Model by OpenAI

o3

o3 is OpenAI's April 2025 reasoning model, and it is now deprecated, so it suits only code that still calls it.

Checked 2026-11-05

o3 is OpenAI's April 2025 reasoning model, and it is now deprecated, so it suits only code that still calls it. OpenRouter listed it on 16 April 2025 with a 200,000 token context, image and file input, at $2 per million input tokens and $8 per million output tokens on its cheapest route, as listed on 5 November 2026. OpenAI's own model page gives the same $2 and $8, adds $0.50 for cached input, and shows a second, unlabelled set of text prices at $1 and $4 that we could not explain, so confirm which applies to your account. The page lists up to 100,000 output tokens and a knowledge cutoff of 1 June 2024. Its status line says o3 is deprecated and succeeded by GPT-5, and the default snapshot is deprecated too. Because the cutoff is that old, it will not know recent library versions. We have not run it ourselves. We would not start new work on it; GPT-5.5 or a current Claude model is a better base, and you can compare costs in the pricing guides. Figures come from OpenAI's model page and OpenRouter's list.

Mentioned here

  • GPT-5.5

    GPT-5.5 is OpenAI's previous flagship, and it suits teams that pinned it for professional and agentic work and have not yet moved to the 6 series.

    • Closed

    OpenAI, 1.1M context, $5 in / 1M

  • GPT-5.4

    GPT-5.4 is an earlier OpenAI frontier model, and it suits teams already on the OpenAI API who need a very long context for coding and document work.

    • Closed

    OpenAI, 1.1M context, $2.50 in / 1M

  • GPT-6 Sol

    GPT-6 Sol is the middle model of OpenAI's GPT-6 family, released 2026-09-22.

    • Closed

    OpenAI, 1.1M context, $2 in / 1M

  • gpt-oss-120b

    gpt-oss-120b is OpenAI's open-weights model under Apache 2.0, a standard permissive licence, with a context of about 131,072 tokens.

    • Open weights

    OpenAI, 131K context, $0.15 in / 1M

  • OpenAI API

    OpenAI's API bills per token.

    • Model / inference API
    • OpenAI compatible

Questions

What is the context window of o3?

200,000 tokens, with up to 100,000 tokens of output.

How much does o3 cost?

$2 per million input tokens and $8 per million output tokens, checked 31 October 2026.

Can I run o3 on my own hardware?

No. The weights are not published, so you use it through the maker's API or a hosting provider.

Who makes o3?

OpenAI makes it, and released it on 16 April 2025.

Reviews

Loading reviews…

Write a review

Your rating

Up to 1000 characters. Stars alone are enough.

Where you can run it

Compare hosts

  • OpenRouter

    OpenRouter routes more than 600 models through one API key.

    • Model gateway (router)
    • OpenAI compatible

Similar

  • GPT-4.1

    GPT-4.1 is OpenAI's April 2025 non-reasoning model, built for instruction following and long-context code work, and it is now deprecated.

    • Closed

    OpenAI, 1M context, $2 in / 1M

  • gpt-oss-20b

    gpt-oss-20b is OpenAI's smaller open-weights model, suited to running a reasoning model on your own machine or paying very little through an API.

    • Open weights

    OpenAI, 131K context, $0.03 in / 1M

  • GPT-5.4 Nano

    GPT-5.4 Nano was OpenAI's cheapest GPT-5.4 model, built for speed-critical, high-volume jobs, and it is now deprecated.

    • Closed

    OpenAI, 400K context, $0.20 in / 1M

  • GPT-5.4 Mini

    GPT-5.4 Mini is OpenAI's smaller GPT-5.4 model, aimed at high-throughput coding and reasoning work where the full model costs too much.

    • Closed

    OpenAI, 400K context, $0.75 in / 1M

  • GPT-5.3-Codex

    GPT-5.3-Codex is OpenAI's agentic coding model from early 2026, and it now suits only teams that must keep an existing pipeline running.

    • Closed
    • Coding

    OpenAI, 400K context, $1.75 in / 1M