Model specification · OpenAI
GPT-4.1 Nano
openai/gpt-4.1-nano
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...
SpecificationsReported values
- Context window
- 1.0M
- Maximum output
- 33K
- Architecture
- text+image+file->text
- Tokenizer
- GPT
- Knowledge cutoff
- 2024-06-30
- Moderated
- Yes
- Input modalities
- image text file
- Output modalities
- text
Full pricingUSD where reported
| Price | Standard |
|---|---|
| Input | $0.100 / M |
| Output | $0.400 / M |
Benchmark indexesReported indexes
- Intelligence
- 9.6
- Coding
- 11.1
- Agentic
- 1.2
- Design Arena Elo
- 977
Example workload costsStandard pricing only
| Workload | Input / output | Cache share | Estimated cost |
|---|---|---|---|
| Quick check | 10K / 1K × 1 | 0% | $0.00140 |
| Long analysis | 100K / 4K × 1 | 50% | $0.00785 |
| Workday | 20K / 2K × 1,000 | 30% | $2.35 |
More from OpenAIAll OpenAI models
| Model | Context | Input / M | Output / M | Intel. |
|---|---|---|---|---|
| GPT-5.6 Sol | 1.1M | $5.00 | $30.00 | 58.9 |
| GPT-5.6 Terra | 1.1M | $1.00 | $6.00 | 55 |
| GPT-5.5 | 1.1M | $5.00 | $30.00 | 54.8 |
| GPT-5.4 | 1.1M | $2.50 | $15.00 | 51.4 |
| GPT-5.6 Luna | 1.1M | $0.100 | $0.600 | 51.2 |
| GPT-5.4 Mini | 400K | $0.750 | $4.50 | 40 |
| GPT-5.4 Nano | 400K | $0.200 | $1.25 | 38.2 |
| GPT-5.1 | 400K | $1.25 | $10.00 | 36.9 |
| GPT-5 | 400K | $1.25 | $10.00 | 34.7 |
| GPT-5 Mini | 400K | $0.250 | $2.00 | 25.3 |
| gpt-oss-120b | 131K | $0.037 | $0.170 | 23.8 |
| o3 Mini High | 200K | $1.10 | $4.40 | 15.6 |