GPT-4.1 Nano API Pricing
OpenAI · Budget · Proprietary · released 2025-04. Prices in USD per 1 million tokens. Data snapshot: 2026-09-11.
- Input: $0.10 per 1M tokens
- Output: $0.40 per 1M tokens
- Batch API (input/output): $0.05 / $0.20
- Prompt-cache read: $0.03
- Context window: 1M
Cost per request by business use case
List price vs optimized (prompt caching on the cached input share, batch API for async workloads, only where the provider publishes those rates).
| Use case | Tokens (in/out) | Cost/req (list) | Cost/req (optimized) | Monthly @100K req |
|---|---|---|---|---|
| Support Ticket | 1,500 / 500 | $0.000350 | $0.000283 | $28 |
| Knowledge Q&A | 2,000 / 800 | $0.000520 | $0.000415 | $42 |
| Meeting Summary | 10,000 / 1,200 | $0.0015 | $0.000715 | $72 |
| Marketing Content | 2,500 / 1,800 | $0.000970 | $0.000933 | $93 |
| Coding Task | 3,000 / 2,000 | $0.0011 | $0.000988 | $99 |
| Invoice Processing | 1,500 / 600 | $0.000390 | $0.000184 | $18 |
| Call Summary | 2,000 / 700 | $0.000480 | $0.000235 | $24 |
| Agent Workflow | 6,000 / 3,000 | $0.0018 | $0.0015 | $149 |
GPT-4.1 Nano pricing by host
A host is a company that runs the model and sells it by the token — the lab that made it, a cloud platform like Amazon Bedrock, Azure or Vertex, or an independent provider. One model, several sellers, and often several prices. This model is sold by 2 different hosts. The price quoted above is the one we publish so that models stay comparable; it is not necessarily the cheapest way to buy this model. List prices as published on 2026-09-11 via OpenRouter — negotiated rates, committed-use discounts and provisioned capacity are not shown.
| Host | Input $/1M | Output $/1M |
|---|---|---|
| Azure (the price shown above) | $0.10 | $0.40 |
| OpenAI (the price shown above) | $0.10 | $0.40 |
Common questions about GPT-4.1 Nano pricing
- How much does GPT-4.1 Nano cost?
- GPT-4.1 Nano costs $0.10 per million input tokens and $0.40 per million output tokens on the API.
- Does GPT-4.1 Nano offer batch or cached pricing?
- Yes. Batch API pricing is $0.05/M input and $0.20/M output. Prompt-cache reads cost $0.03/M.
- What would GPT-4.1 Nano cost per month?
- For a support-ticket workload (1,500 input + 500 output tokens per request) at 100K requests/month, GPT-4.1 Nano costs about $35 at list prices.
These are list prices: real cost also depends on caching, batching, negotiated discounts, marketplace agreements, and existing contracts. Get a FinOps review from OptimNow or compare all models.
Build the business case for GPT-4.1 Nano in the AI ROI Calculator: add your business value on top of these costs to get ROI, break-even and payback.
All models · Compare side by side · Cloud compute pricing · Price barometer · FinOps guides · API and MCP server