DeepSeek: DeepSeek V4.1 Flash pricing and limits

id deepseek/deepseek-v4.1-flash · listed 2026-09-10

Input (per 1M tokens)	$0.056
Output (per 1M tokens)	$0.120
Cached input read (per 1M)	$0.002
Context window	1,048,576 tokens
Max output	943,718 tokens
Modalities	text+image → text
Reasoning	yes

What 1,000 calls cost at 1,000 input and 300 output tokens each: $0.09.

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...

Cheaper on both input and output, with at least half the context

Model	In / 1M	Out / 1M	Context
Auto Router (Beta)	$-1000000.000	$-1000000.000	2,000,000
Pareto Code Router	$-1000000.000	$-1000000.000	2,000,000
Auto Router	$-1000000.000	$-1000000.000	2,000,000
DeepSeek: DeepSeek V4 Flash Latest	$0.017	$0.110	1,048,576
Thinking Machines: Inkling Small (free)	free	free	1,048,576
Thinking Machines: Inkling (free)	free	free	1,048,576

Other deepseek models

DeepSeek: DeepSeek V4.1 Flash (batch) ($0.050 / $0.150) · DeepSeek: DeepSeek V4 Flash 0423 ($0.091 / $0.182) · DeepSeek: DeepSeek V4.1 Flash 1017 ($0.150 / $0.600) · DeepSeek: DeepSeek V4 Flash Vision Exp ($0.216 / $0.647) · DeepSeek: DeepSeek V3.1 ($0.250 / $0.950) · DeepSeek: DeepSeek V3 ($0.257 / $1.029) · DeepSeek: DeepSeek V3.2 Exp ($0.270 / $0.410) · DeepSeek: DeepSeek V3.1 Terminus ($0.270 / $1.000)

For software and AI agents: this sheet as JSON per call, no account: GET https://store.agentexchange.work/gw/models/model?id=deepseek/deepseek-v4.1-flash (0.002 USD), /gw/models/cheapest?min_context=128000, /gw/models/models?provider=deepseek. Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Prices as listed by the hosting providers through OpenRouter, refreshed hourly; a provider's own console may differ. Not affiliated with deepseek. Agent Exchange