OpenAI · LLMs & Coding

o3

Catalog data · checked Nov 16, 2026

o3 is a language model from OpenAI, released in April 2025. It reads text, images and PDF files and writes text, with a context window of 200K tokens and up to 100K output tokens per answer. It costs $2 per million input tokens and $8 per million output tokens. That puts it in the upper price range: 72% of the 185 paid language models we track cost less.

Calculate my costCompare

Input price$2per 1M tokens
Output price$8per 1M tokens
Context window200Ktokens per request
Max output100Ktokens per answer
ReleasedApr 2025Apr 2025
Knowledge cutoffMay 2024training data ends
WeightsClosedAPI only

What it can do

  • Tool calling
  • Structured output
  • Reasoning mode
  • Image input
  • File input
  • Audio input
  • Video input
  • Image output
  • Audio output
  • Prompt caching

More prices

Cached input (read)$0.5 /1M

What it costs in practice

1,000 support replies1,000 chats with 800 input and 250 output tokens each$3.6
Summarize a 300-page reportabout 150,000 input tokens in one request, 2,000 tokens out$0.316
10,000 product descriptions300 input and 200 output tokens per text$22
One day of agentic codingabout 3M input and 150K output tokens across many calls$7.2

Calculated from the list prices above. Your bill depends on your real token counts. Use your own numbers →

Compare o3 with

Questions & answers

How much does o3 cost?

o3 costs $2 per 1 million input tokens and $8 per 1 million output tokens (USD, list price checked Nov 16, 2026).

How large is the context window of o3?

o3 can process up to 200,000 tokens per request and return up to 100,000 tokens. As a rule of thumb, 1,000 tokens are about 750 English words.

Does o3 support tool calling?

Yes. The API accepts tool (function) definitions and also supports structured JSON output.

Can o3 read images?

Yes, image input is supported, as well as file input (for example PDFs).