DeepSeek V4 Flash Official Release: The Cheap, Fast, Agentic 1M-Context Model, Explained

DeepSeek's efficiency model, V4 Flash, has graduated from preview to an official public-beta release — the code>-0731/code> build shipped on July 31, 2026. The architecture didn't change (it's still a 284-billion-parameter mixture-of-experts model with a 1-million-token context), but a round of additional post-training sharply improved its agentic, coding, and tool-calling abilities, and it now natively supports the Responses API with specific adaptations for Codex-style agents. This guide explains what V4 Flash is, what the official release actually upgraded, how its (DeepSeek-reported) benchmarks read, what it costs, and how to use it — every figure labeled by source.

Accuracy note: the release details and benchmark scores below are from DeepSeek's official API change log (dated 2026-07-31); architecture, context, and pricing are cross-checked against OrcaRouter's model page; the Artificial Analysis composites are independent. DeepSeek-reported benchmarks use its own harness settings — treat them as vendor figures and run your own evals. Specs and prices change; verify before building.

TL;DR. V4 Flash is the cost-efficient sibling of the giant DeepSeek V4 Pro: a 284B / 13B-active MoE with a 1M-token context and up to 384K output, tuned for high-volume, low-latency, agentic work. The July 31 official release is a post-training upgrade — same size, materially better agents and coding — that also adds native Responses-API and Codex support. DeepSeek reports strong agentic/coding scores (e.g., Terminal-Bench 2.1 82.7, Toolathlon 70.3), and it costs about $0.15 / $0.29 per million input/output tokens, roughly a third of V4 Pro's price. Only the Flash API was upgraded; V4 Pro and the DeepSeek app/web are unchanged. On OrcaRouter you get it at 0% markup through one OpenAI-compatible endpoint.

Key takeaways

• Official release (build -0731, July 31, 2026): a post-training upgrade of the preview — same architecture, much stronger agents, coding, and tool use.

• Architecture unchanged: 284B total / 13B active (MoE), 1M-token context (1,048,576), up to 384K output, text-only input, with reasoning, tools, and JSON.

• New: native Responses API support plus specific Codex adaptation; continues to support OpenAI ChatCompletions and Anthropic-style interfaces. Model id code>deepseek-v4-flash/code>.

• DeepSeek-reported agentic/coding gains: Terminal-Bench 2.1 82.7, Toolathlon (verified) 70.3, Cybergym 76.7, DeepSWE 54.4, NL2Repo 54.2, DSBench-FullStack 68.7.

• Very cheap: about $0.15 / $0.29 per 1M input/output tokens with ~$0.02 cache reads (OrcaRouter, 0% markup) — roughly a third of V4 Pro's $0.44 / $0.88. Only the Flash API changed; Pro and app/web are the same.

What the official release actually upgraded

V4 Flash first appeared as a preview on April 24, 2026. The July 31, 2026 official release (the code>-0731/code> build, per DeepSeek's API change log) is explicitly not a new architecture: total and active parameters (284B / 13B) and the 1M context are unchanged. What changed is post-training — extra fine-tuning that DeepSeek says significantly improved core agentic, coding, and tool-calling capabilities. Two practical additions matter: V4 Flash now natively supports the Responses API and is specifically adapted for Codex-style coding agents, while still speaking OpenAI ChatCompletions and Anthropic-style interfaces. Importantly, only the Flash API was upgraded in this release; V4 Pro and the DeepSeek app/web experiences are unchanged. For teams, that means a drop-in improvement for agentic workloads at the same price, with no migration.

Architecture: a small-active MoE built for throughput

V4 Flash is a mixture-of-experts model with roughly 284 billion total parameters but only about 13 billion active per token. That low active-parameter count is the point: it keeps inference fast and cheap while a large expert pool preserves quality. The context window is a full 1,048,576 tokens (about 1M), with a very large 384K maximum output, and the model supports reasoning (extended thinking), tool calling, and structured JSON. Input is text-only. The design goal — high-volume, low-latency, agentic work — shows up in the serving numbers: a p50 time-to-first-token around 394 milliseconds and output around 184 tokens per second on OrcaRouter's measurements.

Benchmarks: what the official numbers say

The official release leans hard on agentic and coding evaluations, run with DeepSeek's own harness (minimal-mode / max-effort settings). Here's how to read the headline results, all DeepSeek-reported:

• Terminal-Bench 2.1: 82.7 — agentic command-line/software tasks in a real terminal. A high score here signals a model that can actually drive tools and shells, not just answer questions.

• Toolathlon (verified): 70.3 and Automation Bench (Public): 25.1 — breadth and reliability of tool use and end-to-end automation. Tool-calling reliability is the make-or-break trait for agents.

• Cybergym: 76.7 — security/CTF-style agentic problem solving.

• DeepSWE: 54.4, NL2Repo: 54.2, DSBench-FullStack: 68.7, DSBench-Hard: 59.6 — software-engineering and full-stack coding, from repo-level generation to hard data-science tasks. Strong DSBench-FullStack (68.7) points to practical, multi-file coding competence.

• Agent Last Exam: 25.2 — a deliberately hard agentic reasoning gauntlet where even top models score low; useful as a relative signal, not an absolute.

For independent context, Artificial Analysis (evaluated 2026-06-25, preview build) placed V4 Flash around 56.2 AA Coding, 40.3 AA Intelligence, and 50.0 AA Math — a coding-leaning generalist above the open-model median. The official post-training bump is aimed squarely at the agentic/coding axis, so expect the newer build to feel stronger on exactly those tasks. As always, vendor-harness numbers run optimistic; validate on your own workloads.

Pricing: the number that changes budgets

On OrcaRouter, which passes provider pricing through at 0% markup, V4 Flash is about $0.15 per million input tokens and $0.29 per million output tokens, with cache reads around $0.02 — and DeepSeek kept pricing low in this release (no increase for the upgrade). That's roughly a third of DeepSeek V4 Pro's $0.44 / $0.88. In real terms: 10 million tokens a month at a 70% input / 30% output split runs on the order of a couple of dollars on V4 Flash; scale to a billion tokens and the gap versus a flagship becomes a line item finance notices. Prompt caching cuts it further for agents and chat with a stable system prompt, since cached input is billed at roughly a tenth of fresh input. Cheaper agentic capability at the same low price is the entire pitch of this release.

Where V4 Flash fits: the DeepSeek V4 ladder

DeepSeek's V4 line is a ladder. V4 Pro is the flagship — a much larger, top-tier reasoning-and-coding model. V4 Flash is the efficiency tier: far less active compute, a fraction of the price, and, after this post-training upgrade, genuinely strong agentic and coding ability. The fact that DeepSeek invested in making Flash a better agent (Responses API, Codex adaptation, tool-use benchmarks) tells you where it expects the volume to run: everyday agentic and coding traffic on Flash, the hardest reasoning reserved for Pro. That mirrors the whole industry's cheap-default-plus-premium-flagship pattern — and it's why routing by difficulty beats defaulting to the biggest model.

Three real-world scenarios

1. Coding agents and Codex-style workflows

The -0731 build's native Responses-API and Codex support, plus its Terminal-Bench (82.7) and DSBench-FullStack (68.7) scores, make V4 Flash a strong, cheap engine for autonomous coding agents — issue-fixing, refactors, test generation, multi-step tool use.

2. High-volume tool-using agents

Fast first tokens (~394 ms), high throughput (~184 tok/s), a 1M context, and strong Toolathlon (70.3) reliability suit production agents that call tools at scale — retrieval, automation, orchestration.

3. Long-document processing on a budget

The full 1M-token context and 384K output handle summarizing, analyzing, or transforming very large inputs — logs, codebases, long reports — in a single pass, cheaply.

How to access V4 Flash

You can call V4 Flash directly on DeepSeek's API (model id code>deepseek-v4-flash/code>; it supports the Responses API, OpenAI ChatCompletions, and Anthropic-style interfaces), or through a vendor-neutral endpoint. a href="https://www.orcarouter.ai/">OrcaRouter/a> exposes V4 Flash at 0% markup through a single OpenAI-compatible endpoint (code>deepseek/deepseek-v4-flash/code>) alongside 185+ other models — so you can benchmark it against GPT-5.6 Luna, Gemini 3.6 Flash, GLM-5.2, Qwen 3.8, and Kimi K3 in one place, and route each request to whatever is cheapest for the job. Because it's OpenAI-compatible, adopting V4 Flash — or switching off it — is a configuration change, not a re-integration.

Limitations and honest caveats

V4 Flash is an efficiency model, not a flagship: on the very hardest reasoning it trails V4 Pro and top Western models. Input is text-only (no native image input). The benchmark scores here are DeepSeek-reported using its own harness, so treat exact numbers as directional and expect independent evaluations to land somewhat lower. And "cheap per token" is not "cheap per task" if you let reasoning or agent loops run long — cap reasoning effort and tool iterations on simple calls. Validate on your own workload before committing production traffic.

FAQ

What is DeepSeek V4 Flash?

DeepSeek's efficiency model in the V4 line: a 284B / 13B-active mixture-of-experts model with a 1M-token context, up to 384K output, tuned for fast, high-volume, agentic and coding work. Its official release (build -0731) shipped July 31, 2026.

What changed in the official release?

The architecture is unchanged; it's a post-training upgrade that significantly improves agentic, coding, and tool-calling ability, and adds native Responses-API support with Codex adaptation. Only the Flash API was upgraded — V4 Pro and the app/web are the same.

How much does V4 Flash cost?

About $0.15 per million input tokens and $0.29 per million output tokens on OrcaRouter (0% markup), with ~$0.02 cache reads — roughly a third of V4 Pro's $0.44 / $0.88. Pricing stayed low in this release.

How good is V4 Flash at agentic and coding tasks?

DeepSeek reports strong scores: Terminal-Bench 2.1 82.7, Toolathlon (verified) 70.3, Cybergym 76.7, DeepSWE 54.4, DSBench-FullStack 68.7 — all vendor-harness figures, so verify on your own tasks.

How does V4 Flash compare to V4 Pro?

Pro is the far larger flagship for the hardest reasoning and coding; Flash is the efficiency tier at ~1/3 the price with strong agentic/coding ability. Route hard tasks to Pro, everything else to Flash.

What's the context window?

A full 1,048,576 tokens (about 1M), with up to 384K output tokens.

Is V4 Flash multimodal?

No — input is text-only. It supports reasoning, tool calling, and JSON output.

Does V4 Flash work with the Responses API and Codex?

Yes — the -0731 release adds native Responses-API support and specific Codex adaptation, alongside OpenAI ChatCompletions and Anthropic-style interfaces.

How do I use V4 Flash?

Directly via DeepSeek's API, or through OrcaRouter's OpenAI-compatible endpoint at 0% markup (code>deepseek/deepseek-v4-flash/code>), where you can also compare and route across rival models.

Bottom line

DeepSeek V4 Flash's official release keeps the cheap, fast recipe and makes it a much better agent: same 284B / 13B-active MoE and 1M context, but post-trained for stronger coding and tool use, with native Responses-API and Codex support — at the same ~$0.15 / $0.29 pricing. It's not a flagship and it isn't multimodal, but for the large majority of agentic, coding, and long-document work it's one of the best value-per-token options in 2026. Try it through a 0%-markup, OpenAI-compatible endpoint like OrcaRouter, and route the hardest minority of requests up to a flagship — that combination is hard to beat on cost.