Skip to main content
NeuronFeed
Groq

What\u2019s new at Groq

Fastest AI inference on the planet

View profile \u2192 \u00b7 36 updates tracked
  1. 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.

  2. 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.

  3. 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.

  4. improvement major

    GroqCloud: Expanding to Meet Demand

    Groq announced expansion of its GroqCloud platform to accommodate growing user demand for AI inference services.

  5. 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.

  6. 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.

  7. 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.

  8. 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.

  9. 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.

  10. 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.

  11. 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.

  12. 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.

  13. 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.

  14. 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.

  15. 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.

  16. 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.

  17. 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.

  18. 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.

  19. 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.

  20. 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.

  21. 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.

  22. 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.

  23. 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.

  24. 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.

  25. 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.

  26. 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.

  27. 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.

  28. 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.

  29. 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.

  30. 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.

  31. 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.

  32. 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.

  33. 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.

  34. 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.

  35. 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+ t/s at $1.50/M tokens blended pricing.

  36. feature major

    Remote Model Context Protocol (MCP)

    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.