DeepSeek: DeepSeek V4 Pro 0813

deepseek/deepseek-v4-pro-0813

DeepSeek V4 Pro 0813 is DeepSeek's open-weight contender, ranking #89 of 271 on the TryAii Score. It's strongest on knowledge (#19 on GPQA). API pricing starts at $0.111/$4.44 per million input/output tokens, though similar scores now sell for about $2.5 per million output tokens, with 20 independent hosts serving it.

Prompt $/1M

$0.111

Completion $/1M

$4.440

Context

1,048,576 tok

Best provider

109 tok/s · DigitalOcean

Specs

Model id: deepseek/deepseek-v4-pro-0813
Display name: DeepSeek: DeepSeek V4 Pro 0813
Modality: text->text
Tokenizer: DeepSeek
Instruct type: —
Context length: 1,048,576
Max completion: 943,718
Prompt $/1M: $0.111
Completion $/1M: $4.440
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
DigitalOcean	109	1,103 ms	1,425 ms
Wafer	94	277 ms	379 ms
Sail Research	90	333 ms	496 ms
CoreWeave	81	425 ms	469 ms
Together	76	422 ms	539 ms
DeepSeek	74	993 ms	1,083 ms
GMICloud	63	1,863 ms	2,242 ms
Nebius	61	484 ms	563 ms
Parasail	59	376 ms	444 ms
BaseTen	53	507 ms	637 ms
Phala	44	5,776 ms	6,384 ms
Baidu	43	1,735 ms	2,097 ms
StreamLake	40	1,131 ms	1,304 ms
DeepInfra	35	1,170 ms	1,402 ms
Novita	32	1,755 ms	1,978 ms
Cloudflare	31	642 ms	789 ms
Alibaba	25	1,051 ms	1,130 ms
SiliconFlow	24	1,005 ms	1,088 ms
AtlasCloud	22	1,332 ms	2,126 ms
Venice	21	1,360 ms	1,589 ms
Relace	11	745 ms	860 ms