DeepSeek: DeepSeek V4 Flash 0731

DeepSeek V4 Flash 0731 is DeepSeek's sparse mixture-of-experts model with 13B active parameters out of 284B total, released 2026-07 as the GA revision of V4 Flash. It targets coding, reasoning, and agent workflows.

Modalities
inTextoutText
Price / 1M−60%
$0.04 / $0.13$0.14 / $0.28
Context
1.311M
Knowledge cutoff

Capabilities

ReasoningTool useLong contextPrompt cachingStructured output

Channels

Same weights on every channel. Requests route to the cheapest healthy one; the channel used is printed on each billing line.

Provider
Discount
Input /M
Output /M
Cache Read /M
Cache Create 5m /M
Cache Create 1h /M
Defaultstable
−60%
$0.04
$0.13
$0.01

Cost Calculator

Pick a channel and a usage scenario, then drag to your workload — each scenario assumes a different prompt-cache hit rate.

Channel
Scenario
Unit $0.04 / $0.13 /1MDaily chat: 40% cache hit assumed · cache read $0.01 /1M
List price $23.20On MirAPI$8.84/ moYou save $14.36Create an API key

Benchmarks

bar = score (0–100) · ▏ median

Scores from vendor reports and public leaderboards. No private evals.

Intelligence Index
General ability
51.8
#22
Coding Index
Code
69.1
#20
Agentic Index
Agentic
48.4
#15
GPQA Diamond
Science QA
87.1
#20
τ-bench (airline)
Agentic tool use
76.7
#15

Showcase

Three fixed prompts, identical for every chat model. Outputs are archived verbatim — copy the prompt to reproduce.

Task prompt · identical for all models
Build a single-file HTML page using three.js from a CDN: a low-poly planet with a tilted ring of ~200 orbiting particles, a soft key light plus rim light, slow auto-rotation, and drag-to-orbit controls. No build tools — one file only.
Archived output
Archive not published yet

Every model will run this exact prompt; the output lands here verbatim, with tokens and per-run cost.

Quick Start

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.mirapi.ai/v1",   # changed
    api_key=os.environ["MIRAPI_API_KEY"],   # changed
)

resp = client.chat.completions.create(
    model="deepseek/deepseek-v4-flash-0731",
    messages=[{"role": "user", "content": "Hello"}],
)
Wire DeepSeek V4 Flash 0731 into your product

1M free tokens to start · no card · OpenAI-compatible, one base_url change

Start free