Price checkPer per million tokens
text-embedding-3-smallCustomtext-embedding-3-largeCustomtext-embedding-ada-002 (Legacy)Custom
See all 3 plans

All OpenAI Embeddings Plans & Pricing

Plan Monthly Annual Best For
View all features by plan (compare side-by-side)

text-embedding-3-small

  • $0.02 per 1 million input tokens
  • 1,536 dimensions (configurable)
  • Best price-to-performance for most use cases
  • Batch API available at $0.01/M tokens (50% off)

text-embedding-3-large

  • $0.13 per 1 million input tokens
  • 3,072 dimensions (configurable)
  • Highest accuracy embedding model
  • Batch API available at $0.065/M tokens (50% off)

text-embedding-ada-002 (Legacy)

  • $0.10 per 1 million input tokens
  • 1,536 dimensions (fixed)
  • Legacy model, still supported
  • Batch API available at $0.05/M tokens (50% off)
See OpenAI Embeddings Plans
Compare OpenAI Embeddings with alternativesAdjust seats, lock a tier, add up to 2 more products side-by-side. Shareable URL.
Quick Answer
Last verified:
Estimate

OpenAI Embeddings costs $0.02 to $0.13 per per million tokens as of July 2026, with 3 plans available. Pricing depends on your chosen tier, contract length, and negotiated discounts.

Use the interactive pricing calculator to estimate your exact cost based on team size and requirements.

  • Free tier: No free tier available

OpenAI Embeddings offers 3 pricing tiers: text-embedding-3-small, text-embedding-3-large, text-embedding-ada-002 (Legacy).

Compared to other embedding apis software, OpenAI Embeddings is positioned at the budget-friendly price point.

  • 7 documented hidden costs beyond list price
  • G2 rating: 4.6 out of 5 from 2,734 reviews (as of Jun 2026)
Last verified:

How much does OpenAI Embeddings cost?

OpenAI Embeddings pricing ranges from $0.02 to $0.13/per million tokens across 3 plans. Plans include text-embedding-3-small (custom pricing), text-embedding-3-large (custom pricing), text-embedding-ada-002 (Legacy) (custom pricing).

OpenAI Embeddings Pricing Overview

OpenAI Embeddings has 3 pricing plans ranging from $0.02 to $0.13/per million tokens. The text-embedding-3-small plan requires contacting sales for a custom quote. The text-embedding-3-large plan requires contacting sales for a custom quote. The text-embedding-ada-002 (Legacy) plan requires contacting sales for a custom quote.

There are at least 7 documented hidden costs beyond OpenAI Embeddings's list price, including implementation, training, and add-on fees.

This pricing was last verified in May 30, 2026.

See OpenAI Embeddings Plans

OpenAI Embeddings is a pay-per-use API that converts text into dense vector representations, enabling semantic search, clustering, classification, and retrieval-augmented generation (RAG). The current generation offers two models: text-embedding-3-small ($0.02/M tokens) for cost-efficient workloads and text-embedding-3-large ($0.13/M tokens) for maximum accuracy. All models support dimensionality reduction and a Batch API for 50% off on asynchronous workloads.

How OpenAI Embeddings Pricing Compares

Compare OpenAI Embeddings pricing against top alternatives in Embedding APIs.

Jina Embeddings $0-$500/per million tokens Compare → Mixedbread $0-$20/month Compare → Nomic Embed Custom pricing Compare →

Compare OpenAI Embeddings vs Alternatives

Before committing to OpenAI Embeddings, compare pricing with these 3 alternatives in the same category.

VSJina Embeddings
Free

Developers evaluating Jina embeddings for non-commercial projects

Full comparison
VSMixedbread
Free

Hobbyists and evaluators trying Mixedbread

Full comparison
VSNomic Embed
Custom

Developers self-hosting embeddings

Full comparison

All OpenAI Embeddings alternatives & migration guides

What Companies Actually Pay for OpenAI Embeddings

Review scores
TrustRadius 9out of 10 (610)
Trustpilot 1.5out of 5 (1,068)
G2 4.6out of 5 (2,734)
Third-party review aggregates, as of Jun 2026

Score gap reflects platform demographics — G2 surveys verified business users; Trustpilot is open to all, skewing toward support complaints.

Top pricing complaints
Sometimes providing incorrect or outdated information.Responses occasionally feeling overly cautious or generic.Limits on deeper customization.Privacy concerns.

How OpenAI Embeddings Pricing Compares

Software Starting Price Top Price
OpenAI Embeddings $0.02/per million tokens $0.13/per million tokens
Jina Embeddings Free $500/per million tokens
Mixedbread Free $20/month
Nomic Embed Custom Custom
Voyage AI Free $0.18/per million tokens
Cohere Embed $0.1/month $0.12/month

Detailed pricing comparisons:

Browse all Embedding APIs pricing →

7 OpenAI Embeddings Hidden Costs Beyond the List Price

Beyond the listed price, OpenAI Embeddings has at least 7 documented hidden costs that can significantly increase total cost of ownership.

Watch for 7 hidden costs
  • Storage Costs for Embeddings $0.33 per GB per month
    high 1 source
    industry "For instance, Pinecone storage can cost approximately $0.33 per GB per month, which can quickly surpass the initial embedding generation cost for long-lived data sets."
  • Inflated Token Counts 10-25%
    medium 1 source
    industry "Inflated Token Counts: The process of chunking documents for embedding, especially with overlap, can inflate the actual token count by 10-25% compared to the raw text size, leading to higher billing than initially estimated."
  • Fine-tuning Premiums 50%
    high 1 source
    industry "For example, fine-tuned GPT-4o usage can incur a 50% premium over base model pricing for both input and output tokens."
  • Unpredictable Scaling $100–$400 per day
    critical 1 source
    industry "A search feature with 1 million daily queries, for example, could cost $100–$400 per day with OpenAI's embedding models."
  • Inefficient Architectures
    high 1 source
    industry "Inefficient Architectures: Over-reliance on more expensive LLMs for tasks that could be handled by cheaper embedding models or fine-tuned open-source alternatives can inflate costs."
  • Excessive API Calls
    medium 1 source
    industry "Excessive API Calls: Unoptimized retry logic or inefficient workflow designs can lead to a higher number of API calls, increasing overall costs."
  • Engineering Investment
    high 1 source
    industry "Engineering Investment: Achieving significant cost savings often requires substantial engineering effort to optimize usage, implement caching, batch requests, and potentially switch to self-hosted embedding solutions."
Tip

Ask your OpenAI Embeddings sales rep about these costs upfront. Getting them in writing before signing can save you from surprise charges later.

Full hidden costs breakdown →

Intelligence sourced from 4 independent sources
industry TrustRadius Enterprise reviews Trustpilot Consumer reviews G2 B2B reviews
Key claims include inline source attribution. Data verified against multiple independent sources. 8 source citations total.

OpenAI Embeddings Contract Terms

OpenAI Embeddings contracts do not auto-renew. Changes require Notice of non-renewal or scope reduction must be provided at least 30 days before the start of the next renewal term.. These terms are sourced from verified buyer experiences.

Contract Terms
Cancellation Notice Notice of non-renewal or scope reduction must be provided at least 30 days before the start of the next renewal term.
Minimum Commitment Enterprise agreements often come with minimum annual spend commitments, such as $250K–$500K for certain discount tiers, or a mandatory annual commitment of 150 seats for ChatGPT Enterprise, setting a floor of approximately $108,000 per year.
Based on 1 verified source

OpenAI Embeddings Pricing FAQ

01 How much does OpenAI Embeddings cost?

OpenAI Embeddings are priced per million input tokens. text-embedding-3-small costs $0.02/M tokens, text-embedding-3-large costs $0.13/M tokens, and the legacy text-embedding-ada-002 costs $0.10/M tokens. The Batch API offers a 50% discount on all models.

02 Does OpenAI charge for output tokens on the Embeddings API?

No. The OpenAI Embeddings API only charges for input tokens. There are no output token charges since the API returns vector representations rather than generated text.

03 What is the difference between the standard API and the Batch API for embeddings?

The standard Embeddings API processes requests synchronously and is best for real-time use cases. The Batch API accepts asynchronous jobs and returns results within 24 hours, offering a 50% cost reduction — making it ideal for large-scale offline embedding tasks like indexing document libraries.

Is this pricing incorrect? — we'll verify and update it.