Ultra-fast inference on custom LPU chips (500+ tokens/sec) for open models like Llama, Qwen, and DeepSeek distills.
Pricing: Free tier (no CC, ~30 RPM); paid ~$0.05-$0.90 /M input; batch 50% off
Instant self-serve — free signup gives a key immediately (a human unblocks an agent in under 2 minutes).
Free signup (email verify), no credit card; instant key at console.groq.com/keys; Developer tier adds a card for higher limits
Groq (GroqCloud) — Ultra-fast inference on custom LPU chips (500+ tokens/sec) for open models like Llama, Qwen, and DeepSeek distills.
Website: https://groq.com
Docs: https://console.groq.com/docs
Get a key: https://console.groq.com/keys
Agent signup: self serve instant key — Free signup (email verify), no credit card; instant key at console.groq.com/keys; Developer tier adds a card for higher limits
Auth: api-key
Pricing: freemium — Free tier (no CC, ~30 RPM); paid ~$0.05-$0.90 /M input; batch 50% off
Full record: https://dreaming.press/api/tools/groq.jsonMachine record: /api/tools/groq.json
from groq import Groq
client = Groq(api_key="GROQ_API_KEY")
r = client.chat.completions.create(
model="llama-3.3-70b-versatile",
messages=[{"role": "user", "content": "Hello"}])
print(r.choices[0].message.content)
python · full docs →
Groq (GroqCloud) is Ultra-fast inference on custom LPU chips (500+ tokens/sec) for open models like Llama, Qwen, and DeepSeek distills. It's in the LLM gateways & inference category of the dreaming.press tool directory.
Groq (GroqCloud) is freemium — free to start, paid plans for scale. Free tier (no CC, ~30 RPM); paid ~$0.05-$0.90 /M input; batch 50% off.
Almost — signup is instant and self-serve (a free key with no sales call), so a human can unblock an agent in under two minutes. Free signup (email verify), no credit card; instant key at console.groq.com/keys; Developer tier adds a card for higher limits.
Groq (GroqCloud) does not publish an official MCP server as of our last check.
Groq (GroqCloud) is a hosted API service, not an open-source project.
Groq (GroqCloud) offers Python, TypeScript, REST, OpenAI-compatible.
We track the AI stack so you don't have to — pricing, MCP support, and which tools an agent can sign up for. Free.