---
id: "meta-llama/llama-3.1-8b-instruct"
also: ["meta-llama/llama-3.1-8b-instruct", "meta-llama/Meta-Llama-3.1-8B-Instruct", "hf/meta-llama/Llama-3.1-8B-Instruct", "requesty/meta/llama-3.1-8b-instruct"]
cheapest_list_usd_per_m: "0.02 in, 0.05 out, at deepinfra on hf"
cheapest_effective_usd_per_m: "0.0194 in, 0.0375 out, at deepinfra/fp8 on openrouter"
context: 131072
max_output: 16384
input: ["text"]
output: ["text"]
released: "2024-07-23"
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p"]
endpoints: 10
gateways: "openrouter (5), hf (4), requesty (1)"
no_training: 6
trains: 0
retains_prompts: 0
coding: 5.4000
---
# Meta: Llama 3.1 8B Instruct

Meta's latest class of models, Llama 3.1, launched with a variety of sizes and configurations. The 8B instruct-tuned version is particularly fast and efficient. It has demonstrated strong performance in human evaluations, outperforming several leading closed-source models.