What's free
Starter (free) plan: 5M embedding tokens/month per model (llama-text-embed-v2, multilingual-e5-large, pinecone-sparse-english-v0) and 500 rerank requests/month (bge-reranker-v2-m3; the rate-limits doc also lists pinecone-rerank-v0 at 500)
- Credit card
- not required
- Phone verification
- not confirmed
- Commercial use
- not confirmed
Free limits
| requests per month | 500 |
|---|---|
| tokens per month | 5,000,000 |
Starter plan: 5M embedding tokens per month for each of llama-text-embed-v2, multilingual-e5-large and pinecone-sparse-english-v0; 500 rerank requests per month for bge-reranker-v2-m3; Starter plan limits as listed on the pricing page, which Pinecone can change. Source: the provider's page, read 2026-10-09.
In the provider's words
Starter: 5M embedding tokens/mo per model; 250K embedding tokens/min per model (passage); 500 rerank requests/mo and 60 rerank requests/min per model; 100 inference requests/s and 2,000/min per project
The catch
Monthly limits are hard: reaching one returns 429 and you must upgrade (no pay-as-you-go overage on Starter). The pricing page lists only bge-reranker-v2-m3 as included on Starter while the rate-limits doc also lists pinecone-rerank-v0 at 500 — an internal inconsistency. Not OpenAI-compatible. Card requirement for Starter not stated on the pricing page or docs. No card was required at signup when last confirmed (2026-08); the current pages do not mention it.
Free models: not listed yet.
Get started
This is a first-party API, not OpenAI-compatible, so there is no drop-in base URL. The endpoint, the key and a working example are in the official docs.
Appears in
Compare
Change history
How this free tier has changed since we started tracking it (2026-07-30) — generated from the git history of providers.json.
- 2026-10-08 Updated free tier, rate limits, the catch
- 2026-07-30 Added to the hub