GPT-4.1 mini
AI model by OpenAI. Real-time pricing and benchmark data.
Benchmarks
Editorial Analysis
Profile. GPT-4.1 mini is a budget-tier option from OpenAI at $1.60/M output tokens. Despite the low price, it scores competitively on Coding Index (20.2) and Intelligence Index (10.2) — making it a candidate for high-volume production workloads where unit cost dominates.
Latency. On latency, GPT-4.1 mini reports 124 tok/s output speed and 860ms time-to-first-token. Output speed is in the normal range — most chat and completion applications will be token-bound, not streaming-bound.
Cost model. For a workload of 1M input tokens + 100K output tokens, GPT-4.1 mini costs $0.56 per million input-equivalent requests. Multiply by your monthly request volume to project the bill, and compare against the speed/correctness profile above to decide if the trade-off is worth it for your workload.
Editorial summary generated from public pricing and benchmark data (Artificial Analysis API). All numbers are sourced — see the Artificial Analysis methodology for benchmark definitions. Last refreshed 2026-10-08.
Compare with similar models
| Model | Input | Output | Speed |
|---|---|---|---|
GPT-4.1 miniCurrent | $0.40 | $1.60 | 124 tok/s |
| Qwen3.7 Plus | $0.40 | $1.60 | 67 tok/s |
| Qwen3 VL 235B A22B Instruct | $0.40 | $1.60 | 49 tok/s |
| DeepSeek V3.1 (Non-reasoning) | $0.57 | $1.68 | — |
| DeepSeek V3.1 (Reasoning) | $0.59 | $1.69 | — |
| Mistral Large 3 | $0.50 | $1.50 | 75 tok/s |