ModelRushText

DeepSeek V4.1 Flash API

DeepSeek V4.1 Flash generates text from chat messages through the ModelRush API and returns generated text. Requests run synchronously and can stream tokens. It is callable in 4 execution regions, from $0.33 per 1M input tokens.
Multimodal understandingTool callingOpenAI-compatible Chat Completions
Starting at
$0.33/ 1M tokens
Try it in the PlaygroundLet an agent integrate this model

Input

sync-or-stream
Estimated run$0.33

Output preview

This is a model capability preview. Sign in to submit a live request and inspect the generated result here.
token5s

Model information

Model ID
modelrush/deepseek-v4.1-flash
Integration status
Inputs
Text and images · up to 1,000,000 input tokens · 4,000,000 UTF-8 byte gateway maximum
Output
Text · up to 393,216 tokens
Billing unit
Per 1M tokens
Execution mode
Synchronous, with optional token streaming.
Available regions
Europe — FrankfurtJapan — TokyoSingaporeUS — Virginia
Last updated
Oct 15, 2026

Capabilities and limits

Context window
1,000,000 tokens
Max output
393,216 tokens

Best for

Agent workflowsImage understandingLong-document reasoning

Current customer pricing

For each Operation and price variant, the highest regional customer price is shown.
ModelCapabilityPrice variantCustomer price
DeepSeek V4.1 Flash · modelrush/deepseek-v4.1-flashChat completionsStandardInput $0.33 · Output $1.32 / 1M tokens

Pricing and documentation

DeepSeek V4.1 Flash API pricingChat completions API documentation

Related guides

One API, Many Models: Designing a Production-Ready ArchitectureMigrating to an OpenAI-Compatible API: What to Check Before the Base URL

Other recommended models

LLM

GLM 5.3

Flagship million-token reasoning for complex agents
Starting price
$1.40/ 1M tokens
LLM

Grok 4.5

Current ModelRush gateway model · released in 2 regions
Starting pricePricing pending
LLM
New

Papaya 1.0

Affordable text chat for everyday writing
Starting pricePricing pending