GPT-5 Models by OpenAI
Details
Capabilities
Links
WebsiteAbout
OpenAI's GPT-5 family (August 2025). Includes gpt-5, gpt-5-mini, and gpt-5-nano. Succeeded by GPT-5.1 and later generations.
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
Use when the workload needs 400k context, tool use, and function calling.
Use when the workload needs 128k context, tool use, and function calling.
Use when the workload needs code, 400k context, and tool use.
Use when the workload needs 400k context, tool use, and function calling.
Use when the workload needs 400k context and multimodal inputs.
Use when the workload needs 400k context, reasoning, and tool use.
Use when the workload needs 400k context, reasoning, and tool use.
Use when the workload needs 400k context, reasoning, and tool use.
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| GPT-5 Pro | Use when the workload needs 400k context, tool use, and function calling. | 2025-10 | 400k contexttool usefunction calling | Current |
| GPT-5 Chat | Use when the workload needs 128k context, tool use, and function calling. | 2025-10 | 128k contexttool usefunction calling | Current |
| GPT-5 Codex | Use when the workload needs code, 400k context, and tool use. | 2025-10 | code400k contexttool use | Current |
| GPT-5 Image | Use when the workload needs 400k context, tool use, and function calling. | 2025-10 | 400k contexttool usefunction calling | Current |
| GPT-5 Image Mini | Use when the workload needs 400k context and multimodal inputs. | 2025-10 | 400k contextmultimodal inputs | Current |
| GPT-5 | Use when the workload needs 400k context, reasoning, and tool use. | 2025-08 | 400k contextreasoningtool use | Current |
| GPT-5 Mini | Use when the workload needs 400k context, reasoning, and tool use. | 2025-08 | 400k contextreasoningtool use | Current |
| GPT-5 Nano | Use when the workload needs 400k context, reasoning, and tool use. | 2025-08 | 400k contextreasoningtool use | Current |
Release Timeline
3 release groupsSpecifications(10 models)
| Model | Released | Context | Vision | Multimodal | Reasoning | Fn Calling | Tool Use | Structured Outputs | Code Exec |
|---|---|---|---|---|---|---|---|---|---|
| GPT-5 Pro | 2025-10 | 400k | Yes | Yes | No | Yes | Yes | Yes | Yes |
| GPT-5 Chat | 2025-10 | 128k | Yes | Yes | No | Yes | Yes | Yes | No |
| GPT-5 Codex | 2025-10 | 400k | Yes | Yes | No | Yes | Yes | Yes | Yes |
| GPT-5 Image | 2025-10 | 400k | Yes | Yes | No | Yes | Yes | No | No |
| GPT-5 Image Mini | 2025-10 | 400k | Yes | Yes | No | No | No | No | No |
| GPT-5 | 2025-08 | 400k | Yes | Yes | Yes | Yes | Yes | Yes | Yes |
| GPT-5 Mini | 2025-08 | 400k | Yes | Yes | Yes | Yes | Yes | Yes | Yes |
| GPT-5 Nano | 2025-08 | 400k | Yes | Yes | Yes | Yes | Yes | Yes | Yes |
Available From(4 providers)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| GPT-5 Nano | Replicate API | $0.05 | $0.4 | Serverless |
| GPT-5 Nano | OpenRouter | $0.05 | $0.4 | Serverless |
| GPT-5 Nano | OpenAI API | $0.05 | $0.4 | Serverless |
| GPT-5 Nano | Vercel AI Gateway | $0.05 | $0.4 | Serverless |
| GPT-5 Mini | Replicate API | $0.25 | $2 | Serverless |
| GPT-5 Mini | OpenRouter | $0.25 | $2 | Serverless |
| GPT-5 Mini | OpenAI API | $0.25 | $2 | Serverless |
| GPT-5 Mini | Vercel AI Gateway | $0.25 | $2 | Serverless |
| GPT-5 | Replicate API | $1.25 | $10 | Serverless |
| GPT-5 | OpenRouter | $1.25 | $10 | Serverless |
| GPT-5 | OpenAI API | $1.25 | $10 | Serverless |
| GPT-5 | Vercel AI Gateway | $1.25 | $10 | Serverless |
| GPT-5 Chat | Vercel AI Gateway | $1.25 | $10 | Serverless |
| GPT-5 Codex | Vercel AI Gateway | $1.25 | $10 | Serverless |
| GPT-5 Pro | Vercel AI Gateway | $15 | $120 | Serverless |
Comparisons
- Qwen3.6-Max vs GPT-5
- GPT-5 vs Claude Sonnet 4.6
- GPT-5 vs Claude Opus 4.6
- GPT-5 vs DeepSeek V4 Pro
- GPT-5 vs Grok 4
- GPT-5 vs Llama 4 Maverick 17B Instruct FP8
- GPT-5 vs Qwen3-Max
- GPT-5.2 vs Claude Sonnet 4.6
Frequently Asked Questions
- What is GPT-5 used for?
- GPT-5 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 compare to GPT Realtime 2?
- GPT-5 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 has 10 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 model should I use?
- For the lowest listed input price, start with GPT-5 Nano through OpenAI API at $0.05/1M input tokens. For the most capable/latest local choice, evaluate GPT-5 with 400k context and reasoning, tool use, function calling, structured outputs, and multimodal inputs.
Models(10)
GPT-5 Pro
GPT-5 Chat
GPT-5 Codex
GPT-5 Image
GPT-5 Image Mini
GPT-5
GPT-5 Mini
GPT-5 Nano






