DeepSeek: DeepSeek V4 Flash 0423

deepseek/deepseek-v4-flash

DeepSeek V4 Flash 0423 (DeepSeek) is a low-cost open-weight model priced near the bottom of the board, at $0.0869/$0.174 per million input/output tokens, served by 27 independent hosts. For the money it delivers #70 of 236 on the TryAii Score — among the best score-per-dollar in its class. Its best result is knowledge (#33 on GPQA).

Prompt $/1M

$0.087

Completion $/1M

$0.174

Context

1,048,576 tok

Best provider

130 tok/s · Artificial Analysis

Specs

Model id: deepseek/deepseek-v4-flash
Display name: DeepSeek: DeepSeek V4 Flash 0423
Modality: text->text
Tokenizer: DeepSeek
Instruct type: —
Context length: 1,048,576
Max completion: 384,000
Prompt $/1M: $0.087
Completion $/1M: $0.174
Free tier: no

Capabilities

Function callingno
JSON modeno
System promptno
Visionno
Moderatedno

Benchmark scores

Each axis is one benchmark, normalized to the best model in the field.

No benchmark data for this model.

Speed by provider

Provider	tok/s	TTFT	Total latency
Artificial Analysis	130	778 ms	—
DeepSeekfastest	82	808 ms	923 ms
DekaLLM	79	1,593 ms	2,234 ms
Alibabafastest	76	939 ms	1,190 ms
Baidu	75	742 ms	870 ms
Fireworks	71	1,077 ms	1,441 ms
Phala	70	1,515 ms	1,678 ms
Cloudflare	66	814 ms	1,039 ms
NextBit	59	2,039 ms	2,280 ms
Novita	54	1,439 ms	1,687 ms
StreamLake	43	1,697 ms	2,067 ms
AtlasCloud	41	1,016 ms	1,269 ms
Azure	38	1,202 ms	1,800 ms
CoreWeave	35	591 ms	999 ms
Mancer 2	29	838 ms	1,181 ms
WandB	25	1,698 ms	2,242 ms
Ambient	23	1,382 ms	1,826 ms
GMICloud	23	4,203 ms	6,345 ms
Venice	23	2,451 ms	3,805 ms
Ionstream	22	1,131 ms	1,664 ms
SiliconFlow	22	2,533 ms	3,146 ms
Io Net	20	999 ms	1,178 ms
Parasail	20	955 ms	1,066 ms
Wafer	18	3,689 ms	4,558 ms
Morph	17	960 ms	1,157 ms
DeepInfra	13	4,249 ms	4,698 ms
AkashML	7	1,669 ms	1,897 ms
OpenInference	7	4,629 ms	5,916 ms
Sail Research	7	1,303 ms	2,292 ms
DigitalOcean	5	1,731 ms	2,031 ms
deepseekfastest	—	—	—