What is the cheapest DeepSeek model?

DeepSeek V4 Flash 0423 is the lowest blended-price option among tracked active non-embedding models, or among all models if only embeddings are listed: $0.03 input and $0.06 output per million tokens ($0.04 blended). Blended pricing uses 75% input and 25% output for generation models; your cheapest option may differ with your workload.

Which DeepSeek model has the highest AA Intelligence score?

DeepSeek V4.1 Flash has the highest listed Artificial Analysis Intelligence Index score among tracked active DeepSeek models: 39.5. This is one evaluation, not a guarantee of the best result for every task. Models without measured results are not ranked as zero.

How do I calculate monthly DeepSeek API costs?

Multiply input tokens in millions by the input rate and add output tokens in millions multiplied by the output rate. For example, 20 million input and 5 million output tokens on DeepSeek V4 Flash 0423 cost an estimated $0.88 at the listed rates. This excludes tool charges, cache-specific charges, taxes and any endpoint-specific adjustments.

Which DeepSeek model has the largest context window?

DeepSeek V4.1 Flash has a listed context window of 1M tokens, the largest among tracked active DeepSeek models. Context capacity and maximum response length are separate limits; verify both on the model page and in the endpoint documentation.

What is the latest DeepSeek model in the catalog?

DeepSeek V4.1 Flash has the most recent listed release date among tracked active DeepSeek models: 2026-09-10. Models without a usable release date are excluded from this comparison. Catalog release dates do not guarantee immediate API availability.

Do DeepSeek models support image inputs?

2 tracked active models list image inputs, including DeepSeek V4.1 Flash, DeepSeek V4 Flash Vision Exp. Accepting images does not mean a model generates images; check each model's separate input and output formats and endpoint limits.

Can prompt caching lower DeepSeek API costs?

11 tracked active models have a listed cached-input rate, including DeepSeek V3 0324, DeepSeek V3.1, R1 0528. Savings depend on eligible repeated input and the endpoint's cache rules, duration and any write charges.

Do DeepSeek models support tool calling?

14 tracked active models list tool-calling capabilities, including DeepSeek V3 0324, DeepSeek V3.1, R1 0528. Verify the exact tool schema and availability with your API endpoint before integrating.

How should I compare DeepSeek benchmark scores and prices?

Compare scores within the same evaluation: Artificial Analysis Intelligence Index, DesignArena Elo, general Arena Elo and MMLU-Pro use different tasks and scales. Missing results are not zeroes. Pair a relevant measured benchmark with input/output pricing and tests of your own workload; the cheapest or highest-scoring model is not automatically the best fit.

Are retired DeepSeek models included in the price list?

The price list shows active models by default. Turn on Show retired models to include retired catalog entries, where available. A retained model page preserves reference information, not a promise that its API is still available.

Is DeepSeek an AI lab or an inference host?

DeepSeek is categorized as an AI lab in this catalog. Individual model pages list available API hosts separately; model creator and API host are different roles.

AI lab

DeepSeek API pricing & models

deepseek.com

Aggressively priced open reasoning models. We track 15 DeepSeek models, priced from $0.02 per 1M input tokens with context windows up to 1M tokens.

Models tracked

Text & Reasoning · Vision · Code & SLMs

$0.04

Cheapest model

DeepSeek V4 Flash 0423

39.5

Top quality score

DeepSeek V4.1 Flash

Largest context

6-mo price trend 32%

Price list

All DeepSeek models and prices

Current DeepSeek API prices per 1M tokens, context windows and benchmark scores. Click a column to sort, or a model for full pricing details.

Show retired models


DeepSeek V4.1 Flash DeepSeek	$0.05	$1.2	1M	39.5	1325	—	—	357%
DeepSeek V4 Pro 0423 DeepSeek	$0.29232	$0.58464	1M	36	1244	—	—	-19%
DeepSeek V4 Flash Vision Exp DeepSeek	$0.2156	$0.6468	1M	34.8	—	—	—	96%
DeepSeek V4 Flash 0423 DeepSeek	$0.03	$0.056	1M	34.3	1209	—	—	3%
DeepSeek V3.2 DeepSeek	$0.259	$0.42	164K	16	—	—	—	48%
DeepSeek V3.2 Exp DeepSeek	$0.27	$0.41	164K	16	—	—	—	0%
DeepSeek V3.1 Terminus DeepSeek	$0.27	$1	164K	13.9	—	—	—	0%
DeepSeek V3.1 DeepSeek	$0.25	$0.95	164K	13.7	—	—	—	0%
DeepSeek R1 DeepSeek	$0.7	$2.5	64K	13.1	—	1239	80	3%
DeepSeek V3 0324 DeepSeek	$0.29	$1.14	164K	9.7	—	—	—	167%
DeepSeek V3 DeepSeek	$0.2574	$1.0287	164K	8.5	—	1211	75.4	-20%
R1 Distill Llama 70B DeepSeek	$0.8	$0.8	8K	7.9	—	—	—	0%
DeepSeek V4 Flash 0731 DeepSeek	$0.018	$0.32	1M	—	1234	—	—	323%
DeepSeek V4 Pro 0813 DeepSeek	$0.66	$1.98	1M	—	—	—	—	282%
R1 0528 DeepSeek	$0.5	$2.15	164K	—	—	—	—	0%

DeepSeek V4.1 Flash DeepSeek

Input /1M: $0.05
Output /1M: $1.2
Context: 1M
AA Intelligence: 39.5
DesignArena Elo: 1325
Arena Elo: —
MMLU-Pro: —
30d trend: 357%

DeepSeek V4 Pro 0423 DeepSeek

Input /1M: $0.29232
Output /1M: $0.58464
Context: 1M
AA Intelligence: 36
DesignArena Elo: 1244
Arena Elo: —
MMLU-Pro: —
30d trend: -19%

DeepSeek V4 Flash Vision Exp DeepSeek

Input /1M: $0.2156
Output /1M: $0.6468
Context: 1M
AA Intelligence: 34.8
DesignArena Elo: —
Arena Elo: —
MMLU-Pro: —
30d trend: 96%

DeepSeek V4 Flash 0423 DeepSeek

Input /1M: $0.03
Output /1M: $0.056
Context: 1M
AA Intelligence: 34.3
DesignArena Elo: 1209
Arena Elo: —
MMLU-Pro: —
30d trend: 3%

DeepSeek V3.2 DeepSeek

Input /1M: $0.259
Output /1M: $0.42
Context: 164K
AA Intelligence: 16
DesignArena Elo: —
Arena Elo: —
MMLU-Pro: —
30d trend: 48%

DeepSeek V3.2 Exp DeepSeek

Input /1M: $0.27
Output /1M: $0.41
Context: 164K
AA Intelligence: 16
DesignArena Elo: —
Arena Elo: —
MMLU-Pro: —
30d trend: 0%

DeepSeek V3.1 Terminus DeepSeek

Input /1M: $0.27
Output /1M: $1
Context: 164K
AA Intelligence: 13.9
DesignArena Elo: —
Arena Elo: —
MMLU-Pro: —
30d trend: 0%

DeepSeek V3.1 DeepSeek

Input /1M: $0.25
Output /1M: $0.95
Context: 164K
AA Intelligence: 13.7
DesignArena Elo: —
Arena Elo: —
MMLU-Pro: —
30d trend: 0%

DeepSeek R1 DeepSeek

Input /1M: $0.7
Output /1M: $2.5
Context: 64K
AA Intelligence: 13.1
DesignArena Elo: —
Arena Elo: 1239
MMLU-Pro: 80
30d trend: 3%

DeepSeek V3 0324 DeepSeek

Input /1M: $0.29
Output /1M: $1.14
Context: 164K
AA Intelligence: 9.7
DesignArena Elo: —
Arena Elo: —
MMLU-Pro: —
30d trend: 167%

DeepSeek V3 DeepSeek

Input /1M: $0.2574
Output /1M: $1.0287
Context: 164K
AA Intelligence: 8.5
DesignArena Elo: —
Arena Elo: 1211
MMLU-Pro: 75.4
30d trend: -20%

R1 Distill Llama 70B DeepSeek

Input /1M: $0.8
Output /1M: $0.8
Context: 8K
AA Intelligence: 7.9
DesignArena Elo: —
Arena Elo: —
MMLU-Pro: —
30d trend: 0%

DeepSeek V4 Flash 0731 DeepSeek

Input /1M: $0.018
Output /1M: $0.32
Context: 1M
AA Intelligence: —
DesignArena Elo: 1234
Arena Elo: —
MMLU-Pro: —
30d trend: 323%

DeepSeek V4 Pro 0813 DeepSeek

Input /1M: $0.66
Output /1M: $1.98
Context: 1M
AA Intelligence: —
DesignArena Elo: —
Arena Elo: —
MMLU-Pro: —
30d trend: 282%

R1 0528 DeepSeek

Input /1M: $0.5
Output /1M: $2.15
Context: 164K
AA Intelligence: —
DesignArena Elo: —
Arena Elo: —
MMLU-Pro: —
30d trend: 0%

DeepSeek input vs output prices

USD per 1M tokens for each model.

DeepSeek price history

Blended price per 1M tokens over the last 6 months.

By use case

DeepSeek models by category

Text & Reasoning

15 models · cheapest

DeepSeek V4 Flash 0423

$0.04 blended / 1M

Vision

2 models · cheapest

DeepSeek V4 Flash Vision Exp

$0.32 blended / 1M

Code & SLMs

2 models · cheapest

DeepSeek V3

$0.45 blended / 1M

Comparisons

DeepSeek vs other AI providers

Compare DeepSeek V4.1 Flash with models from other AI providers, including pricing and benchmark results.

DeepSeek vs Google

DeepSeek V4.1 Flash vs Nano Banana Pro (Gemini 3 Pro Image)

$0.34 vs $4.50 · Arena Elo — vs 1211

DeepSeek vs Anthropic

DeepSeek V4.1 Flash vs Claude Opus 5.5

$0.34 vs $8.00 · Arena Elo — vs —

DeepSeek vs OpenAI

DeepSeek V4.1 Flash vs GPT-5.2 Pro

$0.34 vs $58 · Arena Elo — vs 1255

DeepSeek vs xAI

DeepSeek V4.1 Flash vs Grok 4.7

$0.34 vs $3.00 · Arena Elo — vs —

DeepSeek vs Meta

DeepSeek V4.1 Flash vs Muse Spark 1.3

$0.34 vs $2.00 · Arena Elo — vs —

DeepSeek vs Mistral AI

DeepSeek V4.1 Flash vs Mistral Medium 3.5

$0.34 vs $3.00 · Arena Elo — vs —

FAQ

DeepSeek pricing FAQ

Tracked active DeepSeek models range from $0.02 to $0.80 per million input tokens. Output rates are listed separately for each model. Prices vary by model and API endpoint; these are token rates, not a subscription quote.