LLM ReferenceLLM Reference
OpenAI Batch API

Using GPT-4.1 Nano on OpenAI Batch API

Implementation guide · GPT-4.1 · OpenAI

Serverless

Quick Start

  1. 1
    Create an account at OpenAI Batch API and generate an API key.
  2. 2
    Use the OpenAI Batch API SDK or REST API to call gpt-4.1-nano — see the documentation for request format.
API PortalDocumentationPricing

About OpenAI Batch API

OpenAI's Batch API for asynchronous, cost-effective processing of large workloads with 50% token discount

View all models on OpenAI Batch API →

Pricing on OpenAI Batch API

Capabilities

VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode Execution

About GPT-4.1 Nano

Fastest and most cost-effective GPT-4.1 variant from OpenAI. Released April 2025 alongside GPT-4.1 and GPT-4.1 Mini. 1 million token context window optimized for high-volume applications.

Full model details →

Model Specs

Released2025-04-01
Context1M
ArchitectureDecoder Only
Knowledge cutoff2025-01

More Models on OpenAI Batch API

GPT-4.1GPT-4.1 Mini
All models on OpenAI Batch API →

Also available on(2)

Replicate API$0.10/1MOpenRouter$0.10/1M
Compare all providers →

Provider

OpenAI Batch API
OpenAI Batch API

OpenAI

San Francisco, California, United States