DeepSeek: DeepSeek V4.1 Flash

deepseek/deepseek-v4.1-flash
Compare Model Lab

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...

Modalities
Text + Image → Text
Input / Output Price$0.15 / $0.60From · per 1M tokens · see provider prices
Context1.05Mtokens · maximum across providers
ReleasedSep 10, 2026OpenRouter public metadata
Availability & data sources Listed in CLSSAI · 19 reference endpoints
ACCESS

Where this model works

OpenRouter testing and CLSSAI API routing are independent decisions with separate sources.

OpenRouter testTestable with your OpenRouter key
Testable

Exact capability metadata is available. CLSSAI can prepare the Image understanding request without guessing the model contract.

Evidence
Exact ID deepseek/deepseek-v4.1-flash · /chat/completions
Mapped mode
Image understanding
CLSSAI APICallable through CLSSAI API
Callable

The exact model ID is listed in the current CLSSAI public directory. This proves current route eligibility, not a completed inference for every mode.

Evidence
Exact ID deepseek/deepseek-v4.1-flash is directory-listed
Vision test status

The request contract and frontend path are ready. A real OpenRouter output has not yet been recorded for this exact model and mode.

Request contract
Build verified
/chat/completions · Schema tests · 2026-08-05
Frontend path
Available
Vision form · 2026-08-05
Real model output
Not yet verified
No keyed OpenRouter smoke record

Providers

Compare published prices and endpoint capabilities. Select a provider for context limits, caching prices and supported parameters.

19 providers · OpenRouter reference data
$0.15$0.6$0.015----99.90%
$0.15$0.6$0.015----99.33%
$0.15$0.6$0.003----100.00%
$0.18$0.72$0.0054----99.63%
$0.2$0.6$0.006----99.09%
$0.22$0.66$0.007----99.87%
$0.285$1.14$0.0057----99.96%
$0.29$1.16$0.029----91.5%
$0.3$1.2$0.006----95.2%
$0.3$1.2$0.006----97.2%
$0.3$1.2$0.006----99.97%
$0.3$1.2$0.006----100.00%
$0.3$1.2$0.03----99.44%
$0.3$1.2$0.006----99.98%
$0.3$1.2$0.03----100.00%
$0.3$1.2$0.006----98.5%
$0.3$1.2$0.006----99.97%
$0.345$1.38$0.0069----99.86%
$0.375$1.5$0.0075----99.87%

USD per 1M tokens. Prices and metrics describe OpenRouter endpoints, not CLSSAI routing. “--” means no measurement was supplied. Uptime: last 30 minutes.

Pricing

Published base rates across providers, in USD per 1M tokens. Actual cost depends on the provider, caching and prompt length.

Input / 1M tokens$0.15 – $0.375
Output / 1M tokens$0.6 – $1.5
Cache read / 1M tokens$0.003 – $0.03

Effective Pricing: request-weighted costs and historical prices are not supplied by the public source.

Performance

Latency and throughput history are not supplied by the public endpoint API. Check OpenRouter for its latest performance charts.

View on OpenRouter

Uptime

Successful requests in the last 30 minutes, as reported by OpenRouter. A snapshot does not show historical reliability.

Alibaba99.90%
Relace Fp499.33%
DeepSeek100.00%
Morph Fp899.63%
DeepInfra Fp899.09%
Fireworks99.87%
GMICloud Fp899.96%
Reka Fp491.5%
Makora95.2%
DigitalOcean97.2%
Together99.97%
SiliconFlow Fp8100.00%
Modal99.44%
Wafer99.98%
BaseTen Fp8100.00%
Parasail Fp898.5%
Novita Fp899.97%
Phala99.86%
Venice Fp899.87%

Benchmarks

No scored evaluations are included in the public model metadata. View the source for benchmarks and their methodology.

View on OpenRouter

Apps

Application rankings require verified traffic data, which is not included in this source.

View on OpenRouter

Activity

Historical token and request volumes are not supplied by the public API. OpenRouter shows activity on its own network.

View on OpenRouter

Frequently asked questions

Provider availability, context limits and API capabilities.

Which providers serve DeepSeek: DeepSeek V4.1 Flash?

Alibaba, Relace Fp4, DeepSeek, Morph Fp8, DeepInfra Fp8, Fireworks, GMICloud Fp8, Reka Fp4, Makora, DigitalOcean, Together, SiliconFlow Fp8, Modal, Wafer, BaseTen Fp8, Parasail Fp8, Novita Fp8, Phala, Venice Fp8 are listed in the OpenRouter reference data. Check CLSSAI availability above before making a request.

What context length is available for DeepSeek: DeepSeek V4.1 Flash?

The largest available context window is 1,048,576 tokens.

Which API parameters does DeepSeek: DeepSeek V4.1 Flash support?

The providers list 20 distinct supported parameters. Open an endpoint row to inspect them.

Explore

Continue comparing models or start integrating.