Back

Meta: Llama 3 8B Instruct

Llama3
Input: text
Output: text
Released: Apr 18, 2024Updated: Mar 28, 2025

Meta's latest class of model (Llama 3) launched with a variety of sizes & flavors. This 8B instruct-tuned version was optimized for high quality dialogue usecases.

It has demonstrated strong performance compared to leading closed-source models in human evaluations.

To read more about the model release, click here. Usage of this model is subject to Meta's Acceptable Use Policy.

8,192 Token Context

Process and analyze large documents and conversations.

Advanced Coding

Improved capabilities in front-end development and full-stack updates.

Agentic Workflows

Autonomously navigate multi-step processes with improved reliability.

Available On

ProviderModel IDContextMax OutputInput CostOutput CostThroughputLatency
DeepInfradeepInfra8K16K$0.03/M$0.06/M131.7 t/s221 ms
NovitanovitaAi8K8K$0.04/M$0.04/M69.4 t/s899 ms
Groqgroq8K8K$0.05/M$0.08/M3862.4 t/s466 ms
Mancer 2mancer (private)16K2K$0.05/M$0.25/M28.3 t/s1022 ms
Togethertogether8K-$0.10/M$0.10/M213.4 t/s333 ms
Cloudflarecloudflare8K-$0.28/M$0.83/M15.5 t/s811 ms
Standard Pricing
Input Tokens
$0.00000003

per 1K tokens

Output Tokens
$0.00000006

per 1K tokens

Do Work. With AI.