[ ](/) * Products Close Products Open Products * [ Pricing ](/pricing/) * [ Products Overview ](/products/) * [ Enterprise Access ](/enterprise-access/) * [ GroqCloud™ Platform ](/groqcloud/) * [ GroqRack™ Cluster ](/groqrack/) * Developers Close Developers Open Developers * [ Free API Key ](https://console.groq.com/keys) * [ Start Building ](https://console.groq.com/) * [ Discord ](https://discord.gg/invite/groq) * [ Groq Libraries ](https://console.groq.com/docs/libraries) * [ Community ](/community/) * [ Showcase ](/showcase/) * Insights Close Insights Open Insights * [ Inference ](/inference/) * [ Blog ](/blog/) * [ Events ](/events/) * [ GroqThoughts ](/groqthoughts/) * [ Press Releases ](/press-releases/) * [ Videos ](/videos/) * [ White Papers ](/docs/) * About Close About Open About * [ About Groq ](/about-us/) * [ In the News ](/groq-in-the-news/) * [ Team ](/leadership/) * [ Careers ](/careers/) [ Dev Console ](https://console.groq.com) [ ](#elementor-action%3Aaction%3Dpopup%3Aopen%26settings%3DeyJpZCI6IjUyNTQiLCJ0b2dnbGUiOmZhbHNlfQ%3D%3D) [ ](#elementor-action%3Aaction%3Dpopup%3Aopen%26settings%3DeyJpZCI6IjM0MDUiLCJ0b2dnbGUiOmZhbHNlfQ%3D%3D) [ ](/) * Products Close Products Open Products * [ Pricing ](/pricing/) * [ Products Overview ](/products/) * [ Enterprise Access ](/enterprise-access/) * [ GroqCloud™ Platform ](/groqcloud/) * [ GroqRack™ Cluster ](/groqrack/) * Developers Close Developers Open Developers * [ Free API Key ](https://console.groq.com/keys) * [ Start Building ](https://console.groq.com/) * [ Discord ](https://discord.gg/invite/groq) * [ Groq Libraries ](https://console.groq.com/docs/libraries) * [ Community ](/community/) * [ Showcase ](/showcase/) * Insights Close Insights Open Insights * [ Inference ](/inference/) * [ Blog ](/blog/) * [ Events ](/events/) * [ GroqThoughts ](/groqthoughts/) * [ Press Releases ](/press-releases/) * [ Videos ](/videos/) * [ White Papers ](/docs/) * About Close About Open About * [ About Groq ](/about-us/) * [ In the News ](/groq-in-the-news/) * [ Team ](/leadership/) * [ Careers ](/careers/) [ Dev Console ](https://console.groq.com) [ ](#elementor-action%3Aaction%3Dpopup%3Aopen%26settings%3DeyJpZCI6IjUyNTQiLCJ0b2dnbGUiOmZhbHNlfQ%3D%3D) [ ](#elementor-action%3Aaction%3Dpopup%3Aopen%26settings%3DeyJpZCI6IjM0MDUiLCJ0b2dnbGUiOmZhbHNlfQ%3D%3D) # On-demand Pricing forTokens-as-a-Service ### Groq powers leading openly-available AI models. Other models are available for specific customer requests including fine tuned models. Send us your inquiries [here](https://groq.com/contact/). #### Large Language Models (LLMs) AI Model| Current Speed(Tokens per Second)| Input Token price(Per Million Tokens)| Output Token Price(Per Million Tokens) ---|---|---|--- [Llama 3.2 1B (Preview) 8k](https://huggingface.co/meta-llama/Llama-3.2-1B)| 3100| $0.04 (25M / $1)*| $0.04 (25M / $1)* [Llama 3.2 3B (Preview) 8k](https://huggingface.co/meta-llama/Llama-3.2-3B)| 1600| $0.06 (17M / $1)*| $0.06 (17M / $1)* [Llama 3.1 70B Versatile 128k](https://huggingface.co/meta-llama/Meta-Llama-3.1-70B)| 250| $0.59 (1.69M / $1)*| $0.79 (1.27M / $1)* [Llama 3.1 8B Instant 128k](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B)| 750| $0.05 (20M / $1)*| $0.08 (12.5M / $1)* [Llama 3 70B 8k](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct)| 330| $0.59 (1.69M / $1)*| $0.79 (1.27M / $1)* [Llama 3 8B 8k](https://huggingface.co/meta-llama/Meta-Llama-3-8B)| 1250| $0.05 (20M / $1)*| $0.08 (12.5M / $1)* [Mixtral 8x7B Instruct 32k](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1)| 575| $0.24 (4.17M / $1)*| $0.24 (4.17M / $1)* [Gemma 7B 8k Instruct](https://huggingface.co/google/gemma-7b-it)| 950| $0.07 (14.29M / $1)*| $0.07 (14.29M / $1)* [Gemma 2 9B 8k](https://huggingface.co/google/gemma-2-9b)| 500| $0.20 (5M / $1)*| $0.20 (5M / $1)* [Llama 3 Groq 70B Tool Use Preview 8k](https://huggingface.co/Groq/Llama-3-Groq-70B-Tool-Use)| 335| $0.89 (1.12M / $1)*| $0.89 (1.12M / $1)* [Llama 3 Groq 8B Tool Use Preview 8k](https://huggingface.co/Groq/Llama-3-Groq-8B-Tool-Use)| 1250| $0.19 (5.26M / $1)*| $0.19 (5.26M / $1)* [Llama Guard 3 8B 8k](https://huggingface.co/meta-llama/Llama-Guard-3-8B)| 765| $0.20 (5M / $1)*| $0.20 (5M / $1)* *Approximate number of tokens per $ #### Automatic Speech Recognition (ASR) Models AI Model| Speed Factor| Price(Per Hour Transcribed) ---|---|--- [Whisper V3 Large](https://huggingface.co/openai/whisper-large-v3)| 189x| $0.111* [Whisper Large v3 Turbo](https://huggingface.co/openai/whisper-large-v3-turbo)| 216x| $0.04* [Distil-Whisper](https://huggingface.co/distil-whisper/distil-large-v3)| 250x| $0.02* *For ASR models above, Groq charges a minimum of 10 seconds per request. #### Vision Models AI Model| Input Token Price(per M tokens)| Output Token Price(per M tokens) ---|---|--- [Llama 3.2 11B Vision 8k (Preview)](https://huggingface.co/meta-llama/Llama-3.2-11B-Vision )| $0.18| $0.18 [Llama 3.2 90B Vision 8k (Preview)](https://huggingface.co/meta-llama/Llama-3.2-90B-Vision)| $0.90| $0.90 For enterprise API solutions or on-prem deployments, please fill out the form on our [Enterprise Access Page](https://groq.com/enterprise-access/). Never miss a Groq update! Sign up below for our latest news. [ Sign up for Groq updates ](#elementor-action%3Aaction%3Dpopup%3Aopen%26settings%3DeyJpZCI6IjI1MzgiLCJ0b2dnbGUiOmZhbHNlfQ%3D%3D) ![](https://groq.com/wp-content/uploads/2024/03/GroqLogo_White.svg) ## © 2024 Groq, Inc., All rights reserved. [ ](https://discord.gg/invite/groq) [ ](https://x.com/groqinc) [ Youtube ](https://www.youtube.com/c/GroqInc) [ Threads ](https://www.threads.net/@groqinc) [ Linkedin ](https://www.linkedin.com/company/groq) [ Instagram ](https://instagram.com/groqinc) This site uses cookies to operate our website and analyze website traffic. [Read More](https://groq.com/privacy-policy/)AcceptReject Privacy & Cookies Policy Close #### Privacy Overview This website uses cookies to improve your experience while you navigate through the website. Out of these, the cookies that are categorized as necessary are stored on your browser as they are essential for the working of basic functionalities of the ... Necessary Necessary Always Enabled Necessary cookies are absolutely essential for the website to function properly. This category only includes cookies that ensures basic functionalities and security features of the website. These cookies do not store any personal information. Non-necessary Non-necessary Any cookies that may not be particularly necessary for the website to function and is used specifically to collect user personal data via analytics, ads, other embedded contents are termed as non-necessary cookies. It is mandatory to procure user consent prior to running these cookies on your website. SAVE & ACCEPT