OpenAI

o3

Launched 2025-04-16 · Knowledge up to 2024-05 · Retires 2026-12-11 · Listed on OpenRouter 2025-04-16

Prices updated . Benchmarks updated .

o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....

You send / 1M

$2.00

tokens in

It replies / 1M

$8.00

tokens out

Context

200K

tokens it can read at once

Typical request

$0.0066

1,000 words in, 400 out

Benchmarks

BenchmarkScoreKindDateSource
Epoch Capabilities Index146.9Independent2025-04-16Epoch AI
ARC-AGI-2High effort6.5%Independent2025-04-16ARC Prize, republished by Epoch AI
CritPtHigh effort1.4%Independent2025-04-16CritPt, republished by Epoch AI

Rankings on this site use the Epoch Capabilities Index, an independent composite. Lab-reported rows are the lab's own figures and are kept separate.

Data privacy

No training or retention: Providers do not train on your prompts, but they may keep them for a time.

Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.

What it can do

  • Reads: image, text, file, pdf
  • Writes: text
  • Weights: Closed
  • Reasoning: Yes
  • Tool calling: Yes
  • Longest reply: 100K tokens
  • Repeated text is billed at $0.500 per 1M (prompt caching)

Compare with

Appears in

Estimate your monthly cost with o3

Sources and licenses

  • OpenRouter: Prices, context windows, modalities and the model list come from the OpenRouter public API. Data: OpenRouter.
  • Vercel AI Gateway: The no-training flag comes from the Vercel AI Gateway model list.
  • models.dev: Lab launch dates, open-weights flags and knowledge cutoffs come from models.dev. Copyright (c) 2025 models.dev, MIT License.
  • Epoch AI: Independent benchmark scores and the Epoch Capabilities Index (ECI) come from Epoch AI's Benchmarking Hub, used under CC BY 4.0. Epoch AI, Capabilities & benchmarking, epoch.ai/benchmarks. Scores Epoch marks as external keep their original license, and the source is named on each score.
  • LMArena: Arena Elo (text, webdev and vision) comes from the LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset), CC BY 4.0, leaderboard date 2026-10-28.
  • Lab-reported scores, when an editor has added them, are the lab's own numbers. Each one links to the source and is labeled lab-reported. They are not used to rank the lists.
  • What a score measures: the benchmark guide.