text-embedding-3-large pricing, context window and limits
text-embedding-3-large costs $0.13 per million input tokens and $0 per million output tokens at OpenAI list price. It accepts up to 8,191 tokens of context and returns up to 3,072 tokens.
- Model id
text-embedding-3-large - Snapshot
What does text-embedding-3-large cost?
| Input | $0.13 |
|---|---|
| Output | $0 |
| Cached input (read) | — |
| Cache write | — |
US dollars per million tokens. A dash means no price is published.
How much can text-embedding-3-large read and write?
| Context window | 8,191 |
|---|---|
| Max output | 3,072 |
What can text-embedding-3-large do?
| Vision (image input) | No |
|---|---|
| Tool calling | No |
| Structured output | No |
| Reasoning | No |
| Input | text |
| Output | text |
What does a request to text-embedding-3-large cost?
| A typical request: 1,000 tokens in, 500 out | $0.00013 |
|---|---|
| A long request: 10,000 tokens in, 1,000 out | $0.0013 |
| 1,000 typical requests | $0.13 |
| 1 million tokens in and 1 million out | $0.13 |
Among 49 OpenAI models with a published price, text-embedding-3-large is the 6th cheapest by input price. Its context window is the 47th largest of 48. List prices only; discounts, batch prices and prices above 200K tokens are not shown.
How do I call text-embedding-3-large through DVARA?
Configure the openai provider in the DVARA LLM Gateway and send the model id text-embedding-3-large. DVARA, the AI governance platform, applies your policies, audit and cost attribution to the call. See LLM cost attribution and budgets.
In DVARA, if you haven't set your own price for a model, its calls are costed at the price in the catalogue that ships with your DVARA version. A price you set in Flightdeck always wins. You can switch catalogue prices off. Then a model with no price you set is counted as costing nothing. Every cost record says which price it used.
What should I check before relying on this data?
The weekly review marked this entry. A person saw each mark and kept the model listed.
- Output is listed cheaper than input, which is unusual.
- This provider bills prompt caching, but no cached-input price is listed.
Which other OpenAI models are there?
- text-embedding-3-small$0.02 in · $0 out · 8K context
- text-embedding-ada-002$0.1 in · $0 out · 8K context
- o4-mini$1.1 in · $4.4 out · 200K context
- o3-pro$20 in · $80 out · 200K context
- o3-mini$1.1 in · $4.4 out · 200K context
- o3$2 in · $8 out · 200K context
- o1-pro$150 in · $600 out · 200K context
- o1$15 in · $60 out · 200K context
- GPT-Realtime-2.1$4 in · $24 out · 128K context
- gpt-image-2$5 in · $30 out · — context
- gpt-image-1.5— in · — out · — context
- gpt-image-1-mini— in · — out · — context
Which models from other providers are similar to text-embedding-3-large?
These are the closest in context window and input price, one per provider.
- Mistral EmbedMistral AI · $0.1 in · $0 out · 8K context
- Gemini Embedding 2Google Gemini · $0.2 in · $0 out · 8K context
- Qwen2.5-Math 7B InstructAlibaba Qwen · $0.144 in · $0.287 out · 4K context
- Qwen3 32BAmazon Bedrock · $0.15 in · $0.6 out · 33K context
- Command RCohere · $0.15 in · $0.6 out · 128K context