Question 1

Can Qwen Code run GPT-5.6 Luna on AgentSky?

Accepted Answer

Yes. This page is generated only when GPT-5.6 Luna is selectable for new Qwen Code runs in AgentSky's current compatibility matrix. If the pair is retired or disabled, the page is removed from discovery and returns not found.

Question 2

What does Qwen Code do in this combination?

Accepted Answer

Qwen Code controls how the agent reads context, invokes tools, works in the cloud computer, and returns progress and results. That behavior remains distinct from the selected model.

Question 3

What does GPT-5.6 Luna do in this combination?

Accepted Answer

GPT-5.6 Luna supplies reasoning and generated output for the turns that Qwen Code sends through its supported model interface. The current AgentSky catalog lists a 1.1M-token context window.

Question 4

How do I start Qwen Code + GPT-5.6 Luna?

Accepted Answer

Use the Composer on this page. It already selects Qwen Code and GPT-5.6 Luna; add a concrete task and any needed project, tools, or connectors. If you are signed out, AgentSky returns you to the same draft after sign-in.

Question 5

How much does Qwen Code + GPT-5.6 Luna cost?

Accepted Answer

GPT-5.6 Luna is currently displayed at $0.2 / $1.20 per 1M input / output tokens. That is the model-token component, not a guaranteed task total. Agent runtime, paid tools, connectors, cache usage, and the task's actual token volume can add cost; AgentSky records charges against the same balance.

Question 6

What happens if I am signed out or do not have enough balance?

Accepted Answer

The shared AgentSky Composer preserves the task and exact pair through sign-in. Before dispatch, the product checks the account and balance; if funding is required, it shows the billing path instead of silently changing the agent or model.

Question 7

Can I switch models without changing Qwen Code?

Accepted Answer

Yes, when another model appears in Qwen Code's supported model list. Treat the switch as a new evaluation because quality, latency, context handling, tool behavior, and token price may change.

Question 8

Is this the same as calling GPT-5.6 Luna through the API gateway?

Accepted Answer

No. A direct gateway call gives you the model response and usage record. This combination also runs Qwen Code's tool-using workflow inside an AgentSky cloud computer, so runtime and task behavior are part of the result.

Question 9

Is Qwen Code + GPT-5.6 Luna the best combination?

Accepted Answer

This page confirms availability and explains how to test the pair; it is not a universal ranking. Compare representative tasks, completion quality, failure recovery, elapsed time, and total recorded cost before choosing a default.

Qwen Code + GPT-5.6 Luna

Qwen Code runs the work. GPT-5.6 Luna powers each turn.

Qwen Code

GPT-5.6 Luna

AgentSky

What the model is

Context window

Accepted input

Model token price

Start with one bounded task and evidence you can inspect.

Open the preselected Composer

Adapt this first task

Verify the outcome

When to choose Qwen Code + GPT-5.6 Luna

Qwen Code

GPT-5.6 Luna API

Compare agent + model

Pricing

Run a real task with Qwen Code + GPT-5.6 Luna.