Sold by: Jina AI
Deployed on AWS
Efficient code embeddings from code generation models
Overview
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.
Highlights
- Multilingual support (15+ programming languages) and compatibility with a wide range of domains, including web development, software development, machine learning, data science, and educational coding problems.
- Task-specific instruction prefixes for NL2Code, Code2Code, Code2NL, Code2Completion, and Technical QA, which can be selected at inference time.
- Flexible embedding size: dense embeddings are 896-dimensional by default but can be truncated to as low as 64 with minimal performance loss.
Details
Sold by
Categories
Delivery method
Latest version
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Trust Center
Access real-time vendor security and compliance information through their Trust Center powered by Drata or Vanta. Review certifications and security standards before purchase.
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/host/hour |
|---|---|---|
ml.g5.xlarge Inference (Batch) Recommended | Model inference on the ml.g5.xlarge instance type, batch mode | $2.50 |
ml.g5.xlarge Inference (Real-Time) Recommended | Model inference on the ml.g5.xlarge instance type, real-time mode | $2.50 |
ml.p2.xlarge Inference (Batch) | Model inference on the ml.p2.xlarge instance type, batch mode | $2.30 |
ml.p2.8xlarge Inference (Batch) | Model inference on the ml.p2.8xlarge instance type, batch mode | $18.00 |
ml.p2.16xlarge Inference (Batch) | Model inference on the ml.p2.16xlarge instance type, batch mode | $35.00 |
ml.p3.2xlarge Inference (Batch) | Model inference on the ml.p3.2xlarge instance type, batch mode | $7.00 |
ml.p3.8xlarge Inference (Batch) | Model inference on the ml.p3.8xlarge instance type, batch mode | $25.00 |
ml.p3.16xlarge Inference (Batch) | Model inference on the ml.p3.16xlarge instance type, batch mode | $48.25 |
ml.g4dn.xlarge Inference (Batch) | Model inference on the ml.g4dn.xlarge instance type, batch mode | $1.50 |
ml.g4dn.2xlarge Inference (Batch) | Model inference on the ml.g4dn.2xlarge instance type, batch mode | $2.20 |
Dimensions summary
You pay by the hour for the compute instance that runs the code embedding model. Pricing depends on two choices: the inference mode and the instance size. Batch mode covers offline processing across P2, P3, G4dn, and G5 instance families. Real-time mode covers live requests and adds more G5 sizes, up to the g5.48xlarge. Within each family, larger instance sizes carry higher hourly rates because they provide more GPU and compute capacity. You select the instance that fits your throughput needs and pay only for the hours it runs.
Top-of-mind questions for buyers
One HostHrs unit is one hour that your chosen instance runs the embedding model. You pay for wall-clock hours the instance stays deployed, whether or not requests arrive. A real-time endpoint accrues charges continuously while running. A stopped or torn-down instance stops accruing software charges.
Batch mode meters instance-hours for offline jobs that process embeddings in bulk, then release the instance. Real-time mode meters hours for a live endpoint that stays running to answer requests as they arrive. Batch suits scheduled workloads; real-time suits always-on serving. Both bill by the hour.
For text inputs, tokens are counted in the standard way based on text length. A token can range from a single character to a whole word. This model supports inputs up to 32,768 tokens. Note that instance charges here bill by the hour, not by token count.
jina.ai
Helpful?
Vendor refund policy
Refunds to be processed under the conditions specified in EULA.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Amazon SageMaker model
An Amazon SageMaker model package is a pre-trained machine learning model ready to use without additional training. Use the model package to create a model on Amazon SageMaker for real-time inference or batch processing. Amazon SageMaker is a fully managed platform for building, training, and deploying machine learning models at scale.
Deploy the model on Amazon SageMaker AI using the following options:
Version release notes
Bug fixes
Additional details
Inputs
- Summary
The model accepts JSON inputs. Texts must be passed in the following format.
https://github.com/jina-ai/jina-sagemaker/blob/main/examples/sample-inference-code-500m-input.json
- Input MIME type
- text/csv
https://github.com/jina-ai/jina-sagemaker/blob/main/examples/sample-inference-code-500m-input.json
https://github.com/jina-ai/jina-sagemaker/blob/main/examples/sample-batch-input.csv
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
data | Texts to embed | n/a | Yes |
parameters.task | Task type:
nl2code.query, nl2code.passage, code2code.query, code2code.passage,
code2nl.query, code2nl.passage, code2completion.query, code2completion.passage,
qa.query, qa.passage.
nl2code.query
Find the most relevant code snippet given the following query.
nl2code.passage
Candidate code snippet.
code2code.query
Find an equivalent code snippet given the following code snippet.
code2code.passage
Candidate code snippet.
code2nl.query
Find the most relevant comment given the following code snippet.
code2nl.passage
Candidate comment.
code2completion.query
Find the most relevant completion given the following start of code snippet.
code2completion.passage
Candidate completion
qa.query
Find the most relevant answer given the following question.
qa.passage
Candidate answer. | - | No |
Support
Vendor support
We provide support for this model package through our enterprise support channel:
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
Efficient code embeddings from code generation models
Text embedding model (base) for Coding Languages with input of size up to 8192 tokens
Jina Embeddings v5 Text Small is a 677M-parameter multilingual text embedding model with a 32K-token context window, Matryoshka dimensions from 32 to 1024, and task-specific LoRA adapters for retrieval, classification, separation, and text matching across 30+ languages.
Jina Embeddings v5 Omni Small is a 1.56B-parameter multimodal embedding model that maps text, images, video, audio, and PDFs into a single shared vector space, with a 32K-token text context, Matryoshka dimensions from 32 to 1024, and task-specific LoRA adapters for retrieval, classification, clustering, and text matching across 30+ languages.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.