Gemma 4 31B by NVIDIA NIM

Free coding model via NVIDIA NIM (tier A, SWE-bench ~45%).

Access
Free API tier
Free limits
Prototyping only · rate limits not published
Modality
code, text
Credit card
Not required
Commercial use
Unclear, verify
Context window
256,000 tokens
Model ID
google/gemma-4-31b-it
Checked
Nov 12, 2026

Benchmarks

AA Intelligence Index
4.38 · Artificial Analysis, Nov 11 2026
Tested as Gemma 4 31B (Reasoning)
LMArena text Elo
1443 · LMArena, Nov 11 2026
Tested as Gemma 4 31B · leaderboard published 2026-11-09
LMArena text rank
#73 of 421 · LMArena, Nov 11 2026
Tested as Gemma 4 31B

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.

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 Gemma 4 31B free?

Yes. NVIDIA NIM offers it as Free API tier with these limits: Prototyping only · rate limits not published. No credit card is required.

Can I use Gemma 4 31B commercially?

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

How do I start using Gemma 4 31B?

Free coding model via NVIDIA NIM (tier A, SWE-bench ~45%).

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