Experiential
ModelsObservability
Star us on GitHubJoin the DiscordDocs
Sign in
Continue with GoogleContinue with GitHub
or
Models

DeepSeek V4 Pro 0813

deepseek-v4-pro-0813by DeepSeek
Try in Chat

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

Context

1.05M

Max output

393K

Price per million tokens

$1.19in$0.097cached$3.56out

Speed

60 tok/s

-5%

Released

Aug 2026

Waterfall

  1. 1
    OpenRouter$1.19/$3.5699.6% up60 tok/s900ms

Quickstart

I want you to route my LLM calls for "deepseek-v4-pro-0813" through the Experiential gateway instead of calling the provider directly. It speaks the OpenAI Chat Completions API, so this is a base-URL and key swap. Please:

1. Point the client at https://api.experientiallabs.jp/v1 as the base URL.
2. Securely ask me for my API key. Authenticate with my Experiential key from EXPLABS_API_KEY. I can create one under Settings -> API Keys.
3. Use the model id "deepseek-v4-pro-0813" exactly.
4. Update every place my code builds an LLM client for this model to use that base URL and key, leaving streaming and tool-calls as they are.
5. Make one test call and show me the reply plus the token usage, so we confirm it runs on my Experiential credits.

Tell me which files you changed.
CapabilitiesAccepts text

Sampling

Temperature0-2Top-p0-1Top-kStop sequencesLogprobs

Tools & structure

ToolsStructured output

Reasoning

Reasoningnone · low · high · maxDefaulthigh

Streaming

Streaming

Limits

Max output943,718Max-tokens fieldmax_tokens

Sending an unsupported field? See error referenceOpenRouter docs

Benchmarks5
BenchmarkScoreSource
SWE-bench Verifiedpublic leaderboard · Aug 202696.4%public leaderboard · Aug 2026
LiveBenchpublic leaderboard · Aug 202677.4%public leaderboard · Aug 2026
Humanity's Last ExamHugging Face · Aug 202642.7%Hugging Face · Aug 2026
LMArena EloLMArena · Aug 20261439LMArena · Aug 2026
Terminal-BenchHugging Face · Aug 202687.9Hugging Face · Aug 2026
Providers serving this model4
Status
OpenRouterexperiential60 tok/s900ms99.6%#1 / 11.05M393K$1.19$3.56cache$0.097-no dataactiveestimated
Fireworksno datano data99.9%-1.05M393K$1.32$3.96cache$0.044-ZDRdisabledestimated
Azure Foundryno datano data99.9%-1.05M393Kno datano datano data-no datadisabled-
TTencent Cloud via Experiential Cloudno datano data99.9%-1.05M393K$1.19$3.56cache$0.097-no datadisabled-
Hugging Face