Pricing
Exploration
Start building with pay-as-you-go simplicity.
Perfect for prototyping, testing, and small-scale applications
- Instant access to popular Cerebras- supported models
- Standard 16k/32k context length
- No minimum commitment – pay only for what you use
- Community support via Discord
Pay per token available
*Llama API coming soon
Growth
Scale your production workloads with confidence.
Perfect for growing teams, production applications, and consistent workloads
Everything in Exploratory, plus:
- Higher rate limits (300+ RPM)
- Higher request priority (lower latency at high traffic times)
- Early access to upcoming models and API features
- Monthly subscription with predictable costs
- Prioritized support via Slack
Monthly subscription starting at $1500/month
Enterprise
Mission-critical performance with white-glove support.
Perfect for large-scale deployments, regulated industries, and organizations requiring guaranteed performance
Everything in Exploratory, plus:
- Access to all Cerebras-supported models and support for fine-tuned models
- Highest rate limits for production workloads
- Lowest latency with dedicated queue priority
- Extended context length support (up to 128k)
- Custom pricing tailored to your usage
- Dedicated deployment options
- Model fine-tuning and training services available
- Dedicated support team with response time guarantees
Exploration
Start building with pay-as-you-go simplicity. Perfect for prototyping, testing, and small-scale applications
*Preview models are intended for evaluation purposes only, and are not intended for use in production environments. They may be discontinued at short notice.
Growth
Scale your production workloads with confidence.
Perfect for growing teams, production applications, and consistent workloads
Qwen3 32B
Llama-4 Scout 17B
Llama-3.3 70B
DeepSeek R1
Llama-70B Distilled
Llama-3.1 8B
ENTERPRISE
Transform your enterprise AI capabilities with our premium offering built for mission-critical deployments. Get access to the best of our models and capabilities, guaranteed performance SLAs, and white-glove support. If you're looking to explore how our enterprise solution can power your most demanding workloads, our expert team can walk through the specifics and design a solution tailored to your needs.
