text-embedding-3-small
text-embedding-3-small turns notes and document passages into compact search vectors, with 1,536 dimensions by default and optional shorter output.
View model details →View sample outputs →Model comparisons
text-embedding-3-small lists a 80% lower unit price than text-embedding-ada-002. Tier prices, request fields and limits side by side.

text-embedding-3-small turns notes and document passages into compact search vectors, with 1,536 dimensions by default and optional shorter output.
View model details →View sample outputs →text-embedding-ada-002 supplies fixed 1,536-dimensional vectors for applications that already maintain an ada embedding index.
View model details →View sample outputs →Compare
Start with the input you have, the result you want and your budget. These are the differences that affect that choice.
Compare the published examples, then try the same input on both models with matching settings.
The Spicy Index and Freedom Score for both models, from the same daily calculation as the leaderboards.
| Measure | text-embedding-3-small | text-embedding-ada-002 |
|---|---|---|
| Spicy Index | 0.0 | 0.0 |
| Freedom Score | Not yet tested | Not yet tested |
| Evidence | — | — |
| Range if the rest pass | — | — |
| Price | — | — |
| Reviews | No review yet | No review yet |
Preliminary · freedom evidence pending
See both on the leaderboard →Current price
A start price answers a different question than the one you have. These are the tiers both models publish, matched setting for setting, in US dollars per billed unit with no conversion step in between.
Swipe horizontally to compare all fields.
| Tier | text-embedding-3-small | text-embedding-ada-002 | Difference |
|---|---|---|---|
| Current price | $0.000004 / thousand tokens | $0.00002 / thousand tokens | text-embedding-3-small −80% |
About this comparison
Every row here is read from the JSON Schema the endpoint validates against, so it matches what the API will really accept rather than a feature list written by hand.
Swipe horizontally to compare all fields.
| Controls and limits | text-embedding-3-small | text-embedding-ada-002 |
|---|---|---|
| Supported tasks | embedding | embedding |
| Input context | 300,000 tokens | 300,000 tokens |
| Execution | Synchronous, with streaming | Synchronous, with streaming |
| Request timeout | 2 minutes | 2 minutes |
| Availability | Live | Live |
Can I swap the model ID without changing the request body?
The task lifecycle is shared; the body is not. Each endpoint publishes its own JSON Schema and the API validates against that, so this is the list to reconcile before a switch.
Compare
The model identifiers are openai/text-embedding-3-small/embedding and openai/text-embedding-ada-002/embedding, and both go in the same field of the same request.
Both return the response on the chat request. With streaming enabled, read the stream until it finishes; there is no media task to poll.
Both use the same submit-and-track flow, but their required inputs may differ. Check each model page before switching.
One key, one balance, one set of spend caps. Both bill to the same account in US dollars, and the per-key daily, monthly and lifetime limits apply to whichever one you call.
Questions developers ask
text-embedding-3-small has the lower listed unit price by 80%. Prices may change; check the estimate shown for your actual settings before submitting.
text-embedding-3-small allows 2 minutes per task and text-embedding-ada-002 allows 2. Those are ceilings rather than typical times — most requests finish far sooner — but they are what your own client timeout has to survive.
Prices and capabilities shown here come from the current public model catalogue. Check each model page for its latest inputs and examples.