Hub/Models/deepseek/deepseek-chat-v3.1
deepseektext → text

DeepSeek: DeepSeek V3.1

Canonical ID: deepseek/deepseek-chat-v3.1

Compare ModelOpen on OpenRouter →

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...

Artificial Analysis Benchmarks

Verified
No standardized Artificial Analysis benchmark scores recorded for this variant yet.

Token Pricing & Economics

Prompt Input (1M Tokens)
$0.25
Input
Completion Output (1M Tokens)
$0.95
Output
Prompt KV-Cache Read (1M Tokens)
$0.13
Cached
Context Window Capacity
160k tokens
Context

Supported Parameters & Features

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p