code-assistant/models.example.json at main · stippi/code-assistant · 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
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
{
  "Claude Sonnet 4.5": {
    "provider": "anthropic-main",
    "id": "claude-sonnet-4-5",
    "context_token_limit": 200000,
    "config": {
      "max_tokens": 32768,
      "thinking": {
        "type": "enabled",
        "budget_tokens": 8192
      }
    }
  },
  "GPT-5-Codex (low)": {
    "provider": "openai-responses",
    "id": "gpt-5-codex",
    "context_token_limit": 128000,
    "config": {
      "temperature": 0.7,
      "reasoning": {
        "effort": "low",
        "summary": "detailed"
      }
    }
  },
  "GPT-5-Codex (medium)": {
    "provider": "openai-responses",
    "id": "gpt-5-codex",
    "context_token_limit": 128000,
    "config": {
      "temperature": 0.7,
      "reasoning": {
        "effort": "medium",
        "summary": "detailed"
      }
    }
  },
  "GPT-4.1": {
    "provider": "openai-main",
    "id": "gpt-4.1",
    "context_token_limit": 128000,
    "config": {
      "temperature": 0.8,
      "max_tokens": 4096
    }
  },
  "Llama 3.2 8B": {
    "provider": "ollama-local",
    "id": "llama3.3:8b",
    "context_token_limit": 16384,
    "config": {
      "options": {
        "num_ctx": 16384,
        "temperature": 0.8
      }
    }
  },
  "Qwen 3 Coder 480B": {
    "provider": "groq-main",
    "id": "qwen-3-coder-480b",
    "context_token_limit": 32768,
    "config": {
      "temperature": 0.7,
      "top_p": 0.8
    }
  },
  "Moonshot Kimi K2": {
    "provider": "groq-main",
    "id": "moonshotai/kimi-k2-instruct",
    "context_token_limit": 32768,
    "config": {
      "temperature": 0.6
    }
  },
  "Cerebras GPT OSS 120B": {
    "provider": "cerebras-main",
    "id": "gpt-oss-120b",
    "context_token_limit": 16384,
    "config": {
      "temperature": 0.7
    }
  },
  "Mistral Devstral Medium": {
    "provider": "mistral-main",
    "id": "devstral-medium-2507",
    "context_token_limit": 200000,
    "config": {
      "temperature": 0.7
    }
  },
  "Gemini 2.5 Pro": {
    "provider": "vertex-main",
    "id": "gemini-2.5-pro-preview-06-05",
    "context_token_limit": 200000,
    "config": {
      "generation_config": {
        "temperature": 0.8
      }
    }
  },
  "AI Core Claude Sonnet 4": {
    "provider": "ai-core-dev",
    "id": "claude-sonnet-4",
    "context_token_limit": 200000,
    "config": {}
  }
}