Skip to main content

New accounts get trial credit — enough to run a full eval suite

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

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." }
    ]
  }'

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

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.