GPT-4.1 nano
GPT-4.1 nano is a multimodal AI model by OpenAI. It features a 1.0M token context window, 105 tok/s output speed, $0.10/1M input tokens pricing. It scores 13.0 on the intelligence index.
Strengths
- +Fast output speed (105 tok/s)
- +1M+ token context window (1.0M)
- +Very affordable pricing ($0.10/1M tokens)
- +Supports image input (vision)
Benchmarks
Intelligence13.0Coding11.2Math24.0
MMLU-Pro
0.7
GPQA
0.5
LiveCodeBench
0.3
Intelligence
13.0
Coding
11.2
Math
24.0
Output Speed
105 tok/s
Latency (TTFT)
0.41s
Blended Price
$0.17/M
Pricing per 1M Tokens
| Input (Prompt) | $0.10 |
| Output (Completion) | $0.40 |
| Cache Read | Free |
| Cache Write | Free |
Specifications
| Context Length | 1.0M |
| Max Output Tokens | N/A |
| Input Modalities | Image + Text + File |
| Output Modalities | Text |
| Tokenizer | N/A |
Compare GPT-4.1 nano with:
Alternatives to GPT-4.1 nano
More from OpenAI
Frequently Asked Questions
How much does GPT-4.1 nano cost?
GPT-4.1 nano costs $0.10/1M input tokens and $0.40/1M output tokens.
What is GPT-4.1 nano's context window?
GPT-4.1 nano supports a context window of 1.0M tokens, which is approximately 524 pages of text.
Is GPT-4.1 nano good for coding?
GPT-4.1 nano has a lower coding score of 11.2. For demanding coding tasks, consider a model with a higher coding benchmark.
How fast is GPT-4.1 nano?
GPT-4.1 nano generates output at 105 tok/s. Time to first token is 0.41s.
Is there a free version of GPT-4.1 nano?
Last updated: