GPT-4.1 Models by OpenAI
OpenAIProprietary
4 models2023–2025Up to 1.05m ctxFrom $0.1/1M input
Details
ResearcherOpenAI
LicenseProprietary
Commercial useCommercial use with conditions
Models4
Released2023–2025
Max context1.05m
Capabilities
Vision3 of 4 models
Multimodal3 of 4 models
Function Calling3 of 4 models
Tool Use3 of 4 models
Structured OutputsAll models
Code Execution3 of 4 models
Links
WebsiteAbout
GPT-4.1 is OpenAI's April 2025 model family designed for coding, instruction-following, and web development. It outperforms GPT-4o in coding tasks and introduces GPT-4.1 mini as an efficient successor to GPT-4o mini, with a 1 million token context window.
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
3 in view1 retired
GPT-4.1Current
Use when the workload needs 1.05m context, tool use, and function calling.
2025-041.05m contexttool usefunction calling
GPT-4.1 MiniCurrent
Use when the workload needs 1.05m context, tool use, and function calling.
2025-041.05m contexttool usefunction calling
GPT-4 Turbo (older v1106)Current
Use when the workload needs 128k context and structured outputs.
2023-11128k contextstructured outputs
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| GPT-4.1 | Use when the workload needs 1.05m context, tool use, and function calling. | 2025-04 | 1.05m contexttool usefunction calling | Current |
| GPT-4.1 Mini | Use when the workload needs 1.05m context, tool use, and function calling. | 2025-04 | 1.05m contexttool usefunction calling | Current |
| GPT-4 Turbo (older v1106) | Use when the workload needs 128k context and structured outputs. | 2023-11 | 128k contextstructured outputs | Current |
Release Timeline
2 release groups2025-04
2 current · 1 retired
GPT-4.1
Current1.05m contexttool usefunction calling
GPT-4.1 Mini
Current1.05m contexttool usefunction calling
GPT-4.1 Nano
Replaced1.05m contexttool usefunction calling
2023-11
1 current
GPT-4 Turbo (older v1106)
Current128k contextstructured outputs
Replaced By
Replaced
Keep for legacy integrations; evaluate GPT-5 Nano before new work.
Specifications(4 models)
| Model | Released | Context | Vision | Multimodal | Fn Calling | Tool Use | Structured Outputs | Code Exec |
|---|---|---|---|---|---|---|---|---|
| GPT-4.1 | 2025-04 | 1.05m | Yes | Yes | Yes | Yes | Yes | Yes |
| GPT-4.1 Mini | 2025-04 | 1.05m | Yes | Yes | Yes | Yes | Yes | Yes |
| GPT-4 Turbo (older v1106) | 2023-11 | 128k | No | No | No | No | Yes | No |
Available From(5 providers)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| GPT-4.1 Mini | OpenRouter | $0.4 | $1.6 | Serverless |
| GPT-4.1 Mini | Replicate API | $0.4 | $1.6 | Serverless |
| GPT-4.1 Mini | OpenAI API | $0.4 | $1.6 | Serverless |
| GPT-4.1 Mini | Vercel AI Gateway | $0.4 | $1.6 | Serverless |
| GPT-4.1 | OpenRouter | $2 | $8 | Serverless |
| GPT-4.1 | OpenAI API | $2 | $8 | Serverless |
| GPT-4.1 | Vercel AI Gateway | $2 | $8 | Serverless |
| GPT-4 Turbo (older v1106) | OpenRouter | $10 | $30 | Serverless |
Frequently Asked Questions
- What is GPT-4.1 used for?
- GPT-4.1 is used for vision and multimodal work, agent workflows and tool use, and structured outputs. The family description and listed model capabilities point to those workloads as the best fit.
- How does GPT-4.1 compare to GPT Realtime 2?
- GPT-4.1 by OpenAI is strongest where you need vision and multimodal work, while GPT Realtime 2 by OpenAI is the closest related family to check for realtime voice. GPT-4.1 has 4 listed variants and reaches up to 1.05m context, while GPT Realtime 2 reaches up to 131k context, so compare the specs and pricing tables before choosing a production model.
- Which GPT-4.1 model should I use?
- For the lowest listed input price, start with GPT-4.1 Nano through OpenAI API at $0.1/1M input tokens. For the most capable/latest local choice, evaluate GPT-4.1 with 1.05m context and tool use, function calling, structured outputs, and multimodal inputs.
