Skip to main content

GPT-5.5

OpenAI's flagship model for autonomous, multi-step agentic work.

GPT-5.5 specifications

ProviderOpenAI
Context window400,000 tokens (400K)
Input price$5.00 / 1M tokens
Output price$30.00 / 1M tokens
InputsText, Images
Reasoning modeYes
Vision (image input)Yes
Tool / function callingYes
Native real-time webNo
Open-weightNo
ReleasedApril 2026

Pricing & context web-verified June 2026 confirm on OpenAI's pricing page. Prompts over 272K input tokens bill at a higher tier.

What GPT-5.5 is best for

  • Agentic, multi-step workflows
  • Computer use and tool orchestration
  • Document and image understanding
  • Production coding

How to prompt GPT-5.5

  • Give it a goal and a set of tools, then let it plan and self-verify rather than scripting every step.
  • Use JSON mode / structured outputs when you need machine-readable results.
  • Front-load instructions before long context — it follows directions placed first more reliably.
  • Prompts over 272K input tokens hit a higher price tier; trim context where you can.

Work with GPT-5.5

Frequently asked questions

What is GPT-5.5's context window?

GPT-5.5 has a 400,000-token context window (about 400K tokens) — the maximum amount of text it can consider at once.

How much does GPT-5.5 cost?

Via the OpenAI API, GPT-5.5 costs $5.00 per 1M input tokens and $30.00 per 1M output tokens (web-verified June 2026). Output tokens cost more, so the length of the model's reply usually drives the bill.

Is GPT-5.5 multimodal?

Yes — GPT-5.5 accepts Text, Images as input, not just text.

Is GPT-5.5 open-weight?

No — GPT-5.5 is available only through the OpenAI API, not as downloadable weights.