PlanExe/llm_config.json at main · 82deutschmark/PlanExe · 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
{
    "openrouter-paid-openai-gpt-oss-20b": {
        "comment": "This is very fast. It's paid, so check the pricing before use. Created August 5, 2025. 131,072 context. $0.05/M input tokens. $0.20/M output tokens. This is a reasoning model, and uses more tokens than LLMs.",
        "class": "OpenRouter",
        "arguments": {
            "model": "openai/gpt-oss-20b",
            "api_key": "${OPENROUTER_API_KEY}",
            "temperature": 0.1,
            "timeout": 60.0,
            "is_function_calling_model": false,
            "is_chat_model": true,
            "max_tokens": 8192,
            "max_retries": 5
        }
    },
    "openrouter-paid-gemini-2.0-flash-001": {
        "comment": "This is very fast. It's paid, so check the pricing before use. Created Feb 25, 2025. 1,048,576 context. $0.075/M input tokens. $0.30/M output tokens.",
        "priority": 1,
        "class": "OpenRouter",
        "arguments": {
            "model": "google/gemini-2.0-flash-001",
            "api_key": "${OPENROUTER_API_KEY}",
            "temperature": 0.1,
            "timeout": 60.0,
            "is_function_calling_model": false,
            "is_chat_model": true,
            "max_tokens": 8192,
            "max_retries": 5
        }
    },
    "openrouter-paid-openai-gpt-4o-mini": {
        "comment": "This is medium fast. It's paid, so check the pricing before use. Created Jul 18, 2024. 128,000 context. Starting at $0.15/M input tokens. Starting at $0.60/M output tokens.",
        "priority": 2,
        "class": "OpenRouter",
        "arguments": {
            "model": "openai/gpt-4o-mini",
            "api_key": "${OPENROUTER_API_KEY}",
            "temperature": 0.1,
            "timeout": 60.0,
            "is_function_calling_model": false,
            "is_chat_model": true,
            "max_tokens": 8192,
            "max_retries": 5
        }
    },
    "openrouter-paid-qwen3-30b-a3b": {
        "comment": "This is slow. It's paid, so check the pricing before use. Created Apr 28, 2025. 40,960 context. $0.08/M input tokens. $0.29/M output tokens.",
        "priority": 3,
        "class": "OpenRouter",
        "arguments": {
            "model": "qwen/qwen3-30b-a3b",
            "api_key": "${OPENROUTER_API_KEY}",
            "temperature": 0.1,
            "timeout": 60.0,
            "is_function_calling_model": false,
            "is_chat_model": true,
            "max_tokens": 8192,
            "max_retries": 5
        }
    },
    "ollama-llama3.1": {
        "comment": "This runs on your own computer. It's free. Requires Ollama to be installed.",
        "class": "Ollama",
        "arguments": {
            "model": "llama3.1:latest",
            "temperature": 0.5,
            "request_timeout": 120.0,
            "is_function_calling_model": false
        }
    },
    "ollama-qwen2.5-coder": {
        "comment": "This runs on your own computer. It's free. Requires Ollama to be installed.",
        "class": "Ollama",
        "arguments": {
            "model": "qwen2.5-coder:latest",
            "temperature": 0.5,
            "request_timeout": 120.0,
            "is_function_calling_model": false
        }
    },
    "lmstudio-qwen2.5-7b-instruct-1m": {
        "comment": "This runs on your own computer. It's free. Requires LM Studio to be installed. Great for inspecting the request/response.",
        "class": "LMStudio",
        "arguments": {
            "model_name": "qwen2.5-7b-instruct-1m",
            "temperature": 0.2,
            "request_timeout": 120.0,
            "is_function_calling_model": false
        }
    }
}