deepseek-reasoner
Common Name: DeepSeek Reasoner
DeepSeek's reasoning model trained via large-scale reinforcement learning, comparable to OpenAI o1 on math, code, and reasoning tasks.
Specifications
Context
128K
Maximum Output
64K
Inputtext
Outputtext
Performance (7-day Average)
Collecting…
Collecting…
Collecting…
Pricing
Input¥2.00/MTokens
Cached Input¥0.20/MTokens
Output¥3.00/MTokens
Availability Trend (24h)
Performance Metrics (24h)
Similar Models
¥2.00/¥3.00/M
ctx128Kmax8Kavail—tps—
InOutCap
DeepSeek's conversational AI model for general-purpose chat and coding tasks with 128K context.
$2.75/$11.00/M
ctx128Kmax16Kavail—tps—
InOutCap
Preview version of GPT-4o with integrated web search for enhanced real-time knowledge and information access.
$2.75/$11.00/M
ctx128Kmax16Kavail—tps—
InOutCap
Latest preview of GPT-4o enhanced with web search capabilities for accessing up-to-date information.
$1.21/$4.84/M
ctx200Kmax100Kavail—tps—
A cost-efficient reasoning model that excels at STEM tasks, particularly science, math, and coding.