@caupulican/pi-ai 0.86.14 → 0.90.0

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.
@@ -1435,7 +1435,7 @@ export const MODELS = {
1435
1435
  cacheRead: 0.022,
1436
1436
  cacheWrite: 0.275,
1437
1437
  },
1438
- contextWindow: 272000,
1438
+ contextWindow: 1050000,
1439
1439
  maxTokens: 128000,
1440
1440
  },
1441
1441
  "openai.gpt-5.6-sol": {
@@ -1452,9 +1452,9 @@ export const MODELS = {
1452
1452
  input: 5.5,
1453
1453
  output: 33,
1454
1454
  cacheRead: 0.55,
1455
- cacheWrite: 6.88,
1455
+ cacheWrite: 6.875,
1456
1456
  },
1457
- contextWindow: 272000,
1457
+ contextWindow: 1050000,
1458
1458
  maxTokens: 128000,
1459
1459
  },
1460
1460
  "openai.gpt-5.6-terra": {
@@ -1473,7 +1473,7 @@ export const MODELS = {
1473
1473
  cacheRead: 0.22,
1474
1474
  cacheWrite: 2.75,
1475
1475
  },
1476
- contextWindow: 272000,
1476
+ contextWindow: 1050000,
1477
1477
  maxTokens: 128000,
1478
1478
  },
1479
1479
  "openai.gpt-oss-120b": {
@@ -3996,7 +3996,7 @@ export const MODELS = {
3996
3996
  cacheWrite: 0,
3997
3997
  },
3998
3998
  contextWindow: 262144,
3999
- maxTokens: 262144,
3999
+ maxTokens: 256000,
4000
4000
  },
4001
4001
  },
4002
4002
  "deepseek": {
@@ -5018,23 +5018,6 @@ export const MODELS = {
5018
5018
  contextWindow: 1048576,
5019
5019
  maxTokens: 8192,
5020
5020
  },
5021
- "gemini-2.0-flash-lite": {
5022
- id: "gemini-2.0-flash-lite",
5023
- name: "Gemini 2.0 Flash-Lite",
5024
- api: "google-generative-ai",
5025
- provider: "google",
5026
- baseUrl: "https://generativelanguage.googleapis.com/v1beta",
5027
- reasoning: false,
5028
- input: ["text", "image"],
5029
- cost: {
5030
- input: 0.075,
5031
- output: 0.3,
5032
- cacheRead: 0,
5033
- cacheWrite: 0,
5034
- },
5035
- contextWindow: 1048576,
5036
- maxTokens: 8192,
5037
- },
5038
5021
  "gemini-2.5-computer-use-preview-10-2025": {
5039
5022
  id: "gemini-2.5-computer-use-preview-10-2025",
5040
5023
  name: "Gemini 2.5 Computer Use Preview 10-2025",
@@ -5121,24 +5104,6 @@ export const MODELS = {
5121
5104
  contextWindow: 1048576,
5122
5105
  maxTokens: 65536,
5123
5106
  },
5124
- "gemini-3-pro-preview": {
5125
- id: "gemini-3-pro-preview",
5126
- name: "Gemini 3 Pro Preview",
5127
- api: "google-generative-ai",
5128
- provider: "google",
5129
- baseUrl: "https://generativelanguage.googleapis.com/v1beta",
5130
- reasoning: true,
5131
- thinkingLevelMap: { "off": null, "minimal": null, "low": "LOW", "medium": null, "high": "HIGH" },
5132
- input: ["text", "image"],
5133
- cost: {
5134
- input: 2,
5135
- output: 12,
5136
- cacheRead: 0.2,
5137
- cacheWrite: 0,
5138
- },
5139
- contextWindow: 1048576,
5140
- maxTokens: 65536,
5141
- },
5142
5107
  "gemini-3.1-flash-lite": {
5143
5108
  id: "gemini-3.1-flash-lite",
5144
5109
  name: "Gemini 3.1 Flash Lite",
@@ -9748,23 +9713,6 @@ export const MODELS = {
9748
9713
  contextWindow: 1000000,
9749
9714
  maxTokens: 128000,
9750
9715
  },
9751
- "north-mini-code-free": {
9752
- id: "north-mini-code-free",
9753
- name: "North Mini Code Free",
9754
- api: "openai-completions",
9755
- provider: "opencode",
9756
- baseUrl: "https://opencode.ai/zen/v1",
9757
- reasoning: true,
9758
- input: ["text"],
9759
- cost: {
9760
- input: 0,
9761
- output: 0,
9762
- cacheRead: 0,
9763
- cacheWrite: 0,
9764
- },
9765
- contextWindow: 256000,
9766
- maxTokens: 64000,
9767
- },
9768
9716
  "qwen3.5-plus": {
9769
9717
  id: "qwen3.5-plus",
9770
9718
  name: "Qwen3.5 Plus",
@@ -11127,9 +11075,9 @@ export const MODELS = {
11127
11075
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
11128
11076
  input: ["text"],
11129
11077
  cost: {
11130
- input: 0.09,
11078
+ input: 0.08,
11131
11079
  output: 0.18,
11132
- cacheRead: 0.018,
11080
+ cacheRead: 0.016,
11133
11081
  cacheWrite: 0,
11134
11082
  },
11135
11083
  contextWindow: 1048576,
@@ -11146,13 +11094,13 @@ export const MODELS = {
11146
11094
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
11147
11095
  input: ["text"],
11148
11096
  cost: {
11149
- input: 0.435,
11150
- output: 0.87,
11151
- cacheRead: 0.003625,
11097
+ input: 0.63168,
11098
+ output: 1.26336,
11099
+ cacheRead: 0.053298,
11152
11100
  cacheWrite: 0,
11153
11101
  },
11154
11102
  contextWindow: 1048576,
11155
- maxTokens: 384000,
11103
+ maxTokens: 393216,
11156
11104
  },
11157
11105
  "google/gemini-2.5-flash": {
11158
11106
  id: "google/gemini-2.5-flash",
@@ -11896,12 +11844,12 @@ export const MODELS = {
11896
11844
  input: ["text", "image"],
11897
11845
  cost: {
11898
11846
  input: 0.19999999999999998,
11899
- output: 0.7999999999999999,
11847
+ output: 0.696,
11900
11848
  cacheRead: 0,
11901
11849
  cacheWrite: 0,
11902
11850
  },
11903
11851
  contextWindow: 1048576,
11904
- maxTokens: 16384,
11852
+ maxTokens: 4096,
11905
11853
  },
11906
11854
  "meta-llama/llama-4-scout": {
11907
11855
  id: "meta-llama/llama-4-scout",
@@ -11920,6 +11868,23 @@ export const MODELS = {
11920
11868
  contextWindow: 1310720,
11921
11869
  maxTokens: 16384,
11922
11870
  },
11871
+ "meta/muse-glimmer-30b": {
11872
+ id: "meta/muse-glimmer-30b",
11873
+ name: "Meta: Muse Glimmer 30B",
11874
+ api: "openai-completions",
11875
+ provider: "openrouter",
11876
+ baseUrl: "https://openrouter.ai/api/v1",
11877
+ reasoning: true,
11878
+ input: ["text", "image"],
11879
+ cost: {
11880
+ input: 0.35,
11881
+ output: 1.5,
11882
+ cacheRead: 0.04,
11883
+ cacheWrite: 0,
11884
+ },
11885
+ contextWindow: 131072,
11886
+ maxTokens: 4096,
11887
+ },
11923
11888
  "meta/muse-spark-1.1": {
11924
11889
  id: "meta/muse-spark-1.1",
11925
11890
  name: "Meta: Muse Spark 1.1",
@@ -12423,9 +12388,9 @@ export const MODELS = {
12423
12388
  reasoning: true,
12424
12389
  input: ["text", "image"],
12425
12390
  cost: {
12426
- input: 0.5795,
12427
- output: 2.44,
12428
- cacheRead: 0.0976,
12391
+ input: 0.95,
12392
+ output: 4,
12393
+ cacheRead: 0.16,
12429
12394
  cacheWrite: 0,
12430
12395
  },
12431
12396
  contextWindow: 262144,
@@ -12576,13 +12541,13 @@ export const MODELS = {
12576
12541
  reasoning: true,
12577
12542
  input: ["text"],
12578
12543
  cost: {
12579
- input: 0.3,
12580
- output: 0.8999999999999999,
12544
+ input: 0.08499999999999999,
12545
+ output: 0.39999999999999997,
12581
12546
  cacheRead: 0,
12582
12547
  cacheWrite: 0,
12583
12548
  },
12584
12549
  contextWindow: 1000000,
12585
- maxTokens: 4096,
12550
+ maxTokens: 16384,
12586
12551
  },
12587
12552
  "nvidia/nemotron-3-super-120b-a12b:free": {
12588
12553
  id: "nvidia/nemotron-3-super-120b-a12b:free",
@@ -13315,7 +13280,7 @@ export const MODELS = {
13315
13280
  cacheWrite: 0,
13316
13281
  },
13317
13282
  contextWindow: 128000,
13318
- maxTokens: 16384,
13283
+ maxTokens: 32000,
13319
13284
  },
13320
13285
  "openai/gpt-5.2-codex": {
13321
13286
  id: "openai/gpt-5.2-codex",
@@ -13389,24 +13354,6 @@ export const MODELS = {
13389
13354
  contextWindow: 400000,
13390
13355
  maxTokens: 128000,
13391
13356
  },
13392
- "openai/gpt-5.3-chat": {
13393
- id: "openai/gpt-5.3-chat",
13394
- name: "OpenAI: GPT-5.3 Chat",
13395
- api: "openai-completions",
13396
- provider: "openrouter",
13397
- baseUrl: "https://openrouter.ai/api/v1",
13398
- reasoning: false,
13399
- thinkingLevelMap: { "xhigh": "xhigh" },
13400
- input: ["text", "image"],
13401
- cost: {
13402
- input: 1.75,
13403
- output: 14,
13404
- cacheRead: 0.175,
13405
- cacheWrite: 0,
13406
- },
13407
- contextWindow: 128000,
13408
- maxTokens: 16384,
13409
- },
13410
13357
  "openai/gpt-5.3-codex": {
13411
13358
  id: "openai/gpt-5.3-codex",
13412
13359
  name: "OpenAI: GPT-5.3-Codex",
@@ -14461,13 +14408,13 @@ export const MODELS = {
14461
14408
  reasoning: true,
14462
14409
  input: ["text"],
14463
14410
  cost: {
14464
- input: 0.22749999999999998,
14465
- output: 0.9099999999999999,
14411
+ input: 0.12,
14412
+ output: 0.24,
14466
14413
  cacheRead: 0,
14467
14414
  cacheWrite: 0,
14468
14415
  },
14469
14416
  contextWindow: 131072,
14470
- maxTokens: 8192,
14417
+ maxTokens: 16384,
14471
14418
  },
14472
14419
  "qwen/qwen3-235b-a22b": {
14473
14420
  id: "qwen/qwen3-235b-a22b",
@@ -14632,12 +14579,12 @@ export const MODELS = {
14632
14579
  input: ["text"],
14633
14580
  cost: {
14634
14581
  input: 0.07,
14635
- output: 0.27,
14582
+ output: 0.28,
14636
14583
  cacheRead: 0,
14637
14584
  cacheWrite: 0,
14638
14585
  },
14639
14586
  contextWindow: 262144,
14640
- maxTokens: 32768,
14587
+ maxTokens: 262144,
14641
14588
  },
14642
14589
  "qwen/qwen3-coder-flash": {
14643
14590
  id: "qwen/qwen3-coder-flash",
@@ -15217,6 +15164,23 @@ export const MODELS = {
15217
15164
  contextWindow: 1000000,
15218
15165
  maxTokens: 128000,
15219
15166
  },
15167
+ "sakana/sakana-namazu": {
15168
+ id: "sakana/sakana-namazu",
15169
+ name: "Sakana: Sakana Namazu",
15170
+ api: "openai-completions",
15171
+ provider: "openrouter",
15172
+ baseUrl: "https://openrouter.ai/api/v1",
15173
+ reasoning: true,
15174
+ input: ["text", "image"],
15175
+ cost: {
15176
+ input: 0.95,
15177
+ output: 4,
15178
+ cacheRead: 0.15,
15179
+ cacheWrite: 0,
15180
+ },
15181
+ contextWindow: 262144,
15182
+ maxTokens: 65536,
15183
+ },
15220
15184
  "sao10k/l3.1-euryale-70b": {
15221
15185
  id: "sao10k/l3.1-euryale-70b",
15222
15186
  name: "Sao10K: Llama 3.1 Euryale 70B v2.2",
@@ -15387,6 +15351,23 @@ export const MODELS = {
15387
15351
  contextWindow: 131072,
15388
15352
  maxTokens: 131072,
15389
15353
  },
15354
+ "upstage/solar-pro4": {
15355
+ id: "upstage/solar-pro4",
15356
+ name: "Upstage: Solar Pro 4",
15357
+ api: "openai-completions",
15358
+ provider: "openrouter",
15359
+ baseUrl: "https://openrouter.ai/api/v1",
15360
+ reasoning: true,
15361
+ input: ["text"],
15362
+ cost: {
15363
+ input: 0.03,
15364
+ output: 0.12,
15365
+ cacheRead: 0.006,
15366
+ cacheWrite: 0,
15367
+ },
15368
+ contextWindow: 524288,
15369
+ maxTokens: 131072,
15370
+ },
15390
15371
  "x-ai/grok-4.20": {
15391
15372
  id: "x-ai/grok-4.20",
15392
15373
  name: "SpaceXAI: Grok 4.20",
@@ -15549,9 +15530,9 @@ export const MODELS = {
15549
15530
  reasoning: true,
15550
15531
  input: ["text"],
15551
15532
  cost: {
15552
- input: 0.5,
15553
- output: 2,
15554
- cacheRead: 0.09999999999999999,
15533
+ input: 0.55,
15534
+ output: 2.2,
15535
+ cacheRead: 0.11,
15555
15536
  cacheWrite: 0,
15556
15537
  },
15557
15538
  contextWindow: 204800,
@@ -15651,9 +15632,9 @@ export const MODELS = {
15651
15632
  reasoning: true,
15652
15633
  input: ["text"],
15653
15634
  cost: {
15654
- input: 0.952,
15655
- output: 2.992,
15656
- cacheRead: 0.17679999999999998,
15635
+ input: 1.4,
15636
+ output: 4.4,
15637
+ cacheRead: 0.26,
15657
15638
  cacheWrite: 0,
15658
15639
  },
15659
15640
  contextWindow: 204800,
@@ -15668,13 +15649,13 @@ export const MODELS = {
15668
15649
  reasoning: true,
15669
15650
  input: ["text"],
15670
15651
  cost: {
15671
- input: 0.07,
15672
- output: 0.22,
15673
- cacheRead: 0.013000000000000001,
15652
+ input: 0.76,
15653
+ output: 2.42,
15654
+ cacheRead: 0.14,
15674
15655
  cacheWrite: 0,
15675
15656
  },
15676
15657
  contextWindow: 1048576,
15677
- maxTokens: 128000,
15658
+ maxTokens: 262144,
15678
15659
  },
15679
15660
  "z-ai/glm-5.2:batch": {
15680
15661
  id: "z-ai/glm-5.2:batch",
@@ -18044,7 +18025,7 @@ export const MODELS = {
18044
18025
  },
18045
18026
  "google/gemma-4-26b-a4b-it": {
18046
18027
  id: "google/gemma-4-26b-a4b-it",
18047
- name: "Gemma 4 26B A4B IT",
18028
+ name: "Google Gemma 4 26B A4B",
18048
18029
  api: "anthropic-messages",
18049
18030
  provider: "vercel-ai-gateway",
18050
18031
  baseUrl: "https://ai-gateway.vercel.sh",
@@ -18314,6 +18295,23 @@ export const MODELS = {
18314
18295
  contextWindow: 128000,
18315
18296
  maxTokens: 8192,
18316
18297
  },
18298
+ "meta/muse-glimmer-30b": {
18299
+ id: "meta/muse-glimmer-30b",
18300
+ name: "Muse Glimmer 30B",
18301
+ api: "anthropic-messages",
18302
+ provider: "vercel-ai-gateway",
18303
+ baseUrl: "https://ai-gateway.vercel.sh",
18304
+ reasoning: true,
18305
+ input: ["text", "image"],
18306
+ cost: {
18307
+ input: 0.35,
18308
+ output: 1.5,
18309
+ cacheRead: 0.04,
18310
+ cacheWrite: 0,
18311
+ },
18312
+ contextWindow: 131072,
18313
+ maxTokens: 131072,
18314
+ },
18317
18315
  "meta/muse-spark-1.1": {
18318
18316
  id: "meta/muse-spark-1.1",
18319
18317
  name: "Muse Spark 1.1",
@@ -19286,24 +19284,6 @@ export const MODELS = {
19286
19284
  contextWindow: 400000,
19287
19285
  maxTokens: 128000,
19288
19286
  },
19289
- "openai/gpt-5.3-chat": {
19290
- id: "openai/gpt-5.3-chat",
19291
- name: "GPT-5.3 Chat",
19292
- api: "anthropic-messages",
19293
- provider: "vercel-ai-gateway",
19294
- baseUrl: "https://ai-gateway.vercel.sh",
19295
- reasoning: false,
19296
- thinkingLevelMap: { "xhigh": "xhigh" },
19297
- input: ["text", "image"],
19298
- cost: {
19299
- input: 1.75,
19300
- output: 14,
19301
- cacheRead: 0.175,
19302
- cacheWrite: 0,
19303
- },
19304
- contextWindow: 128000,
19305
- maxTokens: 16384,
19306
- },
19307
19287
  "openai/gpt-5.3-codex": {
19308
19288
  id: "openai/gpt-5.3-codex",
19309
19289
  name: "GPT 5.3 Codex",
@@ -19688,6 +19668,23 @@ export const MODELS = {
19688
19668
  contextWindow: 1000000,
19689
19669
  maxTokens: 1000000,
19690
19670
  },
19671
+ "sakana/namazu": {
19672
+ id: "sakana/namazu",
19673
+ name: "Sakana Namazu",
19674
+ api: "anthropic-messages",
19675
+ provider: "vercel-ai-gateway",
19676
+ baseUrl: "https://ai-gateway.vercel.sh",
19677
+ reasoning: true,
19678
+ input: ["text", "image"],
19679
+ cost: {
19680
+ input: 0.95,
19681
+ output: 4,
19682
+ cacheRead: 0.15,
19683
+ cacheWrite: 0,
19684
+ },
19685
+ contextWindow: 256000,
19686
+ maxTokens: 256000,
19687
+ },
19691
19688
  "stepfun/step-3.5-flash": {
19692
19689
  id: "stepfun/step-3.5-flash",
19693
19690
  name: "StepFun 3.5 Flash",