Inference

inference

Updated 24 minutes ago

Inference.net is a high-performance AI inference platform that provides access to leading large language models including Meta's Llama family, DeepSeek, Mistral, Google's Gemma, Qwen, and OpenAI models. The platform focuses on delivering fast, efficient inference with various precision options (fp-16, fp-8, bf-16) to optimize performance and cost. Inference.net offers an OpenAI-compatible API interface, making it easy to integrate with existing applications while providing access to state-of-the-art models through their unified endpoint.

Visit Website LLM.txt

Browse 20 LLM models available from Inference. Compare prices and features.

Models (20)

Organization	Model Name	Original Model	Input	Output
DeepSeek	DeepSeek-R1-0528	`deepseek/deepseek-r1-0528/fp-8`	-	-	View
OpenAI	GPT OSS 120B	`openai/gpt-oss-120b`	-	-	View
OpenAI	GPT OSS 20B	`openai/gpt-oss-20b`	-	-	View
DeepSeek	DeepSeek-V3 0324	`deepseek/deepseek-v3-0324/fp-8`	-	-	View
qwen	Qwen3 30B A3B	`qwen/qwen3-30b-a3b/fp8`	-	-	View
qwen	QwQ-32B	`qwen/qwq-32b/fp-8`	-	-	View
DeepSeek	DeepSeek-V3	`deepseek/deepseek-v3/fp-8`	-	-	View
Meta	Llama 3.3 70B Instruct	`meta-llama/llama-3.3-70b-instruct/fp-8`	-	-	View
Meta	Llama 3.1 70B Instruct	`meta-llama/llama-3.1-70b-instruct/fp-16`	-	-	View
qwen	Qwen2.5 7B Instruct	`qwen/qwen2.5-7b-instruct/bf-16`	-	-	View
Meta	Llama 3.2 3B Instruct	`meta/llama-3.2-3b-instruct`	$0.02	$0.02	View
Meta	Llama 3.2 3B Instruct	`meta-llama/llama-3.2-3b-instruct/fp-16`	-	-	View
Meta	Llama 3.2 11B Instruct	`meta-llama/llama-3.2-11b-instruct/fp-16`	-	-	View
Meta	Llama 3.1 8B Instruct	`meta/llama-3.1-8b-instruct`	$0.03	$0.03	View
Meta	Llama 3.1 8B Instruct	`meta-llama/llama-3.1-8b-instruct/fp-16`	-	-	View
qwen	Qwen3 Embedding 4B	`qwen/qwen3-embedding-4b`	$0.01	$0.00	View
Nvidia	Llama 3.2 11b Vision Instruct	`meta/llama-3.2-11b-vision-instruct`	$0.06	$0.06	View
Meta	llama-3.2-1b-instruct	`meta/llama-3.2-1b-instruct`	$0.01	$0.01	View
Meta	llama-3.2-1b-instruct	`meta-llama/llama-3.2-1b-instruct/fp-16`	-	-	View
DeepSeek	DeepSeek-R1	`deepseek/deepseek-r1/fp-8`	-	-	View

Back to Providers Visit Website