GPT-4.1 Nano
Apr 2025
Retired 2026-10-23Replace withGPT-5.6 LunaNewer version
Agnes 2.5 Pro BetaCheaper, as goodGPT-6 LunaBetter
MiMo v2.6 ProOpen weights
GPT-5.6 LunaNewer versionAgnes 2.5 Pro BetaCheaper, as goodGPT-6 LunaBetterMiMo v2.6 ProOpen weightsGPT-4.1 NanoCompare inon
Benchmarks of GPT-4.1 Nano29
BenchmarkByScoreRank
Overall1
Knowledge5
Reasoning4
Science2
Coding1
Agents2
Multimodal2
Writing4
Health & law1
Documents1
Legacy · saturated or no longer reported6
No benchmark matches
Rankingin non-thinking mode?
Retired models are left out of the current rankings.
Alternatives?
ModelScoreCostPer taskWhat changes
CheaperAgnes 2.5 Pro Beta×4.5-14%$0.10 / $0.30BetterGPT-6 Lunalow×2.8+14%$0.005Function calling only with none · Chat Completions+3OpenMiMo v2.6 Prothinking×5.9+211%$0.13Pass back reasoning_content+3
CheaperLing 3.0 Flash VLthinkingOpen×3.1-49%$0.06 / $0.18Context: 1M → 262K
CheaperSolar Mini 4×3.1-50%$0.37Context: 1M → 524K+1ModelScoreCostPer taskWhat changes
Agnes 2.5 Pro Beta×4.5-14%$0.10 / $0.30Ling 3.0 Flash VLthinkingOpen×3.1-49%$0.06 / $0.18Context: 1M → 262KSolar Mini 4×3.1-50%$0.37Context: 1M → 524K+1Ling 3.0 Flash FinthinkingOpen×2.9-49%$0.06 / $0.18Context: 1M → 262K+1Ling 3.0 FlashthinkingOpen×2.6-49%$0.06 / $0.18Context: 1M → 262K+1ModelScoreCostPer taskWhat changes
GPT-6 Lunalow×2.8+14%$0.005Function calling only with none · Chat Completions+3GPT-5.6 Lunalow×2.7+157%$0.01
Mistral Small 4thinkingOpen+44%+50%$0.015Context: 1M → 262KMiMo v2.5thinkingOpen×2.8same$0.019
Granite 4.2 8BthinkingOpen+42%-39%$0.024Context: 1M → 128K+1ModelScoreCostPer taskWhat changes
MiMo v2.6 ProthinkingOpen×5.9+211%$0.13Pass back reasoning_content+3
DeepSeek V4.1 Flash 1017maxOpen×5.8+200%$0.26Pass back reasoning_content · Chat Completions+4
GLM 5.3maxOpen×5.7+1,129%$2.01No image input+4
Step 5 PreviewthinkingOpen×5.6+714%$1.03web_search not available · Chat Completions+2
Kimi K3maxOpen×5.6+3,329%$2.00Sampling parameters are fixed+3ModelScoreCostPer taskWhat changes
GPT-6 Astramedium×6.3—$1.54Monitoring can return HTTP 403+2GPT-6.1 Solmedium×6.1—$0.21Remove unsupported parameters+5GPT-6 Solmedium×5.1—$0.25GPT-5.6 Solmedium×5—$0.50GPT-5.5medium×4.3—$0.90Prompts with >272K input tokensGPT-5.3 Codexxhigh×4.2—$1.75 / $14Context: 1M → 400K+1GPT-5.6 Terramedium×3.8—$0.18Prompts with >272K input tokensGPT-6 Lunamedium×3.8—$0.017Function calling only with none · Chat Completions+3All OpenAI models →History
5 versionsBenchmarks
all categoriesChat & Knowledge
AA Omniscience Index-57.6
GPQA Diamond51.2
Coding
Agents & Tool Use
τ²-bench · AA17.3
Writing & Language
Vision & Documents
FAQ
How much does GPT-4.1 Nano cost?›
$0.10 per 1M input tokens and $0.40 per 1M output tokens; cached input $0.025 per 1M.
Is GPT-4.1 Nano free to use?›
There is no free API; the cheapest paid price is $0.10 per 1M input tokens.
How can I use GPT-4.1 Nano?›
Through the API of Azure, OpenAI.
What is the context window of GPT-4.1 Nano?›
1M tokens, with up to 33K output tokens.
When was GPT-4.1 Nano released? Is there a newer version?›
Released 2025-04-14. It has been superseded by GPT-5.6 Luna.
Is GPT-4.1 Nano open source?›
No, GPT-4.1 Nano is a closed model available through an API. The closest open-weights option here is MiMo v2.6 Pro.
Can GPT-4.1 Nano read images?›
It accepts text and images, PDF files as input.
What is GPT-4.1 Nano?›
GPT-4.1 Nano is a closed language model from OpenAI, released Apr 2025.
What are the best alternatives to GPT-4.1 Nano?›
Agnes 2.5 Pro Beta (cheaper), GPT-6 Luna (better), MiMo v2.6 Pro (open weights).