openai/gpt-5.5
OpenAI's flagship GPT-5.5. State-of-the-art reasoning, agentic coding, and tool use with a 1M-token context window. Prompt caching cuts repeated-context cost 90%. Pick it for the hardest tasks.
Source: launch_0023 · Verified 2026-06-01
Fast $1 / $6 /M
Cache read $0.05/M · Cache write —/M
| Tier | Input | Cache read | Cache write | Output |
|---|---|---|---|---|
| Standard ≤272K | $0.5 | $0.05 | — | $3 |
| Standard >272K | $1 | $0.1 | — | $4.5 |
| Priority | $1 | $0.1 | — | $6 |
Use either ID to call this model via the API.
openai/gpt-5.5Replace the ONEHOP_KEY placeholder with your API key. Create one →
from openai import OpenAI
client = OpenAI(
base_url="https://api.onehop.ai/v1",
api_key="<ONEHOP_KEY>",
)
completion = client.chat.completions.create(
model="openai/gpt-5.5",
messages=[{"role": "user", "content": "What is the meaning of life?"}],
)
print(completion.choices[0].message.content)OpenAI's flagship GPT-5.6 for the hardest reasoning, coding, and agentic work.
$0.25/M↓ · $1.5/M↑
Balanced GPT-5.6 quality and cost for production workloads.
$0.125/M↓ · $0.75/M↑
The most efficient GPT-5.6 for high-volume and latency-sensitive work.
$0.05/M↓ · $0.3/M↑
OpenAI GPT-5.4 — strong general model, 1M context, lower cost than 5.5.
$0.25/M↓ · $1.5/M↑
OpenAI GPT-5.4 mini — fast, cheapest GPT-5 text route.
$0.075/M↓ · $0.45/M↑
49,626 requests · last 30 days