Crusoe Managed Inference

Inference
that scales

Serve models with ultra-low latency and high throughput. Now with flexible deployment options that fit your workload.

Crusoe's inference engine is powered by MemoryAlloy™ technology, a unique cluster-native memory fabric that persists across nodes and enables intelligent routing to eliminate redundant prefill computation.

Abstract illustration composed of layered curved lines forming an organic shape

Flexible deployment options

Serverless Inference

Get started fast with usage-based consumption of top open-source models via a fully managed inference API in Crusoe Intelligence Foundry.

Best for

• Early-stage workloads

• Low volume traffic

• Rapid experimentation

Self-Serve Deployments

Run top models in Crusoe Intelligence Foundry with inference optimized for throughput or responsiveness. Deploy models customized with Serverless Fine-Tuning in one click.

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

Request benchmarking

Model hub

Explore a curated selection of pre-configured top open models from leading AI labs, ranging from lightweight and ultra-fast to large with frontier reasoning power.

DeepSeek

models

Model

Parameters

Context

AVAILABLE FOR

Google

models

Model

Parameters

Context

AVAILABLE FOR

Z.ai

models

Model

Parameters

Context

AVAILABLE FOR

OpenAI

models

Model

Parameters

Context

AVAILABLE FOR

Kimi

models

Model

Parameters

Context

AVAILABLE FOR

Meta

models

Model

Parameters

Context

AVAILABLE FOR

Alibaba

models

Model

Parameters

Context

AVAILABLE FOR

Yutori

models

Model

Parameters

Context

AVAILABLE FOR

NVIDIA

models

Model

Parameters

Context

AVAILABLE FOR

DeepSeek V4 Flash

Parameters

158.1B

Context

1,048,576

AVAILABLE FOR

Serverless Inference Self-Serve Deployments

DeepSeek V4 Pro

Parameters

861.6B

Context

1,048,576

AVAILABLE FOR

Serverless Inference

Gemma 4 31B it

Parameters

32.7B

Context

262,144

AVAILABLE FOR

Serverless Inference Self-Serve Deployments

GPT-OSS 120B

Parameters

120.4B

Context

131,072

AVAILABLE FOR

Serverless Inference Self-Serve Deployments

GPT-OSS 20B

Parameters

21B

Context

128,000

AVAILABLE FOR

Self-Serve Deployments

Kimi K2.6

Parameters

1.1T

Context

262,144

AVAILABLE FOR

Serverless Inference

Llama 3.1 8B Instruct

Parameters

8B

Context

128,000

AVAILABLE FOR

Self-Serve Deployments

Nemotron 3 Nano 30B A3B FP8

Parameters

31.6B

Context

261,144

AVAILABLE FOR

Serverless Inference

Nemotron 3 Nano Omni 30B A3B Reasoning

Parameters

33B

Context

256,000

AVAILABLE FOR

Serverless Inference

Nemotron 3 Super 120B A12B FP8

Parameters

123.6B

Context

261,144

AVAILABLE FOR

Serverless Inference

Nemotron 3 VoiceChat

Parameters

12B

Context

131,072

AVAILABLE FOR

Serverless Inference

Qwen3 8B

Parameters

8.2B

Context

32,000

AVAILABLE FOR

Self-Serve Deployments

Qwen3.5 9B

Parameters

9B

Context

256,000

AVAILABLE FOR

Self-Serve Deployments

Qwen3.5 2B

Parameters

2B

Context

256,000

AVAILABLE FOR

Self-Serve Deployments

Qwen3.6 35B A3B

Parameters

35B

Context

256,000

AVAILABLE FOR

Self-Serve Deployments

Yutori n2

Parameters

33.4B

Context

128,000

AVAILABLE FOR

Serverless Inference

Nemotron 3.5 Lightning

Parameters

30B

Context

1,000,000

AVAILABLE FOR

Serverless Inference Self-Serve Deployments

GLM 5.3 Flash

Parameters

320B

Context

1,000,000

AVAILABLE FOR

Serverless Inference

GLM 5.3

Parameters

753B

Context

1,000,000

AVAILABLE FOR

Serverless Inference

DeepSeek V4 Flash 0731

Parameters

284B

Context

1,000,000

AVAILABLE FOR

Self-Serve Deployments

Qwen 3.5 4B

Parameters

4B

Context

262,144

AVAILABLE FOR

Self-Serve Deployments

Qwen 3.8 27B

Parameters

27B

Context

256,000

AVAILABLE FOR

Self-Serve Deployments

Unmatched performance, flexibility, and scalability

1

Breakthrough speed

Powered by MemoryAlloy technology with a cluster-wide KV cache, Crusoe's inference engine delivers up to 9.9x faster time-to-first-token* and 5x higher throughput using speculative decoding and dynamic batching.

2

Ultimate flexibility

Choose the right inference deployment option for your workload. Pay as you go with Serverless Inference APIs, use Self-Serve Deployments to further optimize for throughput or responsiveness, or work with us via Tailored Deployments to customize for your unique needs.

3

Seamless scaling

Go from experiment to production without the operational burden. We handle the infrastructure to deliver reliable performance even under peak load. Meet changing user demands with elastic scaling that flexes from single-user testing to sustained, high-volume production deployments.

*

Benchmarked against vLLM for Llama-3.3-70B model. Read our blog to learn more details.

We need to process complex records instantly. Crusoe Managed Inference helps us meet that challenge. It provides a reliable path to production at a pace we haven't seen on other platforms.

Grant Jensen

Co-Founder & CEO

We are firmly entering the agentic era where swarms of digital minds proactively assist humans. This requires fundamentally rethinking the entire stack — models, harnesses, and infra. Crusoe is a recognized leader in the AI inference space, helping Yutori push out the Pareto frontier of capabilities, latency, and cost.

Dhruv Batra

Co-founder & Chief Scientist

Crusoe Intelligence Foundry, designed for AI developers

Discover new models, accelerate fine-tuning, and quickly deploy with flexible inference options.

API keys for fastest path to production

Experiment with top open-source models rapidly. Generate API keys, monitor performance metrics and enable provisioned throughput for production-scale deployments.

Managed endpoints for rapid deployment

Leverage fully managed endpoints powered by our inference engine tuned specifically to each model for optimized performance.

Unified interface for cross-team collaboration

Users working across teams can easily switch between the Crusoe Intelligence Foundry for inference tasks and the Crusoe Cloud Console for infrastructure-as-a-service (IaaS) resources within a single, integrated environment.

Crusoe inference engine vs vLLM

0

2

4

6

8

10

TTFT

Throughput

9.9x

5.0x

x Improvement vs. vLLM

Llama-3.3-70B model, 4-node deployment

$Screenshot of a coding interface showing a prompt requesting a Python 3.11+ fractal viewer app, followed by a partial Python script with imports and comments.$

Frequently
asked questions

Are you ready to build something amazing?