DeepSeek: DeepSeek V4 Flash

deepseek · Released Apr 24, 2026
DFO score #61 / 753
32.2 leaderboard score
Speed #82 / 358
152.1 tok/s
Input Price #255 / 753
$0.090 per 1M tokens
Output Price #227 / 753
$0.180 per 1M tokens
Context #39 / 753
1M tokens

Analysis Summary

DeepSeek V4 Flash is a DeepSeek model released in April 2026, with a 1,048,576-token context window and support for tool use and function calling. Its coding index is 69.1 and agentic index is 41.0. The data also shows strong instruction following and long-context performance, so it can handle substantial inputs while supporting structured, multi-step tasks.

This profile fits code assistance, repository analysis, document-heavy work, and agent workflows where the model needs to call tools. It is text-only in the supplied modality data, so vision use is not established. Listed pricing is $0.0825 per million input tokens and $0.1649 per million output tokens, substantially below the Pro version in this batch. For teams that need technical capability at volume, Flash is the more practical first deployment; reserve Pro for cases where its additional cost is justified by testing.

Assessed September 23, 2026

Editorial notes

DeepSeek V4 Flash combines strong coding and tool-use results, a 1M-token context, function calling, and low listed token prices, making it well suited to high-volume technical workflows.

The DFO score ranks models on the Artificial Analysis Intelligence Index and is refreshed as new models launch. The write-up and verdict are our own. Feedback?

DFO Verdict

DeepSeek V4 Flash combines strong coding and tool-use results, a 1M-token context, function calling, and low listed token prices, making it well suited to high-volume technical workflows.

#61 of 753 overall Down 5 this week

Benchmarks

Intelligence Index 21.9 #61 of 456 · Artificial Analysis
Coding Index 44.1 #34 of 199 · Artificial Analysis
Agentic Index 26.2 #34 of 181 · Artificial Analysis
Creative Writing 1,408 #30 of 32 · Arena rating
Instruction Following 1,428 #35 of 35 · Arena rating
GPQA Diamond 89.4%
HLE 32.1%
SciCode 44.9%
TerminalBench Hard 35.6%
τ²-Bench 95%
IFBench 79.2%
LCR 63%

Artificial Analysis data refreshed Nov 17, 2026. Arena ratings from the Nov 9, 2026 text leaderboard, with style control. Bars: magenta = reasoning, ink = coding and agents, cyan = instructions and long context.

Artificial Analysis no longer lists this model, so its indexes are converted from their older scale to stay comparable.

How DeepSeek: DeepSeek V4 Flash compares

DeepSeek: DeepSeek V4 Flash ranks #61 of 456 AI models we track for overall intelligence, #34 of 199 for coding, #34 of 181 for agentic tasks. Its 1M-token context window is larger than 95% of the models we list. At $0.09 per million input tokens it is cheaper than 66% of comparable models.

Position in the field
DFO score: ahead of 92% of models #61
Speed: faster than 77% of models #82
Price: cheaper than 66% of models #255
Context: larger than 95% of models #39
worst in fieldmedianbest in field
Price vs frontier peers · $ per 1M tokens
DeepSeek: DeepSeek V4 Flash $0.09 in $0.18 out
Anthropic: Claude Fable 5.2 $8.00 in $40.00 out
Google: Gemini 4 Carbon $2.00 in $10.00 out
Google: Gemini 4 Argon $2.00 in $10.00 out

Dark bar = input · light bar = output, scaled to the priciest peer.

Context window vs peers · tokens

1M tokens ≈ 8 full-length novels or ~2,500 pages of business documents in a single request.

Pricing

Token Type Cost per 1M tokens Cost per 1K tokens
Input $0.09 $0.000090
Output $0.18 $0.000180

What would DeepSeek: DeepSeek V4 Flash cost your business?

Pick the job that looks most like yours, then fine-tune with the sliders. Estimates update live.

A website chatbot handling around 100 customer conversations a day, a few short messages each.

3,000
One request is one message, email, draft or automation call.
1,200 tokens

$0.421/mo DeepSeek: DeepSeek V4 Flash $0.0001 per request
$63.36/mo Anthropic: Claude Fable 5.2 $0.02 per request
$15.84/mo Google: Gemini 4 Carbon · best value $0.0053 per request

Full calculator with 753 models → Price Calculator

DFO AI AUTOMATION

These numbers get smaller with the right architecture.

We route routine calls to cheap models and save DeepSeek: DeepSeek V4 Flash for the hard ones. Most clients cut their estimate by 60-80%.

Talk to our team

About DeepSeek: DeepSeek V4 Flash

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and..

Frequently asked questions about DeepSeek: DeepSeek V4 Flash

How much does DeepSeek: DeepSeek V4 Flash cost?

DeepSeek: DeepSeek V4 Flash costs $0.09 per million input tokens and $0.18 per million output tokens.

What is the context window of DeepSeek: DeepSeek V4 Flash?

DeepSeek: DeepSeek V4 Flash has a context window of 1,048,576 tokens (1M).

Is DeepSeek: DeepSeek V4 Flash good for coding?

On our coding benchmark index, DeepSeek: DeepSeek V4 Flash ranks #34 of 199 models, placing it in the top quartile of the field for code generation and debugging.

What can DeepSeek: DeepSeek V4 Flash do?

DeepSeek: DeepSeek V4 Flash supports tool use and function calling.

Who created DeepSeek: DeepSeek V4 Flash?

DeepSeek: DeepSeek V4 Flash is developed by DeepSeek and was released on April 24, 2026.

© 2026 Design for Online Ltd. Registered in England and Wales No. 10328553. VAT Registered. Design for Online® and Forerunner® are registered trademarks.