Qwen3 Embedding 8B

Overview

This model produces dense vector representations with a 32,768-token context window. It is designed for text-only embedding tasks and does not support reasoning, vision, or structured output generation. On Kyma, it runs as an OpenAI-compatible endpoint behind a single API key. Requests benefit from automatic failover if a serving path degrades, and responses return the exact cost in usage.cost alongside an X-Kyma-Model header. Prompt caching does not apply to embeddings: every input token bills at the input rate. Because it is strictly an embedding model, it returns zero output tokens and cannot generate conversational text. It operates at a medium speed tier, making it better suited for batch indexing or retrieval-heavy workflows than for real-time, low-latency interactive search.

Specs

Field	Value
Model ID	`qwen3-embedding-8b`
Best for	Multilingual retrieval, long documents, high-recall RAG
Context window	32,768
Input modalities	Text
Output modalities	Text
Speed	Medium
Cost band	Cheap
Release stage	Stable

Pricing

	Per 1M tokens
Input	$0.0135
Output	$0.00

Use this when

Multilingual Document Search — Finds relevant passages across different languages without translation overhead.
Long-Form Context Indexing — Embeds full documents up to 32K tokens to avoid aggressive chunking.
High-Recall Retrieval Pipelines — Prioritizes semantic match quality over minimal compute cost for RAG systems.

Not ideal for

Do not use this model for real-time chat, text generation, or tasks requiring sub-100ms latency, as it only outputs vectors and runs at a medium speed tier.

Pick something else when

You need minimal compute cost and fast indexing: use embeddinggemma-300m.

Example

from openai import OpenAI

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

response = client.embeddings.create(
    model="qwen3-embedding-8b",
    input=["first document", "second document"],
)

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=frontier-open"

FAQ

Does this model generate text responses? No, it is strictly an embedding model that outputs 4096-dimensional vectors and returns zero output tokens. How does Kyma handle prompt caching for this endpoint? Prompt caching does not apply to embedding requests: there is no cached rate, and every input token bills at the input rate. Can I use the same API key for this model as I do for others? Yes, Kyma is OpenAI-compatible and uses a single API key across all models at the standard base URL.

​Overview

​Specs

​Pricing

​Use this when

​Not ideal for

​Pick something else when

​Example

​Agent query example

​FAQ