Deepseek

DeepSeek V3.2 API Pricing 2026

Compare pricing, benchmarks, and providers for DeepSeek V3.2. 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 V3.2 was released on December 1, 2025. Pricing starts at $0.209 per million input tokens and $0.310 per million output tokens. The model supports a context window of up to 164K tokens. API access is available through Deepseek.

Context Window
164K
tokens
Pricing
Input$0.209
Output$0.310
Cached$0.022
per 1M tokens
Speed
Output-
TTFT-
median latency
Capabilities
ReasoningToolsCaching

DeepSeek V3.2 is priced at $0.209 per million input tokens and $0.310 per million output tokens. It has a context window of 163,840 tokens. It is available from 9 providers, with GMICloud the cheapest at $0.209 per million input tokens (input prices range from $0.209 to $1.00). Over the past ~90 days its cheapest input price has risen 24%, from $0.209 to $0.259 per million tokens.

Pricing Comparison

Compare DeepSeek V3.2 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
$0.209
$0.310
—
—
—
163,840
Try
$0.200
$1.100
—
—
—
1,000,192
Try
$0.200
$0.880
—
—
—
262,144
Try
$0.200
$0.200
—
34.4
9.3
32,768
Try
$0.200
$0.200
—
—
—
8,192
Try
$0.200
$0.200
—
—
—
33,000
Try
$0.200
$0.200
—
—
—
32,768
Try
$0.200
$0.200
—
—
—
2,048
Try
$0.200
$0.200
—
—
—
32,768
Try
$0.200
$0.200
—
—
—
2,048
Try
$0.207
$0.828
—
—
—
256,000
Try

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

Compare Providers

DeepSeek V3.2 is available from multiple providers with different pricing and availability.

9
Providers
$0.209
Cheapest Input/M
$0.310
Cheapest Output/M
GMICloud
Best Price

Provider Pricing

9 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
GMICloud
GMICloud
Best Price
$0.209
$0.310
$0.022
-
100.0%
$0.259
$0.800
$0.140
-
100.0%
$0.260
$0.380
-
-
-
A
AtlasCloud
$0.260
$0.380
$0.130
-
0.0%
$0.260
$0.380
$0.130
-
-
Baidu
Baidu
$0.280
$0.420
$0.028
-
100.0%
D
DigitalOcean
$0.300
$0.960
$0.090
-
100.0%
$0.620
$1.850
-
-
-
P
Phala
$1.000
$1.000
$0.500
-
100.0%
Provider pricing data sourced from OpenRouter and Helicone

Community Rankings

How does DeepSeek V3.2 perform? Vote based on your experience.

Cost vs. Quality

Compare DeepSeek V3.2's benchmark performance against all models.

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

Try DeepSeek V3.2

Use our Calculator

Estimate your costs based on expected token usage.

Open Cost Calculator

Try in Playground

Test DeepSeek V3.2 directly in your browser.

Open Playground

Frequently Asked Questions

DeepSeek V3.2 costs $0.000209 per 1,000 input tokens and $0.000310 per 1,000 output tokens.
DeepSeek V3.2 is available from 9 providers. GMICloud offers the best price.
GMICloud offers DeepSeek V3.2 at $0.209 per million input tokens, the lowest of 9 providers (input prices range from $0.209 to $1.00 per million tokens).
Yes. Over the past ~90 days, the cheapest input price for DeepSeek V3.2 has increased 24%, from $0.209 to $0.259 per million tokens.
We compare DeepSeek V3.2 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 →