EmbeddingGemma 300M
Google · open weights
$0.0020 per 1M input tokens, cheapest of 1 seller (DeepInfra)
What was measured
| Board | Mean (Task) | Mean (TaskType) | Tasks | Revision |
|---|---|---|---|---|
| MTEB(eng, v2) | 69.67 | 65.11 | 41 of 41 | 64614b0b8b64f0c6c1e52b07e4e9a4e8fe4d2da2 |
By task type: Classification 87.55 · Clustering 56.55 · PairClassification 87.29 · Reranking 47.43 · Retrieval 55.69 · STS 83.61 · Summarization 37.64
What sellers charge
| Seller | As the seller states it | Conditions | Normalised per 1M input tokens | Source |
|---|---|---|---|---|
| DeepInfra | 2e-9 per_token | — | $0.0020 per token × 1,000,000 | api.deepinfra.com read 2026-09-19 · feed |
Provenance
- Quality: https://github.com/embeddings-benchmark/results, licensed cc0-1.0.
- Prices: https://api.deepinfra.com/models/list
- 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.