GPT-5.6 Luna API pricing and integration guide

Current prices and model reference

Model ID

gpt-5.6-luna

Documented context

1M

Documented image input

Supported

Live model multiplier

1×

Input price

¥0.4 / 1M tokens

Output price

¥0.24 / 1M tokens

Prices are in CNY. A 1× multiplier equals CNY 0.4 per million input tokens. Output and cache charges follow the billing configuration; your usage record is authoritative.

When to consider this model

The reference positions Luna as a fast, cost-conscious route. Start with classification, rewriting, short summaries and coding assistance, then use failure samples to decide when to escalate.

How to evaluate it

Sample real tasks and define format and accuracy requirements before increasing concurrency. Track latency, errors and retries; duplicate submissions can add cost to batch jobs.

What to check before integration

A low multiplier does not imply unlimited throughput or lower total cost for every complex task. Include retries and human corrections when comparing completion cost with Sol or Terra.

Client configuration

In a client supporting a custom API endpoint, enter this base URL and model ID with your own API key. Select the protocol described in the client tutorial and validate a short request first.

Base URL: https://api.llm-token.cn/v1
Model ID: gpt-5.6-luna