@elyracode/ai 0.9.38 → 0.9.39

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: 0.04956,
12252
+ output: 0.09912,
12253
+ cacheRead: 0.009911999999999999,
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,
@@ -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: 2.0999999999999996,
14021
+ output: 10.950000000000001,
14022
+ cacheRead: 0.22999999999999998,
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",
@@ -16541,6 +16560,23 @@ export const MODELS = {
16541
16560
  contextWindow: 1000000,
16542
16561
  maxTokens: 131072,
16543
16562
  },
16563
+ "qwen/qwen3.8-27b:free": {
16564
+ id: "qwen/qwen3.8-27b:free",
16565
+ name: "Qwen: Qwen3.8 27B (free)",
16566
+ api: "openai-completions",
16567
+ provider: "openrouter",
16568
+ baseUrl: "https://openrouter.ai/api/v1",
16569
+ reasoning: true,
16570
+ input: ["text", "image"],
16571
+ cost: {
16572
+ input: 0,
16573
+ output: 0,
16574
+ cacheRead: 0,
16575
+ cacheWrite: 0,
16576
+ },
16577
+ contextWindow: 262144,
16578
+ maxTokens: 235929,
16579
+ },
16544
16580
  "qwen/qwen3.8-flash": {
16545
16581
  id: "qwen/qwen3.8-flash",
16546
16582
  name: "Qwen: Qwen3.8 Flash",
@@ -16737,9 +16773,9 @@ export const MODELS = {
16737
16773
  reasoning: true,
16738
16774
  input: ["text"],
16739
16775
  cost: {
16740
- input: 0.13199999999999998,
16741
- output: 0.5279999999999999,
16742
- cacheRead: 0.032999999999999995,
16776
+ input: 0.0825,
16777
+ output: 0.33,
16778
+ cacheRead: 0.020625,
16743
16779
  cacheWrite: 0,
16744
16780
  },
16745
16781
  contextWindow: 262144,
@@ -16762,23 +16798,6 @@ export const MODELS = {
16762
16798
  contextWindow: 1048576,
16763
16799
  maxTokens: 64000,
16764
16800
  },
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
16801
  "thinkingmachines/inkling": {
16783
16802
  id: "thinkingmachines/inkling",
16784
16803
  name: "Thinking Machines: Inkling",
@@ -16864,6 +16883,23 @@ export const MODELS = {
16864
16883
  contextWindow: 1048576,
16865
16884
  maxTokens: 262144,
16866
16885
  },
16886
+ "unbiased/pareto": {
16887
+ id: "unbiased/pareto",
16888
+ name: "Pareto",
16889
+ api: "openai-completions",
16890
+ provider: "openrouter",
16891
+ baseUrl: "https://openrouter.ai/api/v1",
16892
+ reasoning: false,
16893
+ input: ["text", "image"],
16894
+ cost: {
16895
+ input: 2.5,
16896
+ output: 7.5,
16897
+ cacheRead: 0.25,
16898
+ cacheWrite: 0,
16899
+ },
16900
+ contextWindow: 262144,
16901
+ maxTokens: 131072,
16902
+ },
16867
16903
  "upstage/solar-pro-3": {
16868
16904
  id: "upstage/solar-pro-3",
16869
16905
  name: "Upstage: Solar Pro 3",
@@ -17213,13 +17249,13 @@ export const MODELS = {
17213
17249
  reasoning: true,
17214
17250
  input: ["text"],
17215
17251
  cost: {
17216
- input: 1.4,
17217
- output: 4.4,
17218
- cacheRead: 0.14,
17252
+ input: 0.5544,
17253
+ output: 1.7424,
17254
+ cacheRead: 0.10296000000000001,
17219
17255
  cacheWrite: 0,
17220
17256
  },
17221
17257
  contextWindow: 1048576,
17222
- maxTokens: 128000,
17258
+ maxTokens: 131072,
17223
17259
  },
17224
17260
  "z-ai/glm-5.2:batch": {
17225
17261
  id: "z-ai/glm-5.2:batch",
@@ -17247,13 +17283,13 @@ export const MODELS = {
17247
17283
  reasoning: true,
17248
17284
  input: ["text"],
17249
17285
  cost: {
17250
- input: 1.4,
17251
- output: 4.4,
17252
- cacheRead: 0.26,
17286
+ input: 0.9099999999999999,
17287
+ output: 2.8600000000000003,
17288
+ cacheRead: 0.16899999999999998,
17253
17289
  cacheWrite: 0,
17254
17290
  },
17255
17291
  contextWindow: 1310720,
17256
- maxTokens: 943717,
17292
+ maxTokens: 131072,
17257
17293
  },
17258
17294
  "z-ai/glm-5.3-flash": {
17259
17295
  id: "z-ai/glm-5.3-flash",
@@ -17264,9 +17300,9 @@ export const MODELS = {
17264
17300
  reasoning: true,
17265
17301
  input: ["text", "image"],
17266
17302
  cost: {
17267
- input: 0.09999999999999999,
17268
- output: 0.3333,
17269
- cacheRead: 0.02,
17303
+ input: 0.09,
17304
+ output: 0.3,
17305
+ cacheRead: 0.018,
17270
17306
  cacheWrite: 0,
17271
17307
  },
17272
17308
  contextWindow: 1310720,
@@ -17407,7 +17443,7 @@ export const MODELS = {
17407
17443
  cacheWrite: 0,
17408
17444
  },
17409
17445
  contextWindow: 1048576,
17410
- maxTokens: 943718,
17446
+ maxTokens: 393216,
17411
17447
  },
17412
17448
  "~deepseek/deepseek-pro-latest": {
17413
17449
  id: "~deepseek/deepseek-pro-latest",
@@ -17418,13 +17454,13 @@ export const MODELS = {
17418
17454
  reasoning: true,
17419
17455
  input: ["text"],
17420
17456
  cost: {
17421
- input: 0.96,
17422
- output: 2.88,
17423
- cacheRead: 0.088,
17457
+ input: 0.57816,
17458
+ output: 1.73448,
17459
+ cacheRead: 0.018396000000000003,
17424
17460
  cacheWrite: 0,
17425
17461
  },
17426
17462
  contextWindow: 1048576,
17427
- maxTokens: 943718,
17463
+ maxTokens: 393216,
17428
17464
  },
17429
17465
  "~deepseek/deepseek-v4-flash-latest": {
17430
17466
  id: "~deepseek/deepseek-v4-flash-latest",
@@ -17437,13 +17473,13 @@ export const MODELS = {
17437
17473
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
17438
17474
  input: ["text"],
17439
17475
  cost: {
17440
- input: 0.04,
17441
- output: 0.09999999999999999,
17442
- cacheRead: 0.01,
17476
+ input: 0.055,
17477
+ output: 0.165,
17478
+ cacheRead: 0.00175,
17443
17479
  cacheWrite: 0,
17444
17480
  },
17445
17481
  contextWindow: 1310720,
17446
- maxTokens: 393216,
17482
+ maxTokens: 384000,
17447
17483
  },
17448
17484
  "~google/gemini-flash-latest": {
17449
17485
  id: "~google/gemini-flash-latest",
@@ -17488,9 +17524,9 @@ export const MODELS = {
17488
17524
  reasoning: true,
17489
17525
  input: ["text", "image"],
17490
17526
  cost: {
17491
- input: 2,
17492
- output: 11.2,
17493
- cacheRead: 0.232,
17527
+ input: 2.0999999999999996,
17528
+ output: 10.950000000000001,
17529
+ cacheRead: 0.22999999999999998,
17494
17530
  cacheWrite: 0,
17495
17531
  },
17496
17532
  contextWindow: 1048576,
@@ -17624,13 +17660,13 @@ export const MODELS = {
17624
17660
  reasoning: true,
17625
17661
  input: ["text"],
17626
17662
  cost: {
17627
- input: 0.8775,
17628
- output: 2.9699999999999998,
17629
- cacheRead: 0.1755,
17663
+ input: 0.8987999999999999,
17664
+ output: 2.8248,
17665
+ cacheRead: 0.16691999999999999,
17630
17666
  cacheWrite: 0,
17631
17667
  },
17632
17668
  contextWindow: 1310720,
17633
- maxTokens: 235929,
17669
+ maxTokens: 131072,
17634
17670
  },
17635
17671
  },
17636
17672
  "together": {
@@ -18286,8 +18322,8 @@ export const MODELS = {
18286
18322
  cacheRead: 0,
18287
18323
  cacheWrite: 0,
18288
18324
  },
18289
- contextWindow: 131072,
18290
- maxTokens: 32768,
18325
+ contextWindow: 262114,
18326
+ maxTokens: 262114,
18291
18327
  },
18292
18328
  "alibaba/qwen3-next-80b-a3b-thinking": {
18293
18329
  id: "alibaba/qwen3-next-80b-a3b-thinking",
@@ -18303,8 +18339,8 @@ export const MODELS = {
18303
18339
  cacheRead: 0,
18304
18340
  cacheWrite: 0,
18305
18341
  },
18306
- contextWindow: 131072,
18307
- maxTokens: 32768,
18342
+ contextWindow: 262144,
18343
+ maxTokens: 262144,
18308
18344
  },
18309
18345
  "alibaba/qwen3-vl-235b-a22b-instruct": {
18310
18346
  id: "alibaba/qwen3-vl-235b-a22b-instruct",
@@ -18539,9 +18575,9 @@ export const MODELS = {
18539
18575
  input: 2,
18540
18576
  output: 6,
18541
18577
  cacheRead: 0.25,
18542
- cacheWrite: 2.5,
18578
+ cacheWrite: 0,
18543
18579
  },
18544
- contextWindow: 1000000,
18580
+ contextWindow: 262144,
18545
18581
  maxTokens: 128000,
18546
18582
  },
18547
18583
  "alibaba/qwen3.8-max-0902": {
@@ -18561,6 +18597,23 @@ export const MODELS = {
18561
18597
  contextWindow: 991000,
18562
18598
  maxTokens: 128000,
18563
18599
  },
18600
+ "alibaba/qwen3.8-omni-flash": {
18601
+ id: "alibaba/qwen3.8-omni-flash",
18602
+ name: "Qwen 3.8 Omni Flash",
18603
+ api: "anthropic-messages",
18604
+ provider: "vercel-ai-gateway",
18605
+ baseUrl: "https://ai-gateway.vercel.sh",
18606
+ reasoning: true,
18607
+ input: ["text", "image"],
18608
+ cost: {
18609
+ input: 0.15,
18610
+ output: 0.47,
18611
+ cacheRead: 0.016,
18612
+ cacheWrite: 0,
18613
+ },
18614
+ contextWindow: 1000000,
18615
+ maxTokens: 131072,
18616
+ },
18564
18617
  "amazon/nova-2-lite": {
18565
18618
  id: "amazon/nova-2-lite",
18566
18619
  name: "Nova 2 Lite",
@@ -19171,13 +19224,13 @@ export const MODELS = {
19171
19224
  reasoning: true,
19172
19225
  input: ["text", "image"],
19173
19226
  cost: {
19174
- input: 0.15,
19175
- output: 0.6,
19176
- cacheRead: 0.015,
19227
+ input: 0.3,
19228
+ output: 1.2,
19229
+ cacheRead: 0.03,
19177
19230
  cacheWrite: 0,
19178
19231
  },
19179
- contextWindow: 1000000,
19180
- maxTokens: 384000,
19232
+ contextWindow: 1048576,
19233
+ maxTokens: 32768,
19181
19234
  },
19182
19235
  "google/gemini-2.5-flash": {
19183
19236
  id: "google/gemini-2.5-flash",
@@ -19587,74 +19640,6 @@ export const MODELS = {
19587
19640
  contextWindow: 1000000,
19588
19641
  maxTokens: 32000,
19589
19642
  },
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
19643
  "meta/llama-3.1-70b": {
19659
19644
  id: "meta/llama-3.1-70b",
19660
19645
  name: "Llama 3.1 70B Instruct",
@@ -20159,11 +20144,11 @@ export const MODELS = {
20159
20144
  cost: {
20160
20145
  input: 0.6,
20161
20146
  output: 3,
20162
- cacheRead: 0.09999999999999999,
20147
+ cacheRead: 0,
20163
20148
  cacheWrite: 0,
20164
20149
  },
20165
- contextWindow: 262114,
20166
- maxTokens: 262114,
20150
+ contextWindow: 256000,
20151
+ maxTokens: 256000,
20167
20152
  },
20168
20153
  "moonshotai/kimi-k2.6": {
20169
20154
  id: "moonshotai/kimi-k2.6",
@@ -21175,8 +21160,8 @@ export const MODELS = {
21175
21160
  reasoning: true,
21176
21161
  input: ["text"],
21177
21162
  cost: {
21178
- input: 0.049999999999999996,
21179
- output: 0.19999999999999998,
21163
+ input: 0.03,
21164
+ output: 0.14,
21180
21165
  cacheRead: 0,
21181
21166
  cacheWrite: 0,
21182
21167
  },
@@ -22033,6 +22018,23 @@ export const MODELS = {
22033
22018
  contextWindow: 1000000,
22034
22019
  maxTokens: 131000,
22035
22020
  },
22021
+ "zai/glm-5.3-flashx": {
22022
+ id: "zai/glm-5.3-flashx",
22023
+ name: "GLM 5.3 FlashX",
22024
+ api: "anthropic-messages",
22025
+ provider: "vercel-ai-gateway",
22026
+ baseUrl: "https://ai-gateway.vercel.sh",
22027
+ reasoning: true,
22028
+ input: ["text", "image"],
22029
+ cost: {
22030
+ input: 0.37,
22031
+ output: 1.25,
22032
+ cacheRead: 0.075,
22033
+ cacheWrite: 0,
22034
+ },
22035
+ contextWindow: 1000000,
22036
+ maxTokens: 131072,
22037
+ },
22036
22038
  "zai/glm-5v-turbo": {
22037
22039
  id: "zai/glm-5v-turbo",
22038
22040
  name: "GLM 5V Turbo",