All integrations
Python framework
How to Use Ruvicode with LangChain
LangChain's ChatOpenAI class talks to any OpenAI-compatible API. Pointing it at Ruvicode gives every chain and agent in your code access to the whole model catalog, tool calling included.
Tested on November 3, 2026. langchain-openai 1.7.3 returned a plain answer and a tool call with its arguments through api.ruvicode.com with the code below.
Set up LangChain
Base URL
https://api.ruvicode.com/v1
API key
rvcd_...
- 1Install the package: pip install langchain-openai.
- 2Create ChatOpenAI with base_url https://api.ruvicode.com/v1, your rvcd_ key and a model id from the catalog.
- 3Use it like any LangChain chat model: invoke, stream, bind_tools, or inside an agent.
import os
from langchain_openai import ChatOpenAI
llm = ChatOpenAI(
model="glm-5.3-flash",
api_key=os.environ["RUVICODE_API_KEY"],
base_url="https://api.ruvicode.com/v1",
)
print(llm.invoke("Hello").content)def get_weather(city: str) -> str:
"""Get the weather for a city."""
return "sunny"
msg = llm.bind_tools([get_weather]).invoke("What is the weather in Paris?")
print(msg.tool_calls) # [{'name': 'get_weather', 'args': {'city': 'Paris'}, ...}]Good to know
- Switch models by changing the model argument; the base URL and key stay the same for Claude, GPT, Gemini, GLM, Kimi and the rest.
- Leave use_responses_api off. Ruvicode serves chat completions, not the Responses API.
Models for coding agents
These models completed streamed tool calls through Ruvicode on November 3, 2026. Every model in the catalog works with the same base URL and key; each model page shows its live rate, context window and max output.
- GLM 5.3 Flash
glm-5.3-flash - Claude Sonnet 5.5
claude-sonnet-5.5 - Kimi K2.7 Code
kimi-k2.7-code
Common errors
- 401 Invalid API key
- The key is mistyped, revoked or not a Ruvicode key. Copy it again from the dashboard; it starts with rvcd_.
- 404 Model not found
- The model id is not in the catalog. Use an id exactly as listed on the models page or by GET /v1/models. A plain 404 page instead of a JSON error means the base URL is missing /v1.
- 402 insufficient_balance
- The wallet cannot cover the request. Top up in the dashboard; the balance never expires.
- 429 rate limit
- Too many requests per minute, on the key or across the account. Agents that fire many calls in parallel can hit it; most tools retry on their own after a short wait.
LangChain with Ruvicode: FAQ
- Does LangChain tool calling work through Ruvicode?
- Yes. bind_tools sends OpenAI-style tools, and the model's tool calls come back with their arguments intact. GLM 5.3 Flash returned get_weather with city Paris in our test.
- Where do I get a Ruvicode API key?
- Create an account, top up your wallet with QRIS or USDC, then open API Keys in the dashboard and create a key. Keys start with rvcd_. You can set a daily or monthly spend limit per key and restrict a key to a list of models.
Guides for other tools
The same base URL and key work everywhere. Setup for each tool: