Pro/deepseek-ai/DeepSeek-R1

Pro/deepseek-ai/DeepSeek-R1

Directly use all open-source models of silicon-based flow at 302.AI.
2025-02-07
LLM
Input:
$0.6/1M tokens
Output:
$2.3/1M tokens
Bulk order? Contact your manager for exclusive deals

API Overview

DeepSeek-R1, launched by the Chinese tech company DeepSeek, is an open-source large-scale model specializing in complex task reasoning. During its post-training phase, the model extensively incorporates reinforcement learning techniques, significantly enhancing its logical reasoning capabilities even with minimal labeled data. R1 excels particularly in scenarios such as mathematical, code, and natural language reasoning, with performance now rivaling that of leading international models like OpenAI o1. Its open-source nature and free commercial availability, combined with a range of versions spanning from 1.5 billion to 70 billion parameters, allow for flexible deployment based on computational resources—making it suitable for everything from notebook-level environments to enterprise-grade private deployments.

Playground

Log in to explore more features! Click to Log In

API Analytics

API Reference (1)

API DescriptionAPI EndpointRequest MethodStabilityParameter Description
Chat(SiliconFlow)
POST
Stable
View Details

API Pricing

$
ModelDescriptionContextOfficial Price302.AI Price

Pro/deepseek-ai/DeepSeek-R1

-
64000

Input$0.6 / 1M tokens
Output$2.3 / 1M tokens

Input$0.6/ 1M tokens
Output$2.3/ 1M tokens
Original Price