Agents Directory
SkillsRankingsAgents
CategoriesModelsBenchmarksCompareAgent LeaderboardSkillsRankingsAgentsAbout
New

Work in progress: Agents Directory has just launched. Stay tuned, more content is on the way.

/Models
/DeepSeek V4 Flash
DeepSeek

DeepSeek V4 Flash

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...

Capabilities:

Input
  • Text input
  • Image input (vision)
  • File input (PDF)
  • Audio input
  • Video input
Output
  • Text output
  • Image output
  • Audio output
Pricing & availability:

  • OpenRouterOpenRouter

    $0.09 / $0.18 per M
Sources:
OpenRouterOpenRouter
Share:
Details:

  • DeepSeekProvider

    DeepSeek

  • Context window

    1.049M

  • Input price

    $0.09/M

  • Output price

    $0.18/M

  • Open weights

    Yes

  • Released

    Apr 2026
Browse:SkillsRankingsModelsBenchmarksProvidersAgentsAgent LeaderboardCompareCategories
Quick Links:AboutBlog

© 2026 Agents Directory

  • CapabilitiesCapabilities
  • LiveCodeBench v6LiveCodeBench v6
  • SWE-bench VerifiedSWE-bench Verified
  • Pricing & availabilityPricing & availability
Benchmark scores:
BenchmarkRankScore
  • LLiveCodeBench v6
    Rank—
    Score91.6%
  • SWE-bench Verified logoSWE-bench Verified
    Rank—
    Score79%
Appears in rankings:
Best cheap AI modelsBest cheap models for HermesBest Chinese AI modelsBest open-source models for HermesBest open-source models for OpenClaw
More DeepSeek models:
DeepSeek V4DeepSeek V3.2DeepSeek V3.2 ExpDeepSeek V3.1 TerminusDeepSeek V3.1R1 0528DeepSeek V3 0324R1 Distill Qwen 32B