Zephyr 7B Beta on Replicate API

Zephyr · Hugging Face H4

ServerlessOpen Source

Last refreshed 2026-09-30. Next refresh: weekly.

Why use Zephyr 7B Beta on Replicate API?

Replicate API offers Zephyr 7B Beta 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 Zephyr 7B Beta across 2 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(
    "nateraw/zephyr-7b-beta",
    input={"prompt": "Hello"}
Model ID
nateraw/zephyr-7b-beta

Request example

import replicate

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

Gotchas

  • Use provider model ID "nateraw/zephyr-7b-beta", not the LLMReference slug "zephyr-7b-beta".
  • 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 Zephyr 7B Beta Across Providers

ProviderInput (per 1M)Output (per 1M)
Fireworks AI$0.20$0.20
Replicate API$0.05$0.25

Pricing

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

Capabilities

No model capability flags are currently sourced.

About Zephyr 7B Beta

Zephyr 7B Beta is a 7-billion parameter large language model, fine-tuned from the Mistral-7B-v0.1 model. It is tailored to serve as an effective virtual assistant, performing well in generating human-like responses. The model's training involved Direct Preference Optimization (DPO) on a combination of publicly available and synthetic datasets, achieving strong performance on benchmarks like MT-Bench and AlpacaEval, especially for conversational tasks. However, its complexity falls short when compared to proprietary models, especially in tasks involving coding and mathematics. A notable limitation is its insufficient alignment to human safety preferences and the absence of in-the-loop filtering to prevent problematic outputs.

Get Started

Model Specs

Released2023-10-26
Parameters7B
ArchitectureDecoder Only

Related Models on Replicate API