OpenAI
text-embedding-3-small
$0.02 in per million tokens · 8,191 tokens of context · answer in 374 ms
Price, limits and measured speed
- OpenAI's list price, input
- $0.02 per million tokens
- OpenAI's list price, as our price feed records it
- Time to answer
- 374 ms
- our probe of 22 November 2026 · measured by us
- Price of our test call
- $0.0000005
- our probe of 22 November 2026, as the API stated it · measured by us
- Input price rank
- Lowest of 4 embedding models
- the models on this site we could call · measured by us
- First-token rank
- 2nd fastest of 4 measured
- our probe of 22 November 2026 · measured by us
- Context rank
- 2nd largest of 4
- the models on this site we could call · measured by us
Call it
curl
curl https://api.plungeai.com/v1/embeddings \
-H "Authorization: Bearer $PLUNGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/text-embedding-3-small",
"input": "The text to embed"
}'What it costs for three jobs
The same three jobs on every model page, so two models can be compared.
| Job | Tokens in | Tokens out | Through One API | At OpenAI's list price |
|---|---|---|---|---|
| One page of text | 500 | 0 | $0.00001 | $0.00001 |
| A handbook of 200 pages | 100,000 | 0 | $0.002 | $0.002 |
| A library of 20,000 pages | 10,000,000 | 0 | $0.2 | $0.2 |
Models near it
Each against text-embedding-3-small: its input price and the time to its first token.
| Model | Why it is here | Input price against it | First token against it | Input, $ per 1M | Output, $ per 1M | Context, tokens | First token | Tokens a second |
|---|---|---|---|---|---|---|---|---|
| openai/text-embedding-3-large | Same provider | +550 % | +81 ms | $0.13 | n/a | 8,191 | 455 ms | n/a |
| google/gemini-embedding-2 | Larger context | +900 % | +17 ms | $0.2 | n/a | 8,192 | 391 ms | n/a |
Request options
| Setting | Value |
|---|---|
| Returns | embeddings |
| Request parameters | temperature, top_p, max_tokens, max_completion_tokens, stop, response_format, n, seed, presence_penalty, frequency_penalty, logprobs, top_logprobs, logit_bias, reasoning_effort, audio, prompt_cache_key, safety_identifier, metadata, prediction, web_search_options, verbosity, modalities |
What changed
- text-embedding-3-small added
In short
- One API charges OpenAI's list price for text-embedding-3-small: $0.02 in per million tokens.
- By input price it is the lowest of the 4 embedding models we could call on 22 November 2026.
- Its context window of 8,191 tokens holds about 16 pages of text at 500 tokens a page.
How this page is made
Prices, context sizes and abilities are read from One API's public price feed and its model endpoints each time this page is built. The time to the first token, the output speed and the price of a call are measured by us: 3 calls for each model through a One API key on 22 November 2026, entering at not recorded. A model that did not answer has no page. How we measure.
Data checked · Last changed