When to try it.
Consider it when a difficult design decision or failure spans multiple components and requires careful analysis.
What to weigh
It has a higher Minaco rate than Sol and Terra. Begin with a representative task and review usage before delegating a large workload.
A first task
Investigate this cross-service failure. Separate observations from hypotheses and propose the smallest verifiable fix.
This is a suggested evaluation task. Check the result against your own requirements; it is not a benchmark or a guarantee of performance.
Know the rate.
Currently published for Codex. Rates below are Minaco Credits per one million tokens.
- Input
- 625
- Cached input
- 62.5
- Output
- 3,125
Estimate a model call
Example: 10,000 uncached input tokens and 1,000 output tokens cost approximately 9.375 Credits before per-request rounding.
An agent turn may make several model calls. Context, tool results and billable reasoning tokens affect the total; enter cache-write tokens separately when applicable. The prompt total determines the rate for the whole request. This estimate is not a charge cap or a checkout quote. How Credits work.
Exact route: gpt-6-astra
Catalog checked 2026-11-17. Model access depends on your plan and current service availability.
Use it in your workspace.
Prepare Codex
Install Minaco on your Apple silicon Mac, connect your account and prepare the native agent in Agent settings.
Choose the exact model
Select Codex and a Minaco-credit account mode. If your plan offers GPT-6 Astra, choose it from the model selector. Desktop 0.13.14 or later reads the server’s model catalog.
Give it a bounded task
Open the project folder, provide the necessary context and review any approvals. Inspect the result and usage before expanding the scope.
When the next stage calls for a different agent, finish the turn and switch in the same conversation. Minaco prepares the visible working context for the next native session; hidden reasoning and credentials do not transfer.
How context handoff works →Read the source.
OpenAI model documentation describes the upstream model.
Editorial review: 2026-11-11. Task suggestions and comparisons are Minaco’s guidance, not vendor benchmark results. Minaco is an independent workspace; model API features do not imply that every feature is exposed by the native agent.
Compare nearby choices.
- GPT-6.1 Sol — GPT-6.1 Sol is positioned for complex work with a lower cost than the most demanding reasoning tier.
- GPT-6.1 Terra — GPT-6.1 Terra emphasizes visual reasoning, computer use and writing alongside general task work.
- GPT-6 Sol — GPT-6 Sol is the earlier Sol option retained in Minaco alongside GPT-6.1 Sol.