← Models

DeepSeek · deprecated

V4 Flash Vision Exp

V4 Flash Vision Exp is attributed to DeepSeek in the catalog. It accepts text and image input and produces text output. Reported capabilities include reasoning, tool calling, and structured output.

Compare model

Modalities

Token rates

Unavailable

No recent paired token rate available

Context

1M

Released

2026-09-10

Knowledge cutoff

May 2025

Where to use it

0 observed offerings · token prices in USD per million where available

Estimate your workload cost

Limits and capabilities reflect each provider’s listed offering. Unknown means support was not reported.

Capabilities and limits

Input
text, image
Output
text
Max output
393K
Weights
Open (source-reported)
Release
2026-09-10
Knowledge cutoff
May 2025
Family
deepseek-flash

Reasoning · Tool calling · Structured output · Vision

Provider-specific limits and support can differ.

Plan a model evaluation

Evaluate quality and latency on examples from your intended use before choosing a model.

Explore available evidence

Models to compare

Candidates match reported specifications; they are not tested replacements.