-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathmodelindex.py
111 lines (110 loc) · 3.84 KB
/
modelindex.py
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
model_specs = {
"gpt-4o": {
"is_local": False,
"supports_agents":True,
"is_used": True, # Add this line and set to True or False as needed
"maximum_context_length_tokens": 128000,
"maximum_output_tokens": 4096,
"friendly_name": "GPT4o",
"cost_per_token": {
"input": 0.01, # $0.01 per 1k tokens
"output": 0.03 # $0.03 per 1k tokens
}
},
"claude-3-opus-20240229": {
"is_local": False,
"supports_agents":True,
"is_used": True, # Add this line and set to True or False as needed
"maximum_context_length_tokens": 200000,
"maximum_output_tokens": 4096,
"friendly_name": "Claude",
"cost_per_token": {
"input": 0.015, # $0.015 per 1k tokens
"output": 0.075 # $0.075 per 1k tokens
}
},
"gemini-pro": {
"is_local": False,
"supports_agents":False,
"is_used": True, # Add this line and set to True or False as needed
"maximum_context_length_tokens": 128000,
"maximum_output_tokens": 2048,
"friendly_name": "Gemini",
"cost_per_token": {
"input": 0.001, # $0.001 per 1k tokens
"output": 0.002 # $0.002 per 1k tokens
}
},
"Mixtral-8x7B-Instruct-v0.1": {
"is_local": False,
"supports_agents":False,
"is_used": True, # Add this line and set to True or False as needed
"maximum_context_length_tokens": 2048,
"maximum_output_tokens": 2048,
"friendly_name": "Mixtral",
"cost_per_token": {
"input": 0.000, # $0.001 per 1k tokens
"output": 0.000 # $0.002 per 1k tokens
}
},
"Ollama: llama3": {
"is_local": True,
"supports_agents":False,
"is_used": True, # Add this line and set to True or False as needed
"maximum_context_length_tokens": 2048,
"maximum_output_tokens": 2048,
"friendly_name": "Ollama: llama3",
"cost_per_token": {
"input": 0.000, # $0.001 per 1k tokens
"output": 0.000 # $0.002 per 1k tokens
}
},
"Ollama: phi": {
"is_local": True,
"supports_agents":False,
"is_used": True, # Add this line and set to True or False as needed
"maximum_context_length_tokens": 2048,
"maximum_output_tokens": 2048,
"friendly_name": "Ollama: phi",
"cost_per_token": {
"input": 0.000, # $0.001 per 1k tokens
"output": 0.000 # $0.002 per 1k tokens
}
},
"Ollama: phi3": {
"is_local": True,
"supports_agents":False,
"is_used": True, # Add this line and set to True or False as needed
"maximum_context_length_tokens": 2048,
"maximum_output_tokens": 2048,
"friendly_name": "Ollama: phi3",
"cost_per_token": {
"input": 0.000, # $0.001 per 1k tokens
"output": 0.000 # $0.002 per 1k tokens
}
},
"OnnxDML: phi3": {
"is_local":True,
"supports_agents":False,
"is_used": True, # Add this line and set to True or False as needed,
"maximum_context_length_tokens": 2048,
"maximum_output_tokens": 2048,
"friendly_name":"OnnxDML: phi3",
"cost_per_token": {
"input": 0.000, # $0.001 per 1k tokens
"output": 0.000 # $0.002 per 1k tokens
}
},
"TorchDML: phi3": {
"is_local":True,
"supports_agents":False,
"is_used": True, # Add this line and set to True or False as needed,
"maximum_context_length_tokens": 2048,
"maximum_output_tokens": 2048,
"friendly_name":"TorchDML: phi3",
"cost_per_token": {
"input": 0.000, # $0.001 per 1k tokens
"output": 0.000 # $0.002 per 1k tokens
}
},
}