superbrain-server 1.0.57 → 1.0.58

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 (5) hide show
  1. package/README.md +114 -114
  2. package/package.json +6 -3
  3. package/payload/api.py +1 -1
  4. package/payload/config/model_rankings.json +82 -82
  5. package/payload/config/openrouter_free_models.json +43 -43
package/README.md CHANGED
@@ -1,115 +1,115 @@
1
- # superbrain-server
2
-
3
- One-command installer and launcher for the SuperBrain backend.
4
-
5
- A self-hosted AI-powered second brain for Android - save Instagram posts, YouTube videos, and web pages directly from the share sheet, have them automatically analysed by AI, and rediscover them with intelligent search, collections, and smart notifications.
6
-
7
- ## Features Included in This Server
8
-
9
- - **Multi-provider AI Router**: Automatic load-balancing across Groq, Google Gemini, OpenRouter, and local Ollama.
10
- - **Background Music Identification**: Automatic detection of background tracks from Instagram Reels (powered by Shazam).
11
- - **Audio Transcription**: Groq Whisper API (cloud) with local OpenAI Whisper as an offline fallback.
12
- - **Docker Support**: Containerized, reproducible deployment ready for servers.
13
- - **Native YouTube & Web Analysis**: Scrapes and analyzes content intelligently without messy manual downloads.
14
-
15
- ## Install and Run
16
-
17
- 1. **Recommended** (No Global Install)
18
-
19
- ```bash
20
- npx -y superbrain-server@latest
21
- ```
22
-
23
- 2. **Global Install**
24
-
25
- ```bash
26
- npm install -g superbrain-server
27
- superbrain-server
28
- ```
29
-
30
- ## What It Does on First Run
31
-
32
- 1. Unpacks backend files into `~/.superbrain-server`
33
- 2. Creates an isolated Python virtual environment
34
- 3. Installs Python dependencies
35
- 4. Runs interactive setup (AI keys, optional Instagram, token)
36
- 5. Starts the backend API server
37
-
38
- ## Requirements
39
-
40
- | Dependency | Version |
41
- |------------|---------|
42
- | Node.js | 20+ |
43
- | Python | 3.10+ |
44
- | ffmpeg | latest |
45
-
46
- ## Commands
47
-
48
- ```bash
49
- # Start server
50
- superbrain-server
51
-
52
- # Show connection QR code & running server info
53
- superbrain-server status
54
-
55
- # Update the backend components
56
- superbrain-server update
57
-
58
- # Configure Ngrok tunnel
59
- superbrain-server ngrok
60
-
61
- # Open interactive reset menu
62
- superbrain-server reset
63
-
64
- # Full reset (destructive)
65
- superbrain-server reset --all
66
- ```
67
-
68
- > **Tip:** You can also run all of these via `npx -y superbrain-server@latest <command>`
69
-
70
- ## Default Runtime Location
71
-
72
- The backend is permanently installed under your user home directory:
73
-
74
- - **Windows**: `%USERPROFILE%\.superbrain-server`
75
- - **macOS / Linux**: `~/.superbrain-server`
76
-
77
- ## Connect Mobile App
78
-
79
- After the backend starts:
80
-
81
- 1. Copy the **Access Token** shown in the backend console.
82
- 2. Open the SuperBrain app **Settings**.
83
- 3. Enter your server IP/URL and the Access Token.
84
-
85
- ## Troubleshooting
86
-
87
- ### Python Not Found
88
-
89
- Install Python 3.10+ and verify:
90
-
91
- ```bash
92
- python --version
93
- ```
94
-
95
- > On Windows, `py -3 --version` should also work.
96
-
97
- ### Backend Not Reachable from Phone
98
-
99
- If you are not on the same local network, expose the local port with Ngrok:
100
-
101
- ```bash
102
- ngrok http 5000
103
- ```
104
-
105
- Use the generated HTTPS URL in the app's Settings.
106
-
107
- ## Links
108
-
109
- - **GitHub Repository**: [sidinsearch/superbrain](https://github.com/sidinsearch/superbrain)
110
- - **Main Project Docs**: [README](https://github.com/sidinsearch/superbrain#readme)
111
- - **NPM Package**: [superbrain-server](https://www.npmjs.com/package/superbrain-server)
112
-
113
- ## License
114
-
1
+ # superbrain-server
2
+
3
+ One-command installer and launcher for the SuperBrain backend.
4
+
5
+ A self-hosted AI-powered second brain for Android - save Instagram posts, YouTube videos, and web pages directly from the share sheet, have them automatically analysed by AI, and rediscover them with intelligent search, collections, and smart notifications.
6
+
7
+ ## Features Included in This Server
8
+
9
+ - **Multi-provider AI Router**: Automatic load-balancing across Groq, Google Gemini, OpenRouter, and local Ollama.
10
+ - **Background Music Identification**: Automatic detection of background tracks from Instagram Reels (powered by Shazam).
11
+ - **Audio Transcription**: Groq Whisper API (cloud) with local OpenAI Whisper as an offline fallback.
12
+ - **Docker Support**: Containerized, reproducible deployment ready for servers.
13
+ - **Native YouTube & Web Analysis**: Scrapes and analyzes content intelligently without messy manual downloads.
14
+
15
+ ## Install and Run
16
+
17
+ 1. **Recommended** (No Global Install)
18
+
19
+ ```bash
20
+ npx -y superbrain-server@latest
21
+ ```
22
+
23
+ 2. **Global Install**
24
+
25
+ ```bash
26
+ npm install -g superbrain-server
27
+ superbrain-server
28
+ ```
29
+
30
+ ## What It Does on First Run
31
+
32
+ 1. Unpacks backend files into `~/.superbrain-server`
33
+ 2. Creates an isolated Python virtual environment
34
+ 3. Installs Python dependencies
35
+ 4. Runs interactive setup (AI keys, optional Instagram, token)
36
+ 5. Starts the backend API server
37
+
38
+ ## Requirements
39
+
40
+ | Dependency | Version |
41
+ |------------|---------|
42
+ | Node.js | 20+ |
43
+ | Python | 3.10+ |
44
+ | ffmpeg | latest |
45
+
46
+ ## Commands
47
+
48
+ ```bash
49
+ # Start server
50
+ superbrain-server
51
+
52
+ # Show connection QR code & running server info
53
+ superbrain-server status
54
+
55
+ # Update the backend components
56
+ superbrain-server update
57
+
58
+ # Configure Ngrok tunnel
59
+ superbrain-server ngrok
60
+
61
+ # Open interactive reset menu
62
+ superbrain-server reset
63
+
64
+ # Full reset (destructive)
65
+ superbrain-server reset --all
66
+ ```
67
+
68
+ > **Tip:** You can also run all of these via `npx -y superbrain-server@latest <command>`
69
+
70
+ ## Default Runtime Location
71
+
72
+ The backend is permanently installed under your user home directory:
73
+
74
+ - **Windows**: `%USERPROFILE%\.superbrain-server`
75
+ - **macOS / Linux**: `~/.superbrain-server`
76
+
77
+ ## Connect Mobile App
78
+
79
+ After the backend starts:
80
+
81
+ 1. Copy the **Access Token** shown in the backend console.
82
+ 2. Open the SuperBrain app **Settings**.
83
+ 3. Enter your server IP/URL and the Access Token.
84
+
85
+ ## Troubleshooting
86
+
87
+ ### Python Not Found
88
+
89
+ Install Python 3.10+ and verify:
90
+
91
+ ```bash
92
+ python --version
93
+ ```
94
+
95
+ > On Windows, `py -3 --version` should also work.
96
+
97
+ ### Backend Not Reachable from Phone
98
+
99
+ If you are not on the same local network, expose the local port with Ngrok:
100
+
101
+ ```bash
102
+ ngrok http 5000
103
+ ```
104
+
105
+ Use the generated HTTPS URL in the app's Settings.
106
+
107
+ ## Links
108
+
109
+ - **GitHub Repository**: [sidinsearch/superbrain](https://github.com/sidinsearch/superbrain)
110
+ - **Main Project Docs**: [README](https://github.com/sidinsearch/superbrain#readme)
111
+ - **NPM Package**: [superbrain-server](https://www.npmjs.com/package/superbrain-server)
112
+
113
+ ## License
114
+
115
115
  MIT (CLI wrapper)
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "superbrain-server",
3
- "version": "1.0.57",
3
+ "version": "1.0.58",
4
4
  "description": "1-Line Auto-Installer and Server Execution wrapper for SuperBrain",
5
5
  "main": "index.js",
6
6
  "bin": {
@@ -17,9 +17,12 @@
17
17
  "homepage": "https://github.com/sidinsearch/superbrain#readme",
18
18
  "author": "sidinsearch",
19
19
  "license": "MIT",
20
- "dependencies": {},
21
20
  "files": [
22
21
  "bin/",
23
22
  "payload/"
24
- ]
23
+ ],
24
+ "publishConfig": {
25
+ "registry": "https://registry.npmjs.org/",
26
+ "access": "public"
27
+ }
25
28
  }
package/payload/api.py CHANGED
@@ -726,7 +726,7 @@ async def check_cache(shortcode: str, token: str = Depends(verify_token)):
726
726
 
727
727
 
728
728
  @app.get("/recent")
729
- async def get_recent_analyses(limit: int = Query(default=10, ge=1, le=100), token: str = Depends(verify_token)):
729
+ async def get_recent_analyses(limit: int = Query(default=50, ge=1, le=1000), token: str = Depends(verify_token)):
730
730
  """
731
731
  Get recent analyses from database
732
732
 
package/payload/config/model_rankings.json CHANGED
@@ -1,52 +1,52 @@
1
1
  {
2
2
  "groq_gpt_oss_20b": {
3
3
  "key": "groq_gpt_oss_20b",
4
- "avg_response_s": 1.5213420135082059,
5
- "success_count": 85,
6
- "fail_count": 6,
7
- "down_until": null,
8
- "last_used": "2026-04-10T06:49:02.416228",
9
- "last_error": null,
4
+ "avg_response_s": 2.1030592078849115,
5
+ "success_count": 311,
6
+ "fail_count": 9,
7
+ "down_until": "2026-04-12T09:18:56.258250",
8
+ "last_used": "2026-04-12T08:48:46.365989",
9
+ "last_error": "Error code: 429 - {'error': {'message': 'Rate limit reached for model `openai/gpt-oss-20b` in organization `org_01jrmafjknfc8tmcz6f2zka3q2` service tier `on_demand` on tokens per day (TPD): Limit 2000",
10
10
  "base_priority": 0.5
11
11
  },
12
12
  "groq_llama33_70b": {
13
13
  "key": "groq_llama33_70b",
14
- "avg_response_s": 1.423364281654358,
15
- "success_count": 2,
16
- "fail_count": 5,
17
- "down_until": "2026-04-09T12:01:26.317058",
18
- "last_used": "2026-02-24T07:53:30.927446",
19
- "last_error": "No module named 'groq'",
14
+ "avg_response_s": 14.10594888995464,
15
+ "success_count": 131,
16
+ "fail_count": 6,
17
+ "down_until": null,
18
+ "last_used": "2026-04-12T08:37:54.068541",
19
+ "last_error": null,
20
20
  "base_priority": 1
21
21
  },
22
22
  "groq_llama4_scout": {
23
23
  "key": "groq_llama4_scout",
24
- "avg_response_s": null,
25
- "success_count": 0,
24
+ "avg_response_s": 11.992687265344381,
25
+ "success_count": 7,
26
26
  "fail_count": 5,
27
- "down_until": "2026-04-09T12:01:26.318058",
28
- "last_used": null,
29
- "last_error": "No module named 'groq'",
27
+ "down_until": null,
28
+ "last_used": "2026-04-12T08:08:47.469811",
29
+ "last_error": null,
30
30
  "base_priority": 1.5
31
31
  },
32
32
  "groq_llama31_8b": {
33
33
  "key": "groq_llama31_8b",
34
- "avg_response_s": null,
35
- "success_count": 0,
34
+ "avg_response_s": 1.9519281985067138,
35
+ "success_count": 347,
36
36
  "fail_count": 5,
37
- "down_until": "2026-04-09T12:01:26.319563",
38
- "last_used": null,
39
- "last_error": "No module named 'groq'",
37
+ "down_until": null,
38
+ "last_used": "2026-04-12T09:01:50.290420",
39
+ "last_error": null,
40
40
  "base_priority": 2
41
41
  },
42
42
  "groq_qwen3_32b": {
43
43
  "key": "groq_qwen3_32b",
44
- "avg_response_s": null,
45
- "success_count": 0,
44
+ "avg_response_s": 3.935154914855957,
45
+ "success_count": 1,
46
46
  "fail_count": 5,
47
- "down_until": "2026-04-09T12:01:26.320569",
48
- "last_used": null,
49
- "last_error": "No module named 'groq'",
47
+ "down_until": null,
48
+ "last_used": "2026-04-12T08:16:41.617443",
49
+ "last_error": null,
50
50
  "base_priority": 2.5
51
51
  },
52
52
  "groq_gpt_oss_120b": {
@@ -313,18 +313,18 @@
313
313
  "key": "gemini_25_flash_vision",
314
314
  "avg_response_s": 15.284299373626709,
315
315
  "success_count": 1,
316
- "fail_count": 6,
317
- "down_until": "2026-04-09T12:01:25.986949",
316
+ "fail_count": 32,
317
+ "down_until": "2026-04-12T09:01:55.494866",
318
318
  "last_used": "2026-02-24T06:25:56.490384",
319
- "last_error": "No module named 'google'",
319
+ "last_error": "No module named 'google.generativeai'",
320
320
  "base_priority": 1
321
321
  },
322
322
  "gemini_25_flash_lite_vision": {
323
323
  "key": "gemini_25_flash_lite_vision",
324
324
  "avg_response_s": 6.709401964075168,
325
325
  "success_count": 14,
326
- "fail_count": 25,
327
- "down_until": "2026-04-09T18:29:31.449579",
326
+ "fail_count": 53,
327
+ "down_until": "2026-04-12T09:03:49.079253",
328
328
  "last_used": "2026-02-24T09:45:09.831171",
329
329
  "last_error": "No module named 'google.generativeai'",
330
330
  "base_priority": 1.5
@@ -333,8 +333,8 @@
333
333
  "key": "gemini_25_pro_vision",
334
334
  "avg_response_s": null,
335
335
  "success_count": 0,
336
- "fail_count": 28,
337
- "down_until": "2026-04-09T18:29:31.445576",
336
+ "fail_count": 56,
337
+ "down_until": "2026-04-12T09:03:49.075655",
338
338
  "last_used": null,
339
339
  "last_error": "No module named 'google.generativeai'",
340
340
  "base_priority": 2
@@ -343,18 +343,18 @@
343
343
  "key": "gemini_3_flash_vision",
344
344
  "avg_response_s": 22.28640604019165,
345
345
  "success_count": 1,
346
- "fail_count": 6,
347
- "down_until": "2026-04-09T12:01:25.991504",
346
+ "fail_count": 29,
347
+ "down_until": "2026-04-12T09:01:59.727849",
348
348
  "last_used": "2026-02-24T07:50:22.906246",
349
- "last_error": "No module named 'google'",
349
+ "last_error": "No module named 'google.generativeai'",
350
350
  "base_priority": 2.5
351
351
  },
352
352
  "gemini_3_pro_vision": {
353
353
  "key": "gemini_3_pro_vision",
354
354
  "avg_response_s": null,
355
355
  "success_count": 0,
356
- "fail_count": 27,
357
- "down_until": "2026-04-09T18:29:31.447577",
356
+ "fail_count": 55,
357
+ "down_until": "2026-04-12T09:03:49.077691",
358
358
  "last_used": null,
359
359
  "last_error": "No module named 'google.generativeai'",
360
360
  "base_priority": 3
@@ -363,8 +363,8 @@
363
363
  "key": "gemini_31_pro_vision",
364
364
  "avg_response_s": null,
365
365
  "success_count": 0,
366
- "fail_count": 26,
367
- "down_until": "2026-04-09T18:29:31.450615",
366
+ "fail_count": 54,
367
+ "down_until": "2026-04-12T09:03:49.080628",
368
368
  "last_used": null,
369
369
  "last_error": "No module named 'google.generativeai'",
370
370
  "base_priority": 3.5
@@ -373,8 +373,8 @@
373
373
  "key": "gemini_20_flash_vision",
374
374
  "avg_response_s": null,
375
375
  "success_count": 0,
376
- "fail_count": 25,
377
- "down_until": "2026-04-09T18:29:31.451578",
376
+ "fail_count": 53,
377
+ "down_until": "2026-04-12T09:03:49.081592",
378
378
  "last_used": null,
379
379
  "last_error": "No module named 'google.generativeai'",
380
380
  "base_priority": 4
@@ -383,8 +383,8 @@
383
383
  "key": "gemini_20_flash_lite_vision",
384
384
  "avg_response_s": null,
385
385
  "success_count": 0,
386
- "fail_count": 25,
387
- "down_until": "2026-04-09T18:29:31.453083",
386
+ "fail_count": 53,
387
+ "down_until": "2026-04-12T09:03:49.082631",
388
388
  "last_used": null,
389
389
  "last_error": "No module named 'google.generativeai'",
390
390
  "base_priority": 4.5
@@ -393,98 +393,98 @@
393
393
  "key": "gemini_15_flash_vision",
394
394
  "avg_response_s": null,
395
395
  "success_count": 0,
396
- "fail_count": 25,
397
- "down_until": "2026-04-09T18:29:31.455139",
396
+ "fail_count": 53,
397
+ "down_until": "2026-04-12T09:03:49.084633",
398
398
  "last_used": null,
399
399
  "last_error": "No module named 'google.generativeai'",
400
400
  "base_priority": 4.8
401
401
  },
402
402
  "groq_llama4_scout_vision": {
403
403
  "key": "groq_llama4_scout_vision",
404
- "avg_response_s": 1.528297446591561,
405
- "success_count": 56,
406
- "fail_count": 5,
407
- "down_until": null,
408
- "last_used": "2026-04-09T18:25:54.184988",
409
- "last_error": null,
404
+ "avg_response_s": 2.0650597900565066,
405
+ "success_count": 217,
406
+ "fail_count": 10,
407
+ "down_until": "2026-04-12T09:13:17.959244",
408
+ "last_used": "2026-04-12T08:42:56.472897",
409
+ "last_error": "Error code: 429 - {'error': {'message': 'Rate limit reached for model `meta-llama/llama-4-scout-17b-16e-instruct` in organization `org_01jrmafjknfc8tmcz6f2zka3q2` service tier `on_demand` on tokens pe",
410
410
  "base_priority": 5
411
411
  },
412
412
  "groq_vision_11b": {
413
413
  "key": "groq_vision_11b",
414
414
  "avg_response_s": null,
415
415
  "success_count": 0,
416
- "fail_count": 5,
417
- "down_until": "2026-04-09T12:01:25.989247",
416
+ "fail_count": 31,
417
+ "down_until": "2026-04-12T09:01:56.480971",
418
418
  "last_used": null,
419
- "last_error": "No module named 'groq'",
419
+ "last_error": "Error code: 400 - {'error': {'message': 'The model `llama-3.2-11b-vision-preview` has been decommissioned and is no longer supported. Please refer to https://console.groq.com/docs/deprecations for a r",
420
420
  "base_priority": 5.5
421
421
  },
422
422
  "groq_vision_90b": {
423
423
  "key": "groq_vision_90b",
424
424
  "avg_response_s": null,
425
425
  "success_count": 0,
426
- "fail_count": 5,
427
- "down_until": "2026-04-09T12:01:25.989247",
426
+ "fail_count": 31,
427
+ "down_until": "2026-04-12T09:01:57.040649",
428
428
  "last_used": null,
429
- "last_error": "No module named 'groq'",
429
+ "last_error": "Error code: 400 - {'error': {'message': 'The model `llama-3.2-90b-vision-preview` has been decommissioned and is no longer supported. Please refer to https://console.groq.com/docs/deprecations for a r",
430
430
  "base_priority": 6
431
431
  },
432
432
  "openrouter_qwen3_vl_235b": {
433
433
  "key": "openrouter_qwen3_vl_235b",
434
434
  "avg_response_s": null,
435
435
  "success_count": 0,
436
- "fail_count": 0,
437
- "down_until": null,
436
+ "fail_count": 23,
437
+ "down_until": "2026-04-12T09:01:58.155413",
438
438
  "last_used": null,
439
- "last_error": null,
439
+ "last_error": "404 Client Error: Not Found for url: https://openrouter.ai/api/v1/chat/completions",
440
440
  "base_priority": 7
441
441
  },
442
442
  "openrouter_qwen3_vl_30b": {
443
443
  "key": "openrouter_qwen3_vl_30b",
444
444
  "avg_response_s": null,
445
445
  "success_count": 0,
446
- "fail_count": 0,
447
- "down_until": null,
446
+ "fail_count": 23,
447
+ "down_until": "2026-04-12T09:01:59.065255",
448
448
  "last_used": null,
449
- "last_error": null,
449
+ "last_error": "404 Client Error: Not Found for url: https://openrouter.ai/api/v1/chat/completions",
450
450
  "base_priority": 7.5
451
451
  },
452
452
  "openrouter_nvidia_vl": {
453
453
  "key": "openrouter_nvidia_vl",
454
- "avg_response_s": null,
455
- "success_count": 0,
456
- "fail_count": 0,
457
- "down_until": null,
458
- "last_used": null,
459
- "last_error": null,
454
+ "avg_response_s": 18.168677418730027,
455
+ "success_count": 64,
456
+ "fail_count": 5,
457
+ "down_until": "2026-04-12T09:17:10.589764",
458
+ "last_used": "2026-04-12T07:46:28.394605",
459
+ "last_error": "429 rate limit: {\"error\":{\"message\":\"Rate limit exceeded: free-models-per-day. Add 10 credits to unlock 1000 free model requests per day\",\"code\":429,\"metadata\":{\"headers\":{\"X-RateLimit-Limit\":\"50\",\"X-",
460
460
  "base_priority": 8
461
461
  },
462
462
  "openrouter_gemma3_vision": {
463
463
  "key": "openrouter_gemma3_vision",
464
- "avg_response_s": null,
465
- "success_count": 0,
466
- "fail_count": 0,
467
- "down_until": null,
468
- "last_used": null,
469
- "last_error": null,
464
+ "avg_response_s": 7.945096383094787,
465
+ "success_count": 3,
466
+ "fail_count": 5,
467
+ "down_until": "2026-04-12T09:13:59.767520",
468
+ "last_used": "2026-04-12T07:43:40.487825",
469
+ "last_error": "429 rate limit: {\"error\":{\"message\":\"Rate limit exceeded: free-models-per-day. Add 10 credits to unlock 1000 free model requests per day\",\"code\":429,\"metadata\":{\"headers\":{\"X-RateLimit-Limit\":\"50\",\"X-",
470
470
  "base_priority": 8.5
471
471
  },
472
472
  "openrouter_mistral_vision": {
473
473
  "key": "openrouter_mistral_vision",
474
474
  "avg_response_s": null,
475
475
  "success_count": 0,
476
- "fail_count": 0,
477
- "down_until": null,
476
+ "fail_count": 23,
477
+ "down_until": "2026-04-12T09:01:59.725111",
478
478
  "last_used": null,
479
- "last_error": null,
479
+ "last_error": "404 Client Error: Not Found for url: https://openrouter.ai/api/v1/chat/completions",
480
480
  "base_priority": 9
481
481
  },
482
482
  "local_qwen3_vl": {
483
483
  "key": "local_qwen3_vl",
484
484
  "avg_response_s": null,
485
485
  "success_count": 0,
486
- "fail_count": 6,
487
- "down_until": "2026-04-09T12:01:25.992508",
486
+ "fail_count": 23,
487
+ "down_until": "2026-04-12T09:04:18.457834",
488
488
  "last_used": null,
489
489
  "last_error": "No module named 'ollama'",
490
490
  "base_priority": 100
package/payload/config/openrouter_free_models.json CHANGED
@@ -1,5 +1,5 @@
1
1
  {
2
- "cached_at": "2026-04-10T06:49:01.068927",
2
+ "cached_at": "2026-04-12T07:04:19.623841",
3
3
  "models": [
4
4
  {
5
5
  "id": "google/lyria-3-pro-preview",
@@ -982,99 +982,99 @@
982
982
  }
983
983
  },
984
984
  {
985
- "id": "cognitivecomputations/dolphin-mistral-24b-venice-edition:free",
986
- "canonical_slug": "venice/uncensored",
987
- "hugging_face_id": "cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition",
988
- "name": "Venice: Uncensored (free)",
989
- "created": 1752094966,
990
- "description": "Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an \u201cuncensored\u201d instruct-tuned LLM, preserving...",
991
- "context_length": 32768,
985
+ "id": "google/gemma-3-27b-it:free",
986
+ "canonical_slug": "google/gemma-3-27b-it",
987
+ "hugging_face_id": "google/gemma-3-27b-it",
988
+ "name": "Google: Gemma 3 27B (free)",
989
+ "created": 1741756359,
990
+ "description": "Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...",
991
+ "context_length": 131072,
992
992
  "architecture": {
993
- "modality": "text->text",
993
+ "modality": "text+image->text",
994
994
  "input_modalities": [
995
- "text"
995
+ "text",
996
+ "image"
996
997
  ],
997
998
  "output_modalities": [
998
999
  "text"
999
1000
  ],
1000
- "tokenizer": "Other",
1001
- "instruct_type": null
1001
+ "tokenizer": "Gemini",
1002
+ "instruct_type": "gemma"
1002
1003
  },
1003
1004
  "pricing": {
1004
1005
  "prompt": "0",
1005
1006
  "completion": "0"
1006
1007
  },
1007
1008
  "top_provider": {
1008
- "context_length": 32768,
1009
- "max_completion_tokens": null,
1009
+ "context_length": 131072,
1010
+ "max_completion_tokens": 8192,
1010
1011
  "is_moderated": false
1011
1012
  },
1012
1013
  "per_request_limits": null,
1013
1014
  "supported_parameters": [
1014
- "frequency_penalty",
1015
1015
  "max_tokens",
1016
- "presence_penalty",
1017
1016
  "response_format",
1017
+ "seed",
1018
1018
  "stop",
1019
- "structured_outputs",
1020
1019
  "temperature",
1021
- "top_k",
1022
1020
  "top_p"
1023
1021
  ],
1024
- "default_parameters": {},
1025
- "knowledge_cutoff": "2024-04-30",
1022
+ "default_parameters": {
1023
+ "temperature": null,
1024
+ "top_p": null,
1025
+ "frequency_penalty": null
1026
+ },
1027
+ "knowledge_cutoff": "2024-08-31",
1026
1028
  "expiration_date": null,
1027
1029
  "links": {
1028
- "details": "/api/v1/models/venice/uncensored/endpoints"
1030
+ "details": "/api/v1/models/google/gemma-3-27b-it/endpoints"
1029
1031
  }
1030
1032
  },
1031
1033
  {
1032
- "id": "google/gemma-3-27b-it:free",
1033
- "canonical_slug": "google/gemma-3-27b-it",
1034
- "hugging_face_id": "google/gemma-3-27b-it",
1035
- "name": "Google: Gemma 3 27B (free)",
1036
- "created": 1741756359,
1037
- "description": "Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...",
1038
- "context_length": 131072,
1034
+ "id": "cognitivecomputations/dolphin-mistral-24b-venice-edition:free",
1035
+ "canonical_slug": "venice/uncensored",
1036
+ "hugging_face_id": "cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition",
1037
+ "name": "Venice: Uncensored (free)",
1038
+ "created": 1752094966,
1039
+ "description": "Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an \u201cuncensored\u201d instruct-tuned LLM, preserving...",
1040
+ "context_length": 32768,
1039
1041
  "architecture": {
1040
- "modality": "text+image->text",
1042
+ "modality": "text->text",
1041
1043
  "input_modalities": [
1042
- "text",
1043
- "image"
1044
+ "text"
1044
1045
  ],
1045
1046
  "output_modalities": [
1046
1047
  "text"
1047
1048
  ],
1048
- "tokenizer": "Gemini",
1049
- "instruct_type": "gemma"
1049
+ "tokenizer": "Other",
1050
+ "instruct_type": null
1050
1051
  },
1051
1052
  "pricing": {
1052
1053
  "prompt": "0",
1053
1054
  "completion": "0"
1054
1055
  },
1055
1056
  "top_provider": {
1056
- "context_length": 131072,
1057
- "max_completion_tokens": 8192,
1057
+ "context_length": 32768,
1058
+ "max_completion_tokens": null,
1058
1059
  "is_moderated": false
1059
1060
  },
1060
1061
  "per_request_limits": null,
1061
1062
  "supported_parameters": [
1063
+ "frequency_penalty",
1062
1064
  "max_tokens",
1065
+ "presence_penalty",
1063
1066
  "response_format",
1064
- "seed",
1065
1067
  "stop",
1068
+ "structured_outputs",
1066
1069
  "temperature",
1070
+ "top_k",
1067
1071
  "top_p"
1068
1072
  ],
1069
- "default_parameters": {
1070
- "temperature": null,
1071
- "top_p": null,
1072
- "frequency_penalty": null
1073
- },
1074
- "knowledge_cutoff": "2024-08-31",
1073
+ "default_parameters": {},
1074
+ "knowledge_cutoff": "2024-04-30",
1075
1075
  "expiration_date": null,
1076
1076
  "links": {
1077
- "details": "/api/v1/models/google/gemma-3-27b-it/endpoints"
1077
+ "details": "/api/v1/models/venice/uncensored/endpoints"
1078
1078
  }
1079
1079
  },
1080
1080
  {