OpenAI · Efficient
GPT 5 Nano
Optimized for speed and ideal for applications requiring low latency. The fastest and most efficient GPT-5 variant.
- Reasoning
- Vision
- Input
- Text, Images
- Output
- Text
- Reasoning effort
- minimal · low · medium · high
- Discovery tier
- Efficient
Pricing
USD per 1M tokens- Input
- $0.05
- Output
- $0.40
- Cache read
- $0.005
Reference prices as published by the model provider. API example
Specifications
- Context window
- 400K
- Max output
- 128K
- Average output (7 days)
- 322 tokens
- Longer than 35% of 465 models
Side by side
Compare models
Put GPT 5 Nano next to up to three other models. The comparison stays in the link, so you can share it.
Public evaluations
Benchmarks
Independent evaluation results, with how each score ranks among the models in the Noumen catalog.
Intelligence Index
13.0
Tested at high reasoning effort
Better than 31% of 326 scored models
Indexes
Math Index
83.7Composite of the math evaluations
Better than 76% of 118 scored models
Document reasoning
AA-LCRv1.1
45.0%Reasoning across long documents
Better than 21% of 309 scored models
Reasoning and knowledge
Humanity’s Last Exam
9.5%Expert-level questions across academic fields
Better than 30% of 323 scored models
GPQA Diamond
67.6%Graduate-level science questions
Better than 25% of 291 scored models
MMLU-Pro
78.0%Multi-subject knowledge and reasoning
Better than 39% of 132 scored models
IFBench
67.6%Following precise output instructions
Better than 66% of 215 scored models
Coding
LiveCodeBench
78.9%Recent competitive programming problems
Better than 80% of 129 scored models
Math
AIME 2025
83.7%Competition mathematics, 2025 problems
Better than 76% of 118 scored models
Legacy evaluations
Terminal-Bench Hard
12.1%Earlier terminal task suite
Better than 25% of 212 scored models
τ²-Bench Telecom
36.5%Tool use in a customer-support simulation
Better than 30% of 214 scored models
AA-LCR (unversioned)
45.0%Long-context reasoning, earlier grading
Better than 21% of 309 scored models
Scores from Artificial Analysis, updated Oct 26, 2026. GPT 5 Nano was tested at high reasoning effort; compare scores measured at the same effort.Artificial Analysis
Live routing data
Performance and reliability
Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.
- Throughput
- 101.5 tok/s
- Faster than 62% of 250 models
- Time to first token
- 2.0 s
- Quicker than 76% of 250 models
- Prompt cache hits
- 23.7%
- About $0.0393 per 1M input tokens with caching
- Request success (24h)
- 100.0%
- Reliable
Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.
- Healthy (98% or more)
- Degraded (90–98%)
- Down (under 90%)
- No requests
Developers
Use it through the API
Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.
curl https://www.noumen.xyz/api/v1/chat/completions \
-H "Authorization: Bearer $NOUMEN_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/gpt-5-nano",
"reasoning_effort": "medium",
"messages": [{ "role": "user", "content": "Explain this stack trace." }]
}'import os
from openai import OpenAI
client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
model="openai/gpt-5-nano",
messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)OpenAI
Related models
Other OpenAI models, starting with the same family.