GPT-5.5 Pro overview
GPT-5.5 Pro by OpenAI
This isn't a patch on GPT-5.4. It thinks faster, uses fewer tokens, and keeps going when problems get messy.
GPT-5.5 Pro specs
- Model ID
openai/gpt-5.5-pro- Developer
- OpenAI
- Context window
- 1,050,000 tokens
- Max output
- 128,000 tokens
- Input
- Text
- Output
- Text
- API
- OpenAI-compatible, base URL
https://api.aimlapi.com/v1
What actually changed and why it matters
Every major GPT-5.x release before this one was a post-training improvement layered on top of the same underlying model. GPT-5.5 is different: OpenAI rebuilt the base from scratch, which is why the capability jumps feel qualitative, not incremental.
Token-efficient reasoning
GPT-5.5 completes the same tasks as GPT-5.4 using significantly fewer tokens. That means lower cost, lower latency, and longer productive agent runs before context limits bite.
Agentic coding at scale
Powers OpenAI's Codex tool. NVIDIA deployed it internally to over 10,000 employees and reported debugging cycles dropping from days to hours, with multi-week experiments finishing overnight.
Computer use + intent parsing
Better at understanding what you actually want, not just what you literally said. It can handle a messy, multi-part brief, build its own plan, and navigate ambiguity across real software environments.
Knowledge work breadth
Financial modeling, legal drafting, investment-banking tasks, data analysis, document creation, GDPval covers 44 occupations across 9 industries, and GPT-5.5 scores near the top of the public leaderboard.
Scientific research assist
OpenAI's chief research officer says GPT-5.5 shows meaningful gains in scientific and technical workflows. Early use cases include drug discovery pipelines and mathematical research under expert oversight.
Use cases
GPT-5.5 Pro is documented as suited to harder, higher-accuracy work, with especially strong performance in business, legal, education, and data science.
It is also described as strong for writing and debugging code, researching online, analyzing data, creating documents and spreadsheets, and operating software across tools until a task is finished.
OpenAI also positions it for complex, real-world work and advanced production workflows, including coding use cases, tool-heavy agents, grounded assistants, long-context retrieval, and product-spec-to-plan workflows.
A further documented fit is demanding decision-support work, such as legal review and financial modeling, where first-pass accuracy matters more than cost or latency.
Capabilities
- Function calling
- Streaming
- Structured outputs
- Reasoning
- Web search
GPT-5.5 Pro API pricing
| Usage | Price | Unit |
|---|---|---|
| Input | $31.74 | 1M tokens |
| Output | $190.44 | 1M tokens |
Prices from the AI/ML API price list, checked on Nov 4, 2026.
GPT-5.5 Pro vs other models: token prices
AI/ML API input and output rates for 5 models, per million tokens.
| Model | Input | Output |
|---|---|---|
| $31.74 | $190.44 | |
| $0.1 | $0.5 | |
| $1 | $5 | |
| $2 | $10 | |
| $2.12 | $10.58 |
How to use the GPT-5.5 Pro API
View docsBuild with your agent
Give your agent the model details, code and documentation.
1Get your API key
Create API keyexport AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"2Make your first request
curl 'https://api.aimlapi.com/v1/chat/completions' \
-H "Authorization: Bearer $AIMLAPI_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "openai/gpt-5.5-pro",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}'import os
import requests
headers = {
"Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
"Content-Type": "application/json",
}
payload = {
"model": "openai/gpt-5.5-pro",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}
response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "openai/gpt-5.5-pro",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}),
});
if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());Related articles
GPT-5.5 Pro FAQ
What is the context window of GPT-5.5 Pro?
GPT-5.5 Pro has a 1,050,000 tokens context window and can return up to 128,000 tokens.
What inputs and outputs does GPT-5.5 Pro support?
GPT-5.5 Pro takes image, text as input and returns text.
What is the model ID for GPT-5.5 Pro?
Use openai/gpt-5.5-pro as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.
How much does GPT-5.5 Pro cost?
GPT-5.5 Pro costs $31.74 input and $190.44 output per 1M tokens on AI/ML API, billed as you go with no subscription.
Does GPT-5.5 Pro support streaming?
Yes, GPT-5.5 Pro can stream responses as they are generated.
Can GPT-5.5 Pro read images?
Yes, GPT-5.5 Pro accepts image input alongside text.
Who created GPT-5.5 Pro?
GPT-5.5 Pro was built by OpenAI.
Can GPT-5.5 Pro call external tools or functions?
Yes, it supports function calling, tool use, and parallel tool calls.

