DeepSeek V4.1 Flash 1017

Provider: DeepSeek CN Official API price

Input price
$0.15
/ 1M tokens
Output price
$0.60
/ 1M tokens
Cache price
$0.003
/ 1M tokens (read)
Batch API
$0.029 / $0.25
input / output per 1M tokens
Context
1.05M tokens
Max output 393K tokens

Overview

DeepSeek V4.1 Flash 1017 is a budget sparse mixture-of-experts model built for high-throughput multimodal tasks across a 1M token context.

Strengths

  • 1048576 token input context window
  • 393216 token maximum output length
  • Supports vision, function calling, and thinking
  • Cached input priced at $0.003 per million

Best use cases

  • Long document analysis and extraction
  • Large context code base processing
  • High-volume structured data generation
  • Automated reasoning and tool calling

Pricing position

Standard pricing matches GPT-4o-mini and Mistral Small 4 at $0.15 input and $0.60 output per million tokens, while undercutting Gemini 2.5 Flash's $1.25 output rate.

Caveats

Batch API rates drop input to $0.011 and output to $0.20, making synchronous calls inefficient for non-latency-critical pipelines.

Notes drafted by an LLM from the figures on this page (2026-11-10) and rewritten when the price changes.

Key facts

Price basis
Official API price
Max output
393K tokens
Listed on OpenRouter
2026-10-17
Tracked since
2026-10-17
Last updated
2026-11-15

Features

Image inputFunction callingJSON outputReasoning

Price history

  • 2026-11-10 Price change $0.30 / $1.20 → $0.15 / $0.60
  • 2026-10-17 Added

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.04
1M (small app) 1 0.5 $0.45
10M (mid scale) 10 5 $4.50
100M (large) 100 50 $45.00

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from DeepSeek

Similar-priced models

Source: OpenRouter API (deepseek/deepseek-v4.1-flash-1017)