[Integrations](https://spiral.ai/integrations) › [ChatGPT](https://spiral.ai/integrations/chatgpt) › [Higgsfield API endpoint reference](https://spiral.ai/integrations/chatgpt/higgsfield-api-endpoint-reference)

# How to Use Higgsfield API endpoint reference in ChatGPT

Returns documented operations from Higgsfield's published OpenAPI specification. Use it to inspect operation paths and shared request controls; Higgsfield says this specification is supplementary to its model documentation.

|  |  |
| --- | --- |
| Model | Higgsfield API endpoint reference |
| Available through | Alexandria |
| Category | Developer |
| Price | $0.00873 per call. |
| Returns | json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Higgsfield API endpoint reference in ChatGPT

- Use Higgsfield API endpoint reference to look this up and give me the result as a table.
- Pull the latest numbers from Higgsfield API endpoint reference and tell me what changed since last week.
- Check Higgsfield API endpoint reference and summarize what you find in three bullet points.
- Pull the newest data from Higgsfield API endpoint reference and give me the result as a table.
- Check Higgsfield API endpoint reference every morning and tell me only when something changed.

## How to set up Higgsfield API endpoint reference in ChatGPT

Pick the way that suits you. Each takes about two minutes.

### Use the ChatGPT connector

1. **Add a custom MCP server**: In ChatGPT open Plugins, then Add › Add custom MCP server. Name it Spiral, paste this URL and keep Authentication on OAuth. Tick I understand and want to continue, then click Create.

```text
https://api.spiral.ai/mcp
```

2. **Click Connect**: ChatGPT asks to connect Spiral. Connect takes you to Spiral in your browser.

3. **Sign in to Spiral and approve**: Sign in, pick the organization ChatGPT should use and click Authorize. Spiral gives the connection its own API key; ChatGPT never sees it, and you can remove the connection under Settings › Connected apps.

### Use the Spiral skill

1. **Send ChatGPT this message**: Your agent reads Spiral's skill and sets itself up.

```
set up https://spiral.ai/SKILL.md
```

2. **Sign in or paste a key**: Approve Spiral in the browser, or give the agent a key from the console.

### Use the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run Higgsfield API endpoint reference**: One request; the result comes back by polling or a webhook.

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "alexandria",
    "model": "docs-higgsfield-ai/developer-documentation/list_endpoints",
    "input": {
      "q": "<q>"
    }
  }'
```

Then paste one of the prompts above: ChatGPT finds Higgsfield API endpoint reference on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/chatgpt

## Higgsfield API endpoint reference tools and prices

- [Higgsfield API Docs · List endpoints](https://spiral.ai/tools/alexandria/docs-higgsfield-ai/developer-documentation/list_endpoints) (Alexandria): $0.00873 per call.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| q |  | — | Case-insensitive text matched against path, summary and description. |
| tag |  | — | Exact tag, case-insensitive, e.g. Requests. |
| url |  | — | The specification URL, https://docs.higgsfield.ai/docs/openapi.json. Pattern: ^https?://. |

## What can you do with Higgsfield API endpoint reference in ChatGPT?

Create a source-linked Higgsfield feature brief for an image or video application. A chat agent can explain documented model choices, workflow requirements, and integration guidance in plain English.

### Plan a product video feature

Compare documented video models for a product demo, inspect the chosen workflow's requirements, and collect the request lifecycle references needed for an implementation plan.

### Evaluate an image generation feature

Build a shortlist from the image catalog, inspect each candidate's workflow documentation, and identify the shared operations and guides needed for an image generation application.

### Maintain a documented capability matrix

Create a source-linked table of image and video models, workflows, endpoint paths, and documented requirements. Keep catalog coverage separate from operations found in the supplementary OpenAPI file.

### Review a model migration

Compare the documented workflows of the current model and a proposed replacement. Identify request changes, different output instructions, and shared API operations that the migration needs to preserve.

### Check request validation code

Compare an application's validation rules with the selected workflow's documented schema and examples. Use the operation reference to distinguish generation requests from shared request controls.

### Investigate a generation failure

Find the relevant error guidance, inspect the selected workflow's requirements, and read the documented request status operations before proposing a correction.

### Write a source-linked developer handbook

Assemble a handbook covering model selection, workflow requirements, shared API operations, and troubleshooting. Link each section to the Higgsfield page that supports it.

## Overview

- [Alexandria](https://spiral.ai/providers/alexandria)
- [All ChatGPT guides](https://spiral.ai/integrations/chatgpt)

## Higgsfield API endpoint reference in other agents

- [Amp](https://spiral.ai/integrations/amp/higgsfield-api-endpoint-reference)
- [Claude](https://spiral.ai/integrations/claude-desktop/higgsfield-api-endpoint-reference)
- [Claude Code](https://spiral.ai/integrations/claude-code/higgsfield-api-endpoint-reference)
- [Cline](https://spiral.ai/integrations/cline/higgsfield-api-endpoint-reference)
- [Codex](https://spiral.ai/integrations/codex/higgsfield-api-endpoint-reference)
- [Cursor](https://spiral.ai/integrations/cursor/higgsfield-api-endpoint-reference)
- [Devin](https://spiral.ai/integrations/devin/higgsfield-api-endpoint-reference)
- [dots](https://spiral.ai/integrations/dots/higgsfield-api-endpoint-reference)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/higgsfield-api-endpoint-reference)
- [Gemini](https://spiral.ai/integrations/gemini/higgsfield-api-endpoint-reference)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/higgsfield-api-endpoint-reference)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/higgsfield-api-endpoint-reference)
- [goose](https://spiral.ai/integrations/goose/higgsfield-api-endpoint-reference)
- [Grok](https://spiral.ai/integrations/grok/higgsfield-api-endpoint-reference)
- [Grok Build](https://spiral.ai/integrations/grok-build/higgsfield-api-endpoint-reference)
- [Hermes](https://spiral.ai/integrations/hermes/higgsfield-api-endpoint-reference)
- [Instinct](https://spiral.ai/integrations/instinct/higgsfield-api-endpoint-reference)
- [Manus](https://spiral.ai/integrations/manus/higgsfield-api-endpoint-reference)
- [Muse](https://spiral.ai/integrations/muse/higgsfield-api-endpoint-reference)
- [Muse Code](https://spiral.ai/integrations/muse-code/higgsfield-api-endpoint-reference)
- [n8n](https://spiral.ai/integrations/n8n/higgsfield-api-endpoint-reference)
- [Notion](https://spiral.ai/integrations/notion/higgsfield-api-endpoint-reference)
- [OpenClaw](https://spiral.ai/integrations/openclaw/higgsfield-api-endpoint-reference)
- [opencode](https://spiral.ai/integrations/opencode/higgsfield-api-endpoint-reference)
- [Perplexity](https://spiral.ai/integrations/perplexity/higgsfield-api-endpoint-reference)
- [Raycast](https://spiral.ai/integrations/raycast/higgsfield-api-endpoint-reference)
- [VS Code](https://spiral.ai/integrations/vscode/higgsfield-api-endpoint-reference)
- [Windsurf](https://spiral.ai/integrations/windsurf/higgsfield-api-endpoint-reference)
- [Zapier](https://spiral.ai/integrations/zapier/higgsfield-api-endpoint-reference)

## More ChatGPT guides

- [Hermes Agent release notes](https://spiral.ai/integrations/chatgpt/hermes-agent-release-notes)
- [Higgsfield documentation index](https://spiral.ai/integrations/chatgpt/higgsfield-documentation-index)
- [Hermes Agent product overview](https://spiral.ai/integrations/chatgpt/hermes-agent-product-overview)
- [Higgsfield documentation page](https://spiral.ai/integrations/chatgpt/higgsfield-documentation-page)
- [Hermes Agent plugin catalog](https://spiral.ai/integrations/chatgpt/hermes-agent-plugin-catalog)
- [Higgsfield documentation search](https://spiral.ai/integrations/chatgpt/higgsfield-documentation-search)

## Questions about Higgsfield API endpoint reference in ChatGPT

**Can ChatGPT use Higgsfield API endpoint reference?**

Yes. Add Spiral to ChatGPT as an MCP server, and ChatGPT can find and run Higgsfield API endpoint reference like any built-in tool.

**How much does Higgsfield API endpoint reference cost in ChatGPT?**

$0.00873 per call. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your ChatGPT plan is separate.

**Do I need an Alexandria account to use Higgsfield API endpoint reference in ChatGPT?**

No. Spiral runs Higgsfield API endpoint reference on its own Alexandria account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Higgsfield API endpoint reference in ChatGPT?**

About two minutes: add a custom MCP server, then click Connect, then sign in to Spiral and approve.

**Does ChatGPT wait while Higgsfield API endpoint reference runs?**

Higgsfield API endpoint reference runs in the background. ChatGPT starts the run, checks on it and gives you the json when it's ready.

**How much of Higgsfield's model catalog is documented?**

The model reference currently lists 84 entries: 17 image entries and 67 video entries. It also identifies Soul ID as a training workflow, so catalog entries do not all represent media generation.

**Does the OpenAPI specification contain every available model?**

Higgsfield explicitly calls the OpenAPI file supplementary. A model missing from that file may still have its own documentation, so use the selected model's documentation when checking its capabilities.

**Can I reuse one workflow's schema for another?**

Higgsfield documents schemas at the workflow level, including required fields, supported values, and examples. Check the exact workflow you intend to use rather than assuming another workflow accepts the same request.

**How often does Higgsfield update its documentation?**

Higgsfield's API terms describe the API reference, changelog, and integration guides as updated from time to time. That wording does not promise a daily or weekly publication schedule.

**What source material do these documentation tools cover?**

They cover public agent-facing Higgsfield documentation, including Markdown pages, the documentation index, published OpenAPI operations, model catalogs, and workflow schemas.

