This model was retired on 2027-04-14. The pricing below is the last-known rate, kept for migration reference.

GPT-4.1 NanoDeprecated

OpenAI
VisionTool usePrompt cachingStructured output
Context
1M
Max output
33K
Serving providers
5
Cheapest input
$0.10 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.

Benchmarks

independent evaluations · source: Artificial Analysis
Speed & latency
Output speed
126 t/s
tokens / second
Time to first token
0.70s
latency
Headline indices
Intelligence Index
9.6
of 100
Coding Index
11.1
of 100
Agentic Index
1.2
of 100
Individual benchmarks · click a row for effort variants
BenchmarkBest scoreEffortCost / task
CritPt0%default
GDPval60.6default
GPQA Diamond51%default
Humanity's Last Exam4%default
IFBench32%default
LiveCodeBench33%default
Long-Context Reasoning19%default
MMLU-Pro66%default
MMMU-Pro40%default
Omniscience-57.6default
Omniscience Accuracy0.1default
Omniscience Non Hallucination0.2default
SciCode26%default
TerminalBench Hard4%default
TerminalBench v2.14%default
τ-bench Banking4%default
τ²-bench17%default

Pricing by serving provider

last-known · per 1M tokens · click a provider to expand
Serving providerInput /1MOutput /1MEndpoints
OpenRouter$0.10$0.401
Azure$0.10$0.401
OpenAI$0.10$0.401
Replicate$0.10$0.401
Vercel AI Gateway$0.10$0.401

Price history

input + output $/1M since we started tracking
Input Output
$0.000$0.100$0.200$0.300$0.400Apr 14Jul 30Jan 12Aug 29$0.400$0.100

Cost calculator

estimate your monthly spend on this model
$52
estimated / month

Model IDs

copy the exact identifier for your platform
openai/gpt-4.1-nanoazure/gpt-4.1-nanogpt-4.1-nanoreplicate/openai/gpt-4.1-nanovercel_ai_gateway/openai/gpt-4.1-nano

Frequently asked questions

GPT-4.1 Nano pricing, context and availability

Is GPT-4.1 Nano still available?

GPT-4.1 Nano was retired on 2027-04-14. The pricing on this page is the last-known rate, kept for migration reference.

How much did GPT-4.1 Nano cost?

GPT-4.1 Nano's last-known pricing, before it was retired on 2027-04-14, was $0.10 per 1M input tokens and $0.40 per 1M output tokens.

What was the context window of GPT-4.1 Nano?

GPT-4.1 Nano had a 1M token context window and could return up to 33K output tokens.

What could GPT-4.1 Nano do?

GPT-4.1 Nano supported image input (vision), tool use, prompt caching and structured output.

Other OpenAI models

compare pricing across the OpenAI lineup

Popular comparisons

head-to-head pages featuring GPT-4.1 Nano
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI