DeepSeek: R1

Text input Text output
Author's Description

DeepSeek R1 is here: Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass. Fully open-source model & [technical report](https://api-docs.deepseek.com/news/news250120). MIT licensed: Distill & commercialize freely!

Key Specifications
Cost
$$$
Context
128K
Parameters
671B (Rumoured)
Released
Jan 20, 2025
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Reasoning Temperature Min P Top Logprobs Structured Outputs Seed Logit Bias Stop Max Tokens Top P Response Format Frequency Penalty Presence Penalty Include Reasoning
Features

This model supports the following features:

Response Format Structured Outputs Reasoning
Performance Summary

DeepSeek R1, a 671B parameter open-source model with 37B active in inference, demonstrates strong performance across several key areas. It consistently ranks among the fastest models and offers highly competitive pricing, positioning it as an attractive option for various applications. In terms of benchmark performance, DeepSeek R1 achieves perfect accuracy in Email Classification and one of the Instruction Following benchmarks, indicating excellent precision in these tasks. It also shows strong capabilities in Coding (93.0% accuracy) and General Knowledge (96.5% accuracy). However, the model exhibits notable weaknesses in complex Reasoning, scoring 0.0% accuracy, and Mathematics, with a low 2.4% accuracy, suggesting these areas require significant improvement. Its hallucination rate is 94.0% accuracy, which is moderate. The model's performance in Ethics is solid at 96.0% accuracy. Overall, DeepSeek R1 presents a compelling open-source alternative, particularly for tasks requiring high accuracy in classification, instruction following, and coding, while offering speed and cost efficiency.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.3
Completion $1.2

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
InferenceNet
InferenceNet | deepseek/deepseek-r1 128K $0.3 / 1M tokens $1.2 / 1M tokens
DeepInfra
DeepInfra | deepseek/deepseek-r1 163K $0.7 / 1M tokens $2.4 / 1M tokens
Lambda
Lambda | deepseek/deepseek-r1 163K $0.3 / 1M tokens $1.2 / 1M tokens
Novita
Novita | deepseek/deepseek-r1 64K $0.3 / 1M tokens $1.2 / 1M tokens
Nebius
Nebius | deepseek/deepseek-r1 163K $0.3 / 1M tokens $1.2 / 1M tokens
DeepInfra
DeepInfra | deepseek/deepseek-r1 40K $1 / 1M tokens $3 / 1M tokens
Kluster
Kluster | deepseek/deepseek-r1 163K $0.3 / 1M tokens $1.2 / 1M tokens
Cent-ML
Cent-ML | deepseek/deepseek-r1 131K $0.3 / 1M tokens $1.2 / 1M tokens
Nebius
Nebius | deepseek/deepseek-r1 163K $0.3 / 1M tokens $1.2 / 1M tokens
Friendli
Friendli | deepseek/deepseek-r1 163K $0.3 / 1M tokens $1.2 / 1M tokens
Fireworks
Fireworks | deepseek/deepseek-r1 163K $0.3 / 1M tokens $1.2 / 1M tokens
Minimax
Minimax | deepseek/deepseek-r1 64K $0.3 / 1M tokens $1.2 / 1M tokens
Azure
Azure | deepseek/deepseek-r1 163K $1.49 / 1M tokens $5.94 / 1M tokens
Targon
Targon | deepseek/deepseek-r1 163K $0.3 / 1M tokens $1.2 / 1M tokens
Chutes
Chutes | deepseek/deepseek-r1 163K $0.3 / 1M tokens $1.2 / 1M tokens
Novita
Novita | deepseek/deepseek-r1 64K $0.56 / 1M tokens $2 / 1M tokens
Chutes
Chutes | deepseek/deepseek-r1 163K $0.3 / 1M tokens $1.2 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by deepseek