DeepSeek: deepseek-v3.2:free

deepseek-v3.2:free
128K context163.8K outToolsCacheStructuredPrefill
Released Dec 1, 2025Knowledge cutoff 2024Updated Dec 1, 2025

DeepSeek-V3.2 is the definitive "Reasoning-First" multimodal foundation model, utilizing the third-generation Multi-head Latent Attention (MLA) and DeepSeek-MoE architecture. This version introduces the "Dynamic Token Pruning" technology, which reduces inference latency by 40% compared to V3.0 while maintaining top-tier coding and mathematical reasoning capabilities. V3.2 is natively multimodal, capable of processing interleaved text, high-resolution images, and long-form video inputs without separate vision encoders. In 2026, it is widely recognized as the most cost-effective "GPT-5 Class" model, offering open-source weights for researchers and a highly scalable API for global developers.

Mode chatTokenizer DeepSeek

All providers for this model are busy right now

Every upstream provider has hit its rate limit. The model comes back automatically once limits lift, usually within hours. Try again in a little while or switch to another model.

Request this model on Discord

Pricing

Input price
$0.00/ 1M tokens
Output price
$0.00/ 1M tokens
Context window 65.5K tokensCompatible endpoints openaiVendor DeepSeek

Quick stats

Quantizationfp8

Performance

Loading performance data...

Supported parameters

All providers = every upstream serving this model supports it. Some providers = depends on which upstream handles the request. Default = the value sent when you leave the parameter unset.

ParameterProvidersDefault
frequency_penaltySome providersNot sent by default
include_reasoningAll providers-
logit_biasSome providers-
logprobsSome providers-
max_tokensAll providers-
min_pSome providers-
presence_penaltySome providersNot sent by default
reasoningAll providers-
repetition_penaltySome providersNot sent by default
response_formatSome providers-
seedSome providers-
stopSome providers-
structured_outputsSome providers-
temperatureAll providers1
tool_choiceSome providers-
toolsSome providers-
top_kSome providersNot sent by default
top_logprobsSome providers-
top_pAll providers0.95

Frequently asked questions

How much does deepseek-v3.2:free cost per 1M tokens?

Input is priced at $0.00 per 1M tokens, output at $0.00 per 1M tokens. Billing is per token, no rounding to batch sizes.

How do I access deepseek-v3.2:free via API?

Send requests to the UnoRouter /v1/chat/completions endpoint with model=deepseek-v3.2:free. Any OpenAI-compatible client library works. Authentication uses a standard Bearer token.

What is the context window of deepseek-v3.2:free?

deepseek-v3.2:free supports a context window of 65.5K tokens, shared between your prompt and the model's response.

Similar models

Try deepseek-v3.2:free now

Create an API key and start making requests in under a minute.

View all models