DeepSeek: DeepSeek V4 Flash 0423

DeepSeek: DeepSeek V4 Flash 0423 is a large language model from DeepSeek. It costs $0.086 per million input tokens and $0.171 per million output tokens. Its context window is 1.0M tokens.

ReasoningTool callingStructured outputPrompt cachingOpen weights

Input / 1M tokens: $0.086
Output / 1M tokens: $0.171
Cached input / 1M: $0.017
Context window: 1.0M

Who serves it cheapest

17 hosts serve DeepSeek V4 Flash 0423. Same weights, same API - the price difference is pure margin and routing.

Providers serving DeepSeek: DeepSeek V4 Flash 0423, cheapest first
Provider	Input / 1M	Output / 1M	Context	Throughput	Uptime 24h
OpenInferenceCheapestfp8	$0.050	$0.140	1.0M	-	98.9%
DigitalOcean	$0.068	$0.168	1.0M	-	99.5%
Baidufp8	$0.085	$0.171	1.0M	-	99.6%
StreamLakefp8	$0.086	$0.171	1.0M	-	97.9%
DeepInfrafp8	$0.090	$0.180	1.0M	-	99.3%
GMICloudfp8	$0.091	$0.182	1.0M	-	100.0%
Venice	$0.097	$0.193	1M	-	99.0%
Wafer	$0.100	$0.250	1.0M	-	100.0%
SiliconFlowfp8	$0.130	$0.280	1.0M	-	95.0%
Alibabafp8	$0.134	$0.268	1M	-	99.4%
Novitafp8	$0.140	$0.280	1.0M	-	99.9%
AtlasCloudfp4	$0.140	$0.280	1.0M	-	100.0%
Parasailfp8	$0.140	$0.280	1.0M	-	99.6%
NextBitfp8	$0.150	$0.350	1.0M	-	99.8%
Phala	$0.200	$0.400	1.0M	-	99.9%
Mancer 2fp8	$0.190	$0.500	1.0M	-	99.1%
Azure	$0.210	$0.560	1.0M	-	96.5%

The spread between OpenInference and Azure is 4.1× for identical weights. Quantization and context limits differ, so check both columns before switching.

Benchmarks

Independent scores published alongside the catalogue.

Intelligence index: 24.8
Coding index: 52.0
Agentic index: 27.9

About DeepSeek V4 Flash 0423

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...

Specifications

DeepSeek: DeepSeek V4 Flash 0423 specifications
Model ID	`deepseek/deepseek-v4-flash`
Provider	DeepSeek
Context window	1.0M tokens
Max output	384K tokens
Input modalities	text
Output modalities	text
Knowledge cutoff	-
Open weights	Yes - deepseek-ai/DeepSeek-V4-Flash
Released	April 24, 2026

Cheaper alternatives

Models that cost less than DeepSeek V4 Flash 0423 while keeping at least half its context window and every input modality it supports.

DeepSeek V4 Flash 0731

$0.060 in · $0.120 out

1.4× cheaper

Qwen3.7 Flash

$0.030 in · $0.130 out

1.9× cheaper

Lyria 3 Pro Preview

Free in · Free out

Lyria 3 Clip Preview

Free in · Free out

Auto Router (Beta)

$-1000000.0000 in · $-1000000.0000 out

about the same cheaper

Frequently asked

How much does DeepSeek: DeepSeek V4 Flash 0423 cost?

$0.086 per million input tokens and $0.171 per million output tokens. Cached input reads cost $0.017 per million tokens.

What is the context window of DeepSeek: DeepSeek V4 Flash 0423?

1.0M tokens, with up to 384K tokens of output per request.

Which provider serves DeepSeek: DeepSeek V4 Flash 0423 cheapest?

OpenInference at $0.050 per million input tokens - 4.1× cheaper than Azure, the most expensive of the 17 hosts serving it.

Confirm against the source: DeepSeek official pricing.