GPT-4o mini API pricing
Standard tier, blended at 3:1 input to output: $0.263 per million tokens.
OpenAI charges $0.150 per million input tokens and $0.600 per million output tokens for GPT-4o mini. It is sold in 8 forms, from $0.131 to $0.263 blended; the table below shows what each costs against standard. 4 of the models nearest it in price are cheaper on a blended basis.
Every tier of GPT-4o mini
Blended at 3:1 input to output. The last column compares each against the standard tier.
| Source | ||||||||
|---|---|---|---|---|---|---|---|---|
| Standard Standard | gpt-4o-mini | OpenAI | $0.150 | $0.600 | $0.075 | $0.263 | Standard | ↗ |
| Standard | gpt-4o-mini | OpenRouter | $0.150 | $0.600 | $0.075 | $0.263 | Same | ↗ |
| Dated snapshot | gpt-4o-mini-2024-07-18 | OpenAI | $0.150 | $0.600 | $0.075 | $0.263 | Same | ↗ |
| Dated snapshot | gpt-4o-mini-2024-07-18 | OpenRouter | $0.150 | $0.600 | $0.075 | $0.263 | Same | ↗ |
| Dated snapshot · Preview · Audio | gpt-4o-mini-audio-preview-2024-12-17 | OpenAI | $0.150 | $0.600 | Not listed | $0.263 | Same | ↗ |
| Preview · Search | gpt-4o-mini-search-preview | OpenAI | $0.150 | $0.600 | $0.075 | $0.263 | Same | ↗ |
| Dated snapshot · Preview · Search | gpt-4o-mini-search-preview-2025-03-11 | OpenAI | $0.150 | $0.600 | $0.075 | $0.263 | Same | ↗ |
| Batch | gpt-4o-mini:batch | OpenRouter | $0.075 | $0.300 | $0.037 | $0.131 | −50% | ↗ |
Prices last checked: . Methodology
Which tier to use
What each costs against standard in our data, and the job it is for.
Batch
The batch tier (gpt-4o-mini:batch) is 50% cheaper than standard. Batch requests are queued and answered asynchronously, typically within 24 hours, so it suits work nobody is waiting on: evaluations, back-fills, bulk classification and tagging. Anything a user is waiting on belongs on the standard tier.
Audio, Search variants
The vendor also lists audio, search variants of gpt-4o-mini, listed at the same price as standard. They are the same model tuned or wired for one job, so pick one only when that is your job; otherwise standard is the reference price.
Dated snapshots
4 dated snapshots are listed at the same price as standard. A snapshot pins the model to one release, while the undated name moves to newer releases when the vendor updates it. Pin a snapshot in production when your prompts depend on exact output; use the undated name to pick up improvements automatically.
Preview and beta
3 pre-release builds (preview, beta or experimental) are listed at the same price as standard. They can change behaviour or be withdrawn at short notice, so they suit trials rather than production.
Direct or through a reseller
Through OpenRouter, gpt-4o-mini is the same price as buying direct. A reseller is worth it for one bill across vendors and automatic fallback; buy direct for the vendor's own batch, caching and rate-limit terms.
Against the models nearest in price
Standard tiers, blended at a 3:1 input to output ratio.
| Source | ||||||
|---|---|---|---|---|---|---|
| GPT-4o mini This model | OpenAI | $0.150 | $0.600 | 128,000 | $0.263 | ↗ |
| Llama 4 Maverick | OpenRouter | $0.188 | $0.652 | 524,288 | $0.304 | ↗ |
| DeepSeek V3.2 | DeepSeek | $0.280 | $0.400 | 163,840 | $0.310 | ↗ |
| DeepSeek Chat | DeepSeek | $0.280 | $0.420 | 131,072 | $0.315 | ↗ |
| DeepSeek Reasoner | DeepSeek | $0.280 | $0.420 | 131,072 | $0.315 | ↗ |
| Claude Haiku 5.5 | Anthropic | $0.100 | $0.500 | 1,000,000 | $0.200 | ↗ |
| Llama 3 8B Chat Hf | Together AI | $0.200 | $0.200 | 8,192 | $0.200 | ↗ |
| GPT-4.1 nano | OpenAI | $0.100 | $0.400 | 1,047,576 | $0.175 | ↗ |
| Gemini 2.5 Flash-Lite | Google AI | $0.100 | $0.400 | 1,048,576 | $0.175 | ↗ |
Prices last checked: . Methodology
Questions
How much does GPT-4o mini cost per million tokens?
$0.150 per million input tokens and $0.600 per million output tokens, with cached input at $0.075. At a 3:1 input to output mix that blends to $0.263. Checked 28 Oct 2026.
How much cheaper is GPT-4o mini through the Batch API?
gpt-4o-mini:batch costs $0.075 in and $0.300 out per million tokens, 50% cheaper than standard, in exchange for asynchronous delivery.
What would GPT-4o mini cost for a real workload?
A thousand requests a day at 2,000 input and 600 output tokens each comes to $19.80 a month on the standard tier, or $9.90 through batch.
What is the context window for GPT-4o mini?
128,000 tokens of input, with up to 16,384 tokens of output.
Llama 4 Maverick · DeepSeek V3.2 · DeepSeek Chat · DeepSeek Reasoner · Claude Haiku 5.5 · All OpenAI models · Cost calculator