hy3

Model ID: hy3
Vendor: 混元
Category: Language Models

Use hy3 with the compatible FoxRouter API below. Prices and groups are synced from foxrouter.org/pricing when the documentation is built; account groups and availability are shown in the console.

#Pricing

List price

Input: ¥1 / 1M tokens
Output: ¥4 / 1M tokens
Cache read: ¥0.25 / 1M tokens

Price by groupUnit: ¥ / 1M tokens, list price × group multiplier

Group	Input	Output	Cache read
default分组×1默认分组	¥1	¥4	¥0.25
国模svip分组（0.06x）×0.1国内模型就选这个分组（deepseek、glm等），比较稳定	¥0.1	¥0.4	¥0.025
国模特惠分组×0.04国内模型特惠，稳定性相对于svip分组会差一些	¥0.04	¥0.16	¥0.01

Prices and groups synced at 2026-10-30.

#Chat Completions

POSThttps://foxrouter.org/v1/chat/completions

Creates model responses based on chat history. Supports streaming and non-streaming responses.

Compatible with OpenAI Chat Completions API.

#Authorization

Name	Type	Required	Description
`Authorization`	`Bearer <token>`	Yes	使用 Bearer Token 认证。格式: Authorization: Bearer sk-xxxxxx In: header

#Example request

bash

curl -X POST "https://foxrouter.org/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "hy3",
    "messages": [
      {
        "role": "system",
        "content": "string"
      }
    ]
  }'

#Request Body

application/json

Name	Type	Required	Description
`model`	`string`	Yes	模型 ID
`messages`	`array<object>`	Yes	对话消息列表
`temperature`	`number`	No	采样温度 · Default: `1` · Range: `0 <= value <= 2`
`top_p`	`number`	No	核采样参数 · Default: `1` · Range: `0 <= value <= 1`
`n`	`integer`	No	生成数量 · Default: `1` · Range: `1 <= value`
`stream`	`boolean`	No	是否流式响应 · Default: `false`
`stream_options`	`object`	No
`stop`	`string\|array<string>`	No	停止序列
`max_tokens`	`integer`	No	最大生成 Token 数
`max_completion_tokens`	`integer`	No	最大补全 Token 数
`presence_penalty`	`number`	No	Default: `0` · Range: `-2 <= value <= 2`
`frequency_penalty`	`number`	No	Default: `0` · Range: `-2 <= value <= 2`
`logit_bias`	`object`	No
`user`	`string`	No
`tools`	`array<object>`	No
`tool_choice`	`string\|object`	No
`response_format`	`object`	No
`seed`	`integer`	No
`reasoning_effort`	`string`	No	推理强度 (用于支持推理的模型) · Allowed: `"low" \| "medium" \| "high"`
`modalities`	`array<string>`	No
`audio`	`object`	No

#Response Body

#200 OK · `application/json`

json

{
  "id": "string",
  "object": "chat.completion",
  "created": 0,
  "model": "hy3",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "system",
        "content": "string",
        "name": "string",
        "tool_calls": [
          {
            "id": "string",
            "type": "function",
            "function": {
              "name": "string",
              "arguments": "string"
            }
          }
        ],
        "tool_call_id": "string",
        "reasoning_content": "string"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 0,
    "completion_tokens": 0,
    "total_tokens": 0,
    "prompt_tokens_details": {
      "cached_tokens": 0,
      "text_tokens": 0,
      "audio_tokens": 0,
      "image_tokens": 0
    },
    "completion_tokens_details": {
      "text_tokens": 0,
      "audio_tokens": 0,
      "reasoning_tokens": 0
    }
  },
  "system_fingerprint": "string"
}

#400 Bad Request · `application/json`

json

{
  "error": {
    "message": "string",
    "type": "string",
    "param": "string",
    "code": "string"
  }
}

#429 Too Many Requests · `application/json`

json

{
  "error": {
    "message": "string",
    "type": "string",
    "param": "string",
    "code": "string"
  }
}

#Pricing

#Chat Completions

#Authorization

#Example request

#Request Body

#Response Body

#200 OK · application/json

#400 Bad Request · application/json

#429 Too Many Requests · application/json

#Try it online

#200 OK · `application/json`

#400 Bad Request · `application/json`

#429 Too Many Requests · `application/json`