$1.10 / $4.40per 1M tokens in / out
$0.55cache read · −50%
#295on OpenRouter by tokens · 1.7B / week
Price sheetper 1M tokens
| Input | $1.10 | list |
| Output | $4.40 | |
| Cache read | $0.55 | −50% vs input |
| Context · max output | 200K · 100K | tokens |
Where to buy1 provider · per 1M tokens
| Provider | Input | Output | Context |
|---|---|---|---|
| OpenAIlab | $1.10 | $4.40 | — |
In OpenAI's line-upper 1M in / out
| GPT-6 Luna Decisions | $0.10 / — | −100% |
| GPT OSS 20B | $0.018 / $0.09 | −98% |
| GPT OSS 120B | $0.03 / $0.15 | −97% |
| GPT OSS Safeguard 20B | $0.07 / $0.20 | −95% |
| GPT-6 Luna | $0.10 / $0.50 | −90% |
| GPT OSS Safeguard 120B | $0.15 / $0.60 | −86% |
| GPT-5.4 Mini (2026-03-17) | $0.75 / $4.50 | −12% |
Cheaper for the same workvs o3 Mini
| MiMo v2.6 Pro thinkingOpen | -72% | score ×3.7 | $0.13 |
| DeepSeek V4.1 Flash 1017 maxOpen | -73% | score ×3.6 | $0.26 |
| Ling 3.1 Flash 1019 | -77% | score ×3.5 | $1.49 |
| Step 5 Preview thinkingOpen | -26% | score ×3.5 | $1.03 |
| Claude Haiku 5.5 max | -90% | score ×3.5 | $0.21 |
Pricing questions
How much does o3 Mini cost?›
$1.10 per 1M input tokens and $4.40 per 1M output tokens. Cached input is $0.55.
Is o3 Mini free to use?›
There is no free API tier.
How much does prompt caching save?›
Cache reads cost $0.55 per 1M, 50% below the input price.
What is a cheaper alternative to o3 Mini?›
MiMo v2.6 Pro at thinking effort costs -72% per task with a score ×3.7 on .