We’re expanding access to GroqCloud™, ramping up our Developer Tier which is a self-serve access point (or upgrade if you’ve been using our Free Tier up until now). It’s easy – now anyone with a credit card can sign up for our Developer Tier to pay-as-you-go, getting on-demand access to GroqCloud™. Here are some of the key benefits of joining our Developer Tier.
Increased Rate Limits
We’re ready to onboard you to fast AI inference that can grow with you. If you’re looking for a rate limit increase, we’ve got you (up to 10x more than the free tier!). Simply let our team know what your needs are and we’ll get you served.
Batch API at a 25% Cost Discount
Besides the ease of self-serve access, the Developer Tier also unlocks access to the Batch API! The Batch API offers efficient parallel processing for high-volume workloads – submit 1000s of API requests per batch with guaranteed 24-hour processing time at a 25% cost discount compared to our synchronous APIs. Pricing and details on how to get started here.
Flex Tier Beta Access
Our Flex Tier is now available in beta for all paid customers. It offers on-demand processing when capacity is available, with rapid timeouts if resources are constrained. This tier is perfect for workloads that prioritize fast inference and can gracefully handle occasional request failures. Key benefits include:
- 10x rate limits compared to on-demand rate limits
- Available for llama-3.3-70b-versatile and llama-3.1-8b-instant models
- Pricing remains the same as On-Demand tier during beta
Growing Fast?
Ready to Build?
Create your free API key and move seamlessly to Groq from other providers like OpenAI by changing three lines of code:
- With our OpenAI endpoint compatibility, simply set OPENAI_API_KEY to your Groq API Key.
- Set the base URL.
- Choose your model and run!
Choose from popular text and audio models like DeepSeek R1 Distill Llama 70B, Llama 3.3 70B, and Whisper Large v3. Here are a few other resources our devs love: