@caupulican/pi-ai 0.80.25 → 0.80.26

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.
@@ -3746,6 +3746,24 @@ export const MODELS = {
3746
3746
  contextWindow: 131072,
3747
3747
  maxTokens: 131072,
3748
3748
  },
3749
+ "@cf/zai-org/glm-5.2": {
3750
+ id: "@cf/zai-org/glm-5.2",
3751
+ name: "Glm 5.2",
3752
+ api: "openai-completions",
3753
+ provider: "cloudflare-workers-ai",
3754
+ baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
3755
+ compat: { "sendSessionAffinityHeaders": true },
3756
+ reasoning: true,
3757
+ input: ["text"],
3758
+ cost: {
3759
+ input: 1.4,
3760
+ output: 4.4,
3761
+ cacheRead: 0.26,
3762
+ cacheWrite: 0,
3763
+ },
3764
+ contextWindow: 262144,
3765
+ maxTokens: 262144,
3766
+ },
3749
3767
  },
3750
3768
  "deepseek": {
3751
3769
  "deepseek-v4-flash": {
@@ -3800,7 +3818,7 @@ export const MODELS = {
3800
3818
  cost: {
3801
3819
  input: 0.14,
3802
3820
  output: 0.28,
3803
- cacheRead: 0.03,
3821
+ cacheRead: 0.028,
3804
3822
  cacheWrite: 0,
3805
3823
  },
3806
3824
  contextWindow: 1000000,
@@ -3842,6 +3860,24 @@ export const MODELS = {
3842
3860
  contextWindow: 202800,
3843
3861
  maxTokens: 131072,
3844
3862
  },
3863
+ "accounts/fireworks/models/glm-5p2": {
3864
+ id: "accounts/fireworks/models/glm-5p2",
3865
+ name: "GLM 5.2",
3866
+ api: "anthropic-messages",
3867
+ provider: "fireworks",
3868
+ baseUrl: "https://api.fireworks.ai/inference",
3869
+ compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
3870
+ reasoning: true,
3871
+ input: ["text"],
3872
+ cost: {
3873
+ input: 1.4,
3874
+ output: 4.4,
3875
+ cacheRead: 0.26,
3876
+ cacheWrite: 0,
3877
+ },
3878
+ contextWindow: 1048576,
3879
+ maxTokens: 131072,
3880
+ },
3845
3881
  "accounts/fireworks/models/gpt-oss-120b": {
3846
3882
  id: "accounts/fireworks/models/gpt-oss-120b",
3847
3883
  name: "GPT OSS 120B",
@@ -4032,7 +4068,7 @@ export const MODELS = {
4032
4068
  reasoning: true,
4033
4069
  input: ["text", "image"],
4034
4070
  cost: {
4035
- input: 2,
4071
+ input: 1.9,
4036
4072
  output: 8,
4037
4073
  cacheRead: 0.38,
4038
4074
  cacheWrite: 0,
@@ -4764,6 +4800,42 @@ export const MODELS = {
4764
4800
  contextWindow: 262144,
4765
4801
  maxTokens: 32768,
4766
4802
  },
4803
+ "gemma-4-E2B-it": {
4804
+ id: "gemma-4-E2B-it",
4805
+ name: "Gemma 4 E2B IT",
4806
+ api: "google-generative-ai",
4807
+ provider: "google",
4808
+ baseUrl: "https://generativelanguage.googleapis.com/v1beta",
4809
+ reasoning: true,
4810
+ thinkingLevelMap: { "off": null, "minimal": "MINIMAL", "low": null, "medium": null, "high": "HIGH" },
4811
+ input: ["text", "image"],
4812
+ cost: {
4813
+ input: 0,
4814
+ output: 0,
4815
+ cacheRead: 0,
4816
+ cacheWrite: 0,
4817
+ },
4818
+ contextWindow: 131072,
4819
+ maxTokens: 8192,
4820
+ },
4821
+ "gemma-4-E4B-it": {
4822
+ id: "gemma-4-E4B-it",
4823
+ name: "Gemma 4 E4B IT",
4824
+ api: "google-generative-ai",
4825
+ provider: "google",
4826
+ baseUrl: "https://generativelanguage.googleapis.com/v1beta",
4827
+ reasoning: true,
4828
+ thinkingLevelMap: { "off": null, "minimal": "MINIMAL", "low": null, "medium": null, "high": "HIGH" },
4829
+ input: ["text", "image"],
4830
+ cost: {
4831
+ input: 0,
4832
+ output: 0,
4833
+ cacheRead: 0,
4834
+ cacheWrite: 0,
4835
+ },
4836
+ contextWindow: 131072,
4837
+ maxTokens: 8192,
4838
+ },
4767
4839
  },
4768
4840
  "google-vertex": {
4769
4841
  "gemini-1.5-flash": {
@@ -6317,6 +6389,24 @@ export const MODELS = {
6317
6389
  contextWindow: 262144,
6318
6390
  maxTokens: 262144,
6319
6391
  },
6392
+ "kimi-k2.7-code-highspeed": {
6393
+ id: "kimi-k2.7-code-highspeed",
6394
+ name: "Kimi K2.7 Code HighSpeed",
6395
+ api: "openai-completions",
6396
+ provider: "moonshotai",
6397
+ baseUrl: "https://api.moonshot.ai/v1",
6398
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
6399
+ reasoning: true,
6400
+ input: ["text", "image"],
6401
+ cost: {
6402
+ input: 1.9,
6403
+ output: 8,
6404
+ cacheRead: 0.38,
6405
+ cacheWrite: 0,
6406
+ },
6407
+ contextWindow: 262144,
6408
+ maxTokens: 262144,
6409
+ },
6320
6410
  },
6321
6411
  "moonshotai-cn": {
6322
6412
  "kimi-k2-0711-preview": {
@@ -6445,6 +6535,42 @@ export const MODELS = {
6445
6535
  contextWindow: 262144,
6446
6536
  maxTokens: 262144,
6447
6537
  },
6538
+ "kimi-k2.7-code": {
6539
+ id: "kimi-k2.7-code",
6540
+ name: "Kimi K2.7 Code",
6541
+ api: "openai-completions",
6542
+ provider: "moonshotai-cn",
6543
+ baseUrl: "https://api.moonshot.cn/v1",
6544
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
6545
+ reasoning: true,
6546
+ input: ["text", "image"],
6547
+ cost: {
6548
+ input: 0.95,
6549
+ output: 4,
6550
+ cacheRead: 0.19,
6551
+ cacheWrite: 0,
6552
+ },
6553
+ contextWindow: 262144,
6554
+ maxTokens: 262144,
6555
+ },
6556
+ "kimi-k2.7-code-highspeed": {
6557
+ id: "kimi-k2.7-code-highspeed",
6558
+ name: "Kimi K2.7 Code HighSpeed",
6559
+ api: "openai-completions",
6560
+ provider: "moonshotai-cn",
6561
+ baseUrl: "https://api.moonshot.cn/v1",
6562
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
6563
+ reasoning: true,
6564
+ input: ["text", "image"],
6565
+ cost: {
6566
+ input: 1.9,
6567
+ output: 8,
6568
+ cacheRead: 0.38,
6569
+ cacheWrite: 0,
6570
+ },
6571
+ contextWindow: 262144,
6572
+ maxTokens: 262144,
6573
+ },
6448
6574
  },
6449
6575
  "openai": {
6450
6576
  "gpt-4": {
@@ -8120,26 +8246,26 @@ export const MODELS = {
8120
8246
  contextWindow: 1000000,
8121
8247
  maxTokens: 384000,
8122
8248
  },
8123
- "glm-5": {
8124
- id: "glm-5",
8125
- name: "GLM-5",
8249
+ "glm-5.1": {
8250
+ id: "glm-5.1",
8251
+ name: "GLM-5.1",
8126
8252
  api: "openai-completions",
8127
8253
  provider: "opencode-go",
8128
8254
  baseUrl: "https://opencode.ai/zen/go/v1",
8129
8255
  reasoning: true,
8130
8256
  input: ["text"],
8131
8257
  cost: {
8132
- input: 1,
8133
- output: 3.2,
8134
- cacheRead: 0.2,
8258
+ input: 1.4,
8259
+ output: 4.4,
8260
+ cacheRead: 0.26,
8135
8261
  cacheWrite: 0,
8136
8262
  },
8137
8263
  contextWindow: 202752,
8138
8264
  maxTokens: 32768,
8139
8265
  },
8140
- "glm-5.1": {
8141
- id: "glm-5.1",
8142
- name: "GLM-5.1",
8266
+ "glm-5.2": {
8267
+ id: "glm-5.2",
8268
+ name: "GLM-5.2",
8143
8269
  api: "openai-completions",
8144
8270
  provider: "opencode-go",
8145
8271
  baseUrl: "https://opencode.ai/zen/go/v1",
@@ -8151,8 +8277,8 @@ export const MODELS = {
8151
8277
  cacheRead: 0.26,
8152
8278
  cacheWrite: 0,
8153
8279
  },
8154
- contextWindow: 202752,
8155
- maxTokens: 32768,
8280
+ contextWindow: 1000000,
8281
+ maxTokens: 131072,
8156
8282
  },
8157
8283
  "kimi-k2.6": {
8158
8284
  id: "kimi-k2.6",
@@ -8862,6 +8988,23 @@ export const MODELS = {
8862
8988
  contextWindow: 128000,
8863
8989
  maxTokens: 4000,
8864
8990
  },
8991
+ "cohere/north-mini-code:free": {
8992
+ id: "cohere/north-mini-code:free",
8993
+ name: "Cohere: North Mini Code (free)",
8994
+ api: "openai-completions",
8995
+ provider: "openrouter",
8996
+ baseUrl: "https://openrouter.ai/api/v1",
8997
+ reasoning: true,
8998
+ input: ["text"],
8999
+ cost: {
9000
+ input: 0,
9001
+ output: 0,
9002
+ cacheRead: 0,
9003
+ cacheWrite: 0,
9004
+ },
9005
+ contextWindow: 256000,
9006
+ maxTokens: 64000,
9007
+ },
8865
9008
  "deepseek/deepseek-chat": {
8866
9009
  id: "deepseek/deepseek-chat",
8867
9010
  name: "DeepSeek: DeepSeek V3",
@@ -9170,7 +9313,7 @@ export const MODELS = {
9170
9313
  cacheWrite: 0.08333333333333334,
9171
9314
  },
9172
9315
  contextWindow: 1048576,
9173
- maxTokens: 65536,
9316
+ maxTokens: 65535,
9174
9317
  },
9175
9318
  "google/gemini-3.1-flash-lite": {
9176
9319
  id: "google/gemini-3.1-flash-lite",
@@ -9357,7 +9500,7 @@ export const MODELS = {
9357
9500
  cacheWrite: 0,
9358
9501
  },
9359
9502
  contextWindow: 262144,
9360
- maxTokens: 32768,
9503
+ maxTokens: 8192,
9361
9504
  },
9362
9505
  "ibm-granite/granite-4.1-8b": {
9363
9506
  id: "ibm-granite/granite-4.1-8b",
@@ -10050,13 +10193,13 @@ export const MODELS = {
10050
10193
  reasoning: true,
10051
10194
  input: ["text", "image"],
10052
10195
  cost: {
10053
- input: 0.75,
10196
+ input: 0.74,
10054
10197
  output: 3.5,
10055
- cacheRead: 0.16,
10198
+ cacheRead: 0.15,
10056
10199
  cacheWrite: 0,
10057
10200
  },
10058
10201
  contextWindow: 262144,
10059
- maxTokens: 262144,
10202
+ maxTokens: 16384,
10060
10203
  },
10061
10204
  "nex-agi/nex-n2-pro:free": {
10062
10205
  id: "nex-agi/nex-n2-pro:free",
@@ -10187,8 +10330,8 @@ export const MODELS = {
10187
10330
  input: ["text"],
10188
10331
  cost: {
10189
10332
  input: 0.5,
10190
- output: 2.5,
10191
- cacheRead: 0.15,
10333
+ output: 2.2,
10334
+ cacheRead: 0.09999999999999999,
10192
10335
  cacheWrite: 0,
10193
10336
  },
10194
10337
  contextWindow: 1000000,
@@ -11003,7 +11146,7 @@ export const MODELS = {
11003
11146
  cacheWrite: 0,
11004
11147
  },
11005
11148
  contextWindow: 131072,
11006
- maxTokens: 8192,
11149
+ maxTokens: 32768,
11007
11150
  },
11008
11151
  "openai/gpt-oss-safeguard-20b": {
11009
11152
  id: "openai/gpt-oss-safeguard-20b",
@@ -11853,7 +11996,7 @@ export const MODELS = {
11853
11996
  cacheWrite: 0,
11854
11997
  },
11855
11998
  contextWindow: 262144,
11856
- maxTokens: 262144,
11999
+ maxTokens: 81920,
11857
12000
  },
11858
12001
  "qwen/qwen3.5-397b-a17b": {
11859
12002
  id: "qwen/qwen3.5-397b-a17b",
@@ -11864,13 +12007,13 @@ export const MODELS = {
11864
12007
  reasoning: true,
11865
12008
  input: ["text", "image"],
11866
12009
  cost: {
11867
- input: 0.39,
11868
- output: 2.34,
12010
+ input: 0.385,
12011
+ output: 2.4499999999999997,
11869
12012
  cacheRead: 0,
11870
12013
  cacheWrite: 0,
11871
12014
  },
11872
- contextWindow: 262144,
11873
- maxTokens: 65536,
12015
+ contextWindow: 256000,
12016
+ maxTokens: 4096,
11874
12017
  },
11875
12018
  "qwen/qwen3.5-9b": {
11876
12019
  id: "qwen/qwen3.5-9b",
@@ -12153,13 +12296,13 @@ export const MODELS = {
12153
12296
  reasoning: true,
12154
12297
  input: ["text"],
12155
12298
  cost: {
12156
- input: 0.063,
12157
- output: 0.21,
12158
- cacheRead: 0.020999999999999998,
12299
+ input: 0.06599999999999999,
12300
+ output: 0.26,
12301
+ cacheRead: 0.029,
12159
12302
  cacheWrite: 0,
12160
12303
  },
12161
12304
  contextWindow: 262144,
12162
- maxTokens: 4096,
12305
+ maxTokens: 262144,
12163
12306
  },
12164
12307
  "thedrummer/rocinante-12b": {
12165
12308
  id: "thedrummer/rocinante-12b",
@@ -12263,23 +12406,6 @@ export const MODELS = {
12263
12406
  contextWindow: 256000,
12264
12407
  maxTokens: 4096,
12265
12408
  },
12266
- "xiaomi/mimo-v2-flash": {
12267
- id: "xiaomi/mimo-v2-flash",
12268
- name: "Xiaomi: MiMo-V2-Flash",
12269
- api: "openai-completions",
12270
- provider: "openrouter",
12271
- baseUrl: "https://openrouter.ai/api/v1",
12272
- reasoning: true,
12273
- input: ["text"],
12274
- cost: {
12275
- input: 0.09999999999999999,
12276
- output: 0.3,
12277
- cacheRead: 0.01,
12278
- cacheWrite: 0,
12279
- },
12280
- contextWindow: 262144,
12281
- maxTokens: 65536,
12282
- },
12283
12409
  "xiaomi/mimo-v2.5": {
12284
12410
  id: "xiaomi/mimo-v2.5",
12285
12411
  name: "Xiaomi: MiMo-V2.5",
@@ -12340,13 +12466,13 @@ export const MODELS = {
12340
12466
  reasoning: true,
12341
12467
  input: ["text"],
12342
12468
  cost: {
12343
- input: 0.125,
12469
+ input: 0.13,
12344
12470
  output: 0.85,
12345
- cacheRead: 0.06,
12471
+ cacheRead: 0.024999999999999998,
12346
12472
  cacheWrite: 0,
12347
12473
  },
12348
12474
  contextWindow: 131072,
12349
- maxTokens: 131070,
12475
+ maxTokens: 98304,
12350
12476
  },
12351
12477
  "z-ai/glm-4.5v": {
12352
12478
  id: "z-ai/glm-4.5v",
@@ -12484,6 +12610,23 @@ export const MODELS = {
12484
12610
  contextWindow: 202752,
12485
12611
  maxTokens: 4096,
12486
12612
  },
12613
+ "z-ai/glm-5.2": {
12614
+ id: "z-ai/glm-5.2",
12615
+ name: "Z.ai: GLM 5.2",
12616
+ api: "openai-completions",
12617
+ provider: "openrouter",
12618
+ baseUrl: "https://openrouter.ai/api/v1",
12619
+ reasoning: true,
12620
+ input: ["text"],
12621
+ cost: {
12622
+ input: 1.4,
12623
+ output: 4.4,
12624
+ cacheRead: 0.26,
12625
+ cacheWrite: 0,
12626
+ },
12627
+ contextWindow: 1048576,
12628
+ maxTokens: 262144,
12629
+ },
12487
12630
  "~anthropic/claude-fable-latest": {
12488
12631
  id: "~anthropic/claude-fable-latest",
12489
12632
  name: "Anthropic: Claude Fable Latest",
@@ -12780,8 +12923,8 @@ export const MODELS = {
12780
12923
  reasoning: false,
12781
12924
  input: ["text"],
12782
12925
  cost: {
12783
- input: 2.5,
12784
- output: 7.5,
12926
+ input: 1.25,
12927
+ output: 3.75,
12785
12928
  cacheRead: 0,
12786
12929
  cacheWrite: 0,
12787
12930
  },
@@ -12881,6 +13024,25 @@ export const MODELS = {
12881
13024
  contextWindow: 262144,
12882
13025
  maxTokens: 131000,
12883
13026
  },
13027
+ "moonshotai/Kimi-K2.7-Code": {
13028
+ id: "moonshotai/Kimi-K2.7-Code",
13029
+ name: "Kimi K2.7 Code",
13030
+ api: "openai-completions",
13031
+ provider: "together",
13032
+ baseUrl: "https://api.together.ai/v1",
13033
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
13034
+ reasoning: true,
13035
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
13036
+ input: ["text"],
13037
+ cost: {
13038
+ input: 0.95,
13039
+ output: 4,
13040
+ cacheRead: 0.19,
13041
+ cacheWrite: 0,
13042
+ },
13043
+ contextWindow: 262144,
13044
+ maxTokens: 131072,
13045
+ },
12884
13046
  "nvidia/nemotron-3-ultra-550b-a55b": {
12885
13047
  id: "nvidia/nemotron-3-ultra-550b-a55b",
12886
13048
  name: "Nemotron 3 Ultra 550B A55B",
@@ -14422,13 +14584,13 @@ export const MODELS = {
14422
14584
  reasoning: false,
14423
14585
  input: ["text"],
14424
14586
  cost: {
14425
- input: 0.02,
14426
- output: 0.04,
14587
+ input: 0.15,
14588
+ output: 0.15,
14427
14589
  cacheRead: 0,
14428
14590
  cacheWrite: 0,
14429
14591
  },
14430
- contextWindow: 131072,
14431
- maxTokens: 131072,
14592
+ contextWindow: 128000,
14593
+ maxTokens: 128000,
14432
14594
  },
14433
14595
  "mistral/mistral-small": {
14434
14596
  id: "mistral/mistral-small",
@@ -14566,6 +14728,23 @@ export const MODELS = {
14566
14728
  contextWindow: 256000,
14567
14729
  maxTokens: 32768,
14568
14730
  },
14731
+ "moonshotai/kimi-k2.7-code-highspeed": {
14732
+ id: "moonshotai/kimi-k2.7-code-highspeed",
14733
+ name: "Kimi K2.7 Code High Speed",
14734
+ api: "anthropic-messages",
14735
+ provider: "vercel-ai-gateway",
14736
+ baseUrl: "https://ai-gateway.vercel.sh",
14737
+ reasoning: true,
14738
+ input: ["text", "image"],
14739
+ cost: {
14740
+ input: 1.9,
14741
+ output: 8,
14742
+ cacheRead: 0.38,
14743
+ cacheWrite: 0,
14744
+ },
14745
+ contextWindow: 262144,
14746
+ maxTokens: 32768,
14747
+ },
14569
14748
  "nvidia/nemotron-3-super-120b-a12b": {
14570
14749
  id: "nvidia/nemotron-3-super-120b-a12b",
14571
14750
  name: "NVIDIA Nemotron 3 Super 120B A12B",
@@ -15802,6 +15981,23 @@ export const MODELS = {
15802
15981
  contextWindow: 202800,
15803
15982
  maxTokens: 64000,
15804
15983
  },
15984
+ "zai/glm-5.2": {
15985
+ id: "zai/glm-5.2",
15986
+ name: "GLM 5.2",
15987
+ api: "anthropic-messages",
15988
+ provider: "vercel-ai-gateway",
15989
+ baseUrl: "https://ai-gateway.vercel.sh",
15990
+ reasoning: true,
15991
+ input: ["text"],
15992
+ cost: {
15993
+ input: 1.5,
15994
+ output: 4.5,
15995
+ cacheRead: 0.3,
15996
+ cacheWrite: 0,
15997
+ },
15998
+ contextWindow: 1000000,
15999
+ maxTokens: 128000,
16000
+ },
15805
16001
  "zai/glm-5v-turbo": {
15806
16002
  id: "zai/glm-5v-turbo",
15807
16003
  name: "GLM 5V Turbo",