AI Squawk the real-time terminal for AI news

↗

Groq

RSS for Groq

Everything AI Squawk tracks for Groq on one page. Source lanes: Groq Status.

Status

up 0 incidents in the last 30 days · full scoreboard

Rate limits

full rate-limit reference

ModelTierRPMTPMITPMOTPMChanged
canopylabs/orpheus-arabic-saudideveloper 101,200 —— since tracking began
canopylabs/orpheus-v1-englishdeveloper 101,200 —— since tracking began
groq/compounddeveloper 3070,000 —— since tracking began
groq/compound-minideveloper 3070,000 —— since tracking began
meta-llama/llama-prompt-guard-2-22mdeveloper 3015,000 —— since tracking began
meta-llama/llama-prompt-guard-2-86mdeveloper 3015,000 —— since tracking began
openai/gpt-oss-120bdeveloper 308,000 —— since tracking began
openai/gpt-oss-20bdeveloper 308,000 —— since tracking began
openai/gpt-oss-safeguard-20bdeveloper 32,000 —— 39d ago
qwen/qwen3.8-27bdeveloper 308,000 —— since tracking began
whisper-large-v3developer 20— —— since tracking began
whisper-large-v3-turbodeveloper 20— —— since tracking began

SDKs

Full SDK reference →

Upcoming retirements

full deprecation tracker · subscribe to Groq's shutdowns (.ics)

ModelShutdown dateReplacement
llama-3.2-1b-preview 2025-04-14 llama-3.1-8b-instant
llama-3.2-3b-preview 2025-04-14 llama-3.1-8b-instant
llama-3.2-11b-vision-preview 2025-04-14 meta-llama/llama-4-scout-17b-16e-instruct
llama-3.2-90b-vision-preview 2025-04-14 meta-llama/llama-4-scout-17b-16e-instruct
deepseek-r1-distill-qwen-32b 2025-04-14 qwen-qwq-32b
qwen-2.5-32b 2025-04-14 qwen-qwq-32b meta-llama/llama-4-scout-17b-16e-instruct
qwen-2.5-coder-32b 2025-04-14 qwen-qwq-32b openai/gpt-oss-120b
llama-3.3-70b-specdec 2025-04-14 meta-llama/llama-4-scout-17b-16e-instruct llama-3.3-70b-versatile
deepseek-r1-distill-llama-70b-specdec 2025-04-14 deepseek-r1-distill-llama-70b deepseek-r1-distill-qwen-32b
llama-guard-3-8b 2025-06-06 meta-llama/llama-guard-4-12b
qwen-qwq-32b 2025-07-14 qwen/qwen3-32b
mistral-saba-24b 2025-07-30 qwen/qwen3-32b
distil-whisper-large-v3-en 2025-08-23 whisper-large-v3-turbo
llama3-70b-8192 2025-08-30 llama-3.3-70b-versatile
llama3-8b-8192 2025-08-30 llama-3.1-8b-instant
deepseek-r1-distill-llama-70b 2025-10-02 llama-3.3-70b-versatile
gemma2-9b-it 2025-10-08 llama-3.1-8b-instant
moonshotai/kimi-k2-instruct 2025-10-10 openai/gpt-oss-120b
playai-tts 2025-12-31 canopylabs/orpheus-v1-english
playai-tts-arabic 2025-12-31 canopylabs/orpheus-arabic-saudi
meta-llama/llama-guard-4-12b 2026-03-05 openai/gpt-oss-safeguard-20b
meta-llama/llama-4-maverick-17b-128e-instruct 2026-03-09 openai/gpt-oss-120b
moonshotai/kimi-k2-instruct-0905 2026-04-15 openai/gpt-oss-120b
qwen/qwen3-32b 2026-07-17 openai/gpt-oss-120b
meta-llama/llama-4-scout-17b-16e-instruct 2026-07-17 openai/gpt-oss-120b
llama-3.1-8b-instant 2026-08-16 openai/gpt-oss-20b
llama-3.3-70b-versatile 2026-08-16 openai/gpt-oss-120b
qwen/qwen3.6-27b 2026-09-14 qwen/qwen3.8-27b
groq/compound 2026-09-21 —
groq/compound-mini 2026-09-21 —

Watched pages

Pricing, rate-limit, and deprecation pages polled for changes; a change publishes a diff row. Full change history for Groq →