/ mlflow / utils / model_catalog / perplexity.json
perplexity.json
  1  {
  2    "schema_version": "1.0",
  3    "models": {
  4      "codellama-34b-instruct": {
  5        "mode": "chat",
  6        "context_window": {
  7          "max_input": 16384,
  8          "max_output": 16384,
  9          "max_tokens": 16384
 10        },
 11        "pricing": {
 12          "input_per_million_tokens": 0.35,
 13          "output_per_million_tokens": 1.4
 14        },
 15        "capabilities": {
 16          "function_calling": false,
 17          "vision": false,
 18          "reasoning": false,
 19          "prompt_caching": false,
 20          "response_schema": false
 21        },
 22        "last_updated_at": "2026-04-24"
 23      },
 24      "codellama-70b-instruct": {
 25        "mode": "chat",
 26        "context_window": {
 27          "max_input": 16384,
 28          "max_output": 16384,
 29          "max_tokens": 16384
 30        },
 31        "pricing": {
 32          "input_per_million_tokens": 0.7,
 33          "output_per_million_tokens": 2.8
 34        },
 35        "capabilities": {
 36          "function_calling": false,
 37          "vision": false,
 38          "reasoning": false,
 39          "prompt_caching": false,
 40          "response_schema": false
 41        },
 42        "last_updated_at": "2026-04-24"
 43      },
 44      "llama-2-70b-chat": {
 45        "mode": "chat",
 46        "context_window": {
 47          "max_input": 4096,
 48          "max_output": 4096,
 49          "max_tokens": 4096
 50        },
 51        "pricing": {
 52          "input_per_million_tokens": 0.7,
 53          "output_per_million_tokens": 2.8
 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      "llama-3.1-70b-instruct": {
 65        "mode": "chat",
 66        "context_window": {
 67          "max_input": 131072,
 68          "max_output": 131072,
 69          "max_tokens": 131072
 70        },
 71        "pricing": {
 72          "input_per_million_tokens": 1.0,
 73          "output_per_million_tokens": 1.0
 74        },
 75        "capabilities": {
 76          "function_calling": false,
 77          "vision": false,
 78          "reasoning": false,
 79          "prompt_caching": false,
 80          "response_schema": false
 81        },
 82        "last_updated_at": "2026-04-24"
 83      },
 84      "llama-3.1-8b-instruct": {
 85        "mode": "chat",
 86        "context_window": {
 87          "max_input": 131072,
 88          "max_output": 131072,
 89          "max_tokens": 131072
 90        },
 91        "pricing": {
 92          "input_per_million_tokens": 0.2,
 93          "output_per_million_tokens": 0.2
 94        },
 95        "capabilities": {
 96          "function_calling": false,
 97          "vision": false,
 98          "reasoning": false,
 99          "prompt_caching": false,
100          "response_schema": false
101        },
102        "last_updated_at": "2026-04-24"
103      },
104      "mistral-7b-instruct": {
105        "mode": "chat",
106        "context_window": {
107          "max_input": 4096,
108          "max_output": 4096,
109          "max_tokens": 4096
110        },
111        "pricing": {
112          "input_per_million_tokens": 0.07,
113          "output_per_million_tokens": 0.28
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      "mixtral-8x7b-instruct": {
125        "mode": "chat",
126        "context_window": {
127          "max_input": 4096,
128          "max_output": 4096,
129          "max_tokens": 4096
130        },
131        "pricing": {
132          "input_per_million_tokens": 0.07,
133          "output_per_million_tokens": 0.28
134        },
135        "capabilities": {
136          "function_calling": false,
137          "vision": false,
138          "reasoning": false,
139          "prompt_caching": false,
140          "response_schema": false
141        },
142        "last_updated_at": "2026-04-24"
143      },
144      "pplx-70b-chat": {
145        "mode": "chat",
146        "context_window": {
147          "max_input": 4096,
148          "max_output": 4096,
149          "max_tokens": 4096
150        },
151        "pricing": {
152          "input_per_million_tokens": 0.7,
153          "output_per_million_tokens": 2.8
154        },
155        "capabilities": {
156          "function_calling": false,
157          "vision": false,
158          "reasoning": false,
159          "prompt_caching": false,
160          "response_schema": false
161        },
162        "last_updated_at": "2026-04-24"
163      },
164      "pplx-70b-online": {
165        "mode": "chat",
166        "context_window": {
167          "max_input": 4096,
168          "max_output": 4096,
169          "max_tokens": 4096
170        },
171        "pricing": {
172          "input_per_million_tokens": 0.0,
173          "output_per_million_tokens": 2.8
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      "pplx-7b-chat": {
185        "mode": "chat",
186        "context_window": {
187          "max_input": 8192,
188          "max_output": 8192,
189          "max_tokens": 8192
190        },
191        "pricing": {
192          "input_per_million_tokens": 0.07,
193          "output_per_million_tokens": 0.28
194        },
195        "capabilities": {
196          "function_calling": false,
197          "vision": false,
198          "reasoning": false,
199          "prompt_caching": false,
200          "response_schema": false
201        },
202        "last_updated_at": "2026-04-24"
203      },
204      "pplx-7b-online": {
205        "mode": "chat",
206        "context_window": {
207          "max_input": 4096,
208          "max_output": 4096,
209          "max_tokens": 4096
210        },
211        "pricing": {
212          "input_per_million_tokens": 0.0,
213          "output_per_million_tokens": 0.28
214        },
215        "capabilities": {
216          "function_calling": false,
217          "vision": false,
218          "reasoning": false,
219          "prompt_caching": false,
220          "response_schema": false
221        },
222        "last_updated_at": "2026-04-24"
223      },
224      "pplx-embed-v1-0.6b": {
225        "mode": "embedding",
226        "context_window": {
227          "max_input": 32768,
228          "max_tokens": 32768
229        },
230        "pricing": {
231          "input_per_million_tokens": 0.004,
232          "output_per_million_tokens": 0.0
233        },
234        "capabilities": {
235          "function_calling": false,
236          "vision": false,
237          "reasoning": false,
238          "prompt_caching": false,
239          "response_schema": false
240        },
241        "last_updated_at": "2026-04-24"
242      },
243      "pplx-embed-v1-4b": {
244        "mode": "embedding",
245        "context_window": {
246          "max_input": 32768,
247          "max_tokens": 32768
248        },
249        "pricing": {
250          "input_per_million_tokens": 0.03,
251          "output_per_million_tokens": 0.0
252        },
253        "capabilities": {
254          "function_calling": false,
255          "vision": false,
256          "reasoning": false,
257          "prompt_caching": false,
258          "response_schema": false
259        },
260        "last_updated_at": "2026-04-24"
261      },
262      "sonar": {
263        "mode": "chat",
264        "context_window": {
265          "max_input": 128000,
266          "max_tokens": 128000
267        },
268        "pricing": {
269          "input_per_million_tokens": 1.0,
270          "output_per_million_tokens": 1.0,
271          "tooling": {
272            "search_context_per_query": {
273              "search_context_size_high": 0.012,
274              "search_context_size_low": 0.005,
275              "search_context_size_medium": 0.008
276            }
277          }
278        },
279        "capabilities": {
280          "function_calling": false,
281          "vision": false,
282          "reasoning": false,
283          "prompt_caching": false,
284          "response_schema": false
285        },
286        "last_updated_at": "2026-04-24"
287      },
288      "sonar-deep-research": {
289        "mode": "chat",
290        "context_window": {
291          "max_input": 128000,
292          "max_tokens": 128000
293        },
294        "pricing": {
295          "input_per_million_tokens": 2.0,
296          "output_per_million_tokens": 8.0,
297          "tooling": {
298            "search_context_per_query": {
299              "search_context_size_high": 0.005,
300              "search_context_size_low": 0.005,
301              "search_context_size_medium": 0.005
302            }
303          }
304        },
305        "capabilities": {
306          "function_calling": false,
307          "vision": false,
308          "reasoning": true,
309          "prompt_caching": false,
310          "response_schema": false
311        },
312        "last_updated_at": "2026-04-24"
313      },
314      "sonar-medium-chat": {
315        "mode": "chat",
316        "context_window": {
317          "max_input": 16384,
318          "max_output": 16384,
319          "max_tokens": 16384
320        },
321        "pricing": {
322          "input_per_million_tokens": 0.6,
323          "output_per_million_tokens": 1.8
324        },
325        "capabilities": {
326          "function_calling": false,
327          "vision": false,
328          "reasoning": false,
329          "prompt_caching": false,
330          "response_schema": false
331        },
332        "last_updated_at": "2026-04-24"
333      },
334      "sonar-medium-online": {
335        "mode": "chat",
336        "context_window": {
337          "max_input": 12000,
338          "max_output": 12000,
339          "max_tokens": 12000
340        },
341        "pricing": {
342          "input_per_million_tokens": 0,
343          "output_per_million_tokens": 1.8
344        },
345        "capabilities": {
346          "function_calling": false,
347          "vision": false,
348          "reasoning": false,
349          "prompt_caching": false,
350          "response_schema": false
351        },
352        "last_updated_at": "2026-04-24"
353      },
354      "sonar-pro": {
355        "mode": "chat",
356        "context_window": {
357          "max_input": 200000,
358          "max_output": 8000,
359          "max_tokens": 8000
360        },
361        "pricing": {
362          "input_per_million_tokens": 3.0,
363          "output_per_million_tokens": 15.0,
364          "tooling": {
365            "search_context_per_query": {
366              "search_context_size_high": 0.014,
367              "search_context_size_low": 0.006,
368              "search_context_size_medium": 0.01
369            }
370          }
371        },
372        "capabilities": {
373          "function_calling": false,
374          "vision": false,
375          "reasoning": false,
376          "prompt_caching": false,
377          "response_schema": false
378        },
379        "last_updated_at": "2026-04-24"
380      },
381      "sonar-reasoning": {
382        "mode": "chat",
383        "context_window": {
384          "max_input": 128000,
385          "max_tokens": 128000
386        },
387        "pricing": {
388          "input_per_million_tokens": 1.0,
389          "output_per_million_tokens": 5.0,
390          "tooling": {
391            "search_context_per_query": {
392              "search_context_size_high": 0.014,
393              "search_context_size_low": 0.005,
394              "search_context_size_medium": 0.008
395            }
396          }
397        },
398        "capabilities": {
399          "function_calling": false,
400          "vision": false,
401          "reasoning": true,
402          "prompt_caching": false,
403          "response_schema": false
404        },
405        "last_updated_at": "2026-04-24"
406      },
407      "sonar-reasoning-pro": {
408        "mode": "chat",
409        "context_window": {
410          "max_input": 128000,
411          "max_tokens": 128000
412        },
413        "pricing": {
414          "input_per_million_tokens": 2.0,
415          "output_per_million_tokens": 8.0,
416          "tooling": {
417            "search_context_per_query": {
418              "search_context_size_high": 0.014,
419              "search_context_size_low": 0.006,
420              "search_context_size_medium": 0.01
421            }
422          }
423        },
424        "capabilities": {
425          "function_calling": false,
426          "vision": false,
427          "reasoning": true,
428          "prompt_caching": false,
429          "response_schema": false
430        },
431        "last_updated_at": "2026-04-24"
432      },
433      "sonar-small-chat": {
434        "mode": "chat",
435        "context_window": {
436          "max_input": 16384,
437          "max_output": 16384,
438          "max_tokens": 16384
439        },
440        "pricing": {
441          "input_per_million_tokens": 0.07,
442          "output_per_million_tokens": 0.28
443        },
444        "capabilities": {
445          "function_calling": false,
446          "vision": false,
447          "reasoning": false,
448          "prompt_caching": false,
449          "response_schema": false
450        },
451        "last_updated_at": "2026-04-24"
452      },
453      "sonar-small-online": {
454        "mode": "chat",
455        "context_window": {
456          "max_input": 12000,
457          "max_output": 12000,
458          "max_tokens": 12000
459        },
460        "pricing": {
461          "input_per_million_tokens": 0,
462          "output_per_million_tokens": 0.28
463        },
464        "capabilities": {
465          "function_calling": false,
466          "vision": false,
467          "reasoning": false,
468          "prompt_caching": false,
469          "response_schema": false
470        },
471        "last_updated_at": "2026-04-24"
472      }
473    }
474  }