Releases Index
Groq

Groq

$npx @buildinternet/releases get groq

Qwen 3.8 reasoning guidance in Groq SDKs

This release2 featuresNew capabilities1 enhancementImprovements to existing featuresAI-tallied from the release notes

Both the Python and TypeScript SDKs add guidance for Qwen 3.8 reasoning in chat completions. The Python SDK also updates dependency lock files for known vulnerabilities.

Read more ↗

Qwen 3 32B and Llama 4 Scout 17B shut down

This release2 enhancementsImprovements to existing featuresAI-tallied from the release notes

qwen/qwen3-32b and meta-llama/llama-4-scout-17b-16e-instruct were shut down on July 17, 2026, with openai/gpt-oss-120b recommended as the replacement.

Read more ↗

Llama 3.1 8B and 3.3 70B models deprecated

This release1 enhancementImprovements to existing featuresAI-tallied from the release notes

llama-3.1-8b-instant and llama-3.3-70b-versatile are deprecated and shut down on August 16, 2026. Migrate to openai/gpt-oss-20b and openai/gpt-oss-120b respectively.

Read more ↗

Qwen 3.6 27B lands on GroqCloud

This release1 featureNew capabilitiesAI-tallied from the release notes

qwen/qwen3.6-27b is now available on GroqCloud, a 27B multimodal model with agentic coding and reasoning, switchable thinking and non-thinking modes, and a 131K-token context window.

Read more ↗

SDK headers configurable via environment variables; iterator validation

This release2 featuresNew capabilities1 enhancementImprovements to existing featuresAI-tallied from the release notes

Both SDKs now support header configuration through environment variables, and the Python SDK adds pydantic iterator validation. The release also includes API spec updates and Node 24/26 compatibility and CI changes.

Read more ↗

MiniMax M2.7 lands on GroqCloud for Enterprise

This release1 featureNew capabilitiesAI-tallied from the release notes

MiniMax M2.7 is now available on GroqCloud for Enterprise customers, a 229B-parameter MoE model with interleaved thinking built for agentic workflows and coding with a 196K-token context window.

Read more ↗

Python SDK streaming, TS SDK memory leak fixed

This release2 featuresNew capabilities2 enhancementsImprovements to existing features5 fixesBug fixesAI-tallied from the release notes

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.

Read more ↗

MiniMax M2.5 and Qwen3-VL 32B available to Enterprise; SDKs hardened

This release2 featuresNew capabilities3 enhancementsImprovements to existing features2 fixesBug fixesAI-tallied from the release notes

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.

Read more ↗

PlayAI TTS deprecated; Orpheus now platform-wide

This release1 enhancementImprovements to existing featuresAI-tallied from the release notes

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.

Read more ↗

Google Workspace connectors (Gmail, Calendar, Drive) now available

This release3 featuresNew capabilitiesAI-tallied from the release notes

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.

Read more ↗

GPT-OSS-Safeguard 20B available; bring-your-own-policy moderation

This release1 featureNew capabilitiesAI-tallied from the release notes

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.

Read more ↗

Prompt caching live for GPT-OSS 120B—50% input token savings

This release2 featuresNew capabilities1 enhancementImprovements to existing featuresAI-tallied from the release notes

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.

Read more ↗

Chat completions get annotation/citation support

This release1 featureNew capabilities1 enhancementImprovements to existing featuresAI-tallied from the release notes

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

Read more ↗