OpenAI · Model guide

GPT-5.5

Q: What is GPT-5.5?

GPT-5.5 is available on CrossModel as openai/gpt-5.5. It has a 1M-token context window and can return up to 128K tokens per request.

Q: How much does GPT-5.5 cost?

Currently $ 5.00 per 1M input tokens and $ 30.00 per 1M output tokens. Cached input is billed at $ 0.50 per 1M.

Q: Does GPT-5.5 support tool calling and structured output?

Tool calling: Supported · Structured output (JSON): Supported · Image input: Supported · Streaming: Supported · Thinking mode: Supported

Q: 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.

Q: 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.

Compare

openai/gpt-5.5

OpenAI's flagship, aimed at work that runs for a while rather than a single answer: code, research, documents and browsing in one session, with a 1.05M-token context and a five-step reasoning-effort dial. gpt-5.5-pro is the slower, higher-compute sibling.

Modalities

Context

Max output

128K

Price / 1M tokens

$ 5.00in$ 30.00out

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 frontier model for complex coding and professional work.source

Best for

Agentic coding · Designed for long-running coding and tool-driven workflows.(vendor claim)source
Professional knowledge work · Targets research, analysis, documents and spreadsheets.(vendor claim)source

Neighbouring models

openai/gpt-5.5-prostronger —Reach for Pro when a single answer must hold up without review.
openai/gpt-5.4-minicheaper —High-volume classification and extraction rarely need 5.5.

Compare them side by side →

Pricing and billing

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

Price / 1M tokens by input size	Input < 272.0K	Input ≥ 272.0K
Input	$ 5.00	$ 10.00
Output	$ 30.00	$ 45.00
Cache read	$ 0.50	$ 1.00
Cache write	$ 5.00	$ 10.00

Estimate a request

Input tokens10,000

Output tokens2,000

Cache hit rate0%

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

$ 0.1100

Estimated cost per request

10.0K × $ 5.00
+ 2.0K × $ 30.00

≈ $ 110.00 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: Supported
Tool calling: Supported
Structured output (JSON): Supported
Image input: Supported
Thinking mode: Supported· always on
Reasoning effort: none · low · 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 coding

Terminal-Bench 2.0
pass_rate·OpenAI · 2026-04-23effort xhighsetup not fully disclosed
82.7%

Agentic search

BrowseComp (with tools)
accuracy·OpenAI · 2026-04-23effort xhighsetup not fully disclosed
84.4%

Coding

SWE-Bench Pro (Public)
pass_rate·OpenAI · 2026-04-23effort xhighsetup not fully disclosed
OpenAI notes possible memorization on the public split; treat this score as an upper bound.
58.6%

Computer use

OSWorld-Verified
success_rate·OpenAI · 2026-04-23effort xhighsetup not fully disclosed
78.7%

Knowledge work

GDPval (wins or ties)
wins_or_ties·OpenAI · 2026-04-23effort xhighsetup not fully disclosed
84.9%

Long context

OpenAI MRCR v2 8-needle 512K–1M
accuracy·OpenAI · 2026-04-23effort xhighsetup not fully disclosed
74%

Multimodal reasoning

MMMU Pro (with tools)
accuracy·OpenAI · 2026-04-23effort xhighsetup not fully disclosed
83.2%

Reasoning

Humanity's Last Exam Full (with tools)
accuracy·OpenAI · 2026-04-23effort xhighsetup not fully disclosed
52.2%

Scientific reasoning

GPQA Diamond
accuracy·OpenAI · 2026-04-23effort xhighsetup not fully disclosed
93.6%

Tool use

Toolathlon
score·OpenAI · 2026-04-23effort xhighsetup not fully disclosed
55.6%

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?

GPT-5.5 is available on CrossModel as openai/gpt-5.5. It has a 1M-token context window and can return up to 128K tokens per request.

How much does GPT-5.5 cost?

Currently $ 5.00 per 1M input tokens and $ 30.00 per 1M output tokens. Cached input is billed at $ 0.50 per 1M.

Does GPT-5.5 support tool calling and structured output?

Tool calling: Supported · Structured output (JSON): Supported · Image input: Supported · Streaming: 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?