gpt-oss-120b by Groq

Free tier, no credit card. Ultra-fast LPU inference.

Access
Free API tier
Free limits
30 RPM · 1,000 RPD · 8K TPM · 200K TPD
Modality
text
Credit card
Not required
Commercial use
Unclear, verify
Context window
131,072 tokens
Rate limit
30 RPM · 1000 RPD · 8,000 TPM · 200,000 TPD
Model ID
gpt-oss-120b
Base URL
https://api.groq.com/openai/v1
Checked
Nov 11, 2026

Benchmarks

LMArena text Elo
1365 · LMArena, Nov 11 2026
Tested as gpt-oss-120b · leaderboard published 2026-11-09
LMArena text rank
#197 of 421 · LMArena, Nov 11 2026
Tested as gpt-oss-120b
SWE-bench Verified
26% · SWE-bench, Nov 11 2026
Tested as gpt-oss-120b · mini-SWE-agent v1.7.0, submitted 2025-08-07

Numbers are copied from the linked public leaderboards for this exact model and version. The free endpoint can run a different reasoning setting or quantization than the tested one.

Quickstart

curl https://api.groq.com/openai/v1/chat/completions \
  -H "Authorization: Bearer $KEY" \
  -d '{"model":"gpt-oss-120b","messages":[{"role":"user","content":"hi"}]}'

Using this model in production?

We wire free-tier and open-weight models into production stacks: evals against your real inputs, failover, cost caps. Book a free 30-minute call.

Frequently asked

Is gpt-oss-120b free?

Yes. Groq offers it as Free API tier with these limits: 30 RPM · 1,000 RPD · 8K TPM · 200K TPD. No credit card is required.

Can I use gpt-oss-120b commercially?

Commercial terms are not clearly documented. Check the provider's current terms before shipping.

How do I start using gpt-oss-120b?

Free tier, no credit card. Ultra-fast LPU inference.

Free monthly update

The monthly free-models update

What is newly free, what got rate-limited, and what to switch to. One email a month. Unsubscribe anytime.

Related free models