Model dossier模型档案
DeepSeek V4 Pro 0423
DeepSeek V4 Pro 0423 is a high-tier model from DeepSeek (Intelligence Score 87.4/100). Strongest in agent (97.7) and knowledge (94.5); best fit: tool-use and multi-step agents. Budget-priced: $0.422 in / $0.845 out per 1M tokens. Context window 1M tokens — long-document friendly. Open weights — self-hostable. Reachable via CN-direct endpoints.
DeepSeek V4 Pro 0423 是 DeepSeek 的高水平梯队模型(智能评分 87.4/100)。 最强项是智能体(97.7分),其次是知识(94.5分);适合工具调用与多步 Agent。 定价属低价档:每百万 token 输入 $0.422 / 输出 $0.845。 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
87.4
Intelligence Score · benchmark coverage 智能评分 · benchmark 覆盖 95%
◈
Benchmark scoresBenchmark 成绩
10 entries 条| Benchmark基准 | Score成绩 | Index指数 | Dated日期 | Measured by测评方 | |
|---|---|---|---|---|---|
| Humanity's Last ExamReasoning | 48.2⚡max | 84 | 2026-08 | 3rd-party第三方 | source ↗×5⚠±25.5 |
| ↳ ⚡high | 34.5 | — | — | 3rd-party第三方 | source ↗ |
| GPQA DiamondReasoning | 90.1 | 94 | 2026-07-18 | 3rd-party第三方 | source ↗×9⚠±4.7 |
| MMLU-ProKnowledge | 87.5 | 94 | — | 3rd-party第三方 | source ↗×5 |
| SWE-bench VerifiedCoding | 80.6 | 84 | 2026-08 | 3rd-party第三方 | source ↗×8⚠±15.8 |
| AIME 2025Math | 96.67⚡max | 97 | — | 3rd-party第三方 | source ↗×6 |
| ↳ ⚡high | 97 | — | 2026-05 | 3rd-party第三方 | source ↗ |
| LiveCodeBenchCoding | 93.5⚡max | 100 | — | 3rd-party第三方 | source ↗×8 |
| FrontierMathMath | 68.3 | 73 | — | 3rd-party第三方 | source ↗×2⚠±64.13 |
| Terminal-BenchCoding | 67.9⚡max | 74 | — | 3rd-party第三方 | source ↗×5⚠±36.4 |
| τ²-benchAgent | 96.2⚡max | 98 | 2026-06-10 | 3rd-party第三方 | source ↗×3 |
| LMArena (Chatbot Arena)Preference | 1458 | 59 | 2026-08-12 | official官方榜 | source ↗×5⚠±39.95 |
| ↳ ⚡high | 1467 | — | — | 3rd-party第三方 | source ↗ |
≡
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 | $0.422 / 1M tokens |
| API output price输出价格 | $0.845 / 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。