GPT-5.1 Models by OpenAI
OpenAIProprietary
5 models2025Up to 400k ctxFrom $0.25/1M input
Details
ResearcherOpenAI
LicenseProprietary
Commercial useCommercial use: conditional
Models5
Released2025
Max context400k
Capabilities
VisionAll models
MultimodalAll models
Reasoning3 of 5 models
Function CallingAll models
Tool UseAll models
Structured Outputs4 of 5 models
Code Execution1 of 5 models
Links
WebsiteAbout
OpenAI's GPT-5.1 family released November 2025, featuring adaptive reasoning with dynamically adjustable thinking effort. Includes a general thinking model and a code-specialized Codex variant. Deprecated in ChatGPT as of March 11, 2026.
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
4 in view1 retired
GPT-5.1 CodexCurrent
Use when the workload needs code, 400k context, and tool use.
2025-12code400k contexttool use
GPT-5.1 ChatCurrent
Use when the workload needs 128k context, tool use, and function calling.
2025-12128k contexttool usefunction calling
GPT-5.1 Codex MaxCurrent
Use when the workload needs code, reasoning, and tool use.
2025-11codereasoningtool use
GPT-5.1 Codex MiniCurrent
Use when the workload needs code, 400k context, and reasoning.
2025-11code400k contextreasoning
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| GPT-5.1 Codex | Use when the workload needs code, 400k context, and tool use. | 2025-12 | code400k contexttool use | Current |
| GPT-5.1 Chat | Use when the workload needs 128k context, tool use, and function calling. | 2025-12 | 128k contexttool usefunction calling | Current |
| GPT-5.1 Codex Max | Use when the workload needs code, reasoning, and tool use. | 2025-11 | codereasoningtool use | Current |
| GPT-5.1 Codex Mini | Use when the workload needs code, 400k context, and reasoning. | 2025-11 | code400k contextreasoning | Current |
Release Timeline
2 release groups2025-12
2 current
GPT-5.1 Chat
Current128k contexttool usefunction calling
GPT-5.1 Codex
Currentcode400k contexttool use
2025-11
2 current · 1 retired
GPT-5.1
Archived262k contextreasoningtool use
GPT-5.1 Codex Max
Currentcodereasoningtool use
GPT-5.1 Codex Mini
Currentcode400k contextreasoning
Specifications(5 models)
| Model | Released | Context | Vision | Multimodal | Reasoning | Fn Calling | Tool Use | Structured Outputs | Code Exec |
|---|---|---|---|---|---|---|---|---|---|
| GPT-5.1 Codex | 2025-12 | 400k | Yes | Yes | No | Yes | Yes | Yes | Yes |
| GPT-5.1 Chat | 2025-12 | 128k | Yes | Yes | No | Yes | Yes | Yes | No |
| GPT-5.1 Codex Max | 2025-11 | — | Yes | Yes | Yes | Yes | Yes | Yes | No |
| GPT-5.1 Codex Mini | 2025-11 | 400k | Yes | Yes | Yes | Yes | Yes | No | No |
Available From(2 providers)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| GPT-5.1 Codex Mini | Vercel AI Gateway | $0.25 | $2 | Serverless |
| GPT-5.1 Codex Mini | OpenRouter | $0.25 | $2 | Serverless |
| GPT-5.1 Codex | OpenRouter | $1.25 | $10 | Serverless |
| GPT-5.1 Codex | Vercel AI Gateway | $1.25 | $10 | Serverless |
| GPT-5.1 Codex Max | Vercel AI Gateway | $1.25 | $10 | Serverless |
| GPT-5.1 Chat | OpenRouter | $1.25 | $10 | Serverless |
Popular comparisons in this family
Frequently Asked Questions
- What is GPT-5.1 used for?
- GPT-5.1 is used for code, vision and multimodal work, and reasoning. The family description and listed model capabilities point to those workloads as the best fit.
- How does GPT-5.1 compare to GPT Realtime 2?
- GPT-5.1 by OpenAI is strongest where you need code, while GPT Realtime 2 by OpenAI is the closest related family to check for realtime voice. GPT-5.1 has 5 listed variants and reaches up to 400k context, while GPT Realtime 2 reaches up to 131k context, so compare the specs and pricing tables before choosing a production model.
- Which GPT-5.1 model should I use?
- For the lowest listed input price, start with GPT-5.1 Codex Mini through OpenRouter at $0.25/1M input tokens. For the most capable/latest local choice, evaluate GPT-5.1 Codex with 400k context and tool use, function calling, structured outputs, and multimodal inputs.
