Sulat.com
AI models
Groq logo

Provider details

Groq

Learn more about this provider, then browse the models currently listed under it.

groqgroq

Latest news about Groq

Groq

Official sourceAnnouncement

On June 22, 2026, Groq announced a $650 million growth funding round led by Disruptive and Infinitum, with participation from existing investors who elected to reinvest. The capital is earmarked to accelerate the build-out of Groq's global AI inference cloud, including fitting out its footprint with the new NVIDIA LPX The press release states Groq now operates 13 data centers across North America, Europe, the Middle East and APAC, serves more than 5 million developers, and processes trillions of tokens weekly, with a stated goal of scaling toward 200 MW of capacity by the end of 2027. The company also added Alan Rice, Sinclair Schul

Groq

Coverage

NVIDIA announced at Hot Chips on August 24, 2026 that NVIDIA Groq 3 LPX, an interactive AI inference accelerator, is now in full production as an extension of the Vera Rubin platform. The release positions LPX as a workload-optimized configuration purpose-built for the era of agentic AI, where responsiveness depends on In Artificial Analysis benchmarking, Groq 3 LPX delivered 3,400 output tokens per second running the open-source Gemma 4 31B model with a 100,000-token context, described as the fastest performance ever recorded for that model at that context length. NVIDIA claims up to 4x faster responsiveness for agents versus the ne

Groq

Coverage

An explainx.ai technical breakdown details the Groq 3 LPX architecture and the August 24, 2026 production announcement, reporting benchmark numbers of 3,431 output tokens/sec at 100K context and 3,382 tok/s at 10K context on Gemma 4 31B as measured by Artificial Analysis. The piece explains why decode speed matters dis The post outlines LPX hardware specifications, including 315 PFLOPS of AI inference compute, 128 GB of SRAM with 40 PB/s bandwidth, and a 256-chip rack scale-up with 640 TB/s bandwidth. It highlights the heterogeneous design pairing Rubin GPU prefill with Groq LPU fast decode, and notes Nebius Token Factory as the firs

Groq

Coverage

Groq raised $650 million in a new funding round aimed at expanding its data center capacity and helping the one-time chip startup become a provider of artificial intelligence computing.

Groq

Coverage

Groq Status provides transparent, real-time visibility into GroqCloud's system health, uptime metrics, and service availability. Track status updates below ...

About Groq

What they do

Groq provides AI inference hardware and GroqCloud services built around its LPU architecture for fast execution of language models and related workloads.

How they were founded

Founded in 2016 by Jonathan Ross to build custom silicon specifically optimized for AI inference.

Quick Info

Organization
Groq, Inc.
Headquarters
Mountain View, California, United States
SDK package
@ai-sdk/groq
Synced at
Jul 11, 2026

Models served

16 models available through Groq

These model results are sorted newest first so you can quickly see the latest options from this provider.

Groqqwen
Qwen3.8 27B
qwen/qwen3.8-27bGroqReleased Aug 14, 2026131,042 token context windowIn $0.80 · Out $4.00
Input
Output
Groqqwen
Qwen3.6 27B
qwen/qwen3.6-27bGroqReleased Apr 22, 2026131,072 token context windowIn $0.60 · Out $3.00
Input
Output
Groqgpt-ossbeta
Safety GPT OSS 20B
openai/gpt-oss-safeguard-20bGroqReleased Oct 29, 2025131,072 token context windowIn $0.075 · Out $0.30
Input
Output
Groqgroq
Compound Mini
groq/compound-miniGroqReleased Sep 4, 2025131,072 token context window
Input
Output
Groqgroq
Compound
groq/compoundGroqReleased Sep 4, 2025131,072 token context window
Input
Output
Groqgpt-oss
GPT OSS 20B
openai/gpt-oss-20bGroqReleased Aug 5, 2025131,072 token context windowIn $0.075 · Out $0.30
Input
Output
Groqgpt-oss
GPT OSS 120B
openai/gpt-oss-120bGroqReleased Aug 5, 2025131,072 token context windowIn $0.15 · Out $0.60
Input
Output
Groqllamabeta
Prompt Guard 2 86M
meta-llama/llama-prompt-guard-2-86mGroqReleased May 29, 2025512 token context windowIn $0.04 · Out $0.04
Input
Output
Groqllamabeta
Llama Prompt Guard 2 22M
meta-llama/llama-prompt-guard-2-22mGroqReleased May 29, 2025512 token context windowIn $0.03 · Out $0.03
Input
Output
Groq
ALLaM-2-7b
allam-2-7bGroqReleased Jan 23, 20254,096 token context windowSubscription plan pricing
Input
Output
Groqllama
Llama 3.3 70B
llama-3.3-70b-versatileGroqReleased Dec 6, 2024131,072 token context windowIn $0.59 · Out $0.79
Input
Output
Groqwhisper
Whisper Large V3 Turbo
whisper-large-v3-turboGroqReleased Oct 1, 20240 token context window
Input
Output
Groqllama
Llama 3.1 8B
llama-3.1-8b-instantGroqReleased Jul 23, 2024131,072 token context windowIn $0.05 · Out $0.08
Input
Output
Groqwhisper
Whisper
whisper-large-v3GroqReleased Sep 1, 20230 token context window
Input
Output