OpenCode + GPT-5.6 Luna
GPT-5.6 Luna is currently selectable with OpenCode on AgentSky. OpenCode controls the work loop and tools; the model supplies reasoning and generation. Start a real task below with both choices already selected.
How the combination works
OpenCode runs the work. GPT-5.6 Luna powers each turn.
OpenCode runs the coding-agent loop in the cloud: it explores the repository, edits files, calls tools, and executes validation with the selected compatible model.
AgentSky supplies the persistent cloud computer, task state, usage records, and enabled tools or connectors around that combination.
OpenCode
Owns the agent loop, repository or computer operations, tool calls, and how results are returned.
GPT-5.6 Luna
OpenAI's model supplies the reasoning and generated output within OpenCode's supported interface.
AgentSky
Keeps the selected pair, workspace, task state, access configuration, and itemized usage together.
Current GPT-5.6 Luna facts
What the model is
The cost-optimised GPT-5.6 tier, built for high-volume workloads.
Context window
1.1M tokens in the current AgentSky catalog.
Accepted input
Text, Image in the current AgentSky catalog.
Model token price
$0.2 / $1.20 per 1M input / output tokens on the displayed AgentSky plan. Runtime and paid tool usage are separate.
Evaluate it on real work
Start with one bounded task and evidence you can inspect.
Connect an authorized repository, state the user-visible outcome, identify the affected path, and provide the command or journey that would disprove a false fix.
Open the preselected Composer
The Composer above starts with OpenCode and GPT-5.6 Luna. Add the repository or project and only the tools the task needs.
Adapt this first task
Trace this requirement from its real entry point, implement the smallest complete change, run the relevant checks, and summarize the evidence and remaining risk.
Verify the outcome
Open the resulting diff, run the affected path from the user's starting point, and confirm that the chosen model did not skip required context or validation.
Fit and limits
When to choose OpenCode + GPT-5.6 Luna
Model-flexible coding work where teams want OpenCode's workflow with a wider choice of compatible model providers.
This page establishes
- The pair is selectable in the current AgentSky compatibility matrix
- The launch carries both selections into the shared Composer
- Current catalog facts are shown when the gateway publishes them
You still need to measure
- Quality on your own repository or workflow
- End-to-end task time, recovery effort, and human review
- Total task cost, which also depends on runtime, tools, connectors, and token usage
Common questions
Related resources