@mariozechner/pi-ai 0.7.10 → 0.7.12

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.
@@ -1094,6 +1094,23 @@ export const MODELS = {
1094
1094
  contextWindow: 128000,
1095
1095
  maxTokens: 16384,
1096
1096
  },
1097
+ "gpt-5.1-codex": {
1098
+ id: "gpt-5.1-codex",
1099
+ name: "GPT-5.1 Codex",
1100
+ api: "openai-responses",
1101
+ provider: "openai",
1102
+ baseUrl: "https://api.openai.com/v1",
1103
+ reasoning: true,
1104
+ input: ["text", "image"],
1105
+ cost: {
1106
+ input: 1.25,
1107
+ output: 5,
1108
+ cacheRead: 0.125,
1109
+ cacheWrite: 1.25,
1110
+ },
1111
+ contextWindow: 400000,
1112
+ maxTokens: 128000,
1113
+ },
1097
1114
  },
1098
1115
  groq: {
1099
1116
  "llama-3.1-8b-instant": {
@@ -1852,6 +1869,40 @@ export const MODELS = {
1852
1869
  },
1853
1870
  },
1854
1871
  openrouter: {
1872
+ "openrouter/sherlock-dash-alpha": {
1873
+ id: "openrouter/sherlock-dash-alpha",
1874
+ name: "Sherlock Dash Alpha",
1875
+ api: "openai-completions",
1876
+ provider: "openrouter",
1877
+ baseUrl: "https://openrouter.ai/api/v1",
1878
+ reasoning: false,
1879
+ input: ["text", "image"],
1880
+ cost: {
1881
+ input: 0,
1882
+ output: 0,
1883
+ cacheRead: 0,
1884
+ cacheWrite: 0,
1885
+ },
1886
+ contextWindow: 1840000,
1887
+ maxTokens: 64000,
1888
+ },
1889
+ "openrouter/sherlock-think-alpha": {
1890
+ id: "openrouter/sherlock-think-alpha",
1891
+ name: "Sherlock Think Alpha",
1892
+ api: "openai-completions",
1893
+ provider: "openrouter",
1894
+ baseUrl: "https://openrouter.ai/api/v1",
1895
+ reasoning: true,
1896
+ input: ["text", "image"],
1897
+ cost: {
1898
+ input: 0,
1899
+ output: 0,
1900
+ cacheRead: 0,
1901
+ cacheWrite: 0,
1902
+ },
1903
+ contextWindow: 1840000,
1904
+ maxTokens: 64000,
1905
+ },
1855
1906
  "openai/gpt-5.1": {
1856
1907
  id: "openai/gpt-5.1",
1857
1908
  name: "OpenAI: GPT-5.1",
@@ -3017,13 +3068,13 @@ export const MODELS = {
3017
3068
  reasoning: true,
3018
3069
  input: ["text"],
3019
3070
  cost: {
3020
- input: 0,
3021
- output: 0,
3071
+ input: 0.04,
3072
+ output: 0.39999999999999997,
3022
3073
  cacheRead: 0,
3023
3074
  cacheWrite: 0,
3024
3075
  },
3025
3076
  contextWindow: 131072,
3026
- maxTokens: 4096,
3077
+ maxTokens: 131072,
3027
3078
  },
3028
3079
  "openai/gpt-oss-120b:exacto": {
3029
3080
  id: "openai/gpt-oss-120b:exacto",
@@ -3722,23 +3773,6 @@ export const MODELS = {
3722
3773
  contextWindow: 200000,
3723
3774
  maxTokens: 100000,
3724
3775
  },
3725
- "meta-llama/llama-3.3-8b-instruct:free": {
3726
- id: "meta-llama/llama-3.3-8b-instruct:free",
3727
- name: "Meta: Llama 3.3 8B Instruct (free)",
3728
- api: "openai-completions",
3729
- provider: "openrouter",
3730
- baseUrl: "https://openrouter.ai/api/v1",
3731
- reasoning: false,
3732
- input: ["text"],
3733
- cost: {
3734
- input: 0,
3735
- output: 0,
3736
- cacheRead: 0,
3737
- cacheWrite: 0,
3738
- },
3739
- contextWindow: 128000,
3740
- maxTokens: 4028,
3741
- },
3742
3776
  "nousresearch/deephermes-3-mistral-24b-preview": {
3743
3777
  id: "nousresearch/deephermes-3-mistral-24b-preview",
3744
3778
  name: "Nous: DeepHermes 3 Mistral 24B Preview",
@@ -4079,23 +4113,6 @@ export const MODELS = {
4079
4113
  contextWindow: 131072,
4080
4114
  maxTokens: 4096,
4081
4115
  },
4082
- "meta-llama/llama-4-maverick:free": {
4083
- id: "meta-llama/llama-4-maverick:free",
4084
- name: "Meta: Llama 4 Maverick (free)",
4085
- api: "openai-completions",
4086
- provider: "openrouter",
4087
- baseUrl: "https://openrouter.ai/api/v1",
4088
- reasoning: false,
4089
- input: ["text", "image"],
4090
- cost: {
4091
- input: 0,
4092
- output: 0,
4093
- cacheRead: 0,
4094
- cacheWrite: 0,
4095
- },
4096
- contextWindow: 128000,
4097
- maxTokens: 4028,
4098
- },
4099
4116
  "meta-llama/llama-4-maverick": {
4100
4117
  id: "meta-llama/llama-4-maverick",
4101
4118
  name: "Meta: Llama 4 Maverick",
@@ -4113,23 +4130,6 @@ export const MODELS = {
4113
4130
  contextWindow: 1048576,
4114
4131
  maxTokens: 16384,
4115
4132
  },
4116
- "meta-llama/llama-4-scout:free": {
4117
- id: "meta-llama/llama-4-scout:free",
4118
- name: "Meta: Llama 4 Scout (free)",
4119
- api: "openai-completions",
4120
- provider: "openrouter",
4121
- baseUrl: "https://openrouter.ai/api/v1",
4122
- reasoning: false,
4123
- input: ["text", "image"],
4124
- cost: {
4125
- input: 0,
4126
- output: 0,
4127
- cacheRead: 0,
4128
- cacheWrite: 0,
4129
- },
4130
- contextWindow: 128000,
4131
- maxTokens: 4028,
4132
- },
4133
4133
  "meta-llama/llama-4-scout": {
4134
4134
  id: "meta-llama/llama-4-scout",
4135
4135
  name: "Meta: Llama 4 Scout",
@@ -4836,8 +4836,8 @@ export const MODELS = {
4836
4836
  reasoning: false,
4837
4837
  input: ["text"],
4838
4838
  cost: {
4839
- input: 0.6,
4840
- output: 0.6,
4839
+ input: 1.2,
4840
+ output: 1.2,
4841
4841
  cacheRead: 0,
4842
4842
  cacheWrite: 0,
4843
4843
  },
@@ -4912,34 +4912,34 @@ export const MODELS = {
4912
4912
  contextWindow: 32768,
4913
4913
  maxTokens: 4096,
4914
4914
  },
4915
- "cohere/command-r-08-2024": {
4916
- id: "cohere/command-r-08-2024",
4917
- name: "Cohere: Command R (08-2024)",
4915
+ "cohere/command-r-plus-08-2024": {
4916
+ id: "cohere/command-r-plus-08-2024",
4917
+ name: "Cohere: Command R+ (08-2024)",
4918
4918
  api: "openai-completions",
4919
4919
  provider: "openrouter",
4920
4920
  baseUrl: "https://openrouter.ai/api/v1",
4921
4921
  reasoning: false,
4922
4922
  input: ["text"],
4923
4923
  cost: {
4924
- input: 0.15,
4925
- output: 0.6,
4924
+ input: 2.5,
4925
+ output: 10,
4926
4926
  cacheRead: 0,
4927
4927
  cacheWrite: 0,
4928
4928
  },
4929
4929
  contextWindow: 128000,
4930
4930
  maxTokens: 4000,
4931
4931
  },
4932
- "cohere/command-r-plus-08-2024": {
4933
- id: "cohere/command-r-plus-08-2024",
4934
- name: "Cohere: Command R+ (08-2024)",
4932
+ "cohere/command-r-08-2024": {
4933
+ id: "cohere/command-r-08-2024",
4934
+ name: "Cohere: Command R (08-2024)",
4935
4935
  api: "openai-completions",
4936
4936
  provider: "openrouter",
4937
4937
  baseUrl: "https://openrouter.ai/api/v1",
4938
4938
  reasoning: false,
4939
4939
  input: ["text"],
4940
4940
  cost: {
4941
- input: 2.5,
4942
- output: 10,
4941
+ input: 0.15,
4942
+ output: 0.6,
4943
4943
  cacheRead: 0,
4944
4944
  cacheWrite: 0,
4945
4945
  },
@@ -5014,22 +5014,22 @@ export const MODELS = {
5014
5014
  contextWindow: 128000,
5015
5015
  maxTokens: 16384,
5016
5016
  },
5017
- "meta-llama/llama-3.1-8b-instruct": {
5018
- id: "meta-llama/llama-3.1-8b-instruct",
5019
- name: "Meta: Llama 3.1 8B Instruct",
5017
+ "meta-llama/llama-3.1-70b-instruct": {
5018
+ id: "meta-llama/llama-3.1-70b-instruct",
5019
+ name: "Meta: Llama 3.1 70B Instruct",
5020
5020
  api: "openai-completions",
5021
5021
  provider: "openrouter",
5022
5022
  baseUrl: "https://openrouter.ai/api/v1",
5023
5023
  reasoning: false,
5024
5024
  input: ["text"],
5025
5025
  cost: {
5026
- input: 0.02,
5027
- output: 0.03,
5026
+ input: 0.39999999999999997,
5027
+ output: 0.39999999999999997,
5028
5028
  cacheRead: 0,
5029
5029
  cacheWrite: 0,
5030
5030
  },
5031
5031
  contextWindow: 131072,
5032
- maxTokens: 16384,
5032
+ maxTokens: 4096,
5033
5033
  },
5034
5034
  "meta-llama/llama-3.1-405b-instruct": {
5035
5035
  id: "meta-llama/llama-3.1-405b-instruct",
@@ -5048,22 +5048,22 @@ export const MODELS = {
5048
5048
  contextWindow: 130815,
5049
5049
  maxTokens: 4096,
5050
5050
  },
5051
- "meta-llama/llama-3.1-70b-instruct": {
5052
- id: "meta-llama/llama-3.1-70b-instruct",
5053
- name: "Meta: Llama 3.1 70B Instruct",
5051
+ "meta-llama/llama-3.1-8b-instruct": {
5052
+ id: "meta-llama/llama-3.1-8b-instruct",
5053
+ name: "Meta: Llama 3.1 8B Instruct",
5054
5054
  api: "openai-completions",
5055
5055
  provider: "openrouter",
5056
5056
  baseUrl: "https://openrouter.ai/api/v1",
5057
5057
  reasoning: false,
5058
5058
  input: ["text"],
5059
5059
  cost: {
5060
- input: 0.39999999999999997,
5061
- output: 0.39999999999999997,
5060
+ input: 0.02,
5061
+ output: 0.03,
5062
5062
  cacheRead: 0,
5063
5063
  cacheWrite: 0,
5064
5064
  },
5065
5065
  contextWindow: 131072,
5066
- maxTokens: 4096,
5066
+ maxTokens: 16384,
5067
5067
  },
5068
5068
  "mistralai/mistral-nemo": {
5069
5069
  id: "mistralai/mistral-nemo",
@@ -5082,9 +5082,9 @@ export const MODELS = {
5082
5082
  contextWindow: 131072,
5083
5083
  maxTokens: 16384,
5084
5084
  },
5085
- "openai/gpt-4o-mini": {
5086
- id: "openai/gpt-4o-mini",
5087
- name: "OpenAI: GPT-4o-mini",
5085
+ "openai/gpt-4o-mini-2024-07-18": {
5086
+ id: "openai/gpt-4o-mini-2024-07-18",
5087
+ name: "OpenAI: GPT-4o-mini (2024-07-18)",
5088
5088
  api: "openai-completions",
5089
5089
  provider: "openrouter",
5090
5090
  baseUrl: "https://openrouter.ai/api/v1",
@@ -5099,9 +5099,9 @@ export const MODELS = {
5099
5099
  contextWindow: 128000,
5100
5100
  maxTokens: 16384,
5101
5101
  },
5102
- "openai/gpt-4o-mini-2024-07-18": {
5103
- id: "openai/gpt-4o-mini-2024-07-18",
5104
- name: "OpenAI: GPT-4o-mini (2024-07-18)",
5102
+ "openai/gpt-4o-mini": {
5103
+ id: "openai/gpt-4o-mini",
5104
+ name: "OpenAI: GPT-4o-mini",
5105
5105
  api: "openai-completions",
5106
5106
  provider: "openrouter",
5107
5107
  baseUrl: "https://openrouter.ai/api/v1",
@@ -5116,23 +5116,6 @@ export const MODELS = {
5116
5116
  contextWindow: 128000,
5117
5117
  maxTokens: 16384,
5118
5118
  },
5119
- "anthropic/claude-3.5-sonnet-20240620": {
5120
- id: "anthropic/claude-3.5-sonnet-20240620",
5121
- name: "Anthropic: Claude 3.5 Sonnet (2024-06-20)",
5122
- api: "openai-completions",
5123
- provider: "openrouter",
5124
- baseUrl: "https://openrouter.ai/api/v1",
5125
- reasoning: false,
5126
- input: ["text", "image"],
5127
- cost: {
5128
- input: 3,
5129
- output: 15,
5130
- cacheRead: 0.3,
5131
- cacheWrite: 3.75,
5132
- },
5133
- contextWindow: 200000,
5134
- maxTokens: 8192,
5135
- },
5136
5119
  "sao10k/l3-euryale-70b": {
5137
5120
  id: "sao10k/l3-euryale-70b",
5138
5121
  name: "Sao10k: Llama 3 Euryale 70B v2.1",
@@ -5269,34 +5252,34 @@ export const MODELS = {
5269
5252
  contextWindow: 128000,
5270
5253
  maxTokens: 4096,
5271
5254
  },
5272
- "meta-llama/llama-3-8b-instruct": {
5273
- id: "meta-llama/llama-3-8b-instruct",
5274
- name: "Meta: Llama 3 8B Instruct",
5255
+ "meta-llama/llama-3-70b-instruct": {
5256
+ id: "meta-llama/llama-3-70b-instruct",
5257
+ name: "Meta: Llama 3 70B Instruct",
5275
5258
  api: "openai-completions",
5276
5259
  provider: "openrouter",
5277
5260
  baseUrl: "https://openrouter.ai/api/v1",
5278
5261
  reasoning: false,
5279
5262
  input: ["text"],
5280
5263
  cost: {
5281
- input: 0.03,
5282
- output: 0.06,
5264
+ input: 0.3,
5265
+ output: 0.39999999999999997,
5283
5266
  cacheRead: 0,
5284
5267
  cacheWrite: 0,
5285
5268
  },
5286
5269
  contextWindow: 8192,
5287
5270
  maxTokens: 16384,
5288
5271
  },
5289
- "meta-llama/llama-3-70b-instruct": {
5290
- id: "meta-llama/llama-3-70b-instruct",
5291
- name: "Meta: Llama 3 70B Instruct",
5272
+ "meta-llama/llama-3-8b-instruct": {
5273
+ id: "meta-llama/llama-3-8b-instruct",
5274
+ name: "Meta: Llama 3 8B Instruct",
5292
5275
  api: "openai-completions",
5293
5276
  provider: "openrouter",
5294
5277
  baseUrl: "https://openrouter.ai/api/v1",
5295
5278
  reasoning: false,
5296
5279
  input: ["text"],
5297
5280
  cost: {
5298
- input: 0.3,
5299
- output: 0.39999999999999997,
5281
+ input: 0.03,
5282
+ output: 0.06,
5300
5283
  cacheRead: 0,
5301
5284
  cacheWrite: 0,
5302
5285
  },
@@ -5388,38 +5371,38 @@ export const MODELS = {
5388
5371
  contextWindow: 128000,
5389
5372
  maxTokens: 4096,
5390
5373
  },
5391
- "openai/gpt-3.5-turbo-0613": {
5392
- id: "openai/gpt-3.5-turbo-0613",
5393
- name: "OpenAI: GPT-3.5 Turbo (older v0613)",
5374
+ "openai/gpt-4-turbo-preview": {
5375
+ id: "openai/gpt-4-turbo-preview",
5376
+ name: "OpenAI: GPT-4 Turbo Preview",
5394
5377
  api: "openai-completions",
5395
5378
  provider: "openrouter",
5396
5379
  baseUrl: "https://openrouter.ai/api/v1",
5397
5380
  reasoning: false,
5398
5381
  input: ["text"],
5399
5382
  cost: {
5400
- input: 1,
5401
- output: 2,
5383
+ input: 10,
5384
+ output: 30,
5402
5385
  cacheRead: 0,
5403
5386
  cacheWrite: 0,
5404
5387
  },
5405
- contextWindow: 4095,
5388
+ contextWindow: 128000,
5406
5389
  maxTokens: 4096,
5407
5390
  },
5408
- "openai/gpt-4-turbo-preview": {
5409
- id: "openai/gpt-4-turbo-preview",
5410
- name: "OpenAI: GPT-4 Turbo Preview",
5391
+ "openai/gpt-3.5-turbo-0613": {
5392
+ id: "openai/gpt-3.5-turbo-0613",
5393
+ name: "OpenAI: GPT-3.5 Turbo (older v0613)",
5411
5394
  api: "openai-completions",
5412
5395
  provider: "openrouter",
5413
5396
  baseUrl: "https://openrouter.ai/api/v1",
5414
5397
  reasoning: false,
5415
5398
  input: ["text"],
5416
5399
  cost: {
5417
- input: 10,
5418
- output: 30,
5400
+ input: 1,
5401
+ output: 2,
5419
5402
  cacheRead: 0,
5420
5403
  cacheWrite: 0,
5421
5404
  },
5422
- contextWindow: 128000,
5405
+ contextWindow: 4095,
5423
5406
  maxTokens: 4096,
5424
5407
  },
5425
5408
  "mistralai/mistral-small": {
@@ -5541,38 +5524,38 @@ export const MODELS = {
5541
5524
  contextWindow: 8191,
5542
5525
  maxTokens: 4096,
5543
5526
  },
5544
- "openai/gpt-3.5-turbo": {
5545
- id: "openai/gpt-3.5-turbo",
5546
- name: "OpenAI: GPT-3.5 Turbo",
5527
+ "openai/gpt-4": {
5528
+ id: "openai/gpt-4",
5529
+ name: "OpenAI: GPT-4",
5547
5530
  api: "openai-completions",
5548
5531
  provider: "openrouter",
5549
5532
  baseUrl: "https://openrouter.ai/api/v1",
5550
5533
  reasoning: false,
5551
5534
  input: ["text"],
5552
5535
  cost: {
5553
- input: 0.5,
5554
- output: 1.5,
5536
+ input: 30,
5537
+ output: 60,
5555
5538
  cacheRead: 0,
5556
5539
  cacheWrite: 0,
5557
5540
  },
5558
- contextWindow: 16385,
5541
+ contextWindow: 8191,
5559
5542
  maxTokens: 4096,
5560
5543
  },
5561
- "openai/gpt-4": {
5562
- id: "openai/gpt-4",
5563
- name: "OpenAI: GPT-4",
5544
+ "openai/gpt-3.5-turbo": {
5545
+ id: "openai/gpt-3.5-turbo",
5546
+ name: "OpenAI: GPT-3.5 Turbo",
5564
5547
  api: "openai-completions",
5565
5548
  provider: "openrouter",
5566
5549
  baseUrl: "https://openrouter.ai/api/v1",
5567
5550
  reasoning: false,
5568
5551
  input: ["text"],
5569
5552
  cost: {
5570
- input: 30,
5571
- output: 60,
5553
+ input: 0.5,
5554
+ output: 1.5,
5572
5555
  cacheRead: 0,
5573
5556
  cacheWrite: 0,
5574
5557
  },
5575
- contextWindow: 8191,
5558
+ contextWindow: 16385,
5576
5559
  maxTokens: 4096,
5577
5560
  },
5578
5561
  "openrouter/auto": {