A rate per million tokens is not a budget. The calculator takes your request volume, prompt size and cache hit rate and gives you a monthly figure.
GPT-4.1 nano API pricing (October 2026)
OpenAI retired GPT-4.1 nano on 23 Oct 2026; the named replacement is GPT-5.6 Luna. Shown at its final price.
What it costs at real volumes
A chat-shaped workload: 800 input tokens and 300 output tokens per request, no caching, no batch.
Specifications
- Provider
- OpenAI
- Context window
- 1.0M tokens
- Max output
- 33K tokens
- Tier
- Small
- Status
- Retired on 23 Oct 2026, replacement GPT-5.6 Luna
- Blended $/1M (3:1)
- $0.175
- Cache break-even, caching each turn
- 0%, caching always saves
- Prices verified
- 12 Oct 2026
Source: OpenAI pricing. Finitizer is not affiliated with OpenAI.
Similar models
Other GPT models
- GPT-6 Astra+$19.83
- GPT-6.1 Sol+$3.83
- GPT-6.1 Terra+$1.83
- GPT-6 Luna+$0.025
- GPT-5.6 Sol+$7.83
- GPT-5.6 Terra+$4.33
- GPT-5.6 Luna+$0.275
- GPT-5+$3.26
- GPT-5 mini+$0.512
- GPT-5 nano-$0.038
- GPT-4.1+$3.33
- GPT-4.1 mini+$0.525
- GPT-4o+$4.20
- GPT-4o mini+$0.087
- o3+$3.33
- o4-mini+$1.75
Closest prices elsewhere
- Claude Haiku 5.5+$0.025
- GPT-OSS 20B (Groq)-$0.044
- Amazon Nova Lite-$0.070
- DeepSeek Flash (V4.1)+$0.087
Frequently asked questions
How much did GPT-4.1 nano cost per 1M tokens?
GPT-4.1 nano cost $0.100 per million input tokens and $0.400 per million output tokens at OpenAI final list prices. Output was 4.0x the input rate, so the input:output ratio of a workload drives the real cost more than the headline price.
Does GPT-4.1 nano support prompt caching?
Yes. Cached input is billed at $0.025 per million tokens, 4x cheaper than uncached input. There is no cache-write premium, so caching is never a net loss.
What is the batch discount for GPT-4.1 nano?
Requests submitted through the asynchronous batch endpoint are billed at 50% off both input and output rates, bringing input to $0.050 and output to $0.200 per million tokens.
What is GPT-4.1 nano's context window?
1.0M tokens of context with up to 33K output tokens per request. A larger context window raises the ceiling on what you can send, not the price per token, but filling it on every request is one of the most common causes of an unexpected bill.
Running GPT-4.1 nano in production?
Finitizer Tokenomics reads what this model actually costs you from your own bills and exports, shows which workload, team or API key is spending it, flags a spike or a new spend source the day your data shows it, and forecasts where the month will land.
See Finitizer Tokenomics