o1

Provider: OpenAI US

No longer listed on OpenRouter since 2026-10-28. The figures below are the last recorded values.
Input price
$15.00
/ 1M tokens
Output price
$60.00
/ 1M tokens
Cache price
$7.50
/ 1M tokens (read)
Context
200K tokens
Max output 100K tokens

Overview

OpenAI's o1 is a flagship model designed for demanding, complex multi-modal workloads. It offers advanced capabilities like vision and function-calling, alongside a substantial 200,000 token context window. This model targets applications requiring deep reasoning and high-fidelity output generation.

Strengths

  • Extensive 200,000 token context window for processing large amounts of information.
  • Supports vision capabilities for understanding and processing image inputs.
  • Robust function-calling and JSON mode for structured data interaction and tool use.
  • Capable of deep 'thinking' for complex problem-solving and reasoning tasks.
  • Generates exceptionally long responses, with a maximum output of 100,000 tokens.

Best use cases

  • In-depth analysis and summarization of very long documents or complex codebases.
  • Developing AI agents that interact with external tools using function calling.
  • Building applications requiring visual input understanding, like image analysis.
  • Generating comprehensive, structured reports or creative content with JSON mode.
  • Advanced reasoning tasks such as scientific research analysis or strategic planning.

Pricing position

Model o1 is positioned as OpenAI's premium offering, with an input price of $15/1M tokens and an output price of $60/1M tokens. This makes it significantly more expensive than OpenAI's cost-optimized models like GPT-4o-mini, which costs $0.15/M input and $0.6/M output. Compared to peers, o1 matches the input price of Claude Opus 4.1/4 but offers a more competitive output price ($60/M vs $75/M).

Caveats

The model does not offer a free tier, meaning all usage incurs costs from the outset. Its premium pricing of $15/M input and $60/M output means it may be cost-prohibitive for high-volume or simpler tasks where a cheaper model could suffice. Users should evaluate if the full suite of vision and extensive context is necessary to justify the cost.

Notes drafted by an LLM from the figures on this page (2026-05-21) and rewritten when the price changes.

Key facts

Max output
100K tokens
Tracked since
2026-05-08
Last updated
2026-10-28

Features

Image inputFunction callingJSON outputReasoning

Price history

  • 2026-10-28 No longer listed

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $4.50
1M (small app) 1 0.5 $45.00
10M (mid scale) 10 5 $450.00
100M (large) 100 50 $4500.00

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from OpenAI

Similar-priced models

Source: OpenRouter API