OpenAI o-series API pricing
OpenAI's earlier reasoning models. o1 shuts down on 23 October 2026 and the o3-2025-04-16 snapshot on 11 December 2026.
o4-mini
PreviousCapability score 145 on the Epoch Capabilities Index (range 144–147). Source: Epoch Capabilities Index by Epoch AI, CC BY 4.0, read 11 Nov 2026.
Previous generation. The current replacement is GPT-6 Luna at $0.10 / $0.50 per 1M tokens.
What it costs in practice
o4-mini at list prices, no batch discount.
| 1,000 chat replies1,500 tokens in and 300 out each | $2.97 |
|---|---|
| Summarising 100 long reports20,000 tokens in and 800 out each | $2.55 |
| A month of a coding agent400 tasks, 85% of input cached | $334 |
The coding-agent example assumes 85% of input is served from cache, typical for agents that resend the same context each step. Work out AI agent cost on o4-mini
Details
o4-miniChecked 13 Jun 2026 against OpenAI pricing .
Estimate your monthly cost
List prices, no batch discount
| Model | Input / output per 1M | Per month |
|---|---|---|
| o4-mini | $1.10 / $4.40 | $19.80 |
Type amounts like 500K, 25M or 2B.
Price o4-mini in: Token cost calculator · AI agent cost · Token counter
Cheapest in its class
No current general-purpose small and fast model from another family costs meaningfully less than o4-mini.
Compare o4-mini with
Side by side: prices, cached and batch rates, and the cost of the same workload.
Other OpenAI o-series versions
GPT-6 models reason natively; OpenAI points o-series users to them.
| Model | Input / 1M | Output / 1M | Cached input | Context | Released |
|---|---|---|---|---|---|
o3Shuts down 11 Dec |
$2.00 | $8.00 | $0.50 | 200K | 16 Apr 2025 |
o3 details
o3
Shuts down 11 Dec$2.00 / $8.00 per 1M tokenscached $0.50 · batch 50% off · 200K context · 100K max output
- OpenAI cut the price by 80% on 10 June 2025.
- The o3-2025-04-16 snapshot shuts down on 11 December 2026.
Newer option: GPT-6.1 Sol at $2.00 / $10.00. Checked 27 Sep 2026 against OpenAI pricing and OpenAI deprecations .
Compare o4-mini
No ready-made comparisons for this family yet.
Price history
All changesNo price changes recorded since we began tracking in June 2026.
Coming up
- OpenAI shuts down the o3-2025-04-16 snapshot. Source
Every upcoming shutdown and price change
Every dated price: price records · CSV. Cite as: AI Token Price, OpenAI o-series pricing, https://aitokenprice.com/pricing/o-series#price-history
OpenAI pricing rules
- Batch and Flex processing cost 50% less.
- For GPT-5.4 and later, prompts longer than 272K tokens are billed at 2× the input price and 1.5× the output price.
- Cached input is billed at a tenth of the input price on most models, and a twentieth on GPT-6.1 Sol.
Retired OpenAI o-series models
- Retired 23 Oct 2026o1 was $15.00 / $60.00 per 1M tokens. Shut down on 23 October 2026. Use GPT-6 Astra instead.
Questions
How much does o4-mini cost?
As of 13 Jun 2026, o4-mini costs $1.10 per million input tokens and $4.40 per million output tokens, and $0.275 per million cached input tokens. Batch requests cost 50% less. Prices checked 13 Jun 2026.
What is o4-mini's context window?
200K tokens, with up to 100K tokens of output.
Does o4-mini support prompt caching?
Yes. Repeated input read from the cache costs $0.275 per million tokens, 75% less than normal input.