GPT-4.1 Mini by OpenAI demonstrates fast output speed, competitive pricing. View detailed benchmark data including scores across coding, math, reasoning, speed, and cost metrics.
Specifications last checked against the provider on . Benchmark scores carry their own source, linked beside each number.
General Benchmarks
Human preference ELO from blind head-to-head votes
LMSYS / HuggingFaceMassive Multitask Language Understanding professional benchmark
HuggingFace LeaderboardCoding Benchmarks
Human preference ELO for building a working web page from a brief
Design Arena (via OpenRouter)Artificial Analysis composite coding score
Artificial Analysis (via OpenRouter)Human preference ELO for building things — websites, UI, games, charts, SVG
Design Arena (via OpenRouter)Math Benchmarks
Reasoning Benchmarks
Multi-turn service agent making tool calls under strict policy constraints
OpenRouter (measured)Speed Benchmarks
Cost Benchmarks
Cost per 1M cached input tokens — the price that actually applies to a long agent conversation
OpenRouter APIContext Benchmarks
Available from 26 providers
The same model costs different amounts depending on who serves it. You can bring your own key for 4 of these — connect it here.
| Provider | Input / 1M | Output / 1M | Cached in | Context | Your key |
|---|---|---|---|---|---|
| Poe | $0.36 | $1.4 | $0.09 | 1.0M | — |
| 302.AI | $0.4 | $1.6 | — | 1.0M | — |
| Abacus | $0.4 | $1.6 | $0.1 | 1.0M | — |
| Aixy | $0.4 | $1.6 | $0.1 | 1.0M | — |
| Azure | $0.4 | $1.6 | $0.1 | 1.0M | Supported |
| Azure Cognitive Services | $0.4 | $1.6 | $0.1 | 1.0M | — |
| Cloudflare AI Gateway | $0.4 | $1.6 | $0.1 | 1.0M | — |
| DevPass (LLM Gateway) | $0.4 | $1.6 | $0.1 | 1.0M | — |
| Eden AI | $0.4 | $1.6 | $0.1 | 1.0M | — |
| Impossibl | $0.4 | $1.6 | $0.1 | 1.0M | — |
| Kilo Gateway | $0.4 | $1.6 | $0.1 | 1.0M | — |
| LLM Gateway | $0.4 | $1.6 | $0.1 | 1.0M | — |
| Merge Gateway | $0.4 | $1.6 | $0.1 | 1.0M | — |
| NanoGPT | $0.4 | $1.6 | $0.1 | 1.0M | — |
| NEAR AI Cloud | $0.4 | $1.6 | $0.1 | 1.0M | — |
| Ofox | $0.4 | $1.6 | $0.1 | 1.0M | — |
| OpenAI | $0.4 | $1.6 | $0.1 | 1.0M | Supported |
| OpenRouter | $0.4 | $1.6 | $0.1 | 1.0M | Supported |
| OrcaRouter | $0.4 | $1.6 | $0.1 | 1.0M | — |
| Pioneer | $0.4 | $1.6 | $0.2 | 1.0M | — |
| SAP AI Core | $0.4 | $1.6 | $0.1 | 1.0M | — |
| Vercel AI Gateway | $0.4 | $1.6 | $0.1 | 1.0M | Supported |
| Cortecs | $0.434 | $1.704 | $0.134 | 1.0M | — |
| Requesty | $0.44 | $1.76 | $0.11 | 1.0M | — |
| AnyAPI | — | — | — | 1.0M | — |
| Model Oracle AI | — | — | — | 1.0M | — |
GPT-4.1 Mini — Benchmark Scores Overview
Scores normalized to percentage scale for visual comparison. ELO scores mapped to 0-100 range (1100-1500).
Compare GPT-4.1 Mini With
GPT-4.1 Mini — Frequently Asked Questions
How intelligent is GPT-4.1 Mini?
GPT-4.1 Mini scores 1250 on the Chatbot Arena ELO rating, making it a mid-tier AI model. This score is based on blind head-to-head human preference voting.
How much does GPT-4.1 Mini cost?
GPT-4.1 Mini costs $0.40 per 1M input tokens and $1.6 per 1M output tokens. This makes it one of the more affordable models.
How fast is GPT-4.1 Mini?
GPT-4.1 Mini generates output at 160 tokens per second, which is very fast compared to other models. The time to first token is 130 ms.
How good is GPT-4.1 Mini at coding?
GPT-4.1 Mini achieves 35.0% on SWE-bench Verified, demonstrating moderate real-world software engineering capability. This benchmark tests the model's ability to resolve actual GitHub issues.
How good is GPT-4.1 Mini at math and reasoning?
GPT-4.1 Mini scores 72.0% on the MATH benchmark (competition-level mathematics). It also achieves 64.1% on GPQA Diamond, a graduate-level science reasoning benchmark.
What is the context window of GPT-4.1 Mini?
GPT-4.1 Mini has a context window of 1.0M tokens. This determines how much text, conversation history, and code the model can process in a single request.
Who created GPT-4.1 Mini?
GPT-4.1 Mini was created by OpenAI. It is classified as a budget model in our catalogue.
Is GPT-4.1 Mini open source?
No, GPT-4.1 Mini is a proprietary model. It is available through OpenAI's API and compatible providers.