@mariozechner/pi-ai 0.65.1 → 0.66.0

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.
@@ -1209,6 +1209,23 @@ export const MODELS = {
1209
1209
  contextWindow: 131072,
1210
1210
  maxTokens: 65536,
1211
1211
  },
1212
+ "qwen.qwen3-coder-next": {
1213
+ id: "qwen.qwen3-coder-next",
1214
+ name: "Qwen3 Coder Next",
1215
+ api: "bedrock-converse-stream",
1216
+ provider: "amazon-bedrock",
1217
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1218
+ reasoning: true,
1219
+ input: ["text"],
1220
+ cost: {
1221
+ input: 0.22,
1222
+ output: 1.8,
1223
+ cacheRead: 0,
1224
+ cacheWrite: 0,
1225
+ },
1226
+ contextWindow: 131072,
1227
+ maxTokens: 65536,
1228
+ },
1212
1229
  "qwen.qwen3-next-80b-a3b": {
1213
1230
  id: "qwen.qwen3-next-80b-a3b",
1214
1231
  name: "Qwen/Qwen3-Next-80B-A3B-Instruct",
@@ -3015,7 +3032,7 @@ export const MODELS = {
3015
3032
  },
3016
3033
  "gpt-5.4-mini": {
3017
3034
  id: "gpt-5.4-mini",
3018
- name: "GPT-5.4 mini",
3035
+ name: "GPT-5.4 Mini",
3019
3036
  api: "openai-responses",
3020
3037
  provider: "github-copilot",
3021
3038
  baseUrl: "https://api.individual.githubcopilot.com",
@@ -3477,8 +3494,8 @@ export const MODELS = {
3477
3494
  contextWindow: 131072,
3478
3495
  maxTokens: 8192,
3479
3496
  },
3480
- "gemma-4-26b": {
3481
- id: "gemma-4-26b",
3497
+ "gemma-4-26b-it": {
3498
+ id: "gemma-4-26b-it",
3482
3499
  name: "Gemma 4 26B",
3483
3500
  api: "google-generative-ai",
3484
3501
  provider: "google",
@@ -3494,8 +3511,8 @@ export const MODELS = {
3494
3511
  contextWindow: 256000,
3495
3512
  maxTokens: 8192,
3496
3513
  },
3497
- "gemma-4-31b": {
3498
- id: "gemma-4-31b",
3514
+ "gemma-4-31b-it": {
3515
+ id: "gemma-4-31b-it",
3499
3516
  name: "Gemma 4 31B",
3500
3517
  api: "google-generative-ai",
3501
3518
  provider: "google",
@@ -4627,6 +4644,24 @@ export const MODELS = {
4627
4644
  contextWindow: 202752,
4628
4645
  maxTokens: 131072,
4629
4646
  },
4647
+ "zai-org/GLM-5.1": {
4648
+ id: "zai-org/GLM-5.1",
4649
+ name: "GLM-5.1",
4650
+ api: "openai-completions",
4651
+ provider: "huggingface",
4652
+ baseUrl: "https://router.huggingface.co/v1",
4653
+ compat: { "supportsDeveloperRole": false },
4654
+ reasoning: true,
4655
+ input: ["text"],
4656
+ cost: {
4657
+ input: 1,
4658
+ output: 3.2,
4659
+ cacheRead: 0.2,
4660
+ cacheWrite: 0,
4661
+ },
4662
+ contextWindow: 202752,
4663
+ maxTokens: 131072,
4664
+ },
4630
4665
  },
4631
4666
  "kimi-coding": {
4632
4667
  "k2p5": {
@@ -6239,6 +6274,23 @@ export const MODELS = {
6239
6274
  contextWindow: 204800,
6240
6275
  maxTokens: 131072,
6241
6276
  },
6277
+ "glm-5.1": {
6278
+ id: "glm-5.1",
6279
+ name: "GLM-5.1",
6280
+ api: "openai-completions",
6281
+ provider: "opencode",
6282
+ baseUrl: "https://opencode.ai/zen/v1",
6283
+ reasoning: true,
6284
+ input: ["text"],
6285
+ cost: {
6286
+ input: 1.4,
6287
+ output: 4.4,
6288
+ cacheRead: 0.26,
6289
+ cacheWrite: 0,
6290
+ },
6291
+ contextWindow: 204800,
6292
+ maxTokens: 131072,
6293
+ },
6242
6294
  "gpt-5": {
6243
6295
  id: "gpt-5",
6244
6296
  name: "GPT-5",
@@ -6545,23 +6597,6 @@ export const MODELS = {
6545
6597
  contextWindow: 204800,
6546
6598
  maxTokens: 128000,
6547
6599
  },
6548
- "qwen3.6-plus-free": {
6549
- id: "qwen3.6-plus-free",
6550
- name: "Qwen3.6 Plus Free",
6551
- api: "openai-completions",
6552
- provider: "opencode",
6553
- baseUrl: "https://opencode.ai/zen/v1",
6554
- reasoning: true,
6555
- input: ["text"],
6556
- cost: {
6557
- input: 0,
6558
- output: 0,
6559
- cacheRead: 0,
6560
- cacheWrite: 0,
6561
- },
6562
- contextWindow: 1048576,
6563
- maxTokens: 64000,
6564
- },
6565
6600
  },
6566
6601
  "opencode-go": {
6567
6602
  "glm-5": {
@@ -6581,6 +6616,23 @@ export const MODELS = {
6581
6616
  contextWindow: 204800,
6582
6617
  maxTokens: 131072,
6583
6618
  },
6619
+ "glm-5.1": {
6620
+ id: "glm-5.1",
6621
+ name: "GLM-5.1",
6622
+ api: "openai-completions",
6623
+ provider: "opencode-go",
6624
+ baseUrl: "https://opencode.ai/zen/go/v1",
6625
+ reasoning: true,
6626
+ input: ["text"],
6627
+ cost: {
6628
+ input: 1.4,
6629
+ output: 4.4,
6630
+ cacheRead: 0.26,
6631
+ cacheWrite: 0,
6632
+ },
6633
+ contextWindow: 204800,
6634
+ maxTokens: 131072,
6635
+ },
6584
6636
  "kimi-k2.5": {
6585
6637
  id: "kimi-k2.5",
6586
6638
  name: "Kimi K2.5",
@@ -6635,9 +6687,9 @@ export const MODELS = {
6635
6687
  "minimax-m2.5": {
6636
6688
  id: "minimax-m2.5",
6637
6689
  name: "MiniMax M2.5",
6638
- api: "openai-completions",
6690
+ api: "anthropic-messages",
6639
6691
  provider: "opencode-go",
6640
- baseUrl: "https://opencode.ai/zen/go/v1",
6692
+ baseUrl: "https://opencode.ai/zen/go",
6641
6693
  reasoning: true,
6642
6694
  input: ["text"],
6643
6695
  cost: {
@@ -6957,6 +7009,23 @@ export const MODELS = {
6957
7009
  contextWindow: 1000000,
6958
7010
  maxTokens: 128000,
6959
7011
  },
7012
+ "anthropic/claude-opus-4.6-fast": {
7013
+ id: "anthropic/claude-opus-4.6-fast",
7014
+ name: "Anthropic: Claude Opus 4.6 (Fast)",
7015
+ api: "openai-completions",
7016
+ provider: "openrouter",
7017
+ baseUrl: "https://openrouter.ai/api/v1",
7018
+ reasoning: true,
7019
+ input: ["text", "image"],
7020
+ cost: {
7021
+ input: 30,
7022
+ output: 150,
7023
+ cacheRead: 3,
7024
+ cacheWrite: 37.5,
7025
+ },
7026
+ contextWindow: 1000000,
7027
+ maxTokens: 128000,
7028
+ },
6960
7029
  "anthropic/claude-sonnet-4": {
6961
7030
  id: "anthropic/claude-sonnet-4",
6962
7031
  name: "Anthropic: Claude Sonnet 4",
@@ -7620,6 +7689,23 @@ export const MODELS = {
7620
7689
  contextWindow: 262144,
7621
7690
  maxTokens: 262144,
7622
7691
  },
7692
+ "google/gemma-4-26b-a4b-it:free": {
7693
+ id: "google/gemma-4-26b-a4b-it:free",
7694
+ name: "Google: Gemma 4 26B A4B (free)",
7695
+ api: "openai-completions",
7696
+ provider: "openrouter",
7697
+ baseUrl: "https://openrouter.ai/api/v1",
7698
+ reasoning: true,
7699
+ input: ["text", "image"],
7700
+ cost: {
7701
+ input: 0,
7702
+ output: 0,
7703
+ cacheRead: 0,
7704
+ cacheWrite: 0,
7705
+ },
7706
+ contextWindow: 262144,
7707
+ maxTokens: 32768,
7708
+ },
7623
7709
  "google/gemma-4-31b-it": {
7624
7710
  id: "google/gemma-4-31b-it",
7625
7711
  name: "Google: Gemma 4 31B",
@@ -7637,6 +7723,23 @@ export const MODELS = {
7637
7723
  contextWindow: 262144,
7638
7724
  maxTokens: 131072,
7639
7725
  },
7726
+ "google/gemma-4-31b-it:free": {
7727
+ id: "google/gemma-4-31b-it:free",
7728
+ name: "Google: Gemma 4 31B (free)",
7729
+ api: "openai-completions",
7730
+ provider: "openrouter",
7731
+ baseUrl: "https://openrouter.ai/api/v1",
7732
+ reasoning: true,
7733
+ input: ["text", "image"],
7734
+ cost: {
7735
+ input: 0,
7736
+ output: 0,
7737
+ cacheRead: 0,
7738
+ cacheWrite: 0,
7739
+ },
7740
+ contextWindow: 262144,
7741
+ maxTokens: 32768,
7742
+ },
7640
7743
  "inception/mercury": {
7641
7744
  id: "inception/mercury",
7642
7745
  name: "Inception: Mercury",
@@ -8345,11 +8448,11 @@ export const MODELS = {
8345
8448
  cost: {
8346
8449
  input: 0.39999999999999997,
8347
8450
  output: 2,
8348
- cacheRead: 0.15,
8451
+ cacheRead: 0,
8349
8452
  cacheWrite: 0,
8350
8453
  },
8351
- contextWindow: 131072,
8352
- maxTokens: 4096,
8454
+ contextWindow: 262144,
8455
+ maxTokens: 262144,
8353
8456
  },
8354
8457
  "moonshotai/kimi-k2-thinking": {
8355
8458
  id: "moonshotai/kimi-k2-thinking",
@@ -8360,12 +8463,12 @@ export const MODELS = {
8360
8463
  reasoning: true,
8361
8464
  input: ["text"],
8362
8465
  cost: {
8363
- input: 0.47,
8364
- output: 2,
8365
- cacheRead: 0.14100000000000001,
8466
+ input: 0.6,
8467
+ output: 2.5,
8468
+ cacheRead: 0,
8366
8469
  cacheWrite: 0,
8367
8470
  },
8368
- contextWindow: 131072,
8471
+ contextWindow: 262144,
8369
8472
  maxTokens: 4096,
8370
8473
  },
8371
8474
  "moonshotai/kimi-k2.5": {
@@ -10289,17 +10392,17 @@ export const MODELS = {
10289
10392
  contextWindow: 1000000,
10290
10393
  maxTokens: 65536,
10291
10394
  },
10292
- "qwen/qwen3.6-plus:free": {
10293
- id: "qwen/qwen3.6-plus:free",
10294
- name: "Qwen: Qwen3.6 Plus (free)",
10395
+ "qwen/qwen3.6-plus": {
10396
+ id: "qwen/qwen3.6-plus",
10397
+ name: "Qwen: Qwen3.6 Plus",
10295
10398
  api: "openai-completions",
10296
10399
  provider: "openrouter",
10297
10400
  baseUrl: "https://openrouter.ai/api/v1",
10298
10401
  reasoning: true,
10299
10402
  input: ["text", "image"],
10300
10403
  cost: {
10301
- input: 0,
10302
- output: 0,
10404
+ input: 0.325,
10405
+ output: 1.95,
10303
10406
  cacheRead: 0,
10304
10407
  cacheWrite: 0,
10305
10408
  },
@@ -10884,6 +10987,23 @@ export const MODELS = {
10884
10987
  contextWindow: 202752,
10885
10988
  maxTokens: 131072,
10886
10989
  },
10990
+ "z-ai/glm-5.1": {
10991
+ id: "z-ai/glm-5.1",
10992
+ name: "Z.ai: GLM 5.1",
10993
+ api: "openai-completions",
10994
+ provider: "openrouter",
10995
+ baseUrl: "https://openrouter.ai/api/v1",
10996
+ reasoning: true,
10997
+ input: ["text"],
10998
+ cost: {
10999
+ input: 1.26,
11000
+ output: 3.9600000000000004,
11001
+ cacheRead: 0,
11002
+ cacheWrite: 0,
11003
+ },
11004
+ contextWindow: 202752,
11005
+ maxTokens: 4096,
11006
+ },
10887
11007
  "z-ai/glm-5v-turbo": {
10888
11008
  id: "z-ai/glm-5v-turbo",
10889
11009
  name: "Z.ai: GLM 5V Turbo",
@@ -10929,13 +11049,13 @@ export const MODELS = {
10929
11049
  reasoning: false,
10930
11050
  input: ["text"],
10931
11051
  cost: {
10932
- input: 0.22,
10933
- output: 0.88,
10934
- cacheRead: 0.11,
11052
+ input: 0.6,
11053
+ output: 1.2,
11054
+ cacheRead: 0.6,
10935
11055
  cacheWrite: 0,
10936
11056
  },
10937
- contextWindow: 32768,
10938
- maxTokens: 16384,
11057
+ contextWindow: 131000,
11058
+ maxTokens: 40000,
10939
11059
  },
10940
11060
  "alibaba/qwen-3-30b": {
10941
11061
  id: "alibaba/qwen-3-30b",
@@ -11170,7 +11290,7 @@ export const MODELS = {
11170
11290
  input: 0.5,
11171
11291
  output: 3,
11172
11292
  cacheRead: 0.09999999999999999,
11173
- cacheWrite: 0.625,
11293
+ cacheWrite: 0,
11174
11294
  },
11175
11295
  contextWindow: 1000000,
11176
11296
  maxTokens: 64000,
@@ -11785,7 +11905,7 @@ export const MODELS = {
11785
11905
  cacheWrite: 0,
11786
11906
  },
11787
11907
  contextWindow: 128000,
11788
- maxTokens: 8192,
11908
+ maxTokens: 100000,
11789
11909
  },
11790
11910
  "meta/llama-3.1-70b": {
11791
11911
  id: "meta/llama-3.1-70b",
@@ -12790,23 +12910,6 @@ export const MODELS = {
12790
12910
  contextWindow: 1050000,
12791
12911
  maxTokens: 128000,
12792
12912
  },
12793
- "openai/gpt-oss-120b": {
12794
- id: "openai/gpt-oss-120b",
12795
- name: "gpt-oss-120b",
12796
- api: "anthropic-messages",
12797
- provider: "vercel-ai-gateway",
12798
- baseUrl: "https://ai-gateway.vercel.sh",
12799
- reasoning: true,
12800
- input: ["text"],
12801
- cost: {
12802
- input: 0.15,
12803
- output: 0.6,
12804
- cacheRead: 0,
12805
- cacheWrite: 0,
12806
- },
12807
- contextWindow: 128000,
12808
- maxTokens: 8192,
12809
- },
12810
12913
  "openai/gpt-oss-20b": {
12811
12914
  id: "openai/gpt-oss-20b",
12812
12915
  name: "gpt-oss-20b",
@@ -12994,23 +13097,6 @@ export const MODELS = {
12994
13097
  contextWindow: 131072,
12995
13098
  maxTokens: 131072,
12996
13099
  },
12997
- "xai/grok-2-vision": {
12998
- id: "xai/grok-2-vision",
12999
- name: "Grok 2 Vision",
13000
- api: "anthropic-messages",
13001
- provider: "vercel-ai-gateway",
13002
- baseUrl: "https://ai-gateway.vercel.sh",
13003
- reasoning: false,
13004
- input: ["text", "image"],
13005
- cost: {
13006
- input: 2,
13007
- output: 10,
13008
- cacheRead: 0,
13009
- cacheWrite: 0,
13010
- },
13011
- contextWindow: 32768,
13012
- maxTokens: 32768,
13013
- },
13014
13100
  "xai/grok-3": {
13015
13101
  id: "xai/grok-3",
13016
13102
  name: "Grok 3 Beta",
@@ -13428,13 +13514,13 @@ export const MODELS = {
13428
13514
  reasoning: true,
13429
13515
  input: ["text"],
13430
13516
  cost: {
13431
- input: 0.6,
13432
- output: 2.2,
13433
- cacheRead: 0.11,
13517
+ input: 2.25,
13518
+ output: 2.75,
13519
+ cacheRead: 2.25,
13434
13520
  cacheWrite: 0,
13435
13521
  },
13436
- contextWindow: 200000,
13437
- maxTokens: 120000,
13522
+ contextWindow: 131000,
13523
+ maxTokens: 40000,
13438
13524
  },
13439
13525
  "zai/glm-4.7-flash": {
13440
13526
  id: "zai/glm-4.7-flash",
@@ -13504,6 +13590,23 @@ export const MODELS = {
13504
13590
  contextWindow: 202800,
13505
13591
  maxTokens: 131100,
13506
13592
  },
13593
+ "zai/glm-5.1": {
13594
+ id: "zai/glm-5.1",
13595
+ name: "GLM 5.1",
13596
+ api: "anthropic-messages",
13597
+ provider: "vercel-ai-gateway",
13598
+ baseUrl: "https://ai-gateway.vercel.sh",
13599
+ reasoning: true,
13600
+ input: ["text"],
13601
+ cost: {
13602
+ input: 1.4,
13603
+ output: 4.4,
13604
+ cacheRead: 0.26,
13605
+ cacheWrite: 0,
13606
+ },
13607
+ contextWindow: 202800,
13608
+ maxTokens: 64000,
13609
+ },
13507
13610
  "zai/glm-5v-turbo": {
13508
13611
  id: "zai/glm-5v-turbo",
13509
13612
  name: "GLM 5V Turbo",