TextArabic — strong supportNEW

GPT-5.6 Terra

GPT-5.6 Terra sits in the middle of OpenAI's GPT-5.6 line, keeping the generation's 1M-token context, image input, function calling, and structured outputs while running at a lower rate than the Sol tier. It is the sensible default for production traffic that needs frontier-family behavior on most requests: assistants, coding help, retrieval over long documents, and structured extraction. Start here, then move up to Sol only for the requests that genuinely need it.

Pricing

Input

$2.00 / 1M

Output

$12.00 / 1M

Pay only for what you use. No subscriptions, no minimums.

Specs

Context
1M
Max output
128K
Latency
Medium
Category
Text
Arabic
Strong

Quick start

Use any OpenAI-compatible client. Just change base_url and your key.

from openai import OpenAI

client = OpenAI(
    api_key="tl-xxxxxxxxxxxxxxxxxxxxxxxx",
    base_url="https://api.thalam.ai/v1",
)

response = client.chat.completions.create(
    model="openai/gpt-5.6-terra",
    messages=[
        {"role": "user", "content": "Hello from Thalam!"}
    ],
)

print(response.choices[0].message.content)

Similar models

GPT-5.6 Sol

NEWTextArabic

The top tier of OpenAI's GPT-5.6 generation. Frontier reasoning, coding, and agentic work with a 1M-token context and image input.

Context
1M
Max output
128K
Latency
Medium
Input price
$5.00 / 1M
Output price
$30.00 / 1M

GPT-5.6 Luna

NEWTextArabic

The fast, high-volume tier of OpenAI's GPT-5.6 generation. Keeps the 1M-token context and image input at the lowest rate in the family.

Context
1M
Max output
128K
Latency
Fast
Input price
$0.20 / 1M
Output price
$1.20 / 1M

Kimi K3

NEWText

Moonshot's new flagship generation. A 1M-token context and the strongest measured reasoning in our catalog.

Context
1M
Max output
400K
Latency
Medium
Input price
$3.00 / 1M
Output price
$15.00 / 1M

Featured in

More from OpenAI

All OpenAI models (8)