GPT-5 Mini
The faster, smaller variant of GPT-5, suited to well-defined tasks where full GPT-5 reasoning is unnecessary.
Key Specifications
- Context window
- 400K tokens
- Max output
- 128K tokens
- Knowledge cutoff
- web search available
- Released
- Inputs
- Image, text
- Capabilities Show details
- Reasoning Thinks before it answers, always on or as a switchable mode. Function calling Connect to external tools, APIs, and systems. Structured output Return responses in structured formats like JSON. Web search Search the web for up-to-date information. Code execution Write and execute code in a sandboxed environment. File upload Process uploaded documents, spreadsheets, and other files. MCP Connect to services via Model Context Protocol.
Hosted API pricing
| Provider | Input /1M tokens | Output /1M tokens | Cached input /1M | Cost at 10M in + 2M out | |
|---|---|---|---|---|---|
|
OpenAI
Creator
|
$0.25 | $2.00 | $0.03 | $6.50 | View |
DigitalOcean
|
$0.25 | $2.00 | $0.03 | $6.50 | View |
Azure
|
$0.25 | $2.00 | $0.03 | $6.50 | View |
Replicate
|
$0.25 | $2.00 | $6.50 | View |
Heads up: Base-tier, on-demand rates per 1M tokens; cached, batch and long-context tiers excluded. A provider may serve a shorter context or a quantized build than the creator's release. Verify before provisioning. More on how we price.
Similarly priced models
The models nearest GPT-5 Mini by blended rate, each at its own cheapest provider.
| Model | Blended /1M | Input /1M | Output /1M | Context | Cutoff | vs GPT-5 Mini |
|---|---|---|---|---|---|---|
MiniMax-M2.5
MiniMax
|
$0.45 | $0.30 | $1.20 | 205K | −17% | |
Gemini 3.1 Flash-Lite
Google Cloud
|
$0.4583 | $0.25 | $1.50 | 1M | Jan 2025 | −15% |
Qwen3.6-Flash
Alibaba Cloud
|
$0.4583 | $0.25 | $1.50 | 1M | −15% | |
|
Qwen3-VL-235B-A22B Instruct
Alibaba Cloud
|
$0.50 | $0.30 | $1.50 | 262K | −8% | |
DeepSeek V4 Pro
DeepSeek
|
$0.5233 | $0.45 | $0.89 | 1M | −3% | |
|
GPT-5 Mini
This model
OpenAI
|
$0.5417 | $0.25 | $2.00 | 400K | May 2024 | |
|
DeepSeek V3 Turbo
DeepSeek
|
$0.55 | $0.40 | $1.30 | 64K | +2% | |
|
Qwen3-VL-30B-A3B Thinking
Alibaba Cloud
|
$0.5667 | $0.20 | $2.40 | 262K | +5% | |
|
Qwen3-235B-A22B Thinking (2507)
Alibaba Cloud
|
$0.575 | $0.23 | $2.30 | 262K | +6% | |
|
Qwen3-Coder-480B-A35B
Alibaba Cloud
|
$0.575 | $0.38 | $1.55 | 262K | +6% | |
|
GPT-4.1 Mini
OpenAI
|
$0.60 | $0.40 | $1.60 | 1M | Jun 2024 | +11% |
Prices are USD per 1M tokens at each model's cheapest listed provider. Blended is the cost of 10M input plus 2M output tokens, spread over the 12M.
Frequently Asked Questions
What is GPT-5 Mini good for?
Well-defined, high-volume tasks with precise prompts, where cost and latency matter. It sits at the lower-cost end of OpenAI's lineup.
When is GPT-5 Mini not a good fit?
Open-ended problems that need full GPT-5 reasoning, and image generation, which it lacks. Not for new workloads either: OpenAI recommends starting with GPT-5.6 Terra and plans to shut down the API model in December 2026.
What is the cheapest way to run GPT-5 Mini?
The cheapest hosted rate is $0.25 / $2.00 per 1M tokens via OpenAI.
How does GPT-5 Mini compare with GPT-5.4 Mini?
OpenAI says GPT-5.4 Mini improves on GPT-5 Mini at coding, reasoning, image understanding and tool use and runs faster, and it adds built-in computer use, tool search and context compaction. Same 400K-token context and text and image input. GPT-5 Mini lists at 67% less per 1M input tokens and 56% less per 1M output tokens than GPT-5.4 Mini. It came out 7 months earlier and has an older knowledge cutoff (May 2024 against August 2025).
Can I self-host GPT-5 Mini?
No. OpenAI does not publish the weights; GPT-5 Mini is available only through hosted APIs.
More from OpenAI
| Model | Context | Input /1M | Output /1M |
|---|---|---|---|
|
GPT-4.1 Mini
|
1M | $0.40 | $1.60 |
|
GPT-3.5 Turbo
|
16K | $0.50 | $1.50 |
|
GPT-5.4 Nano
|
400K | $0.20 | $1.25 |
|
GPT-5.6 Luna
|
1M | $0.20 | $1.20 |
|
GPT-4o Mini
|
128K | $0.15 | $0.60 |
|
GPT-5.4 Mini
|
400K | $0.75 | $4.50 |
|
o4-mini
|
200K | $1.00 | $4.00 |
|
o3-mini
|
200K | $1.10 | $4.40 |