# Launching o3-mini in the API **URL:** \ **Category:** Announcements\ **Created:** [January 31, 2025, 7:38pm UTC](https://community.openai.com/t/launching-o3-mini-in-the-api/1109387 "2025-01-31T19:38:51Z")\ **Posts on this page:** 20\ **Page:** 1
**Author:** ![nikunj](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/nikunj/32/222621_2.png) [@nikunj](https://community.openai.com/u/nikunj)\ **Post date:** [January 31, 2025, 7:38pm UTC](https://community.openai.com/t/launching-o3-mini-in-the-api/1109387/1 "2025-01-31T19:38:51Z")
Today we’re releasing the latest model in our reasoning series, OpenAI o3-mini, and you can start using it now in the API. o3-mini can outperform o1 in coding and other reasoning tasks, and is 93% cheaper and has lower latency. It supports function calling, Structured Outputs, streaming, and developer messages. You can also choose between three reasoning effort options—low, medium, and high—to optimize for your specific use cases. This flexibility allows o3-mini to “think harder” when tackling complex challenges or to prioritize speed. In addition to the Chat Completions API, you can use o3-mini in the Assistants API and Batch API today. Similar to o1, o3-mini comes with a larger context window of 200,000 tokens and a max output of 100,000 tokens. o3-mini is our first small reasoning model that supports these developer features out of the gate, making it production-ready today. Keep in mind that prompting our reasoning models differs from our GPT-series, so [we’ve created a guide](https://platform.openai.com/docs/guides/reasoning#advice-on-prompting) to help you get the best results. With its cost efficiency and speed, we’re excited to see how you integrate o3-mini, particularly in agentic and coding use cases. Get started with our docs: [https://platform.openai.com/docs/models#o3-mini](https://platform.openai.com/docs/models#o3-mini) ---
**Author:** ![sps](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/sps/32/7736_2.png) [@sps](https://community.openai.com/u/sps)\ **Post date:** [January 31, 2025, 7:39pm UTC](https://community.openai.com/t/launching-o3-mini-in-the-api/1109387/2 "2025-01-31T19:39:48Z")
---
**Author:** ![excelformulabot.com](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/excelformulabot.com/32/11306_2.png) [@excelformulabot.com](https://community.openai.com/u/excelformulabot.com)\ **Post date:** [January 31, 2025, 7:53pm UTC](https://community.openai.com/t/launching-o3-mini-in-the-api/1109387/5 "2025-01-31T19:53:25Z")
Will assistant api tools be able to be enabled with the reasoning models? Currently, they’re not. ---
**Author:** ![jim](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/jim/32/1976_2.png) [@jim](https://community.openai.com/u/jim)\ **Post date:** [January 31, 2025, 8:02pm UTC](https://community.openai.com/t/launching-o3-mini-in-the-api/1109387/6 "2025-01-31T20:02:51Z")
They do in the Playground…but having issues locally trying to get it to work with the Assistants API (blog post says yes). ---
**Author:** ![excelformulabot.com](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/excelformulabot.com/32/11306_2.png) [@excelformulabot.com](https://community.openai.com/u/excelformulabot.com)\ **Post date:** [January 31, 2025, 8:12pm UTC](https://community.openai.com/t/launching-o3-mini-in-the-api/1109387/8 "2025-01-31T20:12:27Z")
Do you have tools enabled? The playground doesn’t let you run the API with reasoning models and tools enabled. ---
**Author:** ![jim](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/jim/32/1976_2.png) [@jim](https://community.openai.com/u/jim)\ **Post date:** [January 31, 2025, 8:14pm UTC](https://community.openai.com/t/launching-o3-mini-in-the-api/1109387/9 "2025-01-31T20:14:29Z")
It did for me…I was able to get a run through on Assistants with o3-mini-2025-01-31 selected in the Playground, with several tools on it. One run came back (quick!) with no tool calls needed (wasn’t needed). Specifically wrote a response that I knew triggers one of my tools (without naming directly), and it called the tool perfectly in the Playground (quick as well!). Was able to get a local ChatCompletion to work with same model. For some reason, it keeps failing for Assistants API local - same id as above - but I’m sure that’s something I have setup that is contradictory to running o3 through Assistants, just not sure what it is quite yet. ---
**Author:** ![kunal1](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/kunal1/32/512568_2.png) [@kunal1](https://community.openai.com/u/kunal1)\ **Post date:** [January 31, 2025, 9:35pm UTC](https://community.openai.com/t/launching-o3-mini-in-the-api/1109387/10 "2025-01-31T21:35:13Z")
Is reasoning\_effort currently supported for o3-mini in the API? ---
**Author:** ![musaev.haybulla](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/musaev.haybulla/32/546320_2.png) [@musaev.haybulla](https://community.openai.com/u/musaev.haybulla)\ **Post date:** [January 31, 2025, 10:25pm UTC](https://community.openai.com/t/launching-o3-mini-in-the-api/1109387/11 "2025-01-31T22:25:00Z")
Hi everyone, I’ve noticed that in the web version there are two O3 models: one labeled “high” and another without any prefix. However, the release notes mention three versions: low, medium, and high. Could someone clarify which version is used in the interface—is it O3-low or O3-medium? Thanks in advance! ---
**Author:** ![VeitB](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/veitb/32/712987_2.png) [@VeitB](https://community.openai.com/u/VeitB)\ **Post date:** [January 31, 2025, 10:27pm UTC](https://community.openai.com/t/launching-o3-mini-in-the-api/1109387/12 "2025-01-31T22:27:07Z")
Yes, it is. You can choose between low, mid and high. The differences are highlighted in the official announcement: [https://openai.com/index/openai-o3-mini/](https://openai.com/index/openai-o3-mini/) ---
**Author:** ![ericatdropzone](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/ericatdropzone/32/250081_2.png) [@ericatdropzone](https://community.openai.com/u/ericatdropzone)\ **Post date:** [January 31, 2025, 10:29pm UTC](https://community.openai.com/t/launching-o3-mini-in-the-api/1109387/13 "2025-01-31T22:29:14Z")
Does it also use o200k\_base for encoding? ---
**Author:** ![musaev.haybulla](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/musaev.haybulla/32/546320_2.png) [@musaev.haybulla](https://community.openai.com/u/musaev.haybulla)\ **Post date:** [January 31, 2025, 10:51pm UTC](https://community.openai.com/t/launching-o3-mini-in-the-api/1109387/14 "2025-01-31T22:51:43Z")
![2025-02-01_02-49-41](https://us1.discourse-cdn.com/openai1/original/4X/6/d/c/6dcfbdd881327da19e0b341f095c18889657ee64.png) My question about that ---
**Author:** ![VeitB](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/veitb/32/712987_2.png) [@VeitB](https://community.openai.com/u/VeitB)\ **Post date:** [January 31, 2025, 11:09pm UTC](https://community.openai.com/t/launching-o3-mini-in-the-api/1109387/15 "2025-01-31T23:09:17Z")
I replied to @kunal1 who asked about the API. I don’t know what the choices in ChatGPT mean, either. ---
**Author:** ![musaev.haybulla](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/musaev.haybulla/32/546320_2.png) [@musaev.haybulla](https://community.openai.com/u/musaev.haybulla)\ **Post date:** [January 31, 2025, 11:10pm UTC](https://community.openai.com/t/launching-o3-mini-in-the-api/1109387/16 "2025-01-31T23:10:30Z")
i’m ssory, my mistake. Wait answer from DevTeam ---
**Author:** ![\_j](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/_j/32/766292_2.png) [@\_j](https://community.openai.com/u/_j)\ **Post date:** [January 31, 2025, 11:34pm UTC](https://community.openai.com/t/launching-o3-mini-in-the-api/1109387/17 "2025-01-31T23:34:18Z")
> [@nikunj](#): > > It supports function calling, Structured Outputs, streaming, … No “thinking” metadata in the streaming, for progress and keep-alive? Is this just not to be included as a feature, or is it still a possibility? (like ChatGPT). * * * **Bonus** : Check “Data Controls → Sharing” in your API organization “profile”. ![image](https://us1.discourse-cdn.com/openai1/original/4X/7/2/b/72b60f9e06089edf38ece51c554a010ff11689a9.png) The o3-mini model is now included. (Sharing may benefit API specialist applications in the future, perhaps a source of RLHF with a different pattern than “I’m ChatGPT”, but one wonders if the models being unsuccessful is also of use.) ---
**Author:** ![edwinarbus](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/edwinarbus/32/455108_2.png) [@edwinarbus](https://community.openai.com/u/edwinarbus)\ **Post date:** [January 31, 2025, 11:50pm UTC](https://community.openai.com/t/launching-o3-mini-in-the-api/1109387/18 "2025-01-31T23:50:10Z")
o3-mini defaults to “medium” in ChatGPT and the API ---
**Author:** ![musaev.haybulla](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/musaev.haybulla/32/546320_2.png) [@musaev.haybulla](https://community.openai.com/u/musaev.haybulla)\ **Post date:** [February 1, 2025, 12:05am UTC](https://community.openai.com/t/launching-o3-mini-in-the-api/1109387/19 "2025-02-01T00:05:18Z")
Thanx for you answer! As I understand it, the usage limits within the Plus plan are specified in total for both models – the medium and the high one? Or is there a separate limit for each model? Thank you. ---
**Author:** ![edwinarbus](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/edwinarbus/32/455108_2.png) [@edwinarbus](https://community.openai.com/u/edwinarbus)\ **Post date:** [February 1, 2025, 12:40am UTC](https://community.openai.com/t/launching-o3-mini-in-the-api/1109387/20 "2025-02-01T00:40:06Z")
Ah, are you referring to the ChatGPT Plus plan? This post and forum are about the API and developing with the `o3-mini` model on the OpenAI Platform, so I don’t have an immediate answer— but I believe it’s the same as o1, 50 messages/a week. Sorry to redirect you, but you can get in touch with the ChatGPT support team and refer to the ChatGPT Help Center here: [https://help.openai.com/en/?q=contact](https://help.openai.com/en/?q=contact). ---
**Author:** ![angeldemirev](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/angeldemirev/32/546357_2.png) [@angeldemirev](https://community.openai.com/u/angeldemirev)\ **Post date:** [February 1, 2025, 12:44am UTC](https://community.openai.com/t/launching-o3-mini-in-the-api/1109387/21 "2025-02-01T00:44:26Z")
How soon after becoming a tier-3 organization does o3-mini become available? I hit tier-3 this morning (~6 hours ago) but still see ```auto {'error': {'message': 'The model `o3-mini` does not exist or you do not have access to it.', 'type': 'invalid_request_error', 'param': None, 'code': 'model_not_found'}} ``` ---
**Author:** ![hatchling](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/hatchling/32/511699_2.png) [@hatchling](https://community.openai.com/u/hatchling)\ **Post date:** [February 1, 2025, 12:59am UTC](https://community.openai.com/t/launching-o3-mini-in-the-api/1109387/22 "2025-02-01T00:59:01Z")
I used o3 mini today to write a prompt for o3 mini-high to write a Python app using flask to search patents. I should say rewrite, 45 seconds roughly. It was fast enough I could hardly scroll to keep up with it. If anyone wants to see what it did in 45 seconds. I made a video but apparently we cant post links here (understandable). My mind is blown, I can’t wait to deep dive! ---
**Author:** ![vet.xwz](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/vet.xwz/32/512255_2.png) [@vet.xwz](https://community.openai.com/u/vet.xwz)\ **Post date:** [February 1, 2025, 1:39am UTC](https://community.openai.com/t/launching-o3-mini-in-the-api/1109387/23 "2025-02-01T01:39:49Z")
Same issue, I’m also tier3 and can’t acces through the API [Next page](https://community.openai.com/t/launching-o3-mini-in-the-api/1109387.md?page=2)