DeepSeek

DeepSeek V4 Pro 0813

deepseek/deepseek-v4-pro-0813

JSON

Specification

Published by the vendor; the platform bills at the target's declared price.

DeepSeek V4 Pro 0813

reasoning open weights tools

DeepSeek deepseek/deepseek-v4-pro-0813

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

Input $/1M: $1.12
Output $/1M: $3.36
Context: 1.0M
Max output: 384K
Released: Aug 12, 2026
Modalities: text

Intelligence index42

Coding index69

Agentic index43

Cached input reads $0.04 per 1M · weights on Hugging Face as deepseek-ai/DeepSeek-V4-Pro-0813

On this deployment

No routing target resolves to this model yet. Declare one and the router picks it up without retraining.

Not routable here yet

Add a target with metadata.model set to this id.

targets.yamlyaml

# targets.yaml - declare a target that runs DeepSeek V4 Pro 0813
targets:
  - id: deepseek-v4-pro-0813
    kind: llm
    name: DeepSeek V4 Pro 0813
    metadata:
      model: deepseek/deepseek-v4-pro-0813          # links the target to this catalogue entry
    capabilities:
      domains: [general]
      supports_tools: true
      context_window: 1048576
    cost:
      usd_per_1k_tokens: 0.002241

Price among DeepSeek models

Input list price per million tokens; DeepSeek V4 Pro 0813 is the 12th cheapest of 13 listed.

More from DeepSeek

Other models by the same vendor in the catalogue.