Official commercial channel
GPT-5.6 Terra API
The everyday tier: the same window as Sol, at half the list price.
Context
1.05M
Max output
128K
Serving precision
Vendor-managed
Licence
Proprietary
GPT-5.6 Terra is the balanced everyday tier, sharing the 1,050,000-token context window, 128,000-token output ceiling and 16 February 2026 knowledge cut-off with Sol and Luna, accepting text and image input. Vendor list pricing is $2.50 per million input and $15 per million output — exactly half of Sol. For the large share of production traffic that needs a long window and steady behaviour but not frontier reasoning, it is the most practical tier in the family.
Proprietary, provided through the vendor’s official commercial licensing. Contract, invoice, audit trail — not an account pool and not a reverse-engineered client protocol.
Specifications
- Model ID
- gpt-5.6-terra
- Published by
- OpenAI
- How it is served
- Official commercial channel
- Licence
- Proprietary
- Context
- 1.05M
- Max output
- 128K
- Serving precision
- Vendor-managed
- Input modalities
- Text · Image
- Released
- 2026-07-09
- Price
- See pricing
What it is good at
- The window is not what got cut
- Identical 1.05M context and 128K output to Sol at half the list price. Long-input workloads never have to drop to a smaller-window model just to save money.
- Switching tiers costs no code
- All three tiers share the interface and the limits, so moving between Terra and Sol is one `model` field. Run everything on Terra, then route only the measured failures up.
- Official channel
- Contract, invoice, audit trail. No account pools, no reverse-engineered client protocols.
Where it fits
- Primary product traffic: chat, summarisation, structured extraction
- Bulk work that needs a long window but not top-tier reasoning
- The default tier in a multi-tier routing setup
- Cost/quality split-testing against Sol
Three steps
Change one line of base_url, put the model ID below in the `model` field, and leave the rest of your code alone.
model: "gpt-5.6-terra"
curl https://api.nexaix.net/v1/chat/completions \
-H "Authorization: Bearer $NEXAIX_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-5.6-terra",
"stream": true,
"messages": [
{ "role": "user", "content": "Summarise this contract." }
]
}'import os
from openai import OpenAI
client = OpenAI(
# the only new line
base_url="https://api.nexaix.net/v1",
api_key=os.environ["NEXAIX_API_KEY"],
)
# everything below is your existing code
stream = client.chat.completions.create(
model="gpt-5.6-terra",
stream=True,
messages=[
{"role": "user", "content": "Summarise this contract."}
],
)
for chunk in stream:
print(chunk.choices[0].delta.content or "", end="")import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.nexaix.net/v1", // the only new line
apiKey: process.env.NEXAIX_API_KEY,
});
// everything below is your existing code
const stream = await client.chat.completions.create({
model: "gpt-5.6-terra",
stream: true,
messages: [
{ role: "user", content: "Summarise this contract." }
],
});
for await (const chunk of stream) {
process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}About this model
Where is Terra weaker than Sol?
In reasoning depth, not in window or interface. On extraction, ordinary conversation and structured output the gap is small; on complex reasoning and long-horizon agents it widens. Set your routing threshold from your own eval, not from a leaderboard.
Can one key reach both Terra and Sol?
Yes. A single key reaches every model you have enabled; change the `model` field. Usage is metered and itemised per model in the console.
What is the knowledge cut-off?
16 February 2026 for all three GPT-5.6 tiers. Inject anything newer via retrieval or tool calls.
Also worth a look
- Official commercial channelClaude Opus 5A million tokens that never degrade, five-level effort control, zero data retention.claude-opus-5
- Official commercial channelClaude Fable 5Anthropic’s tier above Opus — the one you pick when the ceiling is the point.claude-fable-5
- Official commercial channelGPT-5.6 SolThe frontier tier of the GPT-5.6 family: 1.05M context, built for long-horizon agents.gpt-5.6-sol
Run your own eval on it
Take the trial credit, run the evals you already have against this model, and then decide whether it gets your production traffic.
