Deprecated on Sep 25, 2026. 12 providers still list it at the prices below.
DeepSeek V4 Pro 0813Deprecated
Context
1M
Max output
1M
Serving providers
12
Cheapest input
$0.66 /1M
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower. An OpenRouter routed quote is the price of whichever upstream provider OpenRouter prefers today, so it moves day to day.
Benchmarks
independent evaluations · source: Artificial AnalysisSpeed & latency
Output speed
99 t/s
tokens / second
Time to first token
1.62s
latency
Headline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Automation Bench | 0.6 | default | — | |||||||||||||
| ||||||||||||||||
| CritPt | 18% | default | — | |||||||||||||
| ||||||||||||||||
| GDPval (normalized)Frozen Aug 18, 2026 | 47% | default | — | |||||||||||||
| ||||||||||||||||
| GPQA Diamond | 93% | default | — | |||||||||||||
| Humanity's Last Exam | 41% | default | — | |||||||||||||
| ||||||||||||||||
| Long-Context Reasoning | 80% | default | — | |||||||||||||
| ||||||||||||||||
| Omniscience | 0.8 | default | — | |||||||||||||
| ||||||||||||||||
| Omniscience Accuracy | 0.5 | default | — | |||||||||||||
| ||||||||||||||||
| Omniscience Non Hallucination | 0.1 | reasoning: false | — | |||||||||||||
| ||||||||||||||||
| SciCode | 51% | default | — | |||||||||||||
| ||||||||||||||||
| Terminal Bench40 | 0.1 | default | — | |||||||||||||
| ||||||||||||||||
| TerminalBench v2.1 | 79% | default | — | |||||||||||||
| τ-bench Banking | 40% | default | — | |||||||||||||
Artificial Analysis last published scores for this benchmark on Aug 18, 2026. Scores here are frozen at that date, and models released since are not on it.
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expandInput pricing runs from $0.66 to $1.32 per 1M tokens across 12 providers, so the dearest route costs 100% more than the cheapest for the same model.
| Serving provider | Input /1M | Output /1M | Endpoints | ||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| OpenRouterRouted quote | $0.66 | $1.98 | 1 | ||||||||||||||||
Standarddeepseek/deepseek-v4-pro-0813
| |||||||||||||||||||
| VercelRouted quoteVercel reseller quote | $0.66 | $1.98 | 1 | ||||||||||||||||
Standarddeepseek/deepseek-v4-pro-0813
| |||||||||||||||||||
| Sail | $0.92 | $2.77 | 1 | ||||||||||||||||
Standardsail/deepseek-ai/DeepSeek-V4-Pro-0813
| |||||||||||||||||||
| DeepInfra | $1.30 | $2.60 | 1 | ||||||||||||||||
Standarddeepinfra/deepseek-ai/DeepSeek-V4-Pro-0813
| |||||||||||||||||||
| Wandb | $1.31 | $3.96 | 1 | ||||||||||||||||
Standardwandb/deepseek-ai/DeepSeek-V4-Pro-0813
| |||||||||||||||||||
| Databricks | $1.32 | $3.96 | 1 | ||||||||||||||||
Standarddatabricks/databricks-deepseek-v4-pro-0813
| |||||||||||||||||||
| Baseten | $1.32 | $3.96 | 1 | ||||||||||||||||
Standardbaseten/deepseek-ai/DeepSeek-V4-Pro-0813
| |||||||||||||||||||
| Fireworks AI | $1.32 | $3.96 | 1 | ||||||||||||||||
Standardfireworks_ai/accounts/fireworks/models/deepseek-v4-pro-0813
| |||||||||||||||||||
| Baseten is dearest at $1.32 / $3.96 | |||||||||||||||||||
Price history
listed seller prices, input and output per 1M tokens Input Output
Input down 30% since first tracked
Cost calculator
estimate your monthly spend on this model$290
estimated / month
Model IDs
copy the exact identifier for your platformdeepseek/deepseek-v4-pro-0813deepseek/deepseek-v4-pro-0813:batchdeepseek/deepseek-v4-pro-0813sail/deepseek-ai/DeepSeek-V4-Pro-0813deepinfra/deepseek-ai/DeepSeek-V4-Pro-0813wandb/deepseek-ai/DeepSeek-V4-Pro-0813databricks/databricks-deepseek-v4-pro-0813tencent/deepseek-v4-pro-0813fireworks_ai/accounts/fireworks/models/deepseek-v4-pro-0813together_ai/deepseek-ai/DeepSeek-V4-Pro-0813novita/deepseek/deepseek-v4-pro-0813nebius/deepseek-ai/DeepSeek-V4-Pro-0813baseten/deepseek-ai/DeepSeek-V4-Pro-0813
Frequently asked questions
DeepSeek V4 Pro 0813 pricing, context and availabilityIs DeepSeek V4 Pro 0813 still available?
DeepSeek V4 Pro 0813 was deprecated on 2026-09-25, but 12 serving providers still list it.
How much does DeepSeek V4 Pro 0813 cost?
DeepSeek V4 Pro 0813 costs $0.66 per 1M input tokens as an OpenRouter routed quote, and $1.98 per 1M output tokens as an OpenRouter routed quote. An OpenRouter routed quote is the price of whichever upstream provider OpenRouter prefers today, so it moves day to day. Across 12 serving providers, input prices range from $0.66 to $1.32 per 1M tokens.
What is the context window of DeepSeek V4 Pro 0813?
DeepSeek V4 Pro 0813 accepts up to 1M tokens of context and can return up to 1M output tokens.
Which providers serve DeepSeek V4 Pro 0813?
DeepSeek V4 Pro 0813 is available from 12 serving providers, each with its own pricing and model ID. OpenRouter is currently the cheapest, as a routed quote.
What can DeepSeek V4 Pro 0813 do?
DeepSeek V4 Pro 0813 supports tool use, reasoning, prompt caching and structured output.
Other DeepSeek models
compare pricing across the DeepSeek lineupDeepSeek V4 Flash 0423$0.09/1M · 18 providersDeepSeek V4 Flash 0731$0.016/1M · 16 providersDeepSeek V4 Pro 0423$0.435/1M · 16 providersR1$0.40/1M · 14 providersDeepSeek V4.1 Flash$0.01/1M · 12 providersDeepSeek V3 0324$0.20/1M · 12 providersDeepSeek R1 Distill Llama 70B$0.20/1M · 11 providersDeepSeek V3.1$0.25/1M · 11 providers
Listed prices from LiteLLM, OpenRouter and Vercel · last checked Oct 14, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI