o3-mini pricing
OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. o3-mini from OpenAI costs $1.10 per 1M input tokens and $4.40 per 1M output tokens. Cached input is $0.550 per 1M. Context window 200,000 tokens.
API id o3-mini · OpenAI · source · updated 2026-09-25 · general-purpose
$1.10
Input / 1M tokens
$4.40
Output / 1M tokens
$0.550
Cached input / 1M
200K
Context window
o3-mini specifications
- Provider
- OpenAI
- API id
o3-mini- Model type
- general-purpose
- Context window
- 200K tokens
- Max output
- 100K tokens
- Currency
- USD
- Price source
- First-party
- Last checked
- 2026-09-25
Tags
- fast
- reasoning
o3-mini across providers
The same model, priced by every seller we track. Ranked by the cost of 1M input + 1M output tokens, standard tier; savings measured against buying from the vendor directly.
| Provider | Input /1M | Cached /1M | Output /1M | 1M in + 1M out | vs vendor |
|---|---|---|---|---|---|
| $1.10 | $0.550 | $4.40 | $5.50 | — | |
OpenRouterHost | $1.10 | $0.550 | $4.40 | $5.50 | — |
What o3-mini costs in practice
| Workload | Input tokens | Output tokens | Estimated cost |
|---|---|---|---|
| Short chat turn | 1,000 | 500 | $0.0033 |
| Document summary | 50,000 | 2,000 | $0.06 |
| 1M tokens in, 200K out | 1,000,000 | 200,000 | $1.98 |
Estimates use the standard tier and ignore caching discounts, so real bills with repeated prompt prefixes are typically lower.
Common questions
- How much does o3-mini cost per 1M tokens?
- o3-mini costs $1.10 per 1M input tokens and $4.40 per 1M output tokens on the standard tier. Cached input is $0.550 per 1M.
- What is o3-mini's context window?
- o3-mini accepts up to 200,000 tokens in a single request, and can return up to 100,000 output tokens.
- Is there a cheaper OpenAI model than o3-mini?
- Yes. omni-moderation-latest is free per 1M input tokens versus $1.10 for o3-mini.
- Where does this o3-mini price come from?
- Directly from OpenAI's published pricing page, re-read every day and normalized to USD per 1,000,000 tokens.