LLMPrice
Updated daily
DeepSeek · OpenRouter

DeepSeek V3.1 pricing

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...

OpenRouterOpenRouter API
Input$0.25per 1M tokens
Cached input$0.13per 1M tokens
Output$0.95per 1M tokens
Context164Kmaximum window
Endpoint and source

OpenRouter

Open OpenRouter API source ↗

This is OpenRouter route pricing from the public models API, not a claim about the creator's direct API price.

Tool useReasoningCachingHugging Face
2,000 input + 500 output tokens$0.000975 / request
Calculate a complete workload →