---
id: "meta-llama/llama-3.3-70b-instruct"
also: ["meta-llama/llama-3.3-70b-instruct", "meta-llama/Llama-3.3-70B-Instruct", "hf/meta-llama/Llama-3.3-70B-Instruct", "requesty/meta/llama-3.3-70b-instruct"]
cheapest_list_usd_per_m: "0.1 in, 0.32 out, at deepinfra/turbo on openrouter"
cheapest_effective_usd_per_m: "0.0997 in, 0.3154 out, at deepinfra/turbo on openrouter"
context: 131072
max_output: 115200
input: ["text"]
output: ["text"]
released: "2024-12-06"
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: 21
gateways: "openrouter (13), hf (5), requesty (3)"
no_training: 16
trains: 0
retains_prompts: 0
coding: 11.9000
---
# 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...