What\u2019s new at Groq
Fastest AI inference on the planet
- improvement minor
GroqCloud: Expanding to Meet Demand
Groq announces expansion of GroqCloud platform capabilities to meet growing customer demand. The expansion includes infrastructure improvements and capacity increases.
- other major
Groq Raises $650M to Scale Its AI Inference Cloud Business
Groq secured $650 million in funding to scale their AI inference cloud business operations. The capital will support infrastructure expansion and business growth.
- other minor
Groq Becomes an NVIDIA Cloud Partner
Groq announces partnership with NVIDIA as an official cloud partner. This partnership expands Groq's integration with NVIDIA's AI infrastructure ecosystem.
- other major
Groq Closes $350 million Series A, Building the World's Leading AI Inference Cloud
Groq completed a $350 million Series A funding round to build and scale their AI inference cloud infrastructure. The funding will support expansion of their inference capabilities.
- feature major
Groq Among the First to Bring NVIDIA Groq 3 LPX and Vera Rubin NVL72 to Market
Groq announces partnership to bring NVIDIA's latest Groq 3 LPX and Vera Rubin NVL72 hardware to market. This represents an expansion of Groq's AI inference hardware offerings.
- other major
Groq Raises $650M to Scale Its AI Inference Cloud Business
Groq secured $650 million in funding to scale its AI inference cloud operations and infrastructure.
- other major
Groq Becomes an NVIDIA Cloud Partner
Groq entered into a cloud partnership with NVIDIA to enhance AI inference capabilities.
- other major
Groq Closes $350 million Series A, Building the World's Leading AI Inference Cloud
Groq completed a $350 million Series A funding round to expand its AI inference cloud infrastructure.
- feature major
Groq Among the First to Bring NVIDIA Groq 3 LPX and Vera Rubin NVL72 to Market
Groq announces partnership to bring NVIDIA's latest Groq 3 LPX and Vera Rubin NVL72 hardware to market. This represents an expansion of Groq's hardware offerings through their NVIDIA partnership.
- feature major
Groq Among the First to Bring NVIDIA Groq 3 LPX and Vera Rubin NVL72 to Market
Groq announces partnership to bring NVIDIA's latest Groq 3 LPX and Vera Rubin NVL72 hardware to market. This represents an expansion of Groq's hardware offerings through strategic NVIDIA collaboration.
- other major
Groq Closes $350 million Series A, Building the World's Leading AI Inference Cloud
Groq successfully raises $350 million in Series A funding to expand their AI inference cloud infrastructure. The funding will support scaling their cloud business operations.
- other major
Groq Closes $350 million Series A, Building the World's Leading AI Inference Cloud
Groq successfully raises $350 million in Series A funding to expand its AI inference cloud infrastructure. The funding will support scaling of the company's inference capabilities globally.
- feature minor
Groq Becomes an NVIDIA Cloud Partner
Groq establishes a cloud partnership with NVIDIA to enhance their AI inference capabilities. This partnership expands Groq's ecosystem integration with NVIDIA's cloud services.
- feature minor
Groq Becomes an NVIDIA Cloud Partner
Groq enters into a cloud partnership with NVIDIA to enhance AI inference capabilities. This partnership expands Groq's ecosystem integration with NVIDIA's cloud infrastructure.
- other major
Groq Becomes an NVIDIA Cloud Partner
Groq announced a partnership with NVIDIA to become an official cloud partner. This collaboration aims to enhance AI inference capabilities through NVIDIA's cloud infrastructure.
- feature major
Groq Expands to Asia-Pacific with Sydney Data Center
Groq launched a new data center in Sydney, Australia to serve the Asia-Pacific region with AI inference capabilities.
- other major
Groq Partners with U.S. Department of Energy
Groq established a partnership with the U.S. Department of Energy to advance AI inference and next-generation computing infrastructure.
- other major
Groq and Nvidia Enter Non-Exclusive Inference Technology Licensing Agreement
Groq partnered with Nvidia through a licensing agreement to accelerate AI inference capabilities at global scale.
- improvement major
GroqCloud: Expanding to Meet Demand
Groq announced expansion of its GroqCloud platform to accommodate growing user demand for AI inference services.
- other major
Groq Raises $650M to Scale Its AI Inference Cloud Business
Groq secured $650 million in funding to expand its AI inference cloud infrastructure and business operations.
- feature major
Prompt Caching
Prompt caching automatically reuses computation from recent requests when they share a common prefix, delivering 50% cost savings for cached portions and improved response times. The feature works automatically with no code changes required.
- feature major
Moonshot AI Kimi K2 Instruct 0905
Kimi K2-0905 brings Moonshot AI's cutting-edge model to GroqCloud with day zero support, featuring a 256K context window and enhanced agentic coding capabilities. The model offers prompt caching with up to 50% cost savings and runs at 200+ tokens/second.
- feature major
OpenAI GPT-OSS 20B & 120B
OpenAI's open-source MoE models with reasoning capabilities, built-in browser search and code execution, and structured outputs support. Performance rivals o4-mini and o3-mini models.
- feature minor
Prompt Caching
Automatic computation reuse for requests with common prefixes, delivering 50% cost savings on cached tokens and improved response times. Rolling out to Kimi K2 with automatic expiration for privacy.
- feature major
Moonshot AI Kimi K2 Instruct 0905
New model release with 256K context window, enhanced agentic coding capabilities, and prompt caching support. Delivers 200+ t/s at $1.50/M tokens blended pricing.
- feature major
Prompt Caching
Automatic computation reuse for requests with common prefixes delivers 50% cost savings on cached tokens with faster response times. Rolling out to Kimi K2 model with automatic expiration for privacy.
- improvement minor
Python SDK v0.31.1, TypeScript SDK v0.32.0
SDK updates improve chat completion message type definitions for better OpenAI compatibility and add support for new Groq Compound tools including Wolfram Alpha and browser automation.
- feature major
Groq Compound and Compound Mini
Production-ready agentic AI systems moved from beta to general availability, integrating web search, code execution, and browser automation in single API calls. Built on GPT-OSS-120B and Llama models.
- feature major
Moonshot AI Kimi K2 Instruct 0905
Latest version of Kimi K2 model with 256K context window, enhanced agentic coding capabilities, and prompt caching support. Delivers 200+ tokens/second at $1.50/M tokens blended pricing.
- feature major
Remote Model Context Protocol (MCP)
Beta integration of Anthropic's MCP standard enables AI models to connect to thousands of external tools through remote MCP servers. Fully compatible with OpenAI APIs for seamless migration with zero code changes.
- feature major
Groq Compound and Compound Mini
Production release of Groq's agentic AI systems that integrate web search, code execution, and browser automation into single API calls. Moved from beta to general availability with improved performance.
- feature major
Moonshot AI Kimi K2 Instruct 0905
Added Kimi K2-0905 model with 256K context window, prompt caching support, and enhanced agentic coding capabilities. Features 200+ t/s performance at $1.50/M tokens blended pricing.
- feature major
Remote Model Context Protocol (MCP)
Beta release of Remote Model Context Protocol server integration on GroqCloud, enabling AI models to connect to thousands of external tools through Anthropic's open MCP standard. Fully compatible with OpenAI APIs for seamless migration.
- feature major
Moonshot AI Kimi K2 Instruct 0905 added
Kimi K2-0905 brings Moonshot AI's cutting-edge model to GroqCloud with enhanced agentic coding capabilities and a 256K context window. The model includes prompt caching for up to 50% cost savings and runs at 200+ tokens/second.
- feature major
Remote Model Context Protocol (MCP) added
Remote Model Context Protocol (MCP) server integration is now available in Beta on GroqCloud, connecting AI models to thousands of external tools through Anthropic's open MCP standard. The implementation is fully compatible with OpenAI APIs, allowing developers to switch from OpenAI to Groq with zero code changes.
- other major
Groq Raises $650M to Scale Its AI Inference Cloud Business
Groq completed a $650 million funding round to expand its AI inference cloud business operations. The funding will support scaling of the company's cloud infrastructure and services.
- feature major
Prompt Caching added
Prompt caching automatically reuses computation from recent requests when they share a common prefix, delivering 50% cost savings for cached portions and improved response times. The feature works automatically with no code changes required and data expires within hours for privacy.
- improvement minor
Python SDK v0.31.1, TypeScript SDK v0.32.0 changed
Updated Python SDK to v0.31.1 and TypeScript SDK to v0.32.0 with improved chat completion message type definitions and added support for new Groq Compound tools. Fixes compatibility issues with different message formats.
- feature major
Moonshot AI Kimi K2 Instruct 0905 added
Kimi K2-0905 brings Moonshot AI's cutting-edge model to GroqCloud with day zero support, featuring a 256K context window and enhanced agentic coding capabilities. The model offers prompt caching with up to 50% cost savings and runs at 200+ tokens/second.
- feature major
Prompt Caching
Automatic prompt caching feature that reuses computation from recent requests with common prefixes, delivering 50% cost savings on cached tokens and improved response times. Initially available for Kimi K2 model.
- improvement minor
Python SDK v0.31.1, TypeScript SDK v0.32.0
SDK updates with improved chat completion message type definitions for better OpenAI compatibility and added support for new Groq Compound tools including Wolfram Alpha and Browser Automation.
- feature major
Groq Compound and Compound Mini
Production-ready agentic AI systems moved from beta to general availability, integrating web search, code execution, and browser automation in a single API call. Built on GPT-OSS-120B and Llama models.
- feature major
Moonshot AI Kimi K2 Instruct 0905
New model release with 256K context window, prompt caching support, and enhanced agentic coding capabilities. Offers 200+ t/s performance at $1.50/M tokens blended pricing.
- feature major
Remote Model Context Protocol (MCP)
Beta release of Remote MCP server integration on GroqCloud, enabling AI models to connect to thousands of external tools through Anthropic's open MCP standard. Fully compatible with OpenAI APIs for seamless migration.
- improvement minor
Python SDK v0.31.1, TypeScript SDK v0.32.0 changed
Updated SDKs with improved chat completion message type definitions for better OpenAI compatibility and added support for new Groq Compound tools including Wolfram Alpha and Browser Automation.
- feature major
Groq Compound and Compound Mini added
Compound and Compound Mini are Groq's production-ready agentic AI systems that integrate web search, code execution, and browser automation into a single API call. Moving from beta to general availability, these systems deliver ~25% higher accuracy and ~50% fewer mistakes across benchmarks.
- feature major
Moonshot AI Kimi K2 Instruct 0905 added
Kimi K2-0905 brings Moonshot AI's cutting-edge model to GroqCloud with enhanced agentic coding capabilities and a 256K context window. The model delivers improved frontend development performance and includes prompt caching for up to 50% cost savings.
- feature major
Remote Model Context Protocol (MCP) added
Remote Model Context Protocol (MCP) server integration is now available in Beta on GroqCloud, connecting AI models to thousands of external tools through Anthropic's open MCP standard. Developers can connect any remote MCP server to models hosted on GroqCloud with zero code changes from OpenAI.
- improvement minor
Python SDK v0.31.1, TypeScript SDK v0.32.0
Updated SDKs with improved chat completion message type definitions for better OpenAI compatibility and added support for new Groq Compound tools including Wolfram Alpha and Browser Automation.
- feature major
Groq Compound and Compound Mini
Compound and Compound Mini are Groq's production-ready agentic AI systems that integrate web search, code execution, and browser automation into a single API call. Moving from beta to general availability, these systems deliver ~25% higher accuracy and ~50% fewer mistakes across benchmarks.