DeepSeek: DeepSeek V4 Flash Vision Exp

Coming soonQuick start

DeepSeek V4 Flash Vision Exp is DeepSeek's experimental vision-enabled take on DeepSeek V4 Flash 0731, released 2026-08, adding image understanding while matching the base model on text tasks. It is a sparse mixture-of-experts model with 13B active parameters out of 284B total, suited to document and chart understanding, visual question answering, and multimodal agent workflows that interleave text and images.

This model isn’t available on MirAPI yet, so the prices shown are the official list prices. Create an account to get notified when it goes live.

Modalities
inTextinImageoutText
Price / 1M
$0.22 / $0.65
Context
1.049M
Released
Aug 21, 2026

Capabilities

ReasoningVisionTool useLong contextPrompt cachingStructured output

Parameters

Request parameters this model accepts through the API.

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

Benchmarks

bar = score (0–100) · ▏ median

Scores come from vendor reports and public leaderboards, not private evals.

Intelligence Index
General ability
34.8
#33
Coding Index
Code
65.0
#29
Agentic Index
Agentic
47.5
#12
GPQA Diamond
Science QA
88.0
#35
τ-bench (airline)
Agentic tool use
74.8
#37

Showcase

Every chat model gets the same three fixed prompts. Outputs are archived verbatim, so you can copy a prompt and reproduce the result.

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, and its output will appear here verbatim with token counts and the cost per run.

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="",
    messages=[{"role": "user", "content": "Hello"}],
)
Wire DeepSeek V4 Flash Vision Exp into your product

1M free tokens to start, no card required. It’s OpenAI-compatible, so you only change the base URL.

Start free