-
Notifications
You must be signed in to change notification settings - Fork 3
/
models.json
244 lines (244 loc) · 10.5 KB
/
models.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
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
{
"GPT":
{
"gpt-4o-mini":
{
"label": "Our affordable and intelligent small model for fast, lightweight tasks. GPT-4o mini is cheaper and more capable than GPT-3.5 Turbo. Currently points to gpt-4o-mini-2024-07-18.",
"max_token": 16384,
"context_token": 128000,
"data": "Up to Oct 2023 (as of 20240718)",
"status": "active",
"status_details": "",
"capability": "vision"
},
"gpt-4o-mini-2024-07-18":
{
"label": "Our affordable and intelligent small model for fast, lightweight tasks. GPT-4o mini is cheaper and more capable than GPT-3.5 Turbo.",
"max_token": 16384,
"context_token": 128000,
"data": "Up to Oct 2023 (as of 20240718)",
"status": "active",
"status_details": "",
"capability": "vision"
},
"gpt-4o":
{
"label": "Our high-intelligence flagship model for complex, multi-step tasks. GPT-4o is cheaper and faster than GPT-4 Turbo. Currently points to gpt-4o-2024-08-06.",
"max_token": 16384,
"context_token": 128000,
"data": "Up to Oct 2023 (as of 20240806)",
"status": "active",
"status_details": "",
"capability": "vision"
},
"gpt-4o-2024-08-06":
{
"label": "Latest snapshot that supports Structured Outputs. gpt-4o currently points to this version.",
"max_token": 16384,
"context_token": 128000,
"data": "Up to Oct 2023 (as of 20240806)",
"status": "active",
"status_details": "",
"capability": "vision"
},
"gpt-4o-2024-05-13":
{
"label": "Original gpt-4o snapshot from May 13, 2024.",
"max_token": 4096,
"context_token": 128000,
"data": "Up to Oct 2023 (as of 20240718)",
"status": "active",
"status_details": "",
"capability": "vision"
},
"o1-preview":
{
"label": "o1 series of large language models are trained with reinforcement learning to perform complex reasoning. o1 models think before they answer, producing a long internal chain of thought before responding to the user. o1-preview: reasoning model designed to solve hard problems across domains. Points to the most recent snapshot of the o1 model: o1-preview-2024-09-12",
"max_token": 32768,
"context_token": 128000,
"data": "Up to Oct 2023 (as of 20240912)",
"status": "active",
"status_details": "",
"capability": "vision"
},
"o1-mini":
{
"label": "o1 series of large language models are trained with reinforcement learning to perform complex reasoning. o1 models think before they answer, producing a long internal chain of thought before responding to the user. o1-mini: faster and cheaper reasoning model particularly good at coding, math, and science. Points to the most recent o1-mini snapshot: o1-mini-2024-09-12",
"max_token": 65536,
"context_token": 128000,
"data": "Up to Oct 2023 (as of 20240912)",
"status": "active",
"status_details": "",
"capability": "vision"
},
"gpt-4-turbo":
{
"label": "The latest GPT-4 Turbo model with vision capabilities. Currently points to gpt-4-turbo-2024-04-09.",
"max_token": 4096,
"context_token": 128000,
"data": "Up to Dec 2023 (as of 20240718)",
"status": "active",
"status_details": "",
"capability": "vision"
},
"gpt-4-turbo-2024-04-09":
{
"label": "GPT-4 Turbo with Vision model. gpt-4-turbo currently points to this version.",
"max_token": 4096,
"context_token": 128000,
"data": "Up to Dec 2023 (as of 20240718)",
"status": "active",
"status_details": "",
"capability": "vision"
},
"gpt-4-turbo-preview":
{
"label": "Currently points to gpt-4-0125-preview: The latest GPT-4 model intended to reduce cases of laziness where the model doesn’t complete a task. Returns a maximum of 4,096 output tokens.",
"max_token": 4096,
"context_token": 128000,
"data": "Up to Dec 2023 (as of 20240718)",
"status": "active",
"status_details": "",
"capability": ""
},
"gpt-4-0125-preview":
{
"label": "GPT-4 Turbo preview model intended to reduce cases of laziness where the model doesn’t complete a task. Returns a maximum of 4,096 output tokens.",
"max_token": 4096,
"context_token": 128000,
"data": "Up to Dec 2023 (as of 20240718)",
"status": "active",
"status_details": "",
"capability": ""
},
"gpt-4-1106-preview":
{
"label": "GPT-4 Turbo model featuring improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. Returns a maximum of 4,096 output tokens. This is a preview model.",
"max_token": 4096,
"context_token": 128000,
"data": "Up to Apr 2023 (as of 20240718)",
"status": "active",
"status_details": "",
"capability": ""
},
"gpt-4":
{
"label": "Currently points to gpt-4-0613: Snapshot of gpt-4 from June 13th 2023 with improved function calling support.",
"max_token": 4096,
"context_token": 8192,
"data": "Up to Sep 2021 (as of 20240718)",
"status": "active",
"status_details": "",
"capability": ""
},
"gpt-4-0613":
{
"label": "Snapshot of gpt-4 from June 13th 2023 with improved function calling support.",
"max_token": 4096,
"context_token": 8192,
"data": "Up to Sep 2021 (as of 20240718)",
"status": "active",
"status_details": "",
"capability": ""
},
"gpt-4-32k":
{
"label": "Currently points to gpt-4-32k-0613: Snapshot of gpt-4-32k from June 13th 2023 with improved function calling support. This model was never rolled out widely in favor of GPT-4 Turbo.",
"max_token": 4096,
"context_token": 32768,
"data": "Up to Sep 2021 (as of 20240606)",
"status": "deprecated",
"status_details": "",
"capability": ""
},
"gpt-4-32k-0613":
{
"label": "Snapshot of gpt-4-32k from June 13th 2023 with improved function calling support. This model was never rolled out widely in favor of GPT-4 Turbo.",
"max_token": 4096,
"context_token": 32768,
"data": "Up to Sep 2021 (as of 20240606)",
"status": "deprecated",
"status_details": "",
"capability": ""
},
"gpt-3.5-turbo-0125":
{
"label": "The latest GPT-3.5 Turbo model with higher accuracy at responding in requested formats and a fix for a bug which caused a text encoding issue for non-English language function calls. Returns a maximum of 4,096 output tokens.",
"max_token": 4096,
"context_token": 16385,
"data": "Up to Sep 2021 (as of 20240718)",
"status": "active",
"status_details": "",
"capability": ""
},
"gpt-3.5-turbo":
{
"label": "Currently points to gpt-3.5-turbo-0125: The latest GPT-3.5 Turbo model with higher accuracy at responding in requested formats and a fix for a bug which caused a text encoding issue for non-English language function calls. Returns a maximum of 4,096 output tokens.",
"max_token": 4096,
"context_token": 16385,
"data": "Up to Sep 2021 (as of 20240718)",
"status": "active",
"status_details": "",
"capability": ""
},
"gpt-3.5-turbo-1106":
{
"label": "GPT-3.5 Turbo model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. Returns a maximum of 4,096 output tokens.",
"max_token": 4096,
"context_token": 16385,
"data": "Up to Sep 2021 (as of 20240718)",
"status": "active",
"status_details": "",
"capability": ""
},
"gpt-3.5-turbo-16k":
{
"label": "Currently points to gpt-3.5-turbo-16k-0613: Snapshot of gpt-3.5-turbo from June 13th 2023. Will be deprecated on June 13, 2024.",
"max_token": 4096,
"context_token": 16385,
"data": "Up to Sep 2021 (as of 20240513)",
"status": "deprecated",
"status_details": "Will be deprecated on June 13, 2024.",
"capability": ""
},
"gpt-3.5-turbo-0613":
{
"label": "Snapshot of gpt-3.5-turbo from June 13th 2023. Will be deprecated on June 13, 2024.",
"max_token": 4096,
"context_token": 4096,
"data": "Up to Sep 2021 (as of 20240513)",
"status": "deprecated",
"status_details": "Will be deprecated on June 13, 2024.",
"capability": ""
},
"gpt-3.5-turbo-16k-0613":
{
"label": "Snapshot of gpt-3.5-16k-turbo from June 13th 2023. Will be deprecated on June 13, 2024.",
"max_token": 4096,
"context_token": 16385,
"data": "Up to Sep 2021 (as of 20240513)",
"status": "deprecated",
"status_details": "Will be deprecated on June 13, 2024.",
"capability": ""
}
},
"DallE":
{
"dall-e-3":
{
"label": "The latest DALL·E model released in Nov 2023. The maximum prompt length is 4000 characters.",
"image_size": ["1024x1024", "1024x1792", "1792x1024"],
"max_prompt_length": 4000,
"status": "active",
"status_details": ""
},
"dall-e-2":
{
"label": "The previous DALL·E model released in Nov 2022. The maximum prompt length is 1000 characters.",
"image_size": ["256x256", "512x512", "1024x1024"],
"max_prompt_length": 1000,
"status": "active",
"status_details": ""
}
}
}