OpenAI / openai/text-embedding-3-small

text-embedding-3-small - access through LLMTR

text-embedding-3-small converts input text into a numerical vector of up to 1,536 dimensions. The cosine similarity between two vectors measures how semantically close the underlying texts are, which is used for search, clustering, recommendation, and anomaly detection. It offers an 8,192-token context window and supports shortening the vector with the `dimensions` parameter, trading some accuracy for a smaller stored size. It accepts text input only and produces no output beyond the vector.

Technical specifications

Canonical IDopenai/text-embedding-3-small
ProviderOpenAI
Context window8,192 tokens
OperationsEMBEDDINGS
Modalitiestext, embedding

Pricing

An 8% platform margin applies to credit top-ups; model usage prices are not separately marked up.

OperationMetricUnitPrice
EMBEDDINGSINPUT_TEXTPER_1M_TOKENS$0.020000

Example usage

With existing OpenAI SDK flows, change only the base URL and model identifier.

curl https://llmtr.com/v1/chat/completions \
  -H "Authorization: Bearer llmtr-your_key" \
  -H "Content-Type: application/json" \
  -d '{"model":"openai/text-embedding-3-small","messages":[{"role":"user","content":"Hello"}]}'

Related models