forked from BerriAI/litellm
-
Notifications
You must be signed in to change notification settings - Fork 0
/
model_prices_and_context_window.json
166 lines (166 loc) · 4.71 KB
/
model_prices_and_context_window.json
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
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
{
"gpt-4": {
"max_tokens": 8192,
"input_cost_per_token": 0.00003,
"output_cost_per_token": 0.00006
},
"gpt-4-0314": {
"max_tokens": 8192,
"input_cost_per_token": 0.00003,
"output_cost_per_token": 0.00006
},
"gpt-4-0613": {
"max_tokens": 8192,
"input_cost_per_token": 0.00003,
"output_cost_per_token": 0.00006
},
"gpt-4-32k": {
"max_tokens": 32768,
"input_cost_per_token": 0.00006,
"output_cost_per_token": 0.00012
},
"gpt-4-32k-0314": {
"max_tokens": 32768,
"input_cost_per_token": 0.00006,
"output_cost_per_token": 0.00012
},
"gpt-4-32k-0613": {
"max_tokens": 32768,
"input_cost_per_token": 0.00006,
"output_cost_per_token": 0.00012
},
"gpt-3.5-turbo": {
"max_tokens": 4097,
"input_cost_per_token": 0.0000015,
"output_cost_per_token": 0.000002
},
"gpt-3.5-turbo-0301": {
"max_tokens": 4097,
"input_cost_per_token": 0.0000015,
"output_cost_per_token": 0.000002
},
"gpt-3.5-turbo-0613": {
"max_tokens": 4097,
"input_cost_per_token": 0.0000015,
"output_cost_per_token": 0.000002
},
"gpt-3.5-turbo-16k": {
"max_tokens": 16385,
"input_cost_per_token": 0.000003,
"output_cost_per_token": 0.000004
},
"gpt-3.5-turbo-16k-0613": {
"max_tokens": 16385,
"input_cost_per_token": 0.000003,
"output_cost_per_token": 0.000004
},
"gpt-3.5-turbo-instruct": {
"max_tokens": 8192,
"input_cost_per_token": 0.0000015,
"output_cost_per_token": 0.000002
},
"text-ada-001": {
"max_tokens": 2049,
"input_cost_per_token": 0.0000004,
"output_cost_per_token": 0.0000004
},
"text-babbage-001": {
"max_tokens": 2049,
"input_cost_per_token": 0.0000005,
"output_cost_per_token": 0.0000005
},
"text-curie-001": {
"max_tokens": 2049,
"input_cost_per_token": 0.000002,
"output_cost_per_token": 0.000002
},
"text-davinci-002": {
"max_tokens": 4097,
"input_cost_per_token": 0.00002,
"output_cost_per_token": 0.00002
},
"text-davinci-003": {
"max_tokens": 4097,
"input_cost_per_token": 0.00002,
"output_cost_per_token": 0.00002
},
"command-nightly": {
"max_tokens": 4096,
"input_cost_per_token": 0.000015,
"output_cost_per_token": 0.000015
},
"command": {
"max_tokens": 4096,
"input_cost_per_token": 0.000015,
"output_cost_per_token": 0.000015
},
"command-light": {
"max_tokens": 4096,
"input_cost_per_token": 0.000015,
"output_cost_per_token": 0.000015
},
"command-medium-beta": {
"max_tokens": 4096,
"input_cost_per_token": 0.000015,
"output_cost_per_token": 0.000015
},
"command-xlarge-beta": {
"max_tokens": 4096,
"input_cost_per_token": 0.000015,
"output_cost_per_token": 0.000015
},
"claude-instant-1": {
"max_tokens": 100000,
"input_cost_per_token": 0.00000163,
"output_cost_per_token": 0.00000551
},
"claude-instant-1.2": {
"max_tokens": 100000,
"input_cost_per_token": 0.00000163,
"output_cost_per_token": 0.00000551
},
"claude-2": {
"max_tokens": 100000,
"input_cost_per_token": 0.00001102,
"output_cost_per_token": 0.00003268
},
"text-bison-001": {
"max_tokens": 8192,
"input_cost_per_token": 0.000004,
"output_cost_per_token": 0.000004
},
"chat-bison-001": {
"max_tokens": 4096,
"input_cost_per_token": 0.000002,
"output_cost_per_token": 0.000002
},
"replicate/llama-2-70b-chat:2c1608e18606fad2812020dc541930f2d0495ce32eee50074220b87300bc16e1": {
"max_tokens": 4096
},
"together-ai-up-to-3b": {
"input_cost_per_token": 0.0000001,
"output_cost_per_token": 0.0000001
},
"together-ai-3.1b-7b": {
"input_cost_per_token": 0.0000002,
"output_cost_per_token": 0.0000002
},
"together-ai-7.1b-20b": {
"max_tokens": 1000,
"input_cost_per_token": 0.0000004,
"output_cost_per_token": 0.0000004
},
"together-ai-20.1b-40b": {
"input_cost_per_token": 0.000001,
"output_cost_per_token": 0.000001
},
"together-ai-40.1b-70b": {
"input_cost_per_token": 0.000003,
"output_cost_per_token": 0.000003
},
"text-embedding-ada-002": {
"max_tokens": 8191,
"input_cost_per_token": 0.0000004,
"output_cost_per_token": 0.0000004
}
}