Llama 3.3 70B by Groq

No longer free

No longer free (checked Nov 11, 2026). Deprecations page: llama-3.3-70b-versatile shutdown 08/16/26 (replacement openai/gpt-oss-120b or qwen/qwen3.6-27b); models page lists it as Enterprise / Contact Sales, absent from rate-limits table

Check the provider docs for current pricing, or browse the models that are free today.

Status
No longer free
Free limits
No longer free (checked Nov 11, 2026)
Modality
text, code
Credit card
Not required
Commercial use
Allowed
Rate limit
30 RPM · 1000 RPD
Model ID
llama-3.3-70b-versatile
Base URL
https://api.groq.com/openai/v1
Checked
Nov 11, 2026

Benchmarks

LMArena text Elo
1274 · LMArena, Nov 11 2026
Tested as Llama 3.3 70B Instruct · leaderboard published 2026-11-09
LMArena text rank
#281 of 421 · LMArena, Nov 11 2026
Tested as Llama 3.3 70B Instruct

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.

Replacing a retired 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 Llama 3.3 70B still free?

No. No longer free (checked Nov 11, 2026). Deprecations page: llama-3.3-70b-versatile shutdown 08/16/26 (replacement openai/gpt-oss-120b or qwen/qwen3.6-27b); models page lists it as Enterprise / Contact Sales, absent from rate-limits table

What should I use instead of llama-3.3-70b-versatile?

Use the paid tier if the price fits, or move to a model that is still free and keep a paid fallback behind it. The directory at https://www.ayautomate.com/free-models lists what is free today, checked against each provider's own docs.

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