FREE AI INDEX / 统一产品界面我的收藏提交资源 ↗

FreeLLM 免费 AI 资源索引FreeLLM Free AI Index / 资源详情Offer details

SiliconFlow · ¥0 listed modelsSiliconFlow · ¥0 listed models

SiliconFlow 硅基流动 · ChinaSiliconFlow · China

◆ 加精◆ Featured✓ 实测通过✓ Network verified国内外均可用China + global国内 214ms · 海外 750msChina 214ms · Global 750ms✓ 接口已验证 · 206ms✓ Endpoint verified · 206ms

◆ 加精理由：实测 206ms · 长期免费，价目表 ¥0◆ Why featured: 206 ms measured · permanently free, ¥0 list price

这个资源提供什么What this offer provides

SiliconFlow's current official price/model pages list XingChenAGI/Xing4.0-29B at ¥0 input and ¥0 output, alongside other ¥0 models. Xing4.0 is a China Telecom model released on 2026-09-17 with 29B total / 4B active parameters and native 256K context.SiliconFlow's current official price/model pages list XingChenAGI/Xing4.0-29B at ¥0 input and ¥0 output, alongside other ¥0 models. Xing4.0 is a China Telecom model released on 2026-09-17 with 29B total / 4B active parameters and native 256K context.

关键信息Key details

免费方式Free methodSelected official ¥0 models now include China Telecom Xing4.0-29B alongside OCR, embedding, reranker and image models.Selected official ¥0 models now include China Telecom Xing4.0-29B alongside OCR, embedding, reranker and image models.
有效期ValidityFree listing can change; recheck the price pageFree listing can change; recheck the price page
访问条件AccessSiliconFlow account; China registrationSiliconFlow account; China registration
最后核验Last checked2026-09-29

快速上手Quick start

Call the models listed at ¥0 on the official price list via the SiliconFlow APIFollow the model-specific steps to register, create a key and connect the model.

✓

注册与接入步骤Registration and access steps

准备条件Prerequisites

  • SiliconFlow account
  • API key from the SiliconFlow cloud console
  1. Register on the SiliconFlow cloud platform and create an API keyRegister on the SiliconFlow cloud platform and create an API key
  2. Call the OpenAI-compatible chat or embeddings endpoint with a model ID listed at ¥0 on the official price pageCall the OpenAI-compatible chat or embeddings endpoint with a model ID listed at ¥0 on the official price page
SiliconFlow 云平台SiliconFlow ↗查看 API 文档 / 控制台API docs / console ↗
4

发送第一条请求Send first request

使用下方命令开始调用。Use the command below to make your first request.

可复制命令Copyable command
export SILICONFLOW_API_KEY="你的 Key"
curl https://api.siliconflow.cn/v1/chat/completions --header "Authorization: Bearer $SILICONFLOW_API_KEY" --header 'Content-Type: application/json' --data '{"model":"tencent/Hunyuan-MT-7B","messages":[{"role":"user","content":"Hello"}]}'

详细操作步骤Detailed operation paths

每条路径都拆成前置条件、步骤、可复制命令和验证动作；免费条件仍以官方页面实时状态为准。curl 命令按 macOS / Linux shell 编写，Windows 用户可使用同页的 Python 或 Node.js 示例。Each path includes prerequisites, steps, copyable commands and a validation action; free terms still follow the provider's live official policy. The curl examples use a macOS/Linux shell; Windows users can run the Python or Node.js examples on this page.

调用 SiliconFlow 免费模型

api

EndpointEndpoint
https://api.siliconflow.cn/v1
认证Authentication
Authorization: Bearer API key
额度与限制Limits

调用额度与限流按提供商当前控制台和官方文档为准；免费条件可能按模型、账号和地区变化。

前置条件Prerequisites

  • 已注册 SiliconFlowSiliconFlow
  • 已创建 API keyAPI key
  • 已在模型广场确认模型的免费或赠送额度状态See official terms

操作步骤Steps

  1. 创建 API key

    进入 SiliconFlow 控制台的 API key 页面创建密钥，并保存为 SILICONFLOW_API_KEY 环境变量。

  2. 查看模型与余额

    在模型广场确认模型 ID、上下文限制和当前免费政策；免费模型不等于无限调用。

    操作Action：打开 https://siliconflow.cn/models

  3. 发送兼容请求

    使用模型广场展示的完整模型 ID。

    命令已在上方「快速上手」给出。The copyable command already appears in Quick start above.

    预期结果Expected：返回 choices[0].message.content；余额不足时停止重试并查看控制台。

  4. Python SDK 示例

    安装 OpenAI SDK；在运行环境设置 SILICONFLOW_API_KEY，示例代码通过环境变量读取密钥。

    可复制命令Copyable command
    python -m pip install -U openai

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["SILICONFLOW_API_KEY"],
    base_url="https://api.siliconflow.cn/v1",
)
response = client.chat.completions.create(
    model="XingChenAGI/Xing4.0-29B",
    messages=[{"role": "user", "content": "用一句话解释 API 是什么。"}],
)
print(response.choices[0].message.content)

    预期结果Expected：终端打印模型生成的回复；再到提供商控制台确认请求状态和额度扣减。

  5. Node.js SDK 示例

    安装 OpenAI SDK；在运行环境设置 SILICONFLOW_API_KEY，示例代码通过环境变量读取密钥。

    可复制命令Copyable command
    npm install openai

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.SILICONFLOW_API_KEY,
  baseURL: "https://api.siliconflow.cn/v1",
});
const response = await client.chat.completions.create({
  model: "XingChenAGI/Xing4.0-29B",
  messages: [{ role: "user", content: "用一句话解释 API 是什么。" }],
});
console.log(response.choices[0].message.content);

    预期结果Expected：Node.js 打印模型生成的回复；再到提供商控制台确认请求状态和额度扣减。

验证动作Validation

GET /v1/models 返回 HTTP 200，并在控制台确认请求消耗与免费政策一致。

常见问题Common issues
  • 401：检查 API Key、环境变量和认证 Header。401： API Key、 Header。
  • 404：从官方模型清单复制当前模型 ID，并确认 endpoint 与账号地域一致。404： ID， endpoint 。
  • 429：查看当前限流和配额重置说明，降低请求频率后再重试。429： ， 。

官方来源Official sources

免费模型逐个看Free models by entry

模型Model上下文窗口Context window免费额度Free quota备注Notes
XingChenAGI/Xing4.0-29BXingChenAGI/Xing4.0-29B
Xing4.0-29BXing4.0-29B		256K native; extensible to 512K256K native; extensible to 512K¥0 input / ¥0 output on SiliconFlow¥0 input / ¥0 output on SiliconFlowChina Telecom XingChen model; official SiliconFlow price/model pages list the hosted API at ¥0. Recheck before production use because the ¥0 list can change.China Telecom XingChen model; official SiliconFlow price/model pages list the hosted API at ¥0. Recheck before production use because the ¥0 list can change.
PaddleOCR-VL-1.5PaddleOCR-VL-1.5——¥0（官方价目表标注免费）¥0（ ）价目表可随时调整，用前重查，
tencent/Hunyuan-MT-7Btencent/Hunyuan-MT-7B——¥0（官方价目表标注免费）¥0（ ）价目表可随时调整，用前重查，
BAAI/bge-m3BAAI/bge-m3——¥0（官方价目表标注免费）¥0（ ）价目表可随时调整，用前重查，
BAAI/bge-reranker-v2-m3BAAI/bge-reranker-v2-m3——¥0（官方价目表标注免费）¥0（ ）价目表可随时调整，用前重查，
BAAI/bge-large-zh-v1.5 · BAAI/bge-large-en-v1.5BAAI/bge-large-zh-v1.5 · BAAI/bge-large-en-v1.5——¥0（官方价目表标注免费）¥0（ ）价目表可随时调整，用前重查，
Kwai-KolorsKwai-Kolors——¥0（官方价目表标注免费）¥0（ ）价目表可随时调整，用前重查，

额度以官方页面和控制台实时显示为准；公测或限免额度可能随时调整。Quota follows the official page and console; preview or limited free access can change.

FreeLLM 实测FreeLLM test · freellm-text-v2 · 22 题 · 7 维度 · 2026-10-19

FreeLLM 模型实测FreeLLM model test

我们用自己的账号直接调用该平台得到的结果（同渠道实测）。Results from calling this platform directly with our own key.

模型Model综合分Score成功率Success首 token p50TTFT p50生成速度Tokens/s报告Report
Xing4.0-29BXingChenAGI/Xing4.0-29B91100%943 msp95 1677 ms66 token/s报告Report →
Hunyuan-MT-7Btencent/Hunyuan-MT-7B3686%1585 msp95 5086 ms25 token/s报告Report →

Xing4.0-29B

XingChenAGI/Xing4.0-29B · 硅基流动 SiliconFlow · 默认思考模式thinks by default
91分pts
综合分Score91 / 100
成功率Success rate100%（22/22 题有回答）
首 token p50 / p95TTFT p50 / p95943 ms / 1677 ms
生成速度（中位）Tokens/s (median)66 token/s
  • 中文知识Chinese knowledge100
  • 推理数学Reasoning & math100
  • 代码Coding100
  • 指令格式Format following100
  • 长文本Long context100
  • 工具调用Tool calling100
  • 防幻觉Anti-hallucination33
中文知识满分Full marks: Chinese knowledge推理数学满分Full marks: Reasoning & math代码满分Full marks: Coding指令格式满分Full marks: Format following长文本满分Full marks: Long context默认长思考，响应慢Thinks by default, slower容易编造Tends to fabricate

硅基流动 ¥0 模型，中文、推理、长文本和工具调用全对，但三道防编造题全部编了答案。

适合Good for
国内直连的中文长文本整理、工具调用
不建议Avoid for
事实核查、学术引用

在实测报告中查看Open in test report →逐题原始输出Raw per-case outputs ↗

Hunyuan-MT-7B

tencent/Hunyuan-MT-7B · 硅基流动 SiliconFlow
36分pts
综合分Score36 / 100
成功率Success rate86%（19/22 题有回答）
首 token p50 / p95TTFT p50 / p951585 ms / 5086 ms
生成速度（中位）Tokens/s (median)25 token/s
  • 中文知识Chinese knowledge100
  • 推理数学Reasoning & math20
  • 代码Coding0
  • 指令格式Format following67
  • 长文本Long context100
  • 工具调用Tool calling0
  • 防幻觉Anti-hallucination0
中文知识满分Full marks: Chinese knowledge长文本满分Full marks: Long context推理数学弱Weak: Reasoning & math代码弱Weak: Coding工具调用弱Weak tool calling容易编造Tends to fabricate

翻译专用模型，不支持工具调用，通用题不建议使用。

适合Good for
中外互译
不建议Avoid for
通用问答、代码、Agent

在实测报告中查看Open in test report →逐题原始输出Raw per-case outputs ↗

查看该平台全部 2 个实测模型（含不可用端点）All 2 tested models on this platform →

方法：同一套 22 道固定题、temperature=0、全部自动评分；测试节点：GitHub Actions 托管运行器（美国）。数字只代表该时间点、我们的账号和该测试节点，地区与账号不同结果会不同。Method: the same 22 fixed cases, temperature 0, auto-graded; vantage: GitHub Actions (US). Numbers reflect that run, our accounts and that vantage only. 完整报告Full report →

官方来源Official sources

Official SiliconFlow pages list XingChenAGI/Xing4.0-29B at ¥0 for both input and output. The official XingChen-AGI repository confirms China Telecom developed Xing4.0-29B-A4B, released it on 2026-09-17, and documents 29B total parameters, 4B active per token and native 256K context extensible to 512K.Official SiliconFlow pages list XingChenAGI/Xing4.0-29B at ¥0 for both input and output. The official XingChen-AGI repository confirms China Telecom developed Xing4.0-29B-A4B, released it on 2026-09-17, and documents 29B total parameters, 4B active per token and native 256K context extensible to 512K.

相关资源Related resources