API pricing per million tokens
- Input
- $0.66
- per 1M, list
- Output
- $1.98
- per 1M tokens
- Cached input
- $0.022
- no batch tier listed
- Context
- 1M
- 384K max output
Price history
List price since Sep 23, 2026, from daily reads of the OpenRouter catalog.
| Seen | Model | Old price | New price | Change |
|---|---|---|---|---|
| Sep 24, 2026 |  DeepSeek V4 Pro 0813Input $0.66 to $1.32, Output $1.98 to $3.96, Cached input $0.022 to $0.044 | Input $0.66Output $1.98Cached input $0.022 | Input $1.32Output $3.96Cached input $0.044 | +100% |
| Sep 24, 2026 | DeepSeek V4 Pro 0813Input $0.4 to $1.32, Output $1.2 to $3.96, Cached input $0.013 to $0.042 on baidu/fp8on baidu/fp8 | Input $0.4Output $1.2Cached input $0.013 | Input $1.32Output $3.96Cached input $0.042 | +230% |
| Sep 24, 2026 | DeepSeek V4 Pro 0813Input $0.581 to $1.12, Output $1.74 to $3.37, Cached input $0.058 to $0.112 on qwenon qwen | Input $0.581Output $1.74Cached input $0.058 | Input $1.12Output $3.37Cached input $0.112 | +93% |
| Sep 24, 2026 | DeepSeek V4 Pro 0813Input $0.395 to $0.387 on waferon wafer | Input $0.395 | Input $0.387 | -2% |
Through a gateway
Your own numbers100M input and 20M output tokens a month: $105.60 direct.
Helicone$105.60+0%
Kong AI Gateway$105.60+0%
LiteLLM$105.60+0%
Vercel AI Gateway$105.60+0%
AWS Bedrock$105.60+0%
Azure AI Foundry$105.60+0%
Google Vertex AI$105.60+0%
Databricks Mosaic AI$105.60+0%
Hugging Face Inference$105.60+0%
Cloudflare AI Gateway$110.88+5%
Requesty$110.88+5%
Eden AI$111.41+5.5%
OpenRouter$111.41+5.5%
Snowflake Cortex AI$126.72+20%
Martian Gatewayn/a
Portkeyn/a
TrueFoundry AI Gatewayn/a
IBM watsonx.ain/a
OCI Generative AIn/a
NVIDIA NIMn/a
Related models
Muse Spark 1.3Meta · 1M$1.25 / $4.25in / out per 1M$1.25$4.25$0.151MSep 2, 2026
Gemini 3.8 FlashGoogle Gemini API · 1M$0.75 / $3.75in / out per 1M$0.75$3.75$0.0751MSep 2, 2026
GLM 5.3Z.ai · via DeepInfra (fp4) · 1.31M$0.563 / $2.5in / out per 1M$0.563$2.5$0.1251.31MAug 18, 2026
About DeepSeek V4 Pro 0813
DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek.
Takes text in and returns text. First listed Sep 23, 2026. Blended price $0.99 per 1M tokens at 3 input to 1 output.
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 384K tokens of output.
Where is DeepSeek V4 Pro 0813 cheapest?
Of 23 routes tracked, StreamLake is cheapest at $0.462 input and $1.39 output per million tokens.
Has DeepSeek V4 Pro 0813's price changed?
Yes. The output price went from $1.98 to $3.96, first seen Sep 24, 2026.
List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.