blob: 4c80712f1e25fa9ca223517def1bd38bbe9d977c (
plain) (
blame)
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
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
|
- type: openai
# docs:
# - https://platform.openai.com/docs/models
# - https://openai.com/pricing
# - https://platform.openai.com/docs/api-reference/chat
models:
- name: gpt-3.5-turbo
max_input_tokens: 16385
max_output_tokens?: 4096
input_price: 0.5
output_price: 1.5
- name: gpt-3.5-turbo-1106
max_input_tokens: 16385
max_output_tokens?: 4096
input_price: 1
output_price: 2
- name: gpt-4-turbo
max_input_tokens: 128000
max_output_tokens?: 4096
input_price: 10
output_price: 30
supports_vision: true
- name: gpt-4-turbo-preview
max_input_tokens: 128000
max_output_tokens?: 4096
input_price: 10
output_price: 30
- name: gpt-4-1106-preview
max_input_tokens: 128000
max_output_tokens?: 4096
input_price: 10
output_price: 30
- name: gpt-4-vision-preview
max_input_tokens: 128000
max_output_tokens: 4096
input_price: 10
output_price: 30
supports_vision: true
- name: gpt-4
max_input_tokens: 8192
max_output_tokens?: 4096
input_price: 30
output_price: 60
- name: gpt-4-32k
max_input_tokens: 32768
max_output_tokens?: 4096
input_price: 60
output_price: 120
- type: gemini
docs:
# - https://ai.google.dev/models/gemini
# - https://ai.google.dev/pricing
# - https://ai.google.dev/api/rest/v1beta/models/streamGenerateContent
models:
- name: gemini-1.0-pro-latest
max_input_tokens: 30720
max_output_tokens?: 2048
input_price: 0.5
output_price: 1.5
- name: gemini-1.0-pro-vision-latest
max_input_tokens: 12288
max_output_tokens?: 4096
input_price: 0.5
output_price: 1.5
supports_vision: true
- name: gemini-1.5-pro-latest
max_input_tokens: 1048576
max_output_tokens?: 8192
input_price: 7
output_price: 21
supports_vision: true
- type: claude
# docs:
# - https://docs.anthropic.com/claude/docs/models-overview
# - https://docs.anthropic.com/claude/reference/messages-streaming
models:
- name: claude-3-opus-20240229
max_input_tokens: 200000
max_output_tokens: 4096
input_price: 15
output_price: 75
supports_vision: true
- name: claude-3-sonnet-20240229
max_input_tokens: 200000
max_output_tokens: 4096
input_price: 3
output_price: 15
supports_vision: true
- name: claude-3-haiku-20240307
max_input_tokens: 200000
max_output_tokens: 4096
input_price: 0.25
output_price: 1.25
supports_vision: true
- type: mistral
# docs:
# - https://docs.mistral.ai/platform/endpoints/
# - https://mistral.ai/technology/#pricing
# - https://docs.mistral.ai/api/
models:
- name: open-mistral-7b
max_input_tokens: 32000
max_output_tokens?: 8191
input_price: 0.25
output_price: 0.25
- name: open-mixtral-8x7b
max_input_tokens: 32000
max_output_tokens?: 8191
input_price: 0.7
output_price: 0.7
- name: open-mixtral-8x22b
max_input_tokens: 64000
max_output_tokens?: 8191
input_price: 2
output_price: 6
- name: mistral-small-latest
max_input_tokens: 32000
max_output_tokens?: 8191
input_price: 2
output_price: 6
- name: mistral-medium-latest
max_input_tokens: 32000
max_output_tokens?: 8191
input_price: 2.7
output_price: 8.1
- name: mistral-large-latest
max_input_tokens: 32000
max_output_tokens?: 8191
input_price: 8
output_price: 24
- type: cohere
# docs:
# - https://docs.cohere.com/docs/command-r
# - https://docs.cohere.com/docs/command-r-plus
# - https://cohere.com/pricing
# - https://docs.cohere.com/reference/chat
models:
- name: command-r
max_input_tokens: 128000
max_output_tokens?: 4096
input_price: 0.5
output_price: 1.5
- name: command-r-plus
max_input_tokens: 128000
max_output_tokens?: 4096
input_price: 3
output_price: 15
- type: perplexity
# docs:
# - https://docs.perplexity.ai/docs/model-cards
# - https://docs.perplexity.ai/docs/pricing
# - https://docs.perplexity.ai/reference/post_chat_completions
models:
- name: sonar-small-chat
max_input_tokens: 16384
- name: sonar-small-online
max_input_tokens: 12000
- name: sonar-medium-chat
max_input_tokens: 16384
- name: sonar-medium-online
max_input_tokens: 12000
- name: llama-3-8b-instruct
max_input_tokens: 8192
max_output_tokens?: 8192
input_price: 0.2
output_price: 0.2
- name: llama-3-70b-instruct
max_input_tokens: 8192
max_output_tokens?: 8192
input_price: 1
output_price: 1
- name: codellama-70b-instruct
max_input_tokens: 16384
max_output_tokens?: 4096
input_price: 1
output_price: 1
- name: mistral-7b-instruct
max_input_tokens: 16384
max_output_tokens?: 8191
input_price: 0.2
output_price: 0.2
- name: mixtral-8x7b-instruct
max_input_tokens: 16384
max_output_tokens?: 8191
input_price: 0.6
output_price: 0.6
- name: mixtral-8x22b-instruct
max_input_tokens: 16384
max_output_tokens?: 8191
input_price: 1
output_price: 1
- type: groq
# docs:
# - https://console.groq.com/docs/models
# - https://console.groq.com/docs/text-chat
models:
- name: llama3-8b-8192
max_input_tokens: 8192
max_output_tokens: 8192
- name: llama3-70b-8192
max_input_tokens: 8192
max_output_tokens: 8192
- name: llama2-70b-4096
max_input_tokens: 4096
max_output_tokens: 4096
- name: mixtral-8x7b-32768
max_input_tokens: 32768
max_output_tokens: 32768
- name: gemma-7b-it
max_input_tokens: 8192
max_output_tokens: 8192
- type: vertexai
# docs:
# - https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models
# - https://cloud.google.com/vertex-ai/generative-ai/pricing
# - https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/gemini
models:
- name: gemini-1.0-pro
max_input_tokens: 24568
max_output_tokens: 24568
input_price: 0.125
output_price: 0.375
- name: gemini-1.0-pro-vision
max_input_tokens: 14336
max_output_tokens: 14336
input_price: 0.125
output_price: 0.375
supports_vision: true
- name: gemini-1.5-pro-preview-0409
max_input_tokens: 1000000
max_output_tokens: 1000000
input_price: 2.5
output_price: 7.5
supports_vision: true
- name: claude-3-opus@20240229
max_input_tokens: 200000
max_output_tokens: 4096
supports_vision: true
- name: claude-3-sonnet@20240229
max_input_tokens: 200000
max_output_tokens: 4096
supports_vision: true
- name: claude-3-haiku@20240307
max_input_tokens: 200000
max_output_tokens: 4096
supports_vision: true
- type: ernie
# docs:
# - https://cloud.baidu.com/doc/WENXINWORKSHOP/s/Nlks5zkzu
# - https://cloud.baidu.com/doc/WENXINWORKSHOP/s/hlrk4akp7
models:
- name: ernie-4.0-8k-preview
max_input_tokens: 5120
max_output_tokens: 2048
input_price: 16.8
output_price: 16.8
- name: ernie-3.5-8k-preview
max_input_tokens: 5120
max_output_tokens: 2048
input_price: 1.68
output_price: 1.68
- name: ernie-speed-128k
max_input_tokens: 124000
max_output_tokens: 4096
input_price: 0.56
output_price: 1.12
- name: ernie-lite-8k
max_input_tokens: 7168
max_output_tokens: 2048
input_price: 0.42
output_price: 0.84
- name: ernie-tiny-8k
max_input_tokens: 7168
max_output_tokens: 2048
input_price: 0.14
output_price: 0.14
- type: qianwen
# docs:
# - https://help.aliyun.com/zh/dashscope/developer-reference/tongyiqianwen-large-language-models/
# - https://help.aliyun.com/zh/dashscope/developer-reference/qwen-vl-plus/
models:
- name: qwen-turbo
max_input_tokens: 6000
max_output_tokens?: 1500
input_price: 1.12
output_price: 1.12
- name: qwen-plus
max_input_tokens: 30000
max_output_tokens?: 2000
input_price: 2.8
output_price: 2.8
- name: qwen-max
max_input_tokens: 6000
max_output_tokens?: 2000
input_price: 16.8
output_price: 16.8
- name: qwen-max-longcontext
max_input_tokens: 28000
max_output_tokens?: 2000
- name: qwen-vl-plus
input_price: 1.12
output_price: 1.12
supports_vision: true
- name: qwen-vl-max
input_price: 2.8
output_price: 2.8
supports_vision: true
- type: moonshot
# docs:
# - https://platform.moonshot.cn/docs/intro
# - https://platform.moonshot.cn/docs/pricing
# - https://platform.moonshot.cn/docs/api-reference
models:
- name: moonshot-v1-8k
max_input_tokens: 8000
input_price: 1.68
output_price: 1.68
- name: moonshot-v1-32k
max_input_tokens: 32000
input_price: 3.36
output_price: 3.36
- name: moonshot-v1-128k
max_input_tokens: 128000
input_price: 8.4
output_price: 8.4
|
