Pinecone integrated embedding now supports OpenAI's text-embedding-3 models
Blog post from Pinecone
Pinecone has added OpenAI’s text-embedding-3-small and text-embedding-3-large models to its integrated embedding service, allowing teams to perform semantic search by sending plain text to Documents API indexes without separately managing OpenAI accounts, API keys, rate limits, embedding pipelines, or billing. Pinecone generates embeddings for document writes and queries, supports combined semantic and full-text search on the same field, bills tokens at OpenAI’s list price, and provides Azure-based regional failover. The models support configurable dimensions from 1 to 1,536 for text-embedding-3-small and 1 to 3,072 for text-embedding-3-large, with global or US processing options depending on plan. They are available for serverless Documents API indexes through the console and Python SDK 10.3.0, while Node.js and Go support is planned; BYOC, pod-based, and Records API indexes are not supported. Starter and Builder subscribers receive temporary doubled monthly token allowances through December 31, 2026, reaching 10 million and 20 million tokens per model, respectively.
| Trend | Post Mentions | Total Month Mentions | Posts | Companies | MoM |
|---|---|---|---|---|---|
| Vector Search | 25 | 1,251 | 223 | 92 | -37% |
| Serverless | 1 | 833 | 236 | 92 | -40% |
Use this post, company, and trend context to find content marketing opportunities, perform competitive analysis, or address product feature gaps via the Plushcap MCP server or the Plushcap API.