Deepseek-V4-Flash-0817

Model IntroductionText

DeepSeek-V4-Flash-0817 is the official release of DeepSeek-V4-Flash, superseding the preview version, with substantially enhanced agentic capabilities.

Introduction

DeepSeek-V4-Flash-0817 is the official release of DeepSeek-V4-Flash, superseding the preview version, with substantially enhanced agentic capabilities. It has the same model structure as DeepSeek-V4-Flash-DSpark, i.e. it comes with a speculative decoding module attached. DeepSeek-V4-Flash-0731 outperforms DeepSeek-V4-Pro (Preview) on benchmarks listed below despite its far smaller activated parameter count, and is broadly competitive with the strongest proprietary models available.

Key Features

  • It has the same model structure as DeepSeek-V4-Flash-DSpark, i.e. it comes with a speculative decoding module attached.
  • DeepSeek-V4-Flash-0817 outperforms DeepSeek-V4-Pro (Preview) on benchmarks listed below despite its far smaller activated parameter count, and is broadly competitive with the strongest proprietary models available.

Benchmarks

Benchmark (Area)Score*
Terminal Bench 2.1 (Overall)82.7 (Eval)
NL2Repo (Overall)54.2 (Eval)
Cybergym (Overall)76.7 (Eval)
DeepSWE (Overall)54.4 (Eval)
Toolathlon-Verified (Overall)70.3 (Eval)
Agents' Last Exam (Overall)25.2 (Eval)
AutomationBench Public (Overall)25.1 (Eval)
DSBench-FullStack † (Overall)68.7 (Eval)
DSBench-Hard † (Overall)59.6 (Eval)

API request example

Endpoint /v1/chat/completions. Replace <API_KEY> with a key from the console.

Standard OpenAI Chat Completions. Swap `model` for the target slug.

curl https://api.ravenrouter.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <API_KEY>" \
  -d '{
  "model": "Deepseek-V4-Flash-0817",
  "messages": [
    {
      "role": "user",
      "content": "Hello! Introduce yourself in one sentence."
    }
  ],
  "max_tokens": 64
}'

More models: API Reference → Examples by model

Deepseek-V4-Flash-0817 API — $0.48/1M input, $1.45/1M output | RavenRouter AI