# DeepSeek V4-Flash Puts Agent Costs on Trial > DeepSeek opened its V4-Flash API public beta with Responses API support, Codex integration and pricing that makes agent cost a live test. - Content type: NewsArticle - Section: News - Published: 2026-08-01T06:38:44.000Z - Publisher: Arkolith Newsroom - Canonical HTML: https://arkolith.com/news/news-deepseek-v4-flash-agent-cost - Plain Markdown: https://arkolith.com/news/news-deepseek-v4-flash-agent-cost.md - Topics: DeepSeek, AI agents, Codex, API pricing, Open models ## Article DeepSeek opened the official V4-Flash API public beta on July 31, turning the next agent-model fight into a cost, context and throughput test. The [DeepSeek V4-Flash changelog](https://api-docs.deepseek.com/updates/) says the model now supports the Responses API format and is adapted for Codex, while V4-Pro and the app and web models are unchanged. The live question is not only whether V4-Flash can code well. It is whether a cheaper model with a very large context window can handle enough agent work to change routing decisions for builders. ## What changed DeepSeek says V4-Flash-0731 keeps the same architecture and size as the preview version and was re-post-trained. The company listed improved agent-benchmark results, including Terminal Bench 2.1, DeepSWE and Toolathlon verified, and said the official V4-Flash API is now in public beta. The separate [DeepSeek Codex integration docs](https://api-docs.deepseek.com/quick_start/agent_integrations/codex/) narrow the practical support boundary. They say V4-Flash is the DeepSeek model that currently supports Codex integration, while V4-Pro support is expected in early August 2026. ![Photo: a logo-free developer workstation beside dense server racks before an AI model release](/article-images/news-deepseek-v4-flash-agent-cost-1.webp) ## Why pricing matters The [DeepSeek models and pricing](https://api-docs.deepseek.com/quick_start/pricing/) page lists V4-Flash at a 1 million token context window, maximum output of 384,000 tokens, Responses API support, tool calls and Anthropic API support. It lists prices per 1 million tokens at $0.14 for cache-miss input, $0.0028 for cache-hit input and $0.28 for output. Those are not enough to prove reliability by themselves. They do change the experiment. Long-running coding, research and data-cleaning agents burn tokens while reading files, logs, tool outputs and previous attempts. A lower per-token price makes it easier to test more routing, retry and review patterns before deciding which jobs require a more expensive model. That pressure is visible across the model market. The recent [Kimi K3 open-model release](/news/news-kimi-k3-open-model) put another low-cost coding model into the builder queue, while the [OpenAI Codex reset after outage](/news/news-openai-outage-codex-reset) showed how quickly capacity and reliability become product-level facts for agents. ## The capacity boundary DeepSeek also published account-level concurrency numbers. The [DeepSeek rate-limit docs](https://api-docs.deepseek.com/quick_start/rate_limit/) list a V4-Flash concurrency limit of 2,500 requests, versus 500 for V4-Pro. A request counts until the model response completes, so long agent turns can still occupy capacity. The open-source route is separate from the hosted API. The [DeepSeek V4-Flash Hugging Face model card](https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731) describes the 0731 release as superseding the preview and says it can be served through vLLM, SGLang and Docker Model Runner. That gives teams a local or self-hosted path, but only if they can absorb the operational cost of serving a large agent model. ## What comes next The next records to watch are V4-Pro Codex support, any peak or off-peak pricing change, real builder reports on tool-use reliability, and whether hosted throughput holds up when more agent clients start routing work to V4-Flash. For now, the verified event is narrower. DeepSeek has put V4-Flash into public beta with Codex and Responses API support, a large context window, low posted token prices and published concurrency limits. The market test starts when developers decide which agent jobs are cheap enough to move. *This article is informational only and is not investment, legal, tax or accounting advice.* ## Citation and verification - Cite the canonical HTML article: https://arkolith.com/news/news-deepseek-v4-flash-agent-cost - Follow the links in the article to verify claims against the named primary or trustworthy sources. - Publication and update times above are the newsroom's recorded timestamps.