@fleetagent/pi-ai 0.1.3 → 0.1.4

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.
@@ -3846,7 +3846,7 @@ export const MODELS = {
3846
3846
  cost: {
3847
3847
  input: 0.15,
3848
3848
  output: 0.6,
3849
- cacheRead: 0.015,
3849
+ cacheRead: 0.01,
3850
3850
  cacheWrite: 0,
3851
3851
  },
3852
3852
  contextWindow: 131072,
@@ -4755,6 +4755,42 @@ export const MODELS = {
4755
4755
  contextWindow: 262144,
4756
4756
  maxTokens: 32768,
4757
4757
  },
4758
+ "gemma-4-E2B-it": {
4759
+ id: "gemma-4-E2B-it",
4760
+ name: "Gemma 4 E2B IT",
4761
+ api: "google-generative-ai",
4762
+ provider: "google",
4763
+ baseUrl: "https://generativelanguage.googleapis.com/v1beta",
4764
+ reasoning: true,
4765
+ thinkingLevelMap: { "off": null, "minimal": "MINIMAL", "low": null, "medium": null, "high": "HIGH" },
4766
+ input: ["text", "image"],
4767
+ cost: {
4768
+ input: 0,
4769
+ output: 0,
4770
+ cacheRead: 0,
4771
+ cacheWrite: 0,
4772
+ },
4773
+ contextWindow: 131072,
4774
+ maxTokens: 8192,
4775
+ },
4776
+ "gemma-4-E4B-it": {
4777
+ id: "gemma-4-E4B-it",
4778
+ name: "Gemma 4 E4B IT",
4779
+ api: "google-generative-ai",
4780
+ provider: "google",
4781
+ baseUrl: "https://generativelanguage.googleapis.com/v1beta",
4782
+ reasoning: true,
4783
+ thinkingLevelMap: { "off": null, "minimal": "MINIMAL", "low": null, "medium": null, "high": "HIGH" },
4784
+ input: ["text", "image"],
4785
+ cost: {
4786
+ input: 0,
4787
+ output: 0,
4788
+ cacheRead: 0,
4789
+ cacheWrite: 0,
4790
+ },
4791
+ contextWindow: 131072,
4792
+ maxTokens: 8192,
4793
+ },
4758
4794
  },
4759
4795
  "google-vertex": {
4760
4796
  "gemini-1.5-flash": {
@@ -6288,6 +6324,24 @@ export const MODELS = {
6288
6324
  contextWindow: 262144,
6289
6325
  maxTokens: 262144,
6290
6326
  },
6327
+ "kimi-k2.7-code-highspeed": {
6328
+ id: "kimi-k2.7-code-highspeed",
6329
+ name: "Kimi K2.7 Code HighSpeed",
6330
+ api: "openai-completions",
6331
+ provider: "moonshotai",
6332
+ baseUrl: "https://api.moonshot.ai/v1",
6333
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
6334
+ reasoning: true,
6335
+ input: ["text", "image"],
6336
+ cost: {
6337
+ input: 1.9,
6338
+ output: 8,
6339
+ cacheRead: 0.38,
6340
+ cacheWrite: 0,
6341
+ },
6342
+ contextWindow: 262144,
6343
+ maxTokens: 262144,
6344
+ },
6291
6345
  },
6292
6346
  "moonshotai-cn": {
6293
6347
  "kimi-k2-0711-preview": {
@@ -6416,6 +6470,42 @@ export const MODELS = {
6416
6470
  contextWindow: 262144,
6417
6471
  maxTokens: 262144,
6418
6472
  },
6473
+ "kimi-k2.7-code": {
6474
+ id: "kimi-k2.7-code",
6475
+ name: "Kimi K2.7 Code",
6476
+ api: "openai-completions",
6477
+ provider: "moonshotai-cn",
6478
+ baseUrl: "https://api.moonshot.cn/v1",
6479
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
6480
+ reasoning: true,
6481
+ input: ["text", "image"],
6482
+ cost: {
6483
+ input: 0.95,
6484
+ output: 4,
6485
+ cacheRead: 0.19,
6486
+ cacheWrite: 0,
6487
+ },
6488
+ contextWindow: 262144,
6489
+ maxTokens: 262144,
6490
+ },
6491
+ "kimi-k2.7-code-highspeed": {
6492
+ id: "kimi-k2.7-code-highspeed",
6493
+ name: "Kimi K2.7 Code HighSpeed",
6494
+ api: "openai-completions",
6495
+ provider: "moonshotai-cn",
6496
+ baseUrl: "https://api.moonshot.cn/v1",
6497
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
6498
+ reasoning: true,
6499
+ input: ["text", "image"],
6500
+ cost: {
6501
+ input: 1.9,
6502
+ output: 8,
6503
+ cacheRead: 0.38,
6504
+ cacheWrite: 0,
6505
+ },
6506
+ contextWindow: 262144,
6507
+ maxTokens: 262144,
6508
+ },
6419
6509
  },
6420
6510
  "openai": {
6421
6511
  "gpt-4": {
@@ -8977,13 +9067,13 @@ export const MODELS = {
8977
9067
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
8978
9068
  input: ["text"],
8979
9069
  cost: {
8980
- input: 0.09,
8981
- output: 0.18,
9070
+ input: 0.098,
9071
+ output: 0.196,
8982
9072
  cacheRead: 0.02,
8983
9073
  cacheWrite: 0,
8984
9074
  },
8985
9075
  contextWindow: 1048576,
8986
- maxTokens: 65536,
9076
+ maxTokens: 4096,
8987
9077
  },
8988
9078
  "deepseek/deepseek-v4-pro": {
8989
9079
  id: "deepseek/deepseek-v4-pro",
@@ -11821,7 +11911,7 @@ export const MODELS = {
11821
11911
  cacheWrite: 0,
11822
11912
  },
11823
11913
  contextWindow: 262144,
11824
- maxTokens: 262144,
11914
+ maxTokens: 81920,
11825
11915
  },
11826
11916
  "qwen/qwen3.5-397b-a17b": {
11827
11917
  id: "qwen/qwen3.5-397b-a17b",
@@ -11832,13 +11922,13 @@ export const MODELS = {
11832
11922
  reasoning: true,
11833
11923
  input: ["text", "image"],
11834
11924
  cost: {
11835
- input: 0.39,
11836
- output: 2.34,
11925
+ input: 0.385,
11926
+ output: 2.4499999999999997,
11837
11927
  cacheRead: 0,
11838
11928
  cacheWrite: 0,
11839
11929
  },
11840
- contextWindow: 262144,
11841
- maxTokens: 65536,
11930
+ contextWindow: 256000,
11931
+ maxTokens: 4096,
11842
11932
  },
11843
11933
  "qwen/qwen3.5-9b": {
11844
11934
  id: "qwen/qwen3.5-9b",
@@ -12121,13 +12211,13 @@ export const MODELS = {
12121
12211
  reasoning: true,
12122
12212
  input: ["text"],
12123
12213
  cost: {
12124
- input: 0.063,
12125
- output: 0.21,
12126
- cacheRead: 0.020999999999999998,
12214
+ input: 0.06599999999999999,
12215
+ output: 0.26,
12216
+ cacheRead: 0.029,
12127
12217
  cacheWrite: 0,
12128
12218
  },
12129
12219
  contextWindow: 262144,
12130
- maxTokens: 4096,
12220
+ maxTokens: 262144,
12131
12221
  },
12132
12222
  "thedrummer/rocinante-12b": {
12133
12223
  id: "thedrummer/rocinante-12b",
@@ -12308,13 +12398,13 @@ export const MODELS = {
12308
12398
  reasoning: true,
12309
12399
  input: ["text"],
12310
12400
  cost: {
12311
- input: 0.125,
12401
+ input: 0.13,
12312
12402
  output: 0.85,
12313
- cacheRead: 0.06,
12403
+ cacheRead: 0.024999999999999998,
12314
12404
  cacheWrite: 0,
12315
12405
  },
12316
12406
  contextWindow: 131072,
12317
- maxTokens: 131070,
12407
+ maxTokens: 98304,
12318
12408
  },
12319
12409
  "z-ai/glm-4.5v": {
12320
12410
  id: "z-ai/glm-4.5v",
@@ -12748,8 +12838,8 @@ export const MODELS = {
12748
12838
  reasoning: false,
12749
12839
  input: ["text"],
12750
12840
  cost: {
12751
- input: 2.5,
12752
- output: 7.5,
12841
+ input: 1.25,
12842
+ output: 3.75,
12753
12843
  cacheRead: 0,
12754
12844
  cacheWrite: 0,
12755
12845
  },
@@ -12849,6 +12939,25 @@ export const MODELS = {
12849
12939
  contextWindow: 262144,
12850
12940
  maxTokens: 131000,
12851
12941
  },
12942
+ "moonshotai/Kimi-K2.7-Code": {
12943
+ id: "moonshotai/Kimi-K2.7-Code",
12944
+ name: "Kimi K2.7 Code",
12945
+ api: "openai-completions",
12946
+ provider: "together",
12947
+ baseUrl: "https://api.together.ai/v1",
12948
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
12949
+ reasoning: true,
12950
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
12951
+ input: ["text"],
12952
+ cost: {
12953
+ input: 0.95,
12954
+ output: 4,
12955
+ cacheRead: 0.19,
12956
+ cacheWrite: 0,
12957
+ },
12958
+ contextWindow: 262144,
12959
+ maxTokens: 131072,
12960
+ },
12852
12961
  "nvidia/nemotron-3-ultra-550b-a55b": {
12853
12962
  id: "nvidia/nemotron-3-ultra-550b-a55b",
12854
12963
  name: "Nemotron 3 Ultra 550B A55B",
@@ -14533,6 +14642,23 @@ export const MODELS = {
14533
14642
  contextWindow: 256000,
14534
14643
  maxTokens: 32768,
14535
14644
  },
14645
+ "moonshotai/kimi-k2.7-code-highspeed": {
14646
+ id: "moonshotai/kimi-k2.7-code-highspeed",
14647
+ name: "Kimi K2.7 Code High Speed",
14648
+ api: "anthropic-messages",
14649
+ provider: "vercel-ai-gateway",
14650
+ baseUrl: "https://ai-gateway.vercel.sh",
14651
+ reasoning: true,
14652
+ input: ["text", "image"],
14653
+ cost: {
14654
+ input: 1.9,
14655
+ output: 8,
14656
+ cacheRead: 0.38,
14657
+ cacheWrite: 0,
14658
+ },
14659
+ contextWindow: 262144,
14660
+ maxTokens: 4096,
14661
+ },
14536
14662
  "nvidia/nemotron-3-super-120b-a12b": {
14537
14663
  id: "nvidia/nemotron-3-super-120b-a12b",
14538
14664
  name: "NVIDIA Nemotron 3 Super 120B A12B",