Skip to main content

​
Quick Setup

1

Get your API key

Sign up at kymaapi.com/signup. You’ll get your API key instantly + $0.50 free credits.
2

Configure OpenClaw

Edit ~/.openclaw/openclaw.json:
{
  "models": {
    "providers": {
      "kyma": {
        "baseUrl": "https://kymaapi.com/v1",
        "apiKey": "ky-YOUR_API_KEY_HERE",
        "api": "openai-completions",
        "models": [
          { "id": "gemma-4-31b", "name": "Gemma 4 31B" },
          { "id": "deepseek-v3", "name": "DeepSeek V3" },
          { "id": "qwen-3.6-plus", "name": "Qwen 3.6 Plus" },
          { "id": "kimi-k2.5", "name": "Kimi K2.5" },
          { "id": "qwen-3-32b", "name": "Qwen 3 32B" }
        ]
      }
    }
  },
  "agents": {
    "defaults": {
      "model": {
        "primary": "kyma/gemma-4-31b"
      }
    }
  }
}
Replace ky-YOUR_API_KEY_HERE with your actual key.
Use 127.0.0.1 instead of localhost if you experience IPv6 connection issues.
3

Start coding

openclaw
That’s it. OpenClaw will use Gemma 4 31B by default. Switch models anytime by changing the primary field.
ModelAliasBest ForContext
Kimi K2.5codeRecommended — best tool calling, agentic workflows262K
Qwen 3.6 PlusbestHighest quality overall131K
MiniMax M2.5—SWE-bench 80.2%, top coding196K
Qwen 3 Coder—Purpose-built for code131K
GPT-OSS 20BcheapLowest cost128K
Use model aliases like code or best — they auto-update when better models become available.
# Get personalized recommendation
curl "https://kymaapi.com/v1/models/recommend?agent=openclaw"

​
Choosing a model

  • Agentic coding: Use code (Kimi K2.5) for autonomous tool use
  • Quality: Use best (Qwen 3.6 Plus) for complex reasoning
  • Speed: Use qwen-3-32b for fast iteration
  • Budget: Use cheap (GPT-OSS 20B) for simple tasks

​
Switch Models

Change the default model in your config: 
"primary": "kyma/code"
Or add multiple models and switch between them in OpenClaw.

​
Auto-Failover

Kyma automatically handles provider failures:
  • If the primary infrastructure for your model is down, Kyma retries on backup infrastructure
  • Most failures are invisible — you get a response without noticing
  • Check X-Kyma-Fallback response header to know if a fallback was used

​
Troubleshooting

Make sure you’re using https://kymaapi.com/v1 (not localhost). Kyma is a cloud API — no local setup needed.
Check the model ID is correct. Use GET https://kymaapi.com/v1/models to see all available models.
Your free 0.50creditsmayhavebeenusedup.Addmorecreditsat[kymaapi.com/dashboard/credits](https://kymaapi.com/dashboard/credits).Packagesstartat0.50 credits may have been used up. Add more credits at [kymaapi.com/dashboard/credits](https://kymaapi.com/dashboard/credits). Packages start at 5.
Try a faster model like qwen-3-32b or llama-3.1-8b. Larger models (DeepSeek V3, Qwen 3.6 Plus) take longer but produce higher quality output.

​
Prompt Caching

Prompt caching is automatic. Your system prompt and tool definitions are cached for 5 minutes, reducing costs by up to 90% on subsequent requests. No code changes needed. See Prompt Caching for details.