Groq

The fastest inference on the market. No credit card.

Groq runs open models on its own LPU chips, which is why tokens come back faster than almost anyone else gives away. An email gets you the key. No card. The free chat list is GPT-OSS, Qwen 3.6/3.8 and Compound — Llama, Kimi and DeepSeek left.

Limits are per model: 30 requests a minute and 1,000 a day on the chat ids, 250 a day on Compound. The old 14,400 figure is only for the prompt-guard classifiers. OpenAI-compatible at api.groq.com/openai/v1; they also ship a native SDK if you want it.

Free models: 7
Max context: 131K
Free tier: 1,000 requests per day
Requirement: Email account, no card

Endpoint

Base URLhttps://api.groq.com/openai/v1

Env varGROQ_API_KEY

Rate limit30 requests/minute, 1,000 requests/day

OpenAI-compatible
Native SDK: Groq SDK
text
image
reasoning

Code examples

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)

Worth knowing

Rate limits are per model: chat models sit at 1,000 requests/day; Compound is 250. The 14,400 figure is only for the prompt-guard classifiers.
Llama 3.3, Kimi K2 and DeepSeek are gone from the free list — they are Enterprise-only or retired.

Models you get for free7

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