@elyracode/ai 0.9.38 → 0.9.40

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.
@@ -4292,6 +4292,23 @@ export const MODELS = {
4292
4292
  contextWindow: 1050000,
4293
4293
  maxTokens: 128000,
4294
4294
  },
4295
+ "gpt-6-astra": {
4296
+ id: "gpt-6-astra",
4297
+ name: "GPT-6 Astra",
4298
+ api: "openai-responses",
4299
+ provider: "cloudflare-ai-gateway",
4300
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
4301
+ reasoning: true,
4302
+ input: ["text", "image"],
4303
+ cost: {
4304
+ input: 10,
4305
+ output: 50,
4306
+ cacheRead: 1,
4307
+ cacheWrite: 12,
4308
+ },
4309
+ contextWindow: 1050000,
4310
+ maxTokens: 128000,
4311
+ },
4295
4312
  "o3": {
4296
4313
  id: "o3",
4297
4314
  name: "o3",
@@ -4968,23 +4985,6 @@ export const MODELS = {
4968
4985
  contextWindow: 512000,
4969
4986
  maxTokens: 512000,
4970
4987
  },
4971
- "accounts/fireworks/models/mistral-large-3-fp8": {
4972
- id: "accounts/fireworks/models/mistral-large-3-fp8",
4973
- name: "Mistral Large 3 675B Instruct 2512",
4974
- api: "anthropic-messages",
4975
- provider: "fireworks",
4976
- baseUrl: "https://api.fireworks.ai/inference",
4977
- reasoning: false,
4978
- input: ["text", "image"],
4979
- cost: {
4980
- input: 0,
4981
- output: 0,
4982
- cacheRead: 0,
4983
- cacheWrite: 0,
4984
- },
4985
- contextWindow: 262144,
4986
- maxTokens: 262144,
4987
- },
4988
4988
  "accounts/fireworks/models/muse-glimmer-30b": {
4989
4989
  id: "accounts/fireworks/models/muse-glimmer-30b",
4990
4990
  name: "Muse Glimmer 30B",
@@ -8624,6 +8624,23 @@ export const MODELS = {
8624
8624
  contextWindow: 1000000,
8625
8625
  maxTokens: 131072,
8626
8626
  },
8627
+ "zai-glm-5-3": {
8628
+ id: "zai-glm-5-3",
8629
+ name: "GLM-5.3",
8630
+ api: "mistral-conversations",
8631
+ provider: "mistral",
8632
+ baseUrl: "https://api.mistral.ai",
8633
+ reasoning: true,
8634
+ input: ["text"],
8635
+ cost: {
8636
+ input: 1.4,
8637
+ output: 4.4,
8638
+ cacheRead: 0.14,
8639
+ cacheWrite: 0,
8640
+ },
8641
+ contextWindow: 1000000,
8642
+ maxTokens: 131072,
8643
+ },
8627
8644
  },
8628
8645
  "moonshotai": {
8629
8646
  "kimi-k2.6": {
@@ -10428,7 +10445,7 @@ export const MODELS = {
10428
10445
  },
10429
10446
  "gpt-5.6-sol": {
10430
10447
  id: "gpt-5.6-sol",
10431
- name: "GPT-5.6 Sol (50% Off)",
10448
+ name: "GPT-5.6 Sol",
10432
10449
  api: "openai-responses",
10433
10450
  provider: "opencode",
10434
10451
  baseUrl: "https://opencode.ai/zen/v1",
@@ -10436,10 +10453,10 @@ export const MODELS = {
10436
10453
  thinkingLevelMap: { "off": null },
10437
10454
  input: ["text", "image"],
10438
10455
  cost: {
10439
- input: 2,
10440
- output: 10,
10441
- cacheRead: 0.2,
10442
- cacheWrite: 2.5,
10456
+ input: 4,
10457
+ output: 20,
10458
+ cacheRead: 0.4,
10459
+ cacheWrite: 5,
10443
10460
  },
10444
10461
  contextWindow: 1050000,
10445
10462
  maxTokens: 128000,
@@ -12093,13 +12110,13 @@ export const MODELS = {
12093
12110
  reasoning: false,
12094
12111
  input: ["text"],
12095
12112
  cost: {
12096
- input: 0.2574,
12097
- output: 1.0287,
12113
+ input: 0.32,
12114
+ output: 0.8899999999999999,
12098
12115
  cacheRead: 0,
12099
12116
  cacheWrite: 0,
12100
12117
  },
12101
12118
  contextWindow: 163840,
12102
- maxTokens: 16000,
12119
+ maxTokens: 16384,
12103
12120
  },
12104
12121
  "deepseek/deepseek-chat-v3-0324": {
12105
12122
  id: "deepseek/deepseek-chat-v3-0324",
@@ -12231,9 +12248,9 @@ export const MODELS = {
12231
12248
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12232
12249
  input: ["text"],
12233
12250
  cost: {
12234
- input: 0.088606,
12235
- output: 0.177212,
12236
- cacheRead: 0.017721200000000003,
12251
+ input: 0.048440000000000004,
12252
+ output: 0.09688000000000001,
12253
+ cacheRead: 0.009688,
12237
12254
  cacheWrite: 0,
12238
12255
  },
12239
12256
  contextWindow: 1048576,
@@ -12277,6 +12294,25 @@ export const MODELS = {
12277
12294
  contextWindow: 1048576,
12278
12295
  maxTokens: 943718,
12279
12296
  },
12297
+ "deepseek/deepseek-v4-flash-0731:free": {
12298
+ id: "deepseek/deepseek-v4-flash-0731:free",
12299
+ name: "DeepSeek: DeepSeek V4 Flash 0731 (free)",
12300
+ api: "openai-completions",
12301
+ provider: "openrouter",
12302
+ baseUrl: "https://openrouter.ai/api/v1",
12303
+ compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
12304
+ reasoning: true,
12305
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12306
+ input: ["text"],
12307
+ cost: {
12308
+ input: 0,
12309
+ output: 0,
12310
+ cacheRead: 0,
12311
+ cacheWrite: 0,
12312
+ },
12313
+ contextWindow: 1048576,
12314
+ maxTokens: 393216,
12315
+ },
12280
12316
  "deepseek/deepseek-v4-flash-vision-exp": {
12281
12317
  id: "deepseek/deepseek-v4-flash-vision-exp",
12282
12318
  name: "DeepSeek: DeepSeek V4 Flash Vision Exp",
@@ -12288,13 +12324,13 @@ export const MODELS = {
12288
12324
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12289
12325
  input: ["text", "image"],
12290
12326
  cost: {
12291
- input: 0.22,
12292
- output: 0.66,
12293
- cacheRead: 0.007,
12327
+ input: 0.21559999999999999,
12328
+ output: 0.6468,
12329
+ cacheRead: 0.00686,
12294
12330
  cacheWrite: 0,
12295
12331
  },
12296
12332
  contextWindow: 1048576,
12297
- maxTokens: 943718,
12333
+ maxTokens: 262144,
12298
12334
  },
12299
12335
  "deepseek/deepseek-v4-flash-vision-exp:batch": {
12300
12336
  id: "deepseek/deepseek-v4-flash-vision-exp:batch",
@@ -12345,13 +12381,13 @@ export const MODELS = {
12345
12381
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12346
12382
  input: ["text"],
12347
12383
  cost: {
12348
- input: 0.9833999999999999,
12349
- output: 2.9502,
12350
- cacheRead: 0.03278,
12384
+ input: 0.57816,
12385
+ output: 1.73448,
12386
+ cacheRead: 0.018396000000000003,
12351
12387
  cacheWrite: 0,
12352
12388
  },
12353
12389
  contextWindow: 1048576,
12354
- maxTokens: 384000,
12390
+ maxTokens: 393216,
12355
12391
  },
12356
12392
  "deepseek/deepseek-v4-pro-0813:batch": {
12357
12393
  id: "deepseek/deepseek-v4-pro-0813:batch",
@@ -12383,9 +12419,9 @@ export const MODELS = {
12383
12419
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
12384
12420
  input: ["text", "image"],
12385
12421
  cost: {
12386
- input: 0.3,
12387
- output: 1.2,
12388
- cacheRead: 0.006,
12422
+ input: 0.15,
12423
+ output: 0.6,
12424
+ cacheRead: 0.003,
12389
12425
  cacheWrite: 0,
12390
12426
  },
12391
12427
  contextWindow: 1048576,
@@ -12898,7 +12934,7 @@ export const MODELS = {
12898
12934
  cacheRead: 0.049999999999999996,
12899
12935
  cacheWrite: 0,
12900
12936
  },
12901
- contextWindow: 262144,
12937
+ contextWindow: 1000000,
12902
12938
  maxTokens: 235929,
12903
12939
  },
12904
12940
  "google/gemma-4-26b-a4b-it:free": {
@@ -13649,23 +13685,6 @@ export const MODELS = {
13649
13685
  contextWindow: 131072,
13650
13686
  maxTokens: 104857,
13651
13687
  },
13652
- "mistralai/mistral-large-2512": {
13653
- id: "mistralai/mistral-large-2512",
13654
- name: "Mistral: Mistral Large 3 2512",
13655
- api: "openai-completions",
13656
- provider: "openrouter",
13657
- baseUrl: "https://openrouter.ai/api/v1",
13658
- reasoning: false,
13659
- input: ["text", "image"],
13660
- cost: {
13661
- input: 0.5,
13662
- output: 1.5,
13663
- cacheRead: 0.049999999999999996,
13664
- cacheWrite: 0,
13665
- },
13666
- contextWindow: 262144,
13667
- maxTokens: 209715,
13668
- },
13669
13688
  "mistralai/mistral-large-2512:batch": {
13670
13689
  id: "mistralai/mistral-large-2512:batch",
13671
13690
  name: "Mistral: Mistral Large 3 2512 (batch)",
@@ -13998,9 +14017,9 @@ export const MODELS = {
13998
14017
  reasoning: true,
13999
14018
  input: ["text", "image"],
14000
14019
  cost: {
14001
- input: 2.6481380629999998,
14002
- output: 13.282724250000001,
14003
- cacheRead: 0.30264435,
14020
+ input: 1.95,
14021
+ output: 10.92,
14022
+ cacheRead: 0.2262,
14004
14023
  cacheWrite: 0,
14005
14024
  },
14006
14025
  contextWindow: 1048576,
@@ -14066,9 +14085,9 @@ export const MODELS = {
14066
14085
  reasoning: true,
14067
14086
  input: ["text"],
14068
14087
  cost: {
14069
- input: 0.049999999999999996,
14070
- output: 0.19999999999999998,
14071
- cacheRead: 0.03,
14088
+ input: 0.06,
14089
+ output: 0.24,
14090
+ cacheRead: 0,
14072
14091
  cacheWrite: 0,
14073
14092
  },
14074
14093
  contextWindow: 262144,
@@ -15360,13 +15379,13 @@ export const MODELS = {
15360
15379
  reasoning: true,
15361
15380
  input: ["text"],
15362
15381
  cost: {
15363
- input: 0.037,
15364
- output: 0.16999999999999998,
15365
- cacheRead: 0,
15382
+ input: 0.15,
15383
+ output: 0.6,
15384
+ cacheRead: 0.075,
15366
15385
  cacheWrite: 0,
15367
15386
  },
15368
15387
  contextWindow: 131072,
15369
- maxTokens: 117964,
15388
+ maxTokens: 65536,
15370
15389
  },
15371
15390
  "openai/gpt-oss-120b:batch": {
15372
15391
  id: "openai/gpt-oss-120b:batch",
@@ -15708,6 +15727,23 @@ export const MODELS = {
15708
15727
  contextWindow: 262144,
15709
15728
  maxTokens: 32768,
15710
15729
  },
15730
+ "prism-ml/ternary-bonsai-2-27b": {
15731
+ id: "prism-ml/ternary-bonsai-2-27b",
15732
+ name: "PrismML: Ternary Bonsai 2 27B",
15733
+ api: "openai-completions",
15734
+ provider: "openrouter",
15735
+ baseUrl: "https://openrouter.ai/api/v1",
15736
+ reasoning: true,
15737
+ input: ["text", "image"],
15738
+ cost: {
15739
+ input: 0.075,
15740
+ output: 0.5,
15741
+ cacheRead: 0,
15742
+ cacheWrite: 0,
15743
+ },
15744
+ contextWindow: 262144,
15745
+ maxTokens: 32768,
15746
+ },
15711
15747
  "qwen/qwen-2.5-72b-instruct": {
15712
15748
  id: "qwen/qwen-2.5-72b-instruct",
15713
15749
  name: "Qwen2.5 72B Instruct",
@@ -16541,6 +16577,23 @@ export const MODELS = {
16541
16577
  contextWindow: 1000000,
16542
16578
  maxTokens: 131072,
16543
16579
  },
16580
+ "qwen/qwen3.8-27b:free": {
16581
+ id: "qwen/qwen3.8-27b:free",
16582
+ name: "Qwen: Qwen3.8 27B (free)",
16583
+ api: "openai-completions",
16584
+ provider: "openrouter",
16585
+ baseUrl: "https://openrouter.ai/api/v1",
16586
+ reasoning: true,
16587
+ input: ["text", "image"],
16588
+ cost: {
16589
+ input: 0,
16590
+ output: 0,
16591
+ cacheRead: 0,
16592
+ cacheWrite: 0,
16593
+ },
16594
+ contextWindow: 262144,
16595
+ maxTokens: 235929,
16596
+ },
16544
16597
  "qwen/qwen3.8-flash": {
16545
16598
  id: "qwen/qwen3.8-flash",
16546
16599
  name: "Qwen: Qwen3.8 Flash",
@@ -16737,9 +16790,9 @@ export const MODELS = {
16737
16790
  reasoning: true,
16738
16791
  input: ["text"],
16739
16792
  cost: {
16740
- input: 0.13199999999999998,
16741
- output: 0.5279999999999999,
16742
- cacheRead: 0.032999999999999995,
16793
+ input: 0.0825,
16794
+ output: 0.33,
16795
+ cacheRead: 0.020625,
16743
16796
  cacheWrite: 0,
16744
16797
  },
16745
16798
  contextWindow: 262144,
@@ -16762,23 +16815,6 @@ export const MODELS = {
16762
16815
  contextWindow: 1048576,
16763
16816
  maxTokens: 64000,
16764
16817
  },
16765
- "thedrummer/unslopnemo-12b": {
16766
- id: "thedrummer/unslopnemo-12b",
16767
- name: "TheDrummer: UnslopNemo 12B",
16768
- api: "openai-completions",
16769
- provider: "openrouter",
16770
- baseUrl: "https://openrouter.ai/api/v1",
16771
- reasoning: false,
16772
- input: ["text"],
16773
- cost: {
16774
- input: 0.39999999999999997,
16775
- output: 0.39999999999999997,
16776
- cacheRead: 0,
16777
- cacheWrite: 0,
16778
- },
16779
- contextWindow: 1024000,
16780
- maxTokens: 819200,
16781
- },
16782
16818
  "thinkingmachines/inkling": {
16783
16819
  id: "thinkingmachines/inkling",
16784
16820
  name: "Thinking Machines: Inkling",
@@ -16864,6 +16900,23 @@ export const MODELS = {
16864
16900
  contextWindow: 1048576,
16865
16901
  maxTokens: 262144,
16866
16902
  },
16903
+ "unbiased/pareto": {
16904
+ id: "unbiased/pareto",
16905
+ name: "Pareto",
16906
+ api: "openai-completions",
16907
+ provider: "openrouter",
16908
+ baseUrl: "https://openrouter.ai/api/v1",
16909
+ reasoning: false,
16910
+ input: ["text", "image"],
16911
+ cost: {
16912
+ input: 2.5,
16913
+ output: 7.5,
16914
+ cacheRead: 0.25,
16915
+ cacheWrite: 0,
16916
+ },
16917
+ contextWindow: 262144,
16918
+ maxTokens: 131072,
16919
+ },
16867
16920
  "upstage/solar-pro-3": {
16868
16921
  id: "upstage/solar-pro-3",
16869
16922
  name: "Upstage: Solar Pro 3",
@@ -17213,13 +17266,13 @@ export const MODELS = {
17213
17266
  reasoning: true,
17214
17267
  input: ["text"],
17215
17268
  cost: {
17216
- input: 1.4,
17217
- output: 4.4,
17218
- cacheRead: 0.14,
17269
+ input: 0.5544,
17270
+ output: 1.7424,
17271
+ cacheRead: 0.10296000000000001,
17219
17272
  cacheWrite: 0,
17220
17273
  },
17221
17274
  contextWindow: 1048576,
17222
- maxTokens: 128000,
17275
+ maxTokens: 131072,
17223
17276
  },
17224
17277
  "z-ai/glm-5.2:batch": {
17225
17278
  id: "z-ai/glm-5.2:batch",
@@ -17247,13 +17300,13 @@ export const MODELS = {
17247
17300
  reasoning: true,
17248
17301
  input: ["text"],
17249
17302
  cost: {
17250
- input: 1.4,
17251
- output: 4.4,
17252
- cacheRead: 0.26,
17303
+ input: 0.9099999999999999,
17304
+ output: 2.8600000000000003,
17305
+ cacheRead: 0.16899999999999998,
17253
17306
  cacheWrite: 0,
17254
17307
  },
17255
17308
  contextWindow: 1310720,
17256
- maxTokens: 943717,
17309
+ maxTokens: 131072,
17257
17310
  },
17258
17311
  "z-ai/glm-5.3-flash": {
17259
17312
  id: "z-ai/glm-5.3-flash",
@@ -17264,9 +17317,9 @@ export const MODELS = {
17264
17317
  reasoning: true,
17265
17318
  input: ["text", "image"],
17266
17319
  cost: {
17267
- input: 0.09999999999999999,
17268
- output: 0.3333,
17269
- cacheRead: 0.02,
17320
+ input: 0.09,
17321
+ output: 0.3,
17322
+ cacheRead: 0.018,
17270
17323
  cacheWrite: 0,
17271
17324
  },
17272
17325
  contextWindow: 1310720,
@@ -17401,13 +17454,13 @@ export const MODELS = {
17401
17454
  reasoning: true,
17402
17455
  input: ["text", "image"],
17403
17456
  cost: {
17404
- input: 0.15,
17405
- output: 0.6,
17406
- cacheRead: 0.015,
17457
+ input: 0.14,
17458
+ output: 0.42,
17459
+ cacheRead: 0.004200000000000001,
17407
17460
  cacheWrite: 0,
17408
17461
  },
17409
17462
  contextWindow: 1048576,
17410
- maxTokens: 943718,
17463
+ maxTokens: 131072,
17411
17464
  },
17412
17465
  "~deepseek/deepseek-pro-latest": {
17413
17466
  id: "~deepseek/deepseek-pro-latest",
@@ -17418,13 +17471,13 @@ export const MODELS = {
17418
17471
  reasoning: true,
17419
17472
  input: ["text"],
17420
17473
  cost: {
17421
- input: 0.96,
17422
- output: 2.88,
17423
- cacheRead: 0.088,
17474
+ input: 0.57816,
17475
+ output: 1.73448,
17476
+ cacheRead: 0.018396000000000003,
17424
17477
  cacheWrite: 0,
17425
17478
  },
17426
17479
  contextWindow: 1048576,
17427
- maxTokens: 943718,
17480
+ maxTokens: 393216,
17428
17481
  },
17429
17482
  "~deepseek/deepseek-v4-flash-latest": {
17430
17483
  id: "~deepseek/deepseek-v4-flash-latest",
@@ -17437,13 +17490,13 @@ export const MODELS = {
17437
17490
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
17438
17491
  input: ["text"],
17439
17492
  cost: {
17440
- input: 0.04,
17441
- output: 0.09999999999999999,
17442
- cacheRead: 0.01,
17493
+ input: 0.054119999999999994,
17494
+ output: 0.16236,
17495
+ cacheRead: 0.001722,
17443
17496
  cacheWrite: 0,
17444
17497
  },
17445
17498
  contextWindow: 1310720,
17446
- maxTokens: 393216,
17499
+ maxTokens: 384000,
17447
17500
  },
17448
17501
  "~google/gemini-flash-latest": {
17449
17502
  id: "~google/gemini-flash-latest",
@@ -17488,9 +17541,9 @@ export const MODELS = {
17488
17541
  reasoning: true,
17489
17542
  input: ["text", "image"],
17490
17543
  cost: {
17491
- input: 2,
17492
- output: 11.2,
17493
- cacheRead: 0.232,
17544
+ input: 1.95,
17545
+ output: 10.92,
17546
+ cacheRead: 0.2262,
17494
17547
  cacheWrite: 0,
17495
17548
  },
17496
17549
  contextWindow: 1048576,
@@ -17624,13 +17677,13 @@ export const MODELS = {
17624
17677
  reasoning: true,
17625
17678
  input: ["text"],
17626
17679
  cost: {
17627
- input: 0.8775,
17628
- output: 2.9699999999999998,
17629
- cacheRead: 0.1755,
17680
+ input: 0.8917999999999999,
17681
+ output: 2.8028,
17682
+ cacheRead: 0.16562,
17630
17683
  cacheWrite: 0,
17631
17684
  },
17632
17685
  contextWindow: 1310720,
17633
- maxTokens: 235929,
17686
+ maxTokens: 131072,
17634
17687
  },
17635
17688
  },
17636
17689
  "together": {
@@ -18286,8 +18339,8 @@ export const MODELS = {
18286
18339
  cacheRead: 0,
18287
18340
  cacheWrite: 0,
18288
18341
  },
18289
- contextWindow: 131072,
18290
- maxTokens: 32768,
18342
+ contextWindow: 262114,
18343
+ maxTokens: 262114,
18291
18344
  },
18292
18345
  "alibaba/qwen3-next-80b-a3b-thinking": {
18293
18346
  id: "alibaba/qwen3-next-80b-a3b-thinking",
@@ -18303,8 +18356,8 @@ export const MODELS = {
18303
18356
  cacheRead: 0,
18304
18357
  cacheWrite: 0,
18305
18358
  },
18306
- contextWindow: 131072,
18307
- maxTokens: 32768,
18359
+ contextWindow: 262144,
18360
+ maxTokens: 262144,
18308
18361
  },
18309
18362
  "alibaba/qwen3-vl-235b-a22b-instruct": {
18310
18363
  id: "alibaba/qwen3-vl-235b-a22b-instruct",
@@ -18539,9 +18592,9 @@ export const MODELS = {
18539
18592
  input: 2,
18540
18593
  output: 6,
18541
18594
  cacheRead: 0.25,
18542
- cacheWrite: 2.5,
18595
+ cacheWrite: 0,
18543
18596
  },
18544
- contextWindow: 1000000,
18597
+ contextWindow: 262144,
18545
18598
  maxTokens: 128000,
18546
18599
  },
18547
18600
  "alibaba/qwen3.8-max-0902": {
@@ -18561,6 +18614,23 @@ export const MODELS = {
18561
18614
  contextWindow: 991000,
18562
18615
  maxTokens: 128000,
18563
18616
  },
18617
+ "alibaba/qwen3.8-omni-flash": {
18618
+ id: "alibaba/qwen3.8-omni-flash",
18619
+ name: "Qwen 3.8 Omni Flash",
18620
+ api: "anthropic-messages",
18621
+ provider: "vercel-ai-gateway",
18622
+ baseUrl: "https://ai-gateway.vercel.sh",
18623
+ reasoning: true,
18624
+ input: ["text", "image"],
18625
+ cost: {
18626
+ input: 0.15,
18627
+ output: 0.47,
18628
+ cacheRead: 0.016,
18629
+ cacheWrite: 0,
18630
+ },
18631
+ contextWindow: 1000000,
18632
+ maxTokens: 131072,
18633
+ },
18564
18634
  "amazon/nova-2-lite": {
18565
18635
  id: "amazon/nova-2-lite",
18566
18636
  name: "Nova 2 Lite",
@@ -19171,13 +19241,13 @@ export const MODELS = {
19171
19241
  reasoning: true,
19172
19242
  input: ["text", "image"],
19173
19243
  cost: {
19174
- input: 0.15,
19175
- output: 0.6,
19176
- cacheRead: 0.015,
19244
+ input: 0.3,
19245
+ output: 1.2,
19246
+ cacheRead: 0.03,
19177
19247
  cacheWrite: 0,
19178
19248
  },
19179
- contextWindow: 1000000,
19180
- maxTokens: 384000,
19249
+ contextWindow: 1048576,
19250
+ maxTokens: 32768,
19181
19251
  },
19182
19252
  "google/gemini-2.5-flash": {
19183
19253
  id: "google/gemini-2.5-flash",
@@ -19587,74 +19657,6 @@ export const MODELS = {
19587
19657
  contextWindow: 1000000,
19588
19658
  maxTokens: 32000,
19589
19659
  },
19590
- "kwaipilot/kat-coder-air-v2.5": {
19591
- id: "kwaipilot/kat-coder-air-v2.5",
19592
- name: "Kat Coder Air V2.5",
19593
- api: "anthropic-messages",
19594
- provider: "vercel-ai-gateway",
19595
- baseUrl: "https://ai-gateway.vercel.sh",
19596
- reasoning: true,
19597
- input: ["text", "image"],
19598
- cost: {
19599
- input: 0.15,
19600
- output: 0.6,
19601
- cacheRead: 0.03,
19602
- cacheWrite: 0,
19603
- },
19604
- contextWindow: 256000,
19605
- maxTokens: 80000,
19606
- },
19607
- "kwaipilot/kat-coder-pro-v1": {
19608
- id: "kwaipilot/kat-coder-pro-v1",
19609
- name: "KAT-Coder-Pro V1",
19610
- api: "anthropic-messages",
19611
- provider: "vercel-ai-gateway",
19612
- baseUrl: "https://ai-gateway.vercel.sh",
19613
- reasoning: false,
19614
- input: ["text"],
19615
- cost: {
19616
- input: 0.3,
19617
- output: 1.2,
19618
- cacheRead: 0.06,
19619
- cacheWrite: 0,
19620
- },
19621
- contextWindow: 256000,
19622
- maxTokens: 32000,
19623
- },
19624
- "kwaipilot/kat-coder-pro-v2": {
19625
- id: "kwaipilot/kat-coder-pro-v2",
19626
- name: "Kat Coder Pro V2",
19627
- api: "anthropic-messages",
19628
- provider: "vercel-ai-gateway",
19629
- baseUrl: "https://ai-gateway.vercel.sh",
19630
- reasoning: true,
19631
- input: ["text"],
19632
- cost: {
19633
- input: 0.3,
19634
- output: 1.2,
19635
- cacheRead: 0.06,
19636
- cacheWrite: 0,
19637
- },
19638
- contextWindow: 256000,
19639
- maxTokens: 256000,
19640
- },
19641
- "kwaipilot/kat-coder-pro-v2.5": {
19642
- id: "kwaipilot/kat-coder-pro-v2.5",
19643
- name: "Kat Coder Pro V2.5",
19644
- api: "anthropic-messages",
19645
- provider: "vercel-ai-gateway",
19646
- baseUrl: "https://ai-gateway.vercel.sh",
19647
- reasoning: true,
19648
- input: ["text", "image"],
19649
- cost: {
19650
- input: 0.74,
19651
- output: 2.96,
19652
- cacheRead: 0.15,
19653
- cacheWrite: 0,
19654
- },
19655
- contextWindow: 256000,
19656
- maxTokens: 80000,
19657
- },
19658
19660
  "meta/llama-3.1-70b": {
19659
19661
  id: "meta/llama-3.1-70b",
19660
19662
  name: "Llama 3.1 70B Instruct",
@@ -20159,11 +20161,11 @@ export const MODELS = {
20159
20161
  cost: {
20160
20162
  input: 0.6,
20161
20163
  output: 3,
20162
- cacheRead: 0.09999999999999999,
20164
+ cacheRead: 0,
20163
20165
  cacheWrite: 0,
20164
20166
  },
20165
- contextWindow: 262114,
20166
- maxTokens: 262114,
20167
+ contextWindow: 256000,
20168
+ maxTokens: 256000,
20167
20169
  },
20168
20170
  "moonshotai/kimi-k2.6": {
20169
20171
  id: "moonshotai/kimi-k2.6",
@@ -21175,8 +21177,8 @@ export const MODELS = {
21175
21177
  reasoning: true,
21176
21178
  input: ["text"],
21177
21179
  cost: {
21178
- input: 0.049999999999999996,
21179
- output: 0.19999999999999998,
21180
+ input: 0.03,
21181
+ output: 0.14,
21180
21182
  cacheRead: 0,
21181
21183
  cacheWrite: 0,
21182
21184
  },
@@ -22033,6 +22035,23 @@ export const MODELS = {
22033
22035
  contextWindow: 1000000,
22034
22036
  maxTokens: 131000,
22035
22037
  },
22038
+ "zai/glm-5.3-flashx": {
22039
+ id: "zai/glm-5.3-flashx",
22040
+ name: "GLM 5.3 FlashX",
22041
+ api: "anthropic-messages",
22042
+ provider: "vercel-ai-gateway",
22043
+ baseUrl: "https://ai-gateway.vercel.sh",
22044
+ reasoning: true,
22045
+ input: ["text", "image"],
22046
+ cost: {
22047
+ input: 0.37,
22048
+ output: 1.25,
22049
+ cacheRead: 0.075,
22050
+ cacheWrite: 0,
22051
+ },
22052
+ contextWindow: 1000000,
22053
+ maxTokens: 131072,
22054
+ },
22036
22055
  "zai/glm-5v-turbo": {
22037
22056
  id: "zai/glm-5v-turbo",
22038
22057
  name: "GLM 5V Turbo",