/ Models

Language models

Meta: Llama 3.1 70B Instruct

Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases. It has demonstrated strong...

Maker
Meta-llama
Context window
131K
Max output
16K
Input / 1M
$0.4
Output / 1M
$0.4
1M in + 1M out
$0.8

Everything else

Max output16K
Input / 1M$0.4
Output / 1M$0.4
Cache read / 1M
Cache write / 1M
1M in + 1M out$0.8
Takestext
Returnstext
Toolsyes
Reasoningno
Open weightsyes
Released2024-07-23
Knowledge cutoff2023-12-31
Retires
Catalog idmeta-llama/llama-3.1-70b-instruct

Benchmarks

sourceepoch
gpqa0.442
gpqaStderr0.0245
mathLevel50.367
mathLevel5Stderr0.0102
aime0.036
aimeStderr0.0169

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