LLM Reference

Llama 2 70B Chat

Released
2023-07-18
Last refreshed
2026-07-09
Status
Researched 90d ago
DeprecatedOpen weightsCommercial use: conditionalClassificationJSON / Tool use

Llama 2 70B Chat is a legacy integration reference; keep it only while you identify a current replacement.

Use it for

  • Teams maintaining an existing integration
  • Workloads that can use a 4k context window
  • Buyers comparing 4 tracked provider routes

Do not use it for

  • New production launches
  • Vision or document-understanding workloads
Specifications
Family
Llama 2
Released
2023-07-18
Context
4k
Parameters
70B
Architecture
Decoder Only
Specialization
general
Openness
Open weights
License
Llama 2 CommunityCommercial use: conditional
Weights
Available
Code
Unknown
Training
Fine-tuned
Created by

Large-scale open-source AI for social technologies.

Menlo Park, California, United States
Founded 2013
Website
Pricing
Output / 1M
$0.500
Input / 1M
$0.500

Cheapest of 14 routes · Lepton AI API

About

Llama 2 70B Chat is a large-scale language model with 70 billion parameters, designed for conversational AI applications. Released on July 18, 2023, it's part of Meta's Llama 2 family, featuring advanced transformer architecture optimized through supervised fine-tuning and reinforcement learning with human feedback. The model excels in generating human-like responses, outperforming many open-source alternatives and rivaling closed-source models like ChatGPT. Trained on 2 trillion tokens from diverse public sources, it's suitable for commercial and research applications in English, particularly for assistant-like functionalities. The model is available on Hugging Face for further exploration and implementation .

Llama 2 70B Chat is an open-weight model in the Llama 2 family. The structured metadata tracks a 4k-token context window and structured outputs. This page tracks provider routes through Databricks Foundation Model Serving, Microsoft Foundry, GCP Vertex AI, and 11 more, with the cheapest tracked route listed at $0.5 input and $0.5 output per 1M tokens. Headline tracked benchmarks include Massive Multitask Language Understanding 68.9.

Top use-case fit

Classification

1 relevant benchmark in the decision map.

JSON / Tool use

Included by capability and metadata signals in the decision map.

Provider price ladder

Compare all 14

Compare API pricing across 4 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
Lepton AI API$0.500$0.500
Serverless
DeepInfra$0.640$0.640
Serverless
Fireworks AI$0.900$0.900
Serverless
Together AI$0.900$0.900
Serverless

Available via routers & gateways(16)

Capabilities

Structured Outputs

Benchmark peer barsfor Classification

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.
BenchmarkScoreVersionEvaluationSource
Massive Multitask Language Understanding68.95-shotObserved 2026-03-07Source

Migration checks

No linked migration route is available for this model yet.

Compare Llama 2 70B Chat with other models

Show all 8 popular comparisonssorted by 7-day search impressions

Frequently asked questions

What is the context window of Llama 2 70B Chat?

Llama 2 70B Chat has a context window of 4k tokens.

How much does Llama 2 70B Chat cost?

Llama 2 70B Chat pricing ranges from $0.5/1M to $1.95/1M input tokens depending on the provider.

When was Llama 2 70B Chat released?

Llama 2 70B Chat was released on 2023-07-18.

Which providers offer Llama 2 70B Chat?

Llama 2 70B Chat is available from 14 providers: Databricks Foundation Model Serving, Microsoft Foundry, GCP Vertex AI, Alibaba Cloud PAI-EAS, AWS Bedrock, OCI Generative AI, NVIDIA NIM, DeepInfra, Lepton AI API, Together AI, IBM watsonx, Scale AI GenAI Platform, Fireworks AI, Replicate API.

What benchmarks has Llama 2 70B Chat been tested on?

Llama 2 70B Chat has been evaluated on 1 benchmark, including Massive Multitask Language Understanding.