openai/gpt-5.5
प्रकाशन तिथि: 2026-04-25
1,050,000 context · $5.00/M input tokens · $30.00/M output tokens
GPT-5.5 is OpenAI's frontier model released April 23, 2026, featuring a 1M+ token context window (922K input, 128K output) with text and image support. It scores 88.7% on SWE-bench Verified and 92.4% on MMLU with 60% fewer hallucinations than GPT-5.4, excelling at agentic coding, computer use, and deep research while matching GPT-5.4 per-token latency.
Pricing
Pay-per-use
No upfront costs, pay only for what you use
Try the model
API Usage
Use the following code examples to integrate with our API:
import OpenAI from 'openai';
if (!process.env.WAVESPEED_API_KEY) throw new Error('Set WAVESPEED_API_KEY');
const client = new OpenAI({
apiKey: process.env.WAVESPEED_API_KEY,
baseURL: 'https://llm.wavespeed.ai/v1',
timeout: 120_000,
maxRetries: 2,
});
try {
const response = await client.chat.completions.create({
model: 'openai/gpt-5.5',
messages: [{ role: 'user', content: 'Hello!' }],
});
console.log(response.choices[0]?.message?.content ?? '');
} catch (error) {
console.error('LLM request failed:', error);
process.exitCode = 1;
}import OpenAI from 'openai';
if (!process.env.WAVESPEED_API_KEY) throw new Error('Set WAVESPEED_API_KEY');
const client = new OpenAI({
apiKey: process.env.WAVESPEED_API_KEY,
baseURL: 'https://llm.wavespeed.ai/v1',
timeout: 120_000,
maxRetries: 2,
});
try {
const response = await client.chat.completions.create({
model: 'openai/gpt-5.5',
messages: [{ role: 'user', content: 'Hello!' }],
});
console.log(response.choices[0]?.message?.content ?? '');
} catch (error) {
console.error('LLM request failed:', error);
process.exitCode = 1;
}Model Introduction
OpenAI GPT-5.5
GPT-5.5 is OpenAI's frontier model released on April 23, 2026, designed for complex professional workloads including agentic coding, computer use, and deep research. Building on GPT-5.4, it delivers stronger reasoning, higher reliability with 60% fewer hallucinations, and improved token efficiency — matching GPT-5.4 per-token latency while performing at a significantly higher level of intelligence. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs.
Why It Looks Great
- Frontier-class reasoning with 88.7% SWE-bench Verified and 92.4% MMLU scores
- 1M token context window for large-scale reasoning, coding, and multimodal workflows
- 60% fewer hallucinations compared to GPT-5.4 with improved token efficiency
- Three variants: standard, Thinking (extended reasoning), and Pro (highest accuracy)
- Same per-token latency as GPT-5.4 despite the intelligence leap
Key Features
- Context Window: 1050000 tokens
- Max Input: 922000 tokens
- Max Output: 128000 tokens
- Vision: Supported
- Function Calling: Supported
- Thinking Mode: Supported (low / medium / high / xhigh effort levels)
- Variants: GPT-5.5, GPT-5.5 Thinking, GPT-5.5 Pro
Benchmarks
| Benchmark | GPT-5.4 | GPT-5.5 | Claude Opus 4.7 | Gemini 3.1 Pro |
|---|---|---|---|---|
| SWE-bench Verified | ~74% | 88.7% | 87.6% | 80.6% |
| MMLU | 91.1% | 92.4% | — | — |
| Terminal-Bench 2.0 | — | 82.7% | — | — |
| Expert-SWE | — | 73.1% | — | — |
| GDPval (44 occupations) | — | 84.9% | — | — |
| OSWorld-Verified | — | 78.7% | — | — |
| Hallucination rate | baseline | −60% | — | — |
Specifications
| Specification | Value |
|---|---|
| Provider | OpenAI |
| Model Type | Large Language Model (LLM) |
| Architecture | Transformer (Frontier) |
| Context Window | 1050000 tokens |
| Max Input | 922000 tokens |
| Max Output | 128000 tokens |
| Input | Text, Image |
| Output | Text |
| Vision | Supported |
| Function Calling | Supported |
| Thinking Mode | Supported |
| Release Date | April 23, 2026 |
Note: GPT-5.5 is 2× GPT-5.4 at the token level, but uses significantly fewer tokens to complete the same tasks. Independent testing puts the net cost increase at roughly 20% once token efficiency is factored in.
How to Use
- Write your prompt — describe the task, provide context, and specify desired output format.
- Submit — the model processes your request and returns the response.
API Integration
Base URL: https://llm.wavespeed.ai/v1 API Endpoint: chat/completions Model ID: openai/gpt-5.5
API Usage
Python SDK
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://llm.wavespeed.ai/v1"
)
response = client.chat.completions.create(
model="openai/gpt-5.5",
messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)cURL
curl https://llm.wavespeed.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "openai/gpt-5.5",
"messages": [{"role": "user", "content": "Hello!"}]
}'What's New vs GPT-5.4
| Aspect | GPT-5.4 | GPT-5.5 |
|---|---|---|
| SWE-bench Verified | ~74% | 88.7% |
| MMLU | 91.1% | 92.4% |
| Hallucination rate | baseline | −60% |
| Context window | 1.05M | 1.05M (922K input) |
| API input price | $2.50/M | $5.00/M |
| API output price | $15.00/M | $30.00/M |
| Computer use | Improving | Production-grade |
| Multi-step tool chains | Single-shot preferred | Full autonomous loops |
| Token efficiency | baseline | ~40% fewer tokens on same tasks |
Info
Supported Functionality
API Access Guide
GPT 5.5 API
openai/gpt-5.5
GPT-5.5 is OpenAI's frontier model released April 23, 2026, featuring a 1M+ token context window (922K input, 128K output) with text and image support. It scores 88.7% on SWE-bench Verified and 92.4% on MMLU with 60% fewer hallucinations than GPT-5.4, excelling at agentic coding, computer use, and deep research while matching GPT-5.4 per-token latency.
Input
$5 /M
Output
$30 /M
Context
1050K
Max Output
128K
Vision
Supported
Tool Use
Supported
Try GPT 5.5 on WaveSpeedAI
Access GPT 5.5 through our unified API — OpenAI-compatible, no cold starts, transparent pricing.
Frequently Asked Questions about GPT 5.5
How much does GPT 5.5 cost via the API?+
Pricing on WaveSpeedAI: $5.00 per million input tokens and $30.00 per million output tokens. Prompt caching and batch processing are billed separately and reduce effective cost on long, repetitive workloads.
What is the context window of GPT 5.5?+
GPT 5.5 supports up to 1050K tokens of context with up to 128K tokens of output per request.
Is GPT 5.5 OpenAI-compatible?+
WaveSpeedAI exposes GPT 5.5 at https://llm.wavespeed.ai/v1 through the OpenAI-compatible Chat Completions interface. Most OpenAI SDK clients work by changing the base URL and API key; optional fields depend on the selected model.
How do I get started with GPT 5.5?+
Sign in to WaveSpeedAI, create an API key in Access Keys, then send a request to https://llm.wavespeed.ai/v1/chat/completions with the model id shown above. Check the current model catalog for availability, capabilities, and pricing.