Qwen3 Reranker 8B

Overview

Scores how well each document answers a query, so a retriever’s top 50 can be cut to the 5 worth sending to a model. Sits between search and synthesis: embeddings decide what to fetch, this decides what survives. A 40K window means whole documents can be judged without chunking.

Specs

Field	Value
Model ID	`qwen3-reranker-8b`
Best for	Cutting retrieval noise before it reaches the context window
Context window	40,960
Input modalities	Text
Output modalities	Text
Speed	Medium
Cost band	Cheap
Release stage	Stable

Pricing

	Per 1M tokens
Input	$0.135
Output	$0.00

Example

from openai import OpenAI

client = OpenAI(base_url="https://kymaapi.com/v1", api_key="kyma-...")

# Reranking is POST /v1/rerank — it takes a query and documents.
response = client.post(
    "/rerank",
    body={"model": "qwen3-reranker-8b", "query": "...", "documents": ["...", "..."]},
)

Agent query example

Ask the API which models fit, instead of hardcoding an id:

curl "https://kymaapi.com/v1/models?recommended_for=search-documents&quality_tier=strong"

​Overview

​Specs

​Pricing

​Example

​Agent query example

Overview

Specs

Pricing

Example

Agent query example