OpenAI: GPT-4.1 Nano

deprecatedproprietary

For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series.

Intelligence
Speed
Context
1.0M
Max output
943K
Input price
$0.1/1M tokens
Output price
$0.4/1M tokens

Capabilities

Reasoning & Interaction
Tool Calling
Output Control
Structured Output
JSON Mode
Infrastructure
Streaming
Batch Processing
Fine-tuning

Details

Model IDopenai/gpt-4.1-nano
Provider OpenRouter
Creator OpenAI
Familygpt-4.1
Licenseproprietary
Statusdeprecated
Typechat
Input modalitiesimage, text
Output modalitiestext
Open weightNo
Parameters—
Architecture—
Context window1.0M tokens
Max input—
Max output943K tokens
Reasoning tokens—
Knowledge cutoff
Release date
Deprecation date
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

Pricing

Input
$0.1
Output
$0.4
Cache write
—
Cache read
$0.03
Batch in
—
Batch out
—

Family Comparison: gpt-4.1

ModelContextMax outPricing
OpenAI: GPT-4.1 Nano (batch)1.0M33K$0.05$0.2
OpenAI: GPT-4.1 Nano1.0M943K$0.1$0.4
OpenAI: GPT-4.1 Mini (batch)1.0M33K$0.2$0.8
OpenAI: GPT-4.1 Mini1.0M33K$0.4$1.6
OpenAI: GPT-4.1 (batch)1.0M33K$1$4
OpenAI: GPT-4.11.0M33K$2$8

API

GET/v1/models/openrouter/openai/gpt-4.1-nano

OpenAI: GPT-4.1 Nano

deprecated
openai/gpt-4.1-nano

For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series.

Changes · 7 entries
openai/gpt-4.1-nanoupdateca7a400Nov 2, 2026, 03:02 AM
max_output_tokens32768→942818
pricingcached input$0.025→$0.03
openai/gpt-4.1-nanoupdateb2f45bfOct 29, 2026, 03:29 AM
max_output_tokens32768→942818
pricingcached input$0.025→$0.03
openai/gpt-4.1-nanoupdatee3fc6e0Aug 31, 2026, 07:31 AM
max_output_tokens942818→32768
pricingcached input$0.03→$0.025
openai/gpt-4.1-nanoupdatee3d7dedAug 31, 2026, 04:13 AM
max_output_tokens32768→942818
pricingcached input$0.025→$0.03
openai/gpt-4.1-nanoupdate1cd659eMar 24, 2026, 04:19 AM
capabilitiesjson modeyes
openai/gpt-4.1-nanoupdate2b100acMar 23, 2026, 05:30 AM
model_typechat
release_date2025-04-14
taglineFor tasks that demand low latency, GPT‑4.1 nano is the fa...
tools["function_calling"]
openai/gpt-4.1-nanocreate7f5c66fMar 21, 2026, 05:16 AM