StarCoder (16B) overview
StarCoder (16B) specs
- Developer
- BigCode
- Input
- Text
- Output
- Text
- API
- OpenAI-compatible, base URL
https://api.aimlapi.com/v1
StarCoder (16B) Description
- Model Type: Text (Code generation)
Overview
The bigcode/starcoder model is a 15.5 billion parameter language model developed by BigCode, a project focused on the open and responsible development of large language models for code. It is designed to assist developers with a wide range of coding tasks, including code generation, completion, and infilling.
Key Features
- Multi-Query Attention architecture: Allows the model to attend to multiple queries simultaneously, improving its ability to understand and generate code.
- 8192 token context window: Enables the model to consider a large amount of context when generating code, resulting in more coherent and relevant outputs.
- Fill-in-the-Middle objective: The model is trained using a novel objective that involves filling in missing code segments, helping it learn to understand and generate code at a deeper level.
- Supports multiple programming languages: bigcode/starcoder is trained on over 80 programming languages, making it a versatile tool for developers working in various languages.
Intended Use
The bigcode/starcoder model is intended for use in scenarios where developers need assistance with coding tasks, such as:
- Generating code snippets based on natural language descriptions
- Completing partially written code
- Infilling missing code segments
- Assisting with code refactoring and optimization
Language Support
The model supports over 80 programming languages, including popular ones like Python, Java, JavaScript, C++, and Go. It also supports multiple natural languages, with English being the predominant language used in the training data.
Architecture
The bigcode/starcoder model is based on the GPT-2 architecture, with a few key modifications:
- Multi-Query Attention: The model uses a novel attention mechanism that allows it to attend to multiple queries simultaneously, improving its ability to understand and generate code.
- Transformer-based: Like GPT-2, bigcode/starcoder is a transformer-based model, which means it uses a series of transformer blocks to process the input and generate the output.
Use cases
- Programming assistance and coding automation across multiple languages
- Large-scale codebase analysis and refactoring
- Educational tools for programming learning and tutoring
- Integration in IDEs and developer tools
- Automated code reviews and documentation generation
Capabilities
- Function calling
- Streaming
- Structured outputs
StarCoder (16B) API pricing
| Usage | Price | Unit |
|---|---|---|
| Input | $0.315 | 1M tokens |
| Output | $0.315 | 1M tokens |
StarCoder (16B) is unlisted on AI/ML API. The rates apply to existing integrations; the models below are current alternatives.
Prices from the AI/ML API price list, checked on Nov 4, 2026.
StarCoder (16B) vs other models: token prices
AI/ML API input and output rates for 5 models, per million tokens.
| Model | Input | Output |
|---|---|---|
 StarCoder (16B) | $0.315 | $0.315 |
 Seed 1.6 Flash | $0.0794 | $0.3174 |
 Ministral 3 8B 2512 | $0.3174 | $0.3174 |
| Voxtral Small 24B 2507 | $0.1058 | $0.3174 |
 gpt-oss-safeguard-20b | $0.0794 | $0.3174 |
Models similar to StarCoder (16B)
Related articles
StarCoder (16B) FAQ
How much does StarCoder (16B) cost?
StarCoder (16B) is priced at input $0.315 / 1M, output $0.315 / 1M.
Does StarCoder (16B) support streaming?
Yes, StarCoder (16B) can stream responses as they are generated.
Does StarCoder (16B) support tool calling and structured outputs?
Yes, StarCoder (16B) supports both function calling and structured outputs.
Who created StarCoder (16B)?
StarCoder (16B) was built by BigCode.