/ mlflow / utils / model_catalog / nscale.json
nscale.json
  1  {
  2    "schema_version": "1.0",
  3    "models": {
  4      "Qwen/QwQ-32B": {
  5        "mode": "chat",
  6        "pricing": {
  7          "input_per_million_tokens": 0.18,
  8          "output_per_million_tokens": 0.2
  9        },
 10        "capabilities": {
 11          "function_calling": false,
 12          "vision": false,
 13          "reasoning": false,
 14          "prompt_caching": false,
 15          "response_schema": false
 16        },
 17        "last_updated_at": "2026-04-24"
 18      },
 19      "Qwen/Qwen2.5-Coder-32B-Instruct": {
 20        "mode": "chat",
 21        "pricing": {
 22          "input_per_million_tokens": 0.06,
 23          "output_per_million_tokens": 0.2
 24        },
 25        "capabilities": {
 26          "function_calling": false,
 27          "vision": false,
 28          "reasoning": false,
 29          "prompt_caching": false,
 30          "response_schema": false
 31        },
 32        "last_updated_at": "2026-04-24"
 33      },
 34      "Qwen/Qwen2.5-Coder-3B-Instruct": {
 35        "mode": "chat",
 36        "pricing": {
 37          "input_per_million_tokens": 0.01,
 38          "output_per_million_tokens": 0.03
 39        },
 40        "capabilities": {
 41          "function_calling": false,
 42          "vision": false,
 43          "reasoning": false,
 44          "prompt_caching": false,
 45          "response_schema": false
 46        },
 47        "last_updated_at": "2026-04-24"
 48      },
 49      "Qwen/Qwen2.5-Coder-7B-Instruct": {
 50        "mode": "chat",
 51        "pricing": {
 52          "input_per_million_tokens": 0.01,
 53          "output_per_million_tokens": 0.03
 54        },
 55        "capabilities": {
 56          "function_calling": false,
 57          "vision": false,
 58          "reasoning": false,
 59          "prompt_caching": false,
 60          "response_schema": false
 61        },
 62        "last_updated_at": "2026-04-24"
 63      },
 64      "deepseek-ai/DeepSeek-R1-Distill-Llama-70B": {
 65        "mode": "chat",
 66        "pricing": {
 67          "input_per_million_tokens": 0.375,
 68          "output_per_million_tokens": 0.375
 69        },
 70        "capabilities": {
 71          "function_calling": false,
 72          "vision": false,
 73          "reasoning": false,
 74          "prompt_caching": false,
 75          "response_schema": false
 76        },
 77        "last_updated_at": "2026-04-24"
 78      },
 79      "deepseek-ai/DeepSeek-R1-Distill-Llama-8B": {
 80        "mode": "chat",
 81        "pricing": {
 82          "input_per_million_tokens": 0.025,
 83          "output_per_million_tokens": 0.025
 84        },
 85        "capabilities": {
 86          "function_calling": false,
 87          "vision": false,
 88          "reasoning": false,
 89          "prompt_caching": false,
 90          "response_schema": false
 91        },
 92        "last_updated_at": "2026-04-24"
 93      },
 94      "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": {
 95        "mode": "chat",
 96        "pricing": {
 97          "input_per_million_tokens": 0.09,
 98          "output_per_million_tokens": 0.09
 99        },
100        "capabilities": {
101          "function_calling": false,
102          "vision": false,
103          "reasoning": false,
104          "prompt_caching": false,
105          "response_schema": false
106        },
107        "last_updated_at": "2026-04-24"
108      },
109      "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": {
110        "mode": "chat",
111        "pricing": {
112          "input_per_million_tokens": 0.07,
113          "output_per_million_tokens": 0.07
114        },
115        "capabilities": {
116          "function_calling": false,
117          "vision": false,
118          "reasoning": false,
119          "prompt_caching": false,
120          "response_schema": false
121        },
122        "last_updated_at": "2026-04-24"
123      },
124      "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": {
125        "mode": "chat",
126        "pricing": {
127          "input_per_million_tokens": 0.15,
128          "output_per_million_tokens": 0.15
129        },
130        "capabilities": {
131          "function_calling": false,
132          "vision": false,
133          "reasoning": false,
134          "prompt_caching": false,
135          "response_schema": false
136        },
137        "last_updated_at": "2026-04-24"
138      },
139      "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B": {
140        "mode": "chat",
141        "pricing": {
142          "input_per_million_tokens": 0.2,
143          "output_per_million_tokens": 0.2
144        },
145        "capabilities": {
146          "function_calling": false,
147          "vision": false,
148          "reasoning": false,
149          "prompt_caching": false,
150          "response_schema": false
151        },
152        "last_updated_at": "2026-04-24"
153      },
154      "meta-llama/Llama-3.1-8B-Instruct": {
155        "mode": "chat",
156        "pricing": {
157          "input_per_million_tokens": 0.03,
158          "output_per_million_tokens": 0.03
159        },
160        "capabilities": {
161          "function_calling": false,
162          "vision": false,
163          "reasoning": false,
164          "prompt_caching": false,
165          "response_schema": false
166        },
167        "last_updated_at": "2026-04-24"
168      },
169      "meta-llama/Llama-3.3-70B-Instruct": {
170        "mode": "chat",
171        "pricing": {
172          "input_per_million_tokens": 0.2,
173          "output_per_million_tokens": 0.2
174        },
175        "capabilities": {
176          "function_calling": false,
177          "vision": false,
178          "reasoning": false,
179          "prompt_caching": false,
180          "response_schema": false
181        },
182        "last_updated_at": "2026-04-24"
183      },
184      "meta-llama/Llama-4-Scout-17B-16E-Instruct": {
185        "mode": "chat",
186        "pricing": {
187          "input_per_million_tokens": 0.09,
188          "output_per_million_tokens": 0.29
189        },
190        "capabilities": {
191          "function_calling": false,
192          "vision": false,
193          "reasoning": false,
194          "prompt_caching": false,
195          "response_schema": false
196        },
197        "last_updated_at": "2026-04-24"
198      },
199      "mistralai/mixtral-8x22b-instruct-v0.1": {
200        "mode": "chat",
201        "pricing": {
202          "input_per_million_tokens": 0.6,
203          "output_per_million_tokens": 0.6
204        },
205        "capabilities": {
206          "function_calling": false,
207          "vision": false,
208          "reasoning": false,
209          "prompt_caching": false,
210          "response_schema": false
211        },
212        "last_updated_at": "2026-04-24"
213      }
214    }
215  }