DeepSeek: DeepSeek V4 Flash

One API key. Live prices. Ready-to-run code.

DeepSeek-V4-Flash is a highly efficient Mixture-of-Experts (MoE) language model featuring 158B total parameters with only 13B activated during inference.

Served on OneInfer by DeepSeek, ByteDance and Novita. Use it with the same API key and pay-as-you-go wallet as every other model in the catalog.

ProviderDeepSeekdeepseek-ai/Deepseek-V4-Flash

Call DeepSeek V4 Flash in 5 steps

Step 1 of 5

DeepSeek, ByteDance and Novita serve this model. The pricing table below lists each provider’s rate.

OverviewProvidersPricingBenchmarksAPI and quickstartReviews
Input tokens
$0.300 / 1M tokens
Output tokens
$1.200 / 1M tokens
Context
1M
Input
text
Output
text
Tool calling
Supported

About this model

DeepSeek-V4-Flash is a highly efficient Mixture-of-Experts (MoE) language model featuring 158B total parameters with only 13B activated during inference. It utilizes a Hybrid Attention Architecture (combining Compressed Sparse Attention and Heavily Compressed Attention) to natively and efficiently support a 1-million-token context window. The model offers switchable reasoning modes (Non-think, Think High, and Think Max) and excels at high-speed generation for reasoning, coding, tool-calling, and agentic tasks.

Input modalities

  • text

    Accepted as model input

Providers

Available routing options for this model through OneInfer.

  • DeepSeek
    Available
    Input tokens
    $0.300 / 1M tokens
    Output tokens
    $1.200 / 1M tokens
    Routing
    OneInfer optimized
  • ByteDance
    Available
    Input tokens
    $0.440 / 1M tokens
    Output tokens
    $1.320 / 1M tokens
    Routing
    OneInfer optimized
  • Novita
    Available
    Input tokens
    $0.440 / 1M tokens
    Output tokens
    $1.320 / 1M tokens
    Routing
    OneInfer optimized

Pricing

Current OneInfer pricing for this model.

UsagePrice
Input tokens$0.300 / 1M tokens
Output tokens$1.200 / 1M tokens
Cached input tokens$0.0060 / 1M tokens

Performance and benchmarks

Independent evaluations and live cluster operational metrics

We haven’t measured this model yet. Published academic results are under Academic evaluations.

API guide

API docs

  1. Generate your access token

    Use your API key to generate the JWT access token required by the Models API.

  2. Add the JWT token

    Copy the generated JWT token and replace JWT_TOKEN in the example below.

  3. Check your credits

    If your balance is too low, before calling the model.

  4. Run the API example

    Choose your preferred language, copy the example, and send your first model request.

    curl https://api.oneinfer.ai/v1/ula/chat/completions \
  -H "Authorization: Bearer $JWT_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-ai/Deepseek-V4-Flash",
    "messages": [
      { "role": "user", "content": "Hello!" }
    ]
  }'

Community reviews and ratings

Visitor and developer evaluations of DeepSeek: DeepSeek V4 Flash's real-world intelligence, code accuracy, and speed

No ratings yet

Top community tags

Be the first to rate and tag this model's coding and reasoning strengths.

No community reviews yet

Be the first to share developer feedback on DeepSeek: DeepSeek V4 Flash's latency, code accuracy, and reliability in production.