CrossModel
GPT-5.5 Pro
openai/gpt-5.5-pro
Back to model catalog

OpenAI · Model guide

GPT-5.5 Pro

Compare
openai/gpt-5.5-pro

GPT-5.5 Pro spends more compute to produce smarter and more precise answers on difficult problems. It supports only medium-to-xhigh reasoning, may take several minutes, and is best used through background Responses workflows when latency is secondary to answer quality.

Modalities
TextImageText
Context
1M
Max output
128K
Price / 1M tokens
$ 30.00in$ 180.00out
StreamingTool callingJSON outputImage inputThinking mode

What this model is good at

What the vendor positions it for, and which of our models to reach for instead.

VendorA higher-compute GPT-5.5 variant for the toughest, accuracy-first work.source

Best for

  • Difficult research and analysis · Uses more compute to think harder and improve answer precision.(vendor claim)source

  • High-stakes knowledge work · Designed for tough problems where latency is less important than a stronger final answer.(vendor claim)source

Neighbouring models
  • openai/gpt-5.5faster —Use the standard model when streaming, latency or cost matters.
  • openai/gpt-5.6-solsuccessor —Use GPT-5.6 Sol for the newer flagship and optional Pro execution mode.
Compare them side by side →

Pricing and billing

Tiered pricing: the rate changes once the input passes the threshold.

Price / 1M tokens by input sizeInput < 272.0KInput ≥ 272.0K
Input$ 30.00$ 60.00
Output$ 180.00$ 270.00
Cache read$ 30.00$ 60.00
Cache write$ 30.00$ 60.00
Estimate a request

At this input size you are on the Input < 272.0K tier.

$ 0.6600
Estimated cost per request
10.0K × $ 30.00
+ 2.0K × $ 180.00
≈ $ 660.00 per 1,000 requests

Capabilities and limits

What CrossModel guarantees across every route this model can take right now.

Context window
1.1M tokens
Max output
128.0K tokens
Input / output modalities
Text + Image → Text
Streaming
Not supported
Tool calling
Supported
Structured output (JSON)
Supported
Image input
Supported
Thinking mode
Supported· always on
Reasoning effort
medium · high · xhigh
Available endpoints
/v1/chat/completions · /v1/responses · /v1/messages
First-party sources:Specsdevelopers.openai.comCapabilitiesdevelopers.openai.com

Published benchmarks

Scores the vendor reported, with the evaluation setup each one came from.

Agentic search
  • BrowseComp (with tools)
    accuracy·OpenAI · 2026-04-23effort xhighsetup not fully disclosed
    90.1%
Knowledge work
  • GDPval (wins or ties)
    wins_or_ties·OpenAI · 2026-04-23effort xhighsetup not fully disclosed
    82.3%
Math reasoning
  • FrontierMath Tier 4
    accuracy·OpenAI · 2026-04-23effort xhighsetup not fully disclosed
    39.6%
Reasoning
  • Humanity's Last Exam Full (with tools)
    accuracy·OpenAI · 2026-04-23effort xhighsetup not fully disclosed
    57.2%
Scientific reasoning
  • GeneBench
    accuracy·OpenAI · 2026-04-23effort xhighsetup not fully disclosed
    33.2%

Vendor-reported numbers, not CrossModel measurements. Scores are only comparable when the benchmark version, metric and evaluation setup match, so nothing here is averaged or ranked.

Use it in your tools

Point the base URL at CrossModel and paste this model ID — every tool below has a setup guide.

Claude Code
Anthropic's official command-line coding assistant
Cursor
AI-first code editor
Cline
Open-source AI coding agent for VS Code
Codex
OpenAI's coding agent for ChatGPT desktop and the terminal
OpenCode
Open-source terminal coding assistant
Zed
High-performance, AI-native code editor
Open WebUI
Open-source, self-hosted AI chat interface
Continue
Open-source AI coding assistant for VS Code & JetBrains
See all integration guides →

Frequently asked questions

What is GPT-5.5 Pro?
GPT-5.5 Pro is available on CrossModel as openai/gpt-5.5-pro. It has a 1M-token context window and can return up to 128K tokens per request.
How much does GPT-5.5 Pro cost?
Currently $ 30.00 per 1M input tokens and $ 180.00 per 1M output tokens. Cached input is billed at $ 30.00 per 1M.
Does GPT-5.5 Pro support tool calling and structured output?
Tool calling: Supported · Structured output (JSON): Supported · Image input: Supported · Streaming: Not supported · Thinking mode: Supported
Which endpoint do I call?
For text models, OpenAI Chat Completions (/v1/chat/completions), OpenAI Responses (/v1/responses) and Anthropic Messages (/v1/messages) all work — pick whichever your SDK already speaks.
Can I try it without writing code?
Yes. Sign in and open the Playground on this page to chat with the model directly — no API key needed. Usage is billed from your wallet at the normal rate.

Chat first, integrate later

Chat first, then wire it in once you like the answers.