Llama 2 7B Chat on Replicate API

Llama 2 · AI at Meta

ServerlessOpen Weights

Last refreshed 2026-07-09. Next refresh: weekly.

Why use Llama 2 7B Chat on Replicate API?

Replicate API offers Llama 2 7B Chat with pay-as-you-go pricing at $0.05/1M input tokens. Replicate is a cloud-based platform that enables users to run machine learning models easily and efficiently.

Compare Llama 2 7B Chat across 10 providers to find the best fit for your use case
Input / 1M
$0.050
Output / 1M
$0.25
Cache
Not sourced
Batch
Not sourced

Setup recipe

Python + curl
Install
pip install replicate
Auth
export REPLICATE_API_TOKEN=...
Call
import replicate
output = replicate.run(
    "meta/llama-2-7b-chat",
    input={"prompt": "Hello"}
Model ID
meta/llama-2-7b-chat

Request example

import replicate

# reads REPLICATE_API_TOKEN from env
# meta/llama-2-7b-chat format: "owner/model-name" (latest version) or "owner/model-name:version-hash"
output = replicate.run(
    "meta/llama-2-7b-chat",
    input={"prompt": "Hello"}
)
# Output is a list or generator depending on the model
print("".join(output))

Gotchas

  • Use provider model ID "meta/llama-2-7b-chat", not the LLMReference slug "llama2-7b-chat".
  • Replicate uses "owner/model-name" format (e.g. "meta/meta-llama-3-8b-instruct") for the latest version, or "owner/model-name:version-sha" to pin to a specific version. The REST endpoint splits owner and model-name into the path: /v1/models/{owner}/{model-name}/predictions.
  • The examples expect REPLICATE_API_TOKEN; rename it only if your application config maps the new variable.

Compare Llama 2 7B Chat Across Providers

ProviderInput (per 1M)Output (per 1M)
Alibaba Cloud PAI-EAS——
Baseten API——
Fireworks AI$0.20$0.20
Microsoft Foundry$0.52$0.67
GCP Vertex AI$0.08$0.24
View all 10 providers →

Pricing

TypePrice (per 1M)
Input tokens$0.05
Output tokens$0.25

Capabilities

Structured Outputs

About Llama 2 7B Chat

The Llama 2 7B Chat model is a fine-tuned variant of Meta's Llama 2 series, optimized for conversational AI applications. Built on an auto-regressive transformer architecture, it boasts 7 billion parameters and has been trained on a diverse dataset of 2 trillion tokens. The model underwent supervised fine-tuning and reinforcement learning with human feedback to enhance its performance in dialogue scenarios. It demonstrates competitive capabilities in terms of helpfulness and safety compared to both open-source and closed-source alternatives like ChatGPT and PaLM.

Get Started