Skip to main content
Models with 1M+ token context windows can process entire books, codebases, and document collections in a single request — no chunking, no RAG pipeline, no lost context. Send the full text and ask questions directly.

​
Models with 1M+ context

ModelContext windowStrengths
deepseek-ai/DeepSeek-V4-Pro1M tokensStrong reasoning, good at code and legal analysis
google/gemini-2.5-flash1M tokensFast, cost-effective for bulk processing
anthropic/claude-4-sonnet1M tokensPrecise instruction following, nuanced writing
All three models are available through the same API — switch between them by changing the model string.

​
Analyze an entire codebase

Load every file from a project into a single prompt: 
from openai import OpenAI
from pathlib import Path

client = OpenAI(
    base_url="https://api.runcrate.ai/v1",
    api_key="rc_live_YOUR_API_KEY",
)

def load_codebase(root: str, extensions: list[str] = [".py", ".ts", ".tsx"]) -> str:
    """Concatenate all source files into a single string."""
    parts = []
    for ext in extensions:
        for path in sorted(Path(root).rglob(f"*{ext}")):
            if "node_modules" in str(path) or ".git" in str(path):
                continue
            relative = path.relative_to(root)
            content = path.read_text(errors="ignore")
            parts.append(f"--- {relative} ---\n{content}")
    return "\n\n".join(parts)

codebase = load_codebase("./my-project")
print(f"Loaded {len(codebase):,} characters")

response = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-V4-Pro",
    messages=[
        {"role": "system", "content": "You are a senior software architect reviewing a codebase."},
        {"role": "user", "content": f"Here is the full codebase:\n\n{codebase}\n\nIdentify the top 5 architectural issues, security vulnerabilities, and performance bottlenecks. For each, cite the exact file and line range."},
    ],
    max_tokens=4096,
)
print(response.choices[0].message.content)

from openai import OpenAI
from pathlib import Path

client = OpenAI(
    base_url="https://api.runcrate.ai/v1",
    api_key="rc_live_YOUR_API_KEY",
)

contract = Path("master-services-agreement.txt").read_text()

response = client.chat.completions.create(
    model="anthropic/claude-4-sonnet",
    messages=[
        {"role": "system", "content": "You are a corporate attorney. Analyze contracts precisely, citing specific sections."},
        {"role": "user", "content": f"Full contract:\n\n{contract}\n\nCreate a risk summary: list every clause that creates financial liability, termination risk, or IP assignment. For each, provide the section number, a one-sentence summary, and a risk rating (low/medium/high)."},
    ],
    max_tokens=4096,
)
print(response.choices[0].message.content)

​
Research paper synthesis

The same pattern works for research: load multiple papers into a single prompt and ask google/gemini-2.5-flash to synthesize findings, map agreements and contradictions, and identify gaps. Gemini’s fast inference keeps costs low even for very long inputs.

​
Next steps