Minaco

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.

OpenAI · Codex

GPT-6.1 Sol

GPT-6.1 Sol is positioned for complex work with a lower cost than the most demanding reasoning tier.

125 / 625Input / output Credits per 1M tokensExplore model →
OpenAI · Codex

GPT-6 Astra

GPT-6 Astra is OpenAI’s most capable option for demanding reasoning and coding in the current family.

625 / 3,125Input / output Credits per 1M tokensExplore model →
OpenAI · Codex

GPT-6.1 Terra

GPT-6.1 Terra emphasizes visual reasoning, computer use and writing alongside general task work.

62.5 / 312.5Input / output Credits per 1M tokensExplore model →
OpenAI · Codex

GPT-6 Sol

GPT-6 Sol is the earlier Sol option retained in Minaco alongside GPT-6.1 Sol.

125 / 625Input / output Credits per 1M tokensExplore model →
OpenAI · Codex

GPT-6 Luna

GPT-6 Luna is designed for focused tasks at high volume.

6.25 / 31.25Input / output Credits per 1M tokensExplore model →
OpenAI · Codex

GPT-5.6 Sol

GPT-5.6 Sol is an earlier model retained as a legacy option in the Minaco catalog.

250 / 1,250Input / output Credits per 1M tokensExplore model →
Claude · Claude Code

Claude Sonnet 5.5

Sonnet 5.5 is the balanced option in the current Claude family.

3,800 / 19,000Input / output Credits per 1M tokensExplore model →
Claude · Claude Code

Claude Opus 5.5

Opus 5.5 is positioned for agentic coding and knowledge work.

7,600 / 38,000Input / output Credits per 1M tokensExplore model →
Claude · Claude Code

Claude Haiku 5.5

Haiku 5.5 targets low-latency tasks such as classification, extraction and routing.

From 190 / 950Input / output Credits per 1M tokensExplore model →
Claude · Claude Code

Claude Fable 5.2

Fable 5.2 is the newer Fable model, announced on November 9, 2026, for demanding reasoning and long-horizon work.

15,200 / 76,000Input / output Credits per 1M tokensExplore model →
Claude · Claude Code

Claude Fable 5.1

Fable 5.1 is the previous Fable model, retained alongside Fable 5.2 in Minaco.

19,000 / 95,000Input / output Credits per 1M tokensExplore model →
DeepSeek · DeepSeek Harness

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.

600 / 2,400Input / output Credits per 1M tokensExplore model →
DeepSeek · DeepSeek Harness

DeepSeek V4 Pro (0813)

This is the pinned August 13 release of DeepSeek V4 Pro, offered separately from Flash.

222 / 8,880Input / output Credits per 1M tokensExplore model →
Muse · Muse Code

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.

8,000 / 40,000Input / output Credits per 1M tokensExplore model →
Muse · Muse Code

Muse Spark 1.3

Muse Spark 1.3 is Meta’s current Spark version for agentic coding and long-context work.

2,500 / 8,500Input / output Credits per 1M tokensExplore model →
Muse · Muse Code

Muse Ember

Muse Ember is Meta’s efficient execution model for repeated work such as tool calls, routing, extraction and coding subtasks.

200 / 1,000Input / output Credits per 1M tokensExplore model →
Kimi · Kimi Code

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.

4,000 / 20,000Input / output Credits per 1M tokensExplore model →
Kimi · Kimi Code

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.

384 / 32,000Input / output Credits per 1M tokensExplore model →
Qwen · Qwen Code

Qwen4-Max

Qwen4-Max is Alibaba’s flagship Qwen4 model for long-context reasoning, coding, professional work and tool-using agent tasks.

3,000 / 9,000Input / output Credits per 1M tokensExplore model →
Grok · Hermes Agent

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.

8,000 / 24,000Input / output Credits per 1M tokensExplore model →
GLM · GLM / ZCode

GLM 5.3

GLM 5.3 is the current GLM model documented for ZCode configuration.

139.8 / 2,800Input / output Credits per 1M tokensExplore model →
Qwen · Qwen Code

Qwen3.8 Max (0902)

Qwen3.8 Max (0902) is the pinned Max version of the Qwen3.8 family published in Minaco.

4,000 / 12,000Input / output Credits per 1M tokensExplore model →
Qwen · Qwen Code

Qwen3.8 Flash

Qwen3.8 Flash is the faster, lower-cost member of the Qwen3.8 family.

300 / 940Input / output Credits per 1M tokensExplore model →

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.

Download for Mac