Text Embedding 3 Large

OpenAI

Regional semantic search and retrieval.

Pilot betaInvited workspaces · Azure South Africa North

Clear usage rates.

Input≈ UGX 1,000per 1M tokens

Introductory pilot rates · UGX

Charged by input tokens at the Embiro pilot rate. The managed model is a separate option; Luganda retrieval remains experimental.

A little head start.

90 days of lower rates.

No platform subscription fee. Pay for your usage, within your approved pilot limits.

How the pilot offer works

Rates apply for 90 days from activation in an approved workspace. Rates and usage limits are confirmed before paid use.

Introductory rates are active for new requests, including existing workspaces. Historical usage keeps its original rates. Billing shows your configured rates; no automatic payments.

We’ll give at least 30 days’ notice of changes after your introductory period. Access is invite-only and subject to scheduled compute capacity. USD is the pricing base; local equivalents are approximate.

Check your workspace’s active rates →

Open in Playground View active workspace rates

Requires an invited account and a key enabled for this model.

What you can build.

Capabilities available in the Embiro pilot.

InputText

OutputEmbeddings

Regional Azure inference in South Africa
Semantic search
3072-dimensional float or base64 output

Know the limits.

Vector dimensions: 3072, fixed in this pilot
Batch size: Up to 16 texts
Input: 8000 characters per text; 24000 combined JSON characters
Index compatibility: Create a separate index and re-embed documents; no Qwen fallback

Full pilot service notes

South Africa regional Azure deployment; 3072 dimensions; 16 texts per batch, 8000 characters per text and 24000 combined JSON characters. Separate index required; no cross-model fallback.

Requests share your workspace’s allowance, rate limit and concurrency limit. Backend capacity varies; some GPU services warm up on demand. Model access does not guarantee immediate capacity.

Make your first request.

Use a server-side workspace API key from Platform → API keys. Examples use https://api.embiro.ai/v1 and the exact pilot model ID.

API model IDtext-embedding-3-large

POST/v1/embeddings

Your workspace key must have access to this model.

# Set EMBIRO_API_KEY in your shell first.
: "${EMBIRO_API_KEY:?Set your workspace API key first}"
curl --fail-with-body --silent --show-error "https://api.embiro.ai/v1/embeddings" \
  -H "Authorization: Bearer $EMBIRO_API_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "text-embedding-3-large",
  "input": [
    "Coffee grown in Uganda",
    "Coffee from East Africa"
  ],
  "encoding_format": "float"
}
JSON

What comes back

A 3072-value vector for each input in data[].embedding.

Cold starts, errors and safe retries

Use the Queued job example when a request can wait for compute. Save its ID and poll that job.
For 401/403, check the key and its model permissions. For 400, check the request and format limits.
Respect Retry-After on 429/503. A timeout after dispatch can be ambiguous; check request logs before submitting again.
These examples do not automatically retry paid work. A job retry must reuse the saved idempotency key and identical payload.

Open API reference

Under the hood.

Publisher specifications. These do not override the Embiro service limits above.

Published context: 8K
Parameters: Not disclosed
Model size: Managed

Publisher context: 8191 tokens. Embiro pilot accepts up to 8000 characters per text; fixed 3072 dimensions. Re-embed documents in a separate index when switching models.

Read the publisher’s model card

No verified benchmark scores are listed in this catalogue for this model.