GPT-4.1 mini: Benchmarks, Pricing & Context Window
GPT-4.1 mini is a language model from OpenAI, released in April 2025, with multimodal input, a 1.0M-token context window, and pricing from $0.400/M input and $1.60/M output.
GPT-4.1 mini provides a balance between intelligence, speed, and cost. It's a significant leap in small model performance, even beating GPT-4o in many benchmarks while reducing latency and cost.
GPT-4.1 mini benchmarks
Capability tiers
Standing within each category, adjusted for leaderboard depth.
Real tasks performance
High-confidence performance for GPT-4.1 mini across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.
Performance by conversation depth
How GPT-4.1 mini holds up as conversations get longer.
Quality Tracker
GPT-4.1 mini Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Fri Oct 02 2026GPT-4.1 mini pricing
Providers
GPT-4.1 mini starts at $0.400 per million input tokens and $1.60 per million output tokens via OpenAI.
| Provider | Input $/M | Cached input $/M | Output $/M | Context in / out | TTFT p95 s | Output p5 c/s | Modalities in / out |
|---|---|---|---|---|---|---|---|
 OpenAI | $0.400 | — | $1.60 | 1.0M/32.8K | 5.00 | — | / |
Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.
GPT-4.1 mini context window
Input and output token limits for GPT-4.1 mini, plus how it ranks on long-context understanding.
Try now
huggleMake it with
GPT-4.1 mini.
GPT-4.1 mini latency
GPT-4.1 mini time to first token, sustained output throughput, and failed-request rate from live model usage over the trailing 7 days.
GPT-4.1 mini examples
Recent arena outputs from GPT-4.1 mini, picked from the highest-ranked matchups.
GPT-4.1 mini license
GPT-4.1 mini is a proprietary model available under its provider's product and API terms, has a knowledge cutoff of May 2024.
- License
- Proprietary
- Hosted access
- Knowledge cutoff
- May 2024
Proprietary license - usage restrictions apply
GPT-4.1 mini resources
Official sources for GPT-4.1 mini: provider documentation, official playground, official launch post.
GPT-4.1 mini vs other models
The most-compared alternatives to GPT-4.1 mini are DeepSeek R1 Distill Llama 70B, QwQ-32B, Kimi K2 Instruct. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like GPT-4.1 mini
Models ranked just above and below GPT-4.1 mini by LLM Stats score.
FAQ
Common questions about GPT-4.1 mini.