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

> ## Agent Instructions
> The Deepshi API is an OpenAI-compatible gateway. Base URL: https://api.deepshi.ai/v1. API keys start with sk-bf- and go in the Authorization: Bearer header. Prefer the official OpenAI SDKs pointed at the Deepshi base URL. Model ids are clean with no provider prefix (e.g. deepshi-3.0, claude-opus-4.8, gpt-5.5). Chat and image requests are synchronous; video and music requests are asynchronous job APIs (create, then poll). Every synchronous response carries usage.cost.total_cost in USD. Do not reference the internal /api/* admin plane or virtual keys.

# Hermes Agent

> Use Deepshi as the model backend for Hermes Agent.

Hermes Agent can run on any OpenAI-compatible model backend, so point its custom provider at Deepshi.

## Configure

The quickest way is the interactive picker:

```bash theme={null}
hermes model
# choose the custom / self-hosted endpoint option
# API base URL:  https://api.deepshi.ai/v1
# API key:       your Deepshi API key
# Model name:    a Deepshi model id, e.g. deepshi-3.0
```

Or set it directly in `~/.hermes/config.yaml`:

```yaml theme={null}
model:
  default: deepshi-3.0
  provider: custom
  base_url: https://api.deepshi.ai/v1
  api_key: YOUR_DEEPSHI_API_KEY
```

To keep the key out of the file, use a named provider with `key_env`:

```yaml theme={null}
custom_providers:
  - name: deepshi
    base_url: https://api.deepshi.ai/v1
    key_env: DEEPSHI_API_KEY
    api_mode: chat_completions

model:
  provider: custom:deepshi:deepshi-3.0   # format: custom:<provider>:<model-id>
```

<Tip>
  Hermes Agent is agentic, so pick a model with the **tools** capability. See
  [Chat models](/models/text-models).
</Tip>