GreenPT / greenpt/green-embedding

Green Embedding - access through LLMTR

Green Embedding is the provider's own embedding model, running on its own infrastructure and producing a 2560-dimension vector per input. Its 32,000-token context window lets you vectorize long documents without splitting them. It emits fewer dimensions than the Qwen3 Embedding 8B row on the same provider, so it takes less room in a vector database. We ran no retrieval-quality comparison between the two; measure on your own collection which one serves you. Pricing is on input tokens only. The provider's catalog carries a second identifier for this model; in measurement the vectors returned under both identifiers were bit-for-bit identical for the same input, so it is listed here once.

Technical specifications

Canonical IDgreenpt/green-embedding
ProviderGreenPT
Context window32,000 tokens
OperationsEMBEDDINGS
Modalitiestext, embedding

Pricing

An 8% platform margin applies to credit top-ups; model usage prices are not separately marked up.

OperationMetricUnitPrice
EMBEDDINGSINPUT_TEXTPER_1M_TOKENS$0.244062

Example usage

With existing OpenAI SDK flows, change only the base URL and model identifier.

curl https://llmtr.com/v1/chat/completions   -H "Authorization: Bearer llmtr-your_key"   -H "Content-Type: application/json"   -d '{"model":"greenpt/green-embedding","messages":[{"role":"user","content":"Hello"}]}'

Guides about this model

Related models