MDL
GPT-4.1 nano
OpenAI
Verified against Artificial Analysis · Jul 13, 2026
Capability
43
percentile index
Price /M
$0.1 / $0.4
in / out
Context
1M
tokens
Avg score
32.6
11 benchmarks
AA Intelligence
9.6
index
Speed
149 tok/s
TTFT 0.5s
Released
Apr 14, 2025
About
GPT-4.1 nano is a proprietary model in the GPT family from OpenAI. Benchmarked on 11 evals, averaging 32.6.
Benchmark scores · 11
avg 32.6 — higher is betterThe research behind this model
all papers mentioning it →Casual as an Anchor: Resolving Supervision Misalignment in Formality Transfer DatasetMay 28, 2026Fine-tuning with Hierarchical Prompting for Robust Propaganda Classification Across Annotation SchemasMay 13, 2026Few-Shot Truly Benign DPO Attack for Jailbreaking LLMsMay 9, 2026EQUITRIAGE: A Fairness Audit of Gender Bias in LLM-Based Emergency Department TriageMay 5, 2026
Mentions matched by name in title/abstract — from the arXiv + HF daily corpus.
Performance & price
Output speed149 tok/s
Latency (TTFT)0.5s
Price in / out$0.1 / $0.4 per 1M
Blended price$0.175 / 1M
Coding index11.1
Math index24.0
Median across API providers, via Artificial Analysis. Blended = 3:1 input:output. For reasoning models, latency includes thinking time. Methodology →
History
full ledger →Capability over time
Append-only ledger — every observed change to this model's numbers.
API providers
Artificial Analysis$0.4/M