GPT-5.6 Terra
Call the default-enabled GPT-5.6 Terra model through OpenAI Chat Completions or the Responses API.
GPT-5.6 Terra is a default-enabled OpenAI-format chat model for general reasoning, structured output, and tool calls. Available capabilities depend on the live model entry and upstream.
Model information
| Item | Value |
|---|---|
| Model ID | gpt-5.6-terra |
| Primary endpoint | POST /v1/chat/completions |
| Request format | OpenAI Chat Completions |
| Responses | Supported when the model entry includes responses_endpoint |
| Official input / output price | $2.5 / $15 per 1M tokens, before your account coefficient |
Request parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
model | string | Yes | Use one of the IDs above returned for the current API key by GET /v1/models |
messages | array | Yes | Conversation messages |
max_completion_tokens | integer | No | Limits response and reasoning tokens |
reasoning_effort | string | No | Reasoning effort; accepted values depend on the current upstream |
tools | array | No | OpenAI-format function tool definitions |
response_format | object | No | Can request structured JSON output |
stream | boolean | No | Set to true to receive an SSE stream |
Model parameters are passed through to the upstream. Before production use, query GET /v1/models
with your API key and test the exact tools, reasoning, or structured-output combination you need.
Request example
curl https://hopsapi.com/v1/chat/completions \
-H "Authorization: Bearer sk-YOUR_KEY" \
-H "content-type: application/json" \
-d '{"model":"gpt-5.6-terra","max_completion_tokens":256,
"messages":[{"role":"user","content":"Return a JSON object with status=ok."}],
"response_format":{"type":"json_object"}}'from openai import OpenAI
client = OpenAI(base_url="https://hopsapi.com/v1", api_key="sk-YOUR_KEY")
response = client.chat.completions.create(
model="gpt-5.6-terra",
max_completion_tokens=256,
messages=[{"role": "user", "content": "Return a JSON object with status=ok."}],
response_format={"type": "json_object"},
)
print(response.choices[0].message.content)Response example
This example shows the protocol shape only. Text, token counts, and additional fields such as id and model come from the live response.
{
"choices": [
{
"message": { "role": "assistant", "content": "{\"status\":\"ok\"}" },
"finish_reason": "stop"
}
],
"usage": { "prompt_tokens": 24, "completion_tokens": 13, "total_tokens": 37 }
}For native Responses fields, continued conversations, and SSE events, see Responses API.