Skip to content
  • Models
  • Rankings
  • Ori
Sign Up
Sign Up
OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Collections
  • Providers
  • Pricing
  • Business
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Trust Center
  • Support
  • Works With OR
  • Data
  • Brand

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon for deepseek

DeepSeek: DeepSeek V4.1 Flash

deepseek/deepseek-v4.1-flash

Model weights
Compare

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on output from a 552B-parameter backbone, an asymmetric split that keeps per-token compute low relative to the model's total size. Image understanding is native to the architecture, with visual and text embeddings trained jointly from the start of pre-training rather than added afterward as in the earlier experimental V4 Flash Vision Exp(opens in new tab).

It is suited for coding, terminal, and computer-use agents, along with long-horizon tasks that must run to completion across many steps and long-context analysis. Compressed KV caching cuts cache memory to roughly a quarter of the previous Flash generation, significantly reducing costs on agentic workloads. DeepSeek positions it as the cost-efficient tier of the V4.1 family and reports that it exceeds V4 Pro(opens in new tab) on performance, speed, and task completion time.

Modalities

In / Out Price

$0.15 / $0.60per 1M

Context

1.0M

Released

Sep 10, 2026

Compare
ProvidersPricingPerformanceUptimeBenchmarksAppsActivityFAQExplore

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick — Balanced (price + speed), Nitro (fastest), or Exacto (highest tool-calling accuracy).

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Benchmarks

Scores on standardized evaluations. Higher percentages are better — and rank percentile shows where this model lands among all models on OpenRouter.

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Activity

Token volume and request traffic to this model over time.

Quick Start

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

Explore more models

AI Models with Vision: Multimodal LLMs for Image UnderstandingCollectionAI Model RankingsRanking
$0.15$0.60$0.0031.08s107 tps
99.98%
$0.30$1.20$0.0061.08s87 tps
99.98%
$0.30$1.20$0.031.06s60 tps
95.88%
$0.30$1.20$0.010.57s27 tps
51.83%
$0.30$1.20$0.0062.92s75 tps
99.85%
$0.30$1.20$0.0061.70s99 tps
99.99%
$0.375$1.50$0.00751.69s51 tps
92.17%
$0.20$0.60$0.0065.21s14 tps
94.28%
$0.22$0.66$0.0071.12s93 tps
98.97%
$0.30$1.20$0.032.19s6 tps
91.64%
$0.30$1.20$0.0035.03s3 tps
90.93%

Throughput

107tok/s

P50, best across providers

Latency

0.57s

P50, best provider

AutoExacto Benchmarks
GPQA DiamondTAU-Bench
SiliconFlow
91.2%--
NovitaAI
91.1%76.7%
GMICloud
91.2%73.3%
Uptime (3d)The model was reachable. Request routed to a provider.

100.00%

Availability (3d)The model returned inference from any provider. Errors and empty responses count against it.

99.85%

Availability over the last 3 days

Last 72 hours
Availability 99.85%
3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability
99.86%
Without Routing
90.37%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and customization options.

1.
Favicon for https://nousresearch.com
Hermes Agent
Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.
183Btokens
2.
Favicon for https://pi.dev/
pi
There are many coding agents, but this one is yours.
102Btokens
3.
Favicon for https://omp.sh/
omp
new
90.7Btokens
4.
Favicon for https://github.com/deepseek-ai/deepseek-harness
DeepSeek Harness
new
82.7Btokens
5.
Favicon for https://claude.ai/apple-touch-icon.png
Claude Code
Claude Code is Anthropic's agentic coding tool that reads your entire codebase, plans and executes changes across files, runs tests, and iterates on failures, all from natural language prompts.
67.9Btokens

Frequently asked questions

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on output from a 552B-parameter backbone, an asymmetric split that keeps per-token compute low relative to the model's total size.

DeepSeek V4.1 Flash costs $0.15/M input tokens and $0.60/M output tokens, with separate rates for Cache Read at $0.003/M tokens.

DeepSeek V4.1 Flash has a 1,048,576 token context window. It supports up to 384,000 completion tokens.

Yes. DeepSeek V4.1 Flash accepts tools and tool_choice for function calling. It supports response_format for JSON output, without JSON-schema enforcement.

DeepSeek V4.1 Flash accepts text and images as input and returns text.

DeepSeek V4.1 Flash is served by 10 providers on OpenRouter: DeepSeek, DeepInfra, Fireworks, SiliconFlow, Modal, GMICloud, Morph, io.net and 2 more. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

DeepSeek V4.1 Flash was released on September 10, 2026.