@mariozechner/pi-ai 0.62.0 → 0.63.0

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.
@@ -801,6 +801,23 @@ export const MODELS = {
801
801
  contextWindow: 204800,
802
802
  maxTokens: 131072,
803
803
  },
804
+ "minimax.minimax-m2.5": {
805
+ id: "minimax.minimax-m2.5",
806
+ name: "MiniMax M2.5",
807
+ api: "bedrock-converse-stream",
808
+ provider: "amazon-bedrock",
809
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
810
+ reasoning: true,
811
+ input: ["text"],
812
+ cost: {
813
+ input: 0.3,
814
+ output: 1.2,
815
+ cacheRead: 0,
816
+ cacheWrite: 0,
817
+ },
818
+ contextWindow: 196608,
819
+ maxTokens: 98304,
820
+ },
804
821
  "mistral.devstral-2-123b": {
805
822
  id: "mistral.devstral-2-123b",
806
823
  name: "Devstral 2 123B",
@@ -1039,6 +1056,23 @@ export const MODELS = {
1039
1056
  contextWindow: 128000,
1040
1057
  maxTokens: 4096,
1041
1058
  },
1059
+ "nvidia.nemotron-super-3-120b": {
1060
+ id: "nvidia.nemotron-super-3-120b",
1061
+ name: "NVIDIA Nemotron 3 Super 120B A12B",
1062
+ api: "bedrock-converse-stream",
1063
+ provider: "amazon-bedrock",
1064
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1065
+ reasoning: true,
1066
+ input: ["text"],
1067
+ cost: {
1068
+ input: 0.15,
1069
+ output: 0.65,
1070
+ cacheRead: 0,
1071
+ cacheWrite: 0,
1072
+ },
1073
+ contextWindow: 262144,
1074
+ maxTokens: 131072,
1075
+ },
1042
1076
  "openai.gpt-oss-120b-1:0": {
1043
1077
  id: "openai.gpt-oss-120b-1:0",
1044
1078
  name: "gpt-oss-120b",
@@ -1413,6 +1447,23 @@ export const MODELS = {
1413
1447
  contextWindow: 200000,
1414
1448
  maxTokens: 131072,
1415
1449
  },
1450
+ "zai.glm-5": {
1451
+ id: "zai.glm-5",
1452
+ name: "GLM-5",
1453
+ api: "bedrock-converse-stream",
1454
+ provider: "amazon-bedrock",
1455
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1456
+ reasoning: true,
1457
+ input: ["text"],
1458
+ cost: {
1459
+ input: 1,
1460
+ output: 3.2,
1461
+ cacheRead: 0,
1462
+ cacheWrite: 0,
1463
+ },
1464
+ contextWindow: 202752,
1465
+ maxTokens: 101376,
1466
+ },
1416
1467
  },
1417
1468
  "anthropic": {
1418
1469
  "claude-3-5-haiku-20241022": {
@@ -4495,91 +4546,6 @@ export const MODELS = {
4495
4546
  },
4496
4547
  },
4497
4548
  "minimax": {
4498
- "MiniMax-M2": {
4499
- id: "MiniMax-M2",
4500
- name: "MiniMax-M2",
4501
- api: "anthropic-messages",
4502
- provider: "minimax",
4503
- baseUrl: "https://api.minimax.io/anthropic",
4504
- reasoning: true,
4505
- input: ["text"],
4506
- cost: {
4507
- input: 0.3,
4508
- output: 1.2,
4509
- cacheRead: 0,
4510
- cacheWrite: 0,
4511
- },
4512
- contextWindow: 204800,
4513
- maxTokens: 131072,
4514
- },
4515
- "MiniMax-M2.1": {
4516
- id: "MiniMax-M2.1",
4517
- name: "MiniMax-M2.1",
4518
- api: "anthropic-messages",
4519
- provider: "minimax",
4520
- baseUrl: "https://api.minimax.io/anthropic",
4521
- reasoning: true,
4522
- input: ["text"],
4523
- cost: {
4524
- input: 0.3,
4525
- output: 1.2,
4526
- cacheRead: 0,
4527
- cacheWrite: 0,
4528
- },
4529
- contextWindow: 204800,
4530
- maxTokens: 131072,
4531
- },
4532
- "MiniMax-M2.1-highspeed": {
4533
- id: "MiniMax-M2.1-highspeed",
4534
- name: "MiniMax-M2.1-highspeed",
4535
- api: "anthropic-messages",
4536
- provider: "minimax",
4537
- baseUrl: "https://api.minimax.io/anthropic",
4538
- reasoning: true,
4539
- input: ["text"],
4540
- cost: {
4541
- input: 0.6,
4542
- output: 2.4,
4543
- cacheRead: 0,
4544
- cacheWrite: 0,
4545
- },
4546
- contextWindow: 204800,
4547
- maxTokens: 131072,
4548
- },
4549
- "MiniMax-M2.5": {
4550
- id: "MiniMax-M2.5",
4551
- name: "MiniMax-M2.5",
4552
- api: "anthropic-messages",
4553
- provider: "minimax",
4554
- baseUrl: "https://api.minimax.io/anthropic",
4555
- reasoning: true,
4556
- input: ["text"],
4557
- cost: {
4558
- input: 0.3,
4559
- output: 1.2,
4560
- cacheRead: 0.03,
4561
- cacheWrite: 0.375,
4562
- },
4563
- contextWindow: 204800,
4564
- maxTokens: 131072,
4565
- },
4566
- "MiniMax-M2.5-highspeed": {
4567
- id: "MiniMax-M2.5-highspeed",
4568
- name: "MiniMax-M2.5-highspeed",
4569
- api: "anthropic-messages",
4570
- provider: "minimax",
4571
- baseUrl: "https://api.minimax.io/anthropic",
4572
- reasoning: true,
4573
- input: ["text"],
4574
- cost: {
4575
- input: 0.6,
4576
- output: 2.4,
4577
- cacheRead: 0.06,
4578
- cacheWrite: 0.375,
4579
- },
4580
- contextWindow: 204800,
4581
- maxTokens: 131072,
4582
- },
4583
4549
  "MiniMax-M2.7": {
4584
4550
  id: "MiniMax-M2.7",
4585
4551
  name: "MiniMax-M2.7",
@@ -4616,91 +4582,6 @@ export const MODELS = {
4616
4582
  },
4617
4583
  },
4618
4584
  "minimax-cn": {
4619
- "MiniMax-M2": {
4620
- id: "MiniMax-M2",
4621
- name: "MiniMax-M2",
4622
- api: "anthropic-messages",
4623
- provider: "minimax-cn",
4624
- baseUrl: "https://api.minimaxi.com/anthropic",
4625
- reasoning: true,
4626
- input: ["text"],
4627
- cost: {
4628
- input: 0.3,
4629
- output: 1.2,
4630
- cacheRead: 0,
4631
- cacheWrite: 0,
4632
- },
4633
- contextWindow: 204800,
4634
- maxTokens: 131072,
4635
- },
4636
- "MiniMax-M2.1": {
4637
- id: "MiniMax-M2.1",
4638
- name: "MiniMax-M2.1",
4639
- api: "anthropic-messages",
4640
- provider: "minimax-cn",
4641
- baseUrl: "https://api.minimaxi.com/anthropic",
4642
- reasoning: true,
4643
- input: ["text"],
4644
- cost: {
4645
- input: 0.3,
4646
- output: 1.2,
4647
- cacheRead: 0,
4648
- cacheWrite: 0,
4649
- },
4650
- contextWindow: 204800,
4651
- maxTokens: 131072,
4652
- },
4653
- "MiniMax-M2.1-highspeed": {
4654
- id: "MiniMax-M2.1-highspeed",
4655
- name: "MiniMax-M2.1-highspeed",
4656
- api: "anthropic-messages",
4657
- provider: "minimax-cn",
4658
- baseUrl: "https://api.minimaxi.com/anthropic",
4659
- reasoning: true,
4660
- input: ["text"],
4661
- cost: {
4662
- input: 0.6,
4663
- output: 2.4,
4664
- cacheRead: 0,
4665
- cacheWrite: 0,
4666
- },
4667
- contextWindow: 204800,
4668
- maxTokens: 131072,
4669
- },
4670
- "MiniMax-M2.5": {
4671
- id: "MiniMax-M2.5",
4672
- name: "MiniMax-M2.5",
4673
- api: "anthropic-messages",
4674
- provider: "minimax-cn",
4675
- baseUrl: "https://api.minimaxi.com/anthropic",
4676
- reasoning: true,
4677
- input: ["text"],
4678
- cost: {
4679
- input: 0.3,
4680
- output: 1.2,
4681
- cacheRead: 0.03,
4682
- cacheWrite: 0.375,
4683
- },
4684
- contextWindow: 204800,
4685
- maxTokens: 131072,
4686
- },
4687
- "MiniMax-M2.5-highspeed": {
4688
- id: "MiniMax-M2.5-highspeed",
4689
- name: "MiniMax-M2.5-highspeed",
4690
- api: "anthropic-messages",
4691
- provider: "minimax-cn",
4692
- baseUrl: "https://api.minimaxi.com/anthropic",
4693
- reasoning: true,
4694
- input: ["text"],
4695
- cost: {
4696
- input: 0.6,
4697
- output: 2.4,
4698
- cacheRead: 0.06,
4699
- cacheWrite: 0.375,
4700
- },
4701
- contextWindow: 204800,
4702
- maxTokens: 131072,
4703
- },
4704
4585
  "MiniMax-M2.7": {
4705
4586
  id: "MiniMax-M2.7",
4706
4587
  name: "MiniMax-M2.7",
@@ -7501,23 +7382,6 @@ export const MODELS = {
7501
7382
  contextWindow: 1048576,
7502
7383
  maxTokens: 65536,
7503
7384
  },
7504
- "google/gemini-3-pro-preview": {
7505
- id: "google/gemini-3-pro-preview",
7506
- name: "Google: Gemini 3 Pro Preview",
7507
- api: "openai-completions",
7508
- provider: "openrouter",
7509
- baseUrl: "https://openrouter.ai/api/v1",
7510
- reasoning: true,
7511
- input: ["text", "image"],
7512
- cost: {
7513
- input: 2,
7514
- output: 12,
7515
- cacheRead: 0.19999999999999998,
7516
- cacheWrite: 0.375,
7517
- },
7518
- contextWindow: 1048576,
7519
- maxTokens: 65536,
7520
- },
7521
7385
  "google/gemini-3.1-flash-lite-preview": {
7522
7386
  id: "google/gemini-3.1-flash-lite-preview",
7523
7387
  name: "Google: Gemini 3.1 Flash Lite Preview",
@@ -8292,13 +8156,13 @@ export const MODELS = {
8292
8156
  reasoning: false,
8293
8157
  input: ["text"],
8294
8158
  cost: {
8295
- input: 0.55,
8296
- output: 2.2,
8159
+ input: 0.5700000000000001,
8160
+ output: 2.3,
8297
8161
  cacheRead: 0,
8298
8162
  cacheWrite: 0,
8299
8163
  },
8300
- contextWindow: 131000,
8301
- maxTokens: 4096,
8164
+ contextWindow: 131072,
8165
+ maxTokens: 131072,
8302
8166
  },
8303
8167
  "moonshotai/kimi-k2-0905": {
8304
8168
  id: "moonshotai/kimi-k2-0905",
@@ -8360,8 +8224,8 @@ export const MODELS = {
8360
8224
  reasoning: false,
8361
8225
  input: ["text"],
8362
8226
  cost: {
8363
- input: 0.27,
8364
- output: 1,
8227
+ input: 0.135,
8228
+ output: 0.5,
8365
8229
  cacheRead: 0,
8366
8230
  cacheWrite: 0,
8367
8231
  },
@@ -8447,7 +8311,7 @@ export const MODELS = {
8447
8311
  cost: {
8448
8312
  input: 0.09999999999999999,
8449
8313
  output: 0.5,
8450
- cacheRead: 0.04,
8314
+ cacheRead: 0.09999999999999999,
8451
8315
  cacheWrite: 0,
8452
8316
  },
8453
8317
  contextWindow: 262144,
@@ -9539,7 +9403,7 @@ export const MODELS = {
9539
9403
  cacheWrite: 0,
9540
9404
  },
9541
9405
  contextWindow: 32768,
9542
- maxTokens: 4096,
9406
+ maxTokens: 32768,
9543
9407
  },
9544
9408
  "qwen/qwen-max": {
9545
9409
  id: "qwen/qwen-max",
@@ -10202,7 +10066,7 @@ export const MODELS = {
10202
10066
  cacheWrite: 0,
10203
10067
  },
10204
10068
  contextWindow: 256000,
10205
- maxTokens: 4096,
10069
+ maxTokens: 65536,
10206
10070
  },
10207
10071
  "qwen/qwen3.5-flash-02-23": {
10208
10072
  id: "qwen/qwen3.5-flash-02-23",
@@ -10255,6 +10119,23 @@ export const MODELS = {
10255
10119
  contextWindow: 131072,
10256
10120
  maxTokens: 131072,
10257
10121
  },
10122
+ "reka/reka-edge": {
10123
+ id: "reka/reka-edge",
10124
+ name: "Reka Edge",
10125
+ api: "openai-completions",
10126
+ provider: "openrouter",
10127
+ baseUrl: "https://openrouter.ai/api/v1",
10128
+ reasoning: false,
10129
+ input: ["text", "image"],
10130
+ cost: {
10131
+ input: 0.09999999999999999,
10132
+ output: 0.09999999999999999,
10133
+ cacheRead: 0,
10134
+ cacheWrite: 0,
10135
+ },
10136
+ contextWindow: 16384,
10137
+ maxTokens: 16384,
10138
+ },
10258
10139
  "relace/relace-search": {
10259
10140
  id: "relace/relace-search",
10260
10141
  name: "Relace: Relace Search",
@@ -10320,8 +10201,8 @@ export const MODELS = {
10320
10201
  cacheRead: 0.02,
10321
10202
  cacheWrite: 0,
10322
10203
  },
10323
- contextWindow: 256000,
10324
- maxTokens: 256000,
10204
+ contextWindow: 262144,
10205
+ maxTokens: 4096,
10325
10206
  },
10326
10207
  "stepfun/step-3.5-flash:free": {
10327
10208
  id: "stepfun/step-3.5-flash:free",
@@ -10791,9 +10672,9 @@ export const MODELS = {
10791
10672
  reasoning: true,
10792
10673
  input: ["text"],
10793
10674
  cost: {
10794
- input: 0.96,
10795
- output: 3.1999999999999997,
10796
- cacheRead: 0.192,
10675
+ input: 1.2,
10676
+ output: 4,
10677
+ cacheRead: 0.24,
10797
10678
  cacheWrite: 0,
10798
10679
  },
10799
10680
  contextWindow: 202752,
@@ -12799,8 +12680,8 @@ export const MODELS = {
12799
12680
  reasoning: false,
12800
12681
  input: ["text", "image"],
12801
12682
  cost: {
12802
- input: 1,
12803
- output: 1,
12683
+ input: 0,
12684
+ output: 0,
12804
12685
  cacheRead: 0,
12805
12686
  cacheWrite: 0,
12806
12687
  },
@@ -12816,8 +12697,8 @@ export const MODELS = {
12816
12697
  reasoning: false,
12817
12698
  input: ["text", "image"],
12818
12699
  cost: {
12819
- input: 3,
12820
- output: 15,
12700
+ input: 0,
12701
+ output: 0,
12821
12702
  cacheRead: 0,
12822
12703
  cacheWrite: 0,
12823
12704
  },
@@ -13011,6 +12892,23 @@ export const MODELS = {
13011
12892
  contextWindow: 2000000,
13012
12893
  maxTokens: 30000,
13013
12894
  },
12895
+ "xai/grok-4.20-multi-agent": {
12896
+ id: "xai/grok-4.20-multi-agent",
12897
+ name: "Grok 4.20 Multi-Agent",
12898
+ api: "anthropic-messages",
12899
+ provider: "vercel-ai-gateway",
12900
+ baseUrl: "https://ai-gateway.vercel.sh",
12901
+ reasoning: true,
12902
+ input: ["text"],
12903
+ cost: {
12904
+ input: 2,
12905
+ output: 6,
12906
+ cacheRead: 0.19999999999999998,
12907
+ cacheWrite: 0,
12908
+ },
12909
+ contextWindow: 2000000,
12910
+ maxTokens: 2000000,
12911
+ },
13014
12912
  "xai/grok-4.20-multi-agent-beta": {
13015
12913
  id: "xai/grok-4.20-multi-agent-beta",
13016
12914
  name: "Grok 4.20 Multi Agent Beta",
@@ -13028,6 +12926,23 @@ export const MODELS = {
13028
12926
  contextWindow: 2000000,
13029
12927
  maxTokens: 2000000,
13030
12928
  },
12929
+ "xai/grok-4.20-non-reasoning": {
12930
+ id: "xai/grok-4.20-non-reasoning",
12931
+ name: "Grok 4.20 Non-Reasoning",
12932
+ api: "anthropic-messages",
12933
+ provider: "vercel-ai-gateway",
12934
+ baseUrl: "https://ai-gateway.vercel.sh",
12935
+ reasoning: false,
12936
+ input: ["text", "image"],
12937
+ cost: {
12938
+ input: 2,
12939
+ output: 6,
12940
+ cacheRead: 0.19999999999999998,
12941
+ cacheWrite: 0,
12942
+ },
12943
+ contextWindow: 2000000,
12944
+ maxTokens: 2000000,
12945
+ },
13031
12946
  "xai/grok-4.20-non-reasoning-beta": {
13032
12947
  id: "xai/grok-4.20-non-reasoning-beta",
13033
12948
  name: "Grok 4.20 Beta Non-Reasoning",
@@ -13045,6 +12960,23 @@ export const MODELS = {
13045
12960
  contextWindow: 2000000,
13046
12961
  maxTokens: 2000000,
13047
12962
  },
12963
+ "xai/grok-4.20-reasoning": {
12964
+ id: "xai/grok-4.20-reasoning",
12965
+ name: "Grok 4.20 Reasoning",
12966
+ api: "anthropic-messages",
12967
+ provider: "vercel-ai-gateway",
12968
+ baseUrl: "https://ai-gateway.vercel.sh",
12969
+ reasoning: true,
12970
+ input: ["text", "image"],
12971
+ cost: {
12972
+ input: 2,
12973
+ output: 6,
12974
+ cacheRead: 0.19999999999999998,
12975
+ cacheWrite: 0,
12976
+ },
12977
+ contextWindow: 2000000,
12978
+ maxTokens: 2000000,
12979
+ },
13048
12980
  "xai/grok-4.20-reasoning-beta": {
13049
12981
  id: "xai/grok-4.20-reasoning-beta",
13050
12982
  name: "Grok 4.20 Beta Reasoning",
@@ -13856,6 +13788,24 @@ export const MODELS = {
13856
13788
  contextWindow: 200000,
13857
13789
  maxTokens: 131072,
13858
13790
  },
13791
+ "glm-4.7-flashx": {
13792
+ id: "glm-4.7-flashx",
13793
+ name: "GLM-4.7-FlashX",
13794
+ api: "openai-completions",
13795
+ provider: "zai",
13796
+ baseUrl: "https://api.z.ai/api/coding/paas/v4",
13797
+ compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai" },
13798
+ reasoning: true,
13799
+ input: ["text"],
13800
+ cost: {
13801
+ input: 0.07,
13802
+ output: 0.4,
13803
+ cacheRead: 0.01,
13804
+ cacheWrite: 0,
13805
+ },
13806
+ contextWindow: 200000,
13807
+ maxTokens: 131072,
13808
+ },
13859
13809
  "glm-5": {
13860
13810
  id: "glm-5",
13861
13811
  name: "GLM-5",