How much does the Hy4 API cost?

On FastMetal, Hy4 is billed per token: $0.8799 per 1M input tokens and $2.64 per 1M output tokens on a US-dollar account, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.

Can I call Hy4 with the OpenAI SDK?

Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "hy4" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.

What is the context window of Hy4?

1,000,000 tokens, shared between the prompt and the response.

#23 on the public arena's Overall board (ELO 1,631). Ranks move as the leaderboard is updated.

What do I need to try Hy4?

Create an account and add credit; the model is then available both in the browser chat and over the API. There is no contract or minimum spend.

Back to Models

Tencent

hy4

Hy4

The official release of Hy4 delivers comprehensive and substantial improvements over Hy4 Preview, with particularly strong gains in agentic capabilities and performance across a wide range of long-horizon, real-world productivity...

11/4/2026

1,000,000 tokens

#23 Code (Overall)

Input: $0.8799/M

Output: $2.64/M

Try in Chat Get API Key

Specifications

Modalities

Input

text

Output

text

Supported Parameters

include_reasoning

max_completion_tokens

max_tokens

reasoning

reasoning_effort

response_format

stop

structured_outputs

temperature

tool_choice

tools

Max Output Tokens

65,536

Reasoning Configuration

Default: Thinking on (effort: high)
Selectable effort levels: high
low
none
Turning thinking off: Possible (reasoning.enabled: false)

How to control thinking, and what it costs

Data policy

Prompt retention: Unknown: we could not confirm
Training: Unknown: not declared

"Unknown" does not mean "safe". It means we could not confirm it.

Whether a provider trains on prompts is a declared value from our terms with them. Retention is determined from the upstream listing for every host this model can reach. Neither is guessed.

Code Examples

curl https://api.fastmetal.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "hy4",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

How Hy4 actually answers

Real responses to our standard prompts, recorded on FastMetal.

Count the number of 'r's in 'strawberry'

Count the number of 'r's in 'strawberry'. Explain your reasoning step by step.

The word **“strawberry”** is spelled: **s t r a w b e r r y** Step by step: 1. Check each letter: s, t, **r**, a, w, b, e, **r**, **r**, y 2. Mark the **r**’s: one after **t**, and two near the end before **y**. 3. Count them: 1 + 1 + 1 = **3** So, there are **3** ‘r’s in **“strawberry”**.

4.2s response343 output tokens

Debug This Error

I'm getting the following error in my Node.js application: TypeError: Cannot read properties of undefined (reading 'map') at UserList (/app/components/UserList.js:12:25) at renderWithHooks (/app/node_modules/rea…

The error is caused by this line: ```js {users.map(user => <li key={user.id}>{user.name}</li>)} ``` At render time, `users` is `undefined`. Since `.map()` only exists on arrays, JavaScript tries to read `map` from `undefined` and throws: ```txt Cannot read properties of undefined (reading 'map') ``` Even though this is in a Node.js app, this specific error is happening during React rendering, likely server-side rendering or a Node-based build/render process. Common causes: 1. The parent component is not passing `users`. 2. The prop name is misspelled. 3. `users` comes from async data and is `undefined` on the first render. 4. Your API returns something like `{ users: [...] }`, but you…

20.3s response1951 output tokens

Code Review

Please review the following Python function and suggest improvements for readability, performance, and best practices: def get_data(url, retries=3): import requests import time for i in range(retries):…

Here are the main improvement areas, followed by a possible rewrite. ## Key issues ### Readability / style - Move imports to the top of the module. - Use descriptive names: `response` instead of `r`, `attempt` instead of `i`. - `if item["active"] == True:` should be `if item.get("active") is True:` or simply `if item.get("active"):`, depending on intent. - The filtering loop can be a list comprehension. - Add type hints and a docstring. ### Performance - Repeated imports are cached by Python, so not a major cost, but top-level imports are cleaner. - Avoid sleeping after the final failed attempt. - Use `requests.Session` for connection pooling if this function may be called repeatedly or i…

110.2s response10761 output tokens

Compare these answers side by side with other models →

Frequently asked questions

How much does the Hy4 API cost?: On FastMetal, Hy4 is billed per token: $0.8799 per 1M input tokens and $2.64 per 1M output tokens on a US-dollar account, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.
Can I call Hy4 with the OpenAI SDK?: Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "hy4" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.
What is the context window of Hy4?: 1,000,000 tokens, shared between the prompt and the response.
How does Hy4 rank?: #23 on the public arena's Overall board (ELO 1,631). Ranks move as the leaderboard is updated.
What do I need to try Hy4?: Create an account and add credit; the model is then available both in the browser chat and over the API. There is no contract or minimum spend.

Try Hy4 right now

Hy4 is available on FastMetal through one API key. Start in the browser, or call it from the OpenAI SDK.

Create a free account

Leaderboard

Code

OverallELO: 1,631

#23

Rankings: LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset), CC BY 4.0, snapshot 2026-10-28; category names mapped and ratings rounded by FastMetal.

More from Tencent