GPT-5.4 Mini
OpenAI's most capable small model. Fast and efficient for coding, reasoning, and multimodal tasks. Approaches GPT-5.4 performance at lower cost and latency.
- Input price
- $0.675list $0.7510% off
- Output price
- $4.05list $4.5010% off
- Context
- 400K
- Max output
- 128K
- Capability
- 149 (#62 of 82)
- Human preference
- 1412
- 30-day uptime
- —
- Released
- 2026-03-17
- Knowledge cutoff
- 2025-08
Providers
This model is served by the dedicated providers below. We pick the provider for each request, so provider preferences don’t apply, including a provider named in your request. Prices in USD per 1M tokens. Need a custom setup? Contact [email protected].
- SuccessTTFT
- Azure AI FoundryGlobal——
- OpenAIUnited States——
Pricing
Prices for this model. Each request is billed at these prices, whichever provider serves it.
| Item | Standard | Standard Discount | Batch | Batch Discount | Priority | Priority Discount | Price | Price Discount | ||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Inputper 1M tokens | $0.675 | list $0.75 | 10% off | $0.3375 | list $0.375 | 10% off | $1.35 | list $1.50 | 10% off | — | ||
| Outputper 1M tokens | $4.05 | list $4.50 | 10% off | $2.025 | list $2.25 | 10% off | $8.10 | list $9.00 | 10% off | — | ||
| Cache readper 1M tokens | $0.0675 | list $0.075 | 10% off | $0.033752 | list $0.0375 | 10% off | $0.135 | list $0.15 | 10% off | — | ||
| Web searchper request | — | — | — | $0.0126 | list $0.014 | 10% off | ||||||
| Estimated cost of common use (500 output tokens each) | ||||||||||||
| One chat message3K input tokens | $0.00406 | — | $0.0081 | — | ||||||||
| Agent first turn100K tokens of context, none cached | $0.0695 | — | $0.139 | — | ||||||||
| Each later agent turncontext read from cache, plus 2K new tokens | $0.0101 | — | $0.0203 | — | ||||||||
| 20-turn agent taskfirst turn plus 19 more | $0.262 | — | $0.524 | — | ||||||||
Try it
Runs on your balance and is billed like any API request.
Similar models
Other models with the same output types at a similar price.
Human preference ratings are from the LMArena Text Arena (CC BY 4.0, as of 2026-11-18): Elo ratings from blind votes, on a different scale from capability scores. lmarena.ai/leaderboard/text