943718,
12454
12399
  },
12400
+ "deepseek/deepseek-v4-flash-0731:free": {
12401
+ id: "deepseek/deepseek-v4-flash-0731:free",
12402
+ name: "DeepSeek: DeepSeek V4 Flash 0731 (free)",
12403
+ api: "openai-completions",
12404
+ provider: "openrouter",
12405
+ baseUrl: "https://openrouter.ai/api/v1",
12406
+ compat: { "requiresReasoningContentOnAssistantMessages": true },
12407
+ reasoning: true,
12408
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
12409
+ input: ["text"],
12410
+ cost: {
12411
+ input: 0,
12412
+ output: 0,
12413
+ cacheRead: 0,
12414
+ cacheWrite: 0,
12415
+ },
12416
+ contextWindow: 1048576,
12417
+ maxTokens: 393216,
12418
+ },
12455
12419
  "deepseek/deepseek-v4-flash-vision-exp": {
12456
12420
  id: "deepseek/deepseek-v4-flash-vision-exp",
12457
12421
  name: "DeepSeek: DeepSeek V4 Flash Vision Exp",
@@ -12463,13 +12427,13 @@ export const MODELS = {
12463
12427
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
12464
12428
  input: ["text", "image"],
12465
12429
  cost: {
12466
- input: 0.22,
12467
- output: 0.66,
12468
- cacheRead: 0.007,
12430
+ input: 0.21559999999999999,
12431
+ output: 0.6468,
12432
+ cacheRead: 0.00686,
12469
12433
  cacheWrite: 0,
12470
12434
  },
12471
12435
  contextWindow: 1048576,
12472
- maxTokens: 943718,
12436
+ maxTokens: 262144,
12473
12437
  },
12474
12438
  "deepseek/deepseek-v4-flash-vision-exp:batch": {
12475
12439
  id: "deepseek/deepseek-v4-flash-vision-exp:batch",
@@ -12501,13 +12465,13 @@ export const MODELS = {
12501
12465
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
12502
12466
  input: ["text"],
12503
12467
  cost: {
12504
- input: 1.5999999999999999,
12505
- output: 3.1999999999999997,
12506
- cacheRead: 0.135,
12468
+ input: 0.45274800000000004,
12469
+ output: 0.9054960000000001,
12470
+ cacheRead: 0.037729,
12507
12471
  cacheWrite: 0,
12508
12472
  },
12509
12473
  contextWindow: 1048576,
12510
- maxTokens: 393216,
12474
+ maxTokens: 384000,
12511
12475
  },
12512
12476
  "deepseek/deepseek-v4-pro-0813": {
12513
12477
  id: "deepseek/deepseek-v4-pro-0813",
@@ -12520,9 +12484,9 @@ export const MODELS = {
12520
12484
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
12521
12485
  input: ["text"],
12522
12486
  cost: {
12523
- input: 0.57948,
12524
- output: 1.73844,
12525
- cacheRead: 0.018438,
12487
+ input: 0.57816,
12488
+ output: 1.73448,
12489
+ cacheRead: 0.018396000000000003,
12526
12490
  cacheWrite: 0,
12527
12491
  },
12528
12492
  contextWindow: 1048576,
@@ -13444,8 +13408,8 @@ export const MODELS = {
13444
13408
  reasoning: true,
13445
13409
  input: ["text", "image"],
13446
13410
  cost: {
13447
- input: 0.3,
13448
- output: 1.1,
13411
+ input: 0.35,
13412
+ output: 1.5,
13449
13413
  cacheRead: 0.04,
13450
13414
  cacheWrite: 0,
13451
13415
  },
@@ -13826,23 +13790,6 @@ export const MODELS = {
13826
13790
  contextWindow: 131072,
13827
13791
  maxTokens: 104857,
13828
13792
  },
13829
- "mistralai/mistral-large-2512": {
13830
- id: "mistralai/mistral-large-2512",
13831
- name: "Mistral: Mistral Large 3 2512",
13832
- api: "openai-completions",
13833
- provider: "openrouter",
13834
- baseUrl: "https://openrouter.ai/api/v1",
13835
- reasoning: false,
13836
- input: ["text", "image"],
13837
- cost: {
13838
- input: 0.5,
13839
- output: 1.5,
13840
- cacheRead: 0.049999999999999996,
13841
- cacheWrite: 0,
13842
- },
13843
- contextWindow: 262144,
13844
- maxTokens: 209715,
13845
- },
13846
13793
  "mistralai/mistral-large-2512:batch": {
13847
13794
  id: "mistralai/mistral-large-2512:batch",
13848
13795
  name: "Mistral: Mistral Large 3 2512 (batch)",
@@ -14176,9 +14123,9 @@ export const MODELS = {
14176
14123
  reasoning: true,
14177
14124
  input: ["text", "image"],
14178
14125
  cost: {
14179
- input: 3,
14180
- output: 15,
14181
- cacheRead: 0.3,
14126
+ input: 1.7,
14127
+ output: 8.5,
14128
+ cacheRead: 0.16999999999999998,
14182
14129
  cacheWrite: 0,
14183
14130
  },
14184
14131
  contextWindow: 1048576,
@@ -14312,13 +14259,13 @@ export const MODELS = {
14312
14259
  reasoning: true,
14313
14260
  input: ["text"],
14314
14261
  cost: {
14315
- input: 0.625,
14316
- output: 3.125,
14317
- cacheRead: 0.1875,
14262
+ input: 0.6,
14263
+ output: 2.4,
14264
+ cacheRead: 0.12,
14318
14265
  cacheWrite: 0,
14319
14266
  },
14320
14267
  contextWindow: 262144,
14321
- maxTokens: 32768,
14268
+ maxTokens: 182520,
14322
14269
  },
14323
14270
  "nvidia/nemotron-3-ultra-550b-a55b:free": {
14324
14271
  id: "nvidia/nemotron-3-ultra-550b-a55b:free",
@@ -14346,13 +14293,13 @@ export const MODELS = {
14346
14293
  reasoning: true,
14347
14294
  input: ["text"],
14348
14295
  cost: {
14349
- input: 0.08,
14296
+ input: 0.07,
14350
14297
  output: 0.19999999999999998,
14351
14298
  cacheRead: 0.04,
14352
14299
  cacheWrite: 0,
14353
14300
  },
14354
14301
  contextWindow: 262144,
14355
- maxTokens: 131072,
14302
+ maxTokens: 235929,
14356
14303
  },
14357
14304
  "nvidia/nemotron-3.5-lightning:free": {
14358
14305
  id: "nvidia/nemotron-3.5-lightning:free",
@@ -15639,13 +15586,13 @@ export const MODELS = {
15639
15586
  reasoning: true,
15640
15587
  input: ["text"],
15641
15588
  cost: {
15642
- input: 0.037,
15643
- output: 0.16999999999999998,
15644
- cacheRead: 0,
15589
+ input: 0.15,
15590
+ output: 0.6,
15591
+ cacheRead: 0.075,
15645
15592
  cacheWrite: 0,
15646
15593
  },
15647
15594
  contextWindow: 131072,
15648
- maxTokens: 117964,
15595
+ maxTokens: 65536,
15649
15596
  },
15650
15597
  "openai/gpt-oss-120b:batch": {
15651
15598
  id: "openai/gpt-oss-120b:batch",
@@ -15987,6 +15934,23 @@ export const MODELS = {
15987
15934
  contextWindow: 262144,
15988
15935
  maxTokens: 32768,
15989
15936
  },
15937
+ "prism-ml/ternary-bonsai-2-27b": {
15938
+ id: "prism-ml/ternary-bonsai-2-27b",
15939
+ name: "PrismML: Ternary Bonsai 2 27B",
15940
+ api: "openai-completions",
15941
+ provider: "openrouter",
15942
+ baseUrl: "https://openrouter.ai/api/v1",
15943
+ reasoning: true,
15944
+ input: ["text", "image"],
15945
+ cost: {
15946
+ input: 0.075,
15947
+ output: 0.5,
15948
+ cacheRead: 0,
15949
+ cacheWrite: 0,
15950
+ },
15951
+ contextWindow: 262144,
15952
+ maxTokens: 32768,
15953
+ },
15990
15954
  "qwen/qwen-2.5-72b-instruct": {
15991
15955
  id: "qwen/qwen-2.5-72b-instruct",
15992
15956
  name: "Qwen2.5 72B Instruct",
@@ -16404,8 +16368,8 @@ export const MODELS = {
16404
16368
  reasoning: false,
16405
16369
  input: ["text", "image"],
16406
16370
  cost: {
16407
- input: 0.13,
16408
- output: 0.52,
16371
+ input: 0.19999999999999998,
16372
+ output: 0.7,
16409
16373
  cacheRead: 0,
16410
16374
  cacheWrite: 0,
16411
16375
  },
@@ -16820,6 +16784,23 @@ export const MODELS = {
16820
16784
  contextWindow: 1000000,
16821
16785
  maxTokens: 131072,
16822
16786
  },
16787
+ "qwen/qwen3.8-27b:free": {
16788
+ id: "qwen/qwen3.8-27b:free",
16789
+ name: "Qwen: Qwen3.8 27B (free)",
16790
+ api: "openai-completions",
16791
+ provider: "openrouter",
16792
+ baseUrl: "https://openrouter.ai/api/v1",
16793
+ reasoning: true,
16794
+ input: ["text", "image"],
16795
+ cost: {
16796
+ input: 0,
16797
+ output: 0,
16798
+ cacheRead: 0,
16799
+ cacheWrite: 0,
16800
+ },
16801
+ contextWindow: 262144,
16802
+ maxTokens: 235929,
16803
+ },
16823
16804
  "qwen/qwen3.8-flash": {
16824
16805
  id: "qwen/qwen3.8-flash",
16825
16806
  name: "Qwen: Qwen3.8 Flash",
@@ -16973,23 +16954,6 @@ export const MODELS = {
16973
16954
  contextWindow: 131072,
16974
16955
  maxTokens: 16384,
16975
16956
  },
16976
- "stealth/union-alpha": {
16977
- id: "stealth/union-alpha",
16978
- name: "Union Alpha",
16979
- api: "openai-completions",
16980
- provider: "openrouter",
16981
- baseUrl: "https://openrouter.ai/api/v1",
16982
- reasoning: false,
16983
- input: ["text", "image"],
16984
- cost: {
16985
- input: 0,
16986
- output: 0,
16987
- cacheRead: 0,
16988
- cacheWrite: 0,
16989
- },
16990
- contextWindow: 262144,
16991
- maxTokens: 131072,
16992
- },
16993
16957
  "stepfun/step-3.5-flash": {
16994
16958
  id: "stepfun/step-3.5-flash",
16995
16959
  name: "StepFun: Step 3.5 Flash",
@@ -17033,9 +16997,9 @@ export const MODELS = {
17033
16997
  reasoning: true,
17034
16998
  input: ["text"],
17035
16999
  cost: {
17036
- input: 0.0825,
17037
- output: 0.33,
17038
- cacheRead: 0.020625,
17000
+ input: 0.13199999999999998,
17001
+ output: 0.5279999999999999,
17002
+ cacheRead: 0.032999999999999995,
17039
17003
  cacheWrite: 0,
17040
17004
  },
17041
17005
  contextWindow: 262144,
@@ -17160,6 +17124,23 @@ export const MODELS = {
17160
17124
  contextWindow: 1048576,
17161
17125
  maxTokens: 262144,
17162
17126
  },
17127
+ "unbiased/pareto": {
17128
+ id: "unbiased/pareto",
17129
+ name: "Pareto",
17130
+ api: "openai-completions",
17131
+ provider: "openrouter",
17132
+ baseUrl: "https://openrouter.ai/api/v1",
17133
+ reasoning: false,
17134
+ input: ["text", "image"],
17135
+ cost: {
17136
+ input: 2.5,
17137
+ output: 7.5,
17138
+ cacheRead: 0.25,
17139
+ cacheWrite: 0,
17140
+ },
17141
+ contextWindow: 262144,
17142
+ maxTokens: 131072,
17143
+ },
17163
17144
  "upstage/solar-pro-3": {
17164
17145
  id: "upstage/solar-pro-3",
17165
17146
  name: "Upstage: Solar Pro 3",
@@ -17509,9 +17490,9 @@ export const MODELS = {
17509
17490
  reasoning: true,
17510
17491
  input: ["text"],
17511
17492
  cost: {
17512
- input: 1.4,
17513
- output: 4.4,
17514
- cacheRead: 0.14,
17493
+ input: 0.5544,
17494
+ output: 1.7424,
17495
+ cacheRead: 0.10296000000000001,
17515
17496
  cacheWrite: 0,
17516
17497
  },
17517
17498
  contextWindow: 1048576,
@@ -17543,13 +17524,13 @@ export const MODELS = {
17543
17524
  reasoning: true,
17544
17525
  input: ["text"],
17545
17526
  cost: {
17546
- input: 1.4,
17547
- output: 4.4,
17548
- cacheRead: 0.26,
17527
+ input: 0.9099999999999999,
17528
+ output: 2.8600000000000003,
17529
+ cacheRead: 0.16899999999999998,
17549
17530
  cacheWrite: 0,
17550
17531
  },
17551
17532
  contextWindow: 1310720,
17552
- maxTokens: 943717,
17533
+ maxTokens: 131072,
17553
17534
  },
17554
17535
  "z-ai/glm-5.3-flash": {
17555
17536
  id: "z-ai/glm-5.3-flash",
@@ -17585,6 +17566,23 @@ export const MODELS = {
17585
17566
  contextWindow: 1048576,
17586
17567
  maxTokens: 943718,
17587
17568
  },
17569
+ "z-ai/glm-5.3-flashx": {
17570
+ id: "z-ai/glm-5.3-flashx",
17571
+ name: "Z.ai: GLM 5.3 FlashX",
17572
+ api: "openai-completions",
17573
+ provider: "openrouter",
17574
+ baseUrl: "https://openrouter.ai/api/v1",
17575
+ reasoning: true,
17576
+ input: ["text", "image"],
17577
+ cost: {
17578
+ input: 0.37,
17579
+ output: 1.25,
17580
+ cacheRead: 0.075,
17581
+ cacheWrite: 0,
17582
+ },
17583
+ contextWindow: 1048576,
17584
+ maxTokens: 131072,
17585
+ },
17588
17586
  "z-ai/glm-5.3:batch": {
17589
17587
  id: "z-ai/glm-5.3:batch",
17590
17588
  name: "Z.ai: GLM 5.3 (batch)",
@@ -17696,13 +17694,13 @@ export const MODELS = {
17696
17694
  reasoning: true,
17697
17695
  input: ["text", "image"],
17698
17696
  cost: {
17699
- input: 0.15,
17700
- output: 0.6,
17701
- cacheRead: 0.015,
17697
+ input: 0.13,
17698
+ output: 0.52,
17699
+ cacheRead: 0.0026000000000000003,
17702
17700
  cacheWrite: 0,
17703
17701
  },
17704
17702
  contextWindow: 1048576,
17705
- maxTokens: 393216,
17703
+ maxTokens: 943718,
17706
17704
  },
17707
17705
  "~deepseek/deepseek-pro-latest": {
17708
17706
  id: "~deepseek/deepseek-pro-latest",
@@ -17713,9 +17711,9 @@ export const MODELS = {
17713
17711
  reasoning: true,
17714
17712
  input: ["text"],
17715
17713
  cost: {
17716
- input: 0.57948,
17717
- output: 1.73844,
17718
- cacheRead: 0.018438,
17714
+ input: 0.57816,
17715
+ output: 1.73448,
17716
+ cacheRead: 0.018396000000000003,
17719
17717
  cacheWrite: 0,
17720
17718
  },
17721
17719
  contextWindow: 1048576,
@@ -17732,13 +17730,13 @@ export const MODELS = {
17732
17730
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
17733
17731
  input: ["text"],
17734
17732
  cost: {
17735
- input: 0.03,
17736
- output: 0.13,
17737
- cacheRead: 0.01,
17733
+ input: 0.04,
17734
+ output: 0.08,
17735
+ cacheRead: 0.016,
17738
17736
  cacheWrite: 0,
17739
17737
  },
17740
17738
  contextWindow: 1310720,
17741
- maxTokens: 393216,
17739
+ maxTokens: 943718,
17742
17740
  },
17743
17741
  "~google/gemini-flash-latest": {
17744
17742
  id: "~google/gemini-flash-latest",
@@ -17783,9 +17781,9 @@ export const MODELS = {
17783
17781
  reasoning: true,
17784
17782
  input: ["text", "image"],
17785
17783
  cost: {
17786
- input: 1.875,
17787
- output: 10.5,
17788
- cacheRead: 0.2175,
17784
+ input: 1.7,
17785
+ output: 8.5,
17786
+ cacheRead: 0.16999999999999998,
17789
17787
  cacheWrite: 0,
17790
17788
  },
17791
17789
  contextWindow: 1048576,
@@ -17919,13 +17917,13 @@ export const MODELS = {
17919
17917
  reasoning: true,
17920
17918
  input: ["text"],
17921
17919
  cost: {
17922
- input: 0.8775,
17923
- output: 2.9699999999999998,
17924
- cacheRead: 0.1755,
17920
+ input: 0.8917999999999999,
17921
+ output: 2.8028,
17922
+ cacheRead: 0.16562,
17925
17923
  cacheWrite: 0,
17926
17924
  },
17927
17925
  contextWindow: 1310720,
17928
- maxTokens: 235929,
17926
+ maxTokens: 131072,
17929
17927
  },
17930
17928
  },
17931
17929
  "together": {
@@ -18856,6 +18854,23 @@ export const MODELS = {
18856
18854
  contextWindow: 991000,
18857
18855
  maxTokens: 128000,
18858
18856
  },
18857
+ "alibaba/qwen3.8-omni-flash": {
18858
+ id: "alibaba/qwen3.8-omni-flash",
18859
+ name: "Qwen 3.8 Omni Flash",
18860
+ api: "anthropic-messages",
18861
+ provider: "vercel-ai-gateway",
18862
+ baseUrl: "https://ai-gateway.vercel.sh",
18863
+ reasoning: true,
18864
+ input: ["text", "image"],
18865
+ cost: {
18866
+ input: 0.15,
18867
+ output: 0.47,
18868
+ cacheRead: 0.016,
18869
+ cacheWrite: 0,
18870
+ },
18871
+ contextWindow: 1000000,
18872
+ maxTokens: 131072,
18873
+ },
18859
18874
  "amazon/nova-2-lite": {
18860
18875
  id: "amazon/nova-2-lite",
18861
18876
  name: "Nova 2 Lite",
@@ -21304,10 +21319,10 @@ export const MODELS = {
21304
21319
  thinkingLevelMap: { "xhigh": "xhigh" },
21305
21320
  input: ["text", "image"],
21306
21321
  cost: {
21307
- input: 2,
21308
- output: 10,
21309
- cacheRead: 0.19999999999999998,
21310
- cacheWrite: 2.5,
21322
+ input: 4,
21323
+ output: 20,
21324
+ cacheRead: 0.39999999999999997,
21325
+ cacheWrite: 5,
21311
21326
  },
21312
21327
  contextWindow: 1050000,
21313
21328
  maxTokens: 128000,
@@ -21322,10 +21337,10 @@ export const MODELS = {
21322
21337
  thinkingLevelMap: { "xhigh": "xhigh" },
21323
21338
  input: ["text", "image"],
21324
21339
  cost: {
21325
- input: 4,
21326
- output: 20,
21327
- cacheRead: 0.39999999999999997,
21328
- cacheWrite: 5,
21340
+ input: 8,
21341
+ output: 40,
21342
+ cacheRead: 0.7999999999999999,
21343
+ cacheWrite: 10,
21329
21344
  },
21330
21345
  contextWindow: 1050000,
21331
21346
  maxTokens: 128000,
@@ -22286,6 +22301,23 @@ export const MODELS = {
22286
22301
  contextWindow: 1000000,
22287
22302
  maxTokens: 131000,
22288
22303
  },
22304
+ "zai/glm-5.3-flashx": {
22305
+ id: "zai/glm-5.3-flashx",
22306
+ name: "GLM 5.3 FlashX",
22307
+ api: "anthropic-messages",
22308
+ provider: "vercel-ai-gateway",
22309
+ baseUrl: "https://ai-gateway.vercel.sh",
22310
+ reasoning: true,
22311
+ input: ["text", "image"],
22312
+ cost: {
22313
+ input: 0.37,
22314
+ output: 1.25,
22315
+ cacheRead: 0.075,
22316
+ cacheWrite: 0,
22317
+ },
22318
+ contextWindow: 1000000,
22319
+ maxTokens: 131072,
22320
+ },
22289
22321
  "zai/glm-5v-turbo": {
22290
22322
  id: "zai/glm-5v-turbo",
22291
22323
  name: "GLM 5V Turbo",