@earendil-works/pi-ai 0.79.5 → 0.79.7

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.
@@ -3882,7 +3882,7 @@ export const MODELS = {
3882
3882
  cost: {
3883
3883
  input: 0.14,
3884
3884
  output: 0.28,
3885
- cacheRead: 0.03,
3885
+ cacheRead: 0.028,
3886
3886
  cacheWrite: 0,
3887
3887
  },
3888
3888
  contextWindow: 1000000,
@@ -3924,6 +3924,24 @@ export const MODELS = {
3924
3924
  contextWindow: 202800,
3925
3925
  maxTokens: 131072,
3926
3926
  },
3927
+ "accounts/fireworks/models/glm-5p2": {
3928
+ id: "accounts/fireworks/models/glm-5p2",
3929
+ name: "GLM 5.2",
3930
+ api: "anthropic-messages",
3931
+ provider: "fireworks",
3932
+ baseUrl: "https://api.fireworks.ai/inference",
3933
+ compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
3934
+ reasoning: true,
3935
+ input: ["text"],
3936
+ cost: {
3937
+ input: 1.4,
3938
+ output: 4.4,
3939
+ cacheRead: 0.26,
3940
+ cacheWrite: 0,
3941
+ },
3942
+ contextWindow: 1048576,
3943
+ maxTokens: 131072,
3944
+ },
3927
3945
  "accounts/fireworks/models/gpt-oss-120b": {
3928
3946
  id: "accounts/fireworks/models/gpt-oss-120b",
3929
3947
  name: "GPT OSS 120B",
@@ -3936,7 +3954,7 @@ export const MODELS = {
3936
3954
  cost: {
3937
3955
  input: 0.15,
3938
3956
  output: 0.6,
3939
- cacheRead: 0.01,
3957
+ cacheRead: 0.015,
3940
3958
  cacheWrite: 0,
3941
3959
  },
3942
3960
  contextWindow: 131072,
@@ -4114,7 +4132,7 @@ export const MODELS = {
4114
4132
  reasoning: true,
4115
4133
  input: ["text", "image"],
4116
4134
  cost: {
4117
- input: 2,
4135
+ input: 1.9,
4118
4136
  output: 8,
4119
4137
  cacheRead: 0.38,
4120
4138
  cacheWrite: 0,
@@ -4545,25 +4563,6 @@ export const MODELS = {
4545
4563
  contextWindow: 400000,
4546
4564
  maxTokens: 128000,
4547
4565
  },
4548
- "raptor-mini": {
4549
- id: "raptor-mini",
4550
- name: "Raptor mini",
4551
- api: "openai-completions",
4552
- provider: "github-copilot",
4553
- baseUrl: "https://api.individual.githubcopilot.com",
4554
- headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
4555
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
4556
- reasoning: true,
4557
- input: ["text", "image"],
4558
- cost: {
4559
- input: 0.25,
4560
- output: 2,
4561
- cacheRead: 0.025,
4562
- cacheWrite: 0,
4563
- },
4564
- contextWindow: 400000,
4565
- maxTokens: 128000,
4566
- },
4567
4566
  },
4568
4567
  "google": {
4569
4568
  "gemini-2.0-flash": {
@@ -8569,7 +8568,7 @@ export const MODELS = {
8569
8568
  api: "openai-completions",
8570
8569
  provider: "opencode-go",
8571
8570
  baseUrl: "https://opencode.ai/zen/go/v1",
8572
- compat: { "maxTokensField": "max_tokens", "requiresReasoningContentOnAssistantMessages": true },
8571
+ compat: { "maxTokensField": "max_tokens", "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
8573
8572
  reasoning: true,
8574
8573
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
8575
8574
  input: ["text"],
@@ -8588,7 +8587,7 @@ export const MODELS = {
8588
8587
  api: "openai-completions",
8589
8588
  provider: "opencode-go",
8590
8589
  baseUrl: "https://opencode.ai/zen/go/v1",
8591
- compat: { "maxTokensField": "max_tokens", "requiresReasoningContentOnAssistantMessages": true },
8590
+ compat: { "maxTokensField": "max_tokens", "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
8592
8591
  reasoning: true,
8593
8592
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
8594
8593
  input: ["text"],
@@ -8601,9 +8600,9 @@ export const MODELS = {
8601
8600
  contextWindow: 1000000,
8602
8601
  maxTokens: 384000,
8603
8602
  },
8604
- "glm-5": {
8605
- id: "glm-5",
8606
- name: "GLM-5",
8603
+ "glm-5.1": {
8604
+ id: "glm-5.1",
8605
+ name: "GLM-5.1",
8607
8606
  api: "openai-completions",
8608
8607
  provider: "opencode-go",
8609
8608
  baseUrl: "https://opencode.ai/zen/go/v1",
@@ -8611,17 +8610,17 @@ export const MODELS = {
8611
8610
  reasoning: true,
8612
8611
  input: ["text"],
8613
8612
  cost: {
8614
- input: 1,
8615
- output: 3.2,
8616
- cacheRead: 0.2,
8613
+ input: 1.4,
8614
+ output: 4.4,
8615
+ cacheRead: 0.26,
8617
8616
  cacheWrite: 0,
8618
8617
  },
8619
8618
  contextWindow: 202752,
8620
8619
  maxTokens: 32768,
8621
8620
  },
8622
- "glm-5.1": {
8623
- id: "glm-5.1",
8624
- name: "GLM-5.1",
8621
+ "glm-5.2": {
8622
+ id: "glm-5.2",
8623
+ name: "GLM-5.2",
8625
8624
  api: "openai-completions",
8626
8625
  provider: "opencode-go",
8627
8626
  baseUrl: "https://opencode.ai/zen/go/v1",
@@ -8634,8 +8633,8 @@ export const MODELS = {
8634
8633
  cacheRead: 0.26,
8635
8634
  cacheWrite: 0,
8636
8635
  },
8637
- contextWindow: 202752,
8638
- maxTokens: 32768,
8636
+ contextWindow: 1000000,
8637
+ maxTokens: 131072,
8639
8638
  },
8640
8639
  "kimi-k2.6": {
8641
8640
  id: "kimi-k2.6",
@@ -9349,6 +9348,23 @@ export const MODELS = {
9349
9348
  contextWindow: 128000,
9350
9349
  maxTokens: 4000,
9351
9350
  },
9351
+ "cohere/north-mini-code:free": {
9352
+ id: "cohere/north-mini-code:free",
9353
+ name: "Cohere: North Mini Code (free)",
9354
+ api: "openai-completions",
9355
+ provider: "openrouter",
9356
+ baseUrl: "https://openrouter.ai/api/v1",
9357
+ reasoning: true,
9358
+ input: ["text"],
9359
+ cost: {
9360
+ input: 0,
9361
+ output: 0,
9362
+ cacheRead: 0,
9363
+ cacheWrite: 0,
9364
+ },
9365
+ contextWindow: 256000,
9366
+ maxTokens: 64000,
9367
+ },
9352
9368
  "deepseek/deepseek-chat": {
9353
9369
  id: "deepseek/deepseek-chat",
9354
9370
  name: "DeepSeek: DeepSeek V3",
@@ -9496,13 +9512,13 @@ export const MODELS = {
9496
9512
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
9497
9513
  input: ["text"],
9498
9514
  cost: {
9499
- input: 0.098,
9500
- output: 0.196,
9515
+ input: 0.09,
9516
+ output: 0.18,
9501
9517
  cacheRead: 0.02,
9502
9518
  cacheWrite: 0,
9503
9519
  },
9504
9520
  contextWindow: 1048576,
9505
- maxTokens: 4096,
9521
+ maxTokens: 65536,
9506
9522
  },
9507
9523
  "deepseek/deepseek-v4-pro": {
9508
9524
  id: "deepseek/deepseek-v4-pro",
@@ -9657,7 +9673,24 @@ export const MODELS = {
9657
9673
  cacheWrite: 0.083333,
9658
9674
  },
9659
9675
  contextWindow: 1048576,
9660
- maxTokens: 65536,
9676
+ maxTokens: 65535,
9677
+ },
9678
+ "google/gemini-3-pro-image": {
9679
+ id: "google/gemini-3-pro-image",
9680
+ name: "Google: Nano Banana Pro (Gemini 3 Pro Image)",
9681
+ api: "openai-completions",
9682
+ provider: "openrouter",
9683
+ baseUrl: "https://openrouter.ai/api/v1",
9684
+ reasoning: true,
9685
+ input: ["text", "image"],
9686
+ cost: {
9687
+ input: 2,
9688
+ output: 12,
9689
+ cacheRead: 0.2,
9690
+ cacheWrite: 0.375,
9691
+ },
9692
+ contextWindow: 65536,
9693
+ maxTokens: 32768,
9661
9694
  },
9662
9695
  "google/gemini-3.1-flash-lite": {
9663
9696
  id: "google/gemini-3.1-flash-lite",
@@ -9844,7 +9877,7 @@ export const MODELS = {
9844
9877
  cacheWrite: 0,
9845
9878
  },
9846
9879
  contextWindow: 262144,
9847
- maxTokens: 32768,
9880
+ maxTokens: 8192,
9848
9881
  },
9849
9882
  "ibm-granite/granite-4.1-8b": {
9850
9883
  id: "ibm-granite/granite-4.1-8b",
@@ -9949,6 +9982,23 @@ export const MODELS = {
9949
9982
  contextWindow: 256000,
9950
9983
  maxTokens: 80000,
9951
9984
  },
9985
+ "liquid/lfm-2.5-1.2b-thinking:free": {
9986
+ id: "liquid/lfm-2.5-1.2b-thinking:free",
9987
+ name: "LiquidAI: LFM2.5-1.2B-Thinking (free)",
9988
+ api: "openai-completions",
9989
+ provider: "openrouter",
9990
+ baseUrl: "https://openrouter.ai/api/v1",
9991
+ reasoning: true,
9992
+ input: ["text"],
9993
+ cost: {
9994
+ input: 0,
9995
+ output: 0,
9996
+ cacheRead: 0,
9997
+ cacheWrite: 0,
9998
+ },
9999
+ contextWindow: 32768,
10000
+ maxTokens: 4096,
10001
+ },
9952
10002
  "meta-llama/llama-3.1-70b-instruct": {
9953
10003
  id: "meta-llama/llama-3.1-70b-instruct",
9954
10004
  name: "Meta: Llama 3.1 70B Instruct",
@@ -10537,13 +10587,13 @@ export const MODELS = {
10537
10587
  reasoning: true,
10538
10588
  input: ["text", "image"],
10539
10589
  cost: {
10540
- input: 0.75,
10590
+ input: 0.74,
10541
10591
  output: 3.5,
10542
- cacheRead: 0.16,
10592
+ cacheRead: 0.15,
10543
10593
  cacheWrite: 0,
10544
10594
  },
10545
10595
  contextWindow: 262144,
10546
- maxTokens: 262144,
10596
+ maxTokens: 16384,
10547
10597
  },
10548
10598
  "nex-agi/nex-n2-pro:free": {
10549
10599
  id: "nex-agi/nex-n2-pro:free",
@@ -10674,8 +10724,8 @@ export const MODELS = {
10674
10724
  input: ["text"],
10675
10725
  cost: {
10676
10726
  input: 0.5,
10677
- output: 2.5,
10678
- cacheRead: 0.15,
10727
+ output: 2.2,
10728
+ cacheRead: 0.1,
10679
10729
  cacheWrite: 0,
10680
10730
  },
10681
10731
  contextWindow: 1000000,
@@ -11490,7 +11540,7 @@ export const MODELS = {
11490
11540
  cacheWrite: 0,
11491
11541
  },
11492
11542
  contextWindow: 131072,
11493
- maxTokens: 8192,
11543
+ maxTokens: 32768,
11494
11544
  },
11495
11545
  "openai/gpt-oss-safeguard-20b": {
11496
11546
  id: "openai/gpt-oss-safeguard-20b",
@@ -11713,6 +11763,23 @@ export const MODELS = {
11713
11763
  contextWindow: 1048756,
11714
11764
  maxTokens: 262144,
11715
11765
  },
11766
+ "poolside/laguna-m.1": {
11767
+ id: "poolside/laguna-m.1",
11768
+ name: "Poolside: Laguna M.1",
11769
+ api: "openai-completions",
11770
+ provider: "openrouter",
11771
+ baseUrl: "https://openrouter.ai/api/v1",
11772
+ reasoning: true,
11773
+ input: ["text"],
11774
+ cost: {
11775
+ input: 0.2,
11776
+ output: 0.4,
11777
+ cacheRead: 0.1,
11778
+ cacheWrite: 0,
11779
+ },
11780
+ contextWindow: 262144,
11781
+ maxTokens: 32768,
11782
+ },
11716
11783
  "poolside/laguna-m.1:free": {
11717
11784
  id: "poolside/laguna-m.1:free",
11718
11785
  name: "Poolside: Laguna M.1 (free)",
@@ -11730,6 +11797,23 @@ export const MODELS = {
11730
11797
  contextWindow: 262144,
11731
11798
  maxTokens: 32768,
11732
11799
  },
11800
+ "poolside/laguna-xs.2": {
11801
+ id: "poolside/laguna-xs.2",
11802
+ name: "Poolside: Laguna XS.2",
11803
+ api: "openai-completions",
11804
+ provider: "openrouter",
11805
+ baseUrl: "https://openrouter.ai/api/v1",
11806
+ reasoning: true,
11807
+ input: ["text"],
11808
+ cost: {
11809
+ input: 0.1,
11810
+ output: 0.2,
11811
+ cacheRead: 0.05,
11812
+ cacheWrite: 0,
11813
+ },
11814
+ contextWindow: 262144,
11815
+ maxTokens: 32768,
11816
+ },
11733
11817
  "poolside/laguna-xs.2:free": {
11734
11818
  id: "poolside/laguna-xs.2:free",
11735
11819
  name: "Poolside: Laguna XS.2 (free)",
@@ -11781,6 +11865,23 @@ export const MODELS = {
11781
11865
  contextWindow: 131072,
11782
11866
  maxTokens: 16384,
11783
11867
  },
11868
+ "qwen/qwen-2.5-7b-instruct": {
11869
+ id: "qwen/qwen-2.5-7b-instruct",
11870
+ name: "Qwen: Qwen2.5 7B Instruct",
11871
+ api: "openai-completions",
11872
+ provider: "openrouter",
11873
+ baseUrl: "https://openrouter.ai/api/v1",
11874
+ reasoning: false,
11875
+ input: ["text"],
11876
+ cost: {
11877
+ input: 0.04,
11878
+ output: 0.1,
11879
+ cacheRead: 0,
11880
+ cacheWrite: 0,
11881
+ },
11882
+ contextWindow: 131072,
11883
+ maxTokens: 32768,
11884
+ },
11784
11885
  "qwen/qwen-plus": {
11785
11886
  id: "qwen/qwen-plus",
11786
11887
  name: "Qwen: Qwen-Plus",
@@ -12336,11 +12437,11 @@ export const MODELS = {
12336
12437
  cost: {
12337
12438
  input: 0.14,
12338
12439
  output: 1,
12339
- cacheRead: 0.05,
12440
+ cacheRead: 0,
12340
12441
  cacheWrite: 0,
12341
12442
  },
12342
12443
  contextWindow: 262144,
12343
- maxTokens: 81920,
12444
+ maxTokens: 262144,
12344
12445
  },
12345
12446
  "qwen/qwen3.5-397b-a17b": {
12346
12447
  id: "qwen/qwen3.5-397b-a17b",
@@ -12453,9 +12554,9 @@ export const MODELS = {
12453
12554
  reasoning: true,
12454
12555
  input: ["text", "image"],
12455
12556
  cost: {
12456
- input: 0.15,
12557
+ input: 0.14,
12457
12558
  output: 1,
12458
- cacheRead: 0.05,
12559
+ cacheRead: 0,
12459
12560
  cacheWrite: 0,
12460
12561
  },
12461
12562
  contextWindow: 262144,
@@ -12750,23 +12851,6 @@ export const MODELS = {
12750
12851
  contextWindow: 256000,
12751
12852
  maxTokens: 4096,
12752
12853
  },
12753
- "xiaomi/mimo-v2-flash": {
12754
- id: "xiaomi/mimo-v2-flash",
12755
- name: "Xiaomi: MiMo-V2-Flash",
12756
- api: "openai-completions",
12757
- provider: "openrouter",
12758
- baseUrl: "https://openrouter.ai/api/v1",
12759
- reasoning: true,
12760
- input: ["text"],
12761
- cost: {
12762
- input: 0.1,
12763
- output: 0.3,
12764
- cacheRead: 0.01,
12765
- cacheWrite: 0,
12766
- },
12767
- contextWindow: 262144,
12768
- maxTokens: 65536,
12769
- },
12770
12854
  "xiaomi/mimo-v2.5": {
12771
12855
  id: "xiaomi/mimo-v2.5",
12772
12856
  name: "Xiaomi: MiMo-V2.5",
@@ -12982,11 +13066,11 @@ export const MODELS = {
12982
13066
  cost: {
12983
13067
  input: 1.4,
12984
13068
  output: 4.4,
12985
- cacheRead: 0.26,
13069
+ cacheRead: 0.7,
12986
13070
  cacheWrite: 0,
12987
13071
  },
12988
13072
  contextWindow: 1048576,
12989
- maxTokens: 131072,
13073
+ maxTokens: 524288,
12990
13074
  },
12991
13075
  "~anthropic/claude-fable-latest": {
12992
13076
  id: "~anthropic/claude-fable-latest",
@@ -14945,13 +15029,13 @@ export const MODELS = {
14945
15029
  reasoning: false,
14946
15030
  input: ["text"],
14947
15031
  cost: {
14948
- input: 0.02,
14949
- output: 0.04,
15032
+ input: 0.15,
15033
+ output: 0.15,
14950
15034
  cacheRead: 0,
14951
15035
  cacheWrite: 0,
14952
15036
  },
14953
- contextWindow: 131072,
14954
- maxTokens: 131072,
15037
+ contextWindow: 128000,
15038
+ maxTokens: 128000,
14955
15039
  },
14956
15040
  "mistral/mistral-small": {
14957
15041
  id: "mistral/mistral-small",
@@ -15104,7 +15188,7 @@ export const MODELS = {
15104
15188
  cacheWrite: 0,
15105
15189
  },
15106
15190
  contextWindow: 262144,
15107
- maxTokens: 4096,
15191
+ maxTokens: 32768,
15108
15192
  },
15109
15193
  "nvidia/nemotron-3-super-120b-a12b": {
15110
15194
  id: "nvidia/nemotron-3-super-120b-a12b",
@@ -16351,9 +16435,9 @@ export const MODELS = {
16351
16435
  reasoning: true,
16352
16436
  input: ["text"],
16353
16437
  cost: {
16354
- input: 1.4,
16355
- output: 4.4,
16356
- cacheRead: 0.26,
16438
+ input: 1.5,
16439
+ output: 4.5,
16440
+ cacheRead: 0.3,
16357
16441
  cacheWrite: 0,
16358
16442
  },
16359
16443
  contextWindow: 1000000,