GPT-5.5

openai/gpt-5.5
VisionToolsJSONReasoning
by OpenAI · 2026-04-24

GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...

Max output128K
Inputfile + image + text
p50 TTFT7.99 s
INPUT$5.00/ 1M tokens
OUTPUT$30.00/ 1M tokens
p50 TTFT7.99 s7d
p95 TTFT10.00 s7d
TRAFFIC58.1Mtokens / 7d

GPT-5.5 is a language model from OpenAI designed for extended output and multimodal input. It accepts files, images, and text, and can generate up to 128,000 tokens in a single completion. This large…

What is OpenAI's GPT-5.5?

Who should use GPT-5.5?

What input types does GPT-5.5 accept?

How large can GPT-5.5's output be?

Code samples

Call from any SDK

OpenAI-compatible — keep the SDK you already use

  • OpenAI SDKhttps://api.orcarouter.ai/v1
from openai import OpenAI

client = OpenAI(
    base_url="https://api.orcarouter.ai/v1",
    api_key="$ORCAROUTER_API_KEY",
)

response = client.chat.completions.create(
    model="openai/gpt-5.5",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Supported parameters

  • include_reasoning
  • max_completion_tokens
  • max_tokens
  • reasoning
  • response_format
  • seed
  • stream
  • structured_outputs
  • tool_choice
  • tools

Pricing

TierInput / 1M tokensOutput / 1M tokensCache read / 1M
272K$5.00$30.00$0.500
$10.00$45.00$1.00
Tier selected by input token count of each request

Cost calculator

Tokens / month10MM
Input share70%%
Estimated / month $125 · With prompt caching $109

Estimate based on list price

Tiered pricing — this estimate uses base-tier rates.

Token & cost estimator

Input tokens: 20Cost per request: $0.0151

Estimate only — actual token counts depend on the provider's tokenizer.

Performance

p50 TTFT
7.99 s
Output speed
367 tok/s
p95 TTFT
10.00 s
Error rate
0.10%

Public benchmarks

64.7
AA Coding
Better than 93% of models compared
#7 of 106
62.7
AA Intelligence
Better than 90% of models compared
#11 of 110
63.7
AA Math
Better than 53% of models compared
#38 of 81
GPQA Diamond
61.7 index
Humanity's Last Exam
44.3
IFBench
75.9
Long-Context Recall
74.3
MMLU-Pro
70.7 index
SciCode
56.1
TerminalBench Hard
60.6
τ²-Bench
56.7 index
Source: artificialanalysis.ai

How it compares

GPT-5.5GPT-5.2 ProGPT-5.4 ProGPT-5.5 Pro
Input $/M$5.00$21.00$60.00$30.00
Output $/M$30.00$168.00$270.00$180.00
Context400K1.1M
Quality10/1010/1010/1010/10
Compare side-by-sideCompare side-by-sideCompare side-by-sideCompare side-by-side

FAQ

What is the cost of using GPT-5.5 on OrcaRouter?
Pricing details are not provided in the available information. OrcaRouter typically charges per token for input and output, with additional fees for processing images and files. Contact OrcaRouter directly for current rates.
What is the context window of GPT-5.5?
The provided data does not specify the input context window size. The maximum output is 128,000 tokens. The total context (input + output) may be larger, but this is not confirmed. Check OrcaRouter documentation or test with your own prompts.
What are GPT-5.5's main strengths?
Based on available data, GPT-5.5 excels at generating very long outputs (128k tokens), processing multimodal inputs (file, image, text), and achieving a high score (93.9) on the τ²-Bench agentic benchmark.
How does GPT-5.5 compare to OpenAI's GPT-4o?
The provided data does not include a direct comparison. GPT-5.5 has a larger output limit (128k vs. GPT-4o’s 4k or 8k standard output) and multimodal input. The τ²-Bench score is available for GPT-5.5 but not for GPT-4o from these facts.
What data does OrcaRouter retain from GPT-5.5 API calls?
Data handling policies are not included in the provided information. You should review OrcaRouter’s privacy policy and terms of service to understand data retention, encryption, and whether inputs are used for model training.
Can I call GPT-5.5 using the OpenAI Python library?
Yes. OrcaRouter’s API is OpenAI-compatible. Set the base URL to https://api.orcarouter.ai/v1 and use the model ID "openai/gpt-5.5". The standard openai Python library works with these changes.
What client libraries are supported for GPT-5.5?
Any client that supports the OpenAI Chat Completion API format (Python, Node.js, Go, Rust, etc.) can be used by changing the base URL and API key to OrcaRouter’s endpoints.
Is GPT-5.5 available in different geographical regions?
The provided data does not specify regional availability. OrcaRouter may serve requests globally or in specific regions. Contact OrcaRouter for details on latency and compliance with regional data regulations.
What is the τ²-Bench benchmark measuring?
τ²-Bench evaluates an AI agent’s ability to use tools, follow multi-step instructions, and recover from errors. A score of 93.9 indicates that GPT-5.5 performs highly on this specific test suite.
Does GPT-5.5 support function calling?
Since OrcaRouter exposes an OpenAI-compatible API, function/tool calling is likely supported if the underlying model has that capability. The provided data does not confirm this; test with a simple function call against the endpoint.

Embed this badge

OpenAI: GPT-5.5$5.00/M in7988ms p50via OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/openai/gpt-5.5" target="_blank"> <img src="https://www.orcarouter.ai/embed/openai/gpt-5.5.svg" alt="OpenAI: GPT-5.5 on OrcaRouter" /> </a>
Markdown [![OpenAI: GPT-5.5](https://www.orcarouter.ai/embed/openai/gpt-5.5.svg)](https://www.orcarouter.ai/models/openai/gpt-5.5)

Model card as data

GET /api/public/models/openai/gpt-5.5Open
Machine-readable:/llms.txt/llms-full.txt