DeepSeek V4 Flash 0731: Benchmarks, Pricing, and Dev Setup Guide

DeepSeek released V4-Flash-0731 on July 31, 2025, and the smaller model now outperforms the larger V4-Pro-Preview across all nine published agentic benchmarks, including Terminal Bench 2.1 (82.7 vs. 72.1) and DeepSWE (54.4 vs. 12.8), at one-third the output cost. The model retains the same 284B MoE architecture, 13B active parameters, and 1M context window, with native Responses API support added. DeepSeek also retired the 'deepseek-chat' and 'deepseek-reasoner' aliases on July 24, requiring migration to 'deepseek-v4-flash'.

DeepSeek made V4 Flash official on July 31, and the buried headline is this: the smaller model now beats the larger one. V4-Flash-0731 outperforms V4-Pro-Preview across all nine published agentic benchmarks — according to DeepSeek’s own release notes https://deepseek.ai/blog/deepseek-v4-flash-ga-agent-benchmarks . Terminal Bench 2.1 sits at 82.7 for Flash versus Pro’s 72.1. DeepSWE lands at 54.4 versus 12.8. Cybergym: 76.7 versus 52.7. The smaller model wins every category, at a third of the output cost. If you’re running coding agents and haven’t switched yet, here’s your migration guide. What Changed From Preview to GA Almost nothing architectural changed — and that’s the interesting part. DeepSeek re-ran only the post-training phase. Same 284B MoE architecture, same 13B active parameters per token, same 1M context window. The model string stays deepseek-v4-flash , so existing integrations require no code changes. What did land in this build: native Responses API support, which makes it directly compatible with Codex-based integrations out of the box. One housekeeping note before setup: if you’re still calling deepseek-chat or deepseek-reasoner , those aliases retired on July 24 . Switch to deepseek-v4-flash now or your calls are failing silently. The Benchmark Numbers Worth Knowing | Benchmark | Flash-0731 | Flash Preview | Pro Preview | |---|---|---|---| | Terminal Bench 2.1 | 82.7 | 61.8 | 72.1 | | DeepSWE | 54.4 | 7.3 | 12.8 | | Cybergym | 76.7 | 38.7 | 52.7 | | NL2Repo | 54.2 | 39.4 | 38.5 | | Toolathlon verified | 70.3 | 49.7 | 55.9 | On DeepSWE — a real-world software engineering benchmark — Flash is more than four times better than its preview version and four times better than Pro Preview. Independent verification from Artificial Analysis puts Flash at 2 of 162 models measured. One developer in the HackerNews discussion https://news.ycombinator.com/item?id=49214008 put it plainly: “It would absolutely have been a frontier model last December.” What It Costs — Honestly | Token Type | V4-Flash | V4-Pro | |---|---|---| | Input cache miss | $0.14/M | $0.435/M | | Input cache hit | $0.0028/M | $0.003625/M | | Output | $0.28/M | $0.87/M | Output tokens cost 3x less than Pro. Cache hits knock 98% off input costs — critical for agentic loops where your system prompt repeats on every tool call. In practice, a full day of agent-heavy work runs under $0.50 on Flash versus roughly $2 on Pro. There’s a real caveat here: Flash generates approximately three times the median token volume on agentic tasks due to its internal reasoning chain. Effective cost per completed task runs higher than raw rates suggest — but it’s still cheaper than Pro in every real-world scenario. Also worth noting: DeepSeek has announced a 2x peak-hour surcharge during Beijing business hours, effective date still TBD. Setting Up in Claude Code DeepSeek provides an Anthropic-compatible endpoint, so setup is a handful of environment variables. The official integration docs https://api-docs.deepseek.com/quick start/agent integrations/claude code/ cover it, but the smart mapping is to assign Flash to lighter slots Haiku, subagents and Pro to the main model role: export ANTHROPIC BASE URL=https://api.deepseek.com/anthropic export ANTHROPIC AUTH TOKEN=your deepseek api key export ANTHROPIC MODEL=deepseek-v4-pro export ANTHROPIC DEFAULT OPUS MODEL=deepseek-v4-pro export ANTHROPIC DEFAULT SONNET MODEL=deepseek-v4-pro export ANTHROPIC DEFAULT HAIKU MODEL=deepseek-v4-flash export CLAUDE CODE SUBAGENT MODEL=deepseek-v4-flash export CLAUDE CODE EFFORT LEVEL=max export CLAUDE CODE AUTO COMPACT WINDOW=786432 This maps Flash to the high-frequency sub-tasks and reserves Pro for the primary reasoning pass. Given that Flash outperforms Pro on every agentic benchmark, you could map everything to Flash — but the hybrid approach is the sensible starting point while Pro’s GA is still pending. Setting Up in Cursor Open Settings Cmd+, on Mac, Ctrl+, on Windows , go to Models, and toggle “Override OpenAI Base URL.” Enter https://api.deepseek.com — no trailing /v1 . Paste your DeepSeek API key into the OpenAI key field, click “+ Add model,” type deepseek-v4-flash , and hit Verify. Switch to it in the chat model picker before starting a session. There’s one important caveat here: Cursor’s Composer panel has a known issue with extended tool-call sequences. Cursor only forwards the content field to the model — not reasoning content — which causes failures when DeepSeek’s thinking mode needs to replay its chain across multiple requests. Use the Chat panel for complex multi-step tasks or disable thinking mode for Composer sessions. Background Agents also don’t support custom models as of this writing. Get Your API Key If you don’t have one, start at the DeepSeek platform https://platform.deepseek.com/api keys . Minimum wallet funding is $5 — that covers weeks of normal agent usage at Flash pricing. The Takeaway V4-Flash is the agent model of summer 2026. A frontier-adjacent model at sub-commodity pricing, MIT-licensed, open weights available for self-hosting on 4x A100s. V4-Pro still hasn’t hit GA — when it does, the picture may shift. For now, Flash is the default choice for coding agents. The benchmarks say so, and so does your wallet.