Model catalog
M

Multilingual E5 Large Instruct

Open weights

Multilingual E5 Large Instruct is a embedding model from Intfloat with a 514-token context window. Provider list price is $0.02 per M tokens; on Allocate you pay $0.021. The weights are open under MIT, so you can fine-tune it and own the result.

Pricing

Provider listOn Allocate
Input, per M tokens$0.02$0.021

Prices checked 2026-07-21.

Price against its peers

Multilingual E5 Large Instruct$0.02

Provider list prices per M tokens, Multilingual E5 Large Instruct against its nearest embedding peers by price.

What a real workload costs

Embedding 100M tokens, roughly 75M words of documents, costs 100 × $0.02 = $2 at list, or $2.14 billed on Allocate.

Multilingual E5 Large Instruct is an open-weights model under the MIT license. Fine-tune it on your own data and the weights stay inside your boundary; they belong to you.

Example usage

Point a route at intfloat/multilingual-e5-large-instruct and the endpoint never changes; swap the model behind it whenever you want.

api.allocate.network
curl https://api.allocate.network/v1/chat/completions \
  -H "Authorization: Bearer $ALLOCATE_KEY" \
  -d '{
    "model": "intfloat/multilingual-e5-large-instruct",
    "messages": [{"role": "user",
      "content": "Summarise the attached contract."}]
  }'
200 · intfloat/multilingual-e5-large-instruct · inside your boundary

Common questions

How much does Multilingual E5 Large Instruct cost?

Provider list price is $0.02 per M tokens. On Allocate you pay $0.021.

What context window does Multilingual E5 Large Instruct have?

514 tokens (514). At roughly 0.75 words per token, that is about 0k words of English text per request.

Can I fine-tune Multilingual E5 Large Instruct?

Yes. Multilingual E5 Large Instruct is an open-weights model under the MIT license. The license is permissive, so the fine-tuned weights are yours to use commercially. On Allocate the trained weights stay inside your boundary and belong to you.

How do I call Multilingual E5 Large Instruct on Allocate?

Send intfloat/multilingual-e5-large-instruct in the model field of the OpenAI-compatible endpoint at api.allocate.network/v1, or point a route name (like prod/support-agent) at it so you can swap the model later without a deploy.