/embeddingsCreate text embeddings
Creates embedding vectors representing the supplied text or token input. Provide model and input, then optionally choose the output encoding, vector dimensions, and end-user identifier. A successful response includes the generated vectors and token usage information.
- RetriesRetries up to 2×, 500ms backoff, 30s timeout.
Embedding request containing the required model and input, with optional output and safety-identification settings.
One documented failure
slow_downYour request rate increased too quickly. Please reduce the request rate and gradually increase it again.
Traffic increased too quickly
One documented failure
server_is_overloadedThe model is temporarily overloaded. Please retry your request after a brief delay.
The requested model is temporarily overloaded
A 429 is returned when traffic exceeds the allowed rate; reduce the request rate if a slow_down error occurs. A 503 is returned when the service or requested model is temporarily overloaded; retry after a brief delay. model and input are required, input cannot be empty or exceed 8192 tokens, and encoding_format must be float or base64.