DeepSeek

DeepSeek V4 Flash Latest

~deepseek/deepseek-v4-flash-latest

JSON

Specification

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

DeepSeek V4 Flash Latest

reasoning tools

DeepSeek ~deepseek/deepseek-v4-flash-latest

This model always redirects to the latest model in the DeepSeek V4 Flash family.

Input $/1M: $0.04
Output $/1M: $0.09
Context: 1.3M
Max output: 944K
Released: Aug 1, 2026
Modalities: text

Cached input reads $0.009 per 1M

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 Latest
targets:
  - id: deepseek-v4-flash-latest
    kind: llm
    name: DeepSeek V4 Flash Latest
    metadata:
      model: ~deepseek/deepseek-v4-flash-latest          # links the target to this catalogue entry
    capabilities:
      domains: [general]
      supports_tools: true
      context_window: 1310720
    cost:
      usd_per_1k_tokens: 0.000068

Price among DeepSeek models

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

More from DeepSeek

Other models by the same vendor in the catalogue.