// OpenAI
o4-mini
A OpenAI model. 1 prices across 1 channels side by side, each with its source and check date – plus specs, licence, speed and benchmarks.
- Official in/out per 1M
- $1.1 / $4.4
- Lowest (official)
- $1.1 / $4.4
- Context
- 200K
- AA index
- 16.7
Prices checked 2026-10-10Official sources linked on every rowNo estimatesCheapest LLM APIs →
01Specs at a glance
Official values first; gaps filled from OpenRouter’s API where the vendor page is silent.
| Vendor | OpenAI |
|---|---|
| Context window | 200K (200,000 tokens) |
| Max output | 100K |
| Input | Image · Text · File/PDF |
| Output | Text |
| Tool calling / JSON | Yes / Yes |
| Weights & licence | Closed · Proprietary (API only) |
| Released | Apr 16, 2025 (OpenRouter listing date) |
| Model IDs | o4-mini |
02Prices on 1 channels
Per 1M tokens, in the currency each source publishes (1 USD = 6.7 CNY for the blended column). Sorted: official first, then cheapest.
| Channel | Source | Input | Output | Cache hit | Blended $ | Context | Notes |
|---|---|---|---|---|---|---|---|
| Official Vendor API, billed in USD | Official 10-10 | $1.1 | $4.4 | $0.275 | 1.93 | 200K | Batch −50%Batch/Flex -50%; regional endpoints +10%; long context (>272K) input 2x / output 1.5x where applicable |
“Official” = vendor pricing page; “Platform” = the platform’s own pricing page; “OpenRouter” = price listed on OpenRouter, not checked on the platform’s site. Click a source tag to open the original page.
03Where you can use it
Derived only from the price sources above. Country restrictions are set by each vendor – check their terms before you sign up.
- Vendor API, billed in USD
Official
04Performance
All results →Speed and AA index from Artificial Analysis public leaderboards (not our own tests); benchmark scores from our benchmark library, best result per benchmark.
- AA indexo4-mini (High)
- 16.7
- Output speed (median)
- 161 tok/s
- Time to first token
- 23.31s
- AA index per $ (blended)
- 8.65
Default TTFT includes thinking time at the highest reasoning setting; low-effort settings respond much faster.
| Benchmark | Best score | Source | Date |
|---|---|---|---|
| LMArena Text | 1391 | official | 2026-10-08 |
| LMArena Vision | 1201 | official | 2026-10-02 |
| LiveCodeBench | 75.8% | official | 2025-04-07 |
| GPQA Diamond | 79.6% | independent | 2025-04-16 |
| SWE-bench Verified | 64.6% | official | 2025-05-03 |
| AIME (OTIS Mock AIME 2024–2025) | 81.7% | independent | 2025-04-16 |
| MATH Level 5 | 97.8% | independent | 2025-04-16 |
| Humanity's Last Exam | 18.1% | compiled | 2025-04-16 |
| τ²-bench | 68.3% | official | 2025-06-09 |
| BFCL v4 (function calling) | 53.2% | official | 2026-10-17 |
05Price changes we recorded
All price changes →From our daily re-checks of the sources above.
No price change recorded since we started tracking (2026-10-10).
06More from OpenAI
FAQ
How much does the o4-mini API cost?
On the official pricing page: $1.1 / $4.4 per 1M input / output tokens, cached input $0.275 (checked 2026-10-10).
What is the context window of o4-mini?
200K tokens of context, up to 100K output tokens. Platforms may cap it lower – see the table.
Is o4-mini open source?
No. It is only available through APIs and the vendor’s apps.