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.
Providers
Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick: Balanced (price + speed), Nitro (fastest), or Floor (cheapest).
BYOK only | $0.05 | $0.20 | $0.0125 | -- | -- |
|---|
Input $0.05 / Output $0.20-- tok/s-- uptimeBYOK only
Pricing
The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.
GPT-4.1 Nano (batch) — Price history
| $0.05 | $0.20 | $0.0125 | — |
- Input $0.05 / Output $0.20
Performance
Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).
Uptime
Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.
Not enough uptime data to display yet.
When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.
Benchmarks
Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.
| Source | Benchmark | Score |
|---|---|---|
| Artificial Analysis | GPT-4.1 nano Coding Index | 11.1 |
| Artificial Analysis | GPT-4.1 nano GPQA Diamond | 51.2% |
| Artificial Analysis | GPT-4.1 nano HLE | 3.8% |
| Artificial Analysis | GPT-4.1 nano IFBench | 32.0% |
| Artificial Analysis | GPT-4.1 nano τ²-Bench Telecom | 17.3% |
| Artificial Analysis | GPT-4.1 nano AA-LCR | 20.3% |
| Artificial Analysis | GPT-4.1 nano τ-Bench Banking | 3.5% |
| Artificial Analysis | GPT-4.1 nano GDPval-AA | 0.0% |
| Artificial Analysis | GPT-4.1 nano CritPt | 0.0% |
| Artificial Analysis | GPT-4.1 nano LiveCodeBench | 32.6% |
| Artificial Analysis | GPT-4.1 nano Terminal-Bench Hard | 3.8% |
| Artificial Analysis | GPT-4.1 nano Terminal-Bench 2.1 | 3.7% |
| Artificial Analysis | GPT-4.1 nano MMLU-Pro | 65.7% |
| Artificial Analysis | GPT-4.1 nano AIME 2025 | 24.0% |
| Artificial Analysis | GPT-4.1 nano AIME | 23.7% |
| Artificial Analysis | GPT-4.1 nano MATH-500 | 84.8% |
| Design Arena | GPT-4.1 nano Models Arena 3D Elo | 905 |
| Design Arena | GPT-4.1 nano Models Arena Code Categories Elo | 952 |
| Design Arena | GPT-4.1 nano Models Arena Data Visualization Elo | 888 |
| Design Arena | GPT-4.1 nano Models Arena Game Development Elo | 960 |
| Design Arena | GPT-4.1 nano Models Arena UI Component Elo | 906 |
| Design Arena | GPT-4.1 nano Models Arena Website Elo | 965 |
| Vals AI | GPT 4.1 Nano AIME | 26.5% |
| Vals AI | GPT 4.1 Nano CorpFin v2 | 42.1% |
| Vals AI | GPT 4.1 Nano Finance Agent v1 | 2.5% |
| Vals AI | GPT 4.1 Nano GPQA Diamond | 50.8% |
| Vals AI | GPT 4.1 Nano LiveCodeBench | 42.7% |
| Vals AI | GPT 4.1 Nano LegalBench | 61.1% |
| Vals AI | GPT 4.1 Nano MATH 500 | 80.2% |
| Vals AI | GPT 4.1 Nano MedQA | 68.2% |
| Vals AI | GPT 4.1 Nano MGSM | 69.3% |
| Vals AI | GPT 4.1 Nano MMLU Pro | 63.5% |
| Vals AI | GPT 4.1 Nano MMMU Pro | 55.1% |
| Vals AI | GPT 4.1 Nano MortgageTax | 52.8% |
| Vals AI | GPT 4.1 Nano TaxEval v2 | 60.8% |
Apps
Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.
Not enough data for apps using this model yet.
Activity
Token volume and request traffic to this model over time.
API
Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.
Not currently available through EU in-region routing. In-region routing docs
Documentation
Guides, cookbooks, blog posts, and tools for building with OpenAI: GPT-4.1 Nano (batch) on OpenRouter.
Frequently asked questions
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.
The GPT-4.1 Nano (batch) documentation on OpenRouter includes the Quasar Alpha and Optimus Alpha Reveal blog post. The quickstart covers API keys and your first request, and the API reference lists every parameter.
GPT-4.1 Nano (batch) costs $0.05/M input tokens and $0.20/M output tokens, with separate rates for Cache Read at $0.0125/M tokens and Web Search at $10.00/1K calls.
GPT-4.1 Nano (batch) has a 1,047,576 token context window. It supports up to 32,768 completion tokens.
Yes. GPT-4.1 Nano (batch) accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
GPT-4.1 Nano (batch) accepts images, text, and files such as PDFs as input and returns text.
GPT-4.1 Nano (batch) is served by 1 provider on OpenRouter: OpenAI.
GPT-6.1 Terra Pro, GPT-6.1 Terra, GPT-6 Luna Decisions and 58 more are other text models from OpenAI.
GPT-4.1 Nano (batch) was released on April 14, 2025. Its knowledge cutoff is June 30, 2024.