@mariozechner/pi-ai 0.63.1 → 0.64.0

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.
@@ -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": {
@@ -3978,6 +3995,40 @@ export const MODELS = {
3978
3995
  contextWindow: 8192,
3979
3996
  maxTokens: 8192,
3980
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
+ },
3981
4032
  "llama-3.1-8b-instant": {
3982
4033
  id: "llama-3.1-8b-instant",
3983
4034
  name: "Llama 3.1 8B Instant",
@@ -4165,6 +4216,23 @@ export const MODELS = {
4165
4216
  contextWindow: 131072,
4166
4217
  maxTokens: 65536,
4167
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
+ },
4168
4236
  "qwen-qwq-32b": {
4169
4237
  id: "qwen-qwq-32b",
4170
4238
  name: "Qwen QwQ 32B",
@@ -4197,7 +4265,7 @@ export const MODELS = {
4197
4265
  cacheWrite: 0,
4198
4266
  },
4199
4267
  contextWindow: 131072,
4200
- maxTokens: 16384,
4268
+ maxTokens: 40960,
4201
4269
  },
4202
4270
  },
4203
4271
  "huggingface": {
@@ -7518,6 +7586,23 @@ export const MODELS = {
7518
7586
  contextWindow: 256000,
7519
7587
  maxTokens: 128000,
7520
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
+ },
7521
7606
  "meituan/longcat-flash-chat": {
7522
7607
  id: "meituan/longcat-flash-chat",
7523
7608
  name: "Meituan: LongCat Flash Chat",
@@ -7714,9 +7799,9 @@ export const MODELS = {
7714
7799
  reasoning: true,
7715
7800
  input: ["text"],
7716
7801
  cost: {
7717
- input: 0.19999999999999998,
7718
- output: 1.17,
7719
- cacheRead: 0.09999999999999999,
7802
+ input: 0.19,
7803
+ output: 1.15,
7804
+ cacheRead: 0.095,
7720
7805
  cacheWrite: 0,
7721
7806
  },
7722
7807
  contextWindow: 196608,
@@ -8045,23 +8130,6 @@ export const MODELS = {
8045
8130
  contextWindow: 262144,
8046
8131
  maxTokens: 4096,
8047
8132
  },
8048
- "mistralai/mistral-small-3.1-24b-instruct:free": {
8049
- id: "mistralai/mistral-small-3.1-24b-instruct:free",
8050
- name: "Mistral: Mistral Small 3.1 24B (free)",
8051
- api: "openai-completions",
8052
- provider: "openrouter",
8053
- baseUrl: "https://openrouter.ai/api/v1",
8054
- reasoning: false,
8055
- input: ["text", "image"],
8056
- cost: {
8057
- input: 0,
8058
- output: 0,
8059
- cacheRead: 0,
8060
- cacheWrite: 0,
8061
- },
8062
- contextWindow: 128000,
8063
- maxTokens: 4096,
8064
- },
8065
8133
  "mistralai/mistral-small-3.2-24b-instruct": {
8066
8134
  id: "mistralai/mistral-small-3.2-24b-instruct",
8067
8135
  name: "Mistral: Mistral Small 3.2 24B",
@@ -9660,23 +9728,6 @@ export const MODELS = {
9660
9728
  contextWindow: 40960,
9661
9729
  maxTokens: 40960,
9662
9730
  },
9663
- "qwen/qwen3-4b:free": {
9664
- id: "qwen/qwen3-4b:free",
9665
- name: "Qwen: Qwen3 4B (free)",
9666
- api: "openai-completions",
9667
- provider: "openrouter",
9668
- baseUrl: "https://openrouter.ai/api/v1",
9669
- reasoning: true,
9670
- input: ["text"],
9671
- cost: {
9672
- input: 0,
9673
- output: 0,
9674
- cacheRead: 0,
9675
- cacheWrite: 0,
9676
- },
9677
- contextWindow: 40960,
9678
- maxTokens: 4096,
9679
- },
9680
9731
  "qwen/qwen3-8b": {
9681
9732
  id: "qwen/qwen3-8b",
9682
9733
  name: "Qwen: Qwen3 8B",
@@ -11515,6 +11566,23 @@ export const MODELS = {
11515
11566
  contextWindow: 32000,
11516
11567
  maxTokens: 16384,
11517
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
+ },
11518
11586
  "meituan/longcat-flash-chat": {
11519
11587
  id: "meituan/longcat-flash-chat",
11520
11588
  name: "LongCat Flash Chat",
@@ -13215,23 +13283,6 @@ export const MODELS = {
13215
13283
  contextWindow: 200000,
13216
13284
  maxTokens: 128000,
13217
13285
  },
13218
- "zai/glm-5": {
13219
- id: "zai/glm-5",
13220
- name: "GLM 5",
13221
- api: "anthropic-messages",
13222
- provider: "vercel-ai-gateway",
13223
- baseUrl: "https://ai-gateway.vercel.sh",
13224
- reasoning: true,
13225
- input: ["text"],
13226
- cost: {
13227
- input: 1,
13228
- output: 3.1999999999999997,
13229
- cacheRead: 0.19999999999999998,
13230
- cacheWrite: 0,
13231
- },
13232
- contextWindow: 202800,
13233
- maxTokens: 131100,
13234
- },
13235
13286
  "zai/glm-5-turbo": {
13236
13287
  id: "zai/glm-5-turbo",
13237
13288
  name: "GLM 5 Turbo",