oxyy.ai
HomeModelsProvidersPricingBlogDocs
Sign inGet API key
  1. Home/
  2. Providers/
  3. DeepSeek/
  4. DeepSeek-V4.1-Flash

DeepSeek: DeepSeek-V4.1-Flash

deepseek/deepseek-flash
Compare Playground Get API key
The smallest model in DeepSeek's new architecture family, with native multimodal visual understanding. Designed for a higher capability ceiling, faster inference, higher throughput, and scaling to larger models.
ModalitiesTextImageText
In / out price$0.060 / $0.240 per 1M
Context1M
ReleasedSep 10, 2026
ProvidersPricingPerformanceAvailabilityAppsActivityFAQExplore

Providers

Where this model runs, and what each route costs. Requests are sent to a healthy provider automatically; if one errors, the gateway retries against another serving the same model.

ProviderInput /MOutput /MCache read /MLatencyThroughput
DeepSeek$0.060$0.240$0.003——

Capabilities (14)

StreamingTool callingStructured outputJson ModeThinkingReasoningSystem promptVisionPrompt cachingResponses ApiAnthropic ApiChat Prefix CompletionFim CompletionFiles API

Supported parameters (5)

streamtoolsresponse_formatthinkingreasoning_effort

Any other parameter you send is ignored rather than rejected.

Pricing

What this model costs to run, next to the rate it is posted at. Caching and discounts mean the price actually paid is often below the listed one.

Effective input price
$0.060
/M tokens · listed $0.150
Effective output price
$0.240
/M tokens · listed $0.600
RateListedChargedUnit
Input$0.150$0.060per 1M tokens
Output$0.600$0.240per 1M tokens
Cache read$0.003$0.003per 1M tokens
UTC

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). Throughput and TTFT are measured on streaming requests, which are the only ones with a first-token moment to time.

Throughput
—tok/s
P50, streaming requests
Latency
—s
P50, end to end
UTC
No requests to this model in the selected window, so there is nothing to measure yet.

Availability

The share of requests to this model that completed successfully. When an upstream provider errors, the gateway retries against another provider serving the same model, so a single provider incident does not necessarily show up here.

Success rate (30d)
0.00%
over 273 requests
Days with traffic
4
of the last 30

Days are UTC days. Days with no requests are omitted rather than drawn at 100% — no traffic is not evidence of availability.

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.

  1. 1.Z Code@electron 28.0K tokens
  2. 2.Oxyy Tester112 tokens

Activity

Token volume and request traffic to this model over time. Daily totals, UTC.

Prompt58.8K
Completion0

Prompt tokens measure input size. Reasoning tokens show internal thinking before a response. Completion tokens reflect total output length. Reasoning is not priced separately for this model, so it is not itemised here.

Frequently asked questions

What is DeepSeek-V4.1-Flash?
The smallest model in DeepSeek's new architecture family, with native multimodal visual understanding. Designed for a higher capability ceiling, faster inference, higher throughput, and scaling to larger models.
How much does DeepSeek-V4.1-Flash cost?
DeepSeek-V4.1-Flash costs $0.150 per million input tokens and $0.600 per million output tokens. Cached prompt tokens are billed at $0.003 per million. You pay per request, with no subscription.
What is the context length of DeepSeek-V4.1-Flash?
DeepSeek-V4.1-Flash has a context window of 1,000,000 tokens, and can return up to 384,000 tokens in one response.
Does DeepSeek-V4.1-Flash support tool calling and structured outputs?
Yes — DeepSeek-V4.1-Flash supports both tool calling and structured outputs.
What inputs and outputs does DeepSeek-V4.1-Flash support?
DeepSeek-V4.1-Flash accepts text, image as input and returns text.
What other models does DeepSeek have?
DeepSeek also offers DeepSeek-V4-Pro-0813 through Oxyy.
When was DeepSeek-V4.1-Flash released?
DeepSeek-V4.1-Flash was released on Sep 10, 2026.

Explore more models

Browse the full catalog ModelsCompare pricing Pricing

More models from DeepSeek

DeepSeek-V4-Pro-0813DeepSeek's flagship model, with a 1M-token context window and both thinking and non-thinking modes. Text only.text · 1M context · $0.660 / $1.98
oxyy.ai

One endpoint for every major model. The OpenAI, Anthropic and Gemini SDKs work unchanged.

Product

  • Models
  • Providers
  • Pricing
  • Status
  • Startup program

Company

  • About
  • Blog
  • Contact
  • Terms of Service
  • Privacy Policy
  • Refund Policy
  • Cookie Policy

Developer

  • Documentation
  • Quickstart
  • SDKs
  • Model catalog
  • AI providers

Connect

  • Telegram
  • Discord
  • WhatsApp
© 2026 Oxyy.ai. All rights reserved.StatusAbout