Back to models
deprecated
OpenAI: o4 Mini
openai/o4-miniPrices
- Input
$1.10 per 1M tokens
medium- Input (batch)
$0.55 per 1M tokens
low- Input (batch) (training: $100.00 / hour)
$2.00 per 1M tokens
medium- Input (cached read, batch)
$0.50 per 1M tokens
medium- Input (cached read, flex)
$0.1375 per 1M tokens
low- Input (cached read, priority)
$0.50 per 1M tokens
low- Input (cached read)
$0.275 per 1M tokens
medium- Input (cached read) (training: $100.00 / hour)
$1.00 per 1M tokens
medium- Input (flex)
$0.55 per 1M tokens
low- Input (priority)
$2.00 per 1M tokens
low- Input (training: $100.00 / hour)
$4.00 per 1M tokens
medium- Output
$4.40 per 1M tokens
medium- Output (batch)
$2.20 per 1M tokens
low- Output (batch) (training: $100.00 / hour)
$8.00 per 1M tokens
medium- Output (flex)
$2.20 per 1M tokens
low- Output (priority)
$8.00 per 1M tokens
low- Output (training: $100.00 / hour)
$16.00 per 1M tokens
medium- Web search (context size: high)
$0.01 per query
low- Web search (context size: low)
$0.01 per query
low- Web search (context size: medium)
$0.01 per query
low
Also available on
The same model, sold by someone else. The price above is the maker's own.
| Channel | What | Price |
|---|---|---|
| Microsoft Azure | Input | $1.10 per 1M tokens |
| Input (batch) | $0.55 per 1M tokens | |
| Input (batch) (region: eu) | $0.605 per 1M tokens | |
| Input (batch) (region: us) | $0.605 per 1M tokens | |
| Input (cached read) | $0.275 per 1M tokens | |
| Input (cached read) (region: eu) | $0.303 per 1M tokens | |
| Input (cached read) (region: us) | $0.303 per 1M tokens | |
| Input (region: eu) | $1.21 per 1M tokens | |
| Input (region: us) | $1.21 per 1M tokens | |
| Output | $4.40 per 1M tokens | |
| Output (batch) | $2.20 per 1M tokens | |
| Output (batch) (region: eu) | $2.42 per 1M tokens | |
| Output (batch) (region: us) | $2.42 per 1M tokens | |
| Output (region: eu) | $4.84 per 1M tokens | |
| Output (region: us) | $4.84 per 1M tokens | |
| Microsoft Azure · azure-ai | Input | $1.10 per 1M tokens |
| Input (cached read) | $0.275 per 1M tokens | |
| Output | $4.40 per 1M tokens | |
| OpenRouter · openai | Input | $1.10 per 1M tokens |
| Input (cached read) | $0.275 per 1M tokens | |
| Output | $4.40 per 1M tokens | |
| Query | $0.01 per query | |
| OpenRouter | Input | $1.10 per 1M tokens |
| Input (cached read) | $0.275 per 1M tokens | |
| Output | $4.40 per 1M tokens | |
| Other · cloudflare-ai-gateway | Input | $1.10 per 1M tokens |
| Input (cached read) | $0.275 per 1M tokens | |
| Output | $4.40 per 1M tokens | |
| Other · edenai | Input | $1.10 per 1M tokens |
| Input (cached read) | $0.275 per 1M tokens | |
| Output | $4.40 per 1M tokens | |
| Other · impossibl | Input | $1.10 per 1M tokens |
| Input (cached read) | $0.275 per 1M tokens | |
| Output | $4.40 per 1M tokens | |
| Other · kilo | Input | $1.10 per 1M tokens |
| Input (cached read) | $0.275 per 1M tokens | |
| Output | $4.40 per 1M tokens | |
| Other · llmgateway-providers | Input | $1.10 per 1M tokens |
| Input (cached read) | $0.275 per 1M tokens | |
| Output | $4.40 per 1M tokens | |
| Other · merge-gateway | Input | $1.10 per 1M tokens |
| Input (cached read) | $0.275 per 1M tokens | |
| Output | $4.40 per 1M tokens | |
| Other · nano-gpt | Input | $1.10 per 1M tokens |
| Input (cached read) | $0.55 per 1M tokens | |
| Output | $4.40 per 1M tokens | |
| Other · nearai | Input | $1.10 per 1M tokens |
| Input (cached read) | $0.275 per 1M tokens | |
| Output | $4.40 per 1M tokens | |
| Other · openrouter | Input | $1.10 per 1M tokens |
| Input (cached read) | $0.275 per 1M tokens | |
| Output | $4.40 per 1M tokens | |
| Other · poe | Input | $0.99 per 1M tokens |
| Input (cached read) | $0.25 per 1M tokens | |
| Output | $4.00 per 1M tokens | |
| Other · vercel | Input | $1.10 per 1M tokens |
| Input (cached read) | $0.275 per 1M tokens | |
| Output | $4.40 per 1M tokens |
Specifications
- Provider
- openai
- Context window
- 200,000
- Max output tokens
- 100,000
- Open weights
- no
- Released
- 04/16/2025
- Retires
- 11/19/2026
- First seen by this tracker
Price history
No price of this model has changed since we started tracking it.
- Input (training: $100.00 / hour)
- 4 per 1M tokens, unchanged since 09/14/2026
- Input (cached read) (training: $100.00 / hour)
- 1 per 1M tokens, unchanged since 09/14/2026
- Output (training: $100.00 / hour)
- 16 per 1M tokens, unchanged since 09/14/2026
- Input (cached read)
- 0.275 per 1M tokens, unchanged since 09/14/2026
- Input (cached read, flex)
- 0.1375 per 1M tokens, unchanged since 09/14/2026
- Input (cached read, priority)
- 0.5 per 1M tokens, unchanged since 09/14/2026
- Input
- 1.1 per 1M tokens, unchanged since 09/14/2026
- Input (flex)
- 0.55 per 1M tokens, unchanged since 09/14/2026
- Input (priority)
- 2 per 1M tokens, unchanged since 09/14/2026
- Output
- 4.4 per 1M tokens, unchanged since 09/14/2026
- Output (flex)
- 2.2 per 1M tokens, unchanged since 09/14/2026
- Output (priority)
- 8 per 1M tokens, unchanged since 09/14/2026
- Web search (context size: high)
- 0.01 per query, unchanged since 09/14/2026
- Web search (context size: low)
- 0.01 per query, unchanged since 09/14/2026
- Web search (context size: medium)
- 0.01 per query, unchanged since 09/14/2026
- Input (batch)
- 0.55 per 1M tokens, unchanged since 09/15/2026
- Output (batch)
- 2.2 per 1M tokens, unchanged since 09/15/2026
- Input (batch) (training: $100.00 / hour)
- 2 per 1M tokens, unchanged since 10/01/2026
- Input (cached read, batch)
- 0.5 per 1M tokens, unchanged since 10/01/2026
- Output (batch) (training: $100.00 / hour)
- 8 per 1M tokens, unchanged since 10/01/2026