{"id":"src_FIDjFbUTi8nPFcHRUVbA7","slug":"groq-changelog","name":"Changelog","type":"scrape","url":"https://console.groq.com/docs/changelog","orgId":"org_GIbvWOHzi7PWCHV2wox65","productId":null,"productSlug":null,"org":{"id":"org_GIbvWOHzi7PWCHV2wox65","slug":"groq","name":"Groq"},"isPrimary":true,"isHidden":false,"discovery":"curated","metadata":"{\"markdownUrl\":\"https://console.groq.com/docs/changelog.md\",\"fetchMethod\":\"markdown\",\"evaluatedMethod\":\"markdown\",\"evaluatedAt\":\"2026-08-11T19:26:54.427Z\",\"parseInstructions\":\"Parse Groq API/platform changelog markdown.\\nOne release per dated day section (e.g. a bare date line like \\\"Apr 18\\\" under year context, or \\\"## YYYY-MM-DD ...\\\" headings).\\nPrefer grouping all Added/Changed/Removed subsections for the same calendar day into one release.\\nTitle: short summary of the lead change that day (prefer the first ### Added/Changed heading text).\\nversion=null unless an explicit SDK/version heading includes one.\\nURL: https://console.groq.com/docs/changelog#<slug-of-lead-heading> when possible.\\npublishedAt: that calendar day at 00:00:00Z (infer year from surrounding context).\\nKeep full markdown body for the day.\\r\\n\",\"sourceActor\":{\"nextAlarmAt\":null,\"lastAlarmAt\":\"2026-08-30T03:42:51.189Z\",\"managed\":false}}","notice":null,"kind":null,"stars":null,"starsFetchedAt":null,"releaseCount":33,"releasesLast30Days":0,"avgReleasesPerWeek":0,"latestVersion":null,"latestDate":"2026-04-18T00:00:00.000Z","changelogUrl":null,"hasChangelogFile":false,"lastFetchedAt":"2026-08-29T23:49:20.244Z","lastPolledAt":"2026-08-29T23:44:52.727Z","changeDetectedAt":null,"trackingSince":"2025-04-14T00:00:00.000Z","releases":[{"id":"rel_yNnDVxxncecG0ou2VbNHv","version":null,"type":"feature","title":"Python SDK v1.2.0 and TypeScript SDK v1.1.2","summary":"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.","titleGenerated":"Groq Python SDK v1.2.0 and TypeScript SDK v1.1.2 ship fixes and streaming","titleShort":"Python SDK streaming, TS SDK memory leak fixed","breaking":"unknown","importance":3,"content":"Following the [v1.0.0 GA in December 2025](https://github.com/groq/groq-python/releases/tag/v1.0.0), both SDKs received a series of updates over Q1.\n\n**Python SDK** ([v1.2.0](https://github.com/groq/groq-python/releases/tag/v1.2.0))\n\n* **v1.2.0** — Preserve hardcoded query params when merging with user params; ensure file data is sent as a single parameter; multipart request file-copy performance improvements; indices array format for query and form serialization.\n* **v1.1.2** — Sanitize endpoint path params; do not pass `by_alias` to Pydantic unless explicitly set; bumped minimum `typing-extensions`.\n* **v1.1.0** — Added support for binary request streaming and a custom JSON encoder for extended type support; deprecated Python 3.9.\n\n**TypeScript SDK** ([v1.1.2](https://github.com/groq/groq-typescript/releases/tag/v1.1.2))\n\n* **v1.1.1** — Restored streaming support in `defaultParseResponse`; fixed an abort-signal memory leak and avoided removing abort listeners too early; preserve URL params already embedded in path; pinned patched `minimatch` versions to address CVE-2026-27….\n* **v1.1.2** — GitHub Actions OIDC token migration; dependency updates.","publishedAt":"2026-04-18T00:00:00.000Z","fetchedAt":"2026-08-14T20:48:54.130Z","url":"https://console.groq.com/docs/changelog#python-sdk-v120-and-typescript-sdk-v112","media":[],"coverageCount":0},{"id":"rel_hp5JSPQH5Ys18uFhrASx3","version":null,"type":"feature","title":"New Voices for Orpheus Arabic Saudi","summary":"Two new voices are available for the Orpheus Arabic Saudi TTS model, with Abdullah now the default. The model now supports six voices total.","titleGenerated":"Groq adds Abdullah and Aisha voices to Orpheus Arabic Saudi TTS","titleShort":"Orpheus Arabic Saudi adds two voices, new default","breaking":"unknown","importance":2,"content":"Two new voices are available for [canopylabs/orpheus-arabic-saudi](https://console.groq.com/docs/model/canopylabs/orpheus-arabic-saudi):\n\n* **Abdullah** — now the default voice\n* **Aisha**\n\nThe Arabic Saudi model now supports six voices total: Abdullah, Fahad, Sultan, Lulwa, Noura, and Aisha. Audio samples and example usage are available on the [Orpheus TTS docs](https://console.groq.com/docs/text-to-speech/orpheus).","publishedAt":"2026-04-18T00:00:00.000Z","fetchedAt":"2026-08-14T20:48:54.130Z","url":"https://console.groq.com/docs/changelog#new-voices-for-orpheus-arabic-saudi","media":[],"coverageCount":0},{"id":"rel_2kz-r5h-_YW-5VRgLA9UH","version":null,"type":"feature","title":"MiniMax M2.5 and Qwen3-VL 32B Instruct (Enterprise)","summary":"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.","titleGenerated":"Groq adds MiniMax M2.5 and Qwen3-VL 32B for Enterprise; Python SDK v1.2.0","titleShort":"MiniMax M2.5 and Qwen3-VL 32B available to Enterprise; SDKs hardened","breaking":"unknown","importance":3,"content":"**Added**\n- `minimaxai/minimax-m2.5` and `qwen/qwen3-vl-32b-instruct` now available on GroqCloud for Enterprise customers. MiniMax M2.5 is a general-purpose model; Qwen3-VL 32B Instruct is a vision-language model for multimodal use cases. Contact your Groq account team for access.\n- New voices for `canopylabs/orpheus-arabic-saudi`: **Abdullah** (now default) and **Aisha**, joining Fahad, Sultan, Lulwa, and Noura for six voices total.\n\n**Changed**\n- Python SDK v1.2.0: preserve hardcoded query params when merging with user params; ensure file data sent as single parameter; multipart request file-copy performance improvements; indices array format for query/form serialization. (Also v1.1.2: sanitized endpoint path params, avoided passing `by_alias` to Pydantic unless set, bumped min `typing-extensions`. v1.1.0: added binary request streaming support and custom JSON encoder, deprecated Python 3.9.)\n- TypeScript SDK v1.1.2: restored streaming support in `defaultParseResponse`, fixed abort-signal memory leak, preserved URL params already embedded in path, pinned patched `minimatch` versions (CVE-2026-27...); GitHub Actions OIDC token migration and dependency updates.","publishedAt":"2026-04-18T00:00:00.000Z","fetchedAt":"2026-08-11T19:28:35.244Z","url":"https://console.groq.com/docs/changelog#minimax-m25-and-qwen3vl-32b-instruct-enterprise","media":[],"coverageCount":0},{"id":"rel_slohPX8XO2tKT7GyKNH-b","version":null,"type":"feature","title":"Platform-wide Migration from PlayAI to Orpheus TTS","summary":"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.","titleGenerated":"Groq completes platform migration from PlayAI to Orpheus TTS","titleShort":"PlayAI TTS deprecated; Orpheus now platform-wide","breaking":"unknown","importance":4,"content":"Following the December 2025 deprecation announcement for `playai-tts` and `playai-tts-arabic`, text-to-speech has been migrated platform-wide to the Orpheus models from Canopy Labs, offering enhanced expressiveness with vocal direction controls, faster inference, and improved audio quality.\n\nGroq Chat now uses Orpheus, with voices:\n- English (`canopylabs/orpheus-v1-english`): autumn, diana, hannah, austin, daniel, troy\n- Arabic (`canopylabs/orpheus-arabic-saudi`): fahad, sultan, lulwa, noura\n\nUsers still on `playai-tts` or `playai-tts-arabic` should migrate before the shutdown date listed on the deprecations page.","publishedAt":"2026-01-30T00:00:00.000Z","fetchedAt":"2026-08-11T19:28:35.244Z","url":"https://console.groq.com/docs/changelog#platformwide-migration-from-playai-to-orpheus-tts","media":[],"coverageCount":0},{"id":"rel_LUkKXRCb5HmCWr3VHCH-g","version":null,"type":"feature","title":"MCP Connectors (Beta)","summary":"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.","titleGenerated":"Groq launches MCP Connectors beta for Google Workspace integration","titleShort":"Google Workspace connectors (Gmail, Calendar, Drive) now available","breaking":"unknown","importance":3,"content":"MCP Connectors provide a streamlined way to integrate with popular business applications without building custom MCP servers. Groq now supports Google Workspace connectors for Gmail, Google Calendar, and Google Drive via pre-built MCP integrations.\n\n**Available Connectors:** Gmail (read/search emails), Google Calendar (view events), Google Drive (search/access files).\n\n**Key Features:** zero configuration, OAuth 2.0 authentication, OpenAI Responses API compatibility.\n\n**Available Tools:** Gmail (`get_profile`, `search_emails`, `get_recent_emails`, `read_email`); Calendar (`get_profile`, `search`, `search_events`, `read_event`); Drive (`get_profile`, `search`, `recent_documents`, `fetch`).\n\nCurrently in beta; feedback welcome via the Community.","publishedAt":"2025-12-01T00:00:00.000Z","fetchedAt":"2026-08-11T19:28:35.244Z","url":"https://console.groq.com/docs/changelog#mcp-connectors-beta","media":[],"coverageCount":0},{"id":"rel_QFRiyluxZeQXt11y7s8KR","version":null,"type":"feature","title":"OpenAI GPT-OSS-Safeguard 20B","summary":"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.","titleGenerated":"Groq adds OpenAI GPT-OSS-Safeguard 20B for content moderation","titleShort":"GPT-OSS-Safeguard 20B available; bring-your-own-policy moderation","breaking":"unknown","importance":3,"content":"GPT-OSS-Safeguard 20B is OpenAI's first open weight reasoning model trained specifically for safety classification tasks, fine-tuned from GPT-OSS, enabling bring-your-own-policy Trust & Safety AI.\n\n**Key Features:** 131K context window; 65K max output tokens; ~1000 TPS; prompt caching enabled (50% cost savings, $0.037/M vs $0.075/M); Harmony response format with low/medium/high reasoning effort; supports tool use, browser search, code execution, JSON modes, content moderation.\n\n**Use Cases:** Trust & Safety content moderation, policy-based classification, automated triage, policy testing.\n\n**Best Practices:** structure policies with Instructions/Definitions/Criteria/Examples sections, keep policies 400-600 tokens, place static content first for caching, use low effort for simple classifications.","publishedAt":"2025-10-29T00:00:00.000Z","fetchedAt":"2026-08-11T19:28:35.244Z","url":"https://console.groq.com/docs/changelog#openai-gptosssafeguard-20b","media":[],"coverageCount":0},{"id":"rel_c6B_XY0z-xXTuWsSQL5YG","version":null,"type":"feature","title":"Python SDK v0.33.0, TypeScript SDK v0.34.0","summary":"Both SDKs add annotation and citation support to chat completion messages and streamed deltas, with improved prompt caching.","titleGenerated":"Groq Python and TypeScript SDKs add annotation support and improve prompt caching","titleShort":"Chat completions get annotation/citation support","breaking":"unknown","importance":2,"content":"The Python SDK has been updated to v0.33.0 and the TypeScript SDK has been updated to v0.34.0.\n\n**Key Changes:**\n\n* Improved prompt caching support\n* Added annotation/citation support to chat completion messages and streamed deltas","publishedAt":"2025-10-21T00:00:00.000Z","fetchedAt":"2026-08-14T20:48:54.170Z","url":"https://console.groq.com/docs/changelog#python-sdk-v0330-typescript-sdk-v0340","media":[],"coverageCount":0},{"id":"rel_o8ua9YNzzWNiq1d950yRf","version":null,"type":"feature","title":"Prompt Caching Enabled for GPT-OSS 120B","summary":"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.","titleGenerated":"Groq enables prompt caching for GPT-OSS 120B with 50% cost savings","titleShort":"Prompt caching live for GPT-OSS 120B—50% input token savings","breaking":"unknown","importance":3,"content":"**Added**\nAutomatic prompt caching now live for `openai/gpt-oss-120b`: 50% cost savings on cached input tokens ($0.075/M vs $0.15/M), lower latency, and higher effective rate limits since cached tokens don't count toward limits. Zero setup required.\n\n**Changed**\nPython SDK updated to v0.33.0, TypeScript SDK to v0.34.0 — improved prompt caching support and added annotation/citation support to chat completion messages and streamed deltas.","publishedAt":"2025-10-21T00:00:00.000Z","fetchedAt":"2026-08-11T19:28:35.244Z","url":"https://console.groq.com/docs/changelog#prompt-caching-enabled-for-gptoss-120b","media":[],"coverageCount":0},{"id":"rel_pfXaVh3l5QB34NVgMR04x","version":null,"type":"feature","title":"Prompt Caching Enabled for GPT-OSS 20B","summary":"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.","titleGenerated":"Groq enables prompt caching for GPT-OSS 20B with 50% cost savings","titleShort":"Prompt caching live for GPT-OSS 20B; 50% cost savings on cached tokens","breaking":"unknown","importance":3,"content":"Automatic prompt caching now live for `openai/gpt-oss-20b`: 50% cost savings on cached input tokens ($0.037/M vs $0.075/M), lower latency, and automatic prefix matching. Zero setup required.","publishedAt":"2025-09-25T00:00:00.000Z","fetchedAt":"2026-08-11T19:28:35.403Z","url":"https://console.groq.com/docs/changelog#prompt-caching-enabled-for-gptoss-20b","media":[],"coverageCount":0},{"id":"rel_LWJIB2p9S8gv29MlGsN7h","version":null,"type":"feature","title":"Remote Model Context Protocol (MCP)","summary":"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.","titleGenerated":"Groq launches remote MCP server integration in beta on GroqCloud","titleShort":"Remote MCP servers now available in beta","breaking":"unknown","importance":3,"content":"Remote MCP server integration now available in Beta on GroqCloud, connecting AI models to thousands of external tools via Anthropic's open MCP standard. Fully compatible with OpenAI Responses API and OpenAI remote MCP spec, enabling zero-code-change migration from OpenAI to Groq.\n\n**Why it matters:** universal interface to remote MCP servers, faster execution, lower costs, seamless migration.\n\n**Supported Models:** openai/gpt-oss-20b, openai/gpt-oss-120b, moonshotai/kimi-k2-instruct-0905, qwen/qwen3-32b, meta-llama/llama-4-maverick-17b-128e-instruct, meta-llama/llama-4-scout-17b-16e-instruct, llama-3.3-70b-versatile, llama-3.1-8b-instant.\n\nLaunch partner tutorials available for BrowserBase, Browser Use, Exa, Firecrawl, HuggingFace, Parallel, Stripe, and Tavily MCP servers.","publishedAt":"2025-09-23T00:00:00.000Z","fetchedAt":"2026-08-11T19:28:35.403Z","url":"https://console.groq.com/docs/changelog#remote-model-context-protocol-mcp","media":[],"coverageCount":0},{"id":"rel_-sMTwSq6cvmCysLaIQDsK","version":null,"type":"feature","title":"Moonshot AI Kimi K2 Instruct 0905","summary":"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.","titleGenerated":"Groq launches Moonshot AI Kimi K2 Instruct 0905 on GroqCloud","titleShort":"Kimi K2-0905 available; 256K context, prompt caching","breaking":"unknown","importance":3,"content":"Kimi K2-0905 brings Moonshot AI's model to GroqCloud with day zero support, delivering production-grade speed, low latency and predictable cost for agentic coding.\n\n**Key Features:** 256K context window (largest on GroqCloud to date); prompt caching (up to 50% savings, faster responses); leading price-to-performance at 200+ t/s for $1.50/M tokens blended ($1.00/M input; $3.00/M output); improved agentic coding reliability especially in multi-turn interactions.","publishedAt":"2025-09-05T00:00:00.000Z","fetchedAt":"2026-08-11T19:28:35.403Z","url":"https://console.groq.com/docs/changelog#moonshot-ai-kimi-k2-instruct-0905","media":[],"coverageCount":0},{"id":"rel_pErCXpis_II9fZkbUn17g","version":null,"type":"feature","title":"Python SDK v0.31.1, TypeScript SDK v0.32.0","summary":"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).","titleGenerated":"Groq SDKs improve chat type definitions and add compound tools","titleShort":"Chat type defs tightened; compound tools added","breaking":"unknown","importance":2,"content":"The Python SDK has been updated to v0.31.1 and the Typescript SDK has been updated to v0.32.0.\n\n**Key Changes:**\n\n* Improved chat completion message type definitions for better compatibility with OpenAI. This fixes errors in certain cases with different message formats.\n* Added support for new types of Groq Compound tools (Wolfram Alpha, Browser Automation, Visit Website)","publishedAt":"2025-09-04T00:00:00.000Z","fetchedAt":"2026-08-14T20:48:54.206Z","url":"https://console.groq.com/docs/changelog#python-sdk-v0311-typescript-sdk-v0320","media":[],"coverageCount":0},{"id":"rel_yIF36XMpvW6tfbSQ3IHZj","version":null,"type":"feature","title":"Groq Compound and Compound Mini","summary":"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.","titleGenerated":"Groq Compound and Compound Mini reach general availability","titleShort":"Compound agentic systems now production-ready","breaking":"unknown","importance":4,"content":"**Added**\nCompound (`groq/compound`) and Compound Mini (`groq/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. Built on GPT-OSS-120B and Llama models, delivering ~25% higher accuracy and ~50% fewer mistakes than OpenAI's Web Search Preview and Perplexity Sonar.\n\n**Key Features:** built-in server-side tools (web search, code execution, Wolfram Alpha, parallel browser automation up to 10 browsers); production-grade stability with increased rate limits; frontier performance on SimpleQA/RealtimeEval; single API call orchestration.\n\n**Changed**\nPython SDK v0.31.1, TypeScript SDK v0.32.0 — improved chat completion message type definitions for OpenAI compatibility; added support for new Compound tool types (Wolfram Alpha, Browser Automation, Visit Website).","publishedAt":"2025-09-04T00:00:00.000Z","fetchedAt":"2026-08-11T19:28:35.403Z","url":"https://console.groq.com/docs/changelog#groq-compound-and-compound-mini","media":[],"coverageCount":0},{"id":"rel_7qAV5shMeTdXXbSAVyN_V","version":null,"type":"feature","title":"Prompt Caching","summary":"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.","titleGenerated":"Groq adds prompt caching to reduce latency and token costs by 50%","titleShort":"Prompt caching cuts token costs 50%; no code changes needed","breaking":"unknown","importance":3,"content":"Prompt caching automatically reuses computation from recent requests sharing a common prefix, delivering cost savings and improved response times with volatile-only storage that expires automatically.\n\n**How It Works:** prefix matching against recently processed requests; cache hit reuses computation reducing latency and cutting token costs by 50% for cached portions; cache miss processes normally and caches the prefix; automatic expiration within a few hours.\n\nRolling out first to Kimi K2, with more models coming. No code changes or additional fees required.","publishedAt":"2025-08-20T00:00:00.000Z","fetchedAt":"2026-08-11T19:28:35.403Z","url":"https://console.groq.com/docs/changelog#prompt-caching","media":[],"coverageCount":0},{"id":"rel_p8W7V8ZBrymspWzDY-J6n","version":null,"type":"feature","title":"Python SDK v0.31.0, TypeScript SDK v0.30.0","summary":"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.","titleGenerated":"Groq Python and TypeScript SDKs add reasoning control and server-side tools for GPT-OSS","titleShort":"GPT-OSS gains reasoning effort, browser search, code interpreter","breaking":"unknown","importance":3,"content":"The Python SDK has been updated to v0.30.0 and the Typescript SDK has been updated to v0.27.0.\n\n**Key Changes:**\n\n* Added support for `high`, `medium`, and `low` options for `reasoning_effort` when using GPT-OSS models to control their reasoning output.\n* Added support for `browser_search` and `code_interpreter` as function/tool definition types in the `tools` array in a chat completion request. Specify one or both of these as tools to allow GPT-OSS models to automatically call them on the server side when needed.\n* Added an optional `include_reasoning` boolean option to chat completion requests to allow configuring if the model returns a response in a `reasoning` field or not.","publishedAt":"2025-08-05T00:00:00.000Z","fetchedAt":"2026-08-14T20:48:54.249Z","url":"https://console.groq.com/docs/changelog#python-sdk-v0310-typescript-sdk-v0300","media":[],"coverageCount":0},{"id":"rel_VoKljfwbhDYkCpSfAxIDf","version":null,"type":"feature","title":"Responses API (Beta)","summary":"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.","titleGenerated":"Groq adds Responses API beta compatible with OpenAI Responses API","titleShort":"Responses API beta lands with OpenAI compatibility","breaking":"unknown","importance":4,"content":"[Groq's Responses API](https://console.groq.com/docs/responses-api) is fully compatible with OpenAI's Responses API, making it easy to integrate advanced conversational AI capabilities into your applications. The Responses API supports both text and image inputs while producing text outputs, stateful conversations, and function calling to connect with external systems.\n\nThis feature is in beta right now — please let us know your feedback on our [Community Forum](https://community.groq.com/)!","publishedAt":"2025-08-05T00:00:00.000Z","fetchedAt":"2026-08-14T20:48:54.249Z","url":"https://console.groq.com/docs/changelog#responses-api-beta","media":[],"coverageCount":0},{"id":"rel_aEuGLWjLjwfMIpPO8_ycu","version":null,"type":"feature","title":"OpenAI GPT-OSS 20B & OpenAI GPT-OSS 120B","summary":"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).","titleGenerated":"Groq adds OpenAI GPT-OSS 20B and 120B models with 131K context","titleShort":"GPT-OSS 20B/120B models available; 131K context, structured outputs","breaking":"unknown","importance":4,"content":"**Added**\nGPT-OSS 20B and GPT-OSS 120B are OpenAI's open-source Mixture-of-Experts models performing on par with o4-mini/o3-mini, with reasoning, built-in browser search and code execution, and structured outputs support.\n\n**Key Features:** 131K context window; 32K max output tokens; ~1000+/~500+ TPS; MoE with 32/128 experts respectively; surpasses o4-mini on many benchmarks.\n\n**Performance (20B):** 85.3% MMLU, 60.7% SWE-Bench Verified, 98.7% AIME 2025, 75.7% avg MMMLU.\n**Performance (120B):** 90.0% MMLU, 62.4% SWE-Bench Verified, 57.6% HealthBench Realistic, 81.3% avg MMMLU.\n\nAlso added: **Responses API (Beta)** — fully compatible with OpenAI's Responses API, supporting text/image inputs, stateful conversations, and function calling.\n\n**Changed**\nPython SDK v0.30.0/v0.31.0, TypeScript SDK v0.27.0 — added `reasoning_effort` (high/medium/low) for GPT-OSS models; added `browser_search` and `code_interpreter` tool types; added optional `include_reasoning` boolean for chat completions.","publishedAt":"2025-08-05T00:00:00.000Z","fetchedAt":"2026-08-11T19:28:35.442Z","url":"https://console.groq.com/docs/changelog#openai-gptoss-20b--openai-gptoss-120b","media":[],"coverageCount":0},{"id":"rel_AGP713OykdehJkzwj97dA","version":null,"type":"feature","title":"Structured Outputs","summary":"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.","titleGenerated":"Groq adds structured outputs with JSON schema support","titleShort":"Structured outputs with JSON schema now available","breaking":"unknown","importance":3,"content":"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`. Guarantees model responses strictly conform to a provided JSON Schema, ensuring reliable data structures without missing fields or invalid values, eliminating complex parsing logic.\n\n**Key Benefits:** guaranteed compliance, type safety, improved developer experience without prompt engineering for format adherence.","publishedAt":"2025-07-18T00:00:00.000Z","fetchedAt":"2026-08-11T19:28:35.442Z","url":"https://console.groq.com/docs/changelog#structured-outputs","media":[],"coverageCount":0},{"id":"rel_a-sX2VN1m73FNwf71Y7YU","version":null,"type":"feature","title":"Moonshot AI Kimi 2 Instruct","summary":"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.","titleGenerated":"Groq adds Moonshot AI Kimi K2 Instruct model","titleShort":"Kimi K2 Instruct available on Groq","breaking":"unknown","importance":4,"content":"[Kimi K2 Instruct](https://console.groq.com/docs/model/moonshotai/kimi-k2-instruct) is Moonshot AI's state-of-the-art Mixture-of-Experts (MoE) language model with 1 trillion total parameters and 32 billion activated parameters. Designed for agentic intelligence, it excels at tool use, coding, and autonomous problem-solving across diverse domains.\n\n**Key Features:**\n\n* 131K token context window\n* 16K max output tokens\n* MoE architecture with 384 experts (8 selected per token)\n* Surpasses GPT-4.1 on agentic and coding use cases\n\n**Performance Metrics:**\n\n* 53.7% Pass@1 on LiveCodeBench (coding performance)\n* 65.8% single-attempt accuracy on SWE-bench Verified\n* 89.5% exact match on MMLU\n* 70.6% Avg@4 on Tau2 retail tasks","publishedAt":"2025-07-15T00:00:00.000Z","fetchedAt":"2026-08-14T20:48:54.249Z","url":"https://console.groq.com/docs/changelog#moonshot-ai-kimi-2-instruct","media":[],"coverageCount":0},{"id":"rel_3iUxNVViu8-VrqIOqSTxP","version":null,"type":"feature","title":"Python SDK v0.30.0, TypeScript SDK v0.27.0","summary":"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.","titleGenerated":"Groq SDK v0.30.0/v0.27.0 adds Moonshot AI Kimi K2 and improves message types","titleShort":"Moonshot AI Kimi K2 added; message type definitions fixed","breaking":"unknown","importance":3,"content":"**Changed**\nPython SDK updated to v0.30.0, TypeScript SDK to v0.27.0 — improved chat completion message type definitions for better OpenAI compatibility, fixing errors with certain message formats.\n\n**Added**\nMoonshot AI Kimi K2 Instruct: a state-of-the-art Mixture-of-Experts model with 1 trillion total parameters and 32 billion activated parameters, designed for agentic intelligence — tool use, coding, autonomous problem-solving.\n\n**Key Features:** 131K context window; 16K max output tokens; MoE with 384 experts (8 selected per token); surpasses GPT-4.1 on agentic and coding use cases.\n\n**Performance:** 53.7% Pass@1 LiveCodeBench, 65.8% SWE-bench Verified, 89.5% MMLU exact match, 70.6% Avg@4 Tau2 retail tasks.","publishedAt":"2025-07-15T00:00:00.000Z","fetchedAt":"2026-08-11T19:28:35.442Z","url":"https://console.groq.com/docs/changelog#python-sdk-v0300-typescript-sdk-v0270","media":[],"coverageCount":0}],"pagination":{"nextCursor":"2025-07-15T00:00:00.000Z|2026-08-11T19:28:35.442Z|rel_3iUxNVViu8-VrqIOqSTxP","limit":20},"summaries":{"rolling":null,"monthly":[]}}