Text Embedding 3 Large API
openai/text-embedding-3-large turns text into vectors and is billed only on input: $0.13 per million tokens. There is no output price because embeddings are not generated tokens, and the catalog snapshot publishes no context window for this id. If $0.13 is too much for your volume, the text-embedding-3-small sibling is listed several times cheaper per 1M input tokens on the same gateway — see its page for the exact rate.
What is Text Embedding 3 Large API in NextModel?
openai/text-embedding-3-large turns text into vectors and is billed only on input: $0.13 per million tokens. There is no output price because embeddings are not generated tokens, and the catalog snapshot publishes no context window for this id. If $0.13 is too much for your volume, the text-embedding-3-small sibling is listed several times cheaper per 1M input tokens on the same gateway — see its page for the exact rate.
Text Embedding 3 Large via NextModel: context unpublished; $0.13 / 1M tokens in / $0 / 1M tokens out per 1M tokens. Capabilities: streaming.
Best use cases
- Retrieval or clustering workloads that want the larger embedding id at its published $0.13 per 1M input tokens.
- Pipelines already speaking the OpenAI embeddings API against an OpenAI-compatible gateway.
- Cases where the published price gap to text-embedding-3-small buys quality your metrics can see.
When not to use
- High-volume embedding where $0.13 per 1M adds up: text-embedding-3-small is the cheaper sibling.
- You need a published context window: none is published for this id.
- You need chat or tool calls — this is an embedding id.
OpenAI-compatible code example
curl https://api.nextmodel.app/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $NEXTMODEL_API_KEY" \
-d '{"model":"openai/text-embedding-3-large","messages":[{"role":"user","content":"Reply with OK."}]}'Switching models only changes the model field.
Similar alternatives
GPT-5 Codex via NextModel: 400k-token context; $1.25 / 1M tokens in / $10 / 1M tokens out per 1M tokens. Capabilities: streaming.
Text Embedding 3 Small via NextModel: context unpublished; $0.02 / 1M tokens in / $0 / 1M tokens out per 1M tokens. Capabilities: streaming.
Whisper Large V3 Turbo via NextModel: context unpublished; $0 / 1M tokens in / $0 / 1M tokens out per 1M tokens. Capabilities: streaming.
Reading
Articles that explain Text Embedding 3 Large
LLM Gateway: Compare Options and Alternatives
Embeddings and chat share the same base URL here.
Zhao Yu'an
How to estimate AI API cost before you ship
Input-only billing makes cost linear in corpus size.
Lin Qiming
FAQ
Text Embedding 3 Large API questions
What model id do I send for Text Embedding 3 Large?
Send openai/text-embedding-3-large to https://api.nextmodel.app/v1 with your OpenAI SDK. If that id is missing from /v1/models, the page is stale.
How is it billed?
Input only: $0.13 per 1M tokens. Embedding ids carry no output token price.
Large or small?
text-embedding-3-large is $0.13 per 1M input tokens; text-embedding-3-small is listed cheaper — check its page for the exact rate. The catalog publishes no quality ranking — benchmark both on your own corpus before paying the gap.
Start now
Ready to start building?
Passwordless signup, pay-as-you-go billing, and one OpenAI-compatible endpoint for every model. Create your key and send your first request in minutes.