---
title: "all-mpnet-base-v2 — text embeddings score and price · Undominated.ai"
canonical: https://undominated.ai/embeddings/sentence-transformers__all-mpnet-base-v2/
description: "all-mpnet-base-v2 by Sentence Transformers: MTEB(eng, v2) partial, 33 of 41; $0.0050 per 1M input tokens at DeepInfra; 2 sellers; as of 2026-09-19. Every figure traces to its source."
---

# all-mpnet-base-v2 — text embeddings score and price · Undominated.ai

> all-mpnet-base-v2 by Sentence Transformers: MTEB(eng, v2) partial, 33 of 41; $0.0050 per 1M input tokens at DeepInfra; 2 sellers; as of 2026-09-19. Every figure traces to its source.

[Text embeddings](/embeddings/)

# all-mpnet-base-v2

Sentence Transformers · open weights

$0.0050 per 1M input tokens, cheapest of 2 sellers (DeepInfra)

Verdict: unrated. As of 2026-09-19 .

## What was measured

| Board | Mean (Task) | Mean (TaskType) | Tasks | Revision |
| --- | --- | --- | --- | --- |
| MTEB(eng, v2) | — | — | 33 of 41 | 84f2bcc00d77236f9e89c8a360a00fb1139bf47d |

This model has 33 of the benchmark's 41 tasks in the results repository, so it has no mean and is not ranked. That is a statement about the public results, not about the model.

By task type: Classification — · Clustering — · PairClassification 83.04 · Reranking 48.41 · Retrieval — · STS 80.36 · Summarization 23.73

## What sellers charge

Spread across 2 distinct sellers: **1×** between cheapest and dearest at the reference unit.

| Seller | As the seller states it | Conditions | Normalised per 1M input tokens | Source |
| --- | --- | --- | --- | --- |
| DeepInfra | 5e-9 per_token | — | $0.0050 per token × 1,000,000 | api.deepinfra.com read 2026-09-19 · feed |
| OpenRouter | 5e-9 per_token | context 512 | $0.0050 per token × 1,000,000 | openrouter.ai read 2026-09-19 · feed |

## Provenance

 - Quality: https://github.com/embeddings-benchmark/results, licensed cc0-1.0.
 - Prices: https://api.deepinfra.com/models/list , https://openrouter.ai/api/v1/embeddings/models
 - Built 2026-09-19 from the catalogue snapshot in this repository.

MTEB results, https://github.com/embeddings-benchmark/results, released under CC0-1.0; MTEB(eng, v2) means computed from the per-task files as described in data/modalities/embeddings/benchmark.json.