Repository navigation
Expand file tree
/
Copy pathhuggingface_nscale.yml
More file actions
308 lines (288 loc) · 7.69 KB
/
Copy pathhuggingface_nscale.yml
File metadata and controls
308 lines (288 loc) · 7.69 KB
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
# yaml-language-server: $schema=.schema.json
# !!!!!!
# This is auto-generated by source_huggingface.py and does not support manual edits yet
# !!!!!!
id: huggingface_nscale
name: HuggingFace (nscale)
pricing_urls:
- https://router.huggingface.co/v1/models
- https://huggingface.co/inference/models
api_pattern: https://router\.huggingface\.co/nscale
provider_match:
and:
- contains: huggingface
- contains: nscale
extractors:
- api_flavor: default
root: usage
model_path: model
mappings:
- path: prompt_tokens
dest: input_tokens
required: true
- path:
- prompt_tokens_details
- cached_tokens
dest: cache_read_tokens
required: false
- path:
- prompt_tokens_details
- cache_write_tokens
dest: cache_write_tokens
required: false
- path:
- prompt_tokens_details
- audio_tokens
dest: input_audio_tokens
required: false
- path:
- completion_tokens_details
- audio_tokens
dest: output_audio_tokens
required: false
- path:
- completion_tokens_details
- reasoning_tokens
dest: output_reasoning_tokens
required: false
- path: completion_tokens
dest: output_tokens
required: true
- api_flavor: chat
root: usage
model_path: model
mappings:
- path: prompt_tokens
dest: input_tokens
required: true
- path:
- prompt_tokens_details
- cached_tokens
dest: cache_read_tokens
required: false
- path:
- prompt_tokens_details
- cache_write_tokens
dest: cache_write_tokens
required: false
- path:
- prompt_tokens_details
- audio_tokens
dest: input_audio_tokens
required: false
- path:
- completion_tokens_details
- audio_tokens
dest: output_audio_tokens
required: false
- path:
- completion_tokens_details
- reasoning_tokens
dest: output_reasoning_tokens
required: false
- path: completion_tokens
dest: output_tokens
required: true
models:
- id: Qwen/QwQ-32B
name: QwQ-32B
match:
or:
- equals: qwen/qwq-32b
- equals: qwen/qwq-32b-fast
context_window: 131072
prices:
input_mtok: 0.18
output_mtok: 0.2
- id: Qwen/Qwen2.5-Coder-32B-Instruct
name: Qwen2.5-Coder-32B-Instruct
match:
or:
- equals: qwen/qwen2.5-coder-32b-instruct
- equals: qwen/qwen2.5-coder-32b-instruct-fast
context_window: 131072
prices:
input_mtok: 0.06
output_mtok: 0.2
- id: Qwen/Qwen2.5-Coder-3B-Instruct
name: Qwen2.5-Coder-3B-Instruct
match:
or:
- equals: qwen/qwen2.5-coder-3b-instruct
- equals: qwen/qwen2.5-coder-3b-instruct-fast
context_window: 32768
prices:
input_mtok: 0.01
output_mtok: 0.03
- id: Qwen/Qwen2.5-Coder-7B-Instruct
name: Qwen2.5-Coder-7B-Instruct
match:
or:
- equals: qwen/qwen2.5-coder-7b-instruct
- equals: qwen/qwen2.5-coder-7b-instruct-fast
context_window: 131072
prices:
input_mtok: 0.01
output_mtok: 0.03
- id: Qwen/Qwen3-14B
name: Qwen3-14B
match:
or:
- equals: qwen/qwen3-14b
- equals: qwen/qwen3-14b-fast
context_window: 40960
prices:
input_mtok: 0.07
output_mtok: 0.2
- id: Qwen/Qwen3-235B-A22B
name: Qwen3-235B-A22B
match:
or:
- equals: qwen/qwen3-235b-a22b
- equals: qwen/qwen3-235b-a22b-fast
- equals: qwen/qwen3-235b-a22b-instruct-2507
- equals: qwen/qwen3-235b-a22b-instruct-2507-fast
context_window: 32000
prices:
input_mtok: 0.2
output_mtok: 0.6
- id: Qwen/Qwen3-32B
name: Qwen3-32B
match:
or:
- equals: qwen/qwen3-32b
- equals: qwen/qwen3-32b-fast
context_window: 40960
prices:
input_mtok: 0.08
output_mtok: 0.25
- id: Qwen/Qwen3-4B-Instruct-2507
name: Qwen3-4B-Instruct-2507
match:
or:
- equals: qwen/qwen3-4b-instruct-2507
- equals: qwen/qwen3-4b-instruct-2507-fast
context_window: 262144
prices:
input_mtok: 0.01
output_mtok: 0.03
- id: Qwen/Qwen3-4B-Thinking-2507
name: Qwen3-4B-Thinking-2507
match:
or:
- equals: qwen/qwen3-4b-thinking-2507
- equals: qwen/qwen3-4b-thinking-2507-fast
context_window: 262144
prices:
input_mtok: 0.01
output_mtok: 0.03
- id: Qwen/Qwen3-8B
name: Qwen3-8B
match:
or:
- equals: qwen/qwen3-8b
- equals: qwen/qwen3-8b-fast
context_window: 40960
prices:
input_mtok: 0.07
output_mtok: 0.18
- id: deepseek-ai/DeepSeek-R1-Distill-Llama-70B
name: DeepSeek-R1-Distill-Llama-70B
match:
or:
- equals: deepseek-ai/deepseek-r1-distill-llama-70b
- equals: deepseek-ai/deepseek-r1-distill-llama-70b-fast
context_window: 131072
prices:
input_mtok: 0.75
output_mtok: 0.75
- id: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
name: DeepSeek-R1-Distill-Llama-8B
match:
or:
- equals: deepseek-ai/deepseek-r1-distill-llama-8b
- equals: deepseek-ai/deepseek-r1-distill-llama-8b-fast
context_window: 131072
prices:
input_mtok: 0.05
output_mtok: 0.05
- id: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
name: DeepSeek-R1-Distill-Qwen-1.5B
match:
or:
- equals: deepseek-ai/deepseek-r1-distill-qwen-1.5b
- equals: deepseek-ai/deepseek-r1-distill-qwen-1.5b-fast
context_window: 131072
prices:
input_mtok: 0.1
output_mtok: 0.1
- id: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
name: DeepSeek-R1-Distill-Qwen-32B
match:
or:
- equals: deepseek-ai/deepseek-r1-distill-qwen-32b
- equals: deepseek-ai/deepseek-r1-distill-qwen-32b-fast
context_window: 131072
prices:
input_mtok: 0.3
output_mtok: 0.3
- id: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
name: DeepSeek-R1-Distill-Qwen-7B
match:
or:
- equals: deepseek-ai/deepseek-r1-distill-qwen-7b
- equals: deepseek-ai/deepseek-r1-distill-qwen-7b-fast
context_window: 131072
prices:
input_mtok: 0.15
output_mtok: 0.15
- id: meta-llama/Llama-3.1-8B-Instruct
name: Llama-3.1-8B-Instruct
match:
or:
- equals: meta-llama/llama-3.1-8b-instruct
- equals: meta-llama/llama-3.1-8b-instruct-fast
context_window: 131072
prices:
input_mtok: 0.06
output_mtok: 0.06
- id: meta-llama/Llama-3.3-70B-Instruct
name: Llama-3.3-70B-Instruct
match:
or:
- equals: meta-llama/llama-3.3-70b-instruct
- equals: meta-llama/llama-3.3-70b-instruct-fast
context_window: 131072
prices:
input_mtok: 0.4
output_mtok: 0.4
- id: meta-llama/Llama-4-Scout-17B-16E-Instruct
name: Llama-4-Scout-17B-16E-Instruct
match:
or:
- equals: meta-llama/llama-4-scout-17b-16e-instruct
- equals: meta-llama/llama-4-scout-17b-16e-instruct-fast
context_window: 890000
prices:
input_mtok: 0.09
output_mtok: 0.29
- id: openai/gpt-oss-120b
name: gpt-oss-120b
match:
or:
- equals: openai/gpt-oss-120b
- equals: openai/gpt-oss-120b-fast
context_window: 131072
prices:
input_mtok: 0.1
output_mtok: 0.4
- id: openai/gpt-oss-20b
name: gpt-oss-20b
match:
or:
- equals: openai/gpt-oss-20b
- equals: openai/gpt-oss-20b-fast
context_window: 131072
prices:
input_mtok: 0.05
output_mtok: 0.2