DeepSeek

DeepSeek V4 Flash 0731

deepseek/deepseek-v4-flash-0731

JSON

Specification

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

DeepSeek V4 Flash 0731

reasoning open weights tools

DeepSeek deepseek/deepseek-v4-flash-0731

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....

Input $/1M: $0.05
Output $/1M: $0.10
Context: 1.3M
Max output: 131K
Released: Jul 31, 2026
Modalities: text

Intelligence index41

Coding index69

Agentic index42

Cached input reads $0.010 per 1M · weights on Hugging Face as deepseek-ai/DeepSeek-V4-Flash-0731

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 Flash 0731
targets:
  - id: deepseek-v4-flash-0731
    kind: llm
    name: DeepSeek V4 Flash 0731
    metadata:
      model: deepseek/deepseek-v4-flash-0731          # links the target to this catalogue entry
    capabilities:
      domains: [general]
      supports_tools: true
      context_window: 1310720
    cost:
      usd_per_1k_tokens: 0.000075

Price among DeepSeek models

Input list price per million tokens; DeepSeek V4 Flash 0731 is the 2nd cheapest of 13 listed.

More from DeepSeek

Other models by the same vendor in the catalogue.