NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...
一个入口,连通你接入的每个模型
免费模型12
NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and...
North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized...
dots-studio
Dots Studio: Dots3-Note Preview (free)
Dots3-Note Preview is an open-weight mixture-of-experts model from Dots Studio, with 16B active parameters out of 280B total. It is the lightest model in the Dots 3 family and is...
Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...
LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or...
A compact 1.7B-parameter text model with a 256K-token context, post-trained for agents, tool calling, and structured outputs. It reasons before it answers. Prompts and outputs may be retained and used...
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...
NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...
付费模型9
比官方价格低 20–44%
GPT 6.1 Sol
1.1M工具
输入 · Free Model US$1.20
US$2.00输出 · Free Model US$6.00
US$10.00低 40%
GPT 6.1 Terra
1.1M工具
输入 · Free Model US$0.60
US$1.00输出 · Free Model US$3.00
US$5.00低 40%
GPT 6 Luna
272K工具
输入 · Free Model US$0.06
US$0.10输出 · Free Model US$0.30
US$0.50低 40%
GPT 6 Astra
272K工具
输入 · Free Model US$5.60
US$10.00输出 · Free Model US$28.00
US$50.00低 44%
Gemini 4 Argon
1M工具
输入 · Free Model US$1.60
US$2.00输出 · Free Model US$8.00
US$10.00低 20%
Claude Sonnet 5.5
1M工具
输入 · Free Model US$1.60
US$2.00输出 · Free Model US$8.00
US$10.00低 20%
Claude Opus 5.5
1M工具
输入 · Free Model US$3.20
US$4.00输出 · Free Model US$16.00
US$20.00低 20%
Claude Haiku 5.5
1M工具
输入 · Free Model US$0.08
US$0.10输出 · Free Model US$0.40
US$0.50低 20%
Grok 4.7
1M工具
输入 · Free Model US$1.60
US$2.00输出 · Free Model US$4.80
US$6.00低 20%
使用方式
- 1
连接服务商
粘贴你的 OpenRouter 密钥。密钥在服务器上加密保存,之后不会再显示。
- 2
和已连接的模型对话
每条消息都可以选模型,也可以交给 Auto 自动选一个可用的。
- 3
在代码中调用
用你自己的 API 密钥,把任意 OpenAI SDK 指向 Free Model。
from openai import OpenAI
client = OpenAI(
base_url="https://freemodel.io/api/v1",
api_key="sk_…",
)
reply = client.chat.completions.create(
model="free/auto",
messages=[{"role": "user", "content": "Hello"}],
)常见问题
哪些免费,哪些付费?
免费模型是 OpenRouter 上以 :free 结尾且推理定价为零的模型。付费模型单独列出,只有你自己选择时才会消耗预付积分。调用额度由 OpenRouter 设定;模型被限流时,Auto 会尝试其他可用的免费模型。
为什么要用自己的密钥?
免费额度按账户计算。用自己的密钥,额度归你自己,也可以随时在服务商那里撤销。
对话会被保存吗?
不会。对话只保存在当前打开的页面中,关闭页面、新建对话或退出登录后即消失。请求记录保存模型、token、状态和耗时等用量元数据,不保存对话正文。
可以发图片或文件吗?
网页对话支持文本;付费 API 还可使用对应模型支持的媒体输入。
有什么可以帮你?
开始对话