OpenAI · language model
GPT-4.1 Nano: pricing, context and benchmarks
GPT-4.1 Nano is OpenAI's model released on April 14, 2025. It costs $0.1 per million input tokens and $0.4 per million output tokens, with a 1M-token context window. Epoch AI ranks it #118 of 125 rated models.
What you need to know about GPT-4.1 Nano
OpenAI, based in United States, put GPT-4.1 Nano online on April 14, 2025. It accepts images, text, and files as input and produces text. Its context window reaches 1,047,576 tokens, larger than 79 % of the models in the registry, and it can write up to 32,768 tokens in one go.
Released more than 1 year ago, it belongs to a generation most vendors have since superseded.
GPT-4.1 Nano pricing
On OpenRouter, GPT-4.1 Nano costs $0.1 per million input tokens and $0.4 per million output tokens. Counting three tokens read for every token written, its average price is $0.175 per million, more expensive than 18 % of paid models (4.4 times cheaper than the median of $0.76).
A concrete example: a task that sends 2,000 tokens (about 1,500 words) and receives a 500-token answer costs $0.0004. At 1,000 tasks a day, budget $12 a month. The price calculator redoes this with your own volumes.
Tokens already sent and cached are billed at $0.025 per million. With batch processing (delayed answers), the price drops to $0.05 input and $0.2 output.
Performance and benchmarks
The Epoch Capabilities Index (ECI), which aggregates published results across many benchmarks, gives GPT-4.1 Nano a score of 129.5 (range 123.3 to 131.8). That places it #118 of 125 rated models.
Scores published by Epoch AI on the benchmarks the site tracks:
| Benchmark | What it measures | Score | Date |
|---|---|---|---|
| GPQA Diamond | PhD-level science questions | 48.9 % | Apr 14, 2025 |
| ARC-AGI-1 | visual abstract-reasoning puzzles | 0 % | Apr 14, 2025 |
| ARC-AGI-2 | harder version of the ARC puzzles | 0 % | Apr 14, 2025 |
| OTIS Mock AIME | maths competition problems | 28.9 % | Apr 14, 2025 |
| SimpleQA Verified | accuracy on simple facts | 6 % | Apr 14, 2025 |
| Aider Polyglot | coding exercises in several languages | 8.9 % | Apr 14, 2025 |
For at least equal performance, DeepSeek V4 Flash 0731, DeepSeek V4 Flash 0423, and Qwen3.7 Flash cost at least 30% less.
Features, privacy and local use
- It supports tool calling, so it can drive an AI agent, call APIs or MCP servers.
- It can answer in an enforced JSON format (structured outputs).
- Its knowledge stops at June 2024.
Its weights are not published: it can only be used through the OpenAI API or a broker such as OpenRouter, which means sending your data off your machines.
Other OpenAI models
| Model | Released | Avg. price | ECI |
|---|---|---|---|
| GPT-6.1 Sol | Sep 29, 2026 | $4 | 168.4 |
| GPT-6.1 Sol Pro | Sep 29, 2026 | $4 | — |
| GPT-6 Sol | Sep 22, 2026 | $4 | 163.7 |
| GPT-6 Luna | Sep 22, 2026 | $0.2 | 156.8 |
| GPT-6 Luna Pro | Sep 22, 2026 | $0.2 | — |
| GPT-6 Sol Pro | Sep 22, 2026 | $4 | — |
| GPT-6 Astra | Sep 4, 2026 | $20 | 168.8 |
| GPT-6 Astra Pro | Sep 4, 2026 | $20 | — |
Verdict
Computed score: 47/100, from public data (performance, price, context, features).
Strengths
- Low price: cheaper than 82 % of paid models.
- Very large context (1M tokens): long documents or a whole codebase fit in one request.
- Agent-ready: tool calling and structured JSON output.
- Discounted batch pricing.
Limitations
- Modest performance: behind 94 % of rated models.
- Older generation, often replaced by a newer model from the same vendor.
Avoid if…
- your data must not leave your servers.
Alternatives
- Llama 4 Scout$0.15
- Llama 4 Maverick$0.3
- Gemma 3 27B$0.15
- Qwen3.5-9B$0.19
- Gemma 3 12B$0.08
- Qwen3 32B$0.13
Comparisons and tools
Learn more
Frequently asked questions
How much does GPT-4.1 Nano cost?
$0.1 per million input tokens and $0.4 per million output tokens on OpenRouter (checked October 25, 2026). A task with 2,000 tokens read and 500 written costs $0.0004.
How big is GPT-4.1 Nano's context window?
1,047,576 tokens, roughly 786,000 words, with a maximum of 32,768 output tokens.
Can GPT-4.1 Nano run locally?
No, OpenAI does not publish its weights: it is API-only.
Is GPT-4.1 Nano suitable for an AI agent?
Technically yes: it supports tool calling and structured outputs. Then check its cost for your volume.
How good is GPT-4.1 Nano?
Epoch AI ranks it #118 of 125 rated models (ECI 129.5). On GPQA Diamond, it scores 48.9%.
What are the alternatives to GPT-4.1 Nano?
The closest models on price and performance are Llama 4 Scout, Llama 4 Maverick, and Gemma 3 27B.
Related articles
- Mistral AI: models, pricing and agentsOctober 25, 2026
- LLM benchmarks: how to read model rankingsOctober 24, 2026
- Running a local LLM: hardware, software, and limitationsOctober 24, 2026
- Open-source or closed models for your AI agents?October 5, 2026
Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score