DeepSeek V4 Flash 0731 - Corvex Token Factory

DeepSeek V4 Flash 0731 is DeepSeek’s open-weight model for text, code, reasoning, and tool use. Token Factory serves this version with a 1,048,576-token context window. Model ID: deepseek-ai/DeepSeek-V4-Flash-0731

Specifications

Context window: 1,048,576 tokens (1M)
Maximum output: 1,048,576 tokens, subject to the remaining context space
Input: text
Output: text
Capabilities: chat, reasoning, coding, tool use, JSON mode, structured output
Sampling parameters: temperature, top_p, stop, max_tokens
License: MIT
Model repository: deepseek-ai/DeepSeek-V4-Flash-0731

Input and reserved output share the context window: input_tokens + max_tokens must fit within 1,048,576 tokens. Image input is not supported. Include the -0731 suffix when selecting this version.

Pricing

Direction	Rate (USD)
Input	$0.14 / 1M tokens
Output	$0.28 / 1M tokens

Inference usage is deducted from your available credits at these rates. See Pricing.

Send a request

curl https://api.tokenfactory.corvex.cloud/v1/chat/completions \
  -H "Authorization: Bearer ${CORVEX_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-ai/DeepSeek-V4-Flash-0731",
    "messages": [
      {"role": "user", "content": "Plan a zero-downtime database migration."}
    ]
  }'

Set stream: true for streamed responses. See the API reference for request fields and the integration guides for SDKs and developer tools. Open DeepSeek V4 Flash 0731 in the Token Factory playground.

Last modified on October 6, 2026