openai/gpt-5.5-2026-04-23

openai/gpt-5.5-2026-04-23
VisionToolsJSONReasoning
by openai

OpenAI GPT-5.5 (2026-04-23): 128K output tokens, multimodal input, τ²-Bench 93.9

Max output128K
Inputfile + image + text
p50 TTFT10.00 s
INPUT$5.00/ 1M tokens
OUTPUT$30.00/ 1M tokens
p50 TTFT10.00 s7d
p95 TTFT10.00 s7d
TRAFFIC75.8Mtokens / 7d

openai/gpt-5.5-2026-04-23 is a language model trained by OpenAI and offered through OrcaRouter. It accepts file, image, and text inputs and can generate up to 128,000 tokens in a single completion.…

What is openai/gpt-5.5-2026-04-23 and who is it for?

What input modalities does the model support?

How does the 128,000 output token limit impact usage?

Code samples

Call from any SDK

OpenAI-compatible — keep the SDK you already use

  • OpenAI SDKhttps://api.orcarouter.ai/v1
import os

from openai import OpenAI

client = OpenAI(
    base_url="https://api.orcarouter.ai/v1",
    api_key=os.environ["ORCAROUTER_API_KEY"],
)

response = client.chat.completions.create(
    model="openai/gpt-5.5-2026-04-23",
    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
10.00 s
Output speed
3885 tok/s
p95 TTFT
10.00 s
Error rate
2.3%

Public benchmarks

74.9
AA Coding
Better than 91% of models compared
#12 of 138
38.6
AA Intelligence
Better than 79% of models compared
#28 of 141
GPQA Diamond
93.5
Humanity's Last Exam
45.8
IFBench
75.9
Long-Context Recall
84.3
SciCode
55.8
tau_banking
39.0
TerminalBench Hard
60.6
terminalbench_v2_1
84.3
τ²-Bench
93.9
Source: artificialanalysis.ai

Community buzz

What developers are saying this week

Hacker News0 mentions · 7d

How it compares

openai/gpt-5.5-2026-04-23GPT-5.2 ProGPT-5.4 ProGPT-5.5
Input $/M$5.00$21.00$60.00$5.00
Output $/M$30.00$168.00$270.00$30.00
Context400K1.1M
Quality5/1010/1010/1010/10
Compare side-by-sideCompare side-by-sideCompare side-by-sideCompare side-by-side

FAQ

What is the cost to use openai/gpt-5.5-2026-04-23 on OrcaRouter?
Pricing is per-token for both input and output, with rates available on OrcaRouter's pricing page. Exact numbers are not provided here, but costs increase with longer outputs. Caching may reduce costs for repeated queries.
What is the maximum context window for input?
The input context window size is not specified for this model. Only the maximum output of 128,000 tokens is provided. Input tokens are consumed according to the total text, image, and file sizes.
What are the main strengths of this model?
Key strengths include a 128,000-token output limit, multimodal input support (file, image, text), and a high τ²-Bench score of 93.9 indicating strong long-context reasoning.
How does it compare to older OpenAI models like GPT-4?
This model offers a much larger output limit (128K vs GPT-4's 4,096 or 8,192) and supports file input in addition to text and images. It likely outperforms GPT-4 on long-context benchmarks.
Does OrcaRouter store my data when using this model?
OrcaRouter's data handling policies are not detailed here. Generally, API providers may log requests for monitoring. Check OrcaRouter's privacy policy and terms for specifics on data retention.
How do I call this model via an OpenAI-compatible API?
Use base URL https://api.orcarouter.ai/v1, model ID "openai/gpt-5.5-2026-04-23". Standard chat completions parameters apply. Include API key in headers.
Can I use this model for real-time chat applications?
Yes, but consider latency. Generating long outputs (up to 128K tokens) will take time. Use streaming and set reasonable max_tokens to improve responsiveness.
What benchmarks does this model excel on?
The only benchmark provided is τ²-Bench with a score of 93.9. It indicates strong performance on long-context reasoning.

Embed this badge

openai/gpt-5.5-2026-04-23$5.00/M in10000ms p50via OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/openai/gpt-5.5-2026-04-23" target="_blank"> <img src="https://www.orcarouter.ai/embed/openai/gpt-5.5-2026-04-23.svg" alt="openai/gpt-5.5-2026-04-23 on OrcaRouter" /> </a>
Markdown [![openai/gpt-5.5-2026-04-23](https://www.orcarouter.ai/embed/openai/gpt-5.5-2026-04-23.svg)](https://www.orcarouter.ai/models/openai/gpt-5.5-2026-04-23)

Model card as data

GET /api/public/models/openai/gpt-5.5-2026-04-23Open
Machine-readable:/llms.txt/llms-full.txt