ModelPriceWatch.com
Last scan 2026-08-09 Models tracked 198 Providers 30 Cheapest paid Granite 4.0 Micro $0.017/Mtok in Every price links to its source

text-embedding-3-small vs text-embedding-3-large

Side-by-side comparison of API pricing, specs, benchmarks, and capabilities

text-embedding-3-small is 84.6% cheaper on blended cost ($0.020 vs $0.130/Mtok)
Specification
Overview
StatusCurrent embedding Current embedding
Released Jan 25, 2024 Jan 25, 2024
Pricing per million tokens
Input $0.020/Mtok $0.130/Mtok
Output $—/Mtok $—/Mtok
Blended avg $0.020/Mtok $0.130/Mtok
Specifications
Context window 8K tokens 8K tokens
Parameters Proprietary Proprietary
Speed (TPS)
Modalities
Input
text
text
Providers
Available from
OpenAI — $0.020/Mtok
OpenAI — $0.130/Mtok

Cost at scale

1M tokens · 50/50 input/output
Projected cost of text-embedding-3-small vs text-embedding-3-large at increasing token volumes
Volumetext-embedding-3-smalltext-embedding-3-largeSavings
1M tokens $0.02 $0.13 $0.11 (84.6%)
10M tokens $0.2 $1.3 $1.1 (84.6%)
100M tokens $2 $13 $11 (84.6%)
1000M tokens $20 $130 $110 (84.6%)

When to pick which

distilled from the pricing and spec data above
Pick text-embedding-3-small if…
  • cost dominates: $0.020/Mtok blended vs $0.130 — 84.6% less on the same 50/50 token mix
Pick text-embedding-3-large if…
  • this pairing gives text-embedding-3-large no edge on price, context, cache discount, or measured performance — pick it only for qualitative fit (ecosystem, compliance, model behavior on your prompts)
Try text-embedding-3-small on OpenAI

The cheaper option here — text-embedding-3-small costs $0.020/Mtok blended on OpenAI.

Get API key →

Summary

text-embedding-3-small by OpenAI costs $0.020/Mtok input, with a 8K-token context window. It supports text input.

text-embedding-3-large by OpenAI costs $0.130/Mtok input, with a 8K-token context window. It supports text input.

On a blended cost basis, text-embedding-3-small is 84.6% cheaper than text-embedding-3-large.

Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.

More comparisons

pairs sharing a model with this page