Overview
Groq provides blazing-fast inference for popular open-source models through their custom LPU hardware. Known for exceptional speed while maintaining strong model quality.Available Models
GPT-OSS (20B)
1 credit • Speed-optimized open-weight 20B model. Ideal for real-time, high-volume applications.
- 131K context window
- Good reasoning
- Speed: Extremely_fast • Cost: Very_low
- Model id:
openai/gpt-oss-20b
Qwen 3.8 (27B)
1 credit • Alibaba’s Qwen 3.8 served on Groq’s inference stack, with a 128K context window.
- 131K context window
- Excellent reasoning
- Speed: Very fast • Cost: Low
- Model id:
qwen/qwen3.8-27b
Groq Compound
1 credit • Groq’s own compound system, combining models and tools behind one model id.
- 131K context window
- Excellent reasoning
- Speed: Very fast • Cost: Low
- Model id:
groq/compound
GPT-OSS (120B)
1 credit • Larger open-weight 120B model with strong performance across diverse tasks.
- 131K context window
- Excellent reasoning
- Speed: Fast • Cost: Low
- Model id:
openai/gpt-oss-120b
Setup
Using BoostGPT-Hosted API Keys
1
Select Groq Model
In your BoostGPT dashboard, select any Groq model when creating or configuring your bot.
2
Choose Your Model
- Llama 3.1 Instant: For real-time, ultra-fast responses
- Llama 3.3 Versatile: For balanced performance
- DeepSeek Llama 70B: For reasoning tasks
- Qwen models: For multilingual applications
Using Your Own Groq API Key
- Dashboard Setup
- Core SDK
1
Navigate to Integrations
Go to app.boostgpt.co and select Integrations
2
Select Groq
Find and click on the Groq provider
3
Add API Key
Enter your Groq API key and select which agents will use this key
4
Save Configuration
Click save to apply your custom API key
Performance Benefits
Next Steps
Reasoning Models
Learn about reasoning models on Groq
Model Comparison
Compare Groq with other providers
SDK Reference
Full API documentation
Bring Your Own Key
Use your own Groq API key