DeepSeek: DeepSeek V4 Pro 0423

deepseek/deepseek-v4-pro

DeepSeek V4 Pro 0423 is an open-weight model from DeepSeek, ranking #89 of 261 on the TryAii Score. It's strongest on knowledge (#15 on GPQA). It's served by 13 independent hosts from $0.955/$1.91 per million input/output tokens — a little under the going rate for its score class.

Prompt $/1M

$0.955

Completion $/1M

$1.911

Context

1,048,576 tok

Best provider

94 tok/s · Artificial Analysis

Specs

Model id: deepseek/deepseek-v4-pro
Display name: DeepSeek: DeepSeek V4 Pro 0423
Modality: text->text
Tokenizer: DeepSeek
Instruct type: —
Context length: 1,048,576
Max completion: 384,000
Prompt $/1M: $0.955
Completion $/1M: $1.911
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	94	1,045 ms	—
Relacefastest	76	1,016 ms	1,294 ms
Azure	76	1,823 ms	2,331 ms
Novita	55	1,989 ms	2,503 ms
Alibaba	51	1,809 ms	2,146 ms
Baidu	44	1,083 ms	1,269 ms
Cloudflare	42	1,597 ms	2,216 ms
Reka	39	926 ms	1,217 ms
AtlasCloud	39	1,625 ms	1,925 ms
StreamLake	38	1,549 ms	1,855 ms
SiliconFlow	32	2,038 ms	2,643 ms
Venice	32	1,843 ms	2,100 ms
DigitalOcean	30	1,222 ms	1,725 ms
Parasail	29	1,525 ms	2,442 ms
DeepInfra	29	1,437 ms	2,207 ms
GMICloud	22	2,810 ms	3,477 ms