Ways to buy 4
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
 OpenAIflex, cheapest · cached $0.0025 | $0.025 | $0.2 | $0.025 / $0.2-50% vs list | $0.0025 | -50% vs list |
| OpenAI API The lab's own API · cached $0.005 | $0.05 | $0.4 | $0.05 / $0.4List price | $0.005 | List price |
 Azure AI FoundryDefault region · cached $0.01 | $0.05 | $0.4 | $0.05 / $0.4Same as list | $0.01 | Same as list |
| Azure AI Foundry swedencentral · cached $0.011 | $0.055 | $0.44 | $0.055 / $0.44+10% vs list | $0.011 | +10% vs list |
USD per 1M tokens; batch $0.025 in, $0.2 out on the lab's API. Regions are separate routes.
Through a gateway
Your own numbers100M input and 20M output tokens a month: $13.00 direct.
Helicone$13.00+0%
Kong AI Gateway$13.00+0%
LiteLLM$13.00+0%
Vercel AI Gateway$13.00+0%
Cloudflare AI Gateway$13.65+5%
Requesty$13.65+5%
Eden AI$13.71+5.5%
OpenRouter$13.71+5.5%
No published token fee: Martian Gateway, Portkey, TrueFoundry AI Gateway.
Related models
| In / out per 1M | Cheapest route | ||||||
|---|---|---|---|---|---|---|---|
| GPT-6 Luna OpenAI · 1.05MCheapest: $0.1 on OpenAI (flex) | $0.1 | $0.5 | $0.1 / $0.5 | $0.2 | 1.05M | $0.1 on OpenAI (flex) | · |
| GPT-6 Luna Pro OpenAI · 1.05MCheapest: $0.1 on OpenAI (flex) | $0.1 | $0.5 | $0.1 / $0.5 | $0.2 | 1.05M | $0.1 on OpenAI (flex) | · |
| GPT-6 Sol OpenAI · 1.05MCheapest: $2 on OpenAI (flex) | $2 | $10 | $2 / $10 | $4 | 1.05M | $2 on OpenAI (flex) | · |
| GPT-6 Sol Pro OpenAI · 1.05MCheapest: $2 on OpenAI (flex) | $2 | $10 | $2 / $10 | $4 | 1.05M | $2 on OpenAI (flex) | · |
 DeepSeek V4.1 FlashDeepSeek · 1MCheapest: $0.1 on Relace | $0.15 | $0.6 | $0.15 / $0.6 | $0.262 | 1M | $0.1 on Relace | · |
 Qwen3.8 Omni FlashQwen (Alibaba) · 1M | $0.15 | $0.47 | $0.15 / $0.47 | $0.23 | 1M | Lab list price | · |
 Muse Spark 1.3 ContributorMeta · 1M | $0.1 | $0.2 | $0.1 / $0.2 | $0.125 | 1M | Lab list price | · |
 GLM 5.3 FlashZ.ai · 1.31M | $0.045 | $0.14 | $0.045 / $0.14 | $0.069 | 1.31M | on InferenceNet (fp4) | · |
About GPT-5 Nano
GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments.
Takes text, image, files in and returns text. First listed Aug 12, 2025. Up to 128K output tokens. Blended price $0.138 per 1M tokens at 3 input to 1 output. Model id gpt-5-nano.
Price history
List price since Aug 12, 2025, from Internet Archive snapshots of the OpenRouter catalog, then daily reads.
| Seen | Model | Old price | New price | Change |
|---|---|---|---|---|
| Jul 17, 2026 | GPT-5 NanoCached input $0.01 to $0.005 | Cached input $0.01 | Cached input $0.005 | -50% |
| Apr 23, 2026 | GPT-5 NanoCached input $0.005 to $0.01 | Cached input $0.005 | Cached input $0.01 | +100% |
Questions
How much does GPT-5 Nano cost?
$0.05 per million input tokens and $0.4 per million output tokens, with cached input at $0.005, or $0.025 and $0.2 through the Batch API.
What is the context window of GPT-5 Nano?
400K tokens, with up to 128K tokens of output.
Where is GPT-5 Nano cheapest?
Of 4 routes tracked, OpenAI is cheapest at $0.025 input and $0.2 output per million tokens.
List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.