impulse

GPT-4.1 Nano

Frontier lab

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

API id gpt-4.1-nanoReleased 14 Apr 2025 (Apr 2025)
A newer model in this line is out: GPT-5.4 Nano, released 17 Mar 2026.
Azure OpenAI retires it on 14 Apr 2027 (in 147 days). 3 hosts keep serving it.
Input / 1M
$0.10
at OpenAI
Output / 1M
$0.40
at OpenAI
Context window
1M
tokens
Max output
33K
tokens per reply
Hosts
4
10 listings
Released
Apr 2025
14 Apr 2025

Pricing

List prices at OpenAI, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.10$0.40
Cached input
75% off input
$0.025
Batch
50% off
$0.05$0.20
Priority
100% more
$0.20$0.80

What it costs a month

At OpenAI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$53.25
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$44.40
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$81.00
  • Overnight batch20,000 requests a day, 4K in / 0.4K out, batch$168
Use your own numbers

Where to run it

4 hosts serve GPT-4.1 Nano. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
OpenAILab API
gpt-4.1-nano
$0.10 / $0.40
gpt-4.1-nano
$0.10 / $0.40
Retires 14 Apr 2027
ReplicateInference
gpt-4.1-nano
$0.10 / $0.40
gpt-4.1-nano
$0.10 / $0.40
Show 6 more listings: regions, snapshots and variants
OpenAI
2025-04-14
gpt-4.1-nano-2025-04-14
$0.10 / $0.40
2025-04-14 · fine-tuning
ft:gpt-4.1-nano-2025-04-14
$0.20 / $0.80
Azure OpenAI
2025-04-14
gpt-4.1-nano-2025-04-14
$0.10 / $0.40
Retires 14 Apr 2027
eu
gpt-4.1-nano
$0.11 / $0.44
+10% vs headline
Retires 14 Apr 2027
us
gpt-4.1-nano
$0.11 / $0.44
+10% vs headline
Retires 14 Apr 2027
us · 2025-04-14
gpt-4.1-nano-2025-04-14
$0.11 / $0.44
+10% vs headline
Retires 14 Apr 2027

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
ImagesTextPDFs
Produces
Text
Features
Parallel tool callsPDF inputPrompt caching

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than OpenAI.

Smaller OpenAI models

No cheaper OpenAI model keeps its key capabilities.

Other frontier labs

No cheaper match from another frontier lab.

Open-weight picks

  • DeepSeek V4.1 Flash
    DeepSeek · on Sail
    $0.09 / $0.30
    Has every key capability
    19% less
  • MiMo V2.6 Flash
    Xiaomi · on GMI Cloud
    $0.112 / $0.224
    Has every key capability
    20% less
  • Qwen3.6 35B A3B
    Alibaba Qwen · on Sail
    $0.05 / $0.40
    Has every key capability
    21% less
  • MiniMax M3.1 Flash
    MiniMax · on Refuseless
    $0.05 / $0.25
    Has every key capability
    43% less

Benchmarks

Scores published on the model card.

  • Aider Polyglot8.9%

Model line

Newer and older versions, at each lab's own price.

  1. Mar 2026GPT-5.4 NanoLatest$0.20 / $1.25
  2. Aug 2025GPT-5 Nano$0.05 / $0.40
  3. Apr 2025GPT-4.1 NanoThis page$0.10 / $0.40

Call it

Using OpenAI's API.

Python
from openai import OpenAI

client = OpenAI()  # reads OPENAI_API_KEY

response = client.responses.create(model="gpt-4.1-nano", input="Hello")
print(response.output_text)

Quick answers

How much does GPT-4.1 Nano cost?

On OpenAI, GPT-4.1 Nano costs $0.10 per million input tokens and $0.40 per million output tokens. Cached input costs $0.025 per million tokens.

Which APIs offer GPT-4.1 Nano?

GPT-4.1 Nano runs on 4 APIs: OpenAI, Azure OpenAI, Replicate and Vercel AI Gateway.

What is GPT-4.1 Nano's context window?

1M tokens, with up to 33K tokens in one reply.

Is GPT-4.1 Nano being retired?

Azure OpenAI retires it on 14 Apr 2027. 3 hosts keep serving it.

Is there a newer version of GPT-4.1 Nano?

Yes. GPT-5.4 Nano is the newest model in this line, released on 17 Mar 2026.

What are cheaper alternatives to GPT-4.1 Nano?

Models that cost less and keep most of what it can do: DeepSeek V4.1 Flash on Sail (19% less). Savings are on a mix of 3 input tokens to 1 output token.

When was GPT-4.1 Nano released?

OpenAI released it on 14 Apr 2025.

What is GPT-4.1 Nano's API model id?

Use gpt-4.1-nano with OpenAI.

Sources

Raw catalog entry for gpt-4.1-nano on OpenAI
{
  "cache_read_input_token_cost": 2.5e-8,
  "cache_read_input_token_cost_priority": 5e-8,
  "deprecation_date": "2026-10-23",
  "deprecation_source": "https://developers.openai.com/api/docs/deprecations",
  "successor_model": "gpt-5.6-luna",
  "input_cost_per_token": 1e-7,
  "input_cost_per_token_batches": 5e-8,
  "input_cost_per_token_priority": 2e-7,
  "litellm_provider": "openai",
  "max_input_tokens": 1047576,
  "max_output_tokens": 32768,
  "mode": "chat",
  "output_cost_per_token": 4e-7,
  "fedramp_uplift_multiplier": 1.1,
  "output_cost_per_token_batches": 2e-7,
  "output_cost_per_token_priority": 8e-7,
  "source": "https://developers.openai.com/api/docs/pricing",
  "supported_endpoints": [
    "/v1/chat/completions",
    "/v1/batch",
    "/v1/responses"
  ],
  "supported_modalities": [
    "text",
    "image"
  ],
  "supported_output_modalities": [
    "text"
  ],
  "supports_function_calling": true,
  "supports_native_streaming": true,
  "supports_parallel_function_calling": true,
  "supports_pdf_input": true,
  "supports_prompt_caching": true,
  "supports_response_schema": true,
  "supports_system_messages": true,
  "supports_tool_choice": true,
  "supports_vision": true
}