# LiteLLM Connection Details for OpenCode

## Quick Connect

| Setting | Value |
|---------|-------|
| **Base URL** | `http://litellm.nxtgauge-ai.svc.cluster.local:4000/v1` |
| **API Key** | `sk-litellm-prod-1c66d63e701c32cd85922a62fd2e087469486a9b7a34d950423a8726d0aceec9` |

## Available Models

- `askash-main` - Primary model (Ollama gemma3:270m)
- `askash-fast` - Faster response variant
- `coding-main` - Optimized for code tasks

## OpenCode Configuration

### Option 1: Environment Variables

```bash
export OPENAI_API_KEY="sk-litellm-prod-1c66d63e701c32cd85922a62fd2e087469486a9b7a34d950423a8726d0aceec9"
export OPENAI_API_BASE="http://litellm.nxtgauge-ai.svc.cluster.local:4000/v1"
export LLM_MODEL="askash-main"
```

### Option 2: Config File

Create `~/.config/opencode/config.json`:

```json
{
  "provider": "openai",
  "apiKey": "sk-litellm-prod-1c66d63e701c32cd85922a62fd2e087469486a9b7a34d950423a8726d0aceec9",
  "baseUrl": "http://litellm.nxtgauge-ai.svc.cluster.local:4000/v1",
  "model": "askash-main"
}
```

### Option 3: .opencode File (Project-specific)

Create `.opencode` in your project root:

```json
{
  "llm": {
    "provider": "openai",
    "apiKey": "sk-litellm-prod-1c66d63e701c32cd85922a62fd2e087469486a9b7a34d950423a8726d0aceec9",
    "baseUrl": "http://litellm.nxtgauge-ai.svc.cluster.local:4000/v1",
    "model": "askash-main"
  }
}
```

## Test Connection

```bash
# List models
curl http://litellm.nxtgauge-ai.svc.cluster.local:4000/v1/models \
  -H "Authorization: Bearer sk-litellm-prod-1c66d63e701c32cd85922a62fd2e087469486a9b7a34d950423a8726d0aceec9"

# Chat completion
curl http://litellm.nxtgauge-ai.svc.cluster.local:4000/v1/chat/completions \
  -H "Authorization: Bearer sk-litellm-prod-1c66d63e701c32cd85922a62fd2e087469486a9b7a34d950423a8726d0aceec9" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "askash-main",
    "messages": [{"role": "user", "content": "Hello"}]
  }'
```

## Port-Forward (If Running Locally)

If you need to access from your local machine:

```bash
kubectl port-forward svc/litellm 4000:4000 -n nxtgauge-ai
```

Then use: `http://localhost:4000/v1`

## Troubleshooting

| Issue | Solution |
|-------|----------|
| Connection refused | Run `kubectl port-forward svc/litellm 4000:4000 -n nxtgauge-ai` |
| 401 Unauthorized | Check API key is correct |
| 404 Not Found | Ensure URL ends with `/v1` |
| Timeout | Model may be loading; retry |

## Verify LiteLLM is Running

```bash
kubectl get pods -n nxtgauge-ai -l app=litellm
```

---

**Last Updated**: 2026-06-14
**Namespace**: nxtgauge-ai
**Service**: litellm:4000