OpenAI: o4 Mini Deep Research
Analysis Summary
OpenAI o4 Mini Deep Research is a cost-optimised research reasoning model from OpenAI, with an intelligence index of 33 and standout math performance at 90.7. It supports tool use, function calling, and vision across a 200K context window, giving it broad capability for analytical and research tasks.
For businesses, it is a strong fit for structured research tasks, literature synthesis, and quantitative analysis where math and science reasoning matter. Its livecodebench score of 85.9 is high, though its broader coding index is more modest, suggesting strength in algorithmic problem-solving rather than full software engineering workflows. The lower agentic index compared to some peers means it is less suited to fully autonomous multi-step agent pipelines.
At $2 input and $8 output per million tokens, it offers substantially better value than o3 Deep Research for similar research use cases. Teams running regular analytical workloads will find the price-to-capability ratio compelling, particularly for math-heavy or science-focused tasks.
Assessed June 6, 2026
Editorial notes
OpenAI o4 Mini Deep Research pairs strong math and science reasoning with tool use and vision at a significantly lower price than its o3 sibling, making it a practical choice for research-intensive workflows on a tighter budget.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How OpenAI: o4 Mini Deep Research compares
OpenAI: o4 Mini Deep Research ranks #65 of 380 AI models we track for overall intelligence, #52 of 94 for coding. Its 200K-token context window is larger than 65% of the models we list. At $2.00 per million input tokens it is cheaper than 16% of comparable models.
About OpenAI: o4 Mini Deep Research
o4-mini-deep-research is OpenAI's faster, more affordable deep research modelāideal for tackling complex, multi-step research tasks. Note: This model always uses the 'web_search' tool which adds additional cost.
Capabilities
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Benchmark data from Artificial Analysis and Hugging Face
How does OpenAI: o4 Mini Deep Research stack up?
Compare side-by-side with other specialist models.
Model Information
| OpenRouter ID |
openai/o4-mini-deep-research
|
| Provider | openai |
| Release Date | October 10, 2025 |
| Context Length | 200,000 tokens |
| Max Completion | 100,000 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $2.00 | $0.002000 |
| Output | $8.00 | $0.008000 |
Live Performance
Live endpoint metrics, refreshed every 30 minutes.
Leaderboard Categories
External Resources
Frequently asked questions about OpenAI: o4 Mini Deep Research
How much does OpenAI: o4 Mini Deep Research cost?
OpenAI: o4 Mini Deep Research costs $2.00 per million input tokens and $8.00 per million output tokens.
What is the context window of OpenAI: o4 Mini Deep Research?
OpenAI: o4 Mini Deep Research has a context window of 200,000 tokens (200K).
Is OpenAI: o4 Mini Deep Research good for coding?
On our coding benchmark index, OpenAI: o4 Mini Deep Research ranks #52 of 94 models, placing it in the broader range of the field for code generation and debugging.
What can OpenAI: o4 Mini Deep Research do?
OpenAI: o4 Mini Deep Research supports image/vision input, tool use, and function calling.
Who created OpenAI: o4 Mini Deep Research?
OpenAI: o4 Mini Deep Research is developed by OpenAI and was released on October 10, 2025.
