Groq

Groq 在自研 LPU 芯片上运行开放模型，这就是 token 回得比别人都快的原因。一个邮箱就能拿到密钥，不要卡。免费对话列表是 GPT-OSS、Qwen 3.6/3.8 和 Compound —— Llama、Kimi 和 DeepSeek 已离开。

获取 API 密钥官方文档 ↗

限额按模型计：对话 id 为每分钟 30 次、每天 1,000 次，Compound 每天 250 次。旧的 14,400 那个数字只适用于提示防护分类器。OpenAI 兼容地址是 api.groq.com/openai/v1；需要的话也有官方 SDK。

免费模型: 7
最大上下文: 131K
免费额度: 每天 1,000 次请求
注册要求: 只要邮箱，不要卡

端点

接口地址https://api.groq.com/openai/v1

环境变量GROQ_API_KEY

速率限制30 requests/minute, 1,000 requests/day

OpenAI 兼容
官方 SDK：Groq SDK
文本
图像
推理

代码示例

npm install openai

import OpenAI from 'openai'

const client = new OpenAI({
  baseURL: 'https://api.groq.com/openai/v1',
  apiKey: process.env.GROQ_API_KEY
})

const response = await client.chat.completions.create({
  model: 'openai/gpt-oss-120b',
  messages: [{ role: 'user', content: 'Explain closures in one paragraph.' }]
})

console.log(response.choices[0].message.content)

pip install openai

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.groq.com/openai/v1",
    api_key=os.environ["GROQ_API_KEY"],
)

response = client.chat.completions.create(
    model="openai/gpt-oss-120b",
    messages=[{"role": "user", "content": "Explain closures in one paragraph."}],
)

print(response.choices[0].message.content)

curl https://api.groq.com/openai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $GROQ_API_KEY" \
  -d '{
    "model": "openai/gpt-oss-120b",
    "messages": [{"role": "user", "content": "Explain closures in one paragraph."}]
  }'

npm install groq-sdk

import Groq from 'groq-sdk'

const groq = new Groq({ apiKey: process.env.GROQ_API_KEY })

const response = await groq.chat.completions.create({
  model: 'openai/gpt-oss-120b',
  messages: [{ role: 'user', content: 'Explain closures in one paragraph.' }]
})

console.log(response.choices[0].message.content)

pip install groq

import os
from groq import Groq

client = Groq(api_key=os.environ["GROQ_API_KEY"])

response = client.chat.completions.create(
    model="openai/gpt-oss-120b",
    messages=[{"role": "user", "content": "Explain closures in one paragraph."}],
)

print(response.choices[0].message.content)

值得注意

速率限制按模型计：对话模型每天 1,000 次；Compound 为 250 次。14,400 那个数字只适用于提示防护分类器。
Llama 3.3、Kimi K2 和 DeepSeek 已离开免费列表 —— 只剩企业版或已下线。

你能免费使用的模型7

GPT-OSS 120Bopenai/gpt-oss-120b
GPT-OSS 20Bopenai/gpt-oss-20b
GPT-OSS Safeguard 20Bopenai/gpt-oss-safeguard-20b
Qwen 3.8 27Bqwen/qwen3.8-27b
Qwen 3.6 27Bqwen/qwen3.6-27b
Groq Compoundgroq/compound
Groq Compound Minigroq/compound-mini