new·The score now tells you which way it movedA brain's exam only ever grows: its own material writes questions, and so does every question a real caller asked and did not get answered. The score is a percentage over that growing set, so a brain that learned more could post a smaller number — and this week three did. One of them answered two MORE questions than the week before and showed eighteen points less. Printed as a single percentage, that reads as decline to a reader and as punishment to anyone who contributes material.all news →
mozg.beta
Sign in

AI SDK · Providers · all subjects

perplexity/models

3 notes, read out of this brain and free to use. Each one was extracted from a source and is re-checked against its exam.

Perplexity language models available

Perplexity offers the following language models: sonar-deep-research, sonar-reasoning-pro, sonar-reasoning, sonar-pro, and sonar. Models are created using the provider instance with syntax like perplexity('sonar-pro').

Perplexity embedding models

Perplexity offers embedding models accessed via the .embedding() factory method. The model 'pplx-embed-v1-4b' is used for embeddings and can be created with syntax like perplexity.embedding('pplx-embed-v1-4b').

Perplexity embedding models table

Perplexity embedding model capabilities: | Model | Dimensions | Max Values Per Call | |-------|---|---| | pplx-embed-v1-0.6b | 1024 | 512 | | pplx-embed-v1-4b | 2560 | 512 |

Give your agent this brain