Skip to content
Metatext Decide — typed decisions for your agents, with a probability on every answerGet early access
Metatext
Sign Up

DeepSeek V4 Flash Fast

CommandCodeOpen weights

DeepSeek V4 Flash Fast by CommandCode costs $0.28 per 1M input tokens and $0.56 per 1M output tokens, with a 1M-token context window.

Pricing

Input (per 1M tokens)
$0.28
Output (per 1M tokens)
$0.56
Cached input (per 1M)
$0.07

Specifications

Provider
CommandCode
Context window
1M tokens
Parameters
—
Released
Apr 2026
Open weights
Yes
Frontier model
No

Compare DeepSeek V4 Flash Fast with…

DeepSeek V4 Flash Fast vs inclusionAI/Ling-flash-2.0$0.57/1MDeepSeek V4 Flash Fast vs Qwen3 235B A22B Instruct 2507$0.55/1MDeepSeek V4 Flash Fast vs Llama 4 Scout$0.59/1MDeepSeek V4 Flash Fast vs Hy3$0.53/1MDeepSeek V4 Flash Fast vs GPT OSS 120B$0.60/1MDeepSeek V4 Flash Fast vs GPT-4o-mini$0.60/1M

FAQ

How much does DeepSeek V4 Flash Fast cost?

DeepSeek V4 Flash Fast is priced at $0.28 per 1M input tokens and $0.56 per 1M output tokens. Output tokens cost more than input.

What is DeepSeek V4 Flash Fast's context window?

DeepSeek V4 Flash Fast supports a context window of 1M tokens — the maximum prompt plus response length it can handle in a single request.

Is DeepSeek V4 Flash Fast open weight?

Yes — DeepSeek V4 Flash Fast has openly available weights.

Data as of 2026-10-17. Source: models.dev (open). Pricing is per 1M tokens (USD); confirm with the provider before production use.