Question 1

What is GPT-4.1 Nano?

Accepted Answer

GPT-4.1 Nano is a model from OpenAI, released on Apr 14, 2025. For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million token context window, and scores 80.1% on MMLU, 50.3% on GPQA, and 9.8% on Aider polyglot coding – even higher than GPT‑4o mini. It’s ideal for tasks like classification or autocompletion.

Question 2

How much does GPT-4.1 Nano cost?

Accepted Answer

On the Respan gateway, input starts at $0.10 per 1M tokens on OpenRouter, and output starts at $0.40 per 1M tokens on OpenRouter, after gateway discounts. Averaged across 5 providers, it costs $0.10 per 1M input tokens and $0.40 per 1M output tokens.

Question 3

Which providers serve GPT-4.1 Nano on Respan?

Accepted Answer

5 providers serve GPT-4.1 Nano: OpenRouter, Azure OpenAI, Inference.net, and OpenAI. Azure OpenAI requires your own provider API key (BYOK).

Question 4

What is GPT-4.1 Nano's context window?

Accepted Answer

GPT-4.1 Nano accepts up to 1.0M tokens of context on its largest provider route.

Question 5

How do I use GPT-4.1 Nano with the Respan gateway?

Accepted Answer

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "openai/gpt-4.1-nano-2025-04-14". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Question 6

How fast is GPT-4.1 Nano?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was Azure OpenAI at 98 tokens per second, and the lowest response latency was 0.8 seconds on OpenRouter. Speed varies with request size and provider.

Question 7

Where does GPT-4.1 Nano rank on the Respan Index?

Accepted Answer

GPT-4.1 Nano scores 9.4 out of 100 on the Respan Index v1.1, ranking #135 of 138 models. By category: Coding 1.5, Agents 4.9 (estimated), Reasoning 9.5, Knowledge & language 6.0, and Human preference 31.9. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by llmmetric.com.

Question 8

How does GPT-4.1 Nano score on benchmarks?

Accepted Answer

GPT-4.1 Nano has 12 published benchmark scores, including WeirdML 19%, GPQA Diamond 50.3%, and MATH Level 5 70%. Each score links to where it was published; the data is collected by llmmetric.com.

Provider	Context	Input	Output
OpenRouter`openrouter/openai/gpt-4.1-nano`	1.0M	$0.10/M	$0.40/M
Azure OpenAIBYOK only`azure/gpt-4.1-nano`	1M	$0.10/M	$0.40/M
Inference.net`inference_net/gpt-4.1-nano`	1.0M	$0.10/M	$0.40/M
OpenAI`openai/gpt-4.1-nano`	1M	$0.10/M	$0.40/M
OpenAI`openai/gpt-4.1-nano-2025-04-14`	1.0M	$0.10/M	$0.40/M

GPT-4.1 Nano

Providers

Certified where it counts.

Pricing

Cost by volume

Throughput and latency

Output speed

Time to first token

Response latency

Benchmarks

Respan Indexv1.1

Coding2

Reasoning2

Apps

GPT-4.1 Nano FAQ

Works with your entire stack

Built for AI agents.
Break less.
Ship more.

Math3

Knowledge3

Arena2