little-coder/models.json at main · L3tum/little-coder · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
{
  "providers": {
    "llamacpp": {
      "api": "openai-completions",
      "baseUrl": "https://ollama.mortimer.website",
      "apiKey": "LLAMACPP_API_KEY",
      "models": [
        {
          "id": "Qwen",
          "name": "Qwen3.6-27B (dense, local llama.cpp)",
          "reasoning": true,
          "input": ["text", "image"],
          "contextWindow": 65536,
          "maxTokens": 8192,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "Gemma-Fast",
          "name": "Gemma 12B",
          "reasoning": true,
          "input": ["text", "image"],
          "contextWindow": 65536,
          "maxTokens": 8192,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "qwen3.5-9b",
          "name": "Qwen3.5-9B (local llama.cpp)",
          "reasoning": true,
          "input": ["text"],
          "contextWindow": 32768,
          "maxTokens": 4096,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        }
      ]
    },
    "ollama": {
      "api": "openai-completions",
      "baseUrl": "http://127.0.0.1:11434/v1",
      "apiKey": "OLLAMA_API_KEY",
      "models": [
        {
          "id": "qwen3.5",
          "name": "Qwen3.5 (ollama)",
          "reasoning": true,
          "input": ["text"],
          "contextWindow": 32768,
          "maxTokens": 4096,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        }
      ]
    },
    "lmstudio": {
      "api": "openai-completions",
      "baseUrl": "http://127.0.0.1:1234/v1",
      "apiKey": "LMSTUDIO_API_KEY",
      "models": [
        {
          "id": "local-model",
          "name": "LM Studio (currently-loaded local model)",
          "reasoning": true,
          "input": ["text"],
          "contextWindow": 32768,
          "maxTokens": 4096,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        }
      ]
    }
  }
}