o3-mini
OpenAI's lightweight reasoning model, released January 2025, and the first of its reasoning models offered to free-tier ChatGPT users.
Key Specifications
- Context window
- 200K tokens
- Max output
- 100K tokens
- Knowledge cutoff
- Released
- Inputs
- 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. 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. Image generation Generate and edit images from text prompts.
Hosted API pricing
| Provider | Input /1M tokens | Output /1M tokens | Cached input /1M | Cost at 10M in + 2M out | |
|---|---|---|---|---|---|
|
OpenAI
Creator
|
$1.10 | $4.40 | $0.55 | $19.80 | View |
DigitalOcean
|
$1.10 | $4.40 | $0.55 | $19.80 | View |
Azure
|
$1.10 | $4.40 | $0.55 | $19.80 | 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 o3-mini by blended rate, each at its own cheapest provider.
| Model | Blended /1M | Input /1M | Output /1M | Context | Cutoff | vs o3-mini |
|---|---|---|---|---|---|---|
Kimi K2.7 Code
Moonshot AI
|
$1.375 | $0.90 | $3.75 | 262K | −17% | |
Grok 4.20 (Non-Reasoning)
xAI
|
$1.4583 | $1.25 | $2.50 | 1M | −12% | |
|
Grok 4.20 (Reasoning)
xAI
|
$1.4583 | $1.25 | $2.50 | 1M | −12% | |
|
Grok 4.3
xAI
|
$1.4583 | $1.25 | $2.50 | 1M | −12% | |
|
o4-mini
OpenAI
|
$1.50 | $1.00 | $4.00 | 200K | Jun 2024 | −9% |
|
o3-mini
This model
OpenAI
|
$1.65 | $1.10 | $4.40 | 200K | Oct 2023 | |
Claude Haiku 4.5
Anthropic
|
$1.6667 | $1.00 | $5.00 | 200K | Feb 2025 | +1% |
GLM-5-Turbo
Z.AI
|
$1.6667 | $1.20 | $4.00 | 205K | +1% | |
|
GLM-5V-Turbo
Z.AI
|
$1.6667 | $1.20 | $4.00 | 205K | +1% | |
Qwen3-Coder-Plus
Alibaba Cloud
|
$1.6667 | $1.00 | $5.00 | 1M | +1% | |
|
Qwen3.7-Max
Alibaba Cloud
|
$1.6667 | $1.25 | $3.75 | 1M | +1% |
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 o3-mini good for?
Text-only reasoning with tools, which OpenAI calls its small reasoning model and the first offered to free-tier ChatGPT users. It sits in the lower half of OpenAI's price range.
When is o3-mini not a good fit?
Image input, since it is text only, and tasks that need web search. Its knowledge is years old, and OpenAI plans to shut it down in October 2026.
What is the cheapest way to run o3-mini?
The cheapest hosted rate is $1.10 / $4.40 per 1M tokens via OpenAI.
How does o3-mini compare with o4-mini?
OpenAI says o4-mini beats o3-mini on non-STEM tasks and data science, not just math and coding, and like o3 it is trained to use tools inside its reasoning and can think with images. Same price and 200K-token context. o3-mini came out 3 months earlier, has an older knowledge cutoff (October 2023 against June 2024) and takes no image input, which o4-mini does.
Can I self-host o3-mini?
No. OpenAI does not publish the weights; o3-mini is available only through hosted APIs.
More from OpenAI
| Model | Context | Input /1M | Output /1M |
|---|---|---|---|
|
o4-mini
|
200K | $1.00 | $4.00 |
|
GPT-5.4 Mini
|
400K | $0.75 | $4.50 |
|
GPT-5
|
400K | $1.25 | $10.00 |
|
GPT-5.1
|
400K | $1.25 | $10.00 |
|
GPT-4.1
|
1M | $2.00 | $8.00 |
|
o3
|
200K | $2.00 | $8.00 |
|
GPT-5.6 Sol
|
1M | $2.00 | $10.00 |
|
GPT-5.6 Terra
|
1M | $2.00 | $12.00 |