Crusoe Model Hub

Top open models, production-ready

Browse open models from leading labs available for managed inference and fine-tuning. No infrastructure to manage.

Type
Providers
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
Text
Self-serve
Reflection

Beam 1.0 501B A23B

Context
1048576
Copy model ID
Text
Vision
Self-serve
Fine-tuning
DeepSeek

DeepSeek V4.1 Flash 1017

Context
1048576
Copy model ID
Text
Self-serve
Fine-tuning
Serverless
DeepSeek

DeepSeek V4 Flash 0731

Context
1048576
Copy model ID
Text
Vision
Self-serve
Google

Gemma 4 26B A4B

Context
262144
Copy model ID
Text
Self-serve
Fine-tuning
Z.ai

GLM-5.2

Context
262144
Copy model ID
Text
Self-serve
Fine-tuning
OpenAI

GPT-OSS 20B

Context
131072
Copy model ID
Text
Vision
Voice
Self-serve
TML

Inkling Small

Context
1048576
Copy model ID
Text
Vision
Voice
Self-serve
TML

Inkling Small FP8 Dynamic

Context
1048576
Copy model ID
Text
Self-serve
Fine-tuning
Meta

Llama 3.3 70B Instruct

Context
131072
Copy model ID
Text
Self-serve
Fine-tuning
Alibaba

Qwen3 235B A22B Instruct

Context
262144
Copy model ID
Text
Vision
Self-serve
Fine-tuning
Alibaba

Qwen3.5 2B

Context
262144
Copy model ID
Text
Vision
Self-serve
Alibaba

Qwen3.5 35B A3B

Context
262144
Copy model ID
Text
Vision
Self-serve
Fine-tuning
Alibaba

Qwen3.5 9B

Context
262144
Copy model ID
Text
Vision
Fine-tuning
Alibaba

Qwen3.5 9B Base

Context
262144
Copy model ID
Text
Vision
Self-serve
Alibaba

Qwen3.6 27B

Context
262144
Copy model ID
Text
Vision
Self-serve
Fine-tuning
Alibaba

Qwen3.6 35B A3B

Context
262144
Copy model ID
Text
Vision
Fine-tuning
Alibaba

Qwen3.6 35B A3B FFT

Copy model ID
Text
Vision
Fine-tuning
Alibaba

Qwen3.8 27B FFT

Copy model ID
Text
Self-serve
Fine-tuning
Alibaba

Qwen3 8B

Context
40960
Copy model ID
Text
Vision
Featured
Self-serve
Serverless
NVIDIA

Nemotron 3.5 Super VL 120B A12B

Context
262144
Copy model ID
Text
Vision
Featured
Self-serve
Fine-tuning
Serverless
Z.ai

GLM-5.3 Flash

Context
1048576
Copy model ID
Text
Featured
Self-serve
Fine-tuning
Serverless
Z.ai

GLM-5.3

Context
1048576
Copy model ID
Text
Vision
Featured
Serverless
DeepSeek

DeepSeek V4.1 Flash

Context
1048576
Copy model ID
Text
Vision
Featured
Self-serve
Fine-tuning
Serverless
Google

Gemma 4 31B

Context
262144
Copy model ID
Text
Featured
Self-serve
Fine-tuning
Serverless
OpenAI

GPT-OSS 120B

Context
131072
Copy model ID
Text
Featured
Self-serve
Fine-tuning
Meta

Llama 3.1 8B Instruct

Context
131072
Copy model ID
Text
Featured
Self-serve
Fine-tuning
Serverless
NVIDIA

Nemotron 3.5 Lightning 30B A3B

Context
262144
Copy model ID
Text
Featured
Serverless
NVIDIA

Nemotron 3 Nano 30B

Context
262144
Copy model ID
Text
Vision
Voice
Featured
Serverless
NVIDIA

Nemotron 3 Nano Omni

Context
262144
Copy model ID
Text
Featured
Serverless
NVIDIA

Nemotron 3 Super 120B

Context
1048576
Copy model ID
Voice
Featured
Serverless
NVIDIA

Nemotron 3 VoiceChat

Copy model ID
Text
Vision
Featured
Fine-tuning
Alibaba

Qwen3.5 4B

Context
262144
Copy model ID
Text
Vision
Featured
Self-serve
Fine-tuning
Serverless
Alibaba

Qwen3.8 27B

Context
262144
Copy model ID
No models match your search. Try clearing filters.

Fine-tune and deploy in Crusoe Intelligence Foundry

Serverless
Inference

Get started fast with usage-based consumption of top open models via a fully managed inference API.

Best for
• Early-stage workloads 
• Low volume traffic
• Rapid experimentation

Self-Serve Deployments

Serve models with a dedicated endpoint, optimized for throughput or responsiveness.

Best for
• Production-scale workloads
• Low-latency applications
• Predictable costs

Tailored
Deployments

Work with our team for the highest level of optimization and a dedicated, benchmarked endpoint. You bring the model and define the requirements, we handle the rest.

Best for
• Proprietary models
• Bespoke inference optimization
• SLA-backed performance

Serverless
Fine-Tuning

Quickly adapt models to your domain. You bring the dataset and pick a base model. We handle the GPUs, the training job and the checkpoints. Go live with Self-Serve Deployments in one click, or download your weights to deploy anywhere.

Best for
• Domain-specific accuracy
• Consistent output formatting
• Smaller models, lower cost

Explore model providers

OpenAI
2 models
View OpenAI models
TML
2 models
View TML models
NVIDIA
6 models
View NVIDIA models
Z.ai
3 models
View Z.ai models
Google
2 models
View Google models
DeepSeek
3 models
View DeepSeek models
Alibaba
12 models
View Alibaba models
Meta
2 models
View Meta models
Reflection
1 models
View Reflection models

Frequently
asked questions

Are you ready to build something amazing?