# Hy3 — API, capabilities & pricing | Y-API

> Tencent Hy3 is a text-only MoE model with 295B total and 21B active parameters in its publisher card. The reference describes direct-answer and reasoning modes, with an emphasis on multi-turn constraints and tool-driven work.

This is the markdown representation of https://y-api.bestvirtualgoods.com/models/tencent/hy3. Generated by `scripts/generate-seo-assets.mjs` from the same copy the page renders — do not edit by hand.

Model ID: `tencent/hy3`

Sources reviewed: 2026-10-04. Y-API catalog snapshot: 2026-10-04.

## Choosing this model

Selection advice by Y-API. The checks below are suggested evaluations, not published test results.

### Where to start

Try it for document extraction with explicit missing-information handling. Make it distinguish a supplied fact from an assumption, especially when a short business request omits a date or amount.

### What to watch for

A published emphasis on grounded answers is not evidence that hallucination has been eliminated. Include underspecified questions in your evaluation and check how reasoning settings reach the gateway.

## Model specifications

These are OpenRouter model-level specifications, not a Y-API compatibility test. A particular route may accept fewer input formats, parameters or tokens. Verify the features you need with a small request; a successful text response does not validate vision or tool calling.

| Field | Value |
| --- | --- |
| Context window | 262,144 tokens |
| Input | Text |
| Output | Text |
| Listed on OpenRouter | 2026-07-06 |
| Parameters listed by OpenRouter | `frequency_penalty`, `include_reasoning`, `logit_bias`, `max_completion_tokens`, `max_tokens`, `min_p`, `presence_penalty`, `reasoning`, `reasoning_effort`, `repetition_penalty`, `response_format`, `seed`, `stop`, `structured_outputs`, `temperature`, `tool_choice`, `tools`, `top_k`, `top_p` |

## Estimate your cost

The current catalog marks this model as free: calls do not deduct credit. This does not promise unlimited capacity, permanent availability or a future free price.

$1 paid adds $10 of credit. Cash equivalent = credit consumed ÷ 10; this is not the model publisher’s list price.

Input tokens / request: 1000. Output tokens / request: 500. Number of requests: 1000.

Estimated credit consumed: Free — no credit deducted. Estimated cash equivalent: Free — no credit deducted.

Illustrative token budget, not measured usage or a quote. Includes input and output; excludes separate media charges, cache discounts and retries. Include billed reasoning tokens in your output budget where applicable. Actual billing follows usage returned by the service.

### Same token budget, different models

| Model | Estimated credit consumed | Estimated cash equivalent |
| --- | --- | --- |
| [Hy3](https://y-api.bestvirtualgoods.com/models/tencent/hy3) | Free — no credit deducted | Free — no credit deducted |
| [Hy4 preview](https://y-api.bestvirtualgoods.com/models/tencent/hy4-preview) | $2.50 | $0.25 |
| [MiniMax M2.7](https://y-api.bestvirtualgoods.com/models/minimax/minimax-m2.7) | Free — no credit deducted | Free — no credit deducted |

## Use the API

These minimal, text-only requests use the exact Y-API model ID. They do not demonstrate image, audio, video, file or tool support. The output limit also needs room for reasoning; an empty answer with finish_reason=length can mean the budget was exhausted.

Set the TOKEN environment variable to a key from your console. Run this on your server or locally; never expose a key in browser code or a public repository.

### A task to try

From this note extract supplier, amount and due_date; use null when absent: Pay Acme Tools USD 240 for the replacement part.

```bash
curl --fail-with-body --silent --show-error --max-time 120 \
  'https://api.y-api.bestvirtualgoods.com/v1/chat/completions' \
  -H "Authorization: Bearer ${TOKEN:?Set TOKEN first}" \
  -H 'Content-Type: application/json' \
  --data-binary @- <<'JSON'
{
  "model": "tencent/hy3",
  "messages": [
    {
      "role": "user",
      "content": "From this note extract supplier, amount and due_date; use null when absent: Pay Acme Tools USD 240 for the replacement part."
    }
  ],
  "max_tokens": 4096
}
JSON
```

```python
import json
import os
import sys
import urllib.error
import urllib.request

payload = {
  "model": "tencent/hy3",
  "messages": [
    {
      "role": "user",
      "content": "From this note extract supplier, amount and due_date; use null when absent: Pay Acme Tools USD 240 for the replacement part."
    }
  ],
  "max_tokens": 4096
}

request = urllib.request.Request(
    "https://api.y-api.bestvirtualgoods.com/v1/chat/completions",
    data=json.dumps(payload).encode("utf-8"),
    headers={
        "Authorization": "Bearer " + os.environ["TOKEN"],
        "Content-Type": "application/json",
    },
    method="POST",
)
try:
    with urllib.request.urlopen(request, timeout=120) as response:
        result = json.load(response)
    print(json.dumps(result, ensure_ascii=False, indent=2))
except urllib.error.HTTPError as error:
    print(error.read().decode("utf-8"), file=sys.stderr)
    raise SystemExit(1)
```

### How to evaluate the result

Expect the supplied supplier and amount, with a null due date. Add contradictory notes and follow-up corrections to see whether the model preserves the latest constraint.

## Before you choose

### Does Hy3 always use a reasoning mode?

OpenRouter describes a direct no-thinking default plus selectable reasoning modes. Do not assume the Y-API route preserves that default; verify the response and token usage with your intended settings.

## Sources & scope

Technical facts come from the cited model page and, where available, its linked publisher card. A card describes that checkpoint; it is not proof of the weights a gateway serves. Prices come only from the Y-API catalog. We do not claim measured latency, uptime or benchmark scores for this endpoint.

- [OpenRouter model page & specifications](https://openrouter.ai/tencent/hy3)
- [Publisher model card linked by OpenRouter](https://huggingface.co/tencent/Hy3)
- [Y-API catalog & prices (JSON)](https://y-api.bestvirtualgoods.com/models.json)

## Models to compare

Compare these alternatives on the same inputs. Their descriptions explain different roles; a lower price does not establish equivalent quality.

### [Hy4 preview](https://y-api.bestvirtualgoods.com/models/tencent/hy4-preview)

Tencent Hy4 preview scales the Hy family to a 770B-parameter backbone with 49B active parameters and a longer context than Hy3. It is a text-only preview aimed at coding agents and sustained tool-use workflows.

### [MiniMax M2.7](https://y-api.bestvirtualgoods.com/models/minimax/minimax-m2.7)

MiniMax M2.7 is a text model centered on agentic productivity: debugging, root-cause analysis and multi-step professional work. Its published examples involve external tools; a completion alone does not execute that workflow.

## Links

- HTML version of this page: https://y-api.bestvirtualgoods.com/models/tencent/hy3
- Site index for agents: https://y-api.bestvirtualgoods.com/llms.txt
- Full reference (single file): https://y-api.bestvirtualgoods.com/llms-full.txt
- OpenAPI 3.1 spec: https://y-api.bestvirtualgoods.com/openapi.json
- Model catalog (JSON, no key needed): https://y-api.bestvirtualgoods.com/models.json
- API base URL: `https://api.y-api.bestvirtualgoods.com/v1`
- Contact: support@bestvirtualgoods.com
- Model catalog: https://y-api.bestvirtualgoods.com/models
- Integration guide: https://y-api.bestvirtualgoods.com/docs