Skip to main content

    DeepSeek

    DeepSeek V4 Flash

    DeepSeek-V4-Flash-0731 is the July 31, 2026 text-only V4 Flash release, with 284B total and 13B active parameters, a 1M-token context and MIT weights. DeepSeek retired its first-party V4 Flash service on September 10, 2026. The legacy deepseek-v4-flash slug now temporarily routes to the newer, vision-capable DeepSeek-V4.1-Flash. These historical weights retain their own architecture and modalities.

    1M tokens
    Text only
    Pro
    New
    Provider
    DeepSeek
    Context
    1M
    Catalog · As of Aug 11, 2026Stale · 31d old
    yno subscription tier
    Pro
    Released
    Jul 31, 2026
    Speed
    Fast
    Reasoning
    Advanced
    Modality
    Text only

    Benchmarks

    Quality

    AA Intelligence Index
    34.5points
    Artificial Analysis · Date unknownAge unknown
    AA Coding Index
    69.1points
    Artificial Analysis · Date unknownAge unknown
    GPQA Diamond
    90.8%
    Artificial Analysis · Date unknownAge unknown

    Speed and latency

    Output speed
    239.38tokens/s
    Configuration: Prompt length: 1,000 · Parallel queries: 1
    Artificial Analysis · Date unknownAge unknown
    Time to first token
    0.78s
    Configuration: Prompt length: 1,000 · Parallel queries: 1
    Artificial Analysis · Date unknownAge unknown
    Time to first answer token
    9.14s
    Configuration: Prompt length: 1,000 · Parallel queries: 1
    Artificial Analysis · Date unknownAge unknown

    API pricing

    API input cost
    $0.44/ 1M tokens
    Artificial Analysis · Date unknownAge unknown
    API output cost
    $1.32/ 1M tokens
    Artificial Analysis · Date unknownAge unknown

    Benchmark variant: DeepSeek V4 Flash 0731 (Reasoning, Max Effort)

    AA data retrieved Sep 11, 2026 · Artificial Analysis

    Indexes use points; evaluations use accuracy percentages. API measurements do not measure yno application performance. Methodology

    Capabilities

    • Code
    • Long Context
    • Open Source
    • Cost-Effective

    Use cases

    • High-volume budget AI
    • Document processing
    • Batch coding
    • Startup development

    Strengths

    • Published V4-Flash-0731 weights
    • 284B MoE / 13B active
    • 1M context
    • Historical text-only model

    Best for

    Historical comparison and self-hosted use of V4-Flash-0731 weights

    Use DeepSeek V4 Flash in yno.ai

    No credit card required

    Related models

    DeepSeek V4 Pro

    DeepSeek

    DeepSeek V3.2

    DeepSeek

    Gemini 3.7 Flash

    Google

    Frequently asked

    What is DeepSeek V4 Flash?
    DeepSeek-V4-Flash-0731 is the July 31, 2026 text-only V4 Flash release, with 284B total and 13B active parameters, a 1M-token context and MIT weights. DeepSeek retired its first-party V4 Flash service on September 10, 2026. The legacy deepseek-v4-flash slug now temporarily routes to the newer, vision-capable DeepSeek-V4.1-Flash. These historical weights retain their own architecture and modalities.
    How much does DeepSeek V4 Flash cost in yno.ai?
    DeepSeek V4 Flash is available on the Pro tier of yno.ai.
    What can DeepSeek V4 Flash do?
    DeepSeek V4 Flash is best for Historical comparison and self-hosted use of V4-Flash-0731 weights. Its main capabilities include Code, Long Context, Open Source, Cost-Effective.
    How does DeepSeek V4 Flash compare to other models?
    DeepSeek V4 Flash excels at Published V4-Flash-0731 weights and is recommended for High-volume budget AI, Document processing, Batch coding, Startup development. See related models below.
    How do I use DeepSeek V4 Flash in yno.ai?
    Sign up for yno.ai, select DeepSeek V4 Flash from the model picker, and start chatting.