Jina Code Embeddings 0.5b
Paid production API
Type / status: embedding / documented_api
Use cases: Code search, RAG
Embedding dimensions (not output tokens): 896
Supported languages: multilingual
Deployment options: api, huggingface, aws, azure, gcp, airgapped
Documented datacenters: US
Model release date: 2025-09-01
API endpoint: https://api.jina.ai/v1/embeddings
Open-weights license (hosted API terms are separate): CC-BY-NC-4.0
Official catalog input-token price. Embeddings produce vectors and rerankers produce rankings, not billable generated output tokens. Zero catalog completion/image/request values do not make the service free. Reader API billing is separate from the model-catalog price.
The Reader page advertises 10 million free tokens for a new API key. Actual allocation and expiry are subject to the official account; this is a trial, not permanent free access.
Subject to hosted service terms; buying API tokens does not license model weights. Each model has its own weight license. CC-BY-NC-4.0 and Qwen Research License must not be described as unrestricted commercial self-hosting. Official FAQ states API requests, inputs and outputs are not used to train models. Jina legal page directs current data processing to Elastic's Data Processing Addendum. Model catalog lists US datacenters; Reader/Search also document EU endpoints. Do not infer identical regions across products.
Official model ID: jina-ai/jina-code-embeddings-0.5b
Input / output: text → embedding
Model developer: Jina AI · Service provider: Jina AI
Model family: — · Currency: USD
- Input: USD 0.05 / 1,000,000 tokens
jina-code-embeddings-0.5b is a 494 million parameter code embedding model designed for retrieving code from natural language queries, technical Q&A, and identifying similar code across languages. Built on Qwen2.5-Coder-0.5B backbone, it generates embeddings via last-token pooling and addresses the fundamental limitation of traditional code embedding models that rely on scarce aligned data like comments and docstrings. The model leverages abundant unaligned code and documentation used in LLM training, achieving state-of-the-art performance despite its compact size. It supports five task categories with specific instruction prefixes: NL2Code, TechQA, Code2Code, Code2NL, and Code2Completion. The model implements Matryoshka representation learning for truncatable embeddings, allowing flexible precision-resource trade-offs. Endpoint and model identifier are declared in the current OpenAPI schema; authenticated inference was not executed. Endpoint support is documented; authenticated inference was not tested. Embedding dimensions are vector size, not generated tokens.
Documented API context: 32,768 tokens
Official source · Last verified: 2026-10-15T09:33:13.684489+00:00