Compare model

openai / Embedding

Text Embedding 3 Small

openai/text-embedding-3-small

Lightweight embeddings

Catalog status

Enabled

Research checked

2026-10-07

Benchmark results

2 reported results

Results are source-attributed, not TokenBazaar measurements. Different tests and thinking variants are not interchangeable.

2 of 2 results

MTEB (English average)

Embedding · Vendor-reported

Test conditions and source

OpenAI release evaluation, January 25, 2024. Published English embedding-task average; not a TokenBazaar run. Source: “the average score on a commonly used benchmark for English tasks (MTEB) has increased from 61.0% to 62.3%”.

Tested model: openai/text-embedding-3-small

OpenAI · New embedding models and API updates · Checked 2026-10-07

62.3%

MIRACL (multilingual retrieval)

Embedding · Vendor-reported

Test conditions and source

OpenAI release evaluation, January 25, 2024. Published multilingual retrieval average; not a TokenBazaar run. Source: “the average score on a commonly used benchmark for multi-language retrieval (MIRACL) has increased from 31.4% to 44.0%”.

Tested model: openai/text-embedding-3-small

OpenAI · New embedding models and API updates · Checked 2026-10-07

44%

Model specifications

Input and output modalities

Provider-reported formats; API compatibility is detailed below.

Input

Text

Output

Embeddings
Exact model ID
openai/text-embedding-3-small
Model type
Embedding

Exact token limits are not published in the reviewed sources, so no estimated limits are shown.

Versions and thinking levels

One enabled version is currently listed for this model.

Text Embedding 3 SmallSelected₹0.96 per 1M tokens

Features and tool support

TokenBazaar’s exposed interface, not every feature advertised by the provider. “Available” describes the implemented interface, not a successful test of every input or tool.

Input through TokenBazaar

Not verified

Consult the integration documentation; no additional input formats are claimed here.

Output through TokenBazaar

Not verified

Output compatibility has not been independently verified for this exact model.

Function-tool conversations

Not exposed

This is a dedicated media or utility endpoint, not a conversational function-tool interface.

Sources and verification

Provider specifications describe the upstream model, not a guarantee of every feature through TokenBazaar. Prices come from the enabled catalog; benchmark results belong to the exact tested model.