8 months ago
2 weeks left - Speed Up Your GPT-OSS Hackathon Build with Groq
Hey builders,
Two weeks left in the OpenAI Open Model Hackathon. If your GPT-OSS project needs fast inference and more compute, we have a cool update: $25 in Groq API credits.
Why Groq for GPT-OSS:
- 1000+ tokens/sec for gpt-oss-20b, 500+ tokens/sec for gpt-oss-120b
- Built-in browser search & code execution enabled
- 128K context with consistent sub-millisecond latency
Get your credits:
- Sign up for free at console.groq.com
- Upgrade to developer tier at https://console.groq.com/settings/billing/plans
- Go to console.groq.com/settings/billing/promo
- Enter code: OPENAIOSSGROQ2025
Quick Start:
- Generate your Groq API key at https://console.groq.com/keys
- Choose your model:
- openai/gpt-oss-20b
- openai/gpt-oss-120b
- Use the Python or TypeScript SDKs and OpenAI-compatible Chat Completions and Responses APIs for your build:
curl https://api.groq.com/openai/v1/chat/completions \ -H "Authorization: Bearer $GROQ_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "openai/gpt-oss-120b", "messages": [ { "role": "user", "content": "Explain why fast inference is critical for reasoning models" } ] }'
Resources:
- Docs: console.groq.com/docs
- Templates: github.com/build-with-groq
- API Cookbook: github.com/groq/groq-api-cookbook
- Community: community.groq.com (reach out to us here if you need help or have feedback for our engineering team)