Skip to content
ModelsChatdeepseek-v4.1-flash-1017

deepseek-v4.1-flash-1017

BytePlus

Chat

deepseek-v4.1-flash-1017

DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name. V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on output from a 552B-parameter backbone, an asymmetric split that keeps per-token compute low relative to the model's total size. Image understanding is native to the architecture, with visual and text embeddings trained jointly from the start of pre-training rather than added afterward as in the earlier experimental V4 Flash Vision Exp.

Input / output per 1M
$0.30 / $1.20
USD
Context Window
1M
tokens
Max output
393,216
tokens
Released
2026-10-17
Chat

Provider pricing

per 1M tokens

The same model is offered by several providers. Prices below are per provider; select a row to switch provider.

ProviderBillingInput / 1MOutput / 1MCache read / 1MContextMax output
Current

Token-based pricing

$0.30$1.20$0.006

1M

393,216

Pricing

USD per 1M tokens

Prices from the current provider, per 1M tokens.

Input / 1MOutput / 1MCache read / 1M
$0.30$1.20$0.006

Performance

Metrics unavailable

Data for this section is coming soon.

Uptime

Metrics unavailable

Data for this section is coming soon.

One API for the world’s leading AI models.

© 2026 Cloudsome. All rights reserved.