# Hunyuan Hy4 Flash MCP and API - Chat model by Tencent | FlyMy.AI

> Tencent Hunyuan Hy4 Flash is a fast, low-cost model for agents and everyday workflows, with image input and a 1M-token context.

Page: https://flymy.ai/mcp/models/hy4-flash/

MCP / Models / Language models

# Hunyuan Hy4 Flash MCP: everyday workflows with no API key

Tencent Hunyuan Hy4 Flash is a fast, low-cost model for agents and everyday workflows, with image input and a 1M-token context. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.

[Use Hunyuan Hy4 Flash](https://flymy.ai/mcp/models/hy4-flash/#start) [Inputs and price](https://flymy.ai/mcp/models/hy4-flash/#inputs)

No API key, $0.07 / $0.281 per 1M tokens, Chat model, Tencent, Commercial use

$ YOUR NEXT RUN

Claude Code, Codex, Cursor, Any agent

## Use Hunyuan Hy4 Flash in your assistant

Paste this prompt into Claude Code, Codex, Cursor or any agent. It reads the guide and helps you connect.

```
Read https://flymy.ai/skill.md and https://flymy.ai/mcp/models/hy4-flash.md. Help me connect the FlyMy.AI MCP to this assistant, then run Hunyuan Hy4 Flash (flymyai/hy4-flash) for this task: Ask Hunyuan Hy4 Flash: review this function for bugs and explain the fix.
```

[Open FlyMy.AI](https://app.flymy.ai/new-agent) [Download brief](https://flymy.ai/mcp/models/hy4-flash.md)

## What Hunyuan Hy4 Flash does

Send a prompt, or a chat history in messages with images as image_url parts, and get a text answer from a 1M-token context. reasoning_effort is none, low or high (high by default), and reasoning tokens are billed as output; system_prompt and max_tokens (up to 65,536) work as usual, and private_mode keeps the prompt and answer out of FlyMy.AI storage and logs on synchronous calls. Call it with your FlyMy.AI key in two ways: the FlyMy.AI API, or the OpenAI-compatible Chat Completions endpoint, where it also calls your function tools and takes their results back. Leave tool_choice at auto there: a named or required tool_choice is not available for this model through FlyMy.AI. It answers in text only; use the image, video and audio models to create media.

## Hunyuan Hy4 Flash inputs

Every input of `flymyai/hy4-flash` as its live schema lists them. Returns `output` (string), `finish_reason` (string), `service_tier` (string), `reasoning` (string), `stream_details` (string).

| Input | Type, values and default |
|---|---|
| [#](https://flymy.ai/mcp/models/hy4-flash/#input-prompt) `prompt` | string required What to ask Hunyuan Hy4 Flash |
| [#](https://flymy.ai/mcp/models/hy4-flash/#input-messages) `messages` | string optional Chat history as a JSON array of {role, content}; used instead of the prompt |
| [#](https://flymy.ai/mcp/models/hy4-flash/#input-system_prompt) `system_prompt` | string optional Instructions for the whole chat |
| [#](https://flymy.ai/mcp/models/hy4-flash/#input-reasoning_effort) `reasoning_effort` | string optional Allowed: none, low, high Default: `high` How hard Hunyuan Hy4 Flash thinks before answering |
| [#](https://flymy.ai/mcp/models/hy4-flash/#input-max_tokens) `max_tokens` | integer optional Allowed: 1 to 65536 Most tokens to generate, reasoning included |
| [#](https://flymy.ai/mcp/models/hy4-flash/#input-private_mode) `private_mode` | boolean optional Default: `false` Keep the prompt and the answer out of FlyMyAI storage and logs (synchronous requests only) |

## Ask your agent

Requests to paste as they are, once the FlyMy.AI MCP is connected.

**“Ask Hunyuan Hy4 Flash: review this function for bugs and explain the fix.”** runs `flymyai/hy4-flash`

**“Summarize this contract into five bullet points with Hunyuan Hy4 Flash.”** runs `flymyai/hy4-flash`

**“With Hunyuan Hy4 Flash, draft a friendly reply to this customer email.”** runs `flymyai/hy4-flash`

## Hunyuan Hy4 Flash price

$0.07 per 1M input tokens, $0.281 per 1M output tokens, cached input $0.003 per 1M. Cached input is $0.003 per 1M tokens. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.

[See usage pricing →](https://flymy.ai/pricing/)

## Call Hunyuan Hy4 Flash from code

The same model, from an agent or from your own code. Keys stay in your FlyMy.AI account.

### From an agent, through the MCP

The agent calls `get_model_schema`, then `run_model` with:

```
{
  "endpoint_id": "flymyai/hy4-flash",
  "input": {
    "prompt": "Explain in two sentences what an MCP server is."
  }
}
```

### From your code, over HTTP

Form fields, not JSON; files go as uploads or public URLs. Text models answer on the streaming route.

```
curl -X POST https://api.flymy.ai/api/v1/flymyai/hy4-flash/predict/stream/ \
  -H "X-API-KEY: $FLYMYAI_API_KEY" \
  -F 'prompt=Explain in two sentences what an MCP server is.'
```

### With the OpenAI SDK

Hunyuan Hy4 Flash also answers the OpenAI Chat Completions protocol.

```
from openai import OpenAI

client = OpenAI(base_url="https://api.flymy.ai/api/v1/flymyai/hy4-flash/openai/v1", api_key="YOUR_FLYMYAI_KEY")
reply = client.chat.completions.create(
    model="flymyai/hy4-flash",
    messages=[{"role": "user", "content": "Explain in two sentences what an MCP server is."}],
)
print(reply.choices[0].message.content)
```

## Questions about Hunyuan Hy4 Flash

**Do I need a Tencent API key for Hunyuan Hy4 Flash?**

No. Hunyuan Hy4 Flash runs on FlyMy.AI's account, so you need no Tencent key or plan: sign in to FlyMy.AI once and each run is billed to your FlyMy.AI balance.

**How much does Hunyuan Hy4 Flash cost?**

$0.07 per 1M input tokens, $0.281 per 1M output tokens, cached input $0.003 per 1M. There is no subscription or minimum; the price comes from FlyMy.AI billing and was checked on 2026-11-18.

**How do I use Hunyuan Hy4 Flash in Claude Code, Codex or Cursor?**

Add the FlyMy.AI MCP with one command and sign in, then ask in plain words, for example: "Ask Hunyuan Hy4 Flash: review this function for bugs and explain the fix." Your agent reads the inputs with get_model_schema and runs flymyai/hy4-flash with run_model.

**What does Hunyuan Hy4 Flash need as input?**

Hunyuan Hy4 Flash requires prompt; it also takes 5 optional inputs, each listed on this page with its allowed values and default.

**Can I call Hunyuan Hy4 Flash from my own code?**

Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/hy4-flash/predict/stream/ with your FlyMy.AI API key in the X-API-KEY header; it also answers the OpenAI Chat Completions protocol at https://api.flymy.ai/api/v1/flymyai/hy4-flash/openai/v1.

## More language models

Chat and reasoning models for code, documents and agents, plus typed decisions for routing and triage.

### Hunyuan Hy4

Tencent's Hy4 reasoning model, the release of Hy4 Preview, for agents and long documents.

Chat model / $0.834 / $2.501 per 1M tokens

Link: https://flymy.ai/mcp/models/hy4/

### Gemini 4 Hydrogen

The Flash-class Gemini 4 for everyday apps and agents, with audio, video and PDF input.

Chat model / $1.50 / $7.50 per 1M tokens

Link: https://flymy.ai/mcp/models/gemini-4-hydrogen/

### GLM 5.3

Z.ai's flagship GLM for long agent runs and coding, with reasoning on by default.

Chat model / $1.40 / $4.40 per 1M tokens

Link: https://flymy.ai/mcp/models/glm-5-3/

### GPT-6.2 Astra

The newer GPT-6 flagship from OpenAI for the hardest coding, research and agent work.

Chat model / $8.00 / $40.00 per 1M tokens

Link: https://flymy.ai/mcp/models/gpt-6-2-astra/

### GPT-6.2 Sol

GPT-6.2 for coding, agents and knowledge work at a quarter of Astra's price.

Chat model / $2.00 / $10.00 per 1M tokens

Link: https://flymy.ai/mcp/models/gpt-6-2-sol/

### Inkling 2 Small

Thinking Machines' open-weight Inkling 2 Small under Apache 2.0, for agents and coding.

Chat model / $0.30 / $1.00 per 1M tokens

Link: https://flymy.ai/mcp/models/inkling-2-small/

## Go to the source

[Hunyuan Hy4 Flash in the playground →](https://app.flymy.ai/models/flymyai/hy4-flash), [Hunyuan Hy4 Flash guide in the docs →](https://docs.flymy.ai/guides/use-llms), [Model endpoints in the docs →](https://docs.flymy.ai/api/models-endpoints), [Every model on FlyMy.AI →](https://flymy.ai/mcp/models/), [Every MCP in the catalog →](https://flymy.ai/mcp/#catalog), [Usage pricing →](https://flymy.ai/pricing/)

From the FlyMy.AI model catalog of 2026-11-18: inputs from the model's live schema, prices from FlyMy.AI billing. Requests are examples to paste, not recorded runs.

---

For agents: the FlyMyAI operating guide (sign up, connect, run models, tools and agents) is https://flymy.ai/skill.md, and https://flymy.ai/llms.txt lists the other pages and the documentation.
