deepseek-reasoner

Common Name: DeepSeek Reasoner

DeepSeek
Released on Feb 17 12:00 AMKnowledge Cutoff Jan 1 12:00 AM

DeepSeek's reasoning model trained via large-scale reinforcement learning, comparable to OpenAI o1 on math, code, and reasoning tasks.

Specifications

Context128,000
Maximum Output64,000
Inputtext
Outputtext

Performance (7-day Average)

Uptime
TPS
RURT

Pricing

Input¥2.00/MTokens
Cached Input¥0.20/MTokens
Output¥3.00/MTokens

Usage Statistics

No usage data available for this model during the selected period
View your usage statistics for this model

Similar Models

¥2.00/¥3.00/M
ctx128Kmax8Kavailtps
InOutCap

DeepSeek's conversational AI model for general-purpose chat and coding tasks with 128K context.

$2.75/$11.00/M
ctx128Kmax16Kavailtps
InOutCap

Preview version of GPT-4o with integrated web search for enhanced real-time knowledge and information access.

$2.75/$11.00/M
ctx128Kmax16Kavailtps
InOutCap

Latest preview of GPT-4o enhanced with web search capabilities for accessing up-to-date information.

$1.21/$4.84/M
ctx200Kmax100Kavailtps
InOutCap

A cost-efficient reasoning model that excels at STEM tasks, particularly science, math, and coding.

Documentation

No documentation available
This model (deepseek-reasoner) uses a dedicated API. Please refer to the official documentation for usage examples.