C

Chinese LLM Models (Kimi 2.5, MiniMax 2.5, Qwen, DeepSeek) with One Key

openclaw-aisa-chinese-llm-models

Configure AIsa as a first-class model provider for OpenClaw, enabling production access to major Chinese AI models (Qwen, DeepSeek, Kimi K2.5, Doubao) throug...

数据来源：ClawHub。在 ClawSkills 查看

778下载量

0收藏数

4浏览量

安装

选择你使用的 Agent

方法一：命令行安装（推荐）

关于 Chinese LLM Models (Kimi 2.5, MiniMax 2.5, Qwen, DeepSeek) with One Key

--- name: aisa-provider description: Configure AIsa as a first-class model provider for OpenClaw, enabling production access to major Chinese AI models (Qwen, DeepSeek, Kimi K2.5, Doubao) through official partnerships with Alibaba Cloud, BytePlus, and Moonshot. Use this skill when the user wants to set up Chinese AI models, configure AIsa API access, compare pricing between AIsa and other providers (OpenRouter, Bailian), switch between Qwen/DeepSeek/Kimi models, or troubleshoot AIsa provider configuration in OpenClaw. Also use when the user mentions AISA_API_KEY, asks about Chinese LLM pricing, Kimi K2.5 setup, or needs help with Qwen Key Account setup. metadata: openclaw: emoji: "🇨🇳" requires: env: - AISA_API_KEY primaryEnv: AISA_API_KEY homepage: "https://marketplace.aisa.one" ---

AIsa Provider for OpenClaw

AIsa is a unified API gateway providing production access to China's leading AI models through official partnerships with all major Chinese AI platforms. It is an Alibaba Cloud Qwen Key Account partner, offering the full Qwen model family at discounted pricing, plus models on the Alibaba Bailian aggregation platform (DeepSeek, Kimi, GLM).

AIsa also provides access to Kimi K2.5 (Moonshot AI's flagship reasoning model) at approximately 80% of official pricing.

> ⚠️ All pricing listed below is for reference. Real-time pricing is subject to change — always check https://marketplace.aisa.one/pricing for the latest rates.

Quick Setup

Option 1: Environment Variable (fastest)

export AISA_API_KEY="your-key-here"

OpenClaw auto-detects AISA_API_KEY and registers AIsa as a provider. No config file changes needed.

Option 2: Interactive Onboarding

openclaw onboard --auth-choice aisa-api-key

Option 3: CLI with Key

openclaw onboard --auth-choice aisa-api-key --aisa-api-key "your-key-here"

Option 4: Manual Config in `~/.openclaw/openclaw.json`

{
  "models": {
    "providers": {
      "aisa": {
        "baseUrl": "https://api.aisa.one/v1",
        "apiKey": "${AISA_API_KEY}",
        "api": "openai-completions",
        "models": [
          {
            "id": "aisa/qwen3-max",
            "name": "Qwen3 Max",
            "reasoning": true,
            "input": ["text", "image"],
            "contextWindow": 256000,
            "maxTokens": 16384,
            "supportsDeveloperRole": false,
            "cost": {
              "input": 1.20,
              "output": 4.80,
              "cacheRead": 0,
              "cacheWrite": 0
            }
          },
          {
            "id": "aisa/qwen-plus-2025-12-01",
            "name": "Qwen Plus",
            "reasoning": true,
            "input": ["text", "image"],
            "contextWindow": 256000,
            "maxTokens": 16384,
            "supportsDeveloperRole": false,
            "cost": {
              "input": 0.30,
              "output": 0.90,
              "cacheRead": 0,
              "cacheWrite": 0
            }
          },
          {
            "id": "aisa/qwen-mt-flash",
            "name": "Qwen MT Flash",
            "reasoning": true,
            "input": ["text"],
            "contextWindow": 256000,
            "maxTokens": 8192,
            "supportsDeveloperRole": false,
            "cost": {
              "input": 0.05,
              "output": 0.30,
              "cacheRead": 0,
              "cacheWrite": 0
            }
          },
          {
            "id": "aisa/deepseek-v3.1",
            "name": "DeepSeek V3.1",
            "reasoning": true,
            "input": ["text"],
            "contextWindow": 131072,
            "maxTokens": 8192,
            "supportsDeveloperRole": false,
            "cost": {
              "input": 0.27,
              "output": 1.10,
              "cacheRead": 0.07,
              "cacheWrite": 0
            }
          },
          {
            "id": "aisa/kimi-k2.5",
            "name": "Kimi K2.5",
            "reasoning": true,
            "input": ["text"],
            "contextWindow": 131072,
            "maxTokens": 8192,
            "supportsDeveloperRole": false,
            "cost": {
              "input": 0.60,
              "output": 2.40,
              "cacheRead": 0,
              "cacheWrite": 0
            }
          }
        ]
      }
    }
  },
  "agents": {
    "defaults": {
      "model": {
        "primary": "aisa/qwen3-max"
      }
    }
  }
}

Available Models

Default Models (pre-configured, API-verified ✅)

| Model | Model ID | Best For | Context | Reasoning | Verified | |-------|----------|----------|---------|-----------|----------| | Qwen3 Max | aisa/qwen3-max | Complex reasoning, flagship tasks | 256K | ✅ | ✅ | | Qwen Plus | aisa/qwen-plus-2025-12-01 | Main production model | 256K | ✅ | ✅ | | Qwen MT Flash | aisa/qwen-mt-flash | High-frequency, lightweight tasks | 256K | ✅ | ✅ | | DeepSeek V3.1 | aisa/deepseek-v3.1 | Cost-effective reasoning | 128K | ✅ | ✅ | | Kimi K2.5 | aisa/kimi-k2.5 | Moonshot's flagship reasoning model | 128K | ✅ | ✅ |

⭐ Kimi K2.5 — Moonshot AI's Flagship Model

Kimi K2.5 is Moonshot AI's latest reasoning model, accessible via AIsa at approximately 80% of official Moonshot pricing.

Key features:

Strong reasoning and multi-step problem solving
Competitive performance on coding and math benchmarks
Available through AIsa's Moonshot partnership

🔒 Zero Data Retention (ZDR) — Enterprise-Grade Privacy

Accessing Kimi K2.5 through AIsa comes with enterprise-level Zero Data Retention guarantees. Users do not need to worry about data privacy — AIsa has executed a formal ZDR agreement with Moonshot AI.

Under the Supplemental Enterprise Service Agreement (dated 10 February 2026) between AIsa and Kimi (Moonshot AI PTE. LTD.):

Customer data is NOT retained by Moonshot after processing
Generated outputs are NOT stored on Moonshot's infrastructure
No data is used for model training — your prompts and completions remain private
Processing is governed by contractual enterprise terms, not consumer ToS

This makes AIsa the recommended path for privacy-sensitive or enterprise workloads that require access to Kimi K2.5. When calling Kimi K2.5 directly via Moonshot's consumer API, standard consumer data policies apply — by routing through AIsa, your data benefits from the negotiated ZDR protections.

⚠️ Important: Temperature restriction

Kimi K2.5 only accepts temperature=1.0. Using any other value will return an error:

Error: invalid temperature: only 1 is allowed for this model

If your OpenClaw config or agent sets a different temperature, override it for Kimi:

/model aisa/kimi-k2.5

OpenClaw will use the model's default temperature when not explicitly set.

Kimi K2.5 Pricing Comparison (per 1M tokens):

| Metric | AIsa | Moonshot Official | Savings | |--------|------|-------------------|---------| | Input/1M | ~$0.60 | ~$0.75 | ~20% off | | Output/1M | ~$2.40 | ~$3.00 | ~20% off |

> Actual pricing may vary. Check https://marketplace.aisa.one/pricing for real-time rates.

Additional Models Available via AIsa

Users can add any model supported by AIsa to their config. The full catalog includes 49+ models:

Qwen family (8 models):

qwen3-max, qwen3-max-2026-01-23, qwen-plus-2025-12-01
qwen-mt-flash, qwen-mt-lite
qwen-vl-max, qwen3-vl-flash, qwen3-vl-plus (vision models)

DeepSeek (4 models):

deepseek-v3.1, deepseek-v3, deepseek-v3-0324, deepseek-r1

Kimi / Moonshot (2 models):

kimi-k2.5, kimi-k2-thinking

Also available: Claude series (10), GPT series (9), Gemini series (5), Grok series (2), and more.

List all available models:

curl https://api.aisa.one/v1/models -H "Authorization: Bearer $AISA_API_KEY"

Model ID Versioning

...

Prompt 示例

安装 Chinese LLM Models (Kimi 2.5, MiniMax 2.5, Qwen, DeepSeek) with One Key 后，可以对 AI 说这些话来触发它

U

Help me get started with Chinese LLM Models (Kimi 2.5, MiniMax 2.5, Qwen, DeepSeek) with One Key

A

Explains what Chinese LLM Models (Kimi 2.5, MiniMax 2.5, Qwen, DeepSeek) with One Key does, walks through the setup, and runs a quick demo based on your current project

U

Use Chinese LLM Models (Kimi 2.5, MiniMax 2.5, Qwen, DeepSeek) with One Key to configure AIsa as a first-class model provider for OpenClaw, enabli...

A

Invokes Chinese LLM Models (Kimi 2.5, MiniMax 2.5, Qwen, DeepSeek) with One Key with the right parameters and returns the result directly in the conversation

U

What can I do with Chinese LLM Models (Kimi 2.5, MiniMax 2.5, Qwen, DeepSeek) with One Key in my ai agent & automation workflow?

常见问题

如何安装 Chinese LLM Models (Kimi 2.5, MiniMax 2.5, Qwen, DeepSeek) with One Key？▾

将技能文件夹放到 ~/.claude/skills/openclaw-aisa-chinese-llm-models/ 目录（个人级，所有项目可用），或 .claude/skills/openclaw-aisa-chinese-llm-models/（项目级）。重启 AI 客户端后，用 /openclaw-aisa-chinese-llm-models 主动调用，或让 AI 根据上下文自动发现并使用。

Chinese LLM Models (Kimi 2.5, MiniMax 2.5, Qwen, DeepSeek) with One Key 支持哪些 AI 平台？▾

Chinese LLM Models (Kimi 2.5, MiniMax 2.5, Qwen, DeepSeek) with One Key 支持 Claude、Cursor、OpenClaw，可与这些 AI 平台无缝集成，扩展其能力。

Chinese LLM Models (Kimi 2.5, MiniMax 2.5, Qwen, DeepSeek) with One Key 是免费的吗？▾

Chinese LLM Models (Kimi 2.5, MiniMax 2.5, Qwen, DeepSeek) with One Key 可免费安装使用。请查阅仓库了解许可证信息。

Chinese LLM Models (Kimi 2.5, MiniMax 2.5, Qwen, DeepSeek) with One Key 有什么功能？▾

Configure AIsa as a first-class model provider for OpenClaw, enabling production access to major Chinese AI models (Qwen, DeepSeek, Kimi K2.5, Doubao) throug...

使用场景

Getting Started with Chinese LLM Models (Kimi 2.5, MiniMax 2.5, Qwen, DeepSeek) with One Key→Automate AI Agent & Automation Workflows with Chinese LLM Models (Kimi 2.5, MiniMax 2.5, Qwen, DeepSeek) with One Key→Team Collaboration with Chinese LLM Models (Kimi 2.5, MiniMax 2.5, Qwen, DeepSeek) with One Key→

Chinese LLM Models (Kimi 2.5, MiniMax 2.5, Qwen, DeepSeek) with One Key

安装

关于 Chinese LLM Models (Kimi 2.5, MiniMax 2.5, Qwen, DeepSeek) with One Key

AIsa Provider for OpenClaw

Quick Setup

Option 1: Environment Variable (fastest)

Option 2: Interactive Onboarding

Option 3: CLI with Key

Option 4: Manual Config in `~/.openclaw/openclaw.json`

Available Models

Default Models (pre-configured, API-verified ✅)

⭐ Kimi K2.5 — Moonshot AI's Flagship Model

🔒 Zero Data Retention (ZDR) — Enterprise-Grade Privacy

Additional Models Available via AIsa

Model ID Versioning

Prompt 示例

常见问题

使用场景

同类技能推荐

self-improving-agent

Skill Vetter

ontology

Self-Improving + Proactive Agent

Chinese LLM Models (Kimi 2.5, MiniMax 2.5, Qwen, DeepSeek) with One Key

安装

关于 Chinese LLM Models (Kimi 2.5, MiniMax 2.5, Qwen, DeepSeek) with One Key

AIsa Provider for OpenClaw

Quick Setup

Option 1: Environment Variable (fastest)

Option 2: Interactive Onboarding

Option 3: CLI with Key

Option 4: Manual Config in ~/.openclaw/openclaw.json

Available Models

Default Models (pre-configured, API-verified ✅)

⭐ Kimi K2.5 — Moonshot AI's Flagship Model

🔒 Zero Data Retention (ZDR) — Enterprise-Grade Privacy

Additional Models Available via AIsa

Model ID Versioning

Prompt 示例

常见问题

使用场景

同类技能推荐

self-improving-agent

Skill Vetter

ontology

Self-Improving + Proactive Agent

Option 4: Manual Config in `~/.openclaw/openclaw.json`