DeepSeek route

deepseek-v4-pro-0813

DeepSeek V4 Pro 0813 API pricing.

One OpenAI-compatible route at the vendor list price with 0% markup, billed per token from one prepaid balance. No subscription required.

Route status Available

#38

Cost rank / 82

mid-range

Cost band

Published route economicsUSD / 1M tokens

Input / 1M tokens

$0.80

Output / 1M tokens

$2.39

Cached input / 1M tokens

$0.21

Context window

1M

Provider

DeepSeek

Dated 2026-08-13 build of DeepSeek V4 Pro, billed exactly like deepseek-v4-pro: the time-weighted average of DeepSeek's off-peak and peak rates.

Workload calculator

Put the token rate into context.

These examples apply the published input and output rates directly. Actual cost follows the exact tokens your client sends and the model returns.

This route is the 38th cheapest of 82 comparable text models and cheaper than 43 on the same key. Its context window ranks 40th of 82.

Cost simulationPublished base rate

Short request

$0.010

10K input + 1K output

Agent turn

$0.10

100K input + 10K output

Exact token billing

No request minimum

One model ID change

OpenAI compatible

Cost neighbourhood

Nearby routes, same workload.

Every comparison uses the same 100K-input / 10K-output turn. Changing route is a one-line model ID edit.

Price does not measure task quality.

First request

Route it in one call.

Use any OpenAI SDK or tool. Keep the request shape, point the base URL at RouterPlex, and set the model ID shown here.

Read the quickstart
curl /chat/completions
curl https://api.routerplex.com/v1/chat/completions \
-H "Authorization: Bearer $ROUTERPLEX_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4-pro-0813",
"messages": [{"role": "user", "content": "Hello!"}]
}'

Route notes

Questions before production traffic.

Same endpoint, every route
01How much does the DeepSeek V4 Pro 0813 API cost?+

Through RouterPlex, DeepSeek V4 Pro 0813 costs $0.80 per 1M input tokens and $2.39 per 1M output tokens — the vendor list price with 0% markup, billed per token from a prepaid balance you top up from $5. Cached input tokens are billed at $0.21 per 1M instead of the full input rate, which is most of the prompt on a repeated agent or coding loop. Dated 2026-08-13 build of DeepSeek V4 Pro, billed exactly like deepseek-v4-pro: the time-weighted average of DeepSeek's off-peak and peak rates.

02What does one DeepSeek V4 Pro 0813 agent turn cost?+

A 100K-token input with a 10K-token reply costs about $0.10 on DeepSeek V4 Pro 0813. That makes it the 38th cheapest of 82 comparable text models on RouterPlex, roughly 8.7× the cost of the cheapest option (Muse Spark 1.2 Contributor).

03What is a cheaper alternative to DeepSeek V4 Pro 0813?+

Doubao Seed 2.0 Pro from ByteDance is the closest cheaper model on RouterPlex — $0.10 per agent turn against $0.10 for DeepSeek V4 Pro 0813, at $0.67/1M input and $3.36/1M output. Both run on the same key and the same endpoint, so switching is a one-line model ID change.

04Is DeepSeek V4 Pro 0813 cheaper than Hy4 Preview?+

Yes. Per agent turn, DeepSeek V4 Pro 0813 costs about $0.10 against $0.11 for Hy4 Preview — 4% less.

05What is the context window of DeepSeek V4 Pro 0813?+

DeepSeek V4 Pro 0813 supports a 1M token context window on RouterPlex, the 40th largest of the 82 models that publish one.

06Can I use DeepSeek V4 Pro 0813 with the OpenAI SDK?+

Yes. RouterPlex serves DeepSeek V4 Pro 0813 through an OpenAI-compatible endpoint at https://api.routerplex.com/v1 — point any OpenAI SDK or tool at that base URL with your RouterPlex key and set model to "deepseek-v4-pro-0813".

Deploy this route

Put DeepSeek V4 Pro 0813 behind one key.

Top up from $5 with no subscription required.