Models
GPT-5.6 Sol
Model id: gpt-5.6-sol
- Agentic
- Frontier
- Coding
- Vision
- Multimodal
- Long context
- Tools
- Research
OpenAI’s current GPT-5.6 Sol flagship for frontier chat, coding, and long-horizon agents.
Best for
Ideal as the default top OpenAI model for hard coding and multi-step tool work.
- Provider
- OpenAI
- Context window
- 1,050,000
- Release date
- 2026-07-09
- Reasoning effort
- nonelowmediumhighxhighDefault: medium
Pricing
Input
$7.716 / 1M
Output
$46.2957 / 1M
Cached input
$0.7716 / 1M
Cache write
$9.6449 / 1M
Long-context rate (above 272,000 tokens)
Input
$15.4319 / 1M
Output
$69.4436 / 1M
Cached input
$1.5432 / 1M
Cache write
$19.2899 / 1M
Web search
Per successful search
$0.0154 / search
Billed on top of tokens when the model uses web search.
Amounts in Canadian dollars, converted at the Bank of Canada indicative rate (2026-07-31).
Performance
Milliseconds
Last 7 days
- Time to first byte (p95)
- 2,437 ms
- Output speed (p95)
- 58.6 tok/s
- Samples
- 244 over 7 days
Measured on real traffic at Pass egress — not a synthetic benchmark.
Activity
Tokens
—
—
—
—
—
Top 5 tools · last 7 days
Tool activity appears only when at least 2 organizations have used this model recently.
Availability
Availability (%)
Last 7 days
- Operational probes
- 99.91% over 7 days
- Samples
- 8,614
Quick start
Call the API with a tonia_ key and the exact model id below.
curl
curl https://pass.tonia.ca:8443/v1/chat/completions \
-H "Authorization: Bearer $TONIA_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-5.6-sol",
"messages": [{"role":"user","content":"Bonjour"}]
}'Python (OpenAI SDK)
import os
from openai import OpenAI
client = OpenAI(
base_url="https://pass.tonia.ca:8443/v1",
api_key=os.environ["TONIA_API_KEY"],
)
response = client.chat.completions.create(
model="gpt-5.6-sol",
messages=[{"role": "user", "content": "Bonjour"}],
)TypeScript (OpenAI SDK)
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://pass.tonia.ca:8443/v1",
apiKey: process.env.TONIA_API_KEY,
});
const response = await client.chat.completions.create({
model: "gpt-5.6-sol",
messages: [{ role: "user", content: "Bonjour" }],
});