Home / Models / DeepSeek / DeepSeek V4.1 Flash

DeepSeek V4.1 Flash pricing and routing profile

DeepSeek V4.1 Flash from DeepSeek lists at $0.0295 per million input tokens and $0.60 per million output tokens, with a 1,048,576-token context window. Prices from OpenRouter's catalogue on 2026-09-28.

Input, per 1M tokens$0.0295

Output, per 1M tokens$0.60

Cached input, per 1M$0.029

Context window1.05M

Confidence signalAvailable

Tool callingStructured outputReasoning controlLog probabilities

Cost per 1,000 requests

Request shape	List cost
Classification or routing (600 tokens in, 10 out)	$0.0237
Chat reply (2,000 in, 400 out)	$0.299
Retrieval-augmented answer (8,000 in, 500 out)	$0.536

Before prompt caching. Try your own shape in the cost calculator.

Can Gimbix route to it first?

Yes. 14 of 27 tracked hosts return token log probabilities for DeepSeek V4.1 Flash, which is the confidence signal Gimbix uses to let a cheaper model answer first.

Measured by Gimbix

On 400 real BANKING77 customer messages, DeepSeek V4.1 Flash answered 316 correctly (95% interval 74.7%–82.7%), with 0 invalid answers, at $0.047 per 1,000 requests and a median of 1,021 ms. See all 22 models.

Who serves DeepSeek V4.1 Flash

Host	Input / output per 1M	Log probabilities	Uptime, last 30 min
Wafer	$0.0295 / $0.60	yes	100.0%
Relace	$0.03 / $0.60	no	100.0%
InferenceNet	$0.035 / $0.29	no	99.8%
Sail Research	$0.08 / $0.40	yes	99.9%
Morph	$0.0805 / $0.31	no	99.8%
OpenInference	$0.10 / $0.50	no	100.0%
DekaLLM	$0.12 / $0.40	yes	99.7%
DeepInfra	$0.14 / $0.42	no	99.9%
StreamLake	$0.178 / $0.714	yes	99.8%
GMICloud	$0.18 / $0.72	yes	100.0%
Novita	$0.195 / $0.78	yes	100.0%
CoreWeave	$0.20 / $0.65	yes	99.7%
NextBit	$0.21 / $0.84	yes	100.0%
Fireworks	$0.22 / $0.66	yes	98.2%
Phala	$0.276 / $1.10	yes	99.7%
AtlasCloud	$0.30 / $1.20	no	97.7%
BaseTen	$0.30 / $1.20	no	100.0%
Makora	$0.30 / $1.20	yes	99.6%
DigitalOcean	$0.30 / $1.20	yes	99.9%
Alibaba	$0.30 / $1.20	no	99.6%
Together	$0.30 / $1.20	yes	99.8%
SiliconFlow	$0.30 / $1.20	no	99.8%
Modal	$0.30 / $1.20	no	99.7%
BaseTen	$0.30 / $1.20	no	99.7%
Parasail	$0.30 / $1.20	no	99.8%
DeepSeek	$0.30 / $1.20	yes	100.0%
Venice	$0.375 / $1.50	no	100.0%

A host that lists log probabilities may still omit them; Gimbix checks each one before relying on it.

Cheaper models that can answer first

Models priced below DeepSeek V4.1 Flash that expose a confidence signal. Whether they answer your traffic as well is what a Gimbix pilot measures.

Model	Input / output per 1M	Cheaper on a chat reply
DeepSeek V4 Flash 0731	$0.021 / $0.32	43%
Granite 4.0 Micro	$0.017 / $0.112	74%
gpt-oss-20b	$0.018 / $0.09	76%
Ling 3.0 Flash	$0.021 / $0.063	78%
Ling 3.0 Flash VL	$0.021 / $0.0616	78%
Mistral Nemo	$0.019 / $0.03	83%

Compare DeepSeek V4.1 Flash

Questions

How much does DeepSeek V4.1 Flash cost?

DeepSeek V4.1 Flash lists at $0.0295 per million input tokens and $0.60 per million output tokens on OpenRouter as of 2026-09-28. A typical chat reply of 2,000 input and 400 output tokens costs about $0.299 per 1,000 requests.

What is the context window of DeepSeek V4.1 Flash?

1,048,576 tokens.

Can a cheaper model replace DeepSeek V4.1 Flash?

Sometimes. Gimbix proves it on your own traffic before routing: the cheaper model must match DeepSeek V4.1 Flash on one half of your requests and make at most three answers worse on the other.