Wirestack
Pinecone document indexes can embed with gemini-embedding-2 and OpenAI text-embedding-3 (November 4, 2026)
Pinecone now hosts gemini-embedding-2, text-embedding-3-small and text-embedding-3-large for integrated embedding on document indexes.
Your keys
0 of 1 ready
Create each key on its own page, paste it below, then copy the finished lines into your project's .env file. What you paste stays in this tab. It is never sent to Wirestack or saved.
- Pinecone API keyPINECONE_API_KEYGet key
Pick your project, open API keys, click + API key, name it, choose its permissions, then Create key
3 of 3 free copies left this month.Unlimited with Pro
What you get
On November 4, 2026 Pinecone added three hosted embedding models for document indexes: gemini-embedding-2 from Google, and text-embedding-3-small and text-embedding-3-large from OpenAI. Pinecone embeds your text for you when you upsert and when you search, so you send plain text and never handle vectors.
text-embedding-3-small: default and maximum dimension 1,536.text-embedding-3-large: default and maximum 3,072. Both embed up to 8,192 tokens per value and take any metric. They are available on every plan, with the usual monthly token limits (5 million on Starter, 10 million on Builder, no limit on Standard and Enterprise). From November 4 to December 31, 2026, Starter and Builder get double: 10 million and 20 million tokens per model a month. On Standard and Enterprise you can keep their processing in the US withprocessing_location: "us".gemini-embedding-2: any dimension from 128 to 3,072 (default 3,072),cosineonly, up to 8,192 tokens per value, processed in thegloballocation only. It is available on the Builder, Standard and Enterprise plans; on Starter, creating an index with it returns a403. You choose atask_type(such asretrieval_document,question_answering,fact_verificationorclustering) for stored text and for queries.