OpenAIGPT-5 Nano

External Link

GPT-5 Nano is the fastest and most cost-efficient model in the original GPT-5 family.

Token context
400K tokens
Inputs
Text, Image
Outputs
Text
Released
Aug 7, 2025

Providers & Pricing

Estimate workload cost →
ProviderInput / 1MOutput / 1MCache read / 1MCache write / 1MObservedEvidence
$0.050$0.40$0.005Sep 3, 2026Provider-reported
$0.025$0.20$0.0025Sep 3, 2026Provider-reported
$0.050$0.40$0.005Sep 4, 2026Provider-reported
ARC-AGI-1verified-v1-2aa739d957fc20.71percentGPT-5 Nano (Medium)unknownOriginal sourcewinner eligibleThird-party benchmark
ARC-AGI-2verified-v2-b5cb5ec6e8c72.61percentGPT-5 Nano (High)unknownOriginal sourcewinner eligibleThird-party benchmark
Berkeley Function Calling Leaderboardv4-ede5081a24bc51.45percentGPT-5-nano-2025-08-07 (FC)unknownRecomputedwinner eligibleThird-party benchmark
Berkeley Function Calling Leaderboardv4-ede5081a24bc27.55percentGPT-5-nano-2025-08-07 (Prompt)unknownRecomputedwinner eligibleThird-party benchmark
LMArena Text Arenatext-2026-09-01-0115087206961,319.84rating8,128gpt-5-nano-high; 95% CI [1312.99438214, 1326.68844296]; votes 8128; rank 214unknownOriginal sourcewinner eligibleThird-party benchmark
LMArena Vision Arenavision-2026-08-27-0115087206961,159.24rating3,950gpt-5-nano-high; 95% CI [1148.19623356, 1170.28699037]; votes 3950; rank 96unknownOriginal sourcewinner eligibleThird-party benchmark
ToneBench2026-08-28-10-task-cd9819ab6e4d61.62points7,46550GPT-5 nanoaverage per caseOriginal sourcewinner eligibleThird-party benchmark

At a Glance

Model Facts

Identity

Status
active
Developer ID
gpt-5-nano
Released
Aug 7, 2025
Version
GPT-5 Nano
License
Unknown

Capacity

Token context
400K tokens
Maximum output
128K tokens
Total parameters
Unknown
Active parameters
Unknown
Knowledge cutoff
May 31, 2024

Interface and Access

Inputs
Text, Image
Outputs
Text
API available
Yes
Open weights
No
Self-hostable
No
Reasoning
Yes
Vision
Yes
Tool calling
Yes
Capabilities
chat, generation, reasoning, structured outputs, tools

This page represents one developer model product. Dated API snapshots, serving endpoints, pricing, regions, quantizations, and service tiers attach as versioned aliases or provider details and never create duplicate public model records.

Version Lineage

PredecessorUnknown
SuccessorsUnknown
Aliasesgpt-5-nano, gpt-5-nano-2025-08-07

Explicit Unknowns

  • Architecture
  • Tokenizer

Primary Evidence

Sources and Observation Date

Comparable Peers

Related Model Comparisons

All comparisons →
APairBContext
vsfamily variantsimage, text
vscross-developer peersimage, text
vscross-developer peerstext
vscross-developer peerstext
vscross-developer peersimage, text
vscross-developer peersimage, text
vscross-developer peersimage, text
vscross-developer peersimage, text
vscross-developer peerstext
vscross-developer peerstext
vscross-developer peersimage, text
vscross-developer peersimage, text
vscross-developer peersimage, text
vscross-developer peersimage, text
vscross-developer peersimage, text
vscross-developer peerstext
vscross-developer peerstext
vscross-developer peerstext
vscross-developer peerstext
vscross-developer peerstext
vscross-developer peerstext
vsfamily variantsimage, text

Questions

GPT-5 Nano FAQs

What is GPT-5 Nano?+

GPT-5 Nano is the fastest and most cost-efficient model in the original GPT-5 family. It is developed by OpenAI and its current sourced lifecycle status is active.

What inputs and outputs does GPT-5 Nano support?+

GPT-5 Nano's current record lists Text and Image as input and Text as output.

How much context does GPT-5 Nano support?+

The current record lists a 400K-token context window and a maximum output of 128K tokens.

Is GPT-5 Nano available through an API?+

GPT-5 Nano is marked as API-available. The directly sourced provider records currently include Openai and Openrouter.

How much does GPT-5 Nano cost through an API?+

The lowest directly sourced prices currently attached to GPT-5 Nano are $0.025 per million input tokens through Openrouter and $0.20 per million output tokens through Openrouter. Prices are provider-specific and should be checked against each cited observation date.

What capabilities and tasks does GPT-5 Nano support?+

GPT-5 Nano's recorded capabilities are chat, generation, reasoning, structured outputs, and tools. Its supported tasks are image, reasoning, and text.

Can GPT-5 Nano be self-hosted?+

GPT-5 Nano is not marked as an open-weight model. Self-hosting is marked as unsupported, with no license recorded.

Does GPT-5 Nano have related versions or aliases?+

No predecessor is recorded. No successor is recorded. Recorded aliases are gpt-5-nano and gpt-5-nano-2025-08-07.

Which models can GPT-5 Nano be compared with?+

The current compatible peer set includes GPT-6 Astra, Claude Fable 5.1, Gemini 3.1 Pro, DeepSeek V4 Pro, and Grok 4.6. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons

How current is the Model Markets record for GPT-5 Nano?+

GPT-5 Nano was last verified Sep 3, 2026 from OpenAI's primary source, “GPT-5 Nano Model | OpenAI API.” The evidence is classified as official fact.

Send Feedback