DeepSeek: DeepSeek V4 Flash 0731

Text input Text output
Author's Description

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows.

Key Specifications
Cost
$$
Context
384K
Released
Jul 30, 2026
Supported Parameters

This model supports the following parameters:

Reasoning Include Reasoning Frequency Penalty Tools Top P Stop Presence Penalty Logprobs Max Tokens Temperature Top Logprobs Tool Choice Response Format
Features

This model supports the following features:

Response Format Reasoning Tools
Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.08
Completion $0.18
Input Cache Read $0.016

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
DeepSeek
DeepSeek | deepseek/deepseek-v4-flash-20260731 1M $0.14 / 1M tokens $0.28 / 1M tokens
Cloudflare
Cloudflare | deepseek/deepseek-v4-flash-20260731 384K $0.08 / 1M tokens $0.18 / 1M tokens
Cloudflare
Cloudflare | deepseek/deepseek-v4-flash-20260731 384K $0.14 / 1M tokens $0.28 / 1M tokens
DeepInfra
DeepInfra | deepseek/deepseek-v4-flash-20260731 1M $0.08 / 1M tokens $0.18 / 1M tokens
Parasail
Parasail | deepseek/deepseek-v4-flash-20260731 1M $0.14 / 1M tokens $0.28 / 1M tokens
Fireworks
Fireworks | deepseek/deepseek-v4-flash-20260731 1M $0.14 / 1M tokens $0.28 / 1M tokens
AtlasCloud
AtlasCloud | deepseek/deepseek-v4-flash-20260731 262K $0.14 / 1M tokens $0.28 / 1M tokens
SiliconFlow
SiliconFlow | deepseek/deepseek-v4-flash-20260731 1M $0.14 / 1M tokens $0.28 / 1M tokens
GMICloud
GMICloud | deepseek/deepseek-v4-flash-20260731 1M $0.112 / 1M tokens $0.224 / 1M tokens
Novita
Novita | deepseek/deepseek-v4-flash-20260731 1M $0.14 / 1M tokens $0.28 / 1M tokens
Mancer 2
Mancer 2 | deepseek/deepseek-v4-flash-20260731 1M $0.175 / 1M tokens $0.5 / 1M tokens
Io Net
Io Net | deepseek/deepseek-v4-flash-20260731 262K $0.149 / 1M tokens $0.32 / 1M tokens
Ionstream
Ionstream | deepseek/deepseek-v4-flash-20260731 1M $0.21 / 1M tokens $0.42 / 1M tokens
Venice
Venice | deepseek/deepseek-v4-flash-20260731 1M $0.175 / 1M tokens $0.35 / 1M tokens
Ambient
Ambient | deepseek/deepseek-v4-flash-20260731 1M $0.14 / 1M tokens $0.28 / 1M tokens
Together
Together | deepseek/deepseek-v4-flash-20260731 1M $0.14 / 1M tokens $0.28 / 1M tokens
Phala
Phala | deepseek/deepseek-v4-flash-20260731 1M $0.2 / 1M tokens $0.4 / 1M tokens
AkashML
AkashML | deepseek/deepseek-v4-flash-20260731 131K $0.14 / 1M tokens $0.28 / 1M tokens
Baidu
Baidu | deepseek/deepseek-v4-flash-20260731 1M $0.14 / 1M tokens $0.28 / 1M tokens
Morph
Morph | deepseek/deepseek-v4-flash-20260731 1M $0.139 / 1M tokens $0.278 / 1M tokens
BaseTen
BaseTen | deepseek/deepseek-v4-flash-20260731 1M $0.13 / 1M tokens $0.26 / 1M tokens
CoreWeave
CoreWeave | deepseek/deepseek-v4-flash-20260731 262K $0.13 / 1M tokens $0.28 / 1M tokens
Sail Research
Sail Research | deepseek/deepseek-v4-flash-20260731 1M $0.08 / 1M tokens $0.18 / 1M tokens
StreamLake
StreamLake | deepseek/deepseek-v4-flash-20260731 1M $0.112 / 1M tokens $0.224 / 1M tokens
DigitalOcean
DigitalOcean | deepseek/deepseek-v4-flash-20260731 1M $0.08 / 1M tokens $0.252 / 1M tokens
Wafer
Wafer | deepseek/deepseek-v4-flash-20260731 1M $0.08 / 1M tokens $0.18 / 1M tokens
Wafer
Wafer | deepseek/deepseek-v4-flash-20260731 1M $0.28 / 1M tokens $0.56 / 1M tokens
Decart
Decart | deepseek/deepseek-v4-flash-20260731 262K $0.09 / 1M tokens $0.18 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by deepseek