text-embedding-ada-002

text-embedding-ada-002 is a budget-tier language model from OpenAI. text-embedding-ada-002 is a proprietary model available exclusively through OpenAI's API. The OpenAI Embeddings family is OpenAI's model series for this capability tier.

text-embedding-ada-002 is priced at $0.1/1M input tokens. Output token pricing does not apply to this model — it returns a vector or score rather than generated text. At 1,000 tokens per call, text-embedding-ada-002 costs approximately $0.10 per 1,000 API calls.

Its 8K-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 90ms — fast enough for real-time interactive applications.

text-embedding-ada-002 is best suited to embedding, search, legacy. 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-ada-002 compares to similar models across these dimensions.

text-embedding-ada-002 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-ada-002 is only available via OpenAI's API — there is no self-hosted option, which simplifies deployment but creates vendor dependency. When comparing text-embedding-ada-002 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.