A model for
the next step.
Understand the model. See its native agent. Choose the next step with current rates in view.
Choose with context.
The agent runs the work; the model powers its responses. Each model below links to its own use cases, exact route and live pricing.
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 Astra
GPT-6 Astra is OpenAI’s most capable option for demanding reasoning and coding in the current family.
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.
GPT-6 Luna
GPT-6 Luna is designed for focused tasks at high volume.
GPT-5.6 Sol
GPT-5.6 Sol is an earlier model retained as a legacy option in the Minaco catalog.
Claude Sonnet 5.5
Sonnet 5.5 is the balanced option in the current Claude family.
Claude Opus 5.5
Opus 5.5 is positioned for agentic coding and knowledge work.
Claude Haiku 5.5
Haiku 5.5 targets low-latency tasks such as classification, extraction and routing.
Claude Fable 5.2
Fable 5.2 is the newer Fable model, announced on November 9, 2026, for demanding reasoning and long-horizon work.
Claude Fable 5.1
Fable 5.1 is the previous Fable model, retained alongside Fable 5.2 in Minaco.
DeepSeek V4.1 Flash (1017)
This is the October 17 update of DeepSeek V4.1 Flash. DeepSeek’s release describes improvements in project creation, including interactive and visual applications.
DeepSeek V4 Pro (0813)
This is the pinned August 13 release of DeepSeek V4 Pro, offered separately from Flash.
Muse Wonder
Muse Wonder is Meta’s model for complex software work and long-horizon agent tasks. The upstream documentation identifies it as a preview.
Muse Spark 1.3
Muse Spark 1.3 is Meta’s current Spark version for agentic coding and long-context work.
Muse Ember
Muse Ember is Meta’s efficient execution model for repeated work such as tool calls, routing, extraction and coding subtasks.
Kimi K3.1 Pro
Kimi K3.1 Pro is the newer Kimi flagship, following K3. Moonshot’s current Kimi Code documentation highlights coding and long-horizon agent work.
Kimi K3
Kimi K3 remains available alongside K3.1 Pro. Kimi’s documentation describes it for codebase analysis, multi-file refactoring and long-document work.
Qwen4-Max
Qwen4-Max is Alibaba’s flagship Qwen4 model for long-context reasoning, coding, professional work and tool-using agent tasks.
Grok 4.7
Grok 4.7 is a model for coding, agentic tasks and knowledge work. In Minaco it is currently routed through Hermes Agent.
GLM 5.3
GLM 5.3 is the current GLM model documented for ZCode configuration.
Qwen3.8 Max (0902)
Qwen3.8 Max (0902) is the pinned Max version of the Qwen3.8 family published in Minaco.
Qwen3.8 Flash
Qwen3.8 Flash is the faster, lower-cost member of the Qwen3.8 family.
Prices are Credits per million tokens, checked 2026-11-17. Cached input has its own rate on each model page. Your plan and the app determine access. Upstream capabilities and Minaco tool support can differ.
Bring your next project.
Your agents. Your workspace. One place to continue.