+Gemini 2.5 Pro and o4-mini deprecations for Assistant
Google has deprecated the Gemini 2.5 Pro model, and OpenAI has deprecated o4-mini. Pinecone Assistant automatically routes all chat requests that specify gemini-2.5-pro to Gemini 3.5 Flash, and all chat requests that specify o4-mini to GPT-5, at the same price.
+Higher namespace limit on the Enterprise plan
The Enterprise limit for namespaces per serverless index is now 1,000,000. Pinecone can accommodate more for specific use cases. Contact Support to request a higher limit.
+General availability: Full-text search and the Documents API
Full-text search is now generally available on API version 2026-07, built on the new Documents API.Create schema-based document indexes that combine full-text (BM25), dense-vector, and sparse-vector ranking fields in a single index.
新的 Standard 和 Enterprise 客户将不再获得一次性 $250 批量导入积分，对象存储的所有导入将按 $0.25/GB 计费。
证据
+Bulk import credit is no longer offered
New Standard and Enterprise subscriptions no longer receive the one-time $250 bulk import credit (1 TB). Imports from object storage are billed at the standard $0.25/GB rate.
−Through July 31, 2026: cohere-rerank-3.5 continues to serve requests as before.
August 1, 2026: requests to cohere-rerank-3.5 are automatically served by cohere-rerank-4-fast.
+Through August 30, 2026: cohere-rerank-3.5 continues to serve requests as before.
August 31, 2026: requests to cohere-rerank-3.5 are automatically served by cohere-rerank-4-fast.
+Index fullness metrics for dedicated read nodes
Indexes that use dedicated read nodes now emit index fullness as time-series metrics. Monitor fullness over time via the Prometheus or Datadog integration.
−2026-08-11
Search
New guide: reciprocal rank fusion (RRF)
Added a guide on reciprocal rank fusion, a client-side method for combining the results of separate searches (for example, full-text and semantic) into one ranking without normalizing scores. RRF fuses rankings rather than raw scores, so it needs no per-signal weighting.
+New guide: reciprocal rank fusion (RRF)
Added a guide on reciprocal rank fusion, a client-side method for combining the results of separate searches (for example, full-text and semantic) into one ranking without normalizing scores. RRF fuses rankings rather than raw scores, so it needs no per-signal weighting.
+Released Pinecone Terraform Provider v4.0.0
Released v4.0.0 of the Terraform Provider for Pinecone. This version adds resources for managing service accounts, role bindings, organization invites, and removing organization members. It also adds data sources for reading existing indexes, collections, projects, service accounts, role bindings, invites, and users, and terraform import support for every resource.
+Fuzzy matching (typo tolerance) — In a query_string search, append ~ to a term to match indexed terms within a small edit distance: body:(compxter~1) matches computer. Use term~ for an automatic distance based on term length, or term~N for a fixed distance (N is 0–2). Fuzzy works on existing indexes with no reindex.
现有角色分配会自动迁移。组织级 User 角色现为 Organization manager，项目级 User 角色现为 Project manager。权限保持不变。
证据
+If you used the previous role model, the User role has been renamed to Manager: the organization-level User role is now Organization manager, and the project-level User role is now Project manager. This is a name change only—permissions are unchanged and existing assignments are migrated automatically.