DeepSeek

DeepSeek V4 Flash 0731 (batch)

deepseek/deepseek-v4-flash-0731:batch

JSON

Specification

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

DeepSeek V4 Flash 0731 (batch)

reasoning open weights tools

DeepSeek deepseek/deepseek-v4-flash-0731:batch

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: $0.14
Output $/1M: $0.28
Context: 1.0M
Max output: 944K
Released: Jul 31, 2026
Modalities: text

Intelligence index41

Coding index69

Agentic index42

Cached input reads $0.03 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 (batch)
targets:
  - id: deepseek-v4-flash-0731-batch
    kind: llm
    name: DeepSeek V4 Flash 0731 (batch)
    metadata:
      model: deepseek/deepseek-v4-flash-0731:batch          # links the target to this catalogue entry
    capabilities:
      domains: [general]
      supports_tools: true
      context_window: 1048576
    cost:
      usd_per_1k_tokens: 0.000210

Price among DeepSeek models

Input list price per million tokens; DeepSeek V4 Flash 0731 (batch) is the 3rd cheapest of 13 listed.

1
DeepSeek V4 Flash Latest
$0.04
2
DeepSeek V4 Flash 0423
$0.09
3
DeepSeek V4 Flash 0731 (batch)
$0.14
4
DeepSeek V4 Flash 0731
$0.14
5
DeepSeek V3.2
$0.27
6
DeepSeek V3.2 Exp
$0.27
7
DeepSeek V3.1 Terminus
$0.27
8
DeepSeek V4 Flash Vision Exp
$0.44
9
R1 0528
$0.50
10
DeepSeek V3.1
$0.55
11
DeepSeek V4 Pro 0423
$1.04
12
DeepSeek V4 Pro 0813
$1.12

More from DeepSeek

Other models by the same vendor in the catalogue.