Deepseek

DeepSeek V4 Pro API Pricing 2026

Compare pricing, benchmarks, and providers for DeepSeek V4 Pro. Find the best value for your use case.

8 Ways to Use Fewer Tokens
Last updated: November 21, 2026 at 08:43 AM

Overview

DeepSeek V4 Pro was released on April 24, 2026. Pricing starts at $0.111 per million input tokens and $1.32 per million output tokens. The model supports a context window of up to 1.0M tokens. API access is available through Deepseek.

Context Window
1.0M
tokens
Pricing
Input$0.111
Output$1.32
Cached$0.022
per 1M tokens
Speed
Output76 tok/s
TTFT1.07s
median latency
Capabilities
ToolsCaching

DeepSeek V4 Pro is priced at $0.111 per million input tokens and $1.32 per million output tokens. It has a context window of 1,048,576 tokens. It is available from 21 providers, with Wafer the cheapest at $0.111 per million input tokens (input prices range from $0.111 to $1.98). It runs at roughly 76 tokens per second with a 1.07s time to first token. On benchmarks, DeepSeek V4 Pro scores Intelligence 23.1 (31st percentile), GPQA 92.8 (88th percentile). Over the past ~90 days its cheapest input price has fallen 72%, from $0.397 to $0.111 per million tokens.

Pricing Comparison

Compare DeepSeek V4 Pro with 10 similar models by price.

Current Pricing (per 1M tokens)

11 models

Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
Provider
Model
Input $/M
Output $/M
Coding
MMLU
GPQA
Context
Actions
$0.111
$1.322
—
—
92.8
1,048,576
Try
$0.100
$0.400
—
—
—
262,144
Try
$0.100
$0.100
—
—
—
8,192
Try
$0.100
$0.100
—
—
—
32,768
Try
$0.100
$0.100
—
—
—
32,768
Try
$0.100
$0.200
—
—
—
1,048,576
Try
$0.100
$0.200
—
—
—
1,048,576
Try
$0.100
$0.224
—
—
—
1,048,576
Try
$0.100
$0.500
—
—
—
-
Try
$0.100
$0.500
—
—
—
-
Try
$0.100
$0.500
—
—
—
1,000,000
Try

* Some models use tiered pricing based on prompt length. Displayed prices are for prompts ≤ 200k tokens.

Compare Providers

DeepSeek V4 Pro is available from multiple providers with different pricing and availability.

21
Providers
$0.111
Cheapest Input/M
$1.322
Cheapest Output/M
Wafer
Best Price

Provider Pricing

21 models

Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
Provider
Input $/M
Output $/M
Cache Read $/M
Cache Write $/M
Uptime
W
Wafer
Best Price
$0.111
$4.440
$0.097
-
-
DeepSeek
DeepSeek
$0.660
$1.980
$0.022
-
-
Baidu
Baidu
$0.661
$1.322
$0.055
-
100.0%
S
StreamLake
$0.662
$1.325
$0.055
-
100.0%
$0.900
$1.700
$0.080
-
100.0%
R
Relace
$0.900
$1.500
$0.200
-
100.0%
$0.900
$1.500
$0.200
-
-
$0.957
$1.914
$0.080
-
100.0%
D
DigitalOcean
$1.044
$2.088
$0.209
-
100.0%
$1.280
$2.560
$0.108
-
100.0%
$1.300
$2.600
-
-
-
C
CoreWeave
$1.310
$3.960
$0.044
-
-
$1.320
$3.960
-
-
-
$1.320
$3.960
$0.040
-
-
$1.320
$3.960
$0.132
-
-
P
Phala
$1.450
$4.360
$0.150
-
-
A
Alibaba
$1.560
$3.120
$0.130
-
-
V
Venice
$1.650
$3.301
$0.330
-
-
A
AtlasCloud
$1.680
$3.380
$0.130
-
-
$1.910
$3.830
$0.160
-
100.0%
$1.980
$5.940
$0.066
-
-
Provider pricing data sourced from OpenRouter and Helicone

Community Rankings

How does DeepSeek V4 Pro perform? Vote based on your experience.

Cost vs. Quality

Compare DeepSeek V4 Pro's benchmark performance against all models.

X-axis:
Y-axis:
Loading chart...
Other models

Detailed Benchmark Scores

Intelligence
23.1 (31st pct)
Coding
-
Math
-
MMLU Pro
-
GPQA
92.8 (88th pct)
LiveCodeBench
-
AIME
-
Aider
-
Benchmark data from Artificial Analysis and HuggingFace Open LLM Leaderboard

Try DeepSeek V4 Pro

Use our Calculator

Estimate your costs based on expected token usage.

Open Cost Calculator

Try in Playground

Test DeepSeek V4 Pro directly in your browser.

Open Playground

Frequently Asked Questions

DeepSeek V4 Pro costs $0.000111 per 1,000 input tokens and $0.001322 per 1,000 output tokens.
DeepSeek V4 Pro is available from 21 providers. Wafer offers the best price.
Wafer offers DeepSeek V4 Pro at $0.111 per million input tokens, the lowest of 21 providers (input prices range from $0.111 to $1.98 per million tokens).
DeepSeek V4 Pro scores Intelligence 23.1 (31st percentile), GPQA 92.8 (88th percentile). Only benchmarks with published data for this model are shown.
Yes. Over the past ~90 days, the cheapest input price for DeepSeek V4 Pro has dropped 72%, from $0.397 to $0.111 per million tokens.
We compare DeepSeek V4 Pro with 10 similarly-priced models. See the benchmark scatter plot above to compare quality vs cost.

All Deepseek Models

See pricing for all Deepseek models.

View all Deepseek models →