Try Bifrost Enterprise free for 14 days.

PERFORMANCE FEATURES ENTERPRISE DOCS BLOG

Groq Models

Browse all 14 AI models from Groq

Total Models

14

Modes

3

Avg Input (1M Tokens)

$0.25

Avg Output (1M Tokens)

$0.63

All Groq Models

Click on any model to view details

Showing 14 of 14 models

Model Name↑	Provider	Mode	Pricing (tokens, images, audio, or pages)	Max Input Tokens	Max Output Tokens	Capabilities
gemma-7b-it groq/gemma-7b-it	Groq	Chat	Input $0.050000 / 1M tokensOutput $0.080000 / 1M tokens	8,192	8,192	Functions
gpt-oss-120b groq/openai/gpt-oss-120b	Groq	Chat	Input $0.150000 / 1M tokensOutput $0.600000 / 1M tokens	131k	32,766	FunctionsReasoningWeb Search
gpt-oss-20b groq/openai/gpt-oss-20b	Groq	Chat	Input $0.075000 / 1M tokensOutput $0.300000 / 1M tokens	131k	32,768	FunctionsReasoningWeb Search
gpt-oss-safeguard-20b groq/openai/gpt-oss-safeguard-20b	Groq	Chat	Input $0.075000 / 1M tokensOutput $0.300000 / 1M tokens	131k	65,536	FunctionsReasoningWeb Search
kimi-k2-instruct-0905 groq/moonshotai/kimi-k2-instruct-0905	Groq	Chat	Input $1.00 / 1M tokensOutput $3.00 / 1M tokens	262k	16,384	Functions
llama-3.1-8b-instant groq/llama-3.1-8b-instant	Groq	Chat	Input $0.050000 / 1M tokensOutput $0.080000 / 1M tokens	128k	8,192	Functions
llama-3.3-70b-versatile groq/llama-3.3-70b-versatile	Groq	Chat	Input $0.590000 / 1M tokensOutput $0.790000 / 1M tokens	128k	32,768	Functions
llama-4-maverick-17b-128e-instruct groq/meta-llama/llama-4-maverick-17b-128e-instruct	Groq	Chat	Input $0.200000 / 1M tokensOutput $0.600000 / 1M tokens	131k	8,192	FunctionsVision
llama-4-scout-17b-16e-instruct groq/meta-llama/llama-4-scout-17b-16e-instruct	Groq	Chat	Input $0.110000 / 1M tokensOutput $0.340000 / 1M tokens	131k	8,192	FunctionsVision
llama-guard-4-12b groq/meta-llama/llama-guard-4-12b	Groq	Chat	Input $0.200000 / 1M tokensOutput $0.200000 / 1M tokens	8,192	8,192
playai-tts groq/playai-tts	Groq	Audio speech	—	10,000	10,000
qwen3-32b groq/qwen/qwen3-32b	Groq	Chat	Input $0.290000 / 1M tokensOutput $0.590000 / 1M tokens	131k	131k	FunctionsReasoning
whisper-large-v3 groq/whisper-large-v3	Groq	Audio Transcription	Input $0.00003083 / secondOutput $0.0000000000 / second	—	—
whisper-large-v3-turbo groq/whisper-large-v3-turbo	Groq	Audio Transcription	Input $0.00001111 / secondOutput $0.0000000000 / second	—	—

Groq Models - Bifrost AI Model Library