Groq

Python SDK v1.2.0 preserves hardcoded query params, improves multipart file-copy performance, and adds binary request streaming with a custom JSON encoder; Python 3.9 is deprecated. TypeScript SDK v1.1.2 restores streaming in defaultParseResponse and fixes an abort-signal memory leak and minimatch CVEs.

Two new voices are available for the Orpheus Arabic Saudi TTS model, with Abdullah now the default. The model now supports six voices total.

MiniMax M2.5 general-purpose model and Qwen3-VL 32B Instruct vision-language model are now available on GroqCloud for Enterprise customers. Python SDK v1.2.0 preserves hardcoded query params when merging with user params, ensures file data is sent as a single parameter, and improves multipart request file-copy performance. TypeScript SDK v1.1.2 restored streaming support in defaultParseResponse, fixed an abort-signal memory leak, and patched a minimatch CVE.

Text-to-speech has migrated platform-wide from PlayAI to Orpheus models from Canopy Labs, which offer enhanced expressiveness with vocal direction controls, faster inference, and improved audio quality. Users still on playai-tts or playai-tts-arabic must migrate before the shutdown date listed on the deprecations page.

Groq now offers pre-built MCP Connectors for Google Workspace applications—Gmail, Google Calendar, and Google Drive—with zero configuration and OAuth 2.0 authentication. Available tools include email search and reading, calendar event viewing, and file search and access.

OpenAI's GPT-OSS-Safeguard 20B, an open-weight reasoning model for safety classification, is now available on Groq. The model offers a 131K context window, up to 65K output tokens, ~1000 TPS throughput, prompt caching for 50% cost savings, and supports tool use, code execution, and multiple response formats for Trust & Safety content moderation and policy-based classification tasks.

Automatic prompt caching is now available for openai/gpt-oss-120b, reducing cached input token costs to $0.075/M (from $0.15/M), lowering latency, and increasing effective rate limits since cached tokens do not count toward limits. Python SDK updated to v0.33.0 and TypeScript SDK to v0.34.0 with improved prompt caching support and annotation/citation support for chat completion messages and streamed deltas.

Both SDKs add annotation and citation support to chat completion messages and streamed deltas, with improved prompt caching.

Automatic prompt caching is now available for openai/gpt-oss-20b, reducing cached input token costs by 50% (from $0.075/M to $0.037/M) while lowering latency through automatic prefix matching. No configuration required.

Remote MCP server integration is available in beta on GroqCloud, connecting AI models to thousands of external tools via Anthropic's open MCP standard. The implementation is fully compatible with OpenAI Responses API and OpenAI remote MCP spec, enabling zero-code-change migration from OpenAI to Groq. Supported across eight models including Llama, Qwen, Kimi, and proprietary OSS variants, with launch partner tutorials for BrowserBase, Browser Use, Exa, Firecrawl, HuggingFace, Parallel, Stripe, and Tavily.

Moonshot AI's Kimi K2-0905 model is now available on GroqCloud with day zero support, featuring a 256K context window (largest on GroqCloud), prompt caching for up to 50% savings, and improved agentic coding reliability in multi-turn interactions. Pricing is $1.00/M input and $3.00/M output tokens.

Compound and Compound Mini move from beta to general availability as production-ready agentic AI systems integrating web search, code execution, and browser automation in a single API call. Both models deliver ~25% higher accuracy and ~50% fewer mistakes than OpenAI's Web Search Preview and Perplexity Sonar. Python SDK v0.31.1 and TypeScript SDK v0.32.0 add support for new Compound tool types including Wolfram Alpha and browser automation.

Improved chat completion message type definitions in Python SDK v0.31.1 and TypeScript SDK v0.32.0 for better OpenAI compatibility, fixing errors with certain message formats. Added support for new Groq Compound tool types (Wolfram Alpha, Browser Automation, Visit Website).

Prompt caching automatically reuses computation from recent requests sharing a common prefix, reducing latency and cutting token costs by 50% for cached portions. Rolling out first to Kimi K2 with more models coming; no code changes or additional fees required.

Both SDKs now support high, medium, and low reasoning_effort options and browser_search and code_interpreter tool definition types for GPT-OSS models, which can call them server-side automatically. An optional include_reasoning boolean controls the reasoning field in responses.

OpenAI's open-source Mixture-of-Experts models GPT-OSS 20B and GPT-OSS 120B are now available, featuring 131K context window, 32K max output tokens, reasoning, built-in browser search and code execution, and structured outputs support. Also launched Responses API (Beta), fully compatible with OpenAI's Responses API with support for text/image inputs, stateful conversations, and function calling. Python and TypeScript SDKs added reasoning_effort control and new tool types (browser_search, code_interpreter).

Groq's Responses API, now in beta, is fully compatible with OpenAI's Responses API and supports text and image inputs with text outputs, stateful conversations, and function calling.

Groq now supports structured outputs with JSON schema for moonshotai/kimi-k2-instruct, meta-llama/llama-4-maverick-17b-128e-instruct, and meta-llama/llama-4-scout-17b-16e-instruct. Model responses are guaranteed to conform strictly to a provided JSON schema, eliminating the need for complex parsing logic.

Moonshot AI's Kimi K2 Instruct, a trillion-parameter MoE model with 32 billion activated parameters, is now available, offering a 131K token context window and 16K max output tokens. It surpasses GPT-4.1 on agentic and coding benchmarks and excels at tool use and autonomous problem-solving.

Python SDK v0.30.0 and TypeScript SDK v0.27.0 improve chat completion message type definitions for better OpenAI compatibility. Moonshot AI Kimi K2 Instruct, a 1-trillion-parameter Mixture-of-Experts model with 131K context window and 16K max output tokens, is now available.