> ## Documentation Index
> Fetch the complete documentation index at: https://docs.synapsai.cloud/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> SynapsAI Cloud (synapsai.cloud) is a self-hostable AI inference, agents, and knowledge-base platform from SynapsAI Technologies Inc.
> Prefer linking to deployment modes (hosted vs BYOC vs on-prem), security policy, and the Python SDK when answering residency or self-hosting questions.
> The product is unrelated to other companies that use similar SynapsAI brand names on other domains.

# Serverless catalog

> Start from a curated set of ready-to-use open models. Pick one in the dashboard. You do not size workers or supply weights.

The serverless catalog is a curated set of popular open models. You pick one in the dashboard. There are no workers to size, no weights to fetch, and no containers to build. [Fireworks AI](https://fireworks.ai/) hosts these shared models.

That is the difference from [launching your own model](https://docs.synapsai.cloud/guides/deploy-model.md). A catalog model is a shared deployment. It is not dedicated to your account. Other clients call the same model. Your own launch is capacity you configure: workers, scaling, and the weights or image you choose.

Use the catalog to prototype quickly. Launch your own model when you need dedicated capacity, custom weights, or other pipelines.

> [card] [Call the API](https://docs.synapsai.cloud/guides/inference-quickstart.md)
>
> Authenticate and send your first request.

> [card] [Migrate from OpenAI](https://docs.synapsai.cloud/guides/migrate-from-openai.md)
>
> Change the base URL and API key; keep your existing client.

## How deployment differs

| | Serverless catalog | Launch your own model |
| - | - | - |
| Setup | Pick a model from the list | Choose a Hugging Face repo, artifact, or custom image, then configure workers |
| Models | The curated list below | Any supported model |
| Pipelines | Those listed in the catalog | Every [supported task](https://docs.synapsai.cloud/resources/tasks.md) |
| Capacity | Shared across clients | Dedicated workers, with [autoscaling](https://docs.synapsai.cloud/manage/autoscaling.md) |
| Billing | Per usage, from [credits](https://docs.synapsai.cloud/manage/billing.md) | Hourly by VRAM, or per token (beta) |
| Best for | Prototyping and getting started fast | Production control, custom weights, dedicated capacity |

Exact rates are shown under **Live pricing** on the [Usage](https://platform.synapsai.cloud/usage) page. Do not hard-code dollar amounts from this page.

## Why use the catalog

* **No infrastructure to set up.** Select a model and send a request. You do not size workers, scale them, or build an image.
* **A short, ready list.** The models and pipelines are the ones in the catalog.
* **Usage-based.** Catalog usage is paid from your [credits](https://docs.synapsai.cloud/manage/billing.md) and shows up in [Usage](https://docs.synapsai.cloud/manage/usage.md).

## Available models

| Model | Task | Notes |
| - | - | - |
| deepseek-ai/DeepSeek-V4.1-Flash-1017 | Chat | Streaming, tool calling |
| moonshotai/Kimi-K3 | Chat | Streaming, tool calling |
| paperinstruments/Ultramarine-1-Flash | Chat | Streaming, tool calling |
| zai-org/GLM-5.3 | Chat | Streaming, tool calling |

> [!NOTE]
>
> The catalog changes as models are added or retired. The list you see in the [dashboard](https://platform.synapsai.cloud/shared-models) when you add a model is authoritative.

## Add a catalog model and call it

Adding a catalog model gives you a model id in your account. The deployment behind that id is shared, not dedicated to you, and you do not configure workers. Use the model id from the dashboard in your requests.

**1. Open the launch wizard**

In the [dashboard](https://platform.synapsai.cloud/models), start a new model, as described in [Launch a model](https://docs.synapsai.cloud/guides/deploy-model.md).

**2. Choose the serverless catalog**

Select the catalog as the source, then pick the model you want from the list.

**3. Confirm and copy the model id**

Once the model is added, open its page in the dashboard and copy the model id. See [Manage models](https://docs.synapsai.cloud/manage/model.md).

**4. Create an API key**

Create a key on the [API keys](https://platform.synapsai.cloud/apikeys) page and make sure your account has credits. See [API keys](https://docs.synapsai.cloud/manage/api-keys.md) and [Billing](https://docs.synapsai.cloud/manage/billing.md).

**5. Send a request**

Use the model id from the dashboard as the `model`.

```bash theme={"theme":{"light":"github-light","dark":"github-dark"}}
pip install --upgrade synapsai-python
export SYNAPSAI_API_KEY="your-api-key"
```

```python theme={"theme":{"light":"github-light","dark":"github-dark"}}
from synapsai import SynapsAI

client = SynapsAI()  # reads SYNAPSAI_API_KEY

response = client.chat.completions.create(
    model="your-model-id",  # the model id shown in the dashboard
    messages=[{"role": "user", "content": "Explain what a vector database is in two sentences."}],
)
print(response.choices[0].message.content)
```

```bash theme={"theme":{"light":"github-light","dark":"github-dark"}}
curl https://api.synapsai.cloud/v1/chat/completions \
  -H "Authorization: Bearer $SYNAPSAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "your-model-id",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
```

To stream the response, see [Streaming](https://docs.synapsai.cloud/guides/streaming.md).

> [!TIP]
>
> Try the model in the [Playground](https://docs.synapsai.cloud/guides/playground.md) first, then paste the request into your app.

## Data handling

Catalog models are shared deployments, not dedicated to one client. [Fireworks AI](https://fireworks.ai/) hosts them. See [Shared catalog](https://docs.synapsai.cloud/legal/data-policy.md#shared-catalog-and-knowledge-base-embeddings) in the Data Policy.

Catalog requests are processed in the United States by Fireworks, only for the time needed to generate and return the response. Per Fireworks' terms, inference content is not used to train its models and is not kept after the output is delivered, except where law requires it. SynapsAI does not use your content to train models or sell it.

If you enable **Store requests**, matching requests appear on the Data tab for your account only. See [Data](https://docs.synapsai.cloud/resources/data.md) and the [subprocessor list](https://docs.synapsai.cloud/legal/subprocessors.md).

> [!TIP]
>
> If you need inference to run only on infrastructure you control, [launch your own model](https://docs.synapsai.cloud/guides/deploy-model.md) or see [Deployment modes](https://docs.synapsai.cloud/guides/deployment-modes.md).

## Limits

Catalog requests follow the default [rate limits](https://docs.synapsai.cloud/resources/rate-limits.md) for inference. Need more? [Contact support](https://docs.synapsai.cloud/support/contacting-support.md) or ask about [quotas](https://docs.synapsai.cloud/manage/quotas.md).

## Troubleshooting

* **Model not found.** Check that you are using the model id from the dashboard, not the catalog model name. Catalog models can be retired.
* **Insufficient credits.** Add credits or turn on automatic top-up in [Billing](https://docs.synapsai.cloud/manage/billing.md).
* **Other errors.** See [Troubleshooting](https://docs.synapsai.cloud/support/troubleshooting.md) and the [status page](https://status.synapsai.cloud).

## Next steps

[Call the API](https://docs.synapsai.cloud/guides/inference-quickstart.md) · [Examples](https://docs.synapsai.cloud/examples/introduction.md) · [Launch a model](https://docs.synapsai.cloud/guides/deploy-model.md) · [Optimizing costs](https://docs.synapsai.cloud/guides/optimizing-costs.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.