
[SkyPilot](https://skypilot.co/) is an open-source framework from UC Berkeley that abstracts away cloud infrastructure, letting you define AI workloads once and run them on any provider. It handles resource discovery, provisioning, cost optimization, and failover across 25+ clouds, including Vast.ai.

With Vast.ai as a SkyPilot backend, you get access to Vast's GPU marketplace, often the lowest-cost option for on-demand GPU compute, through SkyPilot's unified interface. SkyPilot automatically finds the cheapest available instance matching your requirements, provisions it, and manages the full lifecycle.

This guide covers setup, configuration, deploying a model, and the advanced Vast-specific options available in SkyPilot.

## Prerequisites

- A [Vast.ai account](https://cloud.vast.ai/) with credits
- Python 3.7-3.13 (on Python 3.12+, install `skypilot[vast]` explicitly - it is excluded from `skypilot[all]`)
- Terminal access

## Installation

Install SkyPilot with Vast.ai support:

```bash
pip install -U "skypilot[vast]"
```

If you use `uv`, you can also install via:

```bash
uv pip install "skypilot[vast]"
```

This pulls in all required dependencies, including the Vast SDK.

## Configuring Credentials

Get your API key from the [Vast.ai Account page](https://cloud.vast.ai/account/), then store it where SkyPilot expects:

```bash
mkdir -p ~/.config/vastai
echo "<YOUR_VAST_API_KEY>" > ~/.config/vastai/vast_api_key
```

Verify that SkyPilot detects your credentials:

```bash
sky check
```

You should see `Vast: enabled` in the output.

## Deploying a Model: DeepSeek R1 on vLLM

This section walks through deploying DeepSeek R1-0528-Qwen3-8B, an 8B parameter model with step-by-step reasoning capabilities, on a Vast.ai H100 GPU using vLLM.

### Create the YAML Configuration

Create a file named `deepseek-r1-inference.yaml`:

```yaml
resources:
  accelerators: H100:1
  cloud: vast
  image_id: docker:vllm/vllm-openai:latest
  disk_size: 100

run: |
  vllm serve deepseek-ai/DeepSeek-R1-0528-Qwen3-8B \
    --host 0.0.0.0 \
    --port 8000 \
    --max-model-len 4096 \
    --gpu-memory-utilization 0.9 \
    --reasoning-parser deepseek_r1
```

| Parameter | Purpose |
|-----------|---------|
| `accelerators: H100:1` | Request 1x H100 GPU |
| `cloud: vast` | Use Vast.ai as the cloud provider |
| `image_id: docker:vllm/vllm-openai:latest` | Pre-built vLLM Docker image |
| `disk_size: 100` | 100GB storage for model weights and container |
| `--reasoning-parser deepseek_r1` | Enable DeepSeek's chain-of-thought reasoning output |
| `--gpu-memory-utilization 0.9` | Use 90% of GPU VRAM for model serving |

### Launch the Cluster

Deploy the service with SkyPilot:

```bash
sky launch deepseek-r1-inference.yaml --cluster deepseek-r1
```

SkyPilot will find the cheapest available H100 on Vast.ai, provision it, download the model (~15GB), and start the vLLM server. This takes 5-10 minutes.

Monitor progress in real time:

```bash
sky logs deepseek-r1 --follow
```

Confirm the cluster is ready:

```bash
sky status deepseek-r1
```

Look for `Status: UP`.

### Access the Service via SSH Tunnel

Vast.ai instances provisioned through SkyPilot don't expose ports directly. Use SSH tunneling to access the vLLM server on your local machine:

```bash
ssh -L 8000:localhost:8000 deepseek-r1
```

Keep this terminal open - the tunnel must remain active for API access.

### Test the Deployment

In a new terminal, verify the server is running:

```bash
curl http://localhost:8000/health
curl http://localhost:8000/v1/models
```

Send a test inference request:

```bash
curl -X POST http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B",
    "messages": [
      {"role": "user", "content": "What is 15 * 8? Show your reasoning step by step."}
    ],
    "max_tokens": 300,
    "temperature": 0.1
  }'
```

### Python Client Example

The vLLM server exposes an OpenAI-compatible API, so you can use the standard OpenAI Python client:

```python
import openai

client = openai.OpenAI(
    base_url="http://localhost:8000/v1",
    api_key="sk-fake-key"  # vLLM doesn't require a real API key
)

response = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-R1-0528-Qwen3-8B",
    messages=[{
        "role": "user",
        "content": "Write a brief history of Los Angeles in one paragraph."
    }],
    max_tokens=300,
    temperature=0.7
)

print(response.choices[0].message.content)
```

## Managing Your Cluster

```bash
# Check status
sky status deepseek-r1

# View logs
sky logs deepseek-r1

# SSH into the instance
ssh deepseek-r1

# Stop the cluster (preserves data, stops billing)
sky stop deepseek-r1

# Restart a stopped cluster
sky start deepseek-r1

# Auto-stop after 30 minutes of idle time
sky autostop deepseek-r1 --idle-minutes 30

# View all clusters and costs
sky status --all

# Tear down completely
sky down deepseek-r1
```

Always stop or tear down clusters when you're done to avoid unnecessary charges.

## Advanced: Vast Configuration in SkyPilot

SkyPilot supports Vast-specific configuration in `~/.sky/config.yaml`. These options let you control instance selection and pass parameters directly to the Vast API.

### Datacenter-Only Instances

Filter to professional datacenter-hosted machines only. This excludes consumer-grade or home-hosted GPUs, which can improve reliability:

```yaml
vast:
  datacenter_only: true
```

Note that some GPU types may only be available on non-datacenter offers, so enabling this may reduce availability.

### Custom Instance Parameters

The `create_instance_kwargs` block passes parameters directly to the Vast API when creating instances. This gives you access to Vast features beyond what SkyPilot's standard YAML exposes:

```yaml
vast:
  datacenter_only: true
  create_instance_kwargs:
    python_utf8: true
    lang_utf8: true
    extra: "--shm-size=16g"
    onstart_cmd: "echo 'Instance started'"
```

#### Supported Parameters

| Parameter | Description |
|-----------|-------------|
| `image` | Docker image override (e.g., `vastai/base-image:@vastai-automatic-tag`) |
| `env` | Environment variables and port mappings (e.g., `"-e KEY=value -p 8080:8080"`) |
| `price` / `bid_price` | Maximum bid price for preemptible (spot) instances |
| `disk` | Disk size in GB (overrides `disk_size` in task YAML) |
| `label` | Custom instance label |
| `extra` | Extra `docker run` arguments (e.g., `"--shm-size=16g"`) |
| `onstart_cmd` | Shell command to run on instance start |
| `onstart` | Path to a local script to run on instance start |
| `login` / `image_login` | Docker registry credentials for private images |
| `python_utf8` | Enable Python UTF-8 mode |
| `lang_utf8` | Enable system UTF-8 locale |
| `jupyter_lab` | Start JupyterLab on the instance |
| `jupyter_dir` | Jupyter notebook directory path |
| `template_hash_id` | Use a pre-configured Vast template by hash ID |
| `args` | Custom Docker command arguments |
| `user` | Run the container as a specific user |
| `vm` | Use VM mode instead of container mode |

### Using Vast Templates

If you have a saved Vast template, you can reference it by hash ID. When using a template, `image` and `disk` are inherited from the template:

```yaml
vast:
  create_instance_kwargs:
    template_hash_id: "abc123def456"
    price: 0.50
```

### Spot (Preemptible) Instances

Request spot instances for lower costs. SkyPilot handles preemption recovery automatically when using managed jobs:

```yaml
resources:
  accelerators: H100:1
  cloud: vast
  use_spot: true
```

You can set a maximum bid price via `create_instance_kwargs`:

```yaml
vast:
  create_instance_kwargs:
    bid_price: 0.50
```

## Current Limitations

Vast.ai support in SkyPilot does not currently include:

- **Multi-node clusters** - interconnection between nodes is non-trivial on Vast
- **Object store mounting** - no direct mounting of S3, GCS, etc.
- **Port opening after launch** - ports must be configured at launch time
- **Custom disk or network tiers** - Vast does not expose these options

## Troubleshooting

### "Vast: not enabled" After `sky check`

Verify your API key file exists and is readable:

```bash
cat ~/.config/vastai/vast_api_key
```

If the file is missing, re-run the credential setup steps above. If you previously stored the key at `~/.vast_api_key`, note that SkyPilot now expects it at `~/.config/vastai/vast_api_key`.

### SSH Tunnel Connection Refused

Confirm the cluster is running before attempting the tunnel:

```bash
sky status deepseek-r1
```

If the status is `UP`, recreate the tunnel:

```bash
ssh -L 8000:localhost:8000 deepseek-r1
```

### Model Not Loading or Out of Memory

SSH into the instance and check GPU utilization:

```bash
ssh deepseek-r1
nvidia-smi
```

If the model exceeds available VRAM, reduce `--gpu-memory-utilization` to `0.7` or `--max-model-len` to a smaller value in your YAML, then redeploy.

### Slow Startup

Large Docker images (vLLM is ~15GB) take time to download. Model weights add another 5-30GB depending on the model. First launch on a new instance can take 10+ minutes. Use `sky logs <cluster> --follow` to monitor progress.

## Cleanup

Tear down the cluster when you're done to stop all charges:

```bash
sky down deepseek-r1
```

## Next Steps

- **Try other models**: Swap the model in the YAML to serve Llama 3, Mistral, or Qwen
- **Use managed jobs**: Run `sky jobs launch` instead of `sky launch` for automatic recovery from preemptions
- **Explore spot instances**: Add `use_spot: true` to your resource block for lower costs
- **Datacenter filtering**: Set `datacenter_only: true` in `~/.sky/config.yaml` for production workloads
- **SkyPilot docs**: Full reference at [docs.skypilot.co](https://docs.skypilot.co/)

## Additional Resources

- [SkyPilot Documentation](https://docs.skypilot.co/)
- [SkyPilot GitHub](https://github.com/skypilot-org/skypilot)
- [SkyPilot Vast Configuration Reference](https://docs.skypilot.co/en/latest/reference/config.html#vast)
- [Vast.ai Console](https://cloud.vast.ai/)
- [Vast.ai Documentation](https://vast.ai/docs/)
- [DeepSeek R1 on HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B)


Learn how to use SkyPilot with Vast.ai to provision low-cost GPUs, deploy vLLM workloads, tune Vast-specific settings, and troubleshoot common issues.

Vast.ai GPUs Can Now Be Rented Through SkyPilot


Welcome back to another round of updates at Vast.ai. We've kicked off the new year with improvements focused on expanding orchestration support, refining billing and serverless workflows, and introducing new templates and guides to help you deploy faster and more securely.

Another exciting update: we recently launched the [Vast.ai Startup Program](https://vast.ai/startup), designed to support early-stage teams building on our platform.

Startups can now get up to **$2,500 in free GPU credits** when they move their workloads to Vast.ai. With 24/7 priority support and access to Vast's full range of GPUs, the program delivers high-performance compute to power the next wave of AI innovation without long-term commitments. For more info, see our blog post [here](https://vast.ai/article/vast-ai-startup-program).

Not to mention we have a comprehensive new [Model Library](https://vast.ai/model-library), giving you a faster path from model selection to deployment.

## NVIDIA Cloud GPU Updates

### SkyPilot Enhancements

For teams using [SkyPilot](https://vast.ai/article/vast-ai-gpus-can-now-be-rentend-through-skypilot) to manage deployments, we've made updates that expand configuration options on Vast.ai. SkyPilot users can now filter capacity by Secure Cloud to ensure that workloads run only on verified datacenter-hosted GPUs.

We've also added full support for instance creation parameters via SkyPilot, enabling precise control over images, environment variables, disk size, pricing, startup commands, and other instance-level settings at launch. See [SkyPilot docs](https://docs.skypilot.co/en/latest/reference/config.html#vast) for full details.

### Fresh New Templates and Guides

Our [Model Library](https://vast.ai/model-library) introduces a model-first approach to deploying AI. Templates are organized by modality and use case and include recommended hardware presets and clear dedicated GPU pricing.

Here are some of our newest templates:

- [Kimi K2.5](https://vast.ai/model/kimi-k2.5) - An open-source, native multimodal agentic model that combines vision and language understanding with agentic capabilities.
- [LTX-2](https://vast.ai/model/ltx-2) - A DiT-based audio-video generation model that produces synchronized video and sound.
- [SGLang](https://cloud.vast.ai/template/readme/1fce7860e11071cae9c357fb1c8b7560) - A high-performance LLM inference framework with a hosted API server template.

And our latest guides:

- [dstack + vLLM](https://docs.vast.ai/examples/serving-infrastructure/dstack-vllm): Deploy language models using vLLM with dstack for automated provisioning and cost control.
- [DR-Tulu](https://docs.vast.ai/examples/mcp/dr-tulu): Deploy a research agent trained with an MCP server and web tools.
- [GLiNER2](https://docs.vast.ai/examples/ner/gliner2): Run GLiNER2 for named entity recognition with custom entity types.
- [BrowseSafe](https://docs.vast.ai/examples/ai-agents/browsesafe): Deploy BrowseSafe to detect prompt injection attacks in HTML.
- [Overnight Ralph Loop](https://docs.vast.ai/examples/ai-agents/overnight-ralph-loop): Budget-friendly alternative workflow to Claude Code.

### Other Improvements

If you missed it late last year, we also launched [Vast.ai Serverless](https://vast.ai/article/vast-ai-serverless-automated-gpu-scaling). It enables automatic, pay-per-use scaling for AI workloads through a fully serverless API on Vast's globally distributed GPU cloud.

## Our Commitment

With new SkyPilot enhancements, startup opportunities, a model-first deployment experience, and improved inference workflows, we're continuing to build a platform that gives you more control with less friction.

Need help? Contact our customer support team anytime at [support@vast.ai](mailto:support@vast.ai) or join our [Discord](https://discord.gg/vast) server for tips, real-time updates, and ongoing community discussion.

## Change Log

### SkyPilot Enhancements

- Advanced configuration options for SkyPilot on Vast.ai.
- Support for filtering by Secure Cloud (`datacenter_only`).
- Full support for instance creation parameters via SkyPilot.
- See [SkyPilot docs](https://docs.skypilot.co/en/latest/reference/config.html#vast).

### New Templates

- [Kimi K2.5](https://vast.ai/model/kimi-k2.5): Multimodal agentic model.
- [LTX-2](https://vast.ai/model/ltx-2): Video and audio generation model.
- [SGLang](https://cloud.vast.ai/template/readme/1fce7860e11071cae9c357fb1c8b7560): High-performance LLM inference engine.
- Find them in the [Model Library](https://vast.ai/model-library).

### Template Updates

- Base Image and PyTorch now support **CUDA 13.1** and updated NVML libraries.
- Ostris AI Toolkit updates.
- ComfyUI updates.
- Llama.cpp (ssl) updates.
- SGLang onstart script fix.
- Pinokio v6.x updates.

### New Guides

- [dstack](https://docs.vast.ai/examples/serving-infrastructure/dstack-vllm): Serving infrastructure.
- [DR-Tulu](https://docs.vast.ai/examples/mcp/dr-tulu): MCP.
- [GLiNER2](https://docs.vast.ai/examples/ner/gliner2): Named Entity Recognition.
- [BrowseSafe](https://docs.vast.ai/examples/ai-agents/browsesafe): AI agents and security.
- [Overnight Ralph Loop](https://docs.vast.ai/examples/ai-agents/overnight-ralph-loop): Budget-friendly alternative to Claude Code.

### Platform Improvements

- Fixed serverless GPU filter UI.
- Fixed serverless template selection UI.
- Billing Transaction History Invoice PDF Export now excludes failed and pending payments and other non-payment activity.
- Billing Transaction History now supports easy individual invoice download.
- Security improvements.
- Local volume deletion issue resolved.
- Copy progress bar issue resolved.
- Disk quota issues resolved.
- Machines missing geolocation resolved.
- Host CLI schedule maintenance command issue resolved.


Vast.ai's January and February 2026 updates include new SkyPilot controls, Startup Program credits, Model Library additions, fresh guides, and major platform fixes.

January & February 2026 Product Updates


February may be a short month, but we've made the most of it with plenty of updates!

Vast.ai is now offering NVIDIA RTX 5000-series GPUs for rent, including the powerful **RTX 5090**, bringing even more high-performance options to our platform. Plus, we've partnered with **SkyPilot** in an integration that allows you to rent Vast machines through SkyPilot's infrastructure and price optimization framework for even greater flexibility.

Of course, keeping everything running smoothly means staying on top of any technical hiccups. As always, we've been hard at work refining our platform and fixing bugs. Here are some of the latest bug fixes we've rolled out since our last update:

-   Fixed instance-to-instance copy issue.
-   Made various virtual machine (VM) enhancements.
-   Corrected an issue where machine is erroneously marked as "unavailable."
-   Fixed earnings display issue and template category display issue.

### NVIDIA Cloud GPU Updates

At Vast.ai, every update is aimed at making your experience smoother, faster, and more efficient. From expanding our GPU offerings to adding templates and updating guides, our latest improvements are designed to give you even more control and streamline your workflow.

#### Highlights of the latest enhancements:

-   NVIDIA RTX 5000-series GPUs are now available, including the [RTX 5090](https://cloud.vast.ai/?gpu_option=RTX+5090).
-   SkyPilot Integration: Rent Vast machines through SkyPilot’s infrastructure and price optimization framework.
-   Added [vLLM Template](https://cloud.vast.ai/?ref_id=62897&template_id=f4c3ccaf87393c5266748b3b42ba8567) and [Guide](https://docs.vast.ai/vllm-llm-inference-and-serving): Fast and easy-to-use library for LLM inference and serving.
-   Added [Unreal Pixel Streaming Template](https://cloud.vast.ai/?ref_id=62897&template_id=c1c84fd5a4d945fc16012e7ca02d1423): Stream high-quality, interactive 3D content directly to web browsers without requiring end users to install anything.
-   Added [Ollama + WebUI Guide](https://docs.vast.ai/ollama-webui) for running DeepSeek R1.
-   Added [Guide for Creating a Custom Template](https://docs.vast.ai/creating-a-custom-template) from Vast Base Image.
-   Updated Hosting Guide.

Please check out the full change log for our February 2025 updates at the bottom of this page.

### Our Commitment

Whether you're looking to try out the RTX 5090, take advantage of SkyPilot integration, explore our new and updated templates and guides, or just enjoy the many features we continue to refine and expand, we're here to help you get the most out of Vast.ai! We're always happy to support both new and longtime users with affordable, on-demand GPU and virtual machine rental.

Our easy-to-use platform is backed by a responsive customer support team and an active Discord community. Need assistance? Email us at [support@vast.ai](mailto:support@vast.ai) or join our Discord server for helpful resources today!

### Change Log

#### Features:

-   NVIDIA RTX 5000 Series GPUs: Rent Blackwell chips on Vast, including the [RTX 5090](https://cloud.vast.ai/?gpu_option=RTX+5090).
-   SkyPilot Integration: Rent Vast machines through SkyPilot’s infrastructure and price optimization framework.

#### Templates & Guides:

-   Added [vLLM Template](https://cloud.vast.ai/?ref_id=62897&template_id=f4c3ccaf87393c5266748b3b42ba8567) and [Guide](https://docs.vast.ai/vllm-llm-inference-and-serving): Fast and easy-to-use library for LLM inference and serving.
-   Added [Unreal Pixel Streaming Template](https://cloud.vast.ai/?ref_id=62897&template_id=c1c84fd5a4d945fc16012e7ca02d1423): Stream high-quality, interactive 3D content directly to web browsers without requiring end users to install anything.
-   Added [Ollama + WebUI Guide](https://docs.vast.ai/ollama-webui) for running DeepSeek R1.
-   Added [Guide for Creating a Custom Template](https://docs.vast.ai/creating-a-custom-template) from Vast Base Image.
-   Updated VM Desktop Template.
-   Updated Open WebUI Template: Now includes pre-built llama.cpp.
-   Updated ComfyUI & ComfyUI + FLUX.1 Templates.
-   Updated SD Swarm & SD Forge Templates.
-   Updated Fooocus Template.
-   Updated Ubuntu 22.04 VM Template: Updated drivers to CUDA 12.8, preinstalled Docker container toolkit, added Tailscale support.
-   Updated Kohya’s GUI.
-   Updated Oobabooga Template.
-   Updated Hosting Guide.

#### Bug Fixes:

-   Various virtual machine (VM) enhancements.
-   Instance-to-instance copy issue.
-   Machine marked as "unavailable" issue.
-   Earnings display issue.
-   Template category display issue.
-   Session key issue.

#### Miscellaneous Tasks:

-   Added API keys section into CLI page for CLI login command.
-   Added length validation to API keys.  


Rent NVIDIA RTX 5090 GPUs on Vast.ai! Now integrated with SkyPilot for better pricing. New templates, guides & fixes to improve your experience.

Posts about: Skypilot

Vast.ai GPUs Can Now Be Rented Through SkyPilot

January & February 2026 Product Updates

February 2025 Product Update