/ Models

Language models

Meta: Llama 3.3 70B Instruct

The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...

Maker
Meta-llama
Context window
131K
Max output
128K
Input / 1M
$0.13
Output / 1M
$0.4
1M in + 1M out
$0.53

Everything else

Max output128K
Input / 1M$0.13
Output / 1M$0.4
Cache read / 1M
Cache write / 1M
1M in + 1M out$0.53
Takestext
Returnstext
Toolsyes
Reasoningno
Open weightsyes
Released2024-12-06
Knowledge cutoff2023-12-31
Retires
Catalog idmeta-llama/llama-3.3-70b-instruct

Benchmarks

sourceepoch
gpqa0.474
gpqaStderr0.0285
mathLevel50.416
mathLevel5Stderr0.0118
aime0.051
aimeStderr0.0236

Benchmark scores by Epoch AI, CC BY 4.0.

Using it

In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.

← all models