OpenAI: O3 Mini
openai/o3-mini
OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the reasoning_effort parameter, which can be set to "high", "medium", or "low" to control the thinking time of the model. The default is "medium". OpenRouter also offers the model slug openai/o3-mini-high to default the parameter to "high". The model features three adjustable reasoning effort levels and supports key developer capabilities including function calling, structured outputs, and streaming, though it does not include vision processing capabilities. The model demonstrates significant improvements over its predecessor, with expert testers preferring its responses 56% of the time and noting a 39% reduction in major errors on complex questions. With medium reasoning effort settings, o3-mini matches the performance of the larger o1 model on challenging reasoning evaluations like AIME and GPQA, while maintaining lower latency and cost.
Model specifications
- Input
- text
- Output
- text
- Context
- 200,000 tokens
- Max output
- 1 tokens
- Input price
- $0.9075 / 1M tokens
- Output price
- $3.63 / 1M tokens
- Released
- 2026-02-18
Capabilities
- Streaming
- Function calling
- JSON mode
- Playground
Provider pricing, discounts and data privacy
Compare effective provider prices, published discounts, regions, retention policies, training use, compliance, and privacy links by service tier.
Standard service tier
1 available provider · discounts up to 25% · tier input average $0.9075 / 1M tokens · tier output average $3.63 / 1M tokens
Azure
Tier: Standard · Region: US
Pricing
- Input
- $0.9075 / 1M tokens
- Output
- $3.63 / 1M tokens
Discounts
- Input: 25% off — list $1.21 / 1M tokens, discounted $0.9075 / 1M tokens, effective $0.9075 / 1M tokens
- Output: 25% off — list $4.84 / 1M tokens, discounted $3.63 / 1M tokens, effective $3.63 / 1M tokens
Data privacy and compliance
- Region
- US
- Zero data retention
- Yes
- Data retention
- Zero retention
- Used for training
- No
- Data collection
- Moderated
- No
- GDPR compliant
- Yes
- HIPAA compliant
- Yes
- SOC 2 certified
- Yes
- BYOK supported
- No
Privacy policy · Terms · Official website · Documentation · Status
Frequently asked questions
- What is OpenAI: O3 Mini?
- OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the reasoning_effort parameter, which can be set to "high", "medium", or "low" to control the thinking time of the model. The default is "medium". OpenRouter also offers the model slug openai/o3-mini-high to default the parameter to "high". The model features three adjustable reasoning effort levels and supports key developer capabilities including function calling, structured outputs, and streaming, though it does not include vision processing capabilities. The model demonstrates significant improvements over its predecessor, with expert testers preferring its responses 56% of the time and noting a 39% reduction in major errors on complex questions. With medium reasoning effort settings, o3-mini matches the performance of the larger o1 model on challenging reasoning evaluations like AIME and GPQA, while maintaining lower latency and cost.
- How much does OpenAI: O3 Mini cost?
- Input costs start at $0.9075 / 1M tokens and output costs start at $3.63 / 1M tokens. Provider-level prices vary by service tier.
- Are provider discounts available for OpenAI: O3 Mini?
- Yes. Current provider offers include discounts of up to 25% from list price. The provider table shows list, discounted, and effective prices.
- What is the context length of OpenAI: O3 Mini?
- OpenAI: O3 Mini supports a 200,000 token context window and up to 1 output tokens.
- What capabilities does OpenAI: O3 Mini support?
- OpenAI: O3 Mini supports Streaming, Function calling, JSON mode, Playground.
- Which providers offer OpenAI: O3 Mini?
- OpenAI: O3 Mini is available from Azure.
- How do providers handle data privacy for OpenAI: O3 Mini?
- 1 of 1 providers report that customer data is not used for training, and 1 offer zero-data-retention routing. Retention, compliance, and privacy-policy links are listed per provider.