pi-io-provider 1.1.39 → 1.1.41

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.
Files changed (3) hide show
  1. package/README.md +17 -15
  2. package/models.json +90 -44
  3. package/package.json +1 -1
package/README.md CHANGED
@@ -16,25 +16,27 @@ A [pi](https://github.com/badlogic/pi-mono) extension that adds [IO Intelligence
16
16
 
17
17
  | Model | ID | Context | Max Output | Vision | Reasoning | Cache | Input $/M | Output $/M |
18
18
  |-------|----|---------|------------|--------|-----------|-------|-----------|------------|
19
+ | Gemma 4 26B A4B | `google/gemma-4-26b-a4b-it` | 262K | 262K | ✅ | ✅ | ✅ | $0.10 | $0.33 |
20
+ | Gemma 4 31B Instruct | `google/gemma-4-31b-it` | 262K | 16K | ✅ | ✅ | ✅ | $0.38 | $1.15 |
19
21
  | Kimi K2.5 | `moonshotai/Kimi-K2.5` | 262K | 262K | ✅ | ✅ | ✅ | $0.53 | $2.79 |
20
- | Kimi K2.6 | `moonshotai/Kimi-K2.6` | 262K | 262K | ✅ | ✅ | ✅ | $0.78 | $3.48 |
21
- | Kimi K2.7 Code | `moonshotai/Kimi-K2.7-Code` | 262K | 262K | ✅ | ✅ | ✅ | $0.88 | $3.81 |
22
- | Kimi K3 | `moonshotai/Kimi-K3` | 1.0M | 1.0M | ✅ | ✅ | ✅ | $3.72 | $17.19 |
23
- | Qwen3.6 27B | `Qwen/Qwen3.6-27B` | 33K | 33K | ✅ | ✅ | ✅ | $0.34 | $2.77 |
24
- | Qwen3.6 35B A3B | `Qwen/Qwen3.6-35B-A3B` | 262K | 262K | ✅ | ✅ | ✅ | $0.20 | $1.29 |
22
+ | Kimi K2.6 | `moonshotai/Kimi-K2.6` | 262K | 262K | ✅ | ✅ | ✅ | $0.88 | $3.70 |
23
+ | Kimi K2.7 Code | `moonshotai/Kimi-K2.7-Code` | 262K | 262K | ✅ | ✅ | ✅ | $1.07 | $4.65 |
24
+ | Kimi K3 | `moonshotai/Kimi-K3` | 1.0M | 1.0M | ✅ | ✅ | ✅ | $3.10 | $16.40 |
25
+ | Qwen3.6 27B | `Qwen/Qwen3.6-27B` | 33K | 33K | ✅ | ✅ | ✅ | $0.34 | $3.01 |
26
+ | Qwen3.6 35B A3B | `Qwen/Qwen3.6-35B-A3B` | 262K | 262K | ✅ | ✅ | ✅ | $0.17 | $1.11 |
25
27
  | Qwen3.8 27B | `Qwen/Qwen3.8-27B` | 66K | 66K | ✅ | ✅ | ✅ | $0.34 | $2.69 |
26
- | GLM 5.3 Flash | `zai-org/GLM-5.3-Flash` | 262K | 131K | ✅ | ✅ | ✅ | $0.20 | $0.67 |
28
+ | GLM 5.3 Flash | `zai-org/GLM-5.3-Flash` | 262K | 131K | ✅ | ✅ | ✅ | $0.21 | $0.70 |
27
29
  | DeepSeek R1 0528 | `deepseek-ai/DeepSeek-R1-0528` | 128K | 128K | ❌ | ✅ | ✅ | $0.57 | $2.28 |
28
- | DeepSeek V3.2 | `deepseek-ai/DeepSeek-V3.2` | 164K | 164K | ❌ | ✅ | ✅ | $0.94 | $1.84 |
30
+ | DeepSeek V3.2 | `deepseek-ai/DeepSeek-V3.2` | 164K | 164K | ❌ | ✅ | ✅ | $1.43 | $2.51 |
29
31
  | DeepSeek V4 Flash | `deepseek-ai/DeepSeek-V4-Flash` | 33K | 33K | ❌ | ✅ | ✅ | $0.15 | $0.32 |
30
- | DeepSeek V4 Flash 0731 | `deepseek-ai/DeepSeek-V4-Flash-0731` | 262K | 66K | ❌ | ✅ | ✅ | $0.20 | $0.54 |
31
- | DeepSeek V4 Pro | `deepseek-ai/DeepSeek-V4-Pro` | 1.0M | 600K | ❌ | ✅ | ✅ | $1.69 | $3.39 |
32
+ | DeepSeek V4 Flash 0731 | `deepseek-ai/DeepSeek-V4-Flash-0731` | 262K | 66K | ❌ | ✅ | ✅ | $0.23 | $0.74 |
33
+ | DeepSeek V4 Pro | `deepseek-ai/DeepSeek-V4-Pro` | 1.0M | 600K | ❌ | ✅ | ✅ | $1.51 | $3.03 |
32
34
  | DeepSeek V4.1 Flash | `deepseek-ai/DeepSeek-V4.1-Flash` | 262K | 131K | ❌ | ✅ | ✅ | $0.28 | $1.09 |
33
- | Gemma 4 26B A4B | `google/gemma-4-26b-a4b-it` | 262K | 262K | ❌ | ✅ | ✅ | $0.10 | $0.37 |
34
- | MiniMax M2.5 | `MiniMaxAI/MiniMax-M2.5` | 197K | 197K | ❌ | ✅ | ✅ | $0.36 | $1.44 |
35
- | MiniMax M2.7 | `MiniMaxAI/MiniMax-M2.7` | 262K | 66K | ❌ | ✅ | ✅ | $0.41 | $1.54 |
35
+ | MiniMax M2.5 | `MiniMaxAI/MiniMax-M2.5` | 197K | 197K | ❌ | ✅ | ✅ | $0.35 | $1.42 |
36
+ | MiniMax M2.7 | `MiniMaxAI/MiniMax-M2.7` | 262K | 66K | ❌ | ✅ | ✅ | $0.42 | $1.61 |
36
37
  | Kimi K2 Thinking | `moonshotai/Kimi-K2-Thinking` | 262K | 262K | ❌ | ✅ | ✅ | $0.60 | $2.50 |
37
- | gpt-oss-120b | `openai/gpt-oss-120b` | 131K | 131K | ❌ | ✅ | ✅ | $0.17 | $0.66 |
38
+ | Nemotron 3.5 Lightning | `nvidia/nemotron-3.5-lightning` | 262K | 131K | ❌ | ✅ | ✅ | $0.07 | $0.20 |
39
+ | gpt-oss-120b | `openai/gpt-oss-120b` | 131K | 131K | ❌ | ✅ | ✅ | $0.18 | $0.68 |
38
40
  | gpt-oss-20b | `openai/gpt-oss-20b` | 64K | 64K | ❌ | ✅ | ✅ | $0.06 | $0.20 |
39
41
  | MiMo-V2.5 | `XiaomiMiMo/MiMo-V2.5` | 1.0M | 1.0M | ❌ | ✅ | ✅ | $0.20 | $0.64 |
40
42
  | GLM-4.5-Air | `zai-org/GLM-4.5-Air` | 131K | 131K | ❌ | ✅ | ✅ | $0.16 | $0.94 |
@@ -44,11 +46,11 @@ A [pi](https://github.com/badlogic/pi-mono) extension that adds [IO Intelligence
44
46
  | GLM 5 | `zai-org/GLM-5` | 203K | 203K | ❌ | ✅ | ✅ | $0.86 | $2.75 |
45
47
  | GLM 5.1 | `zai-org/GLM-5.1` | 203K | 33K | ❌ | ✅ | ✅ | $1.36 | $4.27 |
46
48
  | GLM 5.2 | `zai-org/GLM-5.2` | 262K | 131K | ❌ | ✅ | ✅ | $1.99 | $6.44 |
47
- | GLM 5.3 | `zai-org/GLM-5.3` | 262K | 131K | ❌ | ✅ | ✅ | $1.31 | $4.18 |
49
+ | GLM 5.3 | `zai-org/GLM-5.3` | 262K | 131K | ❌ | ✅ | ✅ | $1.36 | $4.27 |
48
50
  | Llama 4 Maverick 17B 128E Instruct FP8 | `meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8` | 430K | 430K | ✅ | ❌ | ✅ | $0.25 | $0.83 |
49
51
  | Qwen3 Coder 480B A35B Instruct INT4 Mixed AR | `Intel/Qwen3-Coder-480B-A35B-Instruct-int4-mixed-ar` | 106K | 106K | ❌ | ❌ | ✅ | $0.45 | $2.15 |
50
52
  | Llama 3.3 70B Instruct | `meta-llama/Llama-3.3-70B-Instruct` | 128K | 128K | ❌ | ❌ | ✅ | $0.55 | $1.02 |
51
- | Mistral Nemo Instruct 2407 | `mistralai/Mistral-Nemo-Instruct-2407` | 128K | 128K | ❌ | ❌ | ✅ | $0.03 | $0.07 |
53
+ | Mistral Nemo Instruct 2407 | `mistralai/Mistral-Nemo-Instruct-2407` | 128K | 128K | ❌ | ❌ | ✅ | $0.05 | $0.08 |
52
54
  | Kimi K2 Instruct 0905 | `moonshotai/Kimi-K2-Instruct-0905` | 262K | 262K | ❌ | ❌ | ✅ | $0.57 | $2.30 |
53
55
  | Qwen3 Next 80B A3B Instruct | `Qwen/Qwen3-Next-80B-A3B-Instruct` | 262K | 262K | ❌ | ❌ | ✅ | $0.12 | $1.14 |
54
56
 
package/models.json CHANGED
@@ -30,9 +30,9 @@
30
30
  "image"
31
31
  ],
32
32
  "cost": {
33
- "input": 0.2,
34
- "output": 0.67,
35
- "cacheRead": 0.1,
33
+ "input": 0.21,
34
+ "output": 0.7,
35
+ "cacheRead": 0.105,
36
36
  "cacheWrite": 0
37
37
  },
38
38
  "contextWindow": 262144,
@@ -52,9 +52,9 @@
52
52
  "text"
53
53
  ],
54
54
  "cost": {
55
- "input": 1.31,
56
- "output": 4.18,
57
- "cacheRead": 0.655,
55
+ "input": 1.358,
56
+ "output": 4.268,
57
+ "cacheRead": 0.679,
58
58
  "cacheWrite": 0
59
59
  },
60
60
  "contextWindow": 262144,
@@ -97,9 +97,9 @@
97
97
  "text"
98
98
  ],
99
99
  "cost": {
100
- "input": 0.196,
101
- "output": 0.537,
102
- "cacheRead": 0.098,
100
+ "input": 0.2276,
101
+ "output": 0.7426,
102
+ "cacheRead": 0.1138,
103
103
  "cacheWrite": 0
104
104
  },
105
105
  "contextWindow": 262100,
@@ -120,9 +120,9 @@
120
120
  "image"
121
121
  ],
122
122
  "cost": {
123
- "input": 3.72,
124
- "output": 17.19,
125
- "cacheRead": 1.86,
123
+ "input": 3.098,
124
+ "output": 16.4,
125
+ "cacheRead": 1.549,
126
126
  "cacheWrite": 0
127
127
  },
128
128
  "contextWindow": 1048576,
@@ -187,9 +187,9 @@
187
187
  "image"
188
188
  ],
189
189
  "cost": {
190
- "input": 0.88124,
191
- "output": 3.81,
192
- "cacheRead": 0.44062,
190
+ "input": 1.072,
191
+ "output": 4.65,
192
+ "cacheRead": 0.536,
193
193
  "cacheWrite": 0
194
194
  },
195
195
  "contextWindow": 262144,
@@ -210,9 +210,9 @@
210
210
  "image"
211
211
  ],
212
212
  "cost": {
213
- "input": 0.1952,
214
- "output": 1.28675,
215
- "cacheRead": 0.0976,
213
+ "input": 0.1672,
214
+ "output": 1.10675,
215
+ "cacheRead": 0.0836,
216
216
  "cacheWrite": 0
217
217
  },
218
218
  "contextWindow": 262144,
@@ -234,7 +234,7 @@
234
234
  ],
235
235
  "cost": {
236
236
  "input": 0.343,
237
- "output": 2.77,
237
+ "output": 3.01,
238
238
  "cacheRead": 0.1715,
239
239
  "cacheWrite": 0
240
240
  },
@@ -255,9 +255,9 @@
255
255
  "text"
256
256
  ],
257
257
  "cost": {
258
- "input": 0.414,
259
- "output": 1.536,
260
- "cacheRead": 0.207,
258
+ "input": 0.424,
259
+ "output": 1.612,
260
+ "cacheRead": 0.212,
261
261
  "cacheWrite": 0
262
262
  },
263
263
  "contextWindow": 262100,
@@ -299,9 +299,9 @@
299
299
  "text"
300
300
  ],
301
301
  "cost": {
302
- "input": 1.694,
303
- "output": 3.3882,
304
- "cacheRead": 0.847,
302
+ "input": 1.514662,
303
+ "output": 3.029524,
304
+ "cacheRead": 0.757331,
305
305
  "cacheWrite": 0
306
306
  },
307
307
  "contextWindow": 1048576,
@@ -322,9 +322,9 @@
322
322
  "image"
323
323
  ],
324
324
  "cost": {
325
- "input": 0.7773,
326
- "output": 3.47592,
327
- "cacheRead": 0.38865,
325
+ "input": 0.8797,
326
+ "output": 3.704,
327
+ "cacheRead": 0.43985,
328
328
  "cacheWrite": 0
329
329
  },
330
330
  "contextWindow": 262142,
@@ -366,9 +366,9 @@
366
366
  "text"
367
367
  ],
368
368
  "cost": {
369
- "input": 0.359,
370
- "output": 1.44,
371
- "cacheRead": 0.1795,
369
+ "input": 0.353,
370
+ "output": 1.416,
371
+ "cacheRead": 0.1765,
372
372
  "cacheWrite": 0
373
373
  },
374
374
  "contextWindow": 196600,
@@ -433,9 +433,9 @@
433
433
  "text"
434
434
  ],
435
435
  "cost": {
436
- "input": 0.9421,
437
- "output": 1.8423,
438
- "cacheRead": 0.47105,
436
+ "input": 1.4341,
437
+ "output": 2.5143,
438
+ "cacheRead": 0.71705,
439
439
  "cacheWrite": 0.5
440
440
  },
441
441
  "contextWindow": 163840,
@@ -496,12 +496,13 @@
496
496
  "name": "Gemma 4 26B A4B",
497
497
  "reasoning": true,
498
498
  "input": [
499
- "text"
499
+ "text",
500
+ "image"
500
501
  ],
501
502
  "cost": {
502
- "input": 0.102,
503
- "output": 0.374,
504
- "cacheRead": 0.051,
503
+ "input": 0.098,
504
+ "output": 0.334,
505
+ "cacheRead": 0.049,
505
506
  "cacheWrite": 0
506
507
  },
507
508
  "contextWindow": 262142,
@@ -586,9 +587,9 @@
586
587
  "text"
587
588
  ],
588
589
  "cost": {
589
- "input": 0.168,
590
- "output": 0.66,
591
- "cacheRead": 0.084,
590
+ "input": 0.178,
591
+ "output": 0.68,
592
+ "cacheRead": 0.089,
592
593
  "cacheWrite": 0.04
593
594
  },
594
595
  "contextWindow": 131072,
@@ -716,9 +717,9 @@
716
717
  "text"
717
718
  ],
718
719
  "cost": {
719
- "input": 0.02675,
720
- "output": 0.065,
721
- "cacheRead": 0.013375,
720
+ "input": 0.0514,
721
+ "output": 0.082,
722
+ "cacheRead": 0.0257,
722
723
  "cacheWrite": 0.04
723
724
  },
724
725
  "contextWindow": 128000,
@@ -771,5 +772,50 @@
771
772
  "supportsDeveloperRole": false,
772
773
  "maxTokensField": "max_tokens"
773
774
  }
775
+ },
776
+ {
777
+ "id": "google/gemma-4-31b-it",
778
+ "name": "Gemma 4 31B Instruct",
779
+ "reasoning": true,
780
+ "input": [
781
+ "text",
782
+ "image"
783
+ ],
784
+ "cost": {
785
+ "input": 0.38,
786
+ "output": 1.15,
787
+ "cacheRead": 0.19,
788
+ "cacheWrite": 0
789
+ },
790
+ "contextWindow": 262144,
791
+ "maxTokens": 16384,
792
+ "compat": {
793
+ "supportsStore": false,
794
+ "supportsDeveloperRole": false,
795
+ "maxTokensField": "max_tokens",
796
+ "supportsReasoningEffort": true
797
+ }
798
+ },
799
+ {
800
+ "id": "nvidia/nemotron-3.5-lightning",
801
+ "name": "Nemotron 3.5 Lightning",
802
+ "reasoning": true,
803
+ "input": [
804
+ "text"
805
+ ],
806
+ "cost": {
807
+ "input": 0.07125,
808
+ "output": 0.195,
809
+ "cacheRead": 0.035625,
810
+ "cacheWrite": 0
811
+ },
812
+ "contextWindow": 262144,
813
+ "maxTokens": 131072,
814
+ "compat": {
815
+ "supportsStore": false,
816
+ "supportsDeveloperRole": false,
817
+ "maxTokensField": "max_tokens",
818
+ "supportsReasoningEffort": true
819
+ }
774
820
  }
775
821
  ]
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "pi-io-provider",
3
- "version": "1.1.39",
3
+ "version": "1.1.41",
4
4
  "description": "IO Intelligence provider extension for pi - Access DeepSeek, Kimi, GLM, Llama, Qwen, Mistral, and more through the IO Intelligence API",
5
5
  "type": "module",
6
6
  "main": "index.ts",