Replit-Code-v1 (3B) overview
Replit-Code-v1 (3B) by Replit
Access Replit's 2.7B parameter code completion model, along with 100+ AI Models. 20 Supported programming languages in your hands.
Replit-Code-v1 (3B) specs
- Developer
- Replit
- Input
- Text
- Output
- Text
- API
- OpenAI-compatible, base URL
https://api.aimlapi.com/v1
Replit-Code-v1 (3B) Description
- Model Type: Causal Language Model
Overview
replit-code-v1-3b is a 2.7B parameter Causal Language Model developed by Replit, Inc. The model is focused on code completion and has been trained on a diverse dataset of 20 programming languages, including Markdown, Java, JavaScript, Python, and more, totaling 525B tokens.
Key Features
- Extensive permissively licensed training data
- State-of-the-art results on HumanEval and Multi-PLe benchmarks
- Broad multi-language support for Replit's top 30 programming languages
- Latest techniques like Flash Attention, AliBi positional embeddings, and LionW optimizer
- High-quality curated training data with specialized filtering and cleaning
Intended Use
The model is intended to be used by anyone as a foundation for application-specific fine-tuning without strict limitations on commercial use.
Language Support
The model supports 20 different programming languages: Markdown, Java, JavaScript, Python, TypeScript, PHP, SQL, JSX, reStructuredText, Rust, C, CSS, Go, C++, HTML, Vue, Ruby, Jupyter Notebook, R, Shell.
Architecture
The model utilizes advanced techniques like Flash Attention and AliBi positional embeddings to enable efficient training and inference on long input sequences.
Use cases
- code completion in IDEs and programming tools for a wide variety of programming languages
- automatic generation of code snippets based on comments or partial code
- software development assistants for debugging, refactoring, and suggestions
- educational tools for teaching coding with example completions
- research into code generation and program synthesis using LLMs
- foundation for fine-tuning on domain-specific programming languages or tasks
Capabilities
- Function calling
- Streaming
- Structured outputs
Replit-Code-v1 (3B) API pricing
| Usage | Price | Unit |
|---|---|---|
| Input | $0.105 | 1M tokens |
| Output | $0.105 | 1M tokens |
Replit-Code-v1 (3B) is deprecated 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.
Replit-Code-v1 (3B) vs other models: token prices
AI/ML API input and output rates for 5 models, per million tokens.
| Model | Input | Output |
|---|---|---|
 Replit-Code-v1 (3B) | $0.105 | $0.105 |
 Small 3 | $0.0529 | $0.0846 |
 RedPajama-INCITE Chat (3B) | $0.105 | $0.105 |
 Gemma 3 (4B) | $0.0529 | $0.1058 |
| Reka Edge | $0.1058 | $0.1058 |
Models similar to Replit-Code-v1 (3B)
Related articles
Replit-Code-v1 (3B) FAQ
How much does Replit-Code-v1 (3B) cost?
Replit-Code-v1 (3B) is priced at input $0.105 / 1M, output $0.105 / 1M.
Does Replit-Code-v1 (3B) support streaming?
Yes, Replit-Code-v1 (3B) can stream responses as they are generated.
Does Replit-Code-v1 (3B) support tool calling and structured outputs?
Yes, Replit-Code-v1 (3B) supports both function calling and structured outputs.
Who created Replit-Code-v1 (3B)?
Replit-Code-v1 (3B) was built by Replit.
What API endpoint does Replit-Code-v1 (3B) use?
It is accessed via the v1 endpoint.