Text embeddings

all-MiniLM-L6-v2

Sentence Transformers · open weights

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

Dominated: EmbeddingGemma 300M scores higher and costs less. As of .

What was measured

BoardMean (Task)Mean (TaskType)TasksRevision
MTEB(eng, v2)59.0355.9341 of 418b3219a92973c328a8e22fadcfa821b5dc75636a

By task type: Classification 69.25 · Clustering 44.9 · PairClassification 82.37 · Reranking 47.14 · Retrieval 42.92 · STS 78.95 · Summarization 25.96

What sellers charge

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

SellerAs the seller states itConditionsNormalised per 1M input tokensSource
DeepInfra5e-9 per_token$0.0050 per token × 1,000,000api.deepinfra.com read 2026-09-19 · feed
OpenRouter5e-9 per_tokencontext 512$0.0050 per token × 1,000,000openrouter.ai read 2026-09-19 · feed

Provenance

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.