Released 144 days after DeepSeek V3.2 · All DeepSeek releases
DeepSeek-V4-Flash, released April 2026, is a lightweight 284-billion-parameter sparse MoE with just 13 billion active parameters per token, supporting a one-million-token context window. It reaches roughly 10% of the inference FLOPs and 7% of the KV-cache memory of V3.2, using a hybrid of Compressed Sparse Attention (CSA) and Heavily Compressed Attention (HCA) for efficient long context. The model offers three reasoning modes, non-think, think-high, and think-max, plus a dedicated XML-based tool-call format that preserves reasoning content across tool-call boundaries for cleaner agentic loops. Its reasoning quality is reported to approach the larger V4-Pro on many tasks. Open-sourced under an MIT license with weights on Hugging Face, V4-Flash targets cost-conscious teams deploying long-context reasoning agents that need affordable million-token inference.
DeepSeek V4 Flash runs on 12 different routes through the Opper gateway. Compare residency, ZDR, and training posture at a glance — full data-handling detail per route below.
| Provider | Region | Zero data retention | Training | Input | Output |
|---|---|---|---|---|---|
| Multi | Not by default | No | $0.15 | $0.30 | |
| Multi | Not by default | No | $0.14 | $0.28 | |
| US | Zero data retention | No | $0.09 | $0.18 | |
| US | Not by default | No | $0.07 | $0.17 | |
| Multi | Zero data retention | No | $0.22 | $0.66 | |
| US | Zero data retention | No | $0.14 | $0.30 | |
| US | Not by default | No | $0.10 | $0.28 | |
| EU | Not by default | No | $0.14 | $0.28 | |
| EU | Not by default | No | $0.14 | $0.28 | |
| US | Zero data retention | No | $0.14 | $0.28 | |
| EU | Zero data retention | No | $0.14 | $0.28 | |
| EU | Zero data retention | No | $0.25 | $0.30 |
DeepSeek V4 Flash runs on 5 independently monitored routes through the Opper gateway. A direct integration leaves you on one of them, the gateway serves whichever is healthy.
Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. 7 further routes for this model are not on the board yet and are not counted above. See uptime for every provider Opper monitors.
Each route hosting DeepSeek V4 Flash has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.
Zero data retention is not on by default — abuse monitoring. No training on customer data. GLOBAL; SCCs; DPA available.
Zero data retention is not on by default — abuse monitoring, 180-day retention. No training on customer data. GLOBAL; SCCs; DPA available.
Zero data retention is on by default on Pay-as-you-go — no action required. No training on customer data. US; unknown; DPA available.
Zero data retention is not on by default — a moderation hold applies. No training on customer data. US; dpf sccs; DPA available.
Zero data retention is on by default on Pay-as-you-go — no action required. No training on customer data. GLOBAL; SCCs; DPA available.
Zero data retention is on by default on Pay-as-you-go — no action required. No training on customer data. US; SCCs; DPA available.
Zero data retention is not on by default — abuse monitoring, 30-day retention. No training on customer data. US; SCCs; DPA available.
Zero data retention is not on by default — abuse monitoring. No training on customer data. EU; DPA available.
Zero data retention is not on by default — provider logging, 90-day retention. No training on customer data. EEA; SCCs; DPA available.
Zero data retention is on by default on Pay-as-you-go — no action required. No training on customer data. US; SCCs; DPA available.
Zero data retention is on by default on Pay-as-you-go — no action required. No training on customer data. EEA; SCCs; DPA available.
Zero data retention is on by default on Pay-as-you-go — no action required. No training on customer data. EU; DPA available.
Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.
Call DeepSeek V4 Flash through the Opper gateway with one API key. Let your coding agent set it up, or call it directly — Opper is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.
Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up Opper for you.
import OpenAI from "openai";const client = new OpenAI({apiKey: process.env.OPPER_API_KEY,baseURL: "https://api.opper.ai/v3/compat",});const completion = await client.chat.completions.create({model: "alibaba:global/deepseek-v4-flash",messages: [{ role: "user", content: "Hello" }],});console.log(completion.choices[0].message.content);
Side-by-side on privacy, EU hosting, pricing, and benchmarks.
