DeepSeek-R1-Distill-Llama-70B is a hybrid 70B-parameter model combining DeepSeek's reasoning capabilities with Llama-70B's architectural efficiency. Knowledge-distilled from DeepSeek-R1 to Llama-3 architecture, delivering 92% of R1's performance with 60% lower inference cost and enhanced tool integration.

Gemma2 9B-IT is Google's lightweight 9B-parameter instruction-tuned model optimized for responsible deployment. Features enhanced reasoning, multilingual support, and hardware-efficient design for accessible AI applications with built-in safety filters and tool integration capabilities.

Groq model available through the OneInfer unified API.

Llama-3.3-70B-Instruct is Meta's flagship 70B parameter model featuring enhanced reasoning, 128K context, and enterprise-grade instruction following. Represents a significant evolution over Llama 3.1 with improved tool integration, safety alignment, and complex task handling.

Llama 4 Maverick 17B-128E Instruct is Meta's 17B-parameter MoE instruction model featuring 128 experts with 4 active per token. Optimized for complex task decomposition and tool-integrated reasoning with constitutional AI safety, delivering expert-level performance at accessible computational requirements.

Llama-4-Scout-17B-16E is Meta's efficiency-optimized MoE model featuring 16 experts with ~2B active parameters per token. Designed for exploratory tasks with enhanced web navigation, research synthesis, and information discovery capabilities at low resource cost.

Groq models on OneInfer

Categories

Modalities

API access

Groq model catalog

Model	Category	Input	Output	Context	Pricing
deepseek-r1-distill-llama-70b d2053a988fdc4a789b16f9442ede5a83	text	text	text	128K	$0.750 in / $0.990 out
gemma2-9b-it 7ae90494d9864f57b43462998d6721f8	text	text	text	8K	$0.200 in / $0.200 out
llama-3.1-8b-instant 2dba2b4d7f51415a8499576a892e1f53	text	N/A	N/A	N/A	$0.050 in / $0.080 out
llama-3.3-70b-versatile 41d777609f63458e8deb0e32f634d21d	text	text	text	128K	$0.590 in / $0.790 out
meta-llama/llama-4-maverick-17b-128e-instruct 288e26cb1f4b4c289573cdcef6f55ea9	text	text	text	128K	$0.200 in / $0.600 out
meta-llama/llama-4-scout-17b-16e-instruct 60b4145e4fe14923bdce3fcdc1a115e9	text	text	text	128K	$0.110 in / $0.340 out