@openeryc/pi-ai 0.75.30 → 0.75.33

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.
@@ -1916,7 +1916,7 @@ export const MODELS = {
1916
1916
  cost: {
1917
1917
  input: 0.1,
1918
1918
  output: 0.4,
1919
- cacheRead: 0.03,
1919
+ cacheRead: 0.025,
1920
1920
  cacheWrite: 0,
1921
1921
  },
1922
1922
  contextWindow: 1047576,
@@ -2001,7 +2001,7 @@ export const MODELS = {
2001
2001
  cost: {
2002
2002
  input: 0.15,
2003
2003
  output: 0.6,
2004
- cacheRead: 0.08,
2004
+ cacheRead: 0.075,
2005
2005
  cacheWrite: 0,
2006
2006
  },
2007
2007
  contextWindow: 128000,
@@ -2127,7 +2127,7 @@ export const MODELS = {
2127
2127
  cost: {
2128
2128
  input: 1.25,
2129
2129
  output: 10,
2130
- cacheRead: 0.13,
2130
+ cacheRead: 0.125,
2131
2131
  cacheWrite: 0,
2132
2132
  },
2133
2133
  contextWindow: 400000,
@@ -2552,7 +2552,7 @@ export const MODELS = {
2552
2552
  cost: {
2553
2553
  input: 1.1,
2554
2554
  output: 4.4,
2555
- cacheRead: 0.28,
2555
+ cacheRead: 0.275,
2556
2556
  cacheWrite: 0,
2557
2557
  },
2558
2558
  contextWindow: 200000,
@@ -2611,23 +2611,6 @@ export const MODELS = {
2611
2611
  contextWindow: 32000,
2612
2612
  maxTokens: 8000,
2613
2613
  },
2614
- "qwen-3-235b-a22b-instruct-2507": {
2615
- id: "qwen-3-235b-a22b-instruct-2507",
2616
- name: "Qwen 3 235B Instruct",
2617
- api: "openai-completions",
2618
- provider: "cerebras",
2619
- baseUrl: "https://api.cerebras.ai/v1",
2620
- reasoning: false,
2621
- input: ["text"],
2622
- cost: {
2623
- input: 0.6,
2624
- output: 1.2,
2625
- cacheRead: 0,
2626
- cacheWrite: 0,
2627
- },
2628
- contextWindow: 131000,
2629
- maxTokens: 32000,
2630
- },
2631
2614
  "zai-glm-4.7": {
2632
2615
  id: "zai-glm-4.7",
2633
2616
  name: "Z.AI GLM-4.7",
@@ -4838,7 +4821,7 @@ export const MODELS = {
4838
4821
  cost: {
4839
4822
  input: 1,
4840
4823
  output: 3,
4841
- cacheRead: 0,
4824
+ cacheRead: 0.5,
4842
4825
  cacheWrite: 0,
4843
4826
  },
4844
4827
  contextWindow: 262144,
@@ -4855,7 +4838,7 @@ export const MODELS = {
4855
4838
  cost: {
4856
4839
  input: 0.15,
4857
4840
  output: 0.6,
4858
- cacheRead: 0,
4841
+ cacheRead: 0.075,
4859
4842
  cacheWrite: 0,
4860
4843
  },
4861
4844
  contextWindow: 131072,
@@ -4872,7 +4855,7 @@ export const MODELS = {
4872
4855
  cost: {
4873
4856
  input: 0.075,
4874
4857
  output: 0.3,
4875
- cacheRead: 0,
4858
+ cacheRead: 0.0375,
4876
4859
  cacheWrite: 0,
4877
4860
  },
4878
4861
  contextWindow: 131072,
@@ -6253,7 +6236,7 @@ export const MODELS = {
6253
6236
  cost: {
6254
6237
  input: 0.1,
6255
6238
  output: 0.4,
6256
- cacheRead: 0.03,
6239
+ cacheRead: 0.025,
6257
6240
  cacheWrite: 0,
6258
6241
  },
6259
6242
  contextWindow: 1047576,
@@ -6338,7 +6321,7 @@ export const MODELS = {
6338
6321
  cost: {
6339
6322
  input: 0.15,
6340
6323
  output: 0.6,
6341
- cacheRead: 0.08,
6324
+ cacheRead: 0.075,
6342
6325
  cacheWrite: 0,
6343
6326
  },
6344
6327
  contextWindow: 128000,
@@ -6464,7 +6447,7 @@ export const MODELS = {
6464
6447
  cost: {
6465
6448
  input: 1.25,
6466
6449
  output: 10,
6467
- cacheRead: 0.13,
6450
+ cacheRead: 0.125,
6468
6451
  cacheWrite: 0,
6469
6452
  },
6470
6453
  contextWindow: 400000,
@@ -6889,7 +6872,7 @@ export const MODELS = {
6889
6872
  cost: {
6890
6873
  input: 1.1,
6891
6874
  output: 4.4,
6892
- cacheRead: 0.28,
6875
+ cacheRead: 0.275,
6893
6876
  cacheWrite: 0,
6894
6877
  },
6895
6878
  contextWindow: 200000,
@@ -7625,6 +7608,23 @@ export const MODELS = {
7625
7608
  contextWindow: 262144,
7626
7609
  maxTokens: 65536,
7627
7610
  },
7611
+ "mimo-v2.5-free": {
7612
+ id: "mimo-v2.5-free",
7613
+ name: "MiMo V2.5 Free",
7614
+ api: "openai-completions",
7615
+ provider: "opencode",
7616
+ baseUrl: "https://opencode.ai/zen/v1",
7617
+ reasoning: true,
7618
+ input: ["text", "image"],
7619
+ cost: {
7620
+ input: 0,
7621
+ output: 0,
7622
+ cacheRead: 0,
7623
+ cacheWrite: 0,
7624
+ },
7625
+ contextWindow: 1000000,
7626
+ maxTokens: 128000,
7627
+ },
7628
7628
  "minimax-m2.5": {
7629
7629
  id: "minimax-m2.5",
7630
7630
  name: "MiniMax M2.5",
@@ -7827,9 +7827,9 @@ export const MODELS = {
7827
7827
  reasoning: true,
7828
7828
  input: ["text", "image"],
7829
7829
  cost: {
7830
- input: 0.4,
7831
- output: 2,
7832
- cacheRead: 0.08,
7830
+ input: 0.14,
7831
+ output: 0.28,
7832
+ cacheRead: 0.0028,
7833
7833
  cacheWrite: 0,
7834
7834
  },
7835
7835
  contextWindow: 1000000,
@@ -7844,9 +7844,9 @@ export const MODELS = {
7844
7844
  reasoning: true,
7845
7845
  input: ["text"],
7846
7846
  cost: {
7847
- input: 1,
7848
- output: 3,
7849
- cacheRead: 0.2,
7847
+ input: 1.74,
7848
+ output: 3.48,
7849
+ cacheRead: 0.0145,
7850
7850
  cacheWrite: 0,
7851
7851
  },
7852
7852
  contextWindow: 1048576,
@@ -7922,6 +7922,23 @@ export const MODELS = {
7922
7922
  contextWindow: 262144,
7923
7923
  maxTokens: 65536,
7924
7924
  },
7925
+ "qwen3.7-max": {
7926
+ id: "qwen3.7-max",
7927
+ name: "Qwen3.7 Max",
7928
+ api: "anthropic-messages",
7929
+ provider: "opencode-go",
7930
+ baseUrl: "https://opencode.ai/zen/go",
7931
+ reasoning: true,
7932
+ input: ["text"],
7933
+ cost: {
7934
+ input: 2.5,
7935
+ output: 7.5,
7936
+ cacheRead: 0.5,
7937
+ cacheWrite: 3.125,
7938
+ },
7939
+ contextWindow: 1000000,
7940
+ maxTokens: 65536,
7941
+ },
7925
7942
  },
7926
7943
  "openrouter": {
7927
7944
  "ai21/jamba-large-1.7": {
@@ -8268,23 +8285,6 @@ export const MODELS = {
8268
8285
  contextWindow: 262144,
8269
8286
  maxTokens: 262144,
8270
8287
  },
8271
- "arcee-ai/trinity-large-thinking:free": {
8272
- id: "arcee-ai/trinity-large-thinking:free",
8273
- name: "Arcee AI: Trinity Large Thinking (free)",
8274
- api: "openai-completions",
8275
- provider: "openrouter",
8276
- baseUrl: "https://openrouter.ai/api/v1",
8277
- reasoning: true,
8278
- input: ["text"],
8279
- cost: {
8280
- input: 0,
8281
- output: 0,
8282
- cacheRead: 0,
8283
- cacheWrite: 0,
8284
- },
8285
- contextWindow: 262144,
8286
- maxTokens: 80000,
8287
- },
8288
8288
  "arcee-ai/trinity-mini": {
8289
8289
  id: "arcee-ai/trinity-mini",
8290
8290
  name: "Arcee AI: Trinity Mini",
@@ -8336,23 +8336,6 @@ export const MODELS = {
8336
8336
  contextWindow: 2000000,
8337
8337
  maxTokens: 30000,
8338
8338
  },
8339
- "baidu/cobuddy:free": {
8340
- id: "baidu/cobuddy:free",
8341
- name: "Baidu Qianfan: CoBuddy (free)",
8342
- api: "openai-completions",
8343
- provider: "openrouter",
8344
- baseUrl: "https://openrouter.ai/api/v1",
8345
- reasoning: true,
8346
- input: ["text"],
8347
- cost: {
8348
- input: 0,
8349
- output: 0,
8350
- cacheRead: 0,
8351
- cacheWrite: 0,
8352
- },
8353
- contextWindow: 131072,
8354
- maxTokens: 65536,
8355
- },
8356
8339
  "baidu/ernie-4.5-21b-a3b": {
8357
8340
  id: "baidu/ernie-4.5-21b-a3b",
8358
8341
  name: "Baidu: ERNIE 4.5 21B A3B",
@@ -9309,7 +9292,7 @@ export const MODELS = {
9309
9292
  cacheRead: 0,
9310
9293
  cacheWrite: 0,
9311
9294
  },
9312
- contextWindow: 204800,
9295
+ contextWindow: 262144,
9313
9296
  maxTokens: 8192,
9314
9297
  },
9315
9298
  "minimax/minimax-m2.7": {
@@ -9771,6 +9754,23 @@ export const MODELS = {
9771
9754
  contextWindow: 262144,
9772
9755
  maxTokens: 262142,
9773
9756
  },
9757
+ "moonshotai/kimi-k2.6:free": {
9758
+ id: "moonshotai/kimi-k2.6:free",
9759
+ name: "MoonshotAI: Kimi K2.6 (free)",
9760
+ api: "openai-completions",
9761
+ provider: "openrouter",
9762
+ baseUrl: "https://openrouter.ai/api/v1",
9763
+ reasoning: true,
9764
+ input: ["text", "image"],
9765
+ cost: {
9766
+ input: 0,
9767
+ output: 0,
9768
+ cacheRead: 0,
9769
+ cacheWrite: 0,
9770
+ },
9771
+ contextWindow: 262144,
9772
+ maxTokens: 4096,
9773
+ },
9774
9774
  "nex-agi/deepseek-v3.1-nex-n1": {
9775
9775
  id: "nex-agi/deepseek-v3.1-nex-n1",
9776
9776
  name: "Nex AGI: DeepSeek V3.1 Nex N1",
@@ -10360,11 +10360,11 @@ export const MODELS = {
10360
10360
  cost: {
10361
10361
  input: 1.25,
10362
10362
  output: 10,
10363
- cacheRead: 0.125,
10363
+ cacheRead: 0.13,
10364
10364
  cacheWrite: 0,
10365
10365
  },
10366
10366
  contextWindow: 128000,
10367
- maxTokens: 16384,
10367
+ maxTokens: 32000,
10368
10368
  },
10369
10369
  "openai/gpt-5.1-codex": {
10370
10370
  id: "openai/gpt-5.1-codex",
@@ -10377,7 +10377,7 @@ export const MODELS = {
10377
10377
  cost: {
10378
10378
  input: 1.25,
10379
10379
  output: 10,
10380
- cacheRead: 0.125,
10380
+ cacheRead: 0.13,
10381
10381
  cacheWrite: 0,
10382
10382
  },
10383
10383
  contextWindow: 400000,
@@ -10411,11 +10411,11 @@ export const MODELS = {
10411
10411
  cost: {
10412
10412
  input: 0.25,
10413
10413
  output: 2,
10414
- cacheRead: 0.03,
10414
+ cacheRead: 0.024999999999999998,
10415
10415
  cacheWrite: 0,
10416
10416
  },
10417
10417
  contextWindow: 400000,
10418
- maxTokens: 128000,
10418
+ maxTokens: 100000,
10419
10419
  },
10420
10420
  "openai/gpt-5.2": {
10421
10421
  id: "openai/gpt-5.2",
@@ -10451,7 +10451,7 @@ export const MODELS = {
10451
10451
  cacheWrite: 0,
10452
10452
  },
10453
10453
  contextWindow: 128000,
10454
- maxTokens: 32000,
10454
+ maxTokens: 16384,
10455
10455
  },
10456
10456
  "openai/gpt-5.2-codex": {
10457
10457
  id: "openai/gpt-5.2-codex",
@@ -11004,8 +11004,8 @@ export const MODELS = {
11004
11004
  cacheRead: 0,
11005
11005
  cacheWrite: 0,
11006
11006
  },
11007
- contextWindow: 131072,
11008
- maxTokens: 8192,
11007
+ contextWindow: 262144,
11008
+ maxTokens: 32768,
11009
11009
  },
11010
11010
  "prime-intellect/intellect-3": {
11011
11011
  id: "prime-intellect/intellect-3",
@@ -11087,7 +11087,7 @@ export const MODELS = {
11087
11087
  input: 0.26,
11088
11088
  output: 0.78,
11089
11089
  cacheRead: 0,
11090
- cacheWrite: 0.325,
11090
+ cacheWrite: 0,
11091
11091
  },
11092
11092
  contextWindow: 1000000,
11093
11093
  maxTokens: 32768,
@@ -11665,7 +11665,7 @@ export const MODELS = {
11665
11665
  input: 0.065,
11666
11666
  output: 0.26,
11667
11667
  cacheRead: 0,
11668
- cacheWrite: 0.08125,
11668
+ cacheWrite: 0,
11669
11669
  },
11670
11670
  contextWindow: 1000000,
11671
11671
  maxTokens: 65536,
@@ -11682,7 +11682,7 @@ export const MODELS = {
11682
11682
  input: 0.26,
11683
11683
  output: 1.56,
11684
11684
  cacheRead: 0,
11685
- cacheWrite: 0.325,
11685
+ cacheWrite: 0,
11686
11686
  },
11687
11687
  contextWindow: 1000000,
11688
11688
  maxTokens: 65536,
@@ -11699,7 +11699,7 @@ export const MODELS = {
11699
11699
  input: 0.3,
11700
11700
  output: 1.7999999999999998,
11701
11701
  cacheRead: 0,
11702
- cacheWrite: 0,
11702
+ cacheWrite: 0.375,
11703
11703
  },
11704
11704
  contextWindow: 1000000,
11705
11705
  maxTokens: 65536,
@@ -11713,13 +11713,13 @@ export const MODELS = {
11713
11713
  reasoning: true,
11714
11714
  input: ["text", "image"],
11715
11715
  cost: {
11716
- input: 0.3,
11717
- output: 2,
11718
- cacheRead: 0.15,
11716
+ input: 0.29,
11717
+ output: 3.1999999999999997,
11718
+ cacheRead: 0,
11719
11719
  cacheWrite: 0,
11720
11720
  },
11721
11721
  contextWindow: 262144,
11722
- maxTokens: 65536,
11722
+ maxTokens: 262140,
11723
11723
  },
11724
11724
  "qwen/qwen3.6-35b-a3b": {
11725
11725
  id: "qwen/qwen3.6-35b-a3b",
@@ -11730,7 +11730,7 @@ export const MODELS = {
11730
11730
  reasoning: true,
11731
11731
  input: ["text", "image"],
11732
11732
  cost: {
11733
- input: 0.15,
11733
+ input: 0.14,
11734
11734
  output: 1,
11735
11735
  cacheRead: 0,
11736
11736
  cacheWrite: 0,
@@ -11798,10 +11798,10 @@ export const MODELS = {
11798
11798
  reasoning: true,
11799
11799
  input: ["text"],
11800
11800
  cost: {
11801
- input: 2.5,
11802
- output: 7.5,
11803
- cacheRead: 0,
11804
- cacheWrite: 3.125,
11801
+ input: 1.25,
11802
+ output: 3.75,
11803
+ cacheRead: 0.25,
11804
+ cacheWrite: 1.5625,
11805
11805
  },
11806
11806
  contextWindow: 1000000,
11807
11807
  maxTokens: 65536,
@@ -12070,9 +12070,9 @@ export const MODELS = {
12070
12070
  reasoning: true,
12071
12071
  input: ["text", "image"],
12072
12072
  cost: {
12073
- input: 0.39999999999999997,
12074
- output: 2,
12075
- cacheRead: 0.08,
12073
+ input: 0.14,
12074
+ output: 0.28,
12075
+ cacheRead: 0.0028,
12076
12076
  cacheWrite: 0,
12077
12077
  },
12078
12078
  contextWindow: 1048576,
@@ -12087,13 +12087,13 @@ export const MODELS = {
12087
12087
  reasoning: true,
12088
12088
  input: ["text"],
12089
12089
  cost: {
12090
- input: 1,
12091
- output: 3,
12092
- cacheRead: 0.19999999999999998,
12090
+ input: 0.435,
12091
+ output: 0.87,
12092
+ cacheRead: 0.0036,
12093
12093
  cacheWrite: 0,
12094
12094
  },
12095
12095
  contextWindow: 1048576,
12096
- maxTokens: 16384,
12096
+ maxTokens: 131072,
12097
12097
  },
12098
12098
  "z-ai/glm-4-32b": {
12099
12099
  id: "z-ai/glm-4-32b",
@@ -12138,13 +12138,13 @@ export const MODELS = {
12138
12138
  reasoning: true,
12139
12139
  input: ["text"],
12140
12140
  cost: {
12141
- input: 0.13,
12142
- output: 0.85,
12143
- cacheRead: 0.024999999999999998,
12141
+ input: 0.125,
12142
+ output: 0.84,
12143
+ cacheRead: 0,
12144
12144
  cacheWrite: 0,
12145
12145
  },
12146
12146
  contextWindow: 131072,
12147
- maxTokens: 98304,
12147
+ maxTokens: 131070,
12148
12148
  },
12149
12149
  "z-ai/glm-4.5-air:free": {
12150
12150
  id: "z-ai/glm-4.5-air:free",
@@ -15249,9 +15249,9 @@ export const MODELS = {
15249
15249
  reasoning: true,
15250
15250
  input: ["text", "image"],
15251
15251
  cost: {
15252
- input: 0.39999999999999997,
15253
- output: 2,
15254
- cacheRead: 0.08,
15252
+ input: 0.14,
15253
+ output: 0.28,
15254
+ cacheRead: 0.0028,
15255
15255
  cacheWrite: 0,
15256
15256
  },
15257
15257
  contextWindow: 1050000,
@@ -15266,9 +15266,9 @@ export const MODELS = {
15266
15266
  reasoning: true,
15267
15267
  input: ["text", "image"],
15268
15268
  cost: {
15269
- input: 1,
15270
- output: 3,
15271
- cacheRead: 0.19999999999999998,
15269
+ input: 0.435,
15270
+ output: 0.87,
15271
+ cacheRead: 0.0036,
15272
15272
  cacheWrite: 0,
15273
15273
  },
15274
15274
  contextWindow: 1050000,