LLM Reference

Llama 3.1-70B

Released
2024-07-23
Last refreshed
2026-04-15
Status
Researched 182d ago
Open weightsCommercial use: conditionalRAGAgentsLong contextClassificationJSON / Tool use

Llama 3.1-70B is worth evaluating for rag, agents, and long context when its provider route and context window match the workload.

Use it for

  • Teams evaluating rag, agents, and long context
  • Workloads that can use a 128k context window
  • Buyers comparing 1 tracked provider route

Do not use it for

  • Vision or document-understanding workloads
Specifications
Family
Llama 3.1
Released
2024-07-23
Context
128k
Parameters
70B
Knowledge cutoff
2024-04
Openness
Open weights
License
Llama 3 CommunityCommercial use: conditional
Created by
AI at MetaAI at Meta

Large-scale open-source AI for social technologies.

Menlo Park, California, United States
Founded 2013
Website
Pricing
Output / 1M
$1.20
Input / 1M
$1.20

Cheapest of 1 route · Replicate API

Providers(1)
Replicate API
View 1 provider route

About

Medium-sized Llama 3.1 model balancing performance and efficiency. Excellent for deployment with strong capability retention.

Llama 3.1-70B is an open-weight model in the Llama 3.1 family. The structured metadata tracks a 128k-token context window, function calling, and tool use. This page tracks provider routes through Replicate API, with the cheapest tracked route listed at $1.2 input and $1.2 output per 1M tokens. Headline tracked benchmarks include MMLU PRO 67.6.

Top use-case fit: coding, agents, and build tasks

RAG

Included by capability and metadata signals in the decision map.

Agents

Included by capability and metadata signals in the decision map.

Long context

Included by capability and metadata signals in the decision map.

Provider price ladder

Compare API pricing across 1 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
Replicate API$1.20$1.20
Serverless

Capabilities

Function CallingTool UseFine-tuning

Benchmark peer barsfor Classification

MMLU PRORank 79 of 104
Gemini 3 Pro
91.8
Gemini 3.1 Pro Preview
91.0
Qwen3.7-Max
89.6
Claude Opus 4.6
89.1
Llama 3.1-70Bcurrent
67.6

Benchmark scores(1)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionSource
MMLU PRO67.6—https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro

Migration checks

No linked migration route is available for this model yet.

Frequently asked questions

What is the context window of Llama 3.1-70B?

Llama 3.1-70B has a context window of 128k tokens.

How much does Llama 3.1-70B cost?

Llama 3.1-70B is available at $1.2/1M input tokens through Replicate API.

When was Llama 3.1-70B released?

Llama 3.1-70B was released on 2024-07-23.

Which providers offer Llama 3.1-70B?

Llama 3.1-70B is available from 1 provider: Replicate API.

What benchmarks has Llama 3.1-70B been tested on?

Llama 3.1-70B has been evaluated on 1 benchmark, including MMLU PRO.