AI TOOLS RADAR
Explore
All models / DEEPSEEK
deepseek logo
deepseek

DeepSeek: DeepSeek V3.2

DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. $0.2088 per million input tokens, $0.3096 per million output tokens. 163,840 token context window. Higher uptime with 14 providers. Includes independent benchmarks from Artificial Analysis.

View source on OpenRouter Hugging Face
Overview

Model specifications

Context
163,840 tokens
Maximum output
65,536 tokens
Architecture
text->text
Tokenizer
DeepSeek
Knowledge cutoff
Not provided
Moderated
No
OPENROUTER

Complete pricing

Synchronized OpenRouter rates. Token prices are shown per one million tokens.

Input
$0.2088
/M tokens
Output
$0.3096
/M tokens
Cache read
$0.0216
/M tokens
API

Model configuration

Default parameters

temperature
1
top_p
0.95

Reasoning

Moderated
No
Default parameters
No
API

Quick start

Call this exact model ID through OpenRouter’s OpenAI-compatible API.

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"deepseek/deepseek-v3.2","messages":[{"role":"user","content":"Hello!"}]}'
Capabilities

Input → Output

Input
text
Output
text
Reasoning

No

API

Supported API parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Available providers

14 providers

Live providers on OpenRouter

Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.

OpenRouter

GMICloud

fp8
Context
164K
Maximum output
147K
Input
$0.209
Output
$0.310
Cache read
$0.022
Cache write
Not provided

StreamLake

fp8
Context
128K
Maximum output
64K
Input
$0.214
Output
$0.322
Cache read
$0.021
Cache write
Not provided

DigitalOcean

unknown
Context
164K
Maximum output
128K
Input
$0.250
Output
$0.800
Cache read
$0.075
Cache write
Not provided

SiliconFlow

fp8
Context
164K
Maximum output
147K
Input
$0.259
Output
$0.420
Cache read
$0.135
Cache write
Not provided

AtlasCloud

fp8
Context
164K
Maximum output
147K
Input
$0.260
Output
$0.380
Cache read
$0.130
Cache write
Not provided

DeepInfra

fp4
Context
164K
Maximum output
16K
Input
$0.260
Output
$0.380
Cache read
$0.130
Cache write
Not provided

Novita

fp8
Context
164K
Maximum output
66K
Input
$0.269
Output
$0.400
Cache read
$0.134
Cache write
Not provided

Baidu

fp8
Context
131K
Maximum output
66K
Input
$0.280
Output
$0.420
Cache read
$0.028
Cache write
Not provided

Venice

unknown
Context
160K
Maximum output
33K
Input
$0.330
Output
$0.480
Cache read
$0.160
Cache write
Not provided

Alibaba

fp8
Context
131K
Maximum output
66K
Input
$0.370
Output
$1.11
Cache read
$0.074
Cache write
$0.463

Friendli

unknown
Context
164K
Maximum output
147K
Input
$0.500
Output
$1.50
Cache read
$0.250
Cache write
Not provided

Google

unknown
Context
164K
Maximum output
66K
Input
$0.560
Output
$1.68
Cache read
Not provided
Cache write
Not provided

Phala

unknown
Context
164K
Maximum output
64K
Input
$1.00
Output
$1.00
Cache read
$0.500
Cache write
Not provided

SambaNova

unknown
Context
33K
Maximum output
7K
Input
$3.00
Output
$4.50
Cache read
Not provided
Cache write
Not provided
deepseek

models

All models
deepseek logodeepseek

DeepSeek: DeepSeek V4 Flash Vision Exp

DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of DeepSeek V4 Flash 0731 from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...

Context
1.0M
Input
text · image
Output
text
Input: $0.440Output: $1.32per 1M tokens
View model details →
deepseek logodeepseek

DeepSeek: DeepSeek V4 Pro 0813

DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.

Context
1.0M
Input
text
Output
text
Input: $1.32Output: $3.96per 1M tokens
View model details →
deepseek logodeepseek

DeepSeek: DeepSeek V4 Pro 0813 (batch)

DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.

Context
1.0M
Input
text
Output
text
Input: $1.32Output: $3.96per 1M tokens
View model details →
deepseek logodeepseek

DeepSeek: DeepSeek V4 Flash 0731

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....

Context
1.3M
Input
text
Output
text
Input: $0.065Output: $0.180per 1M tokens
View model details →