DeepSeek: DeepSeek V4 Pro 0423

DeepSeek V4 Pro is DeepSeek's large-scale mixture-of-experts model, released 2026-04, with 1.6T total and 49B active parameters. Built for advanced reasoning, coding, and long-horizon agent workflows, it uses a hybrid attention system for efficient long-context processing. It targets complex tasks like full-codebase analysis and multi-step automation.

Modalities
inTextoutText
Price / 1M−89%
$0.17 / $0.35$1.60 / $3.20
Context
1.049M
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
−89%
$0.17
$0.35
$0.001

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 $0.17 / $0.35 /1MDaily chat: 40% cache hit assumed · cache read $0.001 /1M
List price $246.27On MirAPI$26.78/ moYou save $219.49Create an API key

Benchmarks

bar = score (0–100) · ▏ median

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

Intelligence Index
General ability
45.3
#28
Coding Index
Code
59.4
#29
Agentic Index
Agentic
37.8
#25
GPQA Diamond
Science QA
86.6
#22
τ-bench (airline)
Agentic tool use
76.1
#20

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-pro",
    messages=[{"role": "user", "content": "Hello"}],
)
Wire DeepSeek V4 Pro 0423 into your product

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

Start free