Koala (7B) overview
Koala (7B) by BAIR
Koala (7B) is an open-source large language model developed by BAIR, offering ChatGPT-level performance with a 7B parameter architecture.
Koala (7B) specs
- Developer
- BAIR
- Input
- Text
- Output
- Text
- API
- OpenAI-compatible, base URL
https://api.aimlapi.com/v1
Basic Information
- Developer/Creator: Berkeley Artificial Intelligence Research (BAIR) Lab
- Model Type: Large Language Model (LLM)
Koala (7B) is an open-source large language model developed by the Berkeley Artificial Intelligence Research (BAIR) Lab. It is designed to be a high-quality chatbot that rivals popular models like ChatGPT in terms of performance and capabilities.Key Features:
- High-quality performance comparable to ChatGPT
- Open-source and freely available for research and development
- Efficient 7 billion parameter architecture
- Fine-tuned on carefully curated datasets
Intended Use:
Koala is primarily intended for research purposes and as a foundation for developing advanced conversational AI applications.Language Support: English (primary), with potential for multilingual capabilities.
Architecture
Koala (7B) is based on the LLaMA architecture, specifically utilizing the 7B parameter version of LLaMA as its foundation. The model employs a transformer-based architecture, which has become the standard for state-of-the-art language models.
Training Data
The Koala model was fine-tuned on a carefully curated dataset comprising:
- Anthropic's Helpful and Harmless (HH) dataset: This dataset consists of 67,000 human-AI conversation samples, focusing on helpful and safe interactions.
- Open-Assistant conversations: A dataset of 9,000 samples from the Open-Assistant project, which aims to create open-source AI assistants.
- Stanford Alpaca data: A dataset of 52,000 instruction-following demonstrations, generated using self-instruct techniques.
Data Source and Size
The total fine-tuning dataset for Koala consists of approximately 128,000 samples, combining the aforementioned sources. This relatively small dataset size demonstrates the efficiency of the fine-tuning process.
Knowledge Cutoff
The knowledge cutoff date for Koala (7B) is not explicitly stated in the available information. However, given its release date in April 2023, it's reasonable to assume that the model's knowledge is current up to early 2023.
Capabilities
- Function calling
- Streaming
- Structured outputs
- Web search
Koala (7B) API pricing
| Usage | Price | Unit |
|---|---|---|
| Input | $0.21 | 1M tokens |
| Output | $0.21 | 1M tokens |
Koala (7B) 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.
Koala (7B) vs other models: token prices
AI/ML API input and output rates for 5 models, per million tokens.
| Model | Input | Output |
|---|---|---|
 Koala (7B) | $0.21 | $0.21 |
 Small 3.2 24B | $0.0794 | $0.2116 |
 Nemotron 3 Nano 30B A3B | $0.0529 | $0.2116 |
| Nemotron 3.5 Content Safety | $0.2116 | $0.2116 |
| Reka Flash 3 | $0.1058 | $0.2116 |
Models similar to Koala (7B)
Related articles
Koala (7B) FAQ
Does Koala (7B) support streaming?
Yes, Koala (7B) can stream responses as they are generated.
Does Koala (7B) support tool calling and structured outputs?
Yes, Koala (7B) supports both function calling and structured outputs.
Who created Koala (7B)?
Koala (7B) was built by BAIR.
Does Koala (7B) support web search?
Yes, Koala (7B) includes web search as one of its capabilities.