OpenCode + Image generation
OpenCode runs the work loop and Image generation performs the selected operation. The Composer below preselects OpenCode, GPT-5.6 Sol, and this tool so you can test one real task with the same billing and recovery path as any AgentSky run.
How the combination works
OpenCode decides when to call Image generation.
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 uses MiniMax Canvas-20 to generate one image at high quality. Specify the subject, composition and exact wording, then choose a square, portrait or landscape size.
OpenCode
Owns the task loop, context, model calls, tool choice, cloud computer, progress and final result.
Image generation
Performs the operation exposed by the current Image generation capability. Its input limits and output shape come from the live tool guide and adapter.
AgentSky
Keeps the selected agent, model, capability grant, task state and usage record together. Tool charges and model or runtime charges remain itemized separately.
Setup and first task
Start with one bounded image generation task.
The Composer carries OpenCode, GPT-5.6 Sol, and Image generation. Begin with the smallest input that lets you inspect the output before expanding the workflow.
Open the OpenCode Composer
The Composer above preselects OpenCode, GPT-5.6 Sol, and Image generation. Add the target, required inputs and a concrete expected result; the draft stays in place through sign-in.
State the Image generation boundary
Create a quiet editorial illustration about human–AI collaboration. Use a light background, a clear focal point, and no text.
Run and verify the returned result
Check the output against the source or brief, confirm that the result has the expected format, and inspect the task usage for model, runtime and tool charges.
Inputs, cost and limits
What OpenCode + Image generation establishes
Model-flexible coding work where teams want OpenCode's workflow with a wider choice of compatible model providers.
Configure and verify
- OpenCode and GPT-5.6 Sol are preselected for the browser evaluation.
- Image generation is enabled from the current capability catalog with its live input and output guidance.
- The first task can be checked from the returned artifact, text or provider result before a larger workflow is attempted.
Still depends on the task
- A tool guide does not guarantee a provider result for malformed, blocked or unsupported Image generation inputs.
- A successful tool call does not establish that the result is correct for your business decision; inspect the output at its source boundary.
- Total task cost can include model tokens, active computer time and the selected tool's billable units.
Current Image generation rates
gptimage.generate
$0.422 per asset.
Tool-specific details
Use the current Image generation contract.
AgentSky uses MiniMax Canvas-20 to generate one image at high quality. Specify the subject, composition and exact wording, then choose a square, portrait or landscape size.
Actual model
MiniMax canvas-20; high quality, one image per request, non-streaming.
Available sizes
1024×1024 square (default), 1024×1536 portrait, or 1536×1024 landscape.
Input and output
Provide a text prompt and size to receive a downloadable image. This tool creates new images; it does not accept an existing image or mask for editing.
Common questions
Related resources