# Playground — try every model in every mode — Hanzo AI

> Test and compare every model in the catalog interactively: chat, completions, vision, embeddings, audio, and image generation with real-time cost tracking.

Playground

# Try a model, then ship it

Chat, completions, decisions, embeddings, image, video, audio and vision, against every model in the catalog, with each run's tokens and cost beside the answer.

[Open the Playground](https://platform.hanzo.ai/playground)[Read the API](https://hanzo.ai/api)

Paste and ship

Paste this into any agent. It reads the skill manifest and calls Playground from there.

Agent promptapi /v1/chat/completionsCopy

```
Read https://hanzo.ai/skill.md and use Hanzo Playground in my project.
```

## Then the same request from code

A key, a model name, and a message is the whole first request.

curlOne request

```
curl https://api.hanzo.ai/v1/chat/completions \ -H "Authorization: Bearer $HANZO_API_KEY" \ -d '{"model":"zen","messages":[{"role":"user","content":"Hello"}]}'
```

pythonThe Python client

```
pip install hanzoai import os from hanzoai.cloud import ApiClient, Configuration, KeysApi api = ApiClient(Configuration( host="https://api.hanzo.ai", access_token=os.environ["HANZO_API_KEY"], )) print(KeysApi(api).get_keys().keys)
```

Related capabilities

[CLI](https://hanzo.ai/cli)[Desktop](https://hanzo.ai/desktop)[API Keys](https://hanzo.ai/cloud/api-keys)

## Get Playground

Hands-on sandbox for every product

License: Apache-2.0[hanzoai](https://github.com/hanzoai)

[Deploy to Cloud](https://platform.hanzo.ai/deploy)