DeepSeek V3.2
DeepSeek V3.2
Version: 1
Fireworks•Last updated April 2026
DeepSeek V3.2 is a 675.2B-parameter Mixture-of-Experts model that combines high computational efficiency with superior reasoning and agent performance, supporting a 163.8K token context window.
Coding
Agents

Fireworks on Foundry

Models available for use with Fireworks on Foundry deliver optimized, best-in-class performance on the Fireworks Inference Cloud. Fireworks on Foundry is a Preview subject to Azure Preview terms and the following supplemental terms: When you use Fireworks on Foundry, data is shared between Microsoft and Fireworks AI, and different compliance and data handling rules will apply. See documentation for details. Customers are responsible for evaluating whether data sharing between Microsoft and Fireworks is appropriate for their organization’s compliance requirements.

Key capabilities

About this model

DeepSeek-V3.2 is a large language model from DeepSeek AI that harmonizes high computational efficiency with superior reasoning and agent performance. It uses a Mixture-of-Experts (MoE) architecture with 675.2 billion total parameters, and supports a context length of 163.8k tokens. DeepSeek-V3.2 is calibrated and supports function calling for agentic workflows.

Key model capabilities

  • High computational efficiency via Mixture-of-Experts (MoE) architecture
  • Superior reasoning and agent performance
  • Function calling support for tool use and agentic workflows
  • 163.8k token context window

Use cases

See Responsible AI for additional considerations for responsible use.

Key use cases

  • Conversational AI
  • Code assistance
  • Agentic systems
  • Enterprise RAG (retrieval-augmented generation)

Out of scope use cases

The provider has not supplied this information.

Pricing

Pricing is based on a number of factors, including deployment type and tokens used. See pricing details here.

Technical specs

The provider has not supplied this information.

Training cut-off date

The provider has not supplied this information.

Training time

The provider has not supplied this information.

Input formats

Text

Output formats

Text

Supported languages

English, Chinese

Sample JSON response

The provider has not supplied this information.

Model architecture

DeepSeek V3.2 is a Mixture-of-Experts (MoE) language model.
PropertyValue
Total Parameters675.2B
ArchitectureMixture-of-Experts (MoE)

Long context

Context Length: 163.8k tokens

Optimizing model performance

The provider has not supplied this information.

Additional assets

The provider has not supplied this information.

Training disclosure

Training, testing and validation

The provider has not supplied this information.

Distribution

Distribution channels

The provider has not supplied this information.

More information

Model Specifications
Context Length163840
LicenseOther
Last UpdatedApril 2026
Input TypeText
Output TypeText
ProviderFireworks
Languages2 Languages