Groq LLM API pricing

Every model Groq serves, with its pricing per 1M tokens and the exact model ID to copy. Sorted cheapest input first. Verified against LiteLLM and OpenRouter daily.

Models served

11

on this provider

Cheapest input

$0.05

per 1M tokens

Cheapest output

$0.08

per 1M tokens

Max context

10.5M

tokens

Model ID
Llama 3.1 8B InstantMeta128K$0.05$0.08groq/llama-3.1-8b-instant
Gemma 7B ItGoogle8K$0.05$0.08groq/gemma-7b-it
gpt-oss-20bOpenAI131K$0.07$0.30groq/openai/gpt-oss-20b
gpt-oss-safeguard-20bOpenAI131K$0.07$0.30groq/openai/gpt-oss-safeguard-20b
Llama 4 Scout 17B 16e InstructMeta10.5M$0.11$0.34groq/meta-llama/llama-4-scout-17b-16e-instruct
gpt-oss-120bOpenAI131K$0.15$0.60groq/openai/gpt-oss-120b
Llama Guard 4 12BMeta164K$0.20$0.20groq/meta-llama/llama-guard-4-12b
Llama 4 Maverick 17B 128e InstructMeta131K$0.20$0.60groq/meta-llama/llama-4-maverick-17b-128e-instruct
Qwen3 32BAlibaba131K$0.29$0.59groq/qwen/qwen3-32b
Llama 3.3 70B VersatileMeta128K$0.59$0.79groq/llama-3.3-70b-versatile
Kimi K2 Instruct 0905Moonshot262K$1.00$3.00groq/moonshotai/kimi-k2-instruct-0905
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI