DeepSeek V4 Flash (0731): specs, pricing and how it performs in a council

DeepSeek V4 Flash (0731) is DeepSeek's model available on Council AI at $0.14 per million input tokens and $0.28 per million output, with a 1,310,720-token context window. Re-post-trained V4 Flash revision (Jul 31, 2026). Sparse MoE, 13B active of 284B total, 1.3M context — the price-performance pick for coding, reasoning and agent workflows. On Council you do not run it alone: the same prompt goes to up to 10 models from different labs in parallel, and a moderator synthesizes one answer with a consensus score showing where the labs agreed.

DeepSeek V4 Flash (0731) specifications

What DeepSeek V4 Flash (0731) is good at

Re-post-trained V4 Flash revision (Jul 31, 2026). Sparse MoE, 13B active of 284B total, 1.3M context — the price-performance pick for coding, reasoning and agent workflows.

Council surfaces it for: fast, coding, high-volume, value.

It has no native web search. Council can still retrieve context for it from your own document library on Ultra.

DeepSeek V4 Flash (0731) pricing on Council AI

Council does not resell tokens. Every paid plan carries a monthly budget and each model draws against it at cost: $0.14 in / $0.28 out per million tokens for DeepSeek V4 Flash (0731). Plans start at $19.99/mo (Plus), $39.99/mo (Pro) and $99.99/mo (Ultra, which adds the personal RAG library and MCP server).

If budget is the binding constraint, Qwen3.7 Flash is the cheaper seat in the lineup at $0.03/$0.13.

Using DeepSeek V4 Flash (0731) in a council

A single model — this one included — can be confidently wrong. Council runs DeepSeek V4 Flash (0731) alongside models from other labs on the same prompt, then scores how much they agreed. High consensus is a signal you can act on the answer; low consensus surfaces the specific point they split on, which is usually the part worth checking yourself.

Other DeepSeek models in the lineup: DeepSeek V4 Pro (0813).

Frequently asked questions