Vendor

DeepSeek models

17 models with the vendor's list prices per million tokens. None answers on this deployment yet - connect your own provider to route to them.

Models

0 available here

Cheapest (blended)

$0.07

DeepSeek V4 Flash 0731

Median list price

$0.32

3:1 input to output per 1M tokens

Strongest

DeepSeek V4.1 Flash 1017

intelligence index 40

Every DeepSeek model

Newest first. Prices are the vendor's published rates per million tokens; click a model for the full specification.

Model	Released	Context	Input / 1M	Output / 1M	Intelligence	Capabilities
DeepSeek V4.1 Flash 1017deepseek/deepseek-v4.1-flash-1017	Oct 17, 2026	1.0M	$0.15	$0.60	40	reasoning tools open weights
DeepSeek Pro Latest~deepseek/deepseek-pro-latest	Sep 14, 2026	1.0M	$0.13	$8.00	-	reasoning tools
DeepSeek Flash Latest~deepseek/deepseek-flash-latest	Sep 14, 2026	1.0M	$0.05	$0.38	-	reasoning tools
DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flash	Sep 10, 2026	1.0M	$0.02	$0.38	25	reasoning tools open weights
DeepSeek V4 Flash Vision Expdeepseek/deepseek-v4-flash-vision-exp	Aug 21, 2026	1.0M	$0.22	$0.65	35	reasoning tools open weights
DeepSeek V4 Pro 0813deepseek/deepseek-v4-pro-0813	Aug 12, 2026	1.0M	$0.66	$1.98	36	reasoning tools open weights
DeepSeek V4 Flash Latest~deepseek/deepseek-v4-flash-latest	Aug 1, 2026	1.0M	$0.04	$0.17	-	reasoning tools
DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-0731	Jul 31, 2026	1.0M	$0.04	$0.13	34	reasoning tools open weights
DeepSeek V4 Pro 0423deepseek/deepseek-v4-pro	Apr 24, 2026	1.0M	$0.42	$0.84	30	reasoning tools open weights
DeepSeek V4 Flash 0423deepseek/deepseek-v4-flash	Apr 24, 2026	1.0M	$0.09	$0.18	24	reasoning tools open weights
DeepSeek V3.2deepseek/deepseek-v3.2	Dec 1, 2025	164K	$0.28	$0.42	22	reasoning tools open weights
DeepSeek V3.2 Expdeepseek/deepseek-v3.2-exp	Sep 29, 2025	164K	$0.27	$0.41	17	reasoning tools open weights
DeepSeek V3.1 Terminusdeepseek/deepseek-v3.1-terminus	Sep 22, 2025	164K	$0.27	$1.00	15	reasoning tools open weights
DeepSeek V3.1deepseek/deepseek-chat-v3.1	Aug 21, 2025	164K	$0.25	$0.95	14	reasoning tools open weights
R1 0528deepseek/deepseek-r1-0528	May 28, 2025	164K	$0.50	$2.15	13	reasoning tools open weights
DeepSeek V3 0324deepseek/deepseek-chat-v3-0324	Mar 24, 2025	164K	$0.29	$1.14	10	tools open weights
DeepSeek V3deepseek/deepseek-chat	Dec 26, 2024	164K	$0.26	$1.03	-	tools open weights

Frequently asked

What is the cheapest DeepSeek model?: DeepSeek V4 Flash 0731 at $0.04 per 1M input tokens and $0.13 per 1M output tokens (vendor list price).
Which DeepSeek model has the largest context window?: DeepSeek V4.1 Flash 1017 accepts 1.0M tokens of context.
How do I route to DeepSeek models with OpenSmartRoute?: Declare a target in targets.yaml with metadata.model set to the catalogue id (for example deepseek/deepseek-v4.1-flash-1017); the router scores it against every other target on cost, quality, latency and your policies for each request.

Route DeepSeek with everything else

OpenSmartRoute picks the cheapest model that meets your quality bar per request, so a DeepSeek flagship handles hard prompts while small models take the rest. Price a workload or try a routing decision live.

Cost estimator Playground Full catalogue

One of many

DeepSeek answers when it is the best answer for the request - and only then.

The prices on this page are the vendor's own list prices. Behind the router they become one column in a scorecard: for every request the candidates from DeepSeek are weighed against every other vendor on cost, quality prior, latency and your policy, and the trace records why the winner won. Bring your own DeepSeek key or buy by the token here; the decision is the same.

Photo: RDNE Stock project

For the business

What it does for the vendor strategy.

One URL, every vendor
No vendor lock-in
Point your OpenAI-compatible client at one address; add, swap or retire providers in the catalogue without touching application code.
Every vendor side by side
89% less
Lower cost per request
On the 150-prompt benchmark the router spent 89% less than sending every prompt to the reference model, and the judged quality went up, not down.
Read the benchmark
Self-hosting is free
Open source, Apache-2.0
The router is a library, a sidecar or a control plane you can run yourself, so the exit is always open.
What is open

Will this lock us into another vendor?: No. The router is Apache-2.0 open source, your provider keys stay yours, and the API is OpenAI-compatible, so leaving is a change of base URL.
How much can we save on our LLM bill?: On the public benchmark the router saved 89% against sending everything to the reference model. Import last month's provider bill on the bill page and the estimate is computed on your own traffic before you change a line of code.
How do we compare AI gateways and routers?: The compare pages score each product against the same documented capabilities and say when the review was done; the benchmark page shows measured cost and quality, including the cases the router lost.

Model

Released

Context

Input / 1M

Output / 1M

Intelligence

Capabilities

DeepSeek V4.1 Flash 1017deepseek/deepseek-v4.1-flash-1017

Oct 17, 2026

1.0M

$0.15

$0.60

reasoning tools open weights

DeepSeek Pro Latest~deepseek/deepseek-pro-latest

Sep 14, 2026

1.0M

$0.13

$8.00

reasoning tools

DeepSeek Flash Latest~deepseek/deepseek-flash-latest

Sep 14, 2026

1.0M

$0.05

$0.38

reasoning tools

DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flash

Sep 10, 2026

1.0M

$0.02

$0.38

reasoning tools open weights

DeepSeek V4 Flash Vision Expdeepseek/deepseek-v4-flash-vision-exp

Aug 21, 2026

1.0M

$0.22

$0.65

reasoning tools open weights

DeepSeek V4 Pro 0813deepseek/deepseek-v4-pro-0813

Aug 12, 2026

1.0M

$0.66

$1.98

reasoning tools open weights

DeepSeek V4 Flash Latest~deepseek/deepseek-v4-flash-latest

Aug 1, 2026

1.0M

$0.04

$0.17

reasoning tools

DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-0731

Jul 31, 2026

1.0M

$0.04

$0.13

reasoning tools open weights

DeepSeek V4 Pro 0423deepseek/deepseek-v4-pro

Apr 24, 2026

1.0M

$0.42

$0.84

reasoning tools open weights

DeepSeek V4 Flash 0423deepseek/deepseek-v4-flash

Apr 24, 2026

1.0M

$0.09

$0.18

reasoning tools open weights

DeepSeek V3.2deepseek/deepseek-v3.2

Dec 1, 2025

164K

$0.28

$0.42

reasoning tools open weights

DeepSeek V3.2 Expdeepseek/deepseek-v3.2-exp

Sep 29, 2025

164K

$0.27

$0.41

reasoning tools open weights

DeepSeek V3.1 Terminusdeepseek/deepseek-v3.1-terminus

Sep 22, 2025

164K

$0.27

$1.00

reasoning tools open weights

DeepSeek V3.1deepseek/deepseek-chat-v3.1

Aug 21, 2025

164K

$0.25

$0.95

reasoning tools open weights

R1 0528deepseek/deepseek-r1-0528

May 28, 2025

164K

$0.50

$2.15

reasoning tools open weights

DeepSeek V3 0324deepseek/deepseek-chat-v3-0324

Mar 24, 2025

164K

$0.29

$1.14

tools open weights

DeepSeek V3deepseek/deepseek-chat

Dec 26, 2024

164K

$0.26

$1.03

tools open weights

Frequently asked

What is the cheapest DeepSeek model?

DeepSeek V4 Flash 0731 at $0.04 per 1M input tokens and $0.13 per 1M output tokens (vendor list price).

Which DeepSeek model has the largest context window?

DeepSeek V4.1 Flash 1017 accepts 1.0M tokens of context.

How do I route to DeepSeek models with OpenSmartRoute?

Declare a target in targets.yaml with metadata.model set to the catalogue id (for example deepseek/deepseek-v4.1-flash-1017); the router scores it against every other target on cost, quality, latency and your policies for each request.

DeepSeek answers when it is the best answer for the request - and only then.

DeepSeek models

Every DeepSeek model

Frequently asked

Route DeepSeek with everything else

DeepSeek answers when it is the best answer for the request - and only then.

What it does for the vendor strategy.

No vendor lock-in

Lower cost per request

Open source, Apache-2.0

DeepSeek models

Every DeepSeek model

Frequently asked

Route DeepSeek with everything else

DeepSeek answers when it is the best answer for the request - and only then.

What it does for the vendor strategy.

No vendor lock-in

Lower cost per request

Open source, Apache-2.0