DeepSeek: DeepSeek V4 Flash
Try DeepSeek V4 Flash for free in your browser, and add it to your app for free with Puter.js AI API.
Try it free Add to your app// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';
puter.ai.chat("Explain quantum computing in simple terms", {
model: "deepseek/deepseek-v4-flash"
}).then(response => {
document.body.innerHTML = response.message.content;
});
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
puter.ai.chat("Explain quantum computing in simple terms", {
model: "deepseek/deepseek-v4-flash"
}).then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
Model Card
DeepSeek V4 Flash is a lightweight, efficiency-focused Mixture-of-Experts model from DeepSeek, with 284B total parameters and 13B activated per token. It supports a 1M-token context window and configurable reasoning modes (standard, high, and max thinking effort).
Designed as the fast and economical option in the V4 family, Flash delivers reasoning capabilities that closely approach the larger V4 Pro, and performs on par with it on simpler agentic tasks. In its max reasoning mode, it achieves comparable reasoning scores to Pro when given a larger thinking budget.
At $0.20/M input and $0.40/M output tokens, it's one of the cheapest frontier-tier models available — well suited for high-throughput workloads like coding assistants, chat systems, and agent pipelines where latency and cost matter most.
Context Window 1M
tokens
Max Output 384K
tokens
Input Cost $0.07
per million tokens
Output Cost $0.14
per million tokens
Input text
modalities
Tool Use Yes
Knowledge Cutoff May 2025
Release Date Apr 24, 2026
Try DeepSeek V4 Flash for free
Try DeepSeek V4 Flash instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.
Benchmarks
How DeepSeek V4 Flash performs on standard evaluations.
| Benchmark | Score |
|---|---|
| GPQA Diamond Graduate-level science Q&A | 90.8% |
| Humanity's Last Exam Cross-domain reasoning | 38.6% |
| SciCode Scientific programming | 50.3% |
| LCR Long-context reasoning | 79.7% |
Scores sourced from Artificial Analysis.
Find other DeepSeek models →
DeepSeek V4.1 Flash 1017
DeepSeek V4.1 Flash 1017 is DeepSeek's October 17, 2026 update to its V4.1 Flash chat model. DeepSeek calls it a minor update that finishes tasks faster and with shorter outputs, with unchanged API usage and pricing. In DeepSeek's own tests it improved on the September V4.1 Flash release on DeepSWE v1.1 (77.0 vs 74.2), Terminal-Bench 4.0 (42.3 vs 31.2), HLE without tools (42.6 vs 36.8), and ProgramBench (29.1 vs 20.3). It accepts text and image input, supports tool calling and a reasoning effort parameter, and has a context window of about 1M tokens. DeepSeek recommends its Harness agent framework at version 0.2.1-rc.1 or later. At $0.30/M input and $1.20/M output tokens on OpenRouter, it suits coding agents, tool-calling pipelines, and long-context workloads.
ChatDeepSeek V4.1 Flash
DeepSeek V4.1 Flash is DeepSeek's fast, low-cost chat model, a 552B-parameter Mixture-of-Experts system using a new causal encoder-decoder design that activates 8B parameters while reading a prompt and 16B while generating a response. It succeeds DeepSeek V4 Flash, keeping a 1,000,000-token context window and adding a continuously adjustable reasoning effort setting (1-100). DeepSeek reports it beating the larger V4 Pro on performance, cost, speed, and total runtime. In DeepSeek's own tests it scored 90.6 on Terminal-Bench 2.1, ahead of Claude Opus 5 (89.1) and GPT-5.6 Sol (88.8), 88.1 on CyberGym versus 84.5 for GPT-5.6 Sol and GLM 5.3, and 74.2 on DeepSWE v1.1 versus 74.0 for Claude Opus 5. It supports tool calling, and DeepSeek says its KV cache footprint is about a quarter of V4 Flash's for cheaper long-context serving. At $0.11/M input and $0.45/M output tokens, it fits high-throughput coding agents, tool-calling pipelines, and long-context workloads.
ChatDeepSeek V4 Flash Vision Experimental
DeepSeek V4 Flash Vision Experimental is an experimental multimodal version of DeepSeek's V4 Flash model, released by DeepSeek in August 2026. It is a sparse Mixture-of-Experts model with 284B total parameters and 13B activated per token, and it accepts images (JPEG, PNG, GIF, WebP) alongside text through the same API used for V4 Flash. DeepSeek reports that it matches V4 Flash on text tasks including agentic reasoning and world knowledge, while adding image understanding for document and chart parsing, visual question answering, and agent workflows that interleave text and images. On multimodal agent benchmarks, DeepSeek's own numbers show gains over the text-only V4 Flash, with Terminal Bench 2.1 rising from 82.7 to 83.9, ApexBench from 26.2 to 36.5, and Agents' Last Exam from 25.2 to 27.3, approaching Anthropic's Opus 4.8 (85.0 on Terminal Bench 2.1). On NL2Repo it trails Opus 4.8, 57.7 versus 69.7.
Frequently Asked Questions
You can access DeepSeek V4 Flash by DeepSeek through Puter.js AI API. Include the library in your web app or Node.js project and start making calls with just a few lines of JavaScript — no backend and no configuration required. You can also use it with Python or cURL via Puter's OpenAI-compatible API.
DeepSeek V4 Flash is free to try with a Puter account. Every account includes a free AI allowance, and you can chat with it in the playground on this page. You can upgrade your account anytime for a larger allowance.
DeepSeek V4 Flash is free to integrate using the Puter.js AI API. With the User-Pays Model, you can add AI to your app for $0, since users cover their own AI usage through their Puter account.
| Price per 1M tokens | |
|---|---|
| Input | $0.07 |
| Output | $0.14 |
DeepSeek V4 Flash was created by DeepSeek and released on Apr 24, 2026.
DeepSeek V4 Flash supports a context window of 1M tokens. For reference, that is roughly equivalent to 2,000 pages of text.
DeepSeek V4 Flash can generate up to 384K tokens in a single response.
DeepSeek V4 Flash has a knowledge cutoff date of May 2025. This means the model was trained on data available up to that date.
DeepSeek V4 Flash accepts the following input types: text. It produces: text.
Yes, DeepSeek V4 Flash supports tool use (function calling), allowing it to interact with external tools, APIs, and data sources as part of its response flow.
DeepSeek V4 Flash scores 34.3 on the Artificial Analysis Intelligence Index, outperforming 86% of tracked models. On coding, it scores 69.1 (outperforms 78% of models).
Yes — the DeepSeek V4 Flash API works with any JavaScript framework, Node.js, or plain HTML through Puter.js. Just include the library and start building. See the documentation for more details.
Add DeepSeek V4 Flash to your app for free
Developers can integrate DeepSeek V4 Flash for free using the Puter.js AI API.
With the User-Pays Model, each user covers their own AI usage instead of the developer.