@mariozechner/pi-ai 0.63.0 → 0.63.2

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.
@@ -3460,6 +3460,23 @@ export const MODELS = {
3460
3460
  contextWindow: 131072,
3461
3461
  maxTokens: 65536,
3462
3462
  },
3463
+ "gemma-3-27b-it": {
3464
+ id: "gemma-3-27b-it",
3465
+ name: "Gemma 3 27B",
3466
+ api: "google-generative-ai",
3467
+ provider: "google",
3468
+ baseUrl: "https://generativelanguage.googleapis.com/v1beta",
3469
+ reasoning: false,
3470
+ input: ["text", "image"],
3471
+ cost: {
3472
+ input: 0,
3473
+ output: 0,
3474
+ cacheRead: 0,
3475
+ cacheWrite: 0,
3476
+ },
3477
+ contextWindow: 131072,
3478
+ maxTokens: 8192,
3479
+ },
3463
3480
  },
3464
3481
  "google-antigravity": {
3465
3482
  "claude-opus-4-5-thinking": {
@@ -3925,6 +3942,23 @@ export const MODELS = {
3925
3942
  contextWindow: 1048576,
3926
3943
  maxTokens: 65536,
3927
3944
  },
3945
+ "gemini-3.1-pro-preview-customtools": {
3946
+ id: "gemini-3.1-pro-preview-customtools",
3947
+ name: "Gemini 3.1 Pro Preview Custom Tools (Vertex)",
3948
+ api: "google-vertex",
3949
+ provider: "google-vertex",
3950
+ baseUrl: "https://{location}-aiplatform.googleapis.com",
3951
+ reasoning: true,
3952
+ input: ["text", "image"],
3953
+ cost: {
3954
+ input: 2,
3955
+ output: 12,
3956
+ cacheRead: 0.2,
3957
+ cacheWrite: 0,
3958
+ },
3959
+ contextWindow: 1048576,
3960
+ maxTokens: 65536,
3961
+ },
3928
3962
  },
3929
3963
  "groq": {
3930
3964
  "deepseek-r1-distill-llama-70b": {
@@ -3961,6 +3995,40 @@ export const MODELS = {
3961
3995
  contextWindow: 8192,
3962
3996
  maxTokens: 8192,
3963
3997
  },
3998
+ "groq/compound": {
3999
+ id: "groq/compound",
4000
+ name: "Compound",
4001
+ api: "openai-completions",
4002
+ provider: "groq",
4003
+ baseUrl: "https://api.groq.com/openai/v1",
4004
+ reasoning: true,
4005
+ input: ["text"],
4006
+ cost: {
4007
+ input: 0,
4008
+ output: 0,
4009
+ cacheRead: 0,
4010
+ cacheWrite: 0,
4011
+ },
4012
+ contextWindow: 131072,
4013
+ maxTokens: 8192,
4014
+ },
4015
+ "groq/compound-mini": {
4016
+ id: "groq/compound-mini",
4017
+ name: "Compound Mini",
4018
+ api: "openai-completions",
4019
+ provider: "groq",
4020
+ baseUrl: "https://api.groq.com/openai/v1",
4021
+ reasoning: true,
4022
+ input: ["text"],
4023
+ cost: {
4024
+ input: 0,
4025
+ output: 0,
4026
+ cacheRead: 0,
4027
+ cacheWrite: 0,
4028
+ },
4029
+ contextWindow: 131072,
4030
+ maxTokens: 8192,
4031
+ },
3964
4032
  "llama-3.1-8b-instant": {
3965
4033
  id: "llama-3.1-8b-instant",
3966
4034
  name: "Llama 3.1 8B Instant",
@@ -4148,6 +4216,23 @@ export const MODELS = {
4148
4216
  contextWindow: 131072,
4149
4217
  maxTokens: 65536,
4150
4218
  },
4219
+ "openai/gpt-oss-safeguard-20b": {
4220
+ id: "openai/gpt-oss-safeguard-20b",
4221
+ name: "Safety GPT OSS 20B",
4222
+ api: "openai-completions",
4223
+ provider: "groq",
4224
+ baseUrl: "https://api.groq.com/openai/v1",
4225
+ reasoning: true,
4226
+ input: ["text"],
4227
+ cost: {
4228
+ input: 0.075,
4229
+ output: 0.3,
4230
+ cacheRead: 0.037,
4231
+ cacheWrite: 0,
4232
+ },
4233
+ contextWindow: 131072,
4234
+ maxTokens: 65536,
4235
+ },
4151
4236
  "qwen-qwq-32b": {
4152
4237
  id: "qwen-qwq-32b",
4153
4238
  name: "Qwen QwQ 32B",
@@ -4180,7 +4265,7 @@ export const MODELS = {
4180
4265
  cacheWrite: 0,
4181
4266
  },
4182
4267
  contextWindow: 131072,
4183
- maxTokens: 16384,
4268
+ maxTokens: 40960,
4184
4269
  },
4185
4270
  },
4186
4271
  "huggingface": {
@@ -7501,6 +7586,23 @@ export const MODELS = {
7501
7586
  contextWindow: 256000,
7502
7587
  maxTokens: 128000,
7503
7588
  },
7589
+ "kwaipilot/kat-coder-pro-v2": {
7590
+ id: "kwaipilot/kat-coder-pro-v2",
7591
+ name: "Kwaipilot: KAT-Coder-Pro V2",
7592
+ api: "openai-completions",
7593
+ provider: "openrouter",
7594
+ baseUrl: "https://openrouter.ai/api/v1",
7595
+ reasoning: false,
7596
+ input: ["text"],
7597
+ cost: {
7598
+ input: 0.3,
7599
+ output: 1.2,
7600
+ cacheRead: 0.06,
7601
+ cacheWrite: 0,
7602
+ },
7603
+ contextWindow: 256000,
7604
+ maxTokens: 80000,
7605
+ },
7504
7606
  "meituan/longcat-flash-chat": {
7505
7607
  id: "meituan/longcat-flash-chat",
7506
7608
  name: "Meituan: LongCat Flash Chat",
@@ -7697,9 +7799,9 @@ export const MODELS = {
7697
7799
  reasoning: true,
7698
7800
  input: ["text"],
7699
7801
  cost: {
7700
- input: 0.19999999999999998,
7701
- output: 1.17,
7702
- cacheRead: 0.09999999999999999,
7802
+ input: 0.19,
7803
+ output: 1.15,
7804
+ cacheRead: 0.095,
7703
7805
  cacheWrite: 0,
7704
7806
  },
7705
7807
  contextWindow: 196608,
@@ -8028,23 +8130,6 @@ export const MODELS = {
8028
8130
  contextWindow: 262144,
8029
8131
  maxTokens: 4096,
8030
8132
  },
8031
- "mistralai/mistral-small-3.1-24b-instruct:free": {
8032
- id: "mistralai/mistral-small-3.1-24b-instruct:free",
8033
- name: "Mistral: Mistral Small 3.1 24B (free)",
8034
- api: "openai-completions",
8035
- provider: "openrouter",
8036
- baseUrl: "https://openrouter.ai/api/v1",
8037
- reasoning: false,
8038
- input: ["text", "image"],
8039
- cost: {
8040
- input: 0,
8041
- output: 0,
8042
- cacheRead: 0,
8043
- cacheWrite: 0,
8044
- },
8045
- contextWindow: 128000,
8046
- maxTokens: 4096,
8047
- },
8048
8133
  "mistralai/mistral-small-3.2-24b-instruct": {
8049
8134
  id: "mistralai/mistral-small-3.2-24b-instruct",
8050
8135
  name: "Mistral: Mistral Small 3.2 24B",
@@ -9643,23 +9728,6 @@ export const MODELS = {
9643
9728
  contextWindow: 40960,
9644
9729
  maxTokens: 40960,
9645
9730
  },
9646
- "qwen/qwen3-4b:free": {
9647
- id: "qwen/qwen3-4b:free",
9648
- name: "Qwen: Qwen3 4B (free)",
9649
- api: "openai-completions",
9650
- provider: "openrouter",
9651
- baseUrl: "https://openrouter.ai/api/v1",
9652
- reasoning: true,
9653
- input: ["text"],
9654
- cost: {
9655
- input: 0,
9656
- output: 0,
9657
- cacheRead: 0,
9658
- cacheWrite: 0,
9659
- },
9660
- contextWindow: 40960,
9661
- maxTokens: 4096,
9662
- },
9663
9731
  "qwen/qwen3-8b": {
9664
9732
  id: "qwen/qwen3-8b",
9665
9733
  name: "Qwen: Qwen3 8B",
@@ -11498,6 +11566,23 @@ export const MODELS = {
11498
11566
  contextWindow: 32000,
11499
11567
  maxTokens: 16384,
11500
11568
  },
11569
+ "kwaipilot/kat-coder-pro-v2": {
11570
+ id: "kwaipilot/kat-coder-pro-v2",
11571
+ name: "Kat Coder Pro V2",
11572
+ api: "anthropic-messages",
11573
+ provider: "vercel-ai-gateway",
11574
+ baseUrl: "https://ai-gateway.vercel.sh",
11575
+ reasoning: true,
11576
+ input: ["text"],
11577
+ cost: {
11578
+ input: 0.3,
11579
+ output: 1.2,
11580
+ cacheRead: 0.06,
11581
+ cacheWrite: 0,
11582
+ },
11583
+ contextWindow: 256000,
11584
+ maxTokens: 256000,
11585
+ },
11501
11586
  "meituan/longcat-flash-chat": {
11502
11587
  id: "meituan/longcat-flash-chat",
11503
11588
  name: "LongCat Flash Chat",
@@ -13198,23 +13283,6 @@ export const MODELS = {
13198
13283
  contextWindow: 200000,
13199
13284
  maxTokens: 128000,
13200
13285
  },
13201
- "zai/glm-5": {
13202
- id: "zai/glm-5",
13203
- name: "GLM 5",
13204
- api: "anthropic-messages",
13205
- provider: "vercel-ai-gateway",
13206
- baseUrl: "https://ai-gateway.vercel.sh",
13207
- reasoning: true,
13208
- input: ["text"],
13209
- cost: {
13210
- input: 1,
13211
- output: 3.1999999999999997,
13212
- cacheRead: 0.19999999999999998,
13213
- cacheWrite: 0,
13214
- },
13215
- contextWindow: 202800,
13216
- maxTokens: 131100,
13217
- },
13218
13286
  "zai/glm-5-turbo": {
13219
13287
  id: "zai/glm-5-turbo",
13220
13288
  name: "GLM 5 Turbo",