GPT-4.1 Nano is
OpenAI's language model with a 1.0M context window and up to 33K output tokens, available from 5 providers, starting at $0.100 / 1M input and $0.400 / 1M output. The smallest and fastest variant of GPT-4.1, featuring a 1M-token context window and designed for high-throughput, cost-sensitive instruction-following tasks.
13.0#217 |
11.2#176 |
24.0#138 |
0.7#174 |
0.5#196 |
0.0#276 |
0.3#140 |
0.2#66 |
0.3#198 |
0.41s#162 |
0.3#183 |
0.8#64 |
0.2#138 |
0.2#166 |
0.0#171 |
0.2#204 |
155.1#42 |
Capabilities
Input3/5
✓
✓
·
·
✓
Output1/5
✓
·
·
·
·
Capabilities5/13
·
·
✓
✓
✓
✓
·
·
·
·
·
✓
·
Pricing by Provider
| Provider | Standard | Batch | ||||
|---|---|---|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Cache Read $ / 1M | Input $ / 1M | Output $ / 1M | Cache Read $ / 1M | |
Azure AI Foundry | $0.100 | $0.400 | $0.025 | $0.050 | $0.200 | N/A |
OpenAI | $0.100 | $0.400 | $0.025 | $0.050 | $0.200 | $0.013 |
OpenRouter | $0.100 | $0.400 | $0.025 | — | — | — |
Replicate | $0.100 | $0.400 | N/A | — | — | — |
Vercel AI Gateway | $0.100 | $0.400 | $0.025 | — | — | — |
Regional pricing
Provider-specific pricing that varies by region.
Azure AI Foundry
15 regions
| Region | Standard | Batch | |||
|---|---|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Cache Read $ / 1M | Input $ / 1M | Output $ / 1M | |
| Global | |||||
| Global | $0.100 | $0.400 | $0.025 | $0.050 | $0.200 |
| Europe | |||||
| France Central (Paris)/ francecentral | $0.110 | $0.440 | $0.028 | $0.055 | $0.220 |
| Germany West Central (Frankfurt)/ germanywestcentral | $0.110 | $0.440 | $0.028 | $0.055 | $0.220 |
| Italy North (Milan)/ italynorth | $0.110 | $0.440 | $0.028 | $0.055 | $0.220 |
| Poland Central (Warsaw)/ polandcentral | $0.110 | $0.440 | $0.028 | $0.055 | $0.220 |
| Spain Central (Madrid)/ spaincentral | $0.110 | $0.440 | $0.028 | $0.055 | $0.220 |
| Sweden Central (Gävle)/ swedencentral | $0.121 | $0.440 | $0.028 | $0.055 | $0.220 |
| West Europe (Netherlands)/ westeurope | $0.110 | $0.440 | $0.028 | $0.055 | $0.220 |
| US | |||||
| Central US (Iowa)/ centralus | $0.110 | $0.440 | $0.028 | $0.055 | $0.220 |
| East US (Virginia)/ eastus | $0.110 | $0.440 | $0.028 | $0.055 | $0.220 |
| East US 2 (Virginia)/ eastus2 | $0.110 | $0.440 | $0.028 | $0.055 | $0.220 |
| North Central US (Illinois)/ northcentralus | $0.110 | $0.440 | $0.028 | $0.055 | $0.220 |
| South Central US (Texas)/ southcentralus | $0.110 | $0.440 | $0.028 | $0.055 | $0.220 |
| West US (California)/ westus | $0.110 | $0.440 | $0.028 | $0.055 | $0.220 |
| West US 3 (Phoenix)/ westus3 | $0.110 | $0.440 | $0.028 | $0.055 | $0.220 |
Cost Calculator
Preset:
Compares every provider & tier in USD
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| GPT-5.4 Nano | 1.1M | $0.200 | $1.25 | Available | |
| GPT-5 Nano | 400K | $0.050 | $0.400 | Available | |
| GPT-4.1 Nano | 1.0M | $0.100 | $0.400 | Current |
Other models
| Model | Tier | Released | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|---|
| GPT-5.4 Mini | Mini | 1.1M | $0.750 | $4.50 | |
| GPT-5.4 | — | 1.1M | $2.50 | $15.00 | |
| GPT-5.4 Pro | Pro | 1.1M | $30.00 | $180.00 | |
| GPT-5.4 3.5 | — | — | 1.1M | — | — |
| GPT-5.4 Pro 3.5 | Pro | — | 1.1M | — | — |
| GPT-5.3 Chat | — | 128K | $1.75 | $14.00 | |
| GPT-5.3 Codex | — | 400K | $1.75 | $14.00 | |
| GPT-5.3 Codex Spark | — | — | 128K | — | — |
| GPT-5.3 Instant | — | — | 128K | — | — |
| GPT-5.2 Codex | — | 400K | $1.75 | $14.00 |