text-embedding-004

text-embedding-004 is a budget-tier language model from Google. text-embedding-004 is a proprietary model available exclusively through Google's API. The Google Embeddings family is Google's model series for this capability tier.

text-embedding-004 does not have a publicly listed price. See Google's pricing page for current rates.

Its 2K-token context window is standard for this tier — adequate for most chat and completion tasks, but may require chunking for long-document workloads. Median latency (P50 time-to-first-token) is approximately 100ms — fast enough for real-time interactive applications.

text-embedding-004 is best suited to embedding, search, cost. It is a text-only model without vision or function calling support. When evaluating this model for a specific workload, the most important factors are: context window (does your input fit?), output price (how long are your generations?), and latency (is this interactive or batch?). The pricing table above shows how text-embedding-004 compares to similar models across these dimensions.

text-embedding-004 sits in the budget tier — the most cost-efficient models, best for high-volume simple tasks, classification, extraction, and applications where cost per call is the primary constraint. Unlike open-weights alternatives, text-embedding-004 is only available via Google's API — there is no self-hosted option, which simplifies deployment but creates vendor dependency. When comparing text-embedding-004 to alternatives, use the similar models section on this page to find models at comparable price points with different capability tradeoffs. The intelligence score (0/100) reflects aggregate benchmark performance — a useful proxy for general capability, though real-world performance varies significantly by task type. Always test with your specific prompts and use case before committing to a model for production.