Open Models, Ready for Production

Run 588,111 Open Models on the Frontier Inference Cloud.

Featured models

LLM

zai-org

GLM-5.2

Model APIs

Dedicated

Multimodal

MiniMaxAI

MiniMax-M3

Dedicated

Multimodal

moonshotai

Kimi-K2.7-Code

Dedicated

LLM

nvidia

NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16

Dedicated

LLM

zai-org

GLM-5.1

Model APIs

Dedicated

LLM

deepseek-ai

DeepSeek-V4-Flash

Dedicated

LLM

deepseek-ai

DeepSeek-V4-Pro

Dedicated

LLM

nvidia

NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4

Dedicated

LLM

deepseek-ai

DeepSeek-V3.2

Model APIs

Dedicated

LLM

MiniMaxAI

MiniMax-M2.5

Model APIs

Dedicated

LLM

nvidia

NVIDIA-Nemotron-3-Ultra-550B-A55B-GenRM

Dedicated

LLM

nvidia

NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16

Dedicated

Multimodal

google

gemma-4-31B-it

Model APIs

Dedicated

LLM

Qwen

Qwen3-235B-A22B-Instruct-2507

Model APIs

Dedicated

All models

61,539 results found

Model Name

Input

Output

Type

neuralmagic

Meta-Llama-3.1-8B-Instruct-quantized.w8a8

Quantized

Deploy

neuralmagic

Meta-Llama-3.1-70B-Instruct-FP8

Quantized

Deploy

neuralmagic

Meta-Llama-3.1-70B-Instruct-FP8-dynamic

Quantized

Deploy

neuralmagic

Meta-Llama-3.1-8B-Instruct-FP8

Quantized

Deploy

unsloth

Meta-Llama-3.1-8B-Instruct-bnb-4bit

Quantized

Deploy

unsloth

Meta-Llama-3.1-8B-bnb-4bit

Quantized

Deploy

hugging-quants

Meta-Llama-3.1-70B-Instruct-AWQ-INT4

Base

Deploy

homebrewltd

llama3-s-2024-07-08

Base

Deploy

neuralmagic

Meta-Llama-3-70B-Instruct-quantized.w8a16

Base

Deploy

elyza

Llama-3-ELYZA-JP-8B

Base

Deploy

Groq

Llama-3-Groq-8B-Tool-Use

Fine-tuned

Deploy

hfl

llama-3-chinese-8b-instruct-v3

Fine-tuned

Deploy

Henrychur

MMed-Llama-3-8B

Base

Deploy

neuralmagic

Meta-Llama-3-8B-Instruct-FP8-KV

Base

Deploy

mlabonne

Meta-Llama-3-120B-Instruct

Fine-tuned

Deploy

neuralmagic

Meta-Llama-3-8B-Instruct-FP8

Base

Deploy

meta-llama

Meta-Llama-3-70B-Instruct

Fine-tuned

Deploy

922-CA

llama-2-7b-monika-v0.3b

Base

Deploy

Bllossom

llama-3.2-Korean-Bllossom-3B

Base

Deploy

NousResearch

Hermes-3-Llama-3.1-8B

Fine-tuned

Deploy

meta-llama

Llama-Guard-3-8B

Fine-tuned

Deploy

MLP-KTLim

llama-3-Korean-Bllossom-8B

Fine-tuned

Deploy

meta-llama

Meta-Llama-3-70B

Base

Deploy

perplexity-ai

r1-1776-distill-llama-70b

Fine-tuned

Deploy

NousResearch

DeepHermes-3-Llama-3-8B-Preview

Fine-tuned

Deploy

meta-llama

Llama-3.1-70B-Instruct

Fine-tuned

Deploy

dementor-research

sft_gsm8k_llama-3.1-8b_as_gpt-oss-20b_seed42

Adapter

Deploy

dementor-research

dpo_gsm8k_llama-3.1-8b_as_gpt-oss-20b_seed42

Adapter

Deploy

dementor-research

dpo_chatbot_arena_qwen3.6-27b_as_llama-3.1-8b_seed42

Adapter

Deploy

tardellirs

Maestro-Retriever-Llama-3.1-8B

Adapter

Deploy

dementor-research

dpo_chatbot_arena_qwen3.5-4b_as_llama-3.1-8b_seed43

Adapter

Deploy

dementor-research

dpo_chatbot_arena_nemotron-nano-30b-a3b_as_llama-3.1-8b_seed42

Adapter

Deploy

Kostya-Lolinger

llama3_8b_client_finance

Adapter

Deploy

amylynn

Prima-Llama-8B.gguf

Base

Deploy

longtermrisk

Llama-3.1-8B-bad-medical-advice-first-third-sft

Fine-tuned

Deploy

ombd

llama-3.1-8b-base

Base

Deploy

kaustubh67

llama3.1-8b-legal-clause-classifier

Fine-tuned

Deploy

quyetdev

llama31_8B_fine_tuned_16bit_v2

Base

Deploy

dementor-research

sft_chatbot_arena_llama-3.3-70b_as_gpt-oss-20b_seed42

Adapter

Deploy

dementor-research

sft_chatbot_arena_llama-3.3-70b_as_qwen3.6-27b_seed42

Adapter

Deploy

dementor-research

sft_chatbot_arena_llama-3.3-70b_as_gpt-oss-120b_seed42

Adapter

Deploy

dementor-research

sft_chatbot_arena_llama-3.3-70b_as_nemotron-super-120b_seed42

Adapter

Deploy