Try Verda Inference
Moonshot AI
Available
Kimi K3.1 Pro
- Context
- 1M tokens
- Input
- Text & Image
- Tool calling
- Supported
curl -X POST "https://inference.verda.com/v1/chat/completions" \ -H "Authorization: Bearer ${VERDA_INFERENCE_API_KEY}" \ -H "Content-Type: application/json" \ -d '{ "model": "kimi-k3-1-pro", "messages": [{"role": "user", "content": "What is the best viewpoint in Helsinki?"}], "max_tokens": 2048 }'
// Save to ~/.config/opencode/opencode.jsonc // Export VERDA_INFERENCE_API_KEY, then run: opencode service restart { "$schema": "https://opencode.ai/config.json", "model": "verda/kimi-k3-1-pro", "provider": { "verda": { "npm": "@ai-sdk/openai-compatible", "options": { "baseURL": "https://inference.verda.com/v1", "apiKey": "{env:VERDA_INFERENCE_API_KEY}" }, "models": { "kimi-k3-1-pro": { "modalities": { "input": [ "text", "image" ], "output": [ "text" ] } } } } } }
import os from openai import OpenAI client = OpenAI( base_url=f"{os.environ['VERDA_INFERENCE_BASE_URL']}/v1", api_key=os.environ["VERDA_INFERENCE_API_KEY"], ) resp = client.chat.completions.create( model="kimi-k3-1-pro", messages=[{"role": "user", "content": "What is the best viewpoint in Helsinki?"}], max_tokens=2048, ) print(resp.choices[0].message.content or resp.choices[0].message.reasoning_content) print(resp.usage)
