Keep your SDK. Connect in minutes.
Point the Base URL to api.acedata.cloud, configure your platform API key and the model ID below, and use your compatible SDK or client.
- API host
api.acedata.cloud- model
gpt-6.1-terra
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["ACEDATACLOUD_API_KEY"],
base_url="https://api.acedata.cloud/v1",
)
response = client.responses.create(
model="gpt-6.1-terra",
input="Hello!",
)
print(response.output_text)Choose an available protocol for this model. OpenAI SDK uses a Base URL ending in /v1; Anthropic SDK uses the root URL. See each guide for protocol-specific parameters, tools and response formats.
GPT-6.1 Terra
GPT-6.1 Terra is a model for everyday conversations, content processing, and coding assistance. The platform invocation ID is gpt-6.1-terra, and it can be used through the Chat Completions and Responses APIs.
Model specifications
- Context window listed in the model catalog
- 1,000,000 tokens
- Maximum output listed in the model catalog
- 128,000 tokens
- Input
- Text, images
- Output
- Text, structured results, or tool calls
- Reasoning levels
- low / medium / high / xhigh / max
- Platform APIs
- Chat Completions, Responses, Messages
Catalog specifications do not guarantee that the full context can be used in a single request; input, output, and API limits must be checked together.
Use cases
Everyday work and coding assistance
Can be used for Q&A, summaries, drafts, code explanations, and suggestions for small-scope modifications. Provide clear inputs and acceptance criteria, and verify important conclusions.
Image and text understanding
You can ask questions using images and text together; image size, quantity, and format are subject to current API limits.
API selection
Chat Completions can be used for ordinary conversations; Responses can be used when you need to process tool calls and return results item by item. Chat Completions and Responses support streaming output; the Messages compatibility endpoint uses the Messages request format. For specific fields, see the corresponding platform documentation.
Reasoning settings
Start with low and compare other levels using the same set of tasks. Chat Completions uses reasoning_effort, and Responses uses reasoning.effort. none and minimal are not currently supported.
Usage and pricing
Costs are determined by actual input, output, and cache usage. Requests exceeding 272,000 input tokens are subject to the long-context tier; final pricing is based on the current pricing page and actual usage records.
Usage boundaries
A model proposing a tool action does not mean the action has been executed. Applications must execute authorized tool calls and then verify the tool results. Long context and image understanding also cannot replace verification of the original materials.
Frequently Asked Questions
What is the model ID?
Use gpt-6.1-terra; do not write it as the old Terra ID.
How do I enable streaming output?
Set stream: true in supported API requests, and read the output according to that API's event format.
Can I use tools?
The model catalog indicates support for tool calling. Applications still need to provide tool definitions, execution authorization, and result return.
Can reasoning be turned off?
The current reasoning level starts at low; none and minimal are not on the supported list.
How do I estimate costs?
First check the current tier on the pricing page, then verify it against the response's actual token usage; cache hits cannot be inferred solely from repeated text.
Use it in your favorite tools
Choose a development approach or application suited to this model and follow its setup guide.
↗Connect gpt-6.1-terra to OpenAI SDK
OpenAI Chat Completions API
SDK installation, authentication and examples↗Connect gpt-6.1-terra to OpenAI SDK · Responses
OpenAI Responses API
SDK installation, authentication and examples
↗Claude Messages API
API parameters and request examples
↗Connect gpt-6.1-terra to Claude Code
Claude Code CLI Setup Guide
Coding tool setup · requires a Coding Plan application key
↗Connect gpt-6.1-terra to Cherry Studio
Using Ace Data Cloud with Cherry Studio
Chat client setup · Base URL, API key and model
↗Connect gpt-6.1-terra to ChatBox
Using Ace Data Cloud with ChatBox
Chat client setup · Base URL, API key and modelInput
$0.20per 1M tokens
Official $1.00
Output
$1.00per 1M tokens
Official $5.00
You pay$13,584for 142,800 credits · $0.0951 / credits46% OFF
You're billed in credits. Pick a top-up tier to see its per-credit rate — the larger the top-up, the cheaper each credit.
Quickstart
This is only a basic call example. See the full docs for more parameters and advanced usage.
View Docs