genai-prices/prices/providers/huggingface_sambanova.yml at main · pydantic/genai-prices · GitHub

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
# yaml-language-server: $schema=.schema.json
# !!!!!!
# This is auto-generated by source_huggingface.py and does not support manual edits yet
# !!!!!!

id: huggingface_sambanova
name: HuggingFace (sambanova)
pricing_urls:
  - https://router.huggingface.co/v1/models
  - https://huggingface.co/inference/models
api_pattern: https://router\.huggingface\.co/sambanova
provider_match:
  and:
    - contains: huggingface
    - contains: sambanova
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/Qwen3-32B
    name: Qwen3-32B
    match:
      or:
        - equals: qwen/qwen3-32b
        - equals: qwen/qwen3-32b-fast
    context_window: 32768
    prices:
      input_mtok: 0.4
      output_mtok: 0.8

  - id: deepseek-ai/DeepSeek-R1-0528
    name: DeepSeek-R1-0528
    match:
      or:
        - equals: deepseek-ai/deepseek-r1-0528
        - equals: deepseek-ai/deepseek-r1-0528-fast
    context_window: 131072
    prices:
      input_mtok: 5
      output_mtok: 7

  - 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: 0.7
      output_mtok: 1.4

  - id: deepseek-ai/DeepSeek-V3-0324
    name: DeepSeek-V3-0324
    match:
      or:
        - equals: deepseek-ai/deepseek-v3-0324
        - equals: deepseek-ai/deepseek-v3-0324-fast
    context_window: 131072
    prices:
      input_mtok: 3
      output_mtok: 4.5

  - 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: 16384
    prices:
      input_mtok: 0.1
      output_mtok: 0.2

  - 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: 0.6
      output_mtok: 1.2

  - 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: 0.22
      output_mtok: 0.59

  - id: tokyotech-llm/Llama-3.3-Swallow-70B-Instruct-v0.4
    name: Llama-3.3-Swallow-70B-Instruct-v0.4
    match:
      or:
        - equals: tokyotech-llm/llama-3.3-swallow-70b-instruct-v0.4
        - equals: tokyotech-llm/llama-3.3-swallow-70b-instruct-v0.4-fast
    context_window: 131072
    prices:
      input_mtok: 0.6
      output_mtok: 1.2