GPT-4.1 nano: Intelligence, Performance & Price Analysis
Analysis of OpenAI's GPT-4.1 nano and comparison to other AI models across key metrics including quality, price, performance (tokens per second & time to first token), context window & more. Click on any model to compare API providers for that model. For more details including relating to our methodology, see our FAQs.
OpenAI has launched a newer model, GPT-5 nano (medium). We suggest considering this model instead of GPT-4.1 nano. See the following pages for a comparison of GPT-5 nano (medium) to other models and GPT-5 nano (medium) API provider benchmarks.
Comparison Summary
Intelligence:
GPT-4.1 nano is of lower intelligence compared to average, with Artificial Analysis Intelligence Index of 27.
Price:GPT-4.1 nano is cheaper compared to average with a price of $0.17 per 1M Tokens (blended 3:1).
GPT-4.1 nano Input token price: $0.10, Output token price: $0.40 per 1M Tokens.
Speed:GPT-4.1 nano Input token price: $0.10, Output token price: $0.40 per 1M Tokens.
GPT-4.1 nano is slower compared to average, with a output speed of 111.1 tokens per second.
Latency:GPT-4.1 nano has a lower latency compared to average, taking 0.42s to receive the first token (TTFT).
Context Window:GPT-4.1 nano has a larger context windows than average, with a context window of 1.0M tokens.
Highlights
Intelligence
Artificial Analysis Intelligence Index; Higher is better
Speed
Output Tokens per Second; Higher is better
Price
USD per 1M Tokens; Lower is better
Parallel Queries:
Prompt Length:
GPT-4.1 nano Model Details
Comparisons to GPT-4.1 nano
- GPT-4.1 nano
- gpt-oss-20B (high)
- GPT-5 (high)
- gpt-oss-120B (high)
- GPT-5 Codex (high)
- GPT-5 (minimal)
Llama 4 Maverick
Gemini 2.5 Pro
Claude 4.1 Opus- Claude 4 Sonnet
Magistral Medium 1.2
DeepSeek R1 0528- DeepSeek V3.1 Terminus
- DeepSeek V3.1 Terminus
Grok 4 Fast- Grok 4
- Grok Code Fast 1
Solar Pro 2
Llama Nemotron Super 49B v1.5
Kimi K2 0905
EXAONE 4.0 32B
GLM-4.5
Qwen3 235B 2507- Gemini 2.5 Flash
- DeepSeek V3.1
Further details
R1 1776
Nova Premier
Phi-4
LFM2 1.2B
MiniMax-Text-01
Granite 3.3 8B (Non-reasoning)
Reka Flash 3
DeepHermes 3 - Mistral 24B Preview (Non-reasoning)
Aya Expanse 32B
Jamba 1.7 Mini
OpenChat 3.5 (1210)
DBRX Instruct
Llama 3.1 Tulu3 405B
Arctic Instruct
Yi-Large