How to Use Hy4 in Instinct
Hy4 is suited to complex coding and research tasks that require sustained planning. Compared with Hy4 Preview, it improves long-task execution and supports up to 65,536 output tokens.
Prompts to try with Hy4 in Instinct
Copy an example into Instinct, or ask in your own words.
Every weekday, use Hy4 to summarize the project updates supplied for that day. Report decisions, blockers, and approaching deadlines with references to the source updates.
Every Monday, use Hy4 to compare the supplied research abstracts on numerical optimization. List methods, evaluation conditions, and claims that need closer examination.
Every Monday at 9am: ask Hy4 through Spiral to review the diff on this branch and list the three riskiest changes.
Get a second opinion from Hy4 on this function, then tell me what the call cost.
Summarize these release notes with Hy4 in five bullet points.
How to set up Hy4 in Instinct
Pick the way that suits you. Each takes about two minutes.
Use the Spiral skill
- Send Instinct this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use Spiral's MCP server
- Create an API key
In the console, open API keys and create a key for Instinct. Copy it.
- Send Instinct this message
Instinct reads Spiral's skill and asks for your API key.
set up https://spiral.ai/SKILL.md
- Give Instinct the key
When Instinct asks for the key, add it where Instinct keeps secrets, never in the chat itself.
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run Hy4
One request; the result comes back by polling or a webhook.
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", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Instinct finds Hy4 on Spiral, shows the price and runs it.
Hy4 providers and prices
Spiral runs Hy4 through OpenRouter. Open a card for today's price, with every fee included.
Up to $0.006679 per run at the default inputs. $0.5421 per 1M input tokens, $1.62565 per 1M output tokens.
Settings you can ask for
Ask Instinct for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Max tokens | 1 to 65536 | The most output tokens to generate. | |
| Temperature | 0 to 2 | ||
| Reasoning effort | none, low, or high | high | How much the model reasons. |
Every API field of Tencent: Hy4 is on its tool page: open its card above.
What can you do with Hy4 in Instinct?
Tencent Hy4 can help produce recurring analyses from newly supplied information. Define the reporting period, evidence requirements, and stopping point for each run.
Fix a bug across several files
Trace a failing behavior through the relevant code, propose a focused patch, and check it against the reported failure.
Plan a code migration
Compare existing code with the target requirements, identify dependencies, and break the migration into changes with acceptance checks.
Turn working notes into a report
Combine supplied notes into a report with decisions, unresolved questions, and evidence attached to each conclusion.
Review a financial model
Examine supplied assumptions and tables, explain the calculations, and flag inconsistencies for review.
Prototype a small game
Build a playable loop from a written brief, then refine controls, rules, and failure states through testing.
Develop a research computation
Translate a mathematical or scientific question into a computational approach with explicit assumptions and validation checks.
More on Hy4 and Instinct
Overview
Hy4 in other agents
More Instinct guides
Questions about Hy4 in Instinct
Can Instinct use Hy4?
Yes. Add Spiral to Instinct as an MCP server, and Instinct can find and run Hy4 like any built-in tool.
How much does Hy4 cost in Instinct?
Up to $0.006679 per run at the default inputs. $0.5421 per 1M input tokens, $1.62565 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Instinct plan is separate.
Do I need an OpenRouter account to use Hy4 in Instinct?
You need no OpenRouter account. Instinct uses one Spiral API key for every tool, and Spiral runs Hy4 on its own OpenRouter account.
How long does it take to set up Hy4 in Instinct?
About two minutes: create an API key, then send Instinct this message, then give Instinct the key.
Does Instinct wait while Hy4 runs?
Hy4 runs in the background. Instinct starts the run, checks on it and gives you the text, json when it's ready.
What is Tencent Hy4 useful for?
Coding, office analysis, and scientific research are documented uses. Give it work that requires connecting evidence and completing several related steps.
How much context can Tencent Hy4 handle?
Hy4 and Hy4 Preview each have a 1,048,576-token context window. For a large request, identify the relevant sections and state the exact question you need answered.
How long can a Tencent Hy4 response be?
Hy4 supports up to 65,536 completion tokens; Hy4 Preview supports up to 64,000. Specify the deliverable's length instead of requesting the maximum by default.
Can Tencent Hy4 make factual mistakes?
Yes. Tencent reported lower hallucination rates for Hy4 than Hy4 Preview in an internal evaluation, but errors remained. Ask for supporting passages and verify consequential claims against the original evidence.
Can Tencent Hy4 help build a game?
Game prototyping is a documented use. Start with a small playable loop, define the controls and win condition, and refine it after testing.
Start using Hy4 in Instinct
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Instinct:
set up https://spiral.ai/SKILL.md


