---
title: "DeepSeek-V4.1-Flash API pricing: ⁨$0.30⁩ in, ⁨$1.20⁩ out · DotsAgent"
description: "DeepSeek-V4.1-Flash by DeepSeek: price per million input, cached and output tokens, context window, agent features and what a real agent task costs on it."
url: https://dotsagent.io/models/deepseek-v4-1-flash
---

[DeepSeek](https://dotsagent.io/providers/deepseek)

· Flagship

# DeepSeek-V4.1-Flash API pricing and specs

DeepSeek's newest model, which DeepSeek says beats V4-Pro on quality, speed and price, and which accepts both OpenAI and Anthropic request formats.

Input

$0.30

Cached input

$0.006

Output

$1.20

US dollars per million tokens, standard tier, short-prompt rate

The old names deepseek-v4-flash and deepseek-v4-flash-vision-exp now route here. Cache hits cost $0.006 per million at peak and half that off-peak.

DeepSeek charges half price off-peak. Peak hours are 01:00 to 04:00 and 06:00 to 10:00 UTC on weekdays; every other hour, weekends included, is off-peak. The table shows peak prices.

## Spec sheet

- **API model string**: `deepseek-flash`
- **Provider**: [DeepSeek](https://dotsagent.io/providers/deepseek)
- **Context**: 1M tokens
- **Max output**: 384K tokens
- **Released**: September 10, 2026
- **Batch API**: No batch discount listed
- **Documented agent features**: Tool callingStructured outputAdjustable reasoningImage input

## What a task costs

Four reference workloads priced at this model's list rates, with caching applied after the first call. Your numbers will differ; the calculator lets you change every assumption.

| Workload | Per task | Per 1,000 tasks |
| --- | --- | --- |
| Support bot 4 calls, short tool lookups | $0.007 | $7 |
| Coding agent 30 calls, files and test output | $0.218 | $218 |
| Browser agent 25 calls, screenshots and page text | $0.186 | $186 |
| Research agent 15 calls, long search results | $0.180 | $180 |

[Change the assumptions](https://dotsagent.io/cost#model=deepseek-v4-1-flash)

## Other DeepSeek models

- [DeepSeek-V4-Pro-0813](https://dotsagent.io/models/deepseek-v4-pro-0813): $1.32 / $3.96

## Similar cost elsewhere

Models from other providers whose cost on the 30-step coding workload is closest to this one.

- [GLM-5.3-Flash](https://dotsagent.io/models/glm-5-3-flash): $0.182 per coding task

- [Gemini 3.5 Flash-Lite](https://dotsagent.io/models/gemini-3-5-flash-lite): $0.333 per coding task

- [Qwen3.7-Plus](https://dotsagent.io/models/qwen3-7-plus): $0.343 per coding task

- [Qwen3.7-Flash](https://dotsagent.io/models/qwen3-7-flash): $0.101 per coding task

## Sources

1. [api-docs.deepseek.com](https://api-docs.deepseek.com/quick_start/pricing)/quick_start/pricing
2. [api-docs.deepseek.com](https://api-docs.deepseek.com/updates)/updates
3. [api-docs.deepseek.com](https://api-docs.deepseek.com/news/news260910)/news/news260910

Independent reference for people who build AI agents. Not affiliated with any vendor named here.

© 2026 DotsAgent · Facts checked October 1, 2026