Pricingby GlyphDeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek.
Ways to buy 25
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
The lab's own API · cached $0.022 | $0.66 | $1.98 | $0.66 / $1.98List price | $0.022 | List price |
| Relace fp4 · cached $0.227 | $0.227 | $3.78 | $0.227 / $3.78+13% vs list | $0.227 | +13% vs list |
| Wafer us, mxfp4 · cached $0.11 | $0.115 | $4.6 | $0.115 / $4.6+25% vs list | $0.11 | +25% vs list |
| Wafer mxfp4 · cached $0.284 | $0.285 | $4.3 | $0.285 / $4.3+30% vs list | $0.284 | +30% vs list |
| Sail Research fp4 · cached $0.195 | $1.35 | $2.4 | $1.35 / $2.4+63% vs list | $0.195 | +63% vs list |
| Sail Research us, fp4 · cached $0.195 | $1.35 | $2.4 | $1.35 / $2.4+63% vs list | $0.195 | +63% vs list |
fp8 · cached $0.1 | $1.3 | $2.6 | $1.3 / $2.6+64% vs list | $0.1 | +64% vs list |
Default region · cached $0.112 | $1.12 | $3.37 | $1.12 / $3.37+70% vs list | $0.112 | +70% vs list |
fp8 · cached $0.044 | $1.31 | $3.96 | $1.31 / $3.96+99% vs list | $0.044 | +99% vs list |
| AtlasCloud fp8 · cached $0.132 | $1.32 | $3.96 | $1.32 / $3.96+100% vs list | $0.132 | +100% vs list |
| Baidu fp8 · cached $0.042 | $1.32 | $3.96 | $1.32 / $3.96+100% vs list | $0.042 | +100% vs list |
fp4 · cached $0.132 | $1.32 | $3.96 | $1.32 / $3.96+100% vs list | $0.132 | +100% vs list |
Default region · cached $0.044 | $1.32 | $3.96 | $1.32 / $3.96+100% vs list | $0.044 | +100% vs list |
Default region · cached $0.044 | $1.32 | $3.96 | $1.32 / $3.96+100% vs list | $0.044 | +100% vs list |
| GMICloud fp8 · cached $0.044 | $1.32 | $3.96 | $1.32 / $3.96+100% vs list | $0.044 | +100% vs list |
fp8 · cached $0.04 | $1.32 | $3.96 | $1.32 / $3.96+100% vs list | $0.04 | +100% vs list |
fp8 · cached $0.044 | $1.32 | $3.96 | $1.32 / $3.96+100% vs list | $0.044 | +100% vs list |
fp8 · cached $0.044 | $1.32 | $3.96 | $1.32 / $3.96+100% vs list | $0.044 | +100% vs list |
us-east-1 · cached $0.132 | $1.32 | $3.96 | $1.32 / $3.96+100% vs list | $0.132 | +100% vs list |
fp8 · cached $0.044 | $1.32 | $3.96 | $1.32 / $3.96+100% vs list | $0.044 | +100% vs list |
| StreamLake Default region · cached $0.044 | $1.32 | $3.96 | $1.32 / $3.96+100% vs list | $0.044 | +100% vs list |
Default region · cached $0.13 | $1.32 | $3.96 | $1.32 / $3.96+100% vs list | $0.13 | +100% vs list |
| Phala Default region · cached $0.15 | $1.45 | $4.36 | $1.45 / $4.36+120% vs list | $0.15 | +120% vs list |
Default region · cached $0.165 | $1.65 | $4.95 | $1.65 / $4.95+150% vs list | $0.165 | +150% vs list |
fast, fp8 · cached $0.066 | $1.98 | $5.94 | $1.98 / $5.94+200% vs list | $0.066 | +200% vs list |
USD per 1M tokens. Regions are separate routes.
Through a gateway
Your own numbers100M input and 20M output tokens a month: $105.60 direct.
Kong AI Gateway$105.60+0%
LiteLLM$105.60+0%
Vercel AI Gateway$105.60+0%
Requesty$110.88+5%
Eden AI$111.41+5.5%
OpenRouter$111.41+5.5%
Cloudflare AI GatewayNot offeredNot offered
HeliconeNot offeredNot offered
Neon AI GatewayNot offeredNot offered
TrueFoundry AI GatewayNot offeredNot offered
A dash: not on that gateway's own model list. No published token fee: Martian Gateway, Portkey.
Related models
| In / out per 1M | Cheapest route | |||||||
|---|---|---|---|---|---|---|---|---|
DeepSeek · 1MCheapest: $0.081 on Particle AI (us-flex) | $0.15 | $0.6 | $0.15 / $0.6 | $0.262 | 1M | $0.081 on Particle AI (us-flex) | · | DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name. |
DeepSeek · 1M | $0.045 | $0.3 | $0.045 / $0.3 | $0.109 | 1M | on InferenceNet (fp8) | · | DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. |
DeepSeek · 1M | $0.44 | $1.32 | $0.44 / $1.32 | $0.66 | 1M | on DeepInfra (fp8) | · | DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of DeepSeek V4 Flash 0731 from DeepSeek, adding image understanding while matching the base model on text capabi |
DeepSeek · 1M | $0.019 | $0.3 | $0.019 / $0.3 | $0.089 | 1M | on Sail Research (us) | · | DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. |
OpenAI · 1.05MCheapest: $1 on OpenAI (flex) | $1 | $5 | $1 / $5 | $2 | 1.05M | $1 on OpenAI (flex) | · | GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. |
Google · 1MCheapest: $0.75 on Google Gemini API (flex) | $0.75 | $3.75 | $0.75 / $3.75 | $1.5 | 1M | $0.75 on Google Gemini API (flex) | · | Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning. |
Meta · 1M | $1.25 | $4.25 | $1.25 / $4.25 | $2 | 1M | Lab list price | · | Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. |
Google · 1MCheapest: $0.75 on Google Vertex AI (global-flex) | $0.75 | $3.75 | $0.75 / $3.75 | $1.5 | 1M | $0.75 on Google Vertex AI (global-flex) | · | Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. |
About DeepSeek V4 Pro 0813
Takes text in and returns text. First listed Sep 23, 2026. Up to 944K output tokens. Blended price $0.99 per 1M tokens at 3 input to 1 output. Model id deepseek-v4-pro-0813.
Price history
List price since Sep 23, 2026, from daily reads of the OpenRouter catalog.
DeepSeek V4 Pro 0813
Wafer (us) raised its price: output $4 to $4.6 per 1M tokens.
Sail Research (fp4) raised its price: input $0.675 to $1.35 and output $1.2 to $2.4 per 1M tokens.
Sail Research (us) raised its price: input $0.675 to $1.35 and output $1.2 to $2.4 per 1M tokens.
Ionstream cut its price: input $0.39 to $0.37 and output $2.88 to $2.93 per 1M tokens.
Wafer (us) cut its price: output $4.3 to $4 per 1M tokens.
Sail Research (fp4) raised its price: input $0.45 to $0.675 and output $0.8 to $1.2 per 1M tokens.
Sail Research (us) raised its price: input $0.45 to $0.675 and output $0.8 to $1.2 per 1M tokens.
Nebius (fp8) set its first price: cached input $0.04 per 1M tokens.
Ionstream cut its price: cached input $0.088 to $0.088 per 1M tokens.
Questions
How much does DeepSeek V4 Pro 0813 cost?
$0.66 per million input tokens and $1.98 per million output tokens, with cached input at $0.022.
What is the context window of DeepSeek V4 Pro 0813?
1M tokens, with up to 944K tokens of output.
Where is DeepSeek V4 Pro 0813 cheapest?
Of 25 routes tracked, DeepSeek is cheapest at $0.66 input and $1.98 output per million tokens.
Has DeepSeek V4 Pro 0813's price changed?
Yes. The output price went from $4 to $4.6, first seen Nov 4, 2026.