The AI tools index that doesn't waste your time.不浪费你时间的 AI 工具索引。
Model dossier模型档案

DeepSeek V4 Flash 0423

DeepSeek V4 Flash 0423 is a high-tier model from DeepSeek (Intelligence Score 82/100). Strongest in math (97) and agent (96.5); best fit: quantitative and scientific work. It trails in preference (34). Budget-priced: $0.066 in / $0.131 out per 1M tokens. Context window 1M tokens — long-document friendly. Open weights — self-hostable. Reachable via CN-direct endpoints.

DeepSeek V4 Flash 0423 是 DeepSeek 的高水平梯队模型(智能评分 82/100)。 最强项是数学(97分),其次是智能体(96.5分);适合数理与科研任务。 短板是偏好(34分)。 定价属低价档:每百万 token 输入 $0.066 / 输出 $0.131。 上下文 1M token,长文档友好。 开放权重,可自托管。 支持国内直连。

open weights开放权重 CN direct国内直连

82
Intelligence Score · benchmark coverage 智能评分 · benchmark 覆盖 88%
ReaCodKnoMatAgtPre

Benchmark scoresBenchmark 成绩

9 entries
Benchmark基准Score成绩Index指数Dated日期Measured by测评方
Humanity's Last ExamReasoning32.1563rd-party第三方source ↗×2⚠±17.3
GPQA DiamondReasoning87.4923rd-party第三方source ↗×4⚠±3.6
MMLU-ProKnowledge86.2912026-083rd-party第三方source ↗×4
SWE-bench VerifiedCoding79822026-083rd-party第三方source ↗×6
AIME 2025Math97973rd-party第三方source ↗×3⚠±27
LiveCodeBenchCoding91.6⚡max983rd-party第三方source ↗×4⚠±26.1
⚡high88.43rd-party第三方source ↗
Terminal-BenchCoding82.7902026-07-313rd-party第三方source ↗×3⚠±25.8
τ²-benchAgent95.6⚡high963rd-party第三方source ↗×2
LMArena (Chatbot Arena)Preference1435342026-08-12official官方榜source ↗×3⚠±31

Specs & pricing规格与价格

Provider厂商DeepSeek
Released发布2026-04-24
Context window上下文1M tokens
Max output最大输出384K tokens
Modality模态text->text
Reasoning tiers推理档位⚡none ⚡high ⚡max default默认 high · thinking off / high effort / max effort
API input price输入价格$0.066 / 1M tokens
API output price输出价格$0.131 / 1M tokens

Tools using this model使用它的工具

Head-to-head正面对比

How we score →评分方法 → · Catalog & pricing via the official OpenRouter API.模型目录与价格来自 OpenRouter 官方 API。