devtools.sh

DeepSeek V4 Pro

DeepSeek

DeepSeek-V4-Pro is a 1.6T-parameter Mixture-of-Experts model with 49B activated, supporting a one-million-token context. The 0813 revision is its GA release.

Model page View on models.dev View on OpenRouter

Specs

Model

Family
DeepSeek
Variant
V4 Pro
Parameters
1.6T total, 49B active (MoE)
Weights
Open
License
MIT

Limits

Context
1,000,000 tokens
Max output
384,000 tokens

Modalities

Input
Text
Output
Text

Pricing

Input
$0.435 / 1M
Output
$0.87 / 1M
Cache read
$0.003625 / 1M

Capabilities

Reasoning
Yes
Reasoning control
On / off, Effort levels
Tool calling
Yes
Attachments
No

Dates

Released
24 Apr 2026
Updated
22 Aug 2026
Knowledge cutoff
May 2025

More from DeepSeek

All models

DeepSeek V4.1 Flash

DeepSeek

We introduce DeepSeek-V4.1-Flash, a multimodal Mixture-of-Experts (MoE) model with 552B backbone parameters and support for contexts of up to one million tokens. The model natively processes images and text, and generates text autoregressively.

MIT17d ago

DeepSeek V4 Flash

DeepSeek

DeepSeek-V4-Flash-0731 is the official release of DeepSeek-V4-Flash, superseding the preview version, with substantially enhanced agentic capabilities.

MIT24 Apr 2026

Keep up with the tools

An occasional email when notable AI dev tools and models land in the directory. No spam, unsubscribe anytime.