text-embedding-3-small

Use the model ID text-embedding-3-small through the compatible embeddings endpoint. Check the current API documentation for the exact endpoint path.

Check the current pricing page for per-token embedding costs. text-embedding-3-small is typically more cost-effective than text-embedding-3-large.

For text-embedding-3-small, set the max_tokens or max_completion_tokens parameter to control spending per call. Start with a budget aligned to your typical response length and increase only when longer outputs are genuinely needed. Monitor token usage in the API response headers to tune your budget over time.

text-embedding-3-small is best used for cost-sensitive embedding workloads including semantic search, clustering, and classification where maximum accuracy is not critical.

Yes. text-embedding-3-small is reachable through an OpenAI-compatible endpoint, so an existing OpenAI SDK client works after pointing the base URL at MixRoute and setting the model parameter to text-embedding-3-small. Keep your current request and response handling.

text-embedding-3-small is billed per use and the record publishes no free-tier allowance. The current published rates are input $0.0200 per 1M tokens and output $0.0200 per 1M tokens. Trial credit or promotional quota is tied to your account rather than to the model, so check the console before planning around a free tier.

text-embedding-3-small is billed per input token at 0.02 USD per 1,000,000 tokens. One million records cost the listed rate multiplied by the total tokens those records produce; the default output dimension is 1,536.