text-embedding-3-small pricing and specs
text-embedding-3-small pricing and specsEmbedding model for semantic search, retrieval, clustering, and ranking pipelines
text-embedding-3-small price per 1M tokens
| Type | ₽ / 1M | $ / 1M |
|---|---|---|
| Input tokens | 1,69 ₽ | $0.02 |
| Output tokens | 0 ₽ | $0 |
Prices in rubles as of 18.09.2026 at the CBR rate: 1 $ = 84.51 ₽.
text-embedding-3-small specs and limits
- Context window
- 8K
- Max output
- 2K
- Input
- text
- Output
- text
- Family
- text-embedding
- Released
- 2024-01-25
- Updated
- 2024-01-25
- Knowledge cutoff
- 2024-01
- Also known as
- chatgpt text-embedding-3-small, chat gpt text-embedding-3-small, openai text-embedding-3-small, gpt text-embedding-3-small, gpt-5 text-embedding-3-small, gpt-5.6 text-embedding-3-small
What text-embedding-3-small can do
- —Reasoning
- —Tool calling
- —Structured output
- —Attachments / files
- —Vision (images)
- —Temperature control
- —Open weights
Frequently asked questions
How much does the text-embedding-3-small API cost?
Input costs $0.02 per 1M tokens (1.69 ₽) and output costs free per 1M (free). OpenAI bills the prompt and the completion separately, so the price of a call depends on how long both are. Ruble figures use the Bank of Russia rate of 84.51 ₽ per dollar for September 2026.
How much do 1,000 text-embedding-3-small tokens cost?
List prices are quoted per 1M tokens, so 1,000 tokens cost a thousandth of that: divide $0.02 for input and free for output by 1,000. The same rates in rubles are 1.69 ₽ and free per 1M tokens. Both prompt tokens and completion tokens are billed.
How many tokens does text-embedding-3-small hold?
The text-embedding-3-small context window is 8K tokens (8,191). Everything shares that budget: the system prompt, the dialogue history, attached files and the answer the model writes. The figure comes from the OpenAI model card as of September 2026.
What are the text-embedding-3-small limits?
The context window is 8K tokens (8,191) and a single response is capped at 2K tokens, so longer output has to be generated in parts. Rate limits are set by OpenAI per account and depend on your plan rather than on the model, so they are not listed here.
How is the text-embedding-3-small price in rubles calculated?
Providers quote their tariffs in US dollars, so the ruble amounts here are a conversion at the official Bank of Russia rate of 84.51 ₽ per dollar. For text-embedding-3-small that gives 1.69 ₽ per 1M input tokens and free per 1M output tokens. When the rate moves, the ruble price moves with it.
How is text-embedding-3-small different from other ChatGPT models?
text-embedding-3-small belongs to the Text embedding family at OpenAI. Models in the ChatGPT line differ in context size, price per 1M tokens and supported capabilities, so compare them by the numbers on their cards rather than by the name. Every ChatGPT model is listed on the provider page.