Back to models
GPT-4.1
Smartest non-reasoning model
| Context window | 32,768 tokens |
| Max output tokens | 32,768 tokens |
Pricing
| Type | Input | Output |
|---|---|---|
| Standard | $3.50 / 1M tokens | $14.00 / 1M tokens |
| Cached input | $0.88 / 1M tokens | |
Parameters
| Parameter | Default | Range |
|---|---|---|
| Max stop sequences | 0 | — |
Supported features
Capabilities
- Streaming
- Function Calling
- Structured Output
- Json Mode
- Reasoning
- System Prompt
Endpoints
- Chat Completions
- Batch
Use cases
- text-chat
- function-calling
- reasoning
Model specifications
| Model ID | gpt-4.1 |
| Family | GPT-4 |
| Access type | Closed |
| Input modalities | text |
| Output modalities | text |
| Last updated | January 3, 2026 |