deepseek logo
deepseek

DeepSeek: DeepSeek V4 Flash 0731 (batch)

Source description (English)

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....

Overview

Model specifications

Context
1,048,576 tokens
Maximum output
384,000 tokens
Architecture
text->text
Tokenizer
DeepSeek
Knowledge cutoff
Not provided
Moderated
No
OPENROUTER

Complete pricing

Synchronized OpenRouter rates. Token prices are shown per one million tokens.

Input
$0.048
per 1M tokens
Output
$0.144
per 1M tokens
Cache read
$0.012
per 1M tokens
API

Model configuration

Reasoning

Reasoning required
No
Default parameters
high
Capabilities
max, high, low, none
API

Quick start

Set OPENROUTER_API_KEY locally. Python requires requests; JavaScript runs in Node.js. Keep the key on the server.

This submits an asynchronous batch using the base model ID. A job ID confirms submission, not completion.

API documentation

curl --fail-with-body https://openrouter.ai/api/beta/batches \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"endpoint":"/v1/chat/completions","model":"deepseek/deepseek-v4-flash-0731","requests":[{"custom_id":"request-1","body":{"messages":[{"role":"user","content":"Hello!"}]}}]}'

# Replace JOB_ID with the returned id to check progress.
curl --fail-with-body "https://openrouter.ai/api/beta/batches/JOB_ID" \
  -H "Authorization: Bearer $OPENROUTER_API_KEY"
Capabilities

Input → Output

Input
text
Output
text
Reasoning

Yes · max · high · low · none

API

Supported API parameters

frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Available providers

1 Provider

Checked: November 7, 2026

Live providers on OpenRouter

Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.

OpenRouter

DeepInfra

fp8
Context
1.0M
Maximum output
384K
Input
$0.048
Output
$0.144
Cache read
$0.012
Cache write
Not provided
deepseek

4 models

All models