{"schema_version":"1.0","documentation_url":"https://taskfuel.ai/catalog/manifest/","source":{"type":"provider_specifications","date":"2026-10-15","catalog_url":"https://taskfuel.ai/catalog/"},"capability":{"id":"embeddings","name":"Create embeddings","description":"Vector embeddings for search, clustering and RAG.","category":{"id":"ai","name":"AI models & text"},"url":"https://taskfuel.ai/catalog/#cap-embeddings","guide_url":null,"related_guide_urls":[],"detail_url":"https://taskfuel.ai/catalog/capabilities/embeddings.json","providers":[{"name":"Perplexity","domains":["perplexity.mpp.paywithlocus.com"]},{"name":"Mistral AI","domains":["mistral.mpp.paywithlocus.com"]}],"price":{"type":"quote_required","amount":null,"currency":"USD","unit":null,"basis":"request_quote","quote_required":true},"example_prompt":"Use TaskFuel to create embeddings for these 500 help articles so I can search them.","endpoint_count":3},"endpoints":[{"provider":{"name":"Mistral AI","domain":"mistral.mpp.paywithlocus.com"},"method":"POST","url":"https://mistral.mpp.paywithlocus.com/mistral/embed","name":"Embeddings","description":"Generate text or code embeddings. Returns 1024-dimensional vectors for retrieval, clustering, and classification.","supporting_call":false,"price":{"currency":"USD","unit":null,"basis":"provider_specification","type":"quote_required","amount":null,"quote_required":true}},{"provider":{"name":"Perplexity","domain":"perplexity.mpp.paywithlocus.com"},"method":"POST","url":"https://perplexity.mpp.paywithlocus.com/perplexity/embed","name":"Embeddings","description":"Generate vector embeddings for semantic search, clustering, and RAG. Supports MRL (Matryoshka) dimensionality reduction and INT8/BINARY quantization.","supporting_call":false,"price":{"currency":"USD","unit":null,"basis":"provider_specification","type":"quote_required","amount":null,"quote_required":true}},{"provider":{"name":"Perplexity","domain":"perplexity.mpp.paywithlocus.com"},"method":"POST","url":"https://perplexity.mpp.paywithlocus.com/perplexity/context-embed","name":"Contextualized Embeddings","description":"Generate document-aware embeddings where chunks share context from a parent document. Better for RAG over chunked documents.","supporting_call":false,"price":{"currency":"USD","unit":null,"basis":"provider_specification","type":"quote_required","amount":null,"quote_required":true}}]}