LangChain

pip install -U langchain-runcrate

export RUNCRATE_API_KEY="rc_live_..."

from langchain_runcrate import ChatRuncrate

llm = ChatRuncrate(model="deepseek-ai/DeepSeek-V3.2", temperature=0)

print(llm.invoke("Explain LoRA fine-tuning in one sentence.").content)

from langchain_runcrate import ChatRuncrate

llm = ChatRuncrate(
    model="deepseek-ai/DeepSeek-V3.2",
    api_key="rc_live_...",                  # or the RUNCRATE_API_KEY env var
    base_url="https://api.runcrate.ai/v1",  # default; or the RUNCRATE_API_BASE env var
    temperature=0.2,
    max_tokens=1024,
)

for chunk in llm.stream("Write a haiku about GPUs."):
    print(chunk.text, end="", flush=True)

from langchain_core.tools import tool


@tool
def gpu_price(gpu: str) -> str:
    """Return the hourly price of a GPU."""
    return "see https://www.runcrate.ai/api/gpu-pricing"


llm_with_tools = llm.bind_tools([gpu_price])
message = llm_with_tools.invoke("What does an H100 cost per hour?")
print(message.tool_calls)

from pydantic import BaseModel


class Summary(BaseModel):
    title: str
    bullets: list[str]


summary = llm.with_structured_output(Summary).invoke("Summarize what a GPU cloud is.")
print(summary.title, summary.bullets)

from langchain.agents import create_agent

agent = create_agent(
    ChatRuncrate(model="Qwen/Qwen3-235B-A22B-Instruct-2507"),
    tools=[gpu_price],
)
agent.invoke({"messages": [{"role": "user", "content": "Price an H100 for 10 hours."}]})