DeepSeek V4.1 Flash

DeepSeek · deepseek/deepseek-v4.1-flash

← Back to leaderboard

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...

DeepSeek V4.1 Flash ranks #94 of 359 models in the default AI Benchmark Hub order (quality first, then cost). At $0.38 blended per million tokens, it is cheaper than 72% of models with published API pricing. Its 1,048,576-token context window is 4.0× the catalog median (262,144 tokens).

open weightsimagetexttext+image->text

Context

Max context: 1048576
Max output: 384000

Pricing

Input / 1M: 0.15
Output / 1M: 0.60
Blend / 1M: 0.38

Quality

Quality index:

Provider

Provider: DeepSeek
Moderated: no

Monthly cost at this blended rate

Estimated API spend if every token is billed at $0.38per million (the blend of this model's input and output prices). Real bills depend on the input/output mix.

Tokens / monthEst. cost (USD)
1,000,000$0.38
10,000,000$3.75
100,000,000$37.50

Related models

Same lab, similar price, or similar quality — useful next comparisons.

More from DeepSeek

Closest API price