o4-mini API pricing
Standard tier, blended at 3:1 input to output: $1.93 per million tokens.
OpenAI charges $1.10 per million input tokens and $4.40 per million output tokens for o4-mini. It is sold in 5 forms, from $0.963 to $1.93 blended; the table below shows what each costs against standard. 6 of the models nearest it in price are cheaper on a blended basis.
Every tier of o4-mini
Blended at 3:1 input to output. The last column compares each against the standard tier.
| Source | ||||||||
|---|---|---|---|---|---|---|---|---|
| Standard Standard | o4-mini | OpenAI | $1.10 | $4.40 | $0.275 | $1.93 | Standard | ↗ |
| Standard | o4-mini | OpenRouter | $1.10 | $4.40 | $0.275 | $1.93 | Same | ↗ |
| Dated snapshot | o4-mini-2025-04-16 | OpenAI | $1.10 | $4.40 | $0.275 | $1.93 | Same | ↗ |
| High effort | o4-mini-high | OpenRouter | $1.10 | $4.40 | $0.275 | $1.93 | Same | ↗ |
| Batch | o4-mini:batch | OpenRouter | $0.550 | $2.20 | $0.138 | $0.963 | −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 (o4-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.
High effort variant
The vendor also lists a high effort variant of o4-mini, listed at the same price as standard. It is 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
One dated snapshot (o4-mini-2025-04-16) is 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.
Direct or through a reseller
Through OpenRouter, o4-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 | ||||||
|---|---|---|---|---|---|---|
| o4-mini This model | OpenAI | $1.10 | $4.40 | 200,000 | $1.93 | ↗ |
| o3-mini | OpenAI | $1.10 | $4.40 | 200,000 | $1.93 | ↗ |
| Claude Haiku 4.5 | Anthropic | $1.00 | $5.00 | 200,000 | $2.00 | ↗ |
| GPT-5.4 mini | OpenAI | $0.750 | $4.50 | 272,000 | $1.69 | ↗ |
| Grok 4.3 | xAI | $1.25 | $2.50 | 1,000,000 | $1.56 | ↗ |
| Grok 4.20 | xAI | $1.25 | $2.50 | 1,000,000 | $1.56 | ↗ |
| Mistral Large 4 | Mistral AI | $0.680 | $2.09 | 1,048,576 | $1.03 | ↗ |
| Mistral Large 4.0 | Mistral AI | $0.680 | $2.09 | 1,048,576 | $1.03 | ↗ |
| Llama 3.1 Nemotron 70B Instruct Hf | Together AI | $0.880 | $0.880 | 32,768 | $0.880 | ↗ |
Prices last checked: . Methodology
Questions
How much does o4-mini cost per million tokens?
$1.10 per million input tokens and $4.40 per million output tokens, with cached input at $0.275. At a 3:1 input to output mix that blends to $1.93. Checked 28 Oct 2026.
How much cheaper is o4-mini through the Batch API?
o4-mini:batch costs $0.550 in and $2.20 out per million tokens, 50% cheaper than standard, in exchange for asynchronous delivery.
What would o4-mini cost for a real workload?
A thousand requests a day at 2,000 input and 600 output tokens each comes to $145.20 a month on the standard tier, or $72.60 through batch.
What is the context window for o4-mini?
200,000 tokens of input, with up to 100,000 tokens of output.
o3-mini · Claude Haiku 4.5 · GPT-5.4 mini · Grok 4.3 · Grok 4.20 · All OpenAI models · Cost calculator