o4-mini
OpenAI's small, fast reasoning model, released April 2025 alongside o3, notably strong at math.
- Input
- $1.10 /1M tokens
- Output
- $4.40 /1M tokens
Cheapest: $1.00 / $4.00 per 1M tokens via Replicate
3 providers
Key Specifications
- Context window
- 200K tokens
- Max output
- 100K tokens
- Knowledge cutoff
- web search available
- Released
- Inputs
- Text, image
- 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 | |
|---|---|---|---|---|---|
|
Replicate
Cheapest
|
$1.00 | $4.00 | $18.00 | View | |
|
OpenAI
Creator
|
$1.10 | $4.40 | $0.28 | $19.80 | View |
|
Azure
|
$1.10 | $4.40 | $0.28 | $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 o4-mini by blended rate, each at its own cheapest provider.
| Model | Blended /1M | Input /1M | Output /1M | Context | Cutoff | vs o4-mini |
|---|---|---|---|---|---|---|
|
GPT-5.4 Mini
OpenAI
|
$1.375 | $0.75 | $4.50 | 400K | Aug 2025 | −8% |
Kimi K2.7 Code
Moonshot AI
|
$1.375 | $0.90 | $3.75 | 262K | −8% | |
Grok 4.20 (Non-Reasoning)
xAI
|
$1.4583 | $1.25 | $2.50 | 1M | −3% | |
|
Grok 4.20 (Reasoning)
xAI
|
$1.4583 | $1.25 | $2.50 | 1M | −3% | |
|
Grok 4.3
xAI
|
$1.4583 | $1.25 | $2.50 | 1M | −3% | |
|
o4-mini
This model
OpenAI
|
$1.50 | $1.00 | $4.00 | 200K | Jun 2024 | |
|
o3-mini
OpenAI
|
$1.65 | $1.10 | $4.40 | 200K | Oct 2023 | +10% |
Claude Haiku 4.5
Anthropic
|
$1.6667 | $1.00 | $5.00 | 200K | Feb 2025 | +11% |
GLM-5-Turbo
Z.AI
|
$1.6667 | $1.20 | $4.00 | 205K | +11% | |
|
GLM-5V-Turbo
Z.AI
|
$1.6667 | $1.20 | $4.00 | 205K | +11% | |
Qwen3-Coder-Plus
Alibaba Cloud
|
$1.6667 | $1.00 | $5.00 | 1M | +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 o4-mini good for?
Cost-sensitive reasoning with tools, coding and visual tasks, as OpenAI's small o-series model. It sits in the lower half of OpenAI's price range.
When is o4-mini not a good fit?
New projects: OpenAI says GPT-5 Mini succeeds it and plans to shut it down in October 2026. Its knowledge is older and its inputs shorter than the GPT-5 line's, and there is no audio or video input.
What is the cheapest way to run o4-mini?
The cheapest hosted rate is $1.00 / $4.00 per 1M tokens via Replicate; the creator's list price is $1.10 / $4.40.
How does o4-mini compare with o3-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. o4-mini came out 3 months later, has a newer knowledge cutoff (June 2024 against October 2023) and takes image input, which o3-mini does not.
Can I self-host o4-mini?
No. OpenAI does not publish the weights; o4-mini is available only through hosted APIs.
More from OpenAI
| Model | Context | Input /1M | Output /1M |
|---|---|---|---|
|
GPT-5.4 Mini
|
400K | $0.75 | $4.50 |
|
o3-mini
|
200K | $1.10 | $4.40 |
|
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-3.5 Turbo
|
16K | $0.50 | $1.50 |