DeepSeek V4 Pro 0813

DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.

deepseek/deepseek-v4-pro-0813

Organization: DeepSeek
Family: deepseek-thinking
Providers: 40
Context: 1,000,000
Output limit: 384,000
Knowledge: —
Release: 2026-08-12
Updated: 2026-08-22
Weights: Open
Input: text
Output: text
Capabilities: Tools, Reasoning, Structured, Temperature

Providers

Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.

68 offers · USD per million tokens

Provider	Model ID	Context	Output	Input / output · 1M	Reasoning	Tools	Structured	Details
above.dev	deepseek-v4-pro	1,000,000	384,000	$0.726 / $2.178	Yes	Yes	Yes	View
AIHubMix	deepseek-v4-pro-0813	1,000,000	384,000	$0.6918 / $2.0754	Yes	Yes	Yes	View
Alibaba Token Plan	deepseek-v4-pro-0813	1,000,000	384,000	$0.00 / $0.00	Yes	Yes	Yes	View
Alibaba Token Plan (China)	deepseek-v4-pro-0813	1,000,000	384,000	$0.00 / $0.00	Yes	Yes	Yes	View
Arcee	deepseek/deepseek-v4-pro-0813	1,048,576	384,000	$1.32 / $3.96	Yes	Yes	Yes	View
Baseten	deepseek-ai/DeepSeek-V4-Pro-0813	1,048,576	262,144	$1.32 / $3.96	Yes	Yes	Yes	View
Bothub	deepseek-v4-pro-0813	1,000,000	384,000	$1.61 / $4.84	Yes	Yes	Yes	View
Charm Hyper	deepseek-v4-pro-0813	1,000,000	262,144	$1.437216 / $4.311648	Yes	Yes	Yes	View
Cloudflare Workers AI	@cf/deepseek-ai/deepseek-v4-pro-0813	1,048,576	1,048,576	$1.32 / $3.96	Yes	Yes	Yes	View
CoreWeave	deepseek-ai/DeepSeek-V4-Pro-0813	1,048,576	1,048,576	$1.31 / $3.96	Yes	Yes	Yes	View
Cortecs	deepseek-v4-pro-0813	1,048,576	64,000	$2.00 / $3.999	Yes	Yes	Yes	View
CrofAI	deepseek-v4-pro-0813	1,000,000	131,072	$0.35 / $0.80	Yes	Yes	Yes	View
Deep Infra	deepseek-ai/DeepSeek-V4-Pro-0813	1,048,576	384,000	$1.30 / $2.60	Yes	Yes	Yes	View
DeepSeek	deepseek-v4-pro	1,000,000	393,216	$0.66 / $1.98	Yes	Yes	Yes	View
DigitalOcean	deepseek-v4-pro-0813	1,048,576	1,048,576	$1.32 / $3.96	Yes	Yes	Yes	View
Eden AI	cloudflare/@cf/deepseek-ai/deepseek-v4-pro-0813	1,048,576	384,000	$1.32 / $3.96	Yes	Yes	Yes	View
Eden AI	qwen/deepseek-v4-pro-0813	1,000,000	384,000	$0.66 / $1.98	Yes	Yes	Yes	View
Eden AI	tensorx/deepseek/deepseek-v4-pro-0813	1,048,576	384,000	$2.00 / $4.00	Yes	Yes	No	View
Eden AI	together_ai/deepseek-ai/DeepSeek-V4-Pro-0813	1,048,576	384,000	$1.32 / $3.96	Yes	Yes	Yes	View
Eden AI	tencent/deepseek-v4-pro-0813	1,000,000	384,000	$0.66 / $1.98	Yes	No	No	View
Eden AI	deepinfra/deepseek-ai/DeepSeek-V4-Pro-0813	1,048,576	384,000	$1.30 / $2.60	Yes	Yes	Yes	View
Eden AI	databricks/databricks-deepseek-v4-pro-0813	1,000,000	384,000	$1.32 / $3.959999	Yes	Yes	No	View
Eden AI	nebius/deepseek-ai/DeepSeek-V4-Pro-0813	979,000	384,000	$1.32 / $3.96	Yes	Yes	Yes	View
EmpirioLabs AI	deepseek-v4-pro-0813	1,000,000	393,216	$1.32 / $3.96	Yes	Yes	Yes	View
Hugging Face	deepseek-ai/DeepSeek-V4-Pro-0813	1,000,000	384,000	$1.32 / $3.96	Yes	Yes	Yes	View
IteraCompute	deepseek/deepseek-v4-pro-0813	1,048,576	393,216	$1.10 / $3.30	Yes	Yes	Yes	View
Kilo Gateway	deepseek/deepseek-v4-pro-0813	1,048,576	943,718	$1.32 / $3.96	Yes	Yes	Yes	View
Merge Gateway	deepseek/deepseek-v4-pro-0813	1,000,000	384,000	$1.74 / $3.48	Yes	Yes	Yes	View
NanoGPT	deepseek/deepseek-v4-pro-0813:thinking	1,048,576	384,000	$1.10 / $2.50	Yes	Yes	Yes	View
NanoGPT	deepseek/deepseek-v4-pro-0813	1,048,576	384,000	$1.10 / $2.50	Yes	Yes	Yes	View
Nebius Token Factory	deepseek-ai/DeepSeek-V4-Pro-0813	979,000	979,000	$1.32 / $3.96	Yes	Yes	Yes	View
Nvidia	deepseek-ai/deepseek-v4-pro-0813	1,000,000	384,000	$0.00 / $0.00	Yes	Yes	Yes	View
Ofox	deepseek/deepseek-v4-pro-0813	1,000,000	384,000	$0.924 / $2.772	Yes	Yes	Yes	View
Ollama Cloud	deepseek-v4-pro:0813	1,048,576	1,048,576	$0.66 / $1.98	Yes	Yes	Yes	View
Alibabavia OpenRouter	deepseek/deepseek-v4-pro-0813 unknown	1,000,000	393,216	$1.122 / $3.366	Yes	Yes	Yes	View
AtlasCloudvia OpenRouter	deepseek/deepseek-v4-pro-0813 fp8	1,048,576	393,216	$1.32 / $3.96	Yes	Yes	Yes	View
Baiduvia OpenRouter	deepseek/deepseek-v4-pro-0813 fp8	1,048,576	393,216	$1.32 / $3.96	Yes	Yes	Yes	View
Cloudflarevia OpenRouter	deepseek/deepseek-v4-pro-0813 unknown	1,048,576	943,718	$1.32 / $3.96	Yes	Yes	Yes	View
CoreWeavevia OpenRouter	deepseek/deepseek-v4-pro-0813 fp8	1,048,576	943,718	$1.31 / $3.96	Yes	Yes	Yes	View
DeepInfravia OpenRouter	deepseek/deepseek-v4-pro-0813 fp8	1,048,576	16,384	$1.30 / $2.60	Yes	Yes	Yes	View
DeepSeekvia OpenRouter	deepseek/deepseek-v4-pro-0813 unknown	1,048,576	393,216	$0.66 / $1.98	Yes	Yes	No	View
DigitalOceanvia OpenRouter	deepseek/deepseek-v4-pro-0813 unknown	1,048,576	943,718	$1.32 / $3.96	Yes	Yes	Yes	View
GMICloudvia OpenRouter	deepseek/deepseek-v4-pro-0813 fp8	1,048,575	943,717	$1.056 / $3.168	Yes	Yes	No	View
Ionstreamvia OpenRouter	deepseek/deepseek-v4-pro-0813 unknown	1,048,576	943,718	$0.237696 / $1.980032	Yes	Yes	Yes	View
NextBitvia OpenRouter	deepseek/deepseek-v4-pro-0813 fp8	1,048,576	943,718	$1.056 / $3.168	Yes	Yes	Yes	View
Novitavia OpenRouter	deepseek/deepseek-v4-pro-0813 fp8	1,048,576	393,216	$0.99 / $2.97	Yes	Yes	No	View
Parasailvia OpenRouter	deepseek/deepseek-v4-pro-0813 fp8	1,048,576	943,718	$1.32 / $3.96	Yes	Yes	Yes	View
Phalavia OpenRouter	deepseek/deepseek-v4-pro-0813 unknown	1,048,576	393,216	$0.957 / $2.8776	Yes	Yes	Yes	View
Relacevia OpenRouter	deepseek/deepseek-v4-pro-0813 fp4	1,048,576	393,216	$0.1901 / $4.20	Yes	Yes	No	View
SiliconFlowvia OpenRouter	deepseek/deepseek-v4-pro-0813 fp8	1,048,576	393,216	$1.32 / $3.96	Yes	Yes	No	View
StreamLakevia OpenRouter	deepseek/deepseek-v4-pro-0813 unknown	1,024,000	384,000	$0.848628 / $2.545884	Yes	Yes	No	View
Togethervia OpenRouter	deepseek/deepseek-v4-pro-0813 unknown	1,048,576	943,718	$1.32 / $3.96	Yes	Yes	Yes	View
Venicevia OpenRouter	deepseek/deepseek-v4-pro-0813 unknown	1,000,000	32,768	$1.65 / $4.95	Yes	Yes	Yes	View
Wafervia OpenRouter	deepseek/deepseek-v4-pro-0813 unknown	1,048,576	943,718	$0.85 / $5.00	Yes	Yes	Yes	View
OrcaRouter	deepseek/deepseek-v4-pro-0813	1,000,000	384,000	$0.442 / $0.884	Yes	Yes	Yes	View
Requesty	deepseek-v4-pro-0813	1,000,000	131,072	$1.32 / $3.96	Yes	Yes	Yes	View
Requesty	deepseek-v4-pro-0813@eu	1,048,576	65,536	$1.75 / $3.50	Yes	Yes	Yes	View
RunInfra	deepseek-ai/DeepSeek-V4-Pro-0813	1,048,576	32,768	$0.60 / $1.90	Yes	Yes	Yes	View
SCNet Token Plan	DeepSeek-V4-Pro-0813	1,000,000	384,000	$0.00 / $0.00	Yes	Yes	Yes	View
SenseNova (China)	deepseek-v4-pro	1,048,576	65,536	$0.00 / $0.00	Yes	Yes	Yes	View
SiliconFlow	deepseek-ai/DeepSeek-V4-Pro-0813	1,000,000	384,000	$1.32 / $3.96	Yes	Yes	Yes	View
Tempr Gateway	deepseek/deepseek-v4-pro	1,000,000	384,000	$0.66 / $1.98	Yes	Yes	Yes	View
TensorX	deepseek/deepseek-v4-pro-0813	1,048,576	64,000	$2.00 / $4.00	Yes	Yes	Yes	View
Together AI	deepseek-ai/DeepSeek-V4-Pro-0813	1,048,576	384,000	$1.32 / $3.96	Yes	Yes	Yes	View
Venice AI	deepseek-v4-pro-0813	1,000,000	32,768	$1.65 / $4.95	Yes	Yes	Yes	View
Vercel AI Gateway	deepseek/deepseek-v4-pro-0813	1,000,000	384,000	$0.66 / $1.98	Yes	Yes	Yes	View
Vivgrid	deepseek-v4-pro-0813	1,000,000	384,000	$1.35 / $3.00	Yes	Yes	Yes	View
Volcengine Ark	deepseek-v4-pro-ga-260813	1,000,000	384,000	$1.3359 / $4.00771	Yes	Yes	Yes	View

Prices and limits apply to each offer. A dash means the value is not provided. OpenRouter offers show the hosting provider and routing channel separately.

Pricing

Compare token rates and cache charges across available routes and hosting configurations.

USD per million tokens

Input from$0.00Per 1M input tokens

Output from$0.00Per 1M output tokens

Available offers68Across 40 providers

Lowest listed input and output prices across the offers above; they may belong to different providers. These are base rates, before conditional pricing, discounts or additional fees.

Endpoint price comparisonLatest observed snapshot · 10 lowest-priced configurations

InputOutput

Relacerelace/fp4

$0.1901$4.20

Ionstreamionstream

$0.237696$1.980032

DeepSeekdeepseek

$0.66$1.98

StreamLakestreamlake

$0.848628$2.545884

Waferwafer

$0.85$5.00

Phalaphala

$0.957$2.8776

Novitanovita/fp8

$0.99$2.97

GMICloudgmicloud/fp8

$1.056$3.168

NextBitnextbit/fp8

$1.056$3.168

Alibabaalibaba

$1.122$3.366

deepseek/deepseek-v4-pro-0813Observed Oct 4, 2026, 11:31 AM UTC

Input: $0.85
Output: $5.00
Cache read: $0.70

Hosting prices through OpenRouter All endpoints and cache rates

Endpoint	Input / 1M	Output / 1M	Cache read / 1M	Cache write / 1M
Alibabaalibaba	$1.122	$3.366	$0.1122	—
AtlasCloudatlas-cloud/fp8	$1.32	$3.96	$0.132	—
Baidubaidu/fp8	$1.32	$3.96	$0.042	—
Cloudflarecloudflare	$1.32	$3.96	$0.044	—
CoreWeavecoreweave/fp8	$1.31	$3.96	$0.044	—
DeepInfradeepinfra/fp8	$1.30	$2.60	$0.10	—
DeepSeekdeepseek	$0.66	$1.98	$0.022	—
DigitalOceandigitalocean	$1.32	$3.96	$0.044	—
GMICloudgmicloud/fp8	$1.056	$3.168	$0.0352	—
Ionstreamionstream	$0.237696	$1.980032	$0.075072	—
NextBitnextbit/fp8	$1.056	$3.168	$0.035	—
Novitanovita/fp8	$0.99	$2.97	$0.033	—
Parasailparasail/fp8	$1.32	$3.96	$0.044	—
Phalaphala	$0.957	$2.8776	$0.099	—
Relacerelace/fp4	$0.1901	$4.20	$0.19	—
SiliconFlowsiliconflow/fp8	$1.32	$3.96	$0.044	—
StreamLakestreamlake	$0.848628	$2.545884	$0.028288	—
Togethertogether	$1.32	$3.96	$0.13	—
Venicevenice	$1.65	$4.95	$0.165	—
Waferwafer	$0.85	$5.00	$0.70	—

Each row is a hosting configuration. Open an offer in Providers for its full pricing conditions and additional fees. Endpoint observations may differ from the routing catalog's base price.

Performance

Review reported latency and output-throughput percentiles from the latest observed rolling window.

Latest 30-minute observation

Time to first token · milliseconds

Latency distributionRolling 30-minute snapshot · 6 endpoints

P50P75P90P99

Alibabaalibaba

1,256–3,266.44 ms

AtlasCloudatlas-cloud/fp8

1,614–8,735.12 ms

Baidubaidu/fp8

1,363.5–7,226.1 ms

Cloudflarecloudflare

1,590–4,565.2 ms

CoreWeavecoreweave/fp8

582–4,293.6 ms

DeepInfradeepinfra/fp8

1,423–6,034.26 ms

All latency percentiles 20 endpoints

Endpoint	P50	P75	P90	P99
Alibabaalibaba	1,256 ms	1,491 ms	1,753.6 ms	3,266.44 ms
AtlasCloudatlas-cloud/fp8	1,614 ms	3,392 ms	5,591.2 ms	8,735.12 ms
Baidubaidu/fp8	1,363.5 ms	2,179.75 ms	3,708.5 ms	7,226.1 ms
Cloudflarecloudflare	1,590 ms	2,445.5 ms	3,374.6 ms	4,565.2 ms
CoreWeavecoreweave/fp8	582 ms	918 ms	1,574.4 ms	4,293.6 ms
DeepInfradeepinfra/fp8	1,423 ms	2,124 ms	2,989.6 ms	6,034.26 ms
DeepSeekdeepseek	1,776 ms	2,908 ms	6,089.9 ms	26,016.62 ms
DigitalOceandigitalocean	990 ms	1,556.5 ms	1,872.8 ms	21,633.03 ms
GMICloudgmicloud/fp8	3,715 ms	3,979.5 ms	4,306 ms	9,343.54 ms
Ionstreamionstream	2,427.5 ms	3,808.5 ms	5,591.4 ms	11,234.58 ms
NextBitnextbit/fp8	2,837 ms	3,379 ms	3,894 ms	6,511.02 ms
Novitanovita/fp8	2,065 ms	3,042 ms	4,900.5 ms	17,008.75 ms
Parasailparasail/fp8	932 ms	1,400.5 ms	2,443.2 ms	7,524.9 ms
Phalaphala	3,302 ms	3,767 ms	4,438.8 ms	6,392.84 ms
Relacerelace/fp4	1,083 ms	1,652 ms	2,303.8 ms	11,120.16 ms
SiliconFlowsiliconflow/fp8	1,487 ms	1,797 ms	2,083.2 ms	2,810.08 ms
StreamLakestreamlake	2,545.5 ms	3,487 ms	5,382.2 ms	14,289.51 ms
Togethertogether	1,692 ms	2,282 ms	3,170 ms	13,058.4 ms
Venicevenice	1,179.5 ms	1,545.75 ms	2,775.7 ms	54,211.3 ms
Waferwafer	802 ms	1,520.25 ms	2,418.8 ms	21,786.25 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 6 endpoints

P50P75P90P99

Alibabaalibaba

69–136.4 t/s

AtlasCloudatlas-cloud/fp8

49–151.55 t/s

Baidubaidu/fp8

46–80.53 t/s

Cloudflarecloudflare

46–66.76 t/s

CoreWeavecoreweave/fp8

129–281.28 t/s

DeepInfradeepinfra/fp8

44–99.54 t/s

All throughput percentiles 20 endpoints

Endpoint	P50	P75	P90	P99
Alibabaalibaba	69 t/s	85.5 t/s	96.8 t/s	136.4 t/s
AtlasCloudatlas-cloud/fp8	49 t/s	57 t/s	73.3 t/s	151.55 t/s
Baidubaidu/fp8	46 t/s	55 t/s	65.3 t/s	80.53 t/s
Cloudflarecloudflare	46 t/s	55 t/s	58 t/s	66.76 t/s
CoreWeavecoreweave/fp8	129 t/s	159 t/s	193 t/s	281.28 t/s
DeepInfradeepinfra/fp8	44 t/s	60 t/s	74.7 t/s	99.54 t/s
DeepSeekdeepseek	57 t/s	74 t/s	95 t/s	131 t/s
DigitalOceandigitalocean	47 t/s	51 t/s	55.3 t/s	56.43 t/s
GMICloudgmicloud/fp8	30 t/s	33 t/s	37 t/s	54.14 t/s
Ionstreamionstream	26 t/s	32 t/s	38 t/s	58 t/s
NextBitnextbit/fp8	37 t/s	46 t/s	64.6 t/s	97 t/s
Novitanovita/fp8	68 t/s	93.75 t/s	105 t/s	138.34 t/s
Parasailparasail/fp8	65 t/s	72 t/s	76 t/s	84 t/s
Phalaphala	44 t/s	55 t/s	67 t/s	85.08 t/s
Relacerelace/fp4	93 t/s	117 t/s	136 t/s	173.52 t/s
SiliconFlowsiliconflow/fp8	61 t/s	64 t/s	78 t/s	105 t/s
StreamLakestreamlake	49 t/s	61 t/s	67 t/s	82 t/s
Togethertogether	56 t/s	68 t/s	81 t/s	102.62 t/s
Venicevenice	52 t/s	62 t/s	71 t/s	95 t/s
Waferwafer	117 t/s	161 t/s	195 t/s	260.6 t/s

Percentiles describe the observed request distribution. These are snapshots of a rolling window, not a historical time series.

Uptime

Compare successful request rates across the latest 5-minute, 30-minute, and 24-hour observations.

Successful requests by window

Availability by endpointCurrent overlapping windows · 20 endpoints

Endpoint5 minutes30 minutes24 hours

AlibabaalibabaObserved Oct 4, 2026, 11:31 AM UTC

—

97.64%

97.4%

AtlasCloudatlas-cloud/fp8Observed Oct 4, 2026, 11:31 AM UTC

100%

99.41%

98.37%

Baidubaidu/fp8Observed Oct 4, 2026, 11:31 AM UTC

—

100%

99.95%

CloudflarecloudflareObserved Oct 4, 2026, 11:31 AM UTC

—

99.05%

CoreWeavecoreweave/fp8Observed Oct 4, 2026, 11:31 AM UTC

99.58%

99.88%

99.98%

DeepInfradeepinfra/fp8Observed Oct 4, 2026, 11:31 AM UTC

100%

99.19%

99.84%

DeepSeekdeepseekObserved Oct 4, 2026, 11:31 AM UTC

99.91%

99.98%

99.99%

DigitalOceandigitaloceanObserved Oct 4, 2026, 11:31 AM UTC

—

99.96%

GMICloudgmicloud/fp8Observed Oct 4, 2026, 11:31 AM UTC

100%

99.98%

IonstreamionstreamObserved Oct 4, 2026, 11:31 AM UTC

100%

99.98%

99.77%

NextBitnextbit/fp8Observed Oct 4, 2026, 11:31 AM UTC

—

100%

99.88%

Novitanovita/fp8Observed Oct 4, 2026, 11:31 AM UTC

100%

99.94%

99.95%

Parasailparasail/fp8Observed Oct 4, 2026, 11:31 AM UTC

100%

99.72%

PhalaphalaObserved Oct 4, 2026, 11:31 AM UTC

100%

99.63%

Relacerelace/fp4Observed Oct 4, 2026, 11:31 AM UTC

100%

99.89%

99.93%

SiliconFlowsiliconflow/fp8Observed Oct 4, 2026, 11:31 AM UTC

—

100%

StreamLakestreamlakeObserved Oct 4, 2026, 11:31 AM UTC

100%

99.91%

99.68%

TogethertogetherObserved Oct 4, 2026, 11:31 AM UTC

100%

98.39%

99.07%

VeniceveniceObserved Oct 4, 2026, 11:31 AM UTC

—

97.36%

WaferwaferObserved Oct 4, 2026, 11:31 AM UTC

100%

99.46%

98.21%

Reported by OpenRouter at the time of collection; rate-limited requests are excluded. A dash means no measurement was reported. This is not a live availability check.

Benchmarks

Review attributed evaluation results on each source's original scale.

External evaluations

deepseek/deepseek-v4-pro-0813Observed Oct 4, 2026, 11:31 AM UTC

Benchmark profileArtificial Analysis · shared source scale from 0 to 70

Coding

68.8

Agentic

41.3

Intelligence

Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not OpenAI Suite ratings.

Detailed evaluations

Evaluation scoresAccuracy or item F1 · higher is better

gpqa diamondDeepSeek: DeepSeek V4 Pro 0813

89.753%

tau bench verified airlineDeepSeek: DeepSeek V4 Pro 0813

76.952%

Evaluation	Configuration	Source	Results	Details
gpqa diamond	DeepSeek: DeepSeek V4 Pro 0813deepseek/deepseek-v4-pro-20260813	OpenRouter	89.753%	Details
tau bench verified airline	DeepSeek: DeepSeek V4 Pro 0813deepseek/deepseek-v4-pro-20260813	OpenRouter	76.952%	Details
Composite indices	DeepSeek V4 Pro 0813 (Reasoning, Max Effort)deepseek/deepseek-v4-pro-20260813	Artificial Analysis	Intelligence 36 · Coding 68.8 · Agentic 41.3	Details

Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 4, 2026.

Apps & session costs

Compare observed median session costs for applications using this model, grouped by conversation length.

30-day sample · through Sep 27, 2026

Application	Model route	Turns	Median cost / session	Details
Kilo Code	deepseek/deepseek-v4-pro-20260813	10–49 turns	$0.248663	Details
Kilo Code	deepseek/deepseek-v4-pro-20260813	50+ turns	$1.399181	Details
Hermes Agent	deepseek/deepseek-v4-pro-20260813	1 turn	$0.006068	Details
Codex	deepseek/deepseek-v4-pro-20260813	1 turn	$0.004655	Details
Kilo Code	deepseek/deepseek-v4-pro-20260813	2–9 turns	$0.05371	Details
Claude Code	deepseek/deepseek-v4-pro-20260813	50+ turns	$1.737687	Details
Claude Code	deepseek/deepseek-v4-pro-20260813	10–49 turns	$0.293043	Details
Hermes Agent	deepseek/deepseek-v4-pro-20260813	2–9 turns	$0.031456	Details
Hermes Agent	deepseek/deepseek-v4-pro-20260813	10–49 turns	$0.226015	Details
Claude Code	deepseek/deepseek-v4-pro-20260813	1 turn	$0.014933	Details
Claude Code	deepseek/deepseek-v4-pro-20260813	2–9 turns	$0.048814	Details
Hermes Agent	deepseek/deepseek-v4-pro-20260813	50+ turns	$1.369741	Details

Source: OpenRouter, as of Oct 2, 2026. Published under CC BY 4.0. These are observed costs per session, not token prices or a forecast for your workload. Apps are compared separately.

Activity

Daily prompt and completion tokens reported for this model's routes in OpenRouter's top 50. Missing days have no published value.

Last 90 complete UTC days

Daily token usage7,668,122,270,018 reported tokens · 52 days with observations

219B0

2026-08-13
142,872,896,552 tokens

2026-08-14
170,617,734,905 tokens

2026-08-15
160,702,050,576 tokens

2026-08-16
142,657,253,042 tokens

2026-08-17
158,225,612,439 tokens

2026-08-18
150,066,093,306 tokens

2026-08-19
143,130,950,148 tokens

2026-08-20
156,319,697,820 tokens

2026-08-21
157,361,704,999 tokens

2026-08-22
118,182,296,394 tokens

2026-08-23
108,660,917,552 tokens

2026-08-24
149,962,740,550 tokens

2026-08-25
175,615,928,918 tokens

2026-08-26
158,211,832,654 tokens

2026-08-27
159,220,935,079 tokens

2026-08-28
161,229,337,159 tokens

2026-08-29
141,592,626,312 tokens

2026-08-30
139,812,274,076 tokens

2026-08-31
157,969,767,296 tokens

2026-09-01
165,725,816,538 tokens

2026-09-02
161,884,749,981 tokens

2026-09-03
150,563,199,232 tokens

2026-09-04
150,926,473,217 tokens

2026-09-05
121,320,086,360 tokens

2026-09-06
126,297,662,315 tokens

2026-09-07
164,501,941,214 tokens

2026-09-08
198,145,144,907 tokens

2026-09-09
187,717,948,589 tokens

2026-09-10
169,522,716,523 tokens

2026-09-11
141,597,066,297 tokens

2026-09-12
98,839,793,339 tokens

2026-09-13
96,357,584,998 tokens

2026-09-14
148,856,919,081 tokens

2026-09-15
158,699,464,095 tokens

2026-09-16
219,243,213,462 tokens

2026-09-17
180,339,949,582 tokens

2026-09-18
153,409,332,889 tokens

2026-09-19
178,079,183,306 tokens

2026-09-20
135,660,109,920 tokens

2026-09-21
158,440,540,743 tokens

2026-09-22
165,088,442,405 tokens

2026-09-23
167,574,511,919 tokens

2026-09-24
141,337,984,030 tokens

2026-09-25
96,807,331,883 tokens

2026-09-26
157,405,835,924 tokens

2026-09-27
131,662,018,050 tokens

2026-09-28
134,050,593,429 tokens

2026-09-29
124,478,725,371 tokens

2026-09-30
114,193,513,797 tokens

2026-10-01
105,756,999,998 tokens

2026-10-02
125,612,406,883 tokens

2026-10-03
85,612,359,964 tokens

Jul 6, 2026Oct 3, 2026

Daily observations · 52 days

Date (UTC)	Reported tokens	Reported routes
Oct 3, 2026	85,612,359,964	1
Oct 2, 2026	125,612,406,883	1
Oct 1, 2026	105,756,999,998	1
Sep 30, 2026	114,193,513,797	1
Sep 29, 2026	124,478,725,371	1
Sep 28, 2026	134,050,593,429	1
Sep 27, 2026	131,662,018,050	1
Sep 26, 2026	157,405,835,924	1
Sep 25, 2026	96,807,331,883	1
Sep 24, 2026	141,337,984,030	1
Sep 23, 2026	167,574,511,919	1
Sep 22, 2026	165,088,442,405	1
Sep 21, 2026	158,440,540,743	1
Sep 20, 2026	135,660,109,920	1
Sep 19, 2026	178,079,183,306	1
Sep 18, 2026	153,409,332,889	1
Sep 17, 2026	180,339,949,582	1
Sep 16, 2026	219,243,213,462	1
Sep 15, 2026	158,699,464,095	1
Sep 14, 2026	148,856,919,081	1
Sep 13, 2026	96,357,584,998	1
Sep 12, 2026	98,839,793,339	1
Sep 11, 2026	141,597,066,297	1
Sep 10, 2026	169,522,716,523	1
Sep 9, 2026	187,717,948,589	1
Sep 8, 2026	198,145,144,907	1
Sep 7, 2026	164,501,941,214	1
Sep 6, 2026	126,297,662,315	1
Sep 5, 2026	121,320,086,360	1
Sep 4, 2026	150,926,473,217	1
Sep 3, 2026	150,563,199,232	1
Sep 2, 2026	161,884,749,981	1
Sep 1, 2026	165,725,816,538	1
Aug 31, 2026	157,969,767,296	1
Aug 30, 2026	139,812,274,076	1
Aug 29, 2026	141,592,626,312	1
Aug 28, 2026	161,229,337,159	1
Aug 27, 2026	159,220,935,079	1
Aug 26, 2026	158,211,832,654	1
Aug 25, 2026	175,615,928,918	1
Aug 24, 2026	149,962,740,550	1
Aug 23, 2026	108,660,917,552	1
Aug 22, 2026	118,182,296,394	1
Aug 21, 2026	157,361,704,999	1
Aug 20, 2026	156,319,697,820	1
Aug 19, 2026	143,130,950,148	1
Aug 18, 2026	150,066,093,306	1
Aug 17, 2026	158,225,612,439	1
Aug 16, 2026	142,657,253,042	1
Aug 15, 2026	160,702,050,576	1
Aug 14, 2026	170,617,734,905	1
Aug 13, 2026	142,872,896,552	1

Source: OpenRouter (openrouter.ai/rankings), as of Oct 4, 2026. CC BY 4.0. Totals include only individually published routes. Tokenizers differ by provider; the aggregated “other” category is never assigned to a model.

Technical details & API

Explore specifications, supported parameters, reasoning controls, and API identifiers for each OpenRouter route.

Current route specifications

deepseek/deepseek-v4-pro-0813Observed Oct 4, 2026, 11:31 AM UTC

Context: 1,048,576
Maximum output: 943,718
Tokenizer: DeepSeek
Input: text
Output: text
Moderation: No
Added to OpenRouter: 2026-08-12

Base URLhttps://openrouter.ai/api/v1

Model IDdeepseek/deepseek-v4-pro-0813

Version IDdeepseek/deepseek-v4-pro-20260813

Weights IDdeepseek-ai/DeepSeek-V4-Pro-0813

Reasoning

Required: No
Enabled by default: Not reported
Default effort: high
Supported efforts: max, high, low

Supported parameters

frequency_penalty
include_reasoning
logit_bias
logprobs
max_tokens
min_p
presence_penalty
reasoning
reasoning_effort
repetition_penalty
response_format
seed
stop
structured_outputs
temperature
tool_choice
tools
top_k
top_logprobs
top_p

Default parameters

top p: 1
temperature: 1

Frequently asked questions

Answers based on the model metadata and serving offers currently in the catalog.

How much does DeepSeek V4 Pro 0813 cost?

Listed rates start at $0.00 per million input tokens and $0.00 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer DeepSeek V4 Pro 0813?

There are 68 cataloged offers across 40 providers. Compare model IDs, prices and limits in Providers.

What is the context window?

The cataloged model context is 1,000,000 tokens. Each serving endpoint may apply a different limit.

Does it support tools and structured output?

Tool calling: Yes. Structured output: Yes. Support can vary by endpoint.

Resources

MIT

Hugging Face ↗

Catalog history · 2 recorded revisions

Metadata observations since this model was first cataloged. These are not model release versions.

Sep 14, 2026 · d9bb6a8725ff
Sep 12, 2026 · 369eab2ff5c0