GPT 5 Nano
openai/gpt-5-nano- OpenAI
- Family · GPT 5 Nano
- Released 7 Aug 2025
- Text · Image · File → Text
- Reasoning · adjustable
- Tools · JSON · Vision
Spec & list price
Context391K
Max output128K
Input / 1M$0.05
Output / 1M$0.408× input
Scores · standing
Intelligence13.0#198/489
Usage
Tokens / day2.8B▼ 10% 7d
Usage rank#144
Requests / day786.6K
Tool calls / req0.01
Per request · 30 days
Avg input9550.1× median
Avg output1030.1× median
Cache hit15%0.2× median
Reasoning share95%1.7× median
Tool-call failures0.6%0.3× median
Consumption
Peak 40.6B 26 SepLow 1.9B 1 NovRank today #144
News & trends
1 mentions this weekGPT 5 Nano family · videos, posts, articles · 30 days
Trending · 14 days
- OpenAI Switches Off GPT-4o, GPT-4.1 and GPT-5-nano: What Breaks, What It Costs, How to Migrate1 views
News · latest from OpenAI
- GPT-6.1 Terra vs. Claude Opus 5.5: Cheaper and faster in three tests at maxthenewstack.io · 2 Nov
- Chinese labs now target OpenAI's GPT-6 Astra for distillationfork.zone · 1 Nov
- GPT-6.1 Terrasimonwillison.net · 31 Oct
- GPT-5.6 Sol can beat Factorio on peaceful moderyanmadden.net · 31 Oct
Benchmarks
bar = share of the top score · Benchmark data: Artificial AnalysisSpeed · median across 4 providers, latest day
Output speed#63/334105 tok/s1.6× faster than median
Fastest provider181 tok/sbest of 4 providers
First token#2321.59 s1.5× longer than median
#5 cheapest of 27 with a similar score
Value
Intelligence Index
Blended price per 1M tokens (log)
Family progress
Intelligence Index
- Family releases20.7
Technical details
- Reasoning
- on · medium
- Tokenizer
- GPT
- Knowledge cutoff
- 2024-05-31
- Moderation
- moderated
Reasoning effort
- high
- medium · default
- low
- minimal
Request parameters 11
- tools
- tool_choice
- response_format
- structured_outputs
- reasoning
- reasoning_effort
- include_reasoning
- max_tokens
- max_completion_tokens
- seed
+1 more
- verbosity
When to use
Best for
- Low-cost bulk classification
- Cheap coding and math helpers
- Reasoning at minimal effort for speed
- Image and file extraction at scale
- Offline bulk jobs via the batch variant
Think twice for
- Hardest reasoning and agent tasks
- New projects (usage is declining)
- Self-hosting (closed weights)
Research papers
- Stronger Judges Do Not See More: Deployment-Integrity Blindness in LLM Evaluation15 Oct
- REPRO: Reflective Evolutionary Prompt Optimizer for Automated LLM Red-Teaming11 Oct
- Illusory Truth or Mere Exposure? Model-Dependent Repetition Effects in LLM-Based Social Media Simulations28 Sep
- Large Language Models for Programming: Actually Fixing or Reimplementing Incorrect Code?24 Sep
- TIAO: Token Importance-Aware Policy Optimization for Text Summarization15 Sep
- Dual-Grained Agent Memory and Shapley Context Attribution for Multimodal Agentic Learner24 Aug
- DIVE: Unlocking Self-Improvement in Frozen Language Models Through Diversity-Driven Skill Evolution12 Aug
- Artificial Intelligence Can Match Domain Experts in Evidence Extraction and Critical Appraisal of Microbial Oncogenesis Research Publications7 Aug
Social
Most watched and discussed · 90 days
- OpenAI Switches Off GPT-4o, GPT-4.1 and GPT-5-nano: What Breaks, What It Costs, How to MigrateAI Unfiltered with Thorsten Meyer · 1 views · 1 Nov
Same family
GPT 5 Nano- 20.7
Alternatives
other vendors · similar capability- 12.9
- 8.5
- 12.3
- 9.2
Using GPT 5 Nano at volume?
Sign in to ask for a volume discount. You will continue in the OSMEXO dashboard.