Skip to main content
ActionFlows AI
Go to actionflows.ai

Groq

Fastest AI inference powered by custom LPU hardware, delivering ultra-low latency for text generation tasks.

Groq

Fastest AI inference powered by custom LPU hardware, delivering ultra-low latency for text generation tasks.

Authentication

Auth Type
API Key
Platform Key
Not configured
Self-serve
Available

Add your Groq API key from Organization → Integrations → AI Vendors. Keys are encrypted at rest and scoped to your organization.

Available Models

27 enabled models across 2 categories.

Text23

ALLaM-2-7ballam-2-7b

chatModel, languageModel, completionModel

Compoundgroq/compound

chatModel, languageModel, completionModel

functionCalling, reasoning

Compound Minigroq/compound-mini

chatModel, languageModel, completionModel

functionCalling, reasoning

DeepSeek R1 Distill Llama 70Bdeepseek-r1-distill-llama-70b

chatModel, languageModel, completionModel

functionCalling, reasoning

Gemma 2 9Bgemma2-9b-it

chatModel, languageModel, completionModel

functionCalling

GPT OSS 120Bopenai/gpt-oss-120b

chatModel, languageModel, completionModel

functionCalling, reasoning

GPT OSS 20Bopenai/gpt-oss-20b

chatModel, languageModel, completionModel

functionCalling, reasoning

Kimi K2 Instructmoonshotai/kimi-k2-instruct

chatModel, languageModel, completionModel

functionCalling

Kimi K2 Instruct 0905moonshotai/kimi-k2-instruct-0905

chatModel, languageModel, completionModel

functionCalling

Llama 3.1 8B Instantllama-3.1-8b-instant

chatModel, languageModel, completionModel

functionCalling

Llama 3.3 70B Versatilellama-3.3-70b-versatile

chatModel, languageModel, completionModel

functionCalling

Llama 3 70Bllama3-70b-8192

chatModel, languageModel, completionModel

functionCalling

Llama 3 8Bllama3-8b-8192

chatModel, languageModel, completionModel

functionCalling

Llama 4 Maverick 17Bmeta-llama/llama-4-maverick-17b-128e-instruct

chatModel, languageModel, completionModel

functionCalling, imageInput, vision

Llama 4 Scout 17Bmeta-llama/llama-4-scout-17b-16e-instruct

chatModel, languageModel, completionModel

functionCalling, imageInput, vision

Llama Guard 3 8Bllama-guard-3-8b

chatModel, languageModel, completionModel

Llama Guard 4 12Bmeta-llama/llama-guard-4-12b

chatModel, languageModel, completionModel

imageInput, vision

Llama Prompt Guard 2 22Mmeta-llama/llama-prompt-guard-2-22m

chatModel, languageModel, completionModel

Llama Prompt Guard 2 86Mmeta-llama/llama-prompt-guard-2-86m

chatModel, languageModel, completionModel

Mistral Saba 24Bmistral-saba-24b

chatModel, languageModel, completionModel

functionCalling

Qwen3 32Bqwen/qwen3-32b

chatModel, languageModel, completionModel

functionCalling, reasoning

Qwen QwQ 32Bqwen-qwq-32b

chatModel, languageModel, completionModel

functionCalling, reasoning

Safety GPT OSS 20Bopenai/gpt-oss-safeguard-20b

chatModel, languageModel, completionModel

functionCalling, reasoning

Sound4

Orpheus Arabic Saudicanopylabs/orpheus-arabic-saudi

speech

Orpheus V1 Englishcanopylabs/orpheus-v1-english

speech

Whisper Large V3whisper-large-v3

transcription

Whisper Large v3 Turbowhisper-large-v3-turbo

transcription

Google Vertex AI

Previous Page

Helicone

Next Page