Using GPT-5 Nano on Replicate API

Implementation guide · GPT-5 · OpenAI

Serverless

Replicate API exposes GPT-5 Nano through model ID openai/gpt-5-nano. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-05-10. Next refresh: weekly.

Quick Start

1
Create an account at Replicate API and generate an API key.
2
Use the Replicate API SDK or REST API to call openai/gpt-5-nano — see the documentation for request format.
3
You'll be billed $0.05/1M input, $0.40/1M output tokens. See full pricing.

API Portal Documentation Pricing Model Card

Code Examples

Install

pip install replicate

API key

REPLICATE_API_TOKEN

Model ID

openai/gpt-5-nano

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.

import replicate

# reads REPLICATE_API_TOKEN from env
# openai/gpt-5-nano format: "owner/model-name" (latest version) or "owner/model-name:version-hash"
output = replicate.run(
    "openai/gpt-5-nano",
    input={"prompt": "Hello"}
)
# Output is a list or generator depending on the model
print("".join(output))

Pricing on Replicate API

Type	Price (per 1M)
Input tokens	$0.05
Output tokens	$0.40

Capabilities

VisionMultimodalReasoningJSON / Tool useStructured OutputsCode ExecutionPrompt CachingBatch API

About GPT-5 Nano

Fastest, cheapest GPT-5 variant for summarization and classification tasks. Also available via Realtime API.

Full model details →

Model Specs

Released2025-08-07

Context400k

ArchitectureDecoder Only

Knowledge cutoff2024-05

Replicate

San Francisco, California, United States