Models / DeepSeek
Code
LLM
Reasoning
Chat

DeepSeek-V3.2-Exp

Experimental sparse attention model for efficient long-context processing

This model is not available on Together’s Serverless API.

Related models
new
Chat
MiniMax M3

  • Cached/1M

    $0.06

  • Input/1M

    $0.30

  • Output/1M

    $1.20
Function Calling
JSON Mode
Reasoning
Vision
Chat
new
Chat
GLM-5.2

  • Cached/1M

    $0.26

  • Input/1M

    $1.40

  • Output/1M

    $4.40
Function Calling
JSON Mode
Reasoning
Chat
Code
new
Chat
Kimi K3

  • Cached/1M

    $0.30

  • Input/1M

    $3.00

  • Output/1M

    $15.00
JSON Mode
Function Calling
Chat
Reasoning
Vision
Model specifications
Model data
  • Model provider
    DeepSeek
  • Type
    Code
    LLM
    Reasoning
    Chat
  • Main use cases
    Chat
  • Parameters
    685B
  • Context length
    128K
  • Category
    Chat

Launching soon

Want to be notified when the model is available on Together AI?

You're on the list

We'll email you when the endpoint goes live. Until then, 200+ models are ready to call.

Browse Models
Continue