GPT-4.1-nano
The smallest and cheapest GPT-4.1 model, built for the highest-throughput, lowest-cost tasks. Best for simple classification, routing and extraction where every token counts.
At a glance
Released
Apr 14, 2025
Provider
OpenAI
Context window
1,000,000 tokens
Max output
16,000 tokens
Modalities
Text → text
Knowledge cutoff
June 2024
API model ID
gpt-4.1-nanoLicense
Proprietary (API only)
Pricing
Standard
Input$0.10 / 1M
Output$0.40 / 1M
Batch (50% off)
Input$0.05 / 1M
Output$0.20 / 1M
A typical 1,500-token prompt with a 650-token answer costs ≈ $0.0004 on the standard tier. Run your own prompt through the calculator →
What's new vs the previous model
Compared withGPT-4.1-mini (April 2025)
- Lowest cost and latency in the 4.1 family
- Retains the large context window
- High throughput for batch workloads
- Reduced reasoning depth
- Smaller output ceiling and text-only
Best use cases
Bulk classification
Labels enormous volumes of text at minimal cost.
Routing
Decides fast, cheap routing in pipelines.
Simple extraction
Pulls fields from text where precision needs are modest.
Strengths & limitations
Strengths
- Rock-bottom cost
- Large context
- Very fast
- High throughput
Limitations
- Shallow reasoning
- Text-only, small output
How to test it
- No-code: open chatgpt.com and pick GPT-4.1-nano from the model switcher — no API key needed.
- Playground: sign in to the OpenAI Platform and run prompts in the workbench, then copy the generated code.
- API: create a key in the OpenAI Platform and call the API (example below).
curl https://api.openai.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-4.1-nano",
"messages": [{"role": "user", "content": "Explain tokenization in one paragraph."}]
}'