Identity
- Status
- active
- Developer ID
gpt-5-nano- Released
- Aug 7, 2025
- Version
- GPT-5 Nano
- License
- Unknown
GPT-5 Nano is the fastest and most cost-efficient model in the original GPT-5 family.
| Provider | Input / 1M | Output / 1M | Cache read / 1M | Cache write / 1M | Observed | Evidence |
|---|---|---|---|---|---|---|
OpenaiAvailable | $0.050 | $0.40 | $0.005 | — | Sep 3, 2026 | Provider-reported |
OpenrouterAvailable | $0.025 | $0.20 | $0.0025 | — | Sep 3, 2026 | Provider-reported |
OpenrouterAvailable | $0.050 | $0.40 | $0.005 | — | Sep 4, 2026 | Provider-reported |
| ARC-AGI-1verified-v1-15fb467fd4fc | 20.71 | — | — | GPT-5 Nano (Medium)unknown | Original sourcewinner eligible | Third-party benchmark |
| ARC-AGI-2verified-v2-9a3db289984e | 2.61 | — | — | GPT-5 Nano (High)unknown | Original sourcewinner eligible | Third-party benchmark |
| Berkeley Function Calling Leaderboardv4-ede5081a24bc | 51.45 | — | — | GPT-5-nano-2025-08-07 (FC)unknown | Recomputedwinner eligible | Third-party benchmark |
| Berkeley Function Calling Leaderboardv4-ede5081a24bc | 27.55 | — | — | GPT-5-nano-2025-08-07 (Prompt)unknown | Recomputedwinner eligible | Third-party benchmark |
| LMArena Text Arenatext-2026-09-01-011508720696 | 1,319.84 | — | 8,128 | gpt-5-nano-high; 95% CI [1312.99438214, 1326.68844296]; votes 8128; rank 214unknown | Original sourcewinner eligible | Third-party benchmark |
| LMArena Vision Arenavision-2026-08-27-011508720696 | 1,159.24 | — | 3,950 | gpt-5-nano-high; 95% CI [1148.19623356, 1170.28699037]; votes 3950; rank 96unknown | Original sourcewinner eligible | Third-party benchmark |
| ToneBench2026-08-28-10-task-cd9819ab6e4d | 61.62 | 7,465 | 50 | GPT-5 nanoaverage per case | Original sourcewinner eligible | Third-party benchmark |
At a Glance
gpt-5-nanoThis 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.
Primary Evidence
Comparable Peers
| A | Pair | B | Context |
|---|---|---|---|
GPT-5 NanoOpenAI | vs | GPT-6 AstraOpenAI | family variantsimage, text |
GPT-5 NanoOpenAI | vs | Claude Fable 5.1Anthropic | cross-developer peersimage, text |
GPT-5 NanoOpenAI | vs | Gemini 3.1 ProGoogle DeepMind | cross-developer peerstext |
GPT-5 NanoOpenAI | vs | DeepSeek V4 ProDeepSeek | cross-developer peerstext |
GPT-5 NanoOpenAI | vs | Grok 4.6xAI | cross-developer peersimage, text |
GPT-5 NanoOpenAI | vs | Qwen3.8 MaxQwen | cross-developer peersimage, text |
GPT-5 NanoOpenAI | vs | Kimi K3Moonshot AI | cross-developer peersimage, text |
GPT-5 NanoOpenAI | vs | MiniMax M3MiniMax | cross-developer peersimage, text |
GPT-5 NanoOpenAI | vs | GLM 5.3Z.ai | cross-developer peerstext |
GPT-5 NanoOpenAI | vs | Hy4 previewTencent | cross-developer peerstext |
GPT-5 NanoOpenAI | vs | Seed 2.1 ProByteDance Seed | cross-developer peersimage, text |
GPT-5 NanoOpenAI | vs | Mistral Large 3Mistral AI | cross-developer peersimage, text |
GPT-5 NanoOpenAI | vs | cross-developer peersimage, text | |
GPT-5 NanoOpenAI | vs | Nova 2 LiteAmazon | cross-developer peersimage, text |
GPT-5 NanoOpenAI | vs | cross-developer peersimage, text | |
GPT-5 NanoOpenAI | vs | ERNIE 5.1Baidu | cross-developer peerstext |
GPT-5 NanoOpenAI | vs | cross-developer peerstext | |
GPT-5 NanoOpenAI | vs | cross-developer peerstext | |
GPT-5 NanoOpenAI | vs | Phi-4 ReasoningMicrosoft | cross-developer peerstext |
GPT-5 NanoOpenAI | vs | cross-developer peerstext | |
GPT-5 NanoOpenAI | vs | Sonar ProPerplexity | cross-developer peerstext |
GPT-5 NanoOpenAI | vs | GPT-5.6 SolOpenAI | family variantsimage, text |
Questions
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.
GPT-5 Nano's current record lists Text and Image as input and Text as output.
The current record lists a 400K-token context window and a maximum output of 128K tokens.
GPT-5 Nano is marked as API-available. The directly sourced provider records currently include Openai and Openrouter.
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.
GPT-5 Nano's recorded capabilities are chat, generation, reasoning, structured outputs, and tools. Its supported tasks are image, reasoning, and text.
GPT-5 Nano is not marked as an open-weight model. Self-hosting is marked as unsupported, with no license recorded.
No predecessor is recorded. No successor is recorded. Recorded aliases are gpt-5-nano and gpt-5-nano-2025-08-07.
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 →
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.