Llama 3.3 70B

Meta · Llama 3 · open · released Dec 6, 2024 · meta-llama/Llama-3.3-70B-Instruct

Llama 3 family:Llama 3.1 405B·Llama 3.1 8B·Llama 3.3 70B

Meta's best open text-only model — beats many frontier models on reasoning while fitting on 2×A100s.

Pricing

InputOpen weights / ~$0.20 / 1M hosted
OutputOpen weights / ~$0.20 / 1M hosted
Cost bandFree/open
Free tierOpen weights (Meta Llama license).

Limits

Context window128k checked Jul 19, 2026
Max outputRuntime-dependent
Knowledge cutoffDec 2023
DeploymentSelf-hosted, Hugging Face, Groq, Together, Fireworks
OpenAI-compatible APIYes
ModalitiesText

Where it fits

Best forProduction text-only self-hosted workloads needing near-frontier quality without GPU excess.
Business fitThe standard reference open model for serious deployments — widely benchmarked and trusted.

Capabilities

Open weightsFunction callingReasoning

Benchmark scores

Composite78 / 100
Coding76 / 100 (LiveCodeBench)
Reasoning80 / 100 (MMLU-Pro)
Long context74 / 100 (RULER 128K)
Instruction following80 / 100 (IFEval)

Editorial aggregate of published benchmark results as of Jan 1, 2025. These are not independent measurements run by this site.

Change history

No recorded changes for this model yet. Pricing and context are checked daily; changes appear here with dates and sources.

Data

Last checkedJul 19, 2026
Cross-checked againstopenrouter.ai/meta-llama/llama-3.3-70b-instruct

Verify with provider documentation before committing spend. Report an error and it gets fixed with a logged correction.

Open in the comparison table JSON API