[Integrations](https://spiral.ai/integrations) › [ChatGPT](https://spiral.ai/integrations/chatgpt) › [Hy4 Flash](https://spiral.ai/integrations/chatgpt/hy4-flash)

# How to Use Hy4 Flash in ChatGPT

Hy4 Flash is suited to document editing, research briefs, slide outlines, and simple frontend demos. Tencent recommends Hy4 for more demanding work such as long-horizon software engineering.

|  |  |
| --- | --- |
| Model | Hy4 Flash |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.000751 per run at the default inputs. $0.0455 per 1M input tokens, $0.18265 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Hy4 Flash in ChatGPT

- Use Hy4 Flash to compare the source passages in this conversation. Use deeper thinking and write a 500-word decision brief with evidence for each recommendation and a list of unresolved questions.
- Use Hy4 Flash to edit the draft above for first-time users. Answer directly, preserve every number and product name, and explain any sentence whose meaning needs clarification.
- Use Hy4 Flash to turn the brief above into six slides. Include a title, three supporting points, and a short speaker note for each slide. Flag claims that need evidence.
- Use Hy4 Flash to diagnose the spreadsheet formula and sample rows above. Use deeper thinking, explain the failing case, and provide a corrected formula with three expected results.
- Use Hy4 Flash to write a single-page HTML demo from the requirements above. Include a working search box, a clear empty state, and keyboard-accessible controls. Explain how I can check each behavior.

## How to set up Hy4 Flash 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 Hy4 Flash**: 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": "openrouter",
    "model": "tencent/hy4-flash",
    "input": {
      "messages": [
        {
          "role": "user",
          "content": "Hello!"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: ChatGPT finds Hy4 Flash on Spiral, shows the price and runs it.

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

## Hy4 Flash tools and prices

- [Tencent: Hy4 flash](https://spiral.ai/tools/openrouter/tencent/hy4-flash) (OpenRouter): Up to $0.000751 per run at the default inputs. $0.0455 per 1M input tokens, $0.18265 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| stop |  | — |  |
| tools |  | — |  |
| reasoning |  | — | Reasoning effort; reasoning tokens count toward max_tokens. |
| max_tokens | 1 to 65536 | — | The most output tokens to generate. On a reasoning model the reasoning tokens count toward it: a cap too low for the effort can end with no answer (finish_reason length). |
| temperature | 0 to 2 | — |  |
| tool_choice |  | — |  |

## What can you do with Hy4 Flash in ChatGPT?

Turn supplied text into research briefs, revised documents, and presentation outlines with Hy4 Flash. Ask for evidence beside conclusions and specify the audience before drafting.

### Research briefs

Turn collected source passages into a decision brief with supporting evidence and unanswered questions.

### Document revisions

Revise a draft for a specific audience while preserving its claims, figures, and terminology.

### Presentation outlines

Convert a written brief into slide titles, supporting points, and speaker notes.

### Simple frontend demos

Build a small interface from a written brief, with explicit acceptance criteria for each control.

### Spreadsheet formula repair

Review formulas and sample rows, propose a correction, and explain how to check the result.

### Recurring document reviews

Compare successive document texts and draft a digest of changed claims, figures, and instructions.

## Overview

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

## Hy4 Flash in other agents

- [Amp](https://spiral.ai/integrations/amp/hy4-flash)
- [Claude](https://spiral.ai/integrations/claude-desktop/hy4-flash)
- [Claude Code](https://spiral.ai/integrations/claude-code/hy4-flash)
- [Cline](https://spiral.ai/integrations/cline/hy4-flash)
- [Codex](https://spiral.ai/integrations/codex/hy4-flash)
- [Cursor](https://spiral.ai/integrations/cursor/hy4-flash)
- [Devin](https://spiral.ai/integrations/devin/hy4-flash)
- [dots](https://spiral.ai/integrations/dots/hy4-flash)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/hy4-flash)
- [Gemini](https://spiral.ai/integrations/gemini/hy4-flash)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/hy4-flash)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/hy4-flash)
- [goose](https://spiral.ai/integrations/goose/hy4-flash)
- [Grok](https://spiral.ai/integrations/grok/hy4-flash)
- [Grok Build](https://spiral.ai/integrations/grok-build/hy4-flash)
- [Hermes](https://spiral.ai/integrations/hermes/hy4-flash)
- [Instinct](https://spiral.ai/integrations/instinct/hy4-flash)
- [Manus](https://spiral.ai/integrations/manus/hy4-flash)
- [Muse](https://spiral.ai/integrations/muse/hy4-flash)
- [Muse Code](https://spiral.ai/integrations/muse-code/hy4-flash)
- [n8n](https://spiral.ai/integrations/n8n/hy4-flash)
- [Notion](https://spiral.ai/integrations/notion/hy4-flash)
- [OpenClaw](https://spiral.ai/integrations/openclaw/hy4-flash)
- [opencode](https://spiral.ai/integrations/opencode/hy4-flash)
- [Perplexity](https://spiral.ai/integrations/perplexity/hy4-flash)
- [Raycast](https://spiral.ai/integrations/raycast/hy4-flash)
- [VS Code](https://spiral.ai/integrations/vscode/hy4-flash)
- [Windsurf](https://spiral.ai/integrations/windsurf/hy4-flash)
- [Zapier](https://spiral.ai/integrations/zapier/hy4-flash)

## More ChatGPT guides

- [Hy4](https://spiral.ai/integrations/chatgpt/hy4)
- [Hy4 Preview](https://spiral.ai/integrations/chatgpt/hy4-preview)
- [Hy3](https://spiral.ai/integrations/chatgpt/hy3)
- [Inkling](https://spiral.ai/integrations/chatgpt/inkling)
- [Hy-MT2-7B](https://spiral.ai/integrations/chatgpt/hy-mt2-7b)
- [Inkling 2 Mini](https://spiral.ai/integrations/chatgpt/inkling-2-mini)

## Questions about Hy4 Flash in ChatGPT

**Can ChatGPT use Hy4 Flash?**

Yes. Add Spiral to ChatGPT as an MCP server, and ChatGPT can find and run Hy4 Flash like any built-in tool.

**How much does Hy4 Flash cost in ChatGPT?**

Up to $0.000751 per run at the default inputs. $0.0455 per 1M input tokens, $0.18265 per 1M output tokens. 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 OpenRouter account to use Hy4 Flash in ChatGPT?**

No. Spiral runs Hy4 Flash on its own OpenRouter account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Hy4 Flash in ChatGPT?**

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

**Does ChatGPT wait while Hy4 Flash runs?**

Hy4 Flash runs in the background. ChatGPT starts the run, checks on it and gives you the text, json when it's ready.

**What is Hy4 Flash good at?**

Tencent recommends it for everyday document work, research, presentation creation, and simple frontend demos. Start with a concrete deliverable, such as a revised document or a six-slide outline.

**When should I choose Hy4 instead?**

Tencent recommends Hy4 for complex work such as long-horizon software engineering. Keep Hy4 Flash tasks focused, such as building one demo or revising one document.

**How much context does Hy4 Flash support?**

Tencent documents support for up to 1 million tokens of context. That context capacity is separate from the maximum length of a generated answer.

**How long can a Hy4 Flash answer be?**

Tencent lists a maximum output of 64k tokens. For a long deliverable, request an outline first, then draft and review each section.

**Can Hy4 Flash reason before answering?**

Yes. Tencent documents direct-answer and deeper-thinking modes. Try deeper thinking for formula diagnosis or comparing conflicting evidence, and direct answers for straightforward editing.

