gpt-5.5 API
GPT-5.5 is OpenAI's flagship general-purpose model with a 1,050,000-token context window. Call it on CaMeL Hub via the OpenAI-compatible API (base_url https://api.camel-hub.com/v1) at $3.75 per 1M input tokens and $22.50 per 1M output tokens.
Pricing
| per 1M input tokens | per 1M output tokens | |
|---|---|---|
| CaMeL Hub | $3.75 | $22.5 |
| Provider list price | $5.00 | $30.00 |
Prices are the public default-group rate in USD per 1M tokens; input and output are billed separately. · Provider list price · verified 2026-07-11
Specifications
- Provider
- OpenAI
- Context window
- 1050000 tokens
- Max output
- 128000 tokens
- Capabilities
- streaming, vision
- Endpoints
- openai, openai-response
What it is good for
- Whole-repository code review and multi-file refactoring — load hundreds of source files into one prompt and get consistent, cross-file changes
- Contract and due-diligence analysis over document sets that approach the 1M-token window, with clause-level citations
- Screenshot and diagram understanding: feed UI captures, architecture diagrams, or chart images and get structured findings
- Long-form technical writing and editing — drafting or revising documentation and reports up to the 128K output ceiling
- Complex multi-step reasoning pipelines where a cheaper model's error rate compounds, such as data-migration planning or root-cause analysis
- Structured extraction from mixed text-and-image inputs, e.g. turning scanned invoices or slide decks into clean JSON
Quickstart
OpenAI-compatible: set base_url to https://api.camel-hub.com/v1 and use your CaMeL Hub API key. No SDK changes needed.
cURL
curl https://api.camel-hub.com/v1/chat/completions \
-H "Authorization: Bearer $CAMEL_HUB_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-5.5",
"messages": [{"role": "user", "content": "Hello!"}]
}'Python
from openai import OpenAI
client = OpenAI(
api_key="$CAMEL_HUB_KEY",
base_url="https://api.camel-hub.com/v1", # <-- the only change vs. the OpenAI default
)
resp = client.chat.completions.create(
model="gpt-5.5",
messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)Node.js
import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.CAMEL_HUB_KEY,
baseURL: "https://api.camel-hub.com/v1", // <-- the only change vs. the OpenAI default
});
const resp = await client.chat.completions.create({
model: "gpt-5.5",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(resp.choices[0].message.content);Get an API key Browse integration guides
Frequently asked questions
How is gpt-5.5 billed on CaMeL Hub?
Input and output tokens are metered separately: $3.75 per 1M input tokens and $22.50 per 1M output tokens on the public default group. Streaming responses are billed identically to non-streaming ones, and usage is deducted from your prepaid balance per request.
Does gpt-5.5 support streaming and image input?
Yes. Set stream: true for token-by-token streaming, and pass images (e.g. as image_url content parts) for vision tasks — gpt-5.5 accepts image input and returns text. Both work through the standard OpenAI request format on CaMeL Hub.
What are the context window and output limits?
Per OpenAI's model documentation, gpt-5.5 has a 1,050,000-token context window and supports up to 128,000 output tokens per response. Note that very large prompts are billed by input token count, so filling the window has a proportional cost.
Which API endpoints can I use for gpt-5.5?
On CaMeL Hub, gpt-5.5 works with both the OpenAI Chat Completions API (/v1/chat/completions) and the newer Responses API (/v1/responses). Existing OpenAI SDK code needs no changes beyond the base_url.
How do I start using gpt-5.5?
Register at https://api.camel-hub.com/console, top up (Alipay, WeChat Pay, and international cards are supported), and create an API key. Then set base_url to https://api.camel-hub.com/v1 in any OpenAI SDK and call model "gpt-5.5" — no other code changes required.