DEEPSEEK API
DeepSeek V3.2 and R1, ready to call.
Run DeepSeek's frontier models through an OpenAI-compatible endpoint. V3.2 handles general chat and code generation at high throughput. R1 delivers extended chain-of-thought reasoning for math, science, and complex analysis. Both models, one API key.
QUICK START
Integrate in minutes.
from openai import OpenAI
client = OpenAI(
base_url="https://api.runcrate.ai/v1",
api_key="rc_live_YOUR_API_KEY",
)
response = client.chat.completions.create(
model="deepseek-ai/DeepSeek-V3",
messages=[
{"role": "user", "content": "Explain the transformer architecture in simple terms."}
],
)
print(response.choices[0].message.content)AVAILABLE MODELS
Models you can use today.
| Model | Provider | Price | Detail |
|---|---|---|---|
| deepseek-ai/DeepSeek-V3 | DeepSeek | Per-token | 128K context, MoE architecture |
| deepseek-ai/DeepSeek-R1 | DeepSeek | Per-token | Extended reasoning, chain-of-thought |
WHY RUNCRATE
Built for production.
Mixture of Experts
DeepSeek V3.2 uses a Mixture-of-Experts architecture that activates only the parameters needed for each token, delivering frontier-quality output at lower compute cost.
Extended Reasoning
DeepSeek R1 generates detailed chain-of-thought traces before answering, excelling at math olympiad problems, code debugging, and multi-step logic.
128K Context Window
Feed entire codebases, research papers, or lengthy documents into a single prompt without truncation.
Drop-In Replacement
Uses the standard OpenAI chat completions format. Swap the base URL and model name, keep everything else.
COMPARISON
Runcrate vs DeepSeek Platform.
| Feature | Runcrate | DeepSeek Platform |
|---|---|---|
| API format | OpenAI-compatible | OpenAI-compatible |
| Region availability | US + EU | China-hosted |
| Rate limits | Flexible, credit-based | Strict tiers |
| Other models | 200+ (Llama, Qwen, Mistral...) | DeepSeek only |
| Billing | Prepaid credits (USD) | DeepSeek tokens (CNY) |
FAQ