DeepSeek

DeepSeek V3.2

Chat
deepseek/deepseek-v3.2
CompareGet Started

DeepSeek V3.2 is DeepSeek's latest general-purpose chat model, released on 2025-12-01, building on the series' instruction-following and coding abilities. Pre-trained on 15 trillion tokens, it delivers an excellent cost-performance ratio for everyday development and production workloads. The model supports tool use (function calling) and prompt caching, which cuts the cost of repeated context. Context window: 128K tokens, output: 32K. Pricing is $0.29/M input tokens and $0.43/M output tokens, with cached input reads at $0.06/M. Available via OpenAI and Anthropic protocols through Ofox.

Context Window
128K
Max Output Tokens
32K
Released
2025-12-01
Capabilities
Function CallingPrompt Caching
Available Providers
VolcengineVolcengineAzureAzure
Supported Protocols
OpenAIopenaiAnthropicanthropic

Providers

AzureAzure
Input Tokens
$0.58/M
Output Tokens
$1.68/M
Cache Read
$0.06/M
Web Search
$0.035/R
Protocols
OpenAIopenai/v1/chat/completions/v1/responses
VolcengineVolcengine
Input Tokens
$0.29/M
Output Tokens
$0.43/M
Cache Read
$0.06/M
Protocols
Anthropicanthropic

Code Examples

from openai import OpenAI
client = OpenAI(
base_url="https://api.ofox.run/v1",
api_key="YOUR_OFOX_API_KEY",
)
response = client.chat.completions.create(
model="deepseek/deepseek-v3.2",
messages=[
{"role": "user", "content": "Hello!"}
],
)
print(response.choices[0].message.content)

Benchmarks

LMArenaEvaluated as deepseek-v3.2

DeepSeek V3.2 scores 1425 in the Overall category of the LMArena text leaderboard (style control), ranking #87 of 374 models based on 47,248 human preference votes (updated 2026-07-12).

Benchmark scores for deepseek-v3.2 on LMArena
CategoryArena Score95% CIRankVotes
Overall14221429#87 of 37447,248
Hard Prompts14431452#85 of 37426,180
Coding14631476#89 of 36910,613
Math14181440#74 of 3623,004
Creative Writing13931409#80 of 3726,678
Instruction Following14151427#77 of 37412,919
Chinese14501476#90 of 3442,441

Source: LMArena · CC BY 4.0 · Updated 2026-07-12 · Methodology · Ranks compare models within each category of the LMArena text leaderboard (style control). Scores come from third-party human preference evaluations, not from OFOX.

Frequently Asked Questions

DeepSeek V3.2 on Ofox.ai costs $0.29/M per million input tokens and $0.43/M per million output tokens. Pay-as-you-go, no monthly fees.