TheRouter.aiTheRouter.ai
Back to Models

Qwen Text Embedding v4

qwenqwen/text-embedding-v4

Latest multilingual text embedding from Qwen — default for new projects.

text-embedding-v4 is the latest generation of Qwen's general-purpose multilingual text embedding. It is the recommended choice for new RAG indices, semantic search, clustering, and classification workloads — higher retrieval quality than v3 at the same headline price.

Same OpenAI-compatible `/v1/embeddings` surface as v3, so migration is a model-ID swap plus a one-off reindex. TheRouter routes between bailian-cn and bailian-sg per request based on cost.

Latest generation
Default Qwen embedding model for new projects — improved retrieval quality over v3.
Multilingual
Chinese, English, and other major languages share a consistent vector space.
8K input window
Embed long passages without aggressive chunking — covers most RAG document slices.
Dual-region routing
Selector picks bailian-cn or bailian-sg per request based on cost.
When to use
New RAG indices, semantic search, clustering, classification, deduplication — any project starting today that needs multilingual embeddings.
When not to use
Existing indices built on text-embedding-v3 unless you can afford the reindex cost — vectors are not comparable across embedding generations.
Pricing: $0.12 per MTok of input. TheRouter routes to the cheaper of bailian-cn / bailian-sg per request.
Context Length
8K
Max Output
--
Input Priceper 1M tokens
$0.144/ 1M tokens

Modalities

text→embedding

Pricing Breakdown

TypeRate
Input$0.144 / 1M tokens

Supported Parameters

inputdimensionsencoding_format

API Usage Examples

Use the global api.therouter.ai endpoint shown below for new integrations; the legacy China accelerated endpoint is retired.

cURL
curl https://api.therouter.ai/v1/chat/completions   -H "Content-Type: application/json"   -H "Authorization: Bearer $THE_ROUTER_API_KEY"   -d '{
    "model": "qwen/text-embedding-v4",
    "messages": [
      {"role": "user", "content": "Summarize the key points from this input."}
    ]
  }'
Customer Support