elph-ai 0.0.28

Unified LLM API with provider collections, auth resolution, and streaming
Documentation 
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
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127

{
    "llama-3.1-8b-instant": {
        "api": "openai-completions",
        "baseUrl": "https://api.groq.com/openai/v1",
        "contextWindow": 131072,
        "cost": {
            "cacheRead": 0,
            "cacheWrite": 0,
            "input": 0.05,
            "output": 0.08
        },
        "id": "llama-3.1-8b-instant",
        "input": ["text"],
        "maxTokens": 131072,
        "name": "Llama 3.1 8B",
        "provider": "groq",
        "reasoning": false
    },
    "llama-3.3-70b-versatile": {
        "api": "openai-completions",
        "baseUrl": "https://api.groq.com/openai/v1",
        "contextWindow": 131072,
        "cost": {
            "cacheRead": 0,
            "cacheWrite": 0,
            "input": 0.59,
            "output": 0.79
        },
        "id": "llama-3.3-70b-versatile",
        "input": ["text"],
        "maxTokens": 32768,
        "name": "Llama 3.3 70B",
        "provider": "groq",
        "reasoning": false
    },
    "meta-llama/llama-4-scout-17b-16e-instruct": {
        "api": "openai-completions",
        "baseUrl": "https://api.groq.com/openai/v1",
        "contextWindow": 131072,
        "cost": {
            "cacheRead": 0,
            "cacheWrite": 0,
            "input": 0.11,
            "output": 0.34
        },
        "id": "meta-llama/llama-4-scout-17b-16e-instruct",
        "input": ["text", "image"],
        "maxTokens": 8192,
        "name": "Llama 4 Scout 17B 16E",
        "provider": "groq",
        "reasoning": false
    },
    "openai/gpt-oss-120b": {
        "api": "openai-completions",
        "baseUrl": "https://api.groq.com/openai/v1",
        "contextWindow": 131072,
        "cost": {
            "cacheRead": 0.075,
            "cacheWrite": 0,
            "input": 0.15,
            "output": 0.6
        },
        "id": "openai/gpt-oss-120b",
        "input": ["text"],
        "maxTokens": 65536,
        "name": "GPT OSS 120B",
        "provider": "groq",
        "reasoning": true
    },
    "openai/gpt-oss-20b": {
        "api": "openai-completions",
        "baseUrl": "https://api.groq.com/openai/v1",
        "contextWindow": 131072,
        "cost": {
            "cacheRead": 0.0375,
            "cacheWrite": 0,
            "input": 0.075,
            "output": 0.3
        },
        "id": "openai/gpt-oss-20b",
        "input": ["text"],
        "maxTokens": 65536,
        "name": "GPT OSS 20B",
        "provider": "groq",
        "reasoning": true
    },
    "openai/gpt-oss-safeguard-20b": {
        "api": "openai-completions",
        "baseUrl": "https://api.groq.com/openai/v1",
        "contextWindow": 131072,
        "cost": {
            "cacheRead": 0,
            "cacheWrite": 0,
            "input": 0.075,
            "output": 0.3
        },
        "id": "openai/gpt-oss-safeguard-20b",
        "input": ["text"],
        "maxTokens": 65536,
        "name": "Safety GPT OSS 20B",
        "provider": "groq",
        "reasoning": true
    },
    "qwen/qwen3-32b": {
        "api": "openai-completions",
        "baseUrl": "https://api.groq.com/openai/v1",
        "contextWindow": 131072,
        "cost": {
            "cacheRead": 0,
            "cacheWrite": 0,
            "input": 0.29,
            "output": 0.59
        },
        "id": "qwen/qwen3-32b",
        "input": ["text"],
        "maxTokens": 40960,
        "name": "Qwen3-32B",
        "provider": "groq",
        "reasoning": true,
        "thinkingLevelMap": {
            "high": "default",
            "low": null,
            "medium": null,
            "minimal": null
        }
    }
}