GreenPT / greenpt/green-rerank
Green Rerank - access through LLMTR
Green Rerank compares a query against a list of candidate documents, gives each one a relevance score and orders them by it. The typical use is to pass the top fifty results from an embedding search through this model and keep the highest-scoring few. It offers a 32,000-token context window and prices on input tokens only, which makes it far cheaper than a chat model because it produces no text, only scores. In measurement a single request with a thousand documents was answered without trouble. Evaluate ranking quality on your own data: in the one sample we have, on a three-document set, the model gave its highest score to a document unrelated to the query. That single observation is not a benchmark, but it is reason enough not to put this in front of a retrieval pipeline without comparing it against your own baseline. On very long documents the provider does not truncate — it fails the whole request — so split documents before sending them.
Technical specifications
| Canonical ID | greenpt/green-rerank |
|---|---|
| Provider | GreenPT |
| Context window | 32,000 tokens |
| Operations | RERANK |
| Modalities | text |
Pricing
An 8% platform margin applies to credit top-ups; model usage prices are not separately marked up.
| Operation | Metric | Unit | Price |
|---|---|---|---|
| RERANK | INPUT_TEXT | PER_1M_TOKENS | $0.146437 |
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-rerank","messages":[{"role":"user","content":"Hello"}]}'Guides about this model
- Why the Sub-Processor Clause Decides an LLM API Contract - Examines the sub-processor clauses of a data processing agreement and why they matter even more in proxy architectures.
- EU-Hosted LLM Models: Reading a 38-Row Catalog - Separates the EU category's 38 rows into chat, embedding and reranking, and gives a selection framework based on measured capabilities.
- How to Use GreenPT Models Through LLMTR - Covers using GreenPT rows through LLMTR, including the hidden system instruction and default reasoning that drive cost.
Related models
- Kimi K3 greenpt/kimi-k3-eu
- GLM-5.3 greenpt/glm-5.3-eu
- GLM-5.3 Flash greenpt/glm-5.3-flash-eu
- Kimi K2.7 Code greenpt/kimi-k2.7-code-eu
- Kimi K2.6 greenpt/kimi-k2.6-eu
- MiniMax M2.5 greenpt/minimax-m2.5-eu
- DeepSeek V4 Flash greenpt/deepseek-v4-flash-0731
- GLM-5.2 greenpt/glm-5.2-eu