someaistuff.
deepseekListed Sep 10, 2026

DeepSeek: DeepSeek V4.1 Flash (batch)

DeepSeek 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...

Compare
Context window1M
Max output384K
Provider endpoints3
Benchmark results0
Image inputTool callingStructured outputReasoningPrompt cachingOpen weights
Measured performance

Benchmark results

All leaderboards ↗
—

No published results in this index yet

Scores appear here when an evaluation matches this exact model.

Access & cost

Prices across providers

3 quotes

Your token mix

USD · listed token rates

Sail Research · via OpenRoutersail-research/fp4 · quantization=fp4
$0.0875
DeepInfra · via OpenRouterdeepinfra/fp8 · quantization=fp8
$0.196

OpenRouter

Catalog quote
Input
$0.05
Output
$0.15
Cached input
$0.004
USD / 1M tokens
1M context384K max outputPrice source ↗Checked Oct 18, 2026
Endpoint IDdeepseek/deepseek-v4.1-flash:batch

Sail Research

via OpenRouter

sail-research/fp4 · quantization=fp4

Input
$0.05
Output
$0.15
Cached input
$0.004
USD / 1M tokens
1M context384K max outputPrice source ↗Checked Oct 18, 2026
Endpoint IDdeepseek/deepseek-v4.1-flash:batch::sail-research/fp4

DeepInfra

via OpenRouter

deepinfra/fp8 · quantization=fp8

Input
$0.112
Output
$0.336
Cached input
$0.00336
USD / 1M tokens

Source discount 30%; rates as published

1M context131.1K max outputPrice source ↗Checked Oct 18, 2026
Endpoint IDdeepseek/deepseek-v4.1-flash:batch::deepinfra/fp8

Model specifications

Developer
deepseek
Modality
Language
Context
1,048,576 tokens
Maximum output
384,000 tokens
Weights
Open weights
Provider listed
Sep 10, 2026
First discovered
Oct 16, 2026

Exact identities

  • openrouterdeepseek/deepseek-v4.1-flash:batch

Sources

OpenRouter ↗

Updated Oct 18, 2026

More from deepseek

View all ↗